Showing 1–50 of 106 results for author: Dustdar, S

LipCache: A Local Inference Proxy with Certified Caching for Edge Image Classification Service

Authors: Zhengzhe Xiang, Yinlin Chen, Fuli Ying, Binbin Zhou, Hailiang Zhao, Schahram Dustdar

Abstract: As edge-side vision services continue to expand toward low-latency, high-throughput scenarios, reducing the inference cost of vision models without sacrificing reliability has become a central concern. Existing semantic caching methods largely rely on empirical similarity thresholds; while such thresholds improve hit rates, they tend to introduce silent misclassifications near decision boundaries.… ▽ More As edge-side vision services continue to expand toward low-latency, high-throughput scenarios, reducing the inference cost of vision models without sacrificing reliability has become a central concern. Existing semantic caching methods largely rely on empirical similarity thresholds; while such thresholds improve hit rates, they tend to introduce silent misclassifications near decision boundaries. To address this, we propose \texttt{LipCache}, a certified semantic caching framework for image classification. Without modifying the existing deployed main model, \texttt{MainNet}, the framework introduces a lightweight network, \texttt{GuardNet}, that maps inputs into a low-dimensional feature space subject to a Lipschitz constraint. It then computes a per-sample certified reuse radius from the local classification margin and the spectral norm of the classification head. At runtime, a cached result is reused only when the query feature falls inside the certified reuse ball; otherwise, the query falls back to \texttt{MainNet}. Thus, cache hits are transformed from empirical threshold tests into geometric certification decisions with explicit theoretical boundaries. Across standard image classification tasks like CIFAR, Tiny-ImageNet, and SVHN, \texttt{LipCache} achieves a measured speedup of up to $1.65\times$ with limited end-to-end accuracy degradation, while all accepted cache hits satisfy the \texttt{GuardNet}-side certified-consistency condition. Furthermore, an enhanced \texttt{GuardNet} training recipe substantially improves cache hit rates in the Tiny-ImageNet multi-class extension while maintaining a certified-consistency rate of $100\%$. These results demonstrate that per-sample certified reuse can reduce main-model fallback while preserving theoretical consistency, providing a feasible approach to reliable cache-assisted inference at the edge. △ Less

Submitted 13 August, 2026; originally announced August 2026.

LYRA: Label-Free Structural Synchronization and Resource Allocation for UAV Edge Networks

Authors: Feng He, Alireza Furutanpey, Paolo Bellavista, Yu Qiu, Jiangchuan Liu, Jiannong Cao, Schahram Dustdar

Abstract: While deploying hierarchical vision models to process mission-critical tasks, UAV edge systems must adaptively update the models to sustain inference reliability under low-level environmental corruption. However, existing work has overlooked the optimal timing for model updates, the impracticality of relying on real-time expert labels, and the significant bandwidth and energy constraints of UAVs.… ▽ More While deploying hierarchical vision models to process mission-critical tasks, UAV edge systems must adaptively update the models to sustain inference reliability under low-level environmental corruption. However, existing work has overlooked the optimal timing for model updates, the impracticality of relying on real-time expert labels, and the significant bandwidth and energy constraints of UAVs. This paper proposes a joint model update scheduling and resource allocation framework, aiming to maximize long-term semantic fidelity and resource efficiency of UAV edge intelligence systems. To address the challenge of label-free semantic evaluation, we formulate the Online Semantic Disagreement Rate (OSDR) as a proxy for timely update triggering, thereby enabling fine-grained Sensitivity-Aware Structural Synchronization (SASS). Furthermore, to overcome the curse of dimensionality in hybrid action spaces and effectively bound long-term energy budgets, we propose a Lyapunov-guided discrete reinforcement learning algorithm that performs action space dimensionality reduction and transforms constraints into virtual queue stability problems. The reported experimental results, based on real traffic traces, demonstrate that the proposed framework consistently outperforms representative baselines in semantic recovery efficiency and update triggering precision, by satisfying long-term energy budget and by reducing average risk backlog by up to 33.3\% in the dynamic environmental corruption scenario. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Clear-Weighted Bit Allocation for Satellite Downlinks

Authors: Alireza Furutanpey, Qiyang Zhang, Yujie Huang, Philipp Raith, Schahram Dustdar

Abstract: Earth-observation satellites capture more imagery than intermittent ground contacts can transmit. Onboard systems threshold a cloud detector, discard frames or tiles, and compress the survivors with a fixed codec. On expert-labeled imagery, these rules remove more than one-fifth of clear pixels, primarily through detector false positives. We train a neural codec with a clear-probability-weighted r… ▽ More Earth-observation satellites capture more imagery than intermittent ground contacts can transmit. Onboard systems threshold a cloud detector, discard frames or tiles, and compress the survivors with a fixed codec. On expert-labeled imagery, these rules remove more than one-fifth of clear pixels, primarily through detector false positives. We train a neural codec with a clear-probability-weighted reconstruction loss, reallocating coded bytes from clouds to clear ground without requiring or transmitting a cloud map onboard. Each capture is encoded into a resumable base layer and a dependent refinement layer, while clear content is estimated from features produced by the encoder. At each contact, we causally rank arrived layers using estimated clear content, unfinished bytes, deadline slack, and aggregate deadline pressure. The scheduler serves base and computational deadlines, bounds stored residual bytes, and resumes interrupted packets. We evaluate the onboard-to-downlink pipeline using real entropy-coded bytes, orbit-derived interruptible contact capacities, and measured service time and energy on resource-constrained embedded accelerators. Clear-weighted codecs require up to 47.8\% fewer bytes than learned-compression baselines at matched clear-region quality. The optimized encoder consumes less time and energy than one pass of the cloud detector used by the frame-discard rules. Relative to fixed two-stage service on the same streams, our scheduler more than doubles deadline-full clear-content delivery for the interrupted combined cohort, reaches 83.6\% of a certified clairvoyant upper bound, and exceeds replayed reference orders in deadline-usable delivery. △ Less

Submitted 2 August, 2026; originally announced August 2026.

Comments: 10 pages, 11 Figures, 6 Tables

A Taxonomy of Performance Metrics for the Distributed Computing Continuum

Authors: Praveen Kumar Donta, Boris Sedlak, Alfreds Lapkovskis, Alaa Saleh, Ying Li, Victor Casamayor Pujol, Ilir Murturi, Manuel Otero Barbasan, Schahram Dustdar

Abstract: Performance evaluation is essential for understanding, comparing, and improving computing systems, including Distributed Computing Continuum Systems (DCCS). In recent years, computational requirements have changed substantially with the growth of artificial intelligence and large-scale data-driven applications. These application tasks are increasingly distributed between resource-intensive data ce… ▽ More Performance evaluation is essential for understanding, comparing, and improving computing systems, including Distributed Computing Continuum Systems (DCCS). In recent years, computational requirements have changed substantially with the growth of artificial intelligence and large-scale data-driven applications. These application tasks are increasingly distributed between resource-intensive data centers and resource-constrained edge environments. In this context, novel computing continuum architectures and algorithms are emerging, creating a need for transparent and consistent performance evaluation. However, existing evaluation practices often focus on isolated dimensions, such as computation, networking, energy efficiency, or application-level quality, and therefore provide only a partial view of cross-layer DCCS behavior. This paper presents a structured taxonomy of performance metrics for DCCS. The taxonomy organizes metrics into computing-level, network-level, and application/user-level categories, while also highlighting emerging dimensions such as sustainability, observability, adaptability, data locality, migration awareness, and continuum fragmentation. Further, we provide mathematical formulations and discuss their relevance to heterogeneous and dynamic continuum environments. We also summarize metric acquisition requirements in terms of acquisition scope, acquisition phase, and measurement method. These requirements help clarify whether a metric can be collected from a single node, multiple nodes, or the full system, and whether it is more suitable for operational monitoring or experimental evaluation. △ Less

Submitted 30 July, 2026; originally announced July 2026.

LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters

Authors: Reza Farahani, Zoha Azimi, Mario Colosi, Schahram Dustdar

Abstract: Large language model (LLM) services increasingly operate on edge infrastructure, enabling low-latency and privacy-preserving AI services. However, efficiently serving LLM requests across heterogeneous and resource-constrained edge devices require orchestration mechanisms that jointly determine model configuration (family, size, and quantization level) and execution placement while satisfying user-… ▽ More Large language model (LLM) services increasingly operate on edge infrastructure, enabling low-latency and privacy-preserving AI services. However, efficiently serving LLM requests across heterogeneous and resource-constrained edge devices require orchestration mechanisms that jointly determine model configuration (family, size, and quantization level) and execution placement while satisfying user- and system-level quality of service (QoS) requirements. This paper introduces LMEdge, a QoS-aware orchestration service that dynamically makes these decisions across heterogeneous edge devices. We formulate the problem as a binary integer linear programming (BILP) optimization that minimizes response time under accuracy, network, and resource constraints. To enable scalable online scheduling, we employ five lightweight machine learning (ML) models to predict query-specific latency, accuracy, resource usage, and response size for each model-size-quantization-device combination, and design a lightweight heuristic that approximates the BILP solution. We collect a comprehensive benchmarking dataset of over 59000 rows to train models and support reproducibility. Evaluation on a Kubernetes-based edge testbed with 57 instances and diverse query categories shows that LMEdge reduces latency, preserves accuracy, improves resource utilization, and increases serving ratio compared to two baselines. △ Less

Submitted 19 July, 2026; originally announced July 2026.

Comments: 12 pages, 5 figures, 2 tables, EUROPAR conference paper

Principled Direction-Free Intrinsic Motivation through Model-Free Epistemic Free-Energy Estimators

Authors: Alireza Furutanpey, Schahram Dustdar

Abstract: Across environments with mixed sources of uncertainty, unsupervised reinforcement learning requires intrinsic motivation that does not precommit to a particular direction of surprise. Surprise minimization is scoped by design to ``unstable'' environments. Prediction-error curiosity rewards total expected surprise, including irreducible noise. Bandit or mixture switching between surprise-minimizing… ▽ More Across environments with mixed sources of uncertainty, unsupervised reinforcement learning requires intrinsic motivation that does not precommit to a particular direction of surprise. Surprise minimization is scoped by design to ``unstable'' environments. Prediction-error curiosity rewards total expected surprise, including irreducible noise. Bandit or mixture switching between surprise-minimizing and surprise-maximizing rewards reintroduces non-stationarity by construction. We propose a single intrinsic reward, stationary within each window, derived from the novelty contribution of a preference-free Expected Free Energy objective, expressed in reward-maximization form. Our claim is that parameter information gain, the expected surprise of the next state minus its irreducible part, is the appropriate intrinsic signal in both high-entropy and low-entropy components of the state space. Maximizing it seeks exactly the surprise the model can explain away. In regions of unresolved dynamics, this epistemic term drives exploration. As dynamics become resolved, the epistemic term vanishes, while an aleatoric penalty favors lower-variance transitions, all without fitting an explicit next-state predictor. A pseudocount supplies epistemic value, a probe-based penalty captures aleatoric variance, and a short-horizon gate protects informative successors. A window-based freeze of all reward-defining objects yields a stationary Bellman operator, explicit bounds on learning targets, and a conditional uniform-concentration result for the nonparametric estimators under mixing, smoothness, bandwidth, and capacity assumptions. In active-inference terms, the agent is preference-free where novelty is retained, standard likelihood ambiguity vanishes under full observability, a nonstandard transition-entropy penalty is added, and surprise minimization emerges in resolved regions of the state space. △ Less

Submitted 18 July, 2026; originally announced July 2026.

Comments: Accepted for a Spotlight Presentation at IWAI 2026

Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing

Authors: Amin Beheshti, Rong N. Chang, Boualem Benatallah, Fabio Casati, Schahram Dustdar, Geoffrey Fox, Quan Z. Sheng, Yan Wang, Jian Yang, Albert Zomaya

Abstract: The rapid emergence of LLM-powered autonomous and semi-autonomous agents is reshaping software systems from static, request-response components into goal-directed, adaptive, and tool-using computational actors. As these agents move from isolated cognitive prototypes into complex distributed workflows, they confront challenges that the Service-Oriented Computing community has studied for more than… ▽ More The rapid emergence of LLM-powered autonomous and semi-autonomous agents is reshaping software systems from static, request-response components into goal-directed, adaptive, and tool-using computational actors. As these agents move from isolated cognitive prototypes into complex distributed workflows, they confront challenges that the Service-Oriented Computing community has studied for more than two decades: composition, interoperability, quality of service, lifecycle management, governance, security, and trust. Yet much of today's agentic AI ecosystem is developing these foundations ad hoc, without the engineering rigour required for dependable enterprise and societal deployment. This paper introduces Agentic Service-Oriented Computing (ASOC) as a new research and practice area concerned with engineering agents as services, orchestrating services through autonomous and semi-autonomous agents, and governing ecosystems of agents and services under constraints of trust, cybersecurity, compliance, performance, and accountability. We articulate six foundational principles of ASOC (harness-ability, composability, lifecycle engineering, trustworthiness by design, goal-driven orchestration, and observability/accountability) and organise a five-dimensional research agenda spanning: (i) agentic services foundations and lifecycle engineering; (ii) composition, orchestration, and interoperability; (iii) governance, observability, and accountability; (iv) security, trust, and risk management; and (v) evaluation, certification, and Agentic QoS. We argue that the Services Computing community is especially well positioned to provide the conceptual and engineering spine for this emerging field, transforming agentic AI from fragmented demonstrations into dependable, service-based systems worthy of human and organisational trust. △ Less

Submitted 14 July, 2026; originally announced July 2026.

Comments: Accepted at the 2026 IEEE International Conference on Web Services (ICWS); Corresponding author: Prof. Amin Beheshti; DOI 10.1109/ICWS72778.2026.00163

Incentives and Evidence in Learned Service Orchestration

Authors: Syed Izhan Khilji, Alireza Furutanpey, Schahram Dustdar

Abstract: Reinforcement learning for service orchestration has been the subject of sustained research for over a decade, yet it is not used in production at scale. The usual explanation is that learned controllers degrade under delayed and noisy telemetry, workload shifts, and uncontrolled tenants. We test whether existing evidence supports that explanation. We evaluate three highly influential RL-based orc… ▽ More Reinforcement learning for service orchestration has been the subject of sustained research for over a decade, yet it is not used in production at scale. The usual explanation is that learned controllers degrade under delayed and noisy telemetry, workload shifts, and uncontrolled tenants. We test whether existing evidence supports that explanation. We evaluate three highly influential RL-based orchestration systems spanning resource allocation, DAG scheduling, and autoscaling, using pre-registered predictions about comparative degradation under production-relevant perturbations and paired inference with family-wise error correction. Across the tests, most predicted performance reversals do not occur. Diagnostic analyses show that these outcomes often reflect comparator collapse, artefact limitations, or evaluation choices rather than evidence that learned controllers tolerate the perturbations. One apparent advantage under observation lag is roughly fortyfold compared to a Kubernetes HPA-equivalent controller. Another widely cited result cannot be reconstructed from its released artefact, and the strongest reproducible margin is far smaller than the published results. Conclusions also reverse under changes in perturbation magnitude and evaluation mode. Based on these results and broader patterns in the literature, we identify an institutional problem. Publication and review incentives favour benchmark gains against convenient comparators, even when those gains provide little evidence of deployment performance. We argue that the problem is not solely technical. Rather, it is institutional, so learned orchestration needs production-grade comparators, registered perturbation models, separate operational metrics, and publication criteria that reward reproducible operational evidence. Without these changes, the literature can grow without establishing whether learning improves orchestration. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: To be presented at the IEEE 2026 International Congress on Intelligent and Service Oriented Systems Engineering (CISOSE 2026)

Fair Comparison of Scheduling Algorithms on Heterogeneous Edge Clusters: A Continuous Adaptive Benchmark

Authors: Zihang Wang, Boris Sedlak, Juan Luis Herrera, Schahram Dustdar

Abstract: Modern Artificial Intelligence (AI) workloads deployed across the heterogeneous tiers of an edge--cloud continuum must satisfy multi-dimensional Service Level Objectives (SLOs) over latency, throughput, and output quality. For each incoming task, the scheduler picks both a target node and a processing mode (e.g., full or reduced inference precision). We call this class of problems \emph{Continuous… ▽ More Modern Artificial Intelligence (AI) workloads deployed across the heterogeneous tiers of an edge--cloud continuum must satisfy multi-dimensional Service Level Objectives (SLOs) over latency, throughput, and output quality. For each incoming task, the scheduler picks both a target node and a processing mode (e.g., full or reduced inference precision). We call this class of problems \emph{Continuous Multi-Mode Scheduling} (CMMS). Comparing CMMS algorithms fairly is difficult because prior studies typically evaluate each controller in its own stack, under a single workload, and without reporting per-decision overhead. To close these gaps, we present an open source benchmark platform that features (i) a unified controller interface, (ii) a closed-loop workload driver covering multiple workload patterns, and (iii) dual-metric SLO scoring that reports raw SLO (overall compliance) and steady-state SLO (compliance during stable operation) separately. Running six controllers across five cluster configurations and two load regimes (424 episodes), we find that controller rankings are strongly configuration-dependent: a deep reinforcement-learning winner under light workloads loses to a rule-based heuristic by nearly 29 percentage points once load intensifies, at roughly 500$\times$ the per-decision operational overhead. We further show that separating raw from steady-state SLOs exposes switching costs that a single aggregate score would otherwise conflate. △ Less

Submitted 10 June, 2026; originally announced June 2026.

Credibility Trilemma in Polymatroidal Service Markets

Authors: Lauri Lovén, Sujit Gujar, Kalle Timperi, Hassan Mehmood, Praveen Kumar Donta, Sasu Tarkoma, Schahram Dustdar

Abstract: Mechanism-mediated service markets with polymatroidal feasibility admit efficient, dominant-strategy incentive-compatible (DSIC) allocation, but these guarantees implicitly assume truthful execution by the marketplace operator. Modelling the operator as a strategic player, we establish a credibility trilemma: for single-parameter agents on a non-modular polymatroid, no static sealed-bid mechanism… ▽ More Mechanism-mediated service markets with polymatroidal feasibility admit efficient, dominant-strategy incentive-compatible (DSIC) allocation, but these guarantees implicitly assume truthful execution by the marketplace operator. Modelling the operator as a strategic player, we establish a credibility trilemma: for single-parameter agents on a non-modular polymatroid, no static sealed-bid mechanism is simultaneously revenue-optimal, DSIC for agents, and credible for the operator. We introduce the Cost of Non-Credibility (CoNC) as a price-of-anarchy-style welfare-loss measure and obtain tight $Θ$-bounds across five topology classes (single-edge, series, parallel, tree, series-parallel), plus a matching upper bound $O(|\mathcal{S}|)$ on general DAGs realised by an $Ω(|\mathcal{S}|)$ witness on the SP-augmented sub-family, turning the trilemma into a structural quantity. Three structurally distinct resolutions follow: public broadcast or deferred-revelation commitment, administrative domain separation under settlement separation and four side conditions, and integrator competition orthogonal to mechanism execution under disjoint actors. An instance-level grounding over the edge-pricing market of Amin et al. confirms the trilemma's robustness on a refereed external setting. The result establishes marketplace neutrality as a first-order design constraint on polymatroidal service markets rather than an implementation detail: where the operator is a strategic player, credibility trades off against revenue optimality and agent incentive compatibility along structurally characterised lines. △ Less

Submitted 26 May, 2026; originally announced May 2026.

Comments: 75 pages, 3 figures. Prepared for submission to the ACM Transactions on Economics and Computation (TEAC)

ACM Class: J.4; F.2.2; C.2.4

Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety

Authors: Muhammad Bilal, Jon Crowcroft, Ruizhi Wang, Xiaolong Xu, Schahram Dustdar

Abstract: Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited self-healing. In both NetOps and AIOps, this shift is changing how tasks are managed. Agent-based operations work as workflows, from gathering evidence to taking ac… ▽ More Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited self-healing. In both NetOps and AIOps, this shift is changing how tasks are managed. Agent-based operations work as workflows, from gathering evidence to taking action, following permissions, policies, and checks, and providing rollback options when necessary. This is crucial because operational decisions can have instant impacts. To make the argument concrete, we organise the relevant literature around the hierarchy of autonomy, tool scope, evidence traces, and assurance contracts. These contracts define what an agent may observe, propose, and execute. They also define the checks that must pass before any action is allowed. A consistent pattern appears across work on telemetry query recommendation, diagnosis, root-cause analysis, configuration synthesis, change planning, and limited self-healing. Operational reliability does not come chiefly from the model itself. It depends on the machinery around the model. We also argue that evaluation should go beyond static question answering. Agentic NetOps and AIOps systems require workflow-centred evaluation, including trace quality, bounded tool use, safe proposal generation, replay in sandboxed environments, and canary trials with rollback-aware scoring. Without these measures, a system may appear robust yet remain too fragile. Finally, we examine security, privacy, and governance risks that become acute when agents sit close to operational control surfaces. Taken together, the survey concludes that progress in intelligent NetOps and AIOps will depend on treating autonomy as a constrained operational control problem, whose outputs must be reliable, auditable, and securely deployable. △ Less

Submitted 15 June, 2026; v1 submitted 12 May, 2026; originally announced May 2026.

Comments: 49 pages, 15 figures, 6 tables; survey article

ACM Class: C.2.3; C.2.1; I.2.11; D.2.4

Orchestrating Serverless Applications in the Edge Cloud Space Continuum: What Breaks and What is Next?

Authors: Hadi Tabatabaee Malazi, Reza Farahani, Nitinder Mohan, Schahram Dustdar

Abstract: Serverless computing has matured into an effective execution model for edge cloud environments, enabling function level decomposition, demand driven scaling, and workflow execution across stable, well provisioned infrastructure. This success motivates extending it to the edge cloud space continuum, where Low Earth Orbit (LEO) constellations are increasingly explored as distributed compute substrat… ▽ More Serverless computing has matured into an effective execution model for edge cloud environments, enabling function level decomposition, demand driven scaling, and workflow execution across stable, well provisioned infrastructure. This success motivates extending it to the edge cloud space continuum, where Low Earth Orbit (LEO) constellations are increasingly explored as distributed compute substrates. However, existing serverless orchestration is not directly applicable in this setting, where LEO systems impose time varying contact graphs, intermittent link availability, and strict feasibility constraints on energy, memory, communication, and operational cost. This article identifies ten broken assumptions in existing serverless orchestration and organizes them into three core challenges: spatiotemporal execution over dynamic graphs, constraint aware function placement and scaling, and correctness and progress under decentralized and delayed state. It then proposes an architecture that enables robust and efficient serverless execution across the continuum, grounded in these challenges and demonstrated through a representative flood response use case. △ Less

Submitted 5 May, 2026; originally announced May 2026.

Comments: 11 pages, 2 figures, 2 tables

ClusterLess: Deadline-Aware Serverless Workflow Orchestration on Federated Edge Clusters

Authors: Reza Farahani, Mario Colosi, Ilir Murturi, Stefan Nastic, Massimo Villari, Schahram Dustdar, Radu Prodan

Abstract: The recent convergence of edge computing, serverless execution, and Kubernetes (K8s) based container orchestration has enabled the processing of application workflows close to data sources. While effective within a single edge cluster, existing schemes do not generalize to federated multi edge environments, where multiple workflows execute concurrently under strict end to end (E2E) deadline constr… ▽ More The recent convergence of edge computing, serverless execution, and Kubernetes (K8s) based container orchestration has enabled the processing of application workflows close to data sources. While effective within a single edge cluster, existing schemes do not generalize to federated multi edge environments, where multiple workflows execute concurrently under strict end to end (E2E) deadline constraints. This paper introduces ClusterLess, a deadline aware serverless workflow orchestration method for federated multi edge K8s clusters. ClusterLess manages the E2E lifecycle of workflow execution, including dependency analysis, execution mode selection, and resource aware placement. To this end, it integrates structured intra cluster orchestration with a leader selected, super master driven intercluster coordination layer, determining where and how each workflow function should be executed across the federated edge clusters. We implement ClusterLess using OpenFaaS as the serverless execution substrate and Argo for workflow management, and deploy it on a realistic testbed of six edge clusters comprising 64 heterogeneous edge nodes. Experimental results with concurrent serverless workflows, spanning 18 workload configurations across different input sizes and deadline classes, show that ClusterLess reduces workflow completion time by up to 40 %, increases deadline satisfaction from below 50 % to over 90 %, and confines deadline violations to single digit seconds compared to four baseline methods. △ Less

Submitted 5 May, 2026; originally announced May 2026.

Comments: 11 pages, 12 figures, 3 algorithms, 3 tables, accepted in IEEE ICDCS 2026

Active Inference-Based Adaptive Routing for Heterogeneous Edge AI Services

Authors: Zihang Wang, Boris Sedlak, Schahram Dustdar

Abstract: Edge computing enables AI inference closer to data sources, reducing latency and bandwidth costs. However, orchestrating AI services across the cloud-edge continuum remains challenging due to dynamic workloads and infrastructure variability. We present AIF-Router, an Active Inference--based routing framework that autonomously learns to balance latency, throughput, and resource utilization across m… ▽ More Edge computing enables AI inference closer to data sources, reducing latency and bandwidth costs. However, orchestrating AI services across the cloud-edge continuum remains challenging due to dynamic workloads and infrastructure variability. We present AIF-Router, an Active Inference--based routing framework that autonomously learns to balance latency, throughput, and resource utilization across multi-tier AI services without offline training. AIF-Router performs Bayesian state inference and expected free energy minimization to guide routing decisions based on observability-driven real-time metrics. Despite device instability on edge nodes, AIF-Router exhibits stable online learning behavior and demonstrates the feasibility of applying Active Inference for adaptive AI service orchestration in unreliable edge environments. Our findings highlight both the promise and practical challenges of deploying self-adaptive decision-making frameworks for real-world edge AI systems. △ Less

Submitted 19 April, 2026; originally announced April 2026.

Pricing-Driven Resource Allocation in the Computing Continuum

Authors: Alejandro García-Fernández, Boris Sedlak, José Antonio Parejo, Pantelis Frangoudis, Antonio Ruiz-Cortés, Schahram Dustdar

Abstract: Deploying applications across the computing continuum requires selecting infrastructure nodes from geographically distributed and heterogeneous environments while satisfying constraints (e.g., performance, location). This decision problem is an important facet of resource allocation. As infrastructures grow in scale and heterogeneity, the resulting decision space becomes inherently combinatorial.… ▽ More Deploying applications across the computing continuum requires selecting infrastructure nodes from geographically distributed and heterogeneous environments while satisfying constraints (e.g., performance, location). This decision problem is an important facet of resource allocation. As infrastructures grow in scale and heterogeneity, the resulting decision space becomes inherently combinatorial. Existing approaches typically formulate this problem as a constrained optimization task using ad-hoc representations of infrastructure topologies and demand, which hinders generalization across solutions. In contrast, Software as a Service ecosystems address a structurally similar configuration problem through pricings -structures whose plans and add-ons implicitly define the configuration space of possible subscriptions. Building on this observation, this work explores the potential of pricings as general-purpose representations of configuration spaces, positioning them as a promising alternative for addressing configuration problems, such as resource allocation, across the computing continuum. To this end, the paper presents the following contributions: i) a pricing-based formulation of the resource allocation problem in the computing continuum, enabling infrastructure configuration spaces to be represented using pricings; ii) a workflow that leverages PRIME, a pricing analysis engine, to explore these spaces and compute cost-optimal deployments satisfying functional and non-functional constraints; iii) generation processes for synthetic infrastructure topologies and workload demands; and iv) a dataset comprising 9,600 precomputed resource allocation scenarios to support benchmarking. △ Less

Submitted 14 April, 2026; originally announced April 2026.

DQ-Ladder: A Deep Reinforcement Learning-based Bitrate Ladder for Adaptive Video Streaming

Authors: Reza Farahani, Zoha Azimi, Vignesh V Menon, Hermann Hellwagner, Radu Prodan, Schahram Dustdar, Christian Timmerer

Abstract: Adaptive streaming of segmented video over HTTP typically relies on a predefined set of bitrate-resolution pairs, known as a bitrate ladder. However, fixed ladders often overlook variations in content and decoding complexities, leading to suboptimal trade-offs between encoding time, decoding efficiency, and video quality. This article introduces DQ-Ladder, a deep reinforcement learning (DRL)-based… ▽ More Adaptive streaming of segmented video over HTTP typically relies on a predefined set of bitrate-resolution pairs, known as a bitrate ladder. However, fixed ladders often overlook variations in content and decoding complexities, leading to suboptimal trade-offs between encoding time, decoding efficiency, and video quality. This article introduces DQ-Ladder, a deep reinforcement learning (DRL)-based scheme for constructing time- and quality-aware bitrate ladders for adaptive video streaming applications. DQ-Ladder employs predicted decoding time, quality scores, and bitrate levels per segment as inputs to a Deep Q-Network (DQN) agent, guided by a weighted reward function of decoding time, video quality, and resolution smoothness. We leverage machine learning models to predict decoding time, bitrate level, and objective quality metrics (VMAF, XPSNR), eliminating the need for exhaustive encoding or quality metric computation. We evaluate DQ-Ladder using the Versatile Video Coding (VVC) toolchain (VVenC/VVdeC) on 750 video sequences across six Apple HLS-compliant resolutions and 41 quantization parameters. Experimental results against four baselines show that DQ-Ladder achieves BD-rate reductions of at least 10.3% for XPSNR compared to the HLS ladder, while reducing decoding time by 22%. DQ-Ladder shows significantly lower sensitivity to prediction errors than competing methods, remaining robust even with up to 20% noise. △ Less

Submitted 13 March, 2026; originally announced March 2026.

Comments: Adaptive Video Streaming, Deep Reinforcement Learning, Q-Learning, Bitrate Ladder, Quality Prediction

Real-Time AI Service Economy: A Framework for Agentic Computing Across the Continuum

Authors: Lauri Lovén, Alaa Saleh, Reza Farahani, Ilir Murturi, Miguel Bordallo López, Praveen Kumar Donta, Schahram Dustdar

Abstract: Real-time AI services increasingly operate across the device-edge-cloud continuum, where autonomous AI agents generate latency-sensitive workloads, orchestrate multi-stage processing pipelines, and compete for shared resources under policy and governance constraints. This article shows that the structure of service-dependency graphs, modelled as DAGs whose nodes represent compute stages and whose… ▽ More Real-time AI services increasingly operate across the device-edge-cloud continuum, where autonomous AI agents generate latency-sensitive workloads, orchestrate multi-stage processing pipelines, and compete for shared resources under policy and governance constraints. This article shows that the structure of service-dependency graphs, modelled as DAGs whose nodes represent compute stages and whose edges encode execution ordering, is a primary determinant of whether decentralised, price-based resource allocation can work reliably at scale. When dependency graphs are hierarchical (tree or series-parallel), prices converge to stable equilibria, optimal allocations can be computed efficiently, and under appropriate mechanism design (with quasilinear utilities and discrete slice items), agents have no incentive to misreport their valuations within each decision epoch. When dependencies are more complex, with cross-cutting ties between pipeline stages, prices oscillate, allocation quality degrades, and the system becomes difficult to manage. To bridge this gap, we propose a hybrid management architecture in which cross-domain integrators encapsulate complex sub-graphs into resource slices that present a simpler, well-structured interface to the rest of the market. A systematic ablation study across six experiments (1,620 runs, 10 seeds each) confirms that (i) dependency-graph topology is a first-order determinant of price stability and scalability,(ii) the hybrid architecture reduces price volatility by up to 70-75% without sacrificing throughput, (iii) governance constraints create quantifiable efficiency-compliance trade-offs that depend jointly on topology and load, and (iv) under truthful bidding the decentralised market matches a centralised value-optimal baseline, confirming that decentralised coordination can replicate centralised allocation quality. △ Less

Submitted 5 March, 2026; originally announced March 2026.

Visual Insights into Agentic Optimization of Pervasive Stream Processing Services

Authors: Boris Sedlak, Víctor Casamayor Pujol, Schahram Dustdar

Abstract: Processing sensory data close to the data source, often involving Edge devices, promises low latency for pervasive applications, like smart cities. This commonly involves a multitude of processing services, executed with limited resources; this setup faces three problems: first, the application demand and the resource availability fluctuate, so the service execution must scale dynamically to susta… ▽ More Processing sensory data close to the data source, often involving Edge devices, promises low latency for pervasive applications, like smart cities. This commonly involves a multitude of processing services, executed with limited resources; this setup faces three problems: first, the application demand and the resource availability fluctuate, so the service execution must scale dynamically to sustain processing requirements (e.g., latency); second, each service permits different actions to adjust its operation, so they require individual scaling policies; third, without a higher-level mediator, services would cannibalize any resources of services co-located on the same device. This demo first presents a platform for context-aware autoscaling of stream processing services that allows developers to monitor and adjust the service execution across multiple service-specific parameters. We then connect a scaling agent to these interfaces that gradually builds an understanding of the processing environment by exploring each service's action space; the agent then optimizes the service execution according to this knowledge. Participants can revisit the demo contents as video summary and introductory poster, or build a custom agent by extending the artifact repository. △ Less

Submitted 19 February, 2026; originally announced February 2026.

Service Orchestration in the Computing Continuum: Structural Challenges and Vision

Authors: Boris Sedlak, Víctor Casamayor Pujol, Ildefons Magrans de Abril, Praveen Kumar Donta, Adel N. Toosi, Schahram Dustdar

Abstract: The Computing Continuum (CC) integrates different layers of processing infrastructure, from Edge to Cloud, to optimize service quality through ubiquitous and reliable computation. Compared to central architectures, however, heterogeneous and dynamic infrastructure increases the complexity for service orchestration. To guide research, this article first summarizes structural problems of the CC, and… ▽ More The Computing Continuum (CC) integrates different layers of processing infrastructure, from Edge to Cloud, to optimize service quality through ubiquitous and reliable computation. Compared to central architectures, however, heterogeneous and dynamic infrastructure increases the complexity for service orchestration. To guide research, this article first summarizes structural problems of the CC, and then, envisions an ideal solution for autonomous service orchestration across the CC. As one instantiation, we show how Active Inference, a concept from neuroscience, can support self-organizing services in continuously interpreting their environment to optimize service quality. Still, we conclude that no existing solution achieves our vision, but that research on service orchestration faces several structural challenges. Most notably: provide standardized simulation and evaluation environments for comparing the performance of orchestration mechanisms. Together, the challenges outline a research roadmap toward resilient and scalable service orchestration in the CC. △ Less

Submitted 17 February, 2026; originally announced February 2026.

A Microservice-Based Platform for Sustainable and Intelligent SLO Fulfilment and Service Management

Authors: Juan Luis Herrera, Daniel Wang, Schahram Dustdar

Abstract: The Microservices Architecture (MSA) design pattern has become a staple for modern applications, allowing functionalities to be divided across fine-grained microservices, fostering reusability, distribution, and interoperability. As MSA-based applications are deployed to the Computing Continuum (CC), meeting their Service Level Objectives (SLOs) becomes a challenge. Trading off performance and sus… ▽ More The Microservices Architecture (MSA) design pattern has become a staple for modern applications, allowing functionalities to be divided across fine-grained microservices, fostering reusability, distribution, and interoperability. As MSA-based applications are deployed to the Computing Continuum (CC), meeting their Service Level Objectives (SLOs) becomes a challenge. Trading off performance and sustainability SLOs is especially challenging. This challenge can be addressed with intelligent decision systems, able to reconfigure the services during runtime to meet the SLOs. However, developing these agents while adhering to the MSA pattern is complex, especially because CC providers, who have key know-how and information to fulfill these SLOs, must comply with the privacy requirements of application developers. This work presents the Carbon-Aware SLO and Control plAtform (CASCA), an open-source MSA-based platform that allows CC providers to reconfigure services and fulfill their SLOs while maintaining the privacy of developers. CASCA is architected to be highly reusable, distributable, and easy to use, extend, and modify. CASCA has been evaluated in a real CC testbed for a media streaming service, where decision systems implemented in Bash, Rust, and Python successfully reconfigured the service, unaffected by upholding privacy. △ Less

Submitted 13 February, 2026; originally announced February 2026.

Comments: This work has been submitted to the IEEE for possible publication

Socio-technical aspects of Agentic AI

Authors: Praveen Kumar Donta, Alaa Saleh, Ying Li, Shubham Vaishnav, Kai Fang, Hailin Feng, Yuchao Xia, Thippa Reddy Gadekallu, Qiyang Zhang, Xiaodan Shi, Ali Beikmohammadi, Sindri Magnússon, Ilir Murturi, Chinmaya Kumar Dehury, Marcin Paprzycki, Lauri Loven, Sasu Tarkoma, Schahram Dustdar

Abstract: Agentic Artificial Intelligence (AI) represents a fundamental shift in the design of intelligent systems, characterized by interconnected components that collectively enable autonomous perception, reasoning, planning, action, and learning. Recent research on agentic AI has largely focused on technical foundations, including system architectures, reasoning and planning mechanisms, coordination stra… ▽ More Agentic Artificial Intelligence (AI) represents a fundamental shift in the design of intelligent systems, characterized by interconnected components that collectively enable autonomous perception, reasoning, planning, action, and learning. Recent research on agentic AI has largely focused on technical foundations, including system architectures, reasoning and planning mechanisms, coordination strategies, and application-level performance across domains. However, the societal, ethical, economic, environmental, and governance implications of agentic AI remain weakly integrated into these technical treatments. This paper addresses this gap by presenting a socio-technical analysis of agentic AI that explicitly connects core technical components with societal context. We examine how architectural choices in perception, cognition, planning, execution, and memory introduce dependencies related to data governance, accountability, transparency, safety, and sustainability. To structure this analysis, we adopt the MAD-BAD-SAD construct as an analytical lens, capturing motivations, applications, and moral dilemmas (MAD); biases, accountability, and dangers (BAD); and societal impact, adoption, and design considerations (SAD). Using this lens, we analyze ethical considerations, implications, and challenges arising from contemporary agentic AI systems and assess their manifestation across emerging applications, including healthcare, education, industry, smart and sustainable cities, social services, communications and networking, and earth observation and satellite communications. The paper further identifies open challenges and suggests future research directions, framing agentic AI as an integrated socio-technical system whose behavior and impact are co-produced by algorithms, data, organizational practices, regulatory frameworks, and social norms. △ Less

Submitted 26 December, 2025; originally announced January 2026.

Comments: Dear Reviewer, please note that this is not survey/review or position paper. This paper introduced new framework (MAD-BAD-SAD Framework) for Socio-technical aspects of Agentic AI, Ethical considerations, which is very important to consider beside technical development

Bio-inspired Agentic Self-healing Framework for Resilient Distributed Computing Continuum Systems

Authors: Alaa Saleh, Praveen Kumar Donta, Roberto Morabito, Sasu Tarkoma, Anders Lindgren, Qiyang Zhang, Schahram Dustdar, Susanna Pirttikangas, Lauri Lovén

Abstract: Human biological systems sustain life through extraordinary resilience, continually detecting damage, orchestrating targeted responses, and restoring function through self-healing. Inspired by these capabilities, this paper introduces ReCiSt, a bio-inspired agentic self-healing framework designed to achieve resilience in Distributed Computing Continuum Systems (DCCS). Modern DCCS integrate heterog… ▽ More Human biological systems sustain life through extraordinary resilience, continually detecting damage, orchestrating targeted responses, and restoring function through self-healing. Inspired by these capabilities, this paper introduces ReCiSt, a bio-inspired agentic self-healing framework designed to achieve resilience in Distributed Computing Continuum Systems (DCCS). Modern DCCS integrate heterogeneous computing resources, ranging from resource-constrained IoT devices to high-performance cloud infrastructures, and their inherent complexity, mobility, and dynamic operating conditions expose them to frequent faults that disrupt service continuity. These challenges underscore the need for scalable, adaptive, and self-regulated resilience strategies. ReCiSt reconstructs the biological phases of Hemostasis, Inflammation, Proliferation, and Remodeling into the computational layers Containment, Diagnosis, Meta-Cognitive, and Knowledge for DCCS. These four layers perform autonomous fault isolation, causal diagnosis, adaptive recovery, and long-term knowledge consolidation through Language Model (LM)-powered agents. These agents interpret heterogeneous logs, infer root causes, refine reasoning pathways, and reconfigure resources with minimal human intervention. The proposed ReCiSt framework is evaluated on public fault datasets using multiple LMs, and no baseline comparison is included due to the scarcity of similar approaches. Nevertheless, our results, evaluated under different LMs, confirm ReCiSt's self-healing capabilities within tens of seconds with minimum of 10% of agent CPU usage. Our results also demonstrated depth of analysis to over come uncertainties and amount of micro-agents invoked to achieve resilience. △ Less

Submitted 1 January, 2026; originally announced January 2026.

QoS-Aware Load Balancing in the Computing Continuum via Multi-Player Bandits

Authors: Ivan Čilić, Ivana Podnar Žarko, Pantelis Frangoudis, Schahram Dustdar

Abstract: As computation shifts from the cloud to the edge to reduce processing latency and network traffic, the resulting Computing Continuum (CC) creates a dynamic environment where meeting strict Quality of Service (QoS) requirements and avoiding service instance overload becomes challenging. Existing methods often prioritize global metrics and overlook per-client QoS, which is crucial for latency-sensit… ▽ More As computation shifts from the cloud to the edge to reduce processing latency and network traffic, the resulting Computing Continuum (CC) creates a dynamic environment where meeting strict Quality of Service (QoS) requirements and avoiding service instance overload becomes challenging. Existing methods often prioritize global metrics and overlook per-client QoS, which is crucial for latency-sensitive and reliability-critical applications. We propose QEdgeProxy, a decentralized QoS-aware load balancer that acts as a proxy between IoT devices and service instances in the CC. We formulate the load balancing problem as a Multi-Player Multi-Armed Bandit (MP-MAB) with heterogeneous rewards: Each load balancer autonomously selects service instances to maximize the probability of meeting its clients' QoS requirements by using Kernel Density Estimation (KDE) to estimate QoS success probabilities. Our load-balancing algorithm also incorporates an adaptive exploration mechanism to recover rapidly from performance shifts and non-stationary conditions. We present a Kubernetes-native QEdgeProxy implementation and evaluate it on an emulated CC testbed deployed on a K3s cluster with realistic network conditions and a latency-sensitive edge-AI workload. Results show that QEdgeProxy significantly outperforms proximity-based and reinforcement-learning baselines in per-client QoS satisfaction, while adapting effectively to load surges and changes in instance availability. △ Less

Submitted 7 January, 2026; v1 submitted 21 December, 2025; originally announced December 2025.

A Conflict-Aware Resource Management Framework for the Computing Continuum

Authors: Vlad Popescu-Vifor, Ilir Murturi, Praveen Kumar Donta, Schahram Dustdar

Abstract: The increasing device heterogeneity and decentralization requirements in the computing continuum (i.e., spanning edge, fog, and cloud) introduce new challenges in resource orchestration. In such environments, agents are often responsible for optimizing resource usage across deployed services. However, agent decisions can lead to persistent conflict loops, inefficient resource utilization, and degr… ▽ More The increasing device heterogeneity and decentralization requirements in the computing continuum (i.e., spanning edge, fog, and cloud) introduce new challenges in resource orchestration. In such environments, agents are often responsible for optimizing resource usage across deployed services. However, agent decisions can lead to persistent conflict loops, inefficient resource utilization, and degraded service performance. To overcome such challenges, we propose a novel framework for adaptive conflict resolution in resource-oriented orchestration using a Deep Reinforcement Learning (DRL) approach. The framework enables handling resource conflicts across deployments and integrates a DRL model trained to mediate such conflicts based on real-time performance feedback and historical state information. The framework has been prototyped and validated on a Kubernetes-based testbed, illustrating its methodological feasibility and architectural resilience. Preliminary results show that the framework achieves efficient resource reallocation and adaptive learning in dynamic scenarios, thus providing a scalable and resilient solution for conflict-aware orchestration in the computing continuum. △ Less

Submitted 21 April, 2026; v1 submitted 13 December, 2025; originally announced December 2025.

Synergizing Monetization, Orchestration, and Semantics in Computing Continuum

Authors: Chinmaya Kumar Dehury, Lauri Lovén, Praveen Kumar Donta, Ilir Murturi, Schahram Dustdar

Abstract: Industry demands are growing for hyper-distributed applications that span from the cloud to the edge in domains such as smart manufacturing, transportation, and agriculture. Yet today's solutions struggle to meet these demands due to inherent limitations in scalability, interoperability, and trust. In this article, we introduce HERMES (Heterogeneous Computing Continuum with Resource Monetization,… ▽ More Industry demands are growing for hyper-distributed applications that span from the cloud to the edge in domains such as smart manufacturing, transportation, and agriculture. Yet today's solutions struggle to meet these demands due to inherent limitations in scalability, interoperability, and trust. In this article, we introduce HERMES (Heterogeneous Computing Continuum with Resource Monetization, Orchestration, and Semantic) - a novel framework designed to transform connectivity and data utilization across the computing continuum. HERMES establishes an open, seamless, and secure environment where resources, from cloud servers to tiny edge devices, can be orchestrated intelligently, data and services can be monetized in a distributed marketplace, and knowledge is shared through semantic interoperability. By bridging these key facets, HERMES lays a foundation for a new generation of distributed applications that are more efficient, trustworthy, and autonomous. △ Less

Submitted 9 December, 2025; originally announced December 2025.

Comments: Currently submitted to IEEE Computers

BIPPO: Budget-Aware Independent PPO for Energy-Efficient Federated Learning Services

Authors: Anna Lackinger, Andrea Morichetta, Pantelis A. Frangoudis, Schahram Dustdar

Abstract: Federated Learning (FL) is a promising machine learning solution in large-scale IoT systems, guaranteeing load distribution and privacy. However, FL does not natively consider infrastructure efficiency, a critical concern for systems operating in resource-constrained environments. Several Reinforcement Learning (RL) based solutions offer improved client selection for FL; however, they do not consi… ▽ More Federated Learning (FL) is a promising machine learning solution in large-scale IoT systems, guaranteeing load distribution and privacy. However, FL does not natively consider infrastructure efficiency, a critical concern for systems operating in resource-constrained environments. Several Reinforcement Learning (RL) based solutions offer improved client selection for FL; however, they do not consider infrastructure challenges, such as resource limitations and device churn. Furthermore, the training of RL methods is often not designed for practical application, as these approaches frequently do not consider generalizability and are not optimized for energy efficiency. To fill this gap, we propose BIPPO (Budget-aware Independent Proximal Policy Optimization), which is an energy-efficient multi-agent RL solution that improves performance. We evaluate BIPPO on two image classification tasks run in a highly budget-constrained setting, with FL clients training on non-IID data, a challenging context for vanilla FL. The improved sampler of BIPPO enables it to increase the mean accuracy compared to non-RL mechanisms, traditional PPO, and IPPO. In addition, BIPPO only consumes a negligible proportion of the budget, which stays consistent even if the number of clients increases. Overall, BIPPO delivers a performant, stable, scalable, and sustainable solution for client selection in IoT-FL. △ Less

Submitted 21 August, 2026; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: Submission to IEEE Transactions on Services Computing

Resilient by Design -- Active Inference for Distributed Continuum Intelligence

Authors: Praveen Kumar Donta, Alfreds Lapkovskis, Enzo Mingozzi, Schahram Dustdar

Abstract: Failures are the norm in highly complex and heterogeneous devices spanning the distributed computing continuum (DCC), from resource-constrained IoT and edge nodes to high-performance computing systems. Ensuring reliability and global consistency across these layers remains a major challenge, especially for AI-driven workloads requiring real-time, adaptive coordination. This work-in-progress paper… ▽ More Failures are the norm in highly complex and heterogeneous devices spanning the distributed computing continuum (DCC), from resource-constrained IoT and edge nodes to high-performance computing systems. Ensuring reliability and global consistency across these layers remains a major challenge, especially for AI-driven workloads requiring real-time, adaptive coordination. This work-in-progress paper introduces a Probabilistic Active Inference Resilience Agent (PAIR-Agent) to achieve resilience in DCC systems. PAIR-Agent performs three core operations: (i) constructing a causal fault graph from device logs, (ii) identifying faults while managing certainties and uncertainties using Markov blankets and the free energy principle, and (iii) autonomously healing issues through active inference. Through continuous monitoring and adaptive reconfiguration, the agent maintains service continuity and stability under diverse failure conditions. Theoretical validations confirm the reliability and effectiveness of the proposed framework. △ Less

Submitted 3 July, 2026; v1 submitted 10 November, 2025; originally announced November 2025.

OmniFuser: Adaptive Multimodal Fusion for Service-Oriented Predictive Maintenance

Authors: Ziqi Wang, Hailiang Zhao, Yuhao Yang, Daojiang Hu, Cheng Bao, Mingyi Liu, Kai Di, Schahram Dustdar, Zhongjie Wang, Shuiguang Deng

Abstract: Accurate and timely prediction of tool conditions is critical for intelligent manufacturing systems, where unplanned tool failures can lead to quality degradation and production downtime. In modern industrial environments, predictive maintenance is increasingly implemented as an intelligent service that integrates sensing, analysis, and decision support across production processes. To meet the dem… ▽ More Accurate and timely prediction of tool conditions is critical for intelligent manufacturing systems, where unplanned tool failures can lead to quality degradation and production downtime. In modern industrial environments, predictive maintenance is increasingly implemented as an intelligent service that integrates sensing, analysis, and decision support across production processes. To meet the demand for reliable and service-oriented operation, we present OmniFuser, a multimodal learning framework for predictive maintenance of milling tools that leverages both visual and sensor data. It performs parallel feature extraction from high-resolution tool images and cutting-force signals, capturing complementary spatiotemporal patterns across modalities. To effectively integrate heterogeneous features, OmniFuser employs a contamination-free cross-modal fusion mechanism that disentangles shared and modality-specific components, allowing for efficient cross-modal interaction. Furthermore, a recursive refinement pathway functions as an anchor mechanism, consistently retaining residual information to stabilize fusion dynamics. The learned representations can be encapsulated as reusable maintenance service modules, supporting both tool-state classification (e.g., Sharp, Used, Dulled) and multi-step force signal forecasting. Experiments on real-world milling datasets demonstrate that OmniFuser consistently outperforms state-of-the-art baselines, providing a dependable foundation for building intelligent industrial maintenance services. △ Less

Submitted 3 November, 2025; originally announced November 2025.

Multi-Dimensional Autoscaling of Stream Processing Services on Edge Devices

Authors: Boris Sedlak, Philipp Raith, Andrea Morichetta, Víctor Casamayor Pujol, Schahram Dustdar

Abstract: Edge devices have limited resources, which inevitably leads to situations where stream processing services cannot satisfy their needs. While existing autoscaling mechanisms focus entirely on resource scaling, Edge devices require alternative ways to sustain the Service Level Objectives (SLOs) of competing services. To address these issues, we introduce a Multi-dimensional Autoscaling Platform (MUD… ▽ More Edge devices have limited resources, which inevitably leads to situations where stream processing services cannot satisfy their needs. While existing autoscaling mechanisms focus entirely on resource scaling, Edge devices require alternative ways to sustain the Service Level Objectives (SLOs) of competing services. To address these issues, we introduce a Multi-dimensional Autoscaling Platform (MUDAP) that supports fine-grained vertical scaling across both service- and resource-level dimensions. MUDAP supports service-specific scaling tailored to available parameters, e.g., scale data quality or model size for a particular service. To optimize the execution across services, we present a scaling agent based on Regression Analysis of Structural Knowledge (RASK). The RASK agent efficiently explores the solution space and learns a continuous regression model of the processing environment for inferring optimal scaling actions. We compared our approach with two autoscalers, the Kubernetes VPA and a reinforcement learning agent, for scaling up to 9 services on a single Edge device. Our results showed that RASK can infer an accurate regression model in merely 20 iterations (i.e., observe 200s of processing). By increasingly adding elasticity dimensions, RASK sustained the highest request load with 28% less SLO violations, compared to baselines. △ Less

Submitted 27 March, 2026; v1 submitted 8 October, 2025; originally announced October 2025.

Agentic Services Computing

Authors: Shuiguang Deng, Hailiang Zhao, Ziqi Wang, Wenzhuo Qian, Xiang Ao, Guanjie Cheng, Jianwei Yin, Albert Y. Zomaya, Schahram Dustdar

Abstract: Services computing has evolved from Web services and microservices to cloud-native and serverless paradigms. These approaches established mature principles for describing, composing, deploying, operating, and governing reusable software functions. LLM-based agents now introduce a fundamentally different service form. Service value in this paradigm emerges not only from invoking predefined function… ▽ More Services computing has evolved from Web services and microservices to cloud-native and serverless paradigms. These approaches established mature principles for describing, composing, deploying, operating, and governing reusable software functions. LLM-based agents now introduce a fundamentally different service form. Service value in this paradigm emerges not only from invoking predefined functions but also from delegating goals to autonomous entities. These entities understand context, use tools, collaborate with peers, and act across open environments. This shift raises a core question for services computing. How can goal-driven, stateful, tool-mediated, and accountable autonomous behavior be engineered and managed as a service? Recent studies on LLM agents and multi-agent systems provide important foundations. A clear service-centered research roadmap for this emerging paradigm nevertheless remains absent. This work introduces Agentic Services Computing (ASC) to address this gap. ASC extends services computing from managing reusable functional endpoints to engineering and governing autonomous service entities. It defines agentic services as service-oriented autonomous agents. Related research is organized through a lifecycle view that connects service objects, system structures, enabling infrastructure, evaluation metrics, application evidence, and open challenges. This service-centered perspective establishes a foundation for future service ecosystems. Autonomous agents can thus be systematically described, composed, delivered, monitored, audited, and evolved as first-class services. △ Less

Submitted 3 July, 2026; v1 submitted 29 September, 2025; originally announced September 2025.

A Novel Hierarchical Co-Optimization Framework for Coordinated Task Scheduling and Power Dispatch in Computing Power Networks

Authors: Haoxiang Luo, Kun Yang, Qi Huang, Marco Aiello, Schahram Dustdar

Abstract: The proliferation of large-scale AI and data-intensive applications has driven the development of Computing Power Networks (CPN). It is a key paradigm for delivering ubiquitous, on-demand computational services with high efficiency. However, CPNs face dual challenges in service computing. Immense energy consumption threatens sustainable operations. And the integration with power grids also feature… ▽ More The proliferation of large-scale AI and data-intensive applications has driven the development of Computing Power Networks (CPN). It is a key paradigm for delivering ubiquitous, on-demand computational services with high efficiency. However, CPNs face dual challenges in service computing. Immense energy consumption threatens sustainable operations. And the integration with power grids also features high penetration of intermittent Renewable Energy Sources (RES), complicating task scheduling while ensuring Quality of Service (QoS). To address these issues, this paper proposes a novel Two-Stage Co-Optimization (TSCO) framework. It synergistically coordinates CPN task scheduling and power system dispatch, aiming to optimize service performance while achieving low-carbon operations. The framework decomposes the complex, large-scale problem into a day-ahead stochastic unit commitment stage and a real-time operational stage. The former is solved using Benders decomposition for computational tractability, while in the latter, economic dispatch of generation assets is coupled with an adaptive CPN task scheduling managed by a deep reinforcement learning agent. It makes carbon-aware decisions by responding to dynamic grid conditions, including real-time electricity prices and marginal carbon intensity. Extensive simulations demonstrate that the TSCO outperforms baseline approaches significantly. It reduces carbon emissions by 16.2% and operational costs by 12.7%, while decreasing RES curtailment by over $60\%$, maintaining a task success rate of 98.5%, and minimizing average task tardiness to 12.3s. This work advances cross-domain service optimization in CPNs. △ Less

Submitted 3 February, 2026; v1 submitted 5 August, 2025; originally announced August 2025.

PeerSync: Accelerating Containerized Service Delivery at the Network Edge

Authors: Yinuo Deng, Hailiang Zhao, Dongjing Wang, Peng Chen, Wenzhuo Qian, Jianwei Yin, Schahram Dustdar, Shuiguang Deng

Abstract: Efficient container image distribution is crucial for enabling machine learning inference at the network edge, where resource limitations and dynamic network conditions create significant challenges. In this paper, we present PeerSync, a decentralized P2P-based system designed to optimize image distribution in edge environments. PeerSync employs a popularity- and network-aware download engine that… ▽ More Efficient container image distribution is crucial for enabling machine learning inference at the network edge, where resource limitations and dynamic network conditions create significant challenges. In this paper, we present PeerSync, a decentralized P2P-based system designed to optimize image distribution in edge environments. PeerSync employs a popularity- and network-aware download engine that dynamically adapts to content popularity and real-time network conditions. PeerSync further integrates automated tracker election for rapid peer discovery and dynamic cache management for efficient storage utilization. We implement PeerSync with 8000+ lines of Rust code and test its performance extensively on both large-scale Docker-based emulations and physical edge devices. Experimental results show that PeerSync delivers a remarkable speed increase of 2.72$\times$, 1.79$\times$, and 1.28$\times$ compared to the Baseline solution, Dragonfly, and Kraken, respectively, while significantly reducing cross-network traffic by 90.72% under congested and varying network conditions. △ Less

Submitted 18 December, 2025; v1 submitted 26 July, 2025; originally announced July 2025.

Edge Intelligence with Spiking Neural Networks

Authors: Shuiguang Deng, Di Yu, Changze Lv, Xin Du, Linshan Jiang, Xiaofan Zhao, Wentao Tong, Xiaoqing Zheng, Weijia Fang, Peng Zhao, Gang Pan, Schahram Dustdar, Albert Y. Zomaya

Abstract: The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational resources and centralized data management, the resulting latency, bandwidth consumption, and privacy concerns have exposed critical limitations in cloud-centric… ▽ More The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational resources and centralized data management, the resulting latency, bandwidth consumption, and privacy concerns have exposed critical limitations in cloud-centric paradigms. Brain-inspired computing, particularly Spiking Neural Networks (SNNs), offers a promising alternative by emulating biological neuronal dynamics to achieve low-power, event-driven computation. This survey provides a comprehensive overview of Edge Intelligence based on SNNs (EdgeSNNs), examining their potential to address the challenges of on-device learning, inference, and security in edge scenarios. We present a systematic taxonomy of EdgeSNN foundations, encompassing neuron models, learning algorithms, and supporting hardware platforms. Three representative practical considerations of EdgeSNN are discussed in depth: on-device inference using lightweight SNN models, resource-aware training and updating under non-stationary data conditions, and secure and privacy-preserving issues. Furthermore, we highlight the limitations of evaluating EdgeSNNs on conventional hardware and introduce a dual-track benchmarking strategy to support fair comparisons and hardware-aware optimization. Through this study, we aim to bridge the gap between brain-inspired learning and practical edge deployment, offering insights into current advancements, open challenges, and future research directions. To the best of our knowledge, this is the first dedicated and comprehensive survey on EdgeSNNs, providing an essential reference for researchers and practitioners working at the intersection of neuromorphic computing and edge intelligence. △ Less

Submitted 18 July, 2025; originally announced July 2025.

Comments: This work has been submitted to Proceeding of IEEE for possible publication

Performance Measurements in the AI-Centric Computing Continuum Systems

Authors: Praveen Kumar Donta, Qiyang Zhang, Schahram Dustdar

Abstract: Over the Eight decades, computing paradigms have shifted from large, centralized systems to compact, distributed architectures, leading to the rise of the Distributed Computing Continuum (DCC). In this model, multiple layers such as cloud, edge, Internet of Things (IoT), and mobile platforms work together to support a wide range of applications. Recently, the emergence of Generative AI and large l… ▽ More Over the Eight decades, computing paradigms have shifted from large, centralized systems to compact, distributed architectures, leading to the rise of the Distributed Computing Continuum (DCC). In this model, multiple layers such as cloud, edge, Internet of Things (IoT), and mobile platforms work together to support a wide range of applications. Recently, the emergence of Generative AI and large language models has further intensified the demand for computational resources across this continuum. Although traditional performance metrics have provided a solid foundation, they need to be revisited and expanded to keep pace with changing computational demands and application requirements. Accurate performance measurements benefit both system designers and users by supporting improvements in efficiency and promoting alignment with system goals. In this context, we review commonly used metrics in DCC and IoT environments. We also discuss emerging performance dimensions that address evolving computing needs, such as sustainability, energy efficiency, and system observability. We also outline criteria and considerations for selecting appropriate metrics, aiming to inspire future research and development in this critical area. △ Less

Submitted 28 June, 2025; originally announced June 2025.

Multi-dimensional Autoscaling of Processing Services: A Comparison of Agent-based Methods

Authors: Boris Sedlak, Alireza Furutanpey, Zihang Wang, Víctor Casamayor Pujol, Schahram Dustdar

Abstract: Edge computing breaks with traditional autoscaling due to strict resource constraints, thus, motivating more flexible scaling behaviors using multiple elasticity dimensions. This work introduces an agent-based autoscaling framework that dynamically adjusts both hardware resources and internal service configurations to maximize requirements fulfillment in constrained environments. We compare four t… ▽ More Edge computing breaks with traditional autoscaling due to strict resource constraints, thus, motivating more flexible scaling behaviors using multiple elasticity dimensions. This work introduces an agent-based autoscaling framework that dynamically adjusts both hardware resources and internal service configurations to maximize requirements fulfillment in constrained environments. We compare four types of scaling agents: Active Inference, Deep Q Network, Analysis of Structural Knowledge, and Deep Active Inference, using two real-world processing services running in parallel: YOLOv8 for visual recognition and OpenCV for QR code detection. Results show all agents achieve acceptable SLO performance with varying convergence patterns. While the Deep Q Network benefits from pre-training, the structural analysis converges quickly, and the deep active inference agent combines theoretical foundations with practical scalability advantages. Our findings provide evidence for the viability of multi-dimensional agent-based autoscaling for edge environments and encourage future work in this research direction. △ Less

Submitted 12 January, 2026; v1 submitted 12 June, 2025; originally announced June 2025.

Distributed Intelligence in the Computing Continuum with Active Inference

Authors: Victor Casamayor Pujol, Boris Sedlak, Tommaso Salvatori, Karl Friston, Schahram Dustdar

Abstract: The Computing Continuum (CC) is an emerging Internet-based computing paradigm that spans from local Internet of Things sensors and constrained edge devices to large-scale cloud data centers. Its goal is to orchestrate a vast array of diverse and distributed computing resources to support the next generation of Internet-based applications. However, the distributed, heterogeneous, and dynamic nature… ▽ More The Computing Continuum (CC) is an emerging Internet-based computing paradigm that spans from local Internet of Things sensors and constrained edge devices to large-scale cloud data centers. Its goal is to orchestrate a vast array of diverse and distributed computing resources to support the next generation of Internet-based applications. However, the distributed, heterogeneous, and dynamic nature of CC platforms demands distributed intelligence for adaptive and resilient service management. This article introduces a distributed stream processing pipeline as a CC use case, where each service is managed by an Active Inference (AIF) agent. These agents collaborate to fulfill service needs specified by SLOiDs, a term we introduce to denote Service Level Objectives that are aware of its deployed devices, meaning that non-functional requirements must consider the characteristics of the hosting device. We demonstrate how AIF agents can be modeled and deployed alongside distributed services to manage them autonomously. Our experiments show that AIF agents achieve over 90% SLOiD fulfillment when using tested transition models, and around 80% when learning the models during deployment. We compare their performance to a multi-agent reinforcement learning algorithm, finding that while both approaches yield similar results, MARL requires extensive training, whereas AIF agents can operate effectively from the start. Additionally, we evaluate the behavior of AIF agents in offloading scenarios, observing a strong capacity for adaptation. Finally, we outline key research directions to advance AIF integration in CC platforms. △ Less

Submitted 30 May, 2025; originally announced May 2025.

MACH: Multi-Agent Coordination for RSU-centric Handovers

Authors: Nikolaus Spring, Andrea Morichetta, Boris Sedlak, Schahram Dustdar

Abstract: This paper introduces MACH, a novel approach for optimizing task handover in vehicular computing scenarios. To ensure fast and latency-aware placement of tasks, the decision-making -- where and when should tasks be offloaded -- is carried out decentralized at the Road Side Units (RSUs) who also execute the tasks. By shifting control to the network edge, MACH moves away from the traditional central… ▽ More This paper introduces MACH, a novel approach for optimizing task handover in vehicular computing scenarios. To ensure fast and latency-aware placement of tasks, the decision-making -- where and when should tasks be offloaded -- is carried out decentralized at the Road Side Units (RSUs) who also execute the tasks. By shifting control to the network edge, MACH moves away from the traditional centralized or vehicle-based handover method. Still, it focuses on contextual factors, such as the current RSU load and vehicle trajectories. Thus, MACH improves the overall Quality of Service (QoS) while fairly balancing computational loads between RSUs. To evaluate the effectiveness of our approach, we develop a robust simulation environment composed of real-world traffic data, dynamic network conditions, and different infrastructure capacities. For scenarios that demand low latency and high reliability, our experimental results demonstrate how MACH significantly improves the adaptability and efficiency of vehicular computations. By decentralizing control to the network edge, MACH effectively reduces communication overhead and optimizes resource utilization, offering a robust framework for task handover management. △ Less

Submitted 29 April, 2025; originally announced May 2025.

Comments: Submitted to ACM TOIT. Currently under review

A Weighted Byzantine Fault Tolerance Consensus Driven Trusted Multiple Large Language Models Network

Authors: Haoxiang Luo, Gang Sun, Yinqiu Liu, Dongcheng Zhao, Dusit Niyato, Hongfang Yu, Schahram Dustdar

Abstract: Large Language Models (LLMs) have achieved remarkable success across a wide range of applications. However, individual LLMs often produce inconsistent, biased, or hallucinated outputs due to limitations in their training corpora and model architectures. Recently, collaborative frameworks such as the Multi-LLM Network (MultiLLMN) have been introduced, enabling multiple LLMs to interact and jointly… ▽ More Large Language Models (LLMs) have achieved remarkable success across a wide range of applications. However, individual LLMs often produce inconsistent, biased, or hallucinated outputs due to limitations in their training corpora and model architectures. Recently, collaborative frameworks such as the Multi-LLM Network (MultiLLMN) have been introduced, enabling multiple LLMs to interact and jointly respond to user queries. Nevertheless, MultiLLMN architectures raise critical concerns regarding the reliability and security of the generated content, particularly in open environments where malicious or compromised LLMs may be present. Moreover, reliance on centralized coordination undermines system efficiency and introduces single points of failure. In this paper, we propose a novel Trusted MultiLLMN framework, driven by a Weighted Byzantine Fault Tolerance (WBFT) blockchain consensus mechanism, to ensure the reliability, security, and efficiency of multi-LLM collaboration. In WBFT, voting weights are adaptively assigned to each LLM based on its response quality and trustworthiness, incentivizing reliable behavior, and reducing the impact of malicious nodes. Extensive simulations demonstrate that WBFT significantly improves both consensus security and efficiency compared to classical and modern consensus mechanisms, particularly under wireless network conditions. Furthermore, our evaluations reveal that Trusted MultiLLMN supported by WBFT can deliver higher-quality and more credible responses than both single LLMs and conventional MultiLLMNs, thereby providing a promising path toward building robust, decentralized AI collaboration networks. △ Less

Submitted 8 May, 2025; originally announced May 2025.

A Trustworthy Multi-LLM Network: Challenges,Solutions, and A Use Case

Authors: Haoxiang Luo, Gang Sun, Yinqiu Liu, Dusit Niyato, Hongfang Yu, Mohammed Atiquzzaman, Schahram Dustdar

Abstract: Large Language Models (LLMs) demonstrate strong potential across a variety of tasks in communications and networking due to their advanced reasoning capabilities. However, because different LLMs have different model structures and are trained using distinct corpora and methods, they may offer varying optimization strategies for the same network issues. Moreover, the limitations of an individual LL… ▽ More Large Language Models (LLMs) demonstrate strong potential across a variety of tasks in communications and networking due to their advanced reasoning capabilities. However, because different LLMs have different model structures and are trained using distinct corpora and methods, they may offer varying optimization strategies for the same network issues. Moreover, the limitations of an individual LLM's training data, aggravated by the potential maliciousness of its hosting device, can result in responses with low confidence or even bias. To address these challenges, we propose a blockchain-enabled collaborative framework that connects multiple LLMs into a Trustworthy Multi-LLM Network (MultiLLMN). This architecture enables the cooperative evaluation and selection of the most reliable and high-quality responses to complex network optimization problems. Specifically, we begin by reviewing related work and highlighting the limitations of existing LLMs in collaboration and trust, emphasizing the need for trustworthiness in LLM-based systems. We then introduce the workflow and design of the proposed Trustworthy MultiLLMN framework. Given the severity of False Base Station (FBS) attacks in B5G and 6G communication systems and the difficulty of addressing such threats through traditional modeling techniques, we present FBS defense as a case study to empirically validate the effectiveness of our approach. Finally, we outline promising future research directions in this emerging area. △ Less

Submitted 6 May, 2025; originally announced May 2025.

UserCentrix: An Agentic Memory-augmented AI Framework for Smart Spaces

Authors: Alaa Saleh, Sasu Tarkoma, Praveen Kumar Donta, Anders Lindgren, Naser Hossein Motlagh, Schahram Dustdar, Susanna Pirttikangas, Lauri Lovén

Abstract: Agentic Artificial Intelligence (AI) constitutes a transformative paradigm in the evolution of intelligent agents and decision-support systems, redefining smart environments by enhancing operational efficiency, optimizing resource allocation, and strengthening systemic resilience. This paper presents UserCentrix, a hybrid agentic orchestration framework for smart spaces that optimizes resource man… ▽ More Agentic Artificial Intelligence (AI) constitutes a transformative paradigm in the evolution of intelligent agents and decision-support systems, redefining smart environments by enhancing operational efficiency, optimizing resource allocation, and strengthening systemic resilience. This paper presents UserCentrix, a hybrid agentic orchestration framework for smart spaces that optimizes resource management and enhances user experience through urgency-aware and intent-driven decision-making mechanisms. The framework integrates interactive modules equipped with agentic behavior and autonomous decision-making capabilities to dynamically balance latency, accuracy, and computational cost. User intent functions as a governing control signal that prioritizes decisions, regulates task execution and resource allocation, and guides the adaptation of decision-making strategies to balance trade-offs between speed and accuracy. Experimental results demonstrate that the framework autonomously enables efficient intent processing and real-time monitoring, while balancing reasoning quality and computational efficiency, particularly under resource-constrained edge conditions. △ Less

Submitted 6 April, 2026; v1 submitted 1 May, 2025; originally announced May 2025.

Formal and Empirical Study of Metadata-Based Profiling for Resource Management in the Computing Continuum

Authors: Andrea Morichetta, Stefan Nastic, Victor Casamayor Pujol, Schahram Dustdar

Abstract: We present and formalize a general approach for profiling workload by leveraging only a priori available static metadata to supply appropriate resource needs. Understanding the requirements and characteristics of a workload's runtime is essential. Profiles are essential for the platform (or infrastructure) provider because they want to ensure that Service Level Agreements and their objectives (SLO… ▽ More We present and formalize a general approach for profiling workload by leveraging only a priori available static metadata to supply appropriate resource needs. Understanding the requirements and characteristics of a workload's runtime is essential. Profiles are essential for the platform (or infrastructure) provider because they want to ensure that Service Level Agreements and their objectives (SLOs) are fulfilled and, at the same time, avoid allocating too many resources to the workload. When the infrastructure to manage is the computing continuum (i.e., from IoT to Edge to Cloud nodes), there is a big problem of placement and tradeoff or distribution and performance. Still, existing techniques either rely on static predictions or runtime profiling, which are proven to deliver poor performance in runtime environments or require laborious mechanisms to produce fast and reliable evaluations. We want to propose a new approach for it. Our profile combines the information from past execution traces with the related workload metadata, equipping an infrastructure orchestrator with a fast and precise association of newly submitted workloads. We differentiate from previous works because we extract the profile group metadata saliency from the groups generated by grouping similar runtime behavior. We first formalize its functioning and its main components. Subsequently, we implement and empirically analyze our proposed technique on two public data sources: Alibaba cloud machine learning workloads and Google cluster data. Despite relying on partially anonymized or obscured information, the approach provides accurate estimates of workload runtime behavior in real-time. △ Less

Submitted 29 April, 2025; originally announced April 2025.

Comments: Submitted to ACM TOIT. Under R2 revision

Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems

Authors: Alireza Furutanpey, Carmen Walser, Philipp Raith, Pantelis A. Frangoudis, Schahram Dustdar

Abstract: This work presents a comprehensive evaluation of neural network graph compilers across heterogeneous hardware platforms, addressing the critical gap between theoretical optimization techniques and practical deployment scenarios. We demonstrate how vendor-specific optimizations can invalidate relative performance comparisons between architectural archetypes, with performance advantages sometimes co… ▽ More This work presents a comprehensive evaluation of neural network graph compilers across heterogeneous hardware platforms, addressing the critical gap between theoretical optimization techniques and practical deployment scenarios. We demonstrate how vendor-specific optimizations can invalidate relative performance comparisons between architectural archetypes, with performance advantages sometimes completely reversing after compilation. Our systematic analysis reveals that graph compilers exhibit performance patterns highly dependent on both neural architecture and batch sizes. Through fine-grained block-level experimentation, we establish that vendor-specific compilers can leverage repeated patterns in simple architectures, yielding disproportionate throughput gains as model depth increases. We introduce novel metrics to quantify a compiler's ability to mitigate performance friction as batch size increases. Our methodology bridges the gap between academic research and practical deployment by incorporating compiler effects throughout the research process, providing actionable insights for practitioners navigating complex optimization landscapes across heterogeneous hardware environments. △ Less

Submitted 7 July, 2026; v1 submitted 28 April, 2025; originally announced April 2025.

Comments: Accepted for publication in IEEE Transactions on Parallel and Distributed Systems

Towards Multi-dimensional Elasticity for Pervasive Stream Processing Services

Authors: Boris Sedlak, Andrea Morichetta, Philipp Raith, Víctor Casamayor Pujol, Schahram Dustdar

Abstract: This paper proposes a hierarchical solution to scale streaming services across quality and resource dimensions. Modern scenarios, like smart cities, heavily rely on the continuous processing of IoT data to provide real-time services and meet application targets (Service Level Objectives -- SLOs). While the tendency is to process data at nearby Edge devices, this creates a bottleneck because resour… ▽ More This paper proposes a hierarchical solution to scale streaming services across quality and resource dimensions. Modern scenarios, like smart cities, heavily rely on the continuous processing of IoT data to provide real-time services and meet application targets (Service Level Objectives -- SLOs). While the tendency is to process data at nearby Edge devices, this creates a bottleneck because resources can only be provisioned up to a limited capacity. To improve elasticity in Edge environments, we propose to scale services in multiple dimensions -- either resources or, alternatively, the service quality. We rely on a two-layer architecture where (1) local, service-specific agents ensure SLO fulfillment through multi-dimensional elasticity strategies; if no more resources can be allocated, (2) a higher-level agent optimizes global SLO fulfillment by swapping resources. The experimental results show promising outcomes, outperforming regular vertical autoscalers, when operating under tight resource constraints. △ Less

Submitted 6 March, 2025; originally announced March 2025.

Comments: Accepted for publication at Percom 2025 as Work in Progress (WIP)

Benchmarking Dynamic SLO Compliance in Distributed Computing Continuum Systems

Authors: Alfreds Lapkovskis, Boris Sedlak, Sindri Magnússon, Schahram Dustdar, Praveen Kumar Donta

Abstract: Ensuring Service Level Objectives (SLOs) in large-scale architectures, such as Distributed Computing Continuum Systems (DCCS), is challenging due to their heterogeneous nature and varying service requirements across different devices and applications. Additionally, unpredictable workloads and resource limitations lead to fluctuating performance and violated SLOs. To improve SLO compliance in DCCS,… ▽ More Ensuring Service Level Objectives (SLOs) in large-scale architectures, such as Distributed Computing Continuum Systems (DCCS), is challenging due to their heterogeneous nature and varying service requirements across different devices and applications. Additionally, unpredictable workloads and resource limitations lead to fluctuating performance and violated SLOs. To improve SLO compliance in DCCS, one possibility is to apply machine learning; however, the design choices are often left to the developer. To that extent, we provide a benchmark of Active Inference -- an emerging method from neuroscience -- against three established reinforcement learning algorithms (Deep Q-Network, Advantage Actor-Critic, and Proximal Policy Optimization). We consider a realistic DCCS use case: an edge device running a video conferencing application alongside a WebSocket server streaming videos. Using one of the respective algorithms, we continuously monitor key performance metrics, such as latency and bandwidth usage, to dynamically adjust parameters -- including the number of streams, frame rate, and resolution -- to optimize service quality and user experience. To test algorithms' adaptability to constant system changes, we simulate dynamically changing SLOs and both instant and gradual data-shift scenarios, such as network bandwidth limitations and fluctuating device thermal states. Although the evaluated algorithms all showed advantages and limitations, our findings demonstrate that Active Inference is a promising approach for ensuring SLO compliance in DCCS, offering lower memory usage, stable CPU utilization, and fast convergence. △ Less

Submitted 5 March, 2025; originally announced March 2025.

A Multidimensional Elasticity Framework for Adaptive Data Analytics Management in the Computing Continuum

Authors: Sergio Laso, Ilir Murturi, Pantelis Frangoudis, Juan Luis Herrera, Juan M. Murillo, Schahram Dustdar

Abstract: The increasing complexity of IoT applications and the continuous growth in data generated by connected devices have led to significant challenges in managing resources and meeting performance requirements in computing continuum architectures. Traditional cloud solutions struggle to handle the dynamic nature of these environments, where both infrastructure demands and data analytics requirements ca… ▽ More The increasing complexity of IoT applications and the continuous growth in data generated by connected devices have led to significant challenges in managing resources and meeting performance requirements in computing continuum architectures. Traditional cloud solutions struggle to handle the dynamic nature of these environments, where both infrastructure demands and data analytics requirements can fluctuate rapidly. As a result, there is a need for more adaptable and intelligent resource management solutions that can respond to these changes in real-time. This paper introduces a framework based on multi-dimensional elasticity, which enables the adaptive management of both infrastructure resources and data analytics requirements. The framework leverages an orchestrator capable of dynamically adjusting architecture resources such as CPU, memory, or bandwidth and modulating data analytics requirements, including coverage, sample, and freshness. The framework has been evaluated, demonstrating the impact of varying data analytics requirements on system performance and the orchestrator's effectiveness in maintaining a balanced and optimized system, ensuring efficient operation across edge and head nodes. △ Less

Submitted 20 January, 2025; originally announced January 2025.

Adversarial Robustness of Bottleneck Injected Deep Neural Networks for Task-Oriented Communication

Authors: Alireza Furutanpey, Pantelis A. Frangoudis, Patrik Szabo, Schahram Dustdar

Abstract: This paper investigates the adversarial robustness of Deep Neural Networks (DNNs) using Information Bottleneck (IB) objectives for task-oriented communication systems. We empirically demonstrate that while IB-based approaches provide baseline resilience against attacks targeting downstream tasks, the reliance on generative models for task-oriented communication introduces new vulnerabilities. Thro… ▽ More This paper investigates the adversarial robustness of Deep Neural Networks (DNNs) using Information Bottleneck (IB) objectives for task-oriented communication systems. We empirically demonstrate that while IB-based approaches provide baseline resilience against attacks targeting downstream tasks, the reliance on generative models for task-oriented communication introduces new vulnerabilities. Through extensive experiments on several datasets, we analyze how bottleneck depth and task complexity influence adversarial robustness. Our key findings show that Shallow Variational Bottleneck Injection (SVBI) provides less adversarial robustness compared to Deep Variational Information Bottleneck (DVIB) approaches, with the gap widening for more complex tasks. Additionally, we reveal that IB-based objectives exhibit stronger robustness against attacks focusing on salient pixels with high intensity compared to those perturbing many pixels with lower intensity. Lastly, we demonstrate that task-oriented communication systems that rely on generative models to extract and recover salient information have an increased attack surface. The results highlight important security considerations for next-generation communication systems that leverage neural networks for goal-oriented compression. △ Less

Submitted 13 December, 2024; originally announced December 2024.

Comments: Submission to ICMLCN, 6 pages, 9 figures, 3 tables

DRDST: Low-latency DAG Consensus through Robust Dynamic Sharding and Tree-broadcasting for IoV

Authors: Runhua Chen, Haoxiang Luo, Gang Sun, Hongfang Yu, Dusit Niyato, Schahram Dustdar

Abstract: The Internet of Vehicles (IoV) is emerging as a pivotal technology for enhancing traffic management and safety. Its rapid development demands solutions for enhanced communication efficiency and reduced latency. However, traditional centralized networks struggle to meet these demands, prompting the exploration of decentralized solutions such as blockchain. Addressing blockchain's scalability challe… ▽ More The Internet of Vehicles (IoV) is emerging as a pivotal technology for enhancing traffic management and safety. Its rapid development demands solutions for enhanced communication efficiency and reduced latency. However, traditional centralized networks struggle to meet these demands, prompting the exploration of decentralized solutions such as blockchain. Addressing blockchain's scalability challenges posed by the growing number of nodes and transactions calls for innovative solutions, among which sharding stands out as a pivotal approach to significantly enhance blockchain throughput. However, existing schemes still face challenges related to a) the impact of vehicle mobility on blockchain consensus, especially for cross-shard transaction; and b) the strict requirements of low latency consensus in a highly dynamic network. In this paper, we propose a DAG (Directed Acyclic Graph) consensus leveraging Robust Dynamic Sharding and Tree-broadcasting (DRDST) to address these challenges. Specifically, we first develop a standard for evaluating the network stability of nodes, combined with the nodes' trust values, to propose a novel robust sharding model that is solved through the design of the Genetic Sharding Algorithm (GSA). Then, we optimize the broadcast latency of the whole sharded network by improving the tree-broadcasting to minimize the maximum broadcast latency within each shard. On this basis, we also design a DAG consensus scheme based on an improved hashgraph protocol, which can efficiently handle cross-shard transactions. Finally, the simulation proves the proposed scheme is superior to the comparison schemes in latency, throughput, consensus success rate, and node traffic load. △ Less

Submitted 5 December, 2024; originally announced December 2024.

Reactive Orchestration for Hierarchical Federated Learning Under a Communication Cost Budget

Authors: Ivan Čilić, Anna Lackinger, Pantelis Frangoudis, Ivana Podnar Žarko, Alireza Furutanpey, Ilir Murturi, Schahram Dustdar

Abstract: Deploying a Hierarchical Federated Learning (HFL) pipeline across the computing continuum (CC) requires careful organization of participants into a hierarchical structure with intermediate aggregation nodes between FL clients and the global FL server. This is challenging to achieve due to (i) cost constraints, (ii) varying data distributions, and (iii) the volatile operating environment of the CC.… ▽ More Deploying a Hierarchical Federated Learning (HFL) pipeline across the computing continuum (CC) requires careful organization of participants into a hierarchical structure with intermediate aggregation nodes between FL clients and the global FL server. This is challenging to achieve due to (i) cost constraints, (ii) varying data distributions, and (iii) the volatile operating environment of the CC. In response to these challenges, we present a framework for the adaptive orchestration of HFL pipelines, designed to be reactive to client churn and infrastructure-level events, while balancing communication cost and ML model accuracy. Our mechanisms identify and react to events that cause HFL reconfiguration actions at runtime, building on multi-level monitoring information (model accuracy, resource availability, resource cost). Moreover, our framework introduces a generic methodology for estimating reconfiguration costs to continuously re-evaluate the quality of adaptation actions, while being extensible to optimize for various HFL performance criteria. By extending the Kubernetes ecosystem, our framework demonstrates the ability to react promptly and effectively to changes in the operating environment, making the best of the available communication cost budget and effectively balancing costs and ML performance at runtime. △ Less

Submitted 28 April, 2025; v1 submitted 4 December, 2024; originally announced December 2024.

A Hybrid BPMN-DMN Framework for Secure Inter-organizational Processes and Decisions Collaboration on Permissioned Blockchain

Authors: Xinzhe Shen, Jiale Luo, Hao Wang, Mingyi Liu, Schahram Dustdar, Zhongjie Wang

Abstract: In the rapidly evolving digital business landscape, organizations increasingly need to collaborate across boundaries to achieve complex business objectives, requiring both efficient process coordination and flexible decision-making capabilities. Traditional collaboration approaches face significant challenges in transparency, trust, and decision flexibility, while existing blockchain-based solutio… ▽ More In the rapidly evolving digital business landscape, organizations increasingly need to collaborate across boundaries to achieve complex business objectives, requiring both efficient process coordination and flexible decision-making capabilities. Traditional collaboration approaches face significant challenges in transparency, trust, and decision flexibility, while existing blockchain-based solutions primarily focus on process execution without addressing the integrated decision-making needs of collaborative enterprises. This paper proposes BlockCollab, a novel model-driven framework that seamlessly integrates Business Process Model and Notation (BPMN) with Decision Model and Notation (DMN) to standardize and implement collaborative business processes and decisions on permissioned blockchain platforms. Our approach automatically translates integrated BPMN-DMN models into smart contracts(SCs) compatible with Hyperledger Fabric, enabling privacy-aware multi-organizational process execution through blockchain-based Attribute-Based Access Control (ABAC). The framework introduces three key innovations: (1) a standardized method for modeling collaborative processes and decisions using integrated BPMN-DMN model, (2) an automated SC generator that preserves both process logic and decision rules while maintaining privacy constraints, and (3) a hybrid on-chain/off-chain execution environment that optimizes collaborative workflows through secure data transfer and external system integration. Experimental evaluation across 11 real-world collaboration scenarios demonstrates that our approach achieves 100\% accuracy in process execution. Furthermore, an analysis of various execution processes highlights the strong practical applicability and reliability of our approach. The proposed framework includes an open-source third-party collaboration platform based on blockchain. △ Less

Submitted 2 December, 2024; originally announced December 2024.

Comments: 16 pages

RainCloud: Decentralized Coordination and Communication in Heterogeneous IoT Swarms

Authors: Filip Loisel, Geri Zeqo, Andrea Morichetta, Anna Lackinger, Schahram Dustdar

Abstract: The increasing volume and complexity of IoT systems demand a transition from the cloud-centric model to a decentralized IoT architecture in the so-called Computing Continuum, with no or minimal reliance on central servers. This paradigm shift, however, raises novel research concerns for decentralized coordination, calling for accurate policies. However, building such strategies is not trivial. Our… ▽ More The increasing volume and complexity of IoT systems demand a transition from the cloud-centric model to a decentralized IoT architecture in the so-called Computing Continuum, with no or minimal reliance on central servers. This paradigm shift, however, raises novel research concerns for decentralized coordination, calling for accurate policies. However, building such strategies is not trivial. Our work aims to relieve the DevOps engineers from this concern and propose a solution for autonomous, decentralized task allocation at runtime for IoT systems. To this end, we present a semantic communication approach and an ad-hoc lightweight coordination strategy based on Ant Colony Optimization (ACO). We compare the ACO strategy with Random Search and Gossip protocol-based algorithms. We conduct accurate experiments with up to a hundred nodes in both a static and a dynamic environment, i.e., with device outages. We show that ACO finds a matching node with the smallest hops and messages sent. While the Gossip strategy can allocate the most tasks successfully, ACO scales better, thus being a promising candidate for decentralized task coordination in IoT clusters. △ Less

Submitted 7 November, 2024; originally announced November 2024.