arXiv subjects

Reza Farahani

Publications and source records attributed to Reza Farahani.

At least 19 recordsLinked to original sources

arXiv2026

Can We Rely on Language Models to Orchestrate Services across the Edge-Cloud Continuum?

Service orchestration across the edge--cloud continuum increasingly uses language models (LMs) to translate intents and operational evidence into scheduling, configuration, diagnosis, and remediation decisions. Yet, useful model outputs do not by themselves establish dependable orchestration: reliability also depends on where the LM enters the decision process, what authority it is granted, how actions are constrained, and what system-level evidence supports the claimed effect. Existing surveys provide limited synthesis of the links between continuum-specific orchestration decisions, LM responsibility, operational authority, assurance controls, and supporting empirical evidence. We systematically review 39 primary studies and develop a five-dimensional analytical framework for connecting system context, orchestration decisions, LM agency, operational safeguards, and evaluation evidence. The synthesis reveals predominantly hybrid designs in which LMs support interpretation, candidate generation, and mitigation planning, while downstream components commonly retain feasibility enforcement and execution authority. Bounded closed-loop remediation is emerging, but continuum-specific constraints remain unevenly represented in decision formulations, and production-scale evidence across heterogeneous edge--cloud environments remains limited. These findings suggest that reliance on LM-enabled orchestration depends on aligning decision constraints, operational authority, safeguards, and evaluation evidence with the claimed system effect.

cs.DC↗

arXiv2026

Agentic Service Markets Across the Computing Continuum: A Polymatroidal Architecture

Autonomous AI agents are becoming economic actors. They compose deadline-bound services across the device-edge-cloud continuum and contend for capacity no single operator owns. This article asks when decentralised pricing can coordinate them exactly and truthfully, and what their service dependencies must satisfy. We model the pipelines as service-dependency graphs under governance constraints and identify the decisive property: laminarity of the induced leaf-block family. Where it holds, the feasible allocation space is a polymatroid and efficient incentive-compatible clearing exists per epoch; where a crossing breaks it, exactness and truthfulness can fail, while clearing prices survive on every totally unimodular family. The formal results instantiate polymatroid, gross-substitutes and Vickrey-Clarke-Groves theory; the contribution is the bridge from dependency structure to that machinery and an integrator architecture that exposes a laminar interface. The node-level evaluation (32,020 runs), at testbed-calibrated congestion, locates the boundary. One crossing costs exactness in 14.7% of high-load rounds and none on laminar instances, and truthfulness fails where exactness does, across contention. An integrator's inner exposure restores exactness at a cost in admitted volume, and before translation overhead it cuts median latency by 16 to 17 percent. Against truth-free posted prices the tuned market leads at medium load and trails a demand-responsive one in four of six high-load cells. Recorded and composed agent workloads drive the allocation. For platform designers, laminar pipelines admit exact decentralised pricing, truthful under the VCG mechanism, and a crossing needs an integrator's inner exposure.

cs.AI↗

arXiv2026

Cloud, Edge, or Split? Profiling Onboard and Split Vision-Language Model Deployment for Drone AI

Vision-Language Models (VLMs) enable edge devices like unmanned aerial vehicles (UAVs) to interpret visual observations and reason about complex environments using natural-language instructions. However, their practical deployment remains challenging as onboard inference is constrained by limited computational, memory, and energy resources, whereas cloud-based inference introduces communication latency, bandwidth overhead, and dependence on network connectivity. To address these limitations, split computing offers a promising alternative by partitioning VLM inference between the resource-constrained UAVs and more capable remote servers. However, the performance trade-offs among fully onboard, cloud-based, and split-computing architectures for lightweight VLMs have not yet been systematically profiled. This paper benchmarks these three deployment paradigms using SmolVLM-256M as a representative lightweight VLM. We quantify their inference latency, computational resource utilization, communication overhead, and energy consumption across varying image resolutions and network conditions. Our results show that no deployment strategy is universally optimal; instead, the preferred strategy depends on the interaction between network conditions and input image resolution.

cs.DC↗

arXiv2026

From Pixels to Semantics: Edge AI for UAV-Based Critical Infrastructure Inspection

Critical infrastructure assets such as bridges, tunnels, dams, and power line networks require timely and scalable inspection. While conventional manual inspection remains costly and hazardous, unmanned aerial vehicle (UAV)-based inspection has emerged as an efficient alternative for monitoring difficult-to-access structures. Existing UAV inspection pipelines have evolved from cloud-centric offline processing toward edge-based perception using lightweight object detectors such as YOLO for real- time defect localization. This article explores the transition toward fully edge-native semantic inspection powered by lightweight vision language models (VLMs), where UAVs move beyond object detection toward contextual structural understanding. It categorizes existing UAV inspection architectures, identifies their key system challenges and architectural requirements, and experimentally assesses the feasibility of semantic edge intelligence on NVIDIA Jetson UAV-class hardware using the COCO-Bridge dataset. The evaluation integrates a fine-tuned YOLO-26M for object localization and a lightweight SmolVLM-256 for semantic reasoning. Finally, it outlines future directions toward agentic, autonomous, trustworthy, and collaborative semantic UAV inspection across the edge-cloud continuum.

cs.DC↗

arXiv2026

DRLM: Deep Reinforcement Learning-Based LLM Query Orchestration in Edge Environments

Large language model (LLM) services increasingly process heterogeneous queries with diverse latency, accuracy, and resource requirements. While edge deployment reduces response time, the heterogeneity of devices and the diversity of model families, parameter scales, and quantization levels make efficient LLM query orchestration challenging. This paper introduces DRLM, a Deep Reinforcement Learning-based LLM query orchestration framework in edge environments. DRLM integrates two lightweight predictors: (i) a class-conditioned quality estimator that maps queries to semantic categories and infers model performance, and (ii) a feature-driven latency predictor that estimates inference time across model-device configurations. These predictions, combined with system state, feed a factorized Proximal Policy Optimization (PPO) agent that performs state-aware orchestration decisions. To enable data-driven orchestration, we construct a large-scale benchmarking dataset with 223 835 measurements spanning 1258 queries, 6 query classes, 8 model families (32 deployed instances), 5 quantization levels, and heterogeneous edge devices. Evaluation on a 64-node edge cluster and comparison with three baselines and two state-of-the-art methods show that DRLM reduces inference latency by up to 51% and queuing delay by up to 67 %, while incurring at most 8% accuracy loss. It improves latency under increasing workloads up to 61.4%, demonstrating robust and stable orchestration.

cs.DC↗

arXiv2026

LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters

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.

cs.DC↗

arXiv2026

Scale: Deep Reinforcement Learning for Container Scheduling in Serverless Edge Computing

Serverless computing has emerged as a promising computing paradigm for edge computing. However, adopting the event driven model in highly dynamic, heterogeneous, and distributed edge systems poses significant challenges in request placement and resource management. Efficiently allocating requests to containers is therefore critical to reduce resource over provisioning and unnecessary data movement. This paper proposes Scale, a Service Level Objective aware container scheduling and resource allocation framework designed for serverless edge computing. Scale employs a policy based deep reinforcement learning algorithm to balance system stability and performance under dynamic workloads. The design jointly incorporates SLO constraints, end to end latency, and data locality into the scheduling decision process. Extensive simulations using large scale real world datasets from Huawei Cloud demonstrate that Scale achieves solutions within a factor of 1.11 to 1.15 of a state of the art Integer Linear Programming solver, while reducing decision making time by up to 99%.

cs.DC↗

arXiv2026

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

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.

cs.DC↗

arXiv2026

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

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.

cs.DC↗

arXiv2026

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

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.

eess.IV↗

arXiv2026

ELLMPEG: An Edge-based Agentic LLM Video Processing Tool

Large language models (LLMs), the foundation of generative AI systems like ChatGPT, are transforming many fields and applications, including multimedia, enabling more advanced content generation, analysis, and interaction. However, cloud-based LLM deployments face three key limitations: high computational and energy demands, privacy and reliability risks from remote processing, and recurring API costs. Recent advances in agentic AI, especially in structured reasoning and tool use, offer a better way to exploit open and locally deployed tools and LLMs. This paper presents ELLMPEG, an edge-enabled agentic LLM framework for the automated generation of video-processing commands. ELLMPEG integrates tool-aware Retrieval-Augmented Generation (RAG) with iterative self-reflection to produce and locally verify executable FFmpeg and VVenC commands directly at the edge, eliminating reliance on external cloud APIs. To evaluate ELLMPEG, we collect a dedicated prompt dataset comprising 480 diverse queries covering different categories of FFmpeg and the Versatile Video Codec (VVC) encoder (VVenC) commands. We validate command generation accuracy and evaluate four open-source LLMs based on command validity, tokens generated per second, inference time, and energy efficiency. We also execute the generated commands to assess their runtime correctness and practical applicability. Experimental results show that Qwen2.5, when augmented with the ELLMPEG framework, achieves an average command-generation accuracy of 78 % with zero recurring API cost, outperforming all other open-source models across both the FFmpeg and VVenC datasets.

cs.LG↗

arXiv2025

Osmotic Learning: A Self-Supervised Paradigm for Decentralized Contextual Data Representation

Data within a specific context gains deeper significance beyond its isolated interpretation. In distributed systems, interdependent data sources reveal hidden relationships and latent structures, representing valuable information for many applications. This paper introduces Osmotic Learning (OSM-L), a self-supervised distributed learning paradigm designed to uncover higher-level latent knowledge from distributed data. The core of OSM-L is osmosis, a process that synthesizes dense and compact representation by extracting contextual information, eliminating the need for raw data exchange between distributed entities. OSM-L iteratively aligns local data representations, enabling information diffusion and convergence into a dynamic equilibrium that captures contextual patterns. During training, it also identifies correlated data groups, functioning as a decentralized clustering mechanism. Experimental results confirm OSM-L's convergence and representation capabilities on structured datasets, achieving over 0.99 accuracy in local information alignment while preserving contextual integrity.

cs.LG↗

arXiv2025

Predicting Encoding Energy from Low-Pass Anchors for Green Video Streaming

Video streaming now represents the dominant share of Internet traffic, as ever-higher-resolution content is distributed across a growing range of heterogeneous devices to sustain user Quality of Experience (QoE). However, this trend raises significant concerns about energy efficiency and carbon emissions, requiring methods to provide a trade-off between energy and QoE. This paper proposes a lightweight energy prediction method that estimates the energy consumption of high-resolution video encodings using reference encodings generated at lower resolutions (so-called anchors), eliminating the need for exhaustive per-segment energy measurements, a process that is infeasible at scale. We automatically select encoding parameters, such as resolution and quantization parameter (QP), to achieve substantial energy savings while maintaining perceptual quality, as measured by the Video Multimethod Fusion Assessment (VMAF), within acceptable limits. We implement and evaluate our approach with the open-source VVenC encoder on 100 video sequences from the Inter4K dataset across multiple encoding settings. Results show that, for an average VMAF score reduction of only 1.68, which stays below the Just Noticeable Difference (JND) threshold, our method achieves 51.22% encoding energy savings and 53.54% decoding energy savings compared to a scenario with no quality degradation.

cs.MM↗

arXiv2025

Toward Sustainability-Aware LLM Inference on Edge Clusters

Large language models (LLMs) require substantial computational resources, leading to significant carbon emissions and operational costs. Although training is energy-intensive, the long-term environmental burden arises from inference, amplified by the massive global query volume. Cloud-based inference offers scalability but suffers from latency and bandwidth constraints due to centralized processing and continuous data transfer. Edge clusters instead can mitigate these limitations by enabling localized execution, yet they face trade-offs between performance, energy efficiency, and device constraints. This short paper presents a sustainability-aware LLM inference for edge clusters comprising NVIDIA Jetson Orin NX (8GB) and Nvidia Ada 2000 (16GB) devices. It aims to balance inference latency and carbon footprint through carbon- and latency-aware routing strategies, guided by empirical benchmarking of energy consumption and execution time across diverse prompts and batch (i.e., group of prompts) configurations. We compared baseline greedy strategies to carbon-aware and latency-aware strategies in prompt routing to specific hardware based on benchmarking information. Experimental evaluation shows that a batch size of four prompts achieves a trade-off between throughput, energy efficiency, while larger batches risk GPU memory saturation.

cs.DC↗

arXiv2025

Serverless Everywhere: A Comparative Analysis of WebAssembly Workflows Across Browser, Edge, and Cloud

WebAssembly (Wasm) is a binary instruction format that enables portable, sandboxed, and near-native execution across heterogeneous platforms, making it well-suited for serverless workflow execution on browsers, edge nodes, and cloud servers. However, its performance and stability depend heavily on factors such as startup overhead, runtime execution model (e.g., Ahead-of-Time (AOT) and Just-in-Time (JIT) compilation), and resource variability across deployment contexts. This paper evaluates a Wasm-based serverless workflow executed consistently from the browser to edge and cloud instances. The setup uses wasm32-wasi modules: in the browser, execution occurs within a web worker, while on Edge and Cloud, an HTTP shim streams frames to the Wasm runtime. We measure cold- and warm-start latency, per-step delays, workflow makespan, throughput, and CPU/memory utilization to capture the end-to-end behavior across environments. Results show that AOT compilation and instance warming substantially reduce startup latency. For workflows with small payloads, the browser achieves competitive performance owing to fully in-memory data exchanges. In contrast, as payloads grow, the workflow transitions into a compute- and memory-intensive phase where AOT execution on edge and cloud nodes distinctly surpasses browser performance.

cs.DC↗

arXiv2025

DEEP: Edge-based Dataflow Processing with Hybrid Docker Hub and Regional Registries

Reducing energy consumption is essential to lessen greenhouse gas emissions, conserve natural resources, and help mitigate the impacts of climate change. In this direction, edge computing, a complementary technology to cloud computing, extends computational capabilities closer to the data producers, enabling energy-efficient and latency-sensitive service delivery for end users. To properly manage data and microservice storage, expanding the Docker Hub registry to the edge using an AWS S3-compatible MinIO-based object storage service can reduce completion time and energy consumption. To address this, we introduce Docker rEgistry-based Edge dataflow Processing (DEEP) to optimize the energy consumption of microservice-based application deployments by focusing on deployments from Docker Hub and MinIO-based regional registries and their processing on edge devices. After applying nash equilibrium and benchmarking the execution of two compute-intensive machine learning (ML) applications of video and text processing, we compare energy consumption across three deployment scenarios: exclusively from Docker Hub, exclusively from the regional registry, and a hybrid method utilizing both. Experimental results show that deploying 83% of text processing microservices from the regional registry improves the energy consumption by 0.34% (18J) compared to microservice deployments exclusively from Docker Hub.

cs.DC↗

arXiv2024

Towards AI-Assisted Sustainable Adaptive Video Streaming Systems: Tutorial and Survey

Improvements in networking technologies and the steadily increasing numbers of users, as well as the shift from traditional broadcasting to streaming content over the Internet, have made video applications (e.g., live and Video-on-Demand (VoD)) predominant sources of traffic. Recent advances in Artificial Intelligence (AI) and its widespread application in various academic and industrial fields have focused on designing and implementing a variety of video compression and content delivery techniques to improve user Quality of Experience (QoE). However, providing high QoE services results in more energy consumption and carbon footprint across the service delivery path, extending from the end user's device through the network and service infrastructure (e.g., cloud providers). Despite the importance of energy efficiency in video streaming, there is a lack of comprehensive surveys covering state-of-the-art AI techniques and their applications throughout the video streaming lifecycle. Existing surveys typically focus on specific parts, such as video encoding, delivery networks, playback, or quality assessment, without providing a holistic view of the entire lifecycle and its impact on energy consumption and QoE. Motivated by this research gap, this survey provides a comprehensive overview of the video streaming lifecycle, content delivery, energy and Video Quality Assessment (VQA) metrics and models, and AI techniques employed in video streaming. In addition, it conducts an in-depth state-of-the-art analysis focused on AI-driven approaches to enhance the energy efficiency of end-to-end aspects of video streaming systems (i.e., encoding, delivery network, playback, and VQA approaches). Finally, it discusses prospective research directions for developing AI-assisted energy-aware video streaming systems.

cs.MM↗

arXiv2024

Network-Assisted Delivery of Adaptive Video Streaming Services through CDN, SDN, and MEC

Multimedia applications, mainly video streaming services, are currently the dominant source of network load worldwide. In recent Video-on-Demand (VoD) and live video streaming services, traditional streaming delivery techniques have been replaced by adaptive solutions based on the HTTP protocol. Current trends toward high-resolution (e.g., 8K) and/or low-latency VoD and live video streaming pose new challenges to end-to-end (E2E) bandwidth demand and have stringent delay requirements. To do this, video providers typically rely on Content Delivery Networks (CDNs) to ensure that they provide scalable video streaming services. To support future streaming scenarios involving millions of users, it is necessary to increase the CDNs' efficiency. It is widely agreed that these requirements may be satisfied by adopting emerging networking techniques to present Network-Assisted Video Streaming (NAVS) methods. Motivated by this, this thesis goes one step beyond traditional pure client-based HAS algorithms by incorporating (an) in-network component(s) with a broader view of the network to present completely transparent NAVS solutions for HAS clients.

cs.MM↗