Jul 2026· Journal of Sensor and Actuator Networks· Vol 15, pp. 56· 0 citations· 25 references
TL;DR
A joint communication–computation optimization (JCCO) framework for energy-efficient resource allocation in edge-assisted swarm robotics that achieves improved fairness, lower communication overhead, and efficient embedded deployment suitability for TinyML-enabled robotic platforms.
Abstract
This paper presents a joint communication–computation optimization (JCCO) framework for energy-efficient resource allocation in edge-assisted swarm robotics. The proposed framework jointly optimizes task offloading, bandwidth allocation, transmission power, and computational workload under latency and energy constraints. A distributed optimization strategy combined with a lightweight deep reinforcement learning controller enables adaptive and scalable decision making for resource-constrained robotic swarms. The simulation results demonstrate that the proposed method reduces the total swarm energy consumption by up to 41% while maintaining more than 99% deadline satisfaction across varying swarm sizes and communication conditions. The framework further achieves improved fairness, lower communication overhead, and efficient embedded deployment suitability for TinyML-enabled robotic platforms.
Energy-efficient coordination of robotic swarms requires effective integration of task scheduling, motion planning, and communication management, particularly in resource-constrained environments where computation and wireless communication compete for limited energy resources. Existing multi-robot approaches typically address these concerns in separate stages: task-allocation methods (e.g., market- and auction-based schemes) price assignments by distance, and computation-offloading methods decide execution placement after a route has been fixed. This paper’s specific contribution is to fold the execution-placement decision (local computation versus offloading to a peer) into the edge-relaxation step of an A* path search, using a composite cost whose communication term is derived from the instantaneous neighborhood of each node; routing and compute placement are therefore co-optimized within a single search rather than in decoupled stages. The framework is evaluated in simulation with a swarm of 25 robots against two decoupled baselines: a path-only planner that ignores workload and communication costs, and a workload-only scheduler that ignores travel and communication costs. Across 20 randomized trials, the proposed heuristic reduces total swarm energy consumption by approximately 22% relative to the path-only baseline and 9% relative to the workload-only baseline, shortens average task completion time by roughly 20%, and lowers the load imbalance factor from 6.7 (path-only) and 3.2 (workload-only) to 1.9. We report these gains for the tested configurations and delimit their scope: the search retains the asymptotic complexity of standard A*, but path optimality does not extend to the compute-placement decisions, which are locally greedy, and all results are obtained in simulation rather than on hardware.
Amir Ijaz, Hashem Haghbayan, E. Nigussie et al.· Italian National Conference...· 0 citations
The rapid evolution of swarm intelligence and edge computing has highlighted the potential of Uncrewed Aerial Vehicle (UAV) swarms for data-driven services. However, heterogeneous capabilities and time-varying communication conditions pose significant challenges for efficient resource orchestration. This letter proposes a novel method for joint communication topology formation and computation offloading in heterogeneous UAV networks to optimize task completion time and energy consumption. A graph attention network is employed for swarm feature extraction, and the communication topology and task offloading ratios are determined by proximal policy optimization. Successive convex approximation is further applied for bandwidth and power allocation. Simulation results demonstrate that the proposed framework effectively reduces task completion time and energy consumption compared with other benchmarks.
—Unmanned aerial vehicle (UAV) swarm networks (USNTs) are a crucial component of the emerging low-altitude intelligent networks. For supporting low-altitude economic activities, this paper explores successful task transmission probability (STP) maximization, while maintaining the performance fairness of each UAV swarm for USNTs with resource limitations (e.g., frequency, power). Towards this goal, this paper formulates STP maximization and its fairness as a nonlinear non-convex optimization problem. To solve the complex optimization problem, we first propose an adaptive frequency block sharing algorithm to determine whether different-sized UAV swarms use the same frequency blocks or not, providing an efficient initial solution for inter-swarm resource allocation. Then we develop a double deep Q-network-based algorithm for inter-swarm resource allocation to guarantee fairness among swarms. Based on the inter-swarm allocation results, we propose a genetic algorithm-based method for intra-swarm resource allocation to achieve the STP maximization, which ensures reliable transmission of high-priority tasks. Extensive simulation results are presented to validate the efficiency of our proposed algorithms, and also to illustrate the impact of system parameters on STP and fairness.
Zhuojia Yang, Wei Su, Bin Yang et al.· IEEE Transactions on Mobile...· 0 citations
A Prioritized Adaptive Weighting based on Deep Deterministic Policy Gradient (PAW-DDPG) as an enhanced Deep Deterministic Policy Gradient (DDPG) algorithm to minimize both processing delay and energy consumption by jointly optimizing user scheduling, partial-task offloading, and UAV trajectory is proposed.
W. Saber, Hanan Algamil, Fifi Farouk et al.· Future Internet· 0 citations
Smart factories are evolving into agentic control systems powered by wireless connectivity, edge computing, and artificial intelligence. This evolution alleviates computational limits and enhances production efficiency. However, the heterogeneity of spatiotemporal control logic, coupled with indeterminate wireless conditions, makes it challenging to coordinate control tasks and radio resources. To overcome these challenges, this paper presents a mixed graph-driven model to characterize spatiotemporal dependencies among control tasks and proposes a semi-centralized multi-agent collaborative framework. This paper employs an improved heterogeneous twin delayed deep deterministic policy gradient algorithm to jointly optimize task scheduling and radio resource allocation, thereby minimizing the average processing delay of industrial control processes. Simulation results demonstrate that the proposed algorithm achieves outstanding performance compared to benchmarks, improving execution success rate and data processing rate, as well as reducing model training time.
Sha Li, Lei Sun, Wanli Ni et al.· IEEE Transactions on Cogniti...· 0 citations
This paper addresses the joint task offloading and resource allocation problem in multi-user MEC systems and proposes a decentralized control framework based on Multi-Agent Reinforcement Learning (MARL), which achieves lower total system cost and faster convergence than the full-local, full-offload, and heuristic baselines.
Youssef Oukissou, Mohamed Amine Meddaoui, Ayoub Belaidi et al.· International journal of Com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
