A reinforcement learning approach for multi-edge task offloading through bi-level optimization

Gouaouri, M. D. E., Bagaa, M., Bekkouche, O., Ouameur, M. A. et Ksentini, A. (2025). A reinforcement learning approach for multi-edge task offloading through bi-level optimization. Dans 2025 International Wireless Communications and Mobile Computing (IWCMC) DOI 10.1109/IWCMC65282.2025.11059480.

PDF Sous embargo jusqu'au 2 juillet 2026. Télécharger (691kB)

Résumé

The Internet of Things (IoT) is rapidly expanding globally, but the limited size of IoT devices restricts their battery capacity, computational resources, and wireless bandwidth, making it difficult to handle resource-intensive tasks. Edge Computing addresses these challenges by enabling task offloading to more capable edge servers. However, optimal task offloading in Edge-IoT networks is complex due to dynamic conditions, such as varying server loads and wireless fluctuations. Traditional and some machine learning-based offloading methods often fall short in adaptability or efficiency. This paper introduces a bi-level optimization approach using Deep Reinforcement Learning (DRL) agents for IoT-level offloading and a priority-aware greedy heuristic for resource allocation on edge servers. The proposed method effectively improves QoS by balancing task execution latency and power consumption, as demonstrated by simulation results.

Type de document:	Document issu d'une conférence ou d'un atelier
Mots-clés libres:	Wireless communication Energy consumption Scheduling algorithms Simulation Quality of service Robustness Servers Internet of Things Resource management Optimization Edge-IoT Computing Task Offloading Bi-level Optimization Reinforcement Learning
Date de dépôt:	18 déc. 2025 15:36
Dernière modification:	18 déc. 2025 15:36
Version du document déposé:	Post-print (version corrigée et acceptée)
URI:	https://depot-e.uqtr.ca/id/eprint/12492

Actions (administrateurs uniquement)

Éditer la notice