Multidimensional Resource Management for Distributed MEC Networks in Jamming Environment: A Hierarchical DRL Approach

• Published in: IEEE internet of things journal Vol. 11; no. 9; pp. 16859 - 16872
• Main Authors: Liu, Songyi, Xu, Yuhua, Li, Guoxin, Xu, Yifan, Zhang, Xiaokai, Gu, Fanglin, Ma, Wenfeng, Chen, Taoyi
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.05.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Actor–critic (AC) model; Algorithms; anti-jamming communication; Computing costs; Data processing; Dynamic scheduling; Edge computing; Energy consumption; Heuristic algorithms; High level networks; Integer programming; Internet of Things; Jamming; Markov decision process (MDP); Markov processes; Mobile computing; multiagent reinforcement learning (MARL); Multiagent systems; multidimensional resource management; Optimization models; Radio equipment; Reinforcement learning; Resource allocation; Resource management; Servers; Task analysis
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2024.3366009

This article investigates the problem of multidimensional resource management in multiaccess mobile edge computing (MEC) networks against external dynamic jamming. The objective is to minimize the long-term computational cost of the MEC network while satisfying the task computation delay requirements of user equipment (UE) by jointly optimizing computing and communication resource allocation. To overcome challenges, such as frequency conflict and dynamic jamming attacks, a distributed multiagent hierarchical deep reinforcement learning (MAHDRL) MEC framework based on hybrid heterogeneous decision making is proposed. Specifically, a hierarchical MEC anti-jamming data offloading optimization model is constructed, and the MEC resource management problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP). Based on this, a distributed MAHDRL algorithm based on the actor-critic (AC) model is designed to solve the multiagent high-dimensional nonlinear hybrid integer programming NP-hard problem: the high-level network in the base station (BS) optimizes discrete channel access strategies, while the low-level network in UEs learns data offloading strategies. Additionally, the computational complexity is discussed and a theoretical proof of the algorithm convergence is presented. Simulation results demonstrate the superiority of the proposed algorithm, which reduces energy consumption and data processing delay across the network.