Attention-Augmented MADDPG in NOMA-Based Vehicular Mobile Edge Computational Offloading

作     者：Wu, Liangshun Qu, Junsuo Li, Shilin Zhang, Cong Du, Jianbo Sun, Xiang Zhou, Jiehan 

作者机构：Xian Univ Posts & Telecommun Sch Automat Xian Key Lab Adv Control & Intelligent Proc Xian 710061 Peoples R China Xian Univ Posts & Telecommun Sch Commun & Informat Engn Xian 710061 Peoples R China Univ New Mexico Dept Elect & Comp Engn Albuquerque NM 87131 USA Univ Oulu Fac Informat Technol & Elect Engn Oulu 90570 Finland 

出 版 物：《IEEE INTERNET OF THINGS JOURNAL》 (IEEE Internet Things J.)

年 卷 期：2024年第11卷第16期

页      面：27000-27014页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Xi'an Key Laboratory of Advanced Control and Intelligent Process [2019220714SYS022CG04] Key Research and Development Plan of Shaanxi Province [2021ZDLGY04-04] Natural Science Foundation of China 

主　　题：Attention mechanism computational offloading deep reinforce learning multiagent deep deterministic policy gradient (MADDPG) nonorthogonal multiple access (NOMA) vehicular Mobile Edge Computing (vMEC) Attention mechanism computational offloading deep reinforce learning multiagent deep deterministic policy gradient (MADDPG) nonorthogonal multiple access (NOMA) vehicular Mobile Edge Computing (vMEC) 

摘      要：Vehicular mobile edge computing (vMEC) and nonorthogonal multiple access (NOMA) have emerged as promising technologies for enabling low-latency and high-throughput applications in vehicular networks. In this article, we propose a novel multiagent deep deterministic policy gradient (MADDPG) approach for resource allocation in NOMA-based vMEC systems. Our approach leverages deep reinforcement learning (DRL) to enable vehicles to offload computation-intensive tasks to nearby edge servers, optimizing resource allocation decisions while ensuring low-latency communication. We introduce an attention mechanism within the MADDPG model to dynamically focus on relevant information from the input state and joint actions, enhancing the model s predictive accuracy. Additionally, we propose an attention-based experience replay method to expedite network convergence. The simulation results highlight the effectiveness of multiagent reinforcement learning (MARL) algorithms, such as MADDPG with attention, in achieving better convergence and performance in various scenarios. The influence of different model parameters, such as input data volumes, task load levels, and resource configurations, on optimization results is also evident. The decision making processes of agents are dynamic and depend on factors specific to the task and environment.