M-DRL的低轨道卫星网络计算卸载和任务迁移
Computing Offloading and Task Migration of LEO Network based on M-DRL
徐飞 1宁辛 1安朔 1申奥祥 1王泽轩1
作者信息
- 1. 西安工业大学 计算机科学与工程学院,西安 710021
- 折叠
摘要
针对无人机网络高时延、低性能、有限带宽、难以解决复杂计算任务问题,提出了一种将低地球轨道卫星和移动边缘计算技术结合形成的 MEC 辅助 LEO 卫星网络计算卸载和任务迁移方法.首先通过建立本地计算模型、卸载模型和迁移模型,确定目标优化成本函数.然后为降低模型复杂度,引入多智能体深度强化学习模型,利用多智能体双延迟深度确定性策略梯度(MATD3)算法求解优化问题,降低系统总时延.仿真结果表明,与本地计算及随机迁移算法相比,MATD3 算法的任务处理时延分别降低 94.55%和 83.02%,证明了 MATD3 算法在计算卸载和任务迁移方面的有效性和可靠性.
Abstract
To solve the problems of high latency,low performance,limited bandwidth,and difficulty in solving complex computing tasks in UAV networks,this paper proposes a MEC assisted LEO satellite network computing offloading and task migration method that combines LEO satellites and Mobile Edge Computing technology.Firstly,the local computing model,offloading model and migration model are established to determine the target optimization cost function.Then,a Multi-agent Deep Reinforcement Learning model is introduced to reduce the complexity of the model,and the Multi-Agent Twin Delayed Deep Deterministic Policy Gradient algorithm is used to solve the optimization problem and reduce the total system delay.The simulation results show that the task processing latency of MATD3 algorithm is reduced by 94.55%and 83.02%compared with the local computation and random migration algorithms,respectively,which proves the effectiveness and reliability of MATD3 algorithm in computing offloading and task migration.
关键词
LEO卫星网络/移动边缘计算/MATD3算法/计算卸载/卫星通信Key words
LEO satellite network/mobile edge computing/MATD3 algorithm/computing offloading/satellite communications引用本文复制引用
基金项目
咸阳市科技局重点研发项目(2021ZDYF-NY-0019)
出版年
2024
NETL
NSTL
万方数据