基于DDPG的边缘计算任务卸载决策研究
Journal: Advances in Computer and Autonomous Intelligence Research DOI: 10.12238/acair.v2i3.8637
Abstract
随着通信技术的不断发展,海量的移动应用数据给原有的服务设备带来了巨大的挑战。边缘计算(Mobile Edge Computing,MEC)作为新的计算范式能够有效应对这一挑战。本文针对MEC任务计算卸载问题,建立了一种多用户多服务器的MEC环境,考虑了一种任务可分的情况,可将任务部分卸载到MEC服务器上,同时考虑了任务的时延和能耗,将最小化时延和能耗的加权和作为优化目标,提出了一种基于DDPG动态卸载算法。一系列仿真结果表明,该算法与基线相比,本研究提出的算法能够有效的降低时延和能耗。
Keywords
边缘计算；任务卸载；DDPG；部分卸载
Full Text
PDF - Viewed/Downloaded: 0 TimesReferences
[1] 刘耿旗,张旭秀,马洪源,等.多边缘节点场景下的任务卸载算法[J].信息与控制,2023,52(05):679-688.
[2] 周天清,许铭.基于PSO的联合任务卸载与缓存算法研究[J].无线电工程,2024,54(03):517-525.
[3] Zhu X,Jia Z,Pang X,etal.Joint Optimization of Task Cach ing and Computation Offloading for Multiuser Multitasking in Mobile Edge Computing[J].Electronics,2024,13(2):389.
[4] Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous control with deep reinforcement learning[J]. arXiv preprint arXiv:1509.02971,2015.
[2] 周天清,许铭.基于PSO的联合任务卸载与缓存算法研究[J].无线电工程,2024,54(03):517-525.
[3] Zhu X,Jia Z,Pang X,etal.Joint Optimization of Task Cach ing and Computation Offloading for Multiuser Multitasking in Mobile Edge Computing[J].Electronics,2024,13(2):389.
[4] Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous control with deep reinforcement learning[J]. arXiv preprint arXiv:1509.02971,2015.
Copyright © 2024 张轩, 胡晓辉
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License