东北大学学报(自然科学版) ›› 2024, Vol. 45 ›› Issue (12): 1688-1695.DOI: 10.12068/j.issn.1005-3026.2024.12.003

• 信息与控制 • 上一篇    

基于边缘服务器任务迁移的资源分配算法

吴菁晶(), 张子轩   

  1. 东北大学 计算机科学与工程学院,辽宁 沈阳 110169
  • 收稿日期:2023-07-10 出版日期:2024-12-10 发布日期:2025-03-18
  • 通讯作者: 吴菁晶
  • 作者简介:吴菁晶(1981-),女,辽宁沈阳人,东北大学副教授,博士生导师.
  • 基金资助:
    国家重点研发计划项目(2021YFB3401004)

Resource Allocation Algorithm Based on Edge Server Task Migration

Jing-jing WU(), Zi-xuan ZHANG   

  1. School of Computer Science & Engineering,Northeastern University,Shenyang 110169,China.
  • Received:2023-07-10 Online:2024-12-10 Published:2025-03-18
  • Contact: Jing-jing WU

摘要:

工业物联网设备会将无法进行本地计算的任务发送至边缘服务器进行处理,但不同设备密度下的覆盖会导致不同边缘服务器的计算任务负载不均衡,进而产生计算时延过大的问题.为了解决这个问题,提出了一种基于改进的深度确定性策略梯度(modified deep deterministic policy gradient,MDDPG)的任务迁移算法,该算法具有基于深度确定性策略梯度的优先经验重放和随机权重平均机制,以寻求最佳的迁移策略,减少任务的计算时延.实验结果表明,MDDPG算法相较于传统的算法有更好的性能.

关键词: 工业物联网, 策略梯度, 任务迁移, 优先经验重放, 随机权重平均

Abstract:

IIoT (industrial Internet of Things) devices send tasks that cannot be computed locally to edge servers for processing. However, different device densities result in imbalanced computational workloads among various edge servers, leading to significant computation latency. To solve this problem, a task migration algorithm based on modified deep deterministic policy gradient (MDDPG) is proposed. The algorithm has a mechanism of priority empirical replay and random weight averaging based on depth deterministic strategy gradient to find the best migration strategy and reduce the computation delay of the task. Experimental results show that MDDPG algorithm has a better performance than the traditional algorithms.

Key words: industrial Internet of Things, policy gradient, task migration, priority experience replay, random weight averaging

中图分类号: