计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (5): 281-290.DOI: 10.3778/j.issn.1002-8331.2304-0293

• 网络、通信与安全 • 上一篇    下一篇

配电网中任务卸载决策与边缘资源分配优化方法

朵春红,匡竹,齐国梁,梅华威,李保罡,李永倩   

  1. 1.华北电力大学 河北省能源电力知识计算重点实验室,河北 保定 071003
    2.华北电力大学 计算机系,河北 保定 071003
    3.华北电力大学 电子与通信工程系,河北 保定 071003
  • 出版日期:2024-03-01 发布日期:2024-03-01

Optimization Method for Task Offloading Decision and Edge Resource Allocation in Distribution Networks

DUO Chunhong, KUANG Zhu, QI Guoliang, MEI Huawei, LI Baogang, LI Yongqian   

  1. 1.Hebei Key Laboratory of Knowledge Computing for Energy & Power, North China Electric Power University, Baoding, Hebei 071003, China
    2.Department of Computer, North China Electric Power University, Baoding, Hebei 071003, China
    3.Department of Electronic and Communication Engineering, North China Electric Power University, Baoding, Hebei 071003, China
  • Online:2024-03-01 Published:2024-03-01

摘要: 移动边缘计算可以减轻配电网核心网络中海量数据的传输及处理压力,相对于云计算,边缘节点有限的计算能力使边缘资源的高效利用成为挑战。基于此,提出一种配电网中任务卸载决策与边缘资源分配优化方法。在包含多边缘节点多用户设备的配电网场景中,考虑任务随机、资源有限、计算能力不均衡及时延要求高等因素,构建云-边-端三层任务卸载及边缘资源分配优化模型;将优化过程分为计算卸载和资源拍卖两个阶段,在计算卸载阶段设计基于DRL的在线决策算法,在资源拍卖阶段设计基于补偿策略的多轮迭代拍卖算法;提出基于改进DQN算法的任务卸载与资源分配优化方法。仿真结果表明,在动态变化的配电网场景中,所提算法可有效提高系统计算能效和边缘节点效益。

关键词: 移动边缘计算, 配电网, 任务卸载, 资源分配

Abstract: Mobile edge computing can reduce the pressure of massive data transmission and processing in core distribution networks, compared to cloud computing, the computing limitations of edge nodes poses a challenge to the efficient utilization of edge resources. Based on this, a task offloading decision and edge resource allocation optimization method in distribution networks is proposed. First of all, in a distribution network scenario containing multiple edge nodes and multiple user devices, a cloud-edge-end three-layer edge computing offloading and resource allocation model is constructed. Secondly, the optimization process is divided into two stages:computing offloading and resource auction. In computing offloading stage, an online decision algorithm based on DRL is proposed, and in resource auction stage, a multi round iterative auction mechanism based on compensation strategy is designed. Finally, a task offloading and resource allocation optimization method based on improved DQN algorithm is proposed. The simulation results show that the proposes algorithm can effectively improve system computing energy efficiency and edge node efficiency in dynamically changing distribution network scenarios.

Key words: mobile edge computing, distribution network, task offloading, resource allocation