基于不确定性时延感知的配电网云边卸载方法  

An Uncertain Delay Awareness Based Cloud-Edge Offloading Method for Distribution Networks

作　　者：文艳 李立生 刘明林 李帅 文祥宇 房牧 李建修 WEN Yan;LI Lisheng;LIU Minglin;LI Shuai;WEN Xiangyu;FANG Mu;LI Jianxiu(Economic and Technology Research Institute,State Grid Shandong Electric Power Company,Jinan 250022,Shandong,China;Electric Power Research Institute,State Grid Shandong Electric Power Company,Jinan 250003,Shandong,China;State Grid Shandong Electric Power Company,Jinan 250001,Shandong,China)

机构地区：[1]国网山东省电力公司经济技术研究院,山东济南250022 [2]国网山东省电力公司电力科学研究院,山东济南250003 [3]国网山东省电力公司,山东济南250001

出　　处：《电网与清洁能源》2025年第1期82-88,共7页Power System and Clean Energy

基　　金：国家重点研发计划项目(2021YFB2401300)。

摘　　要：在新型电力系统场景下,边缘计算与云计算互为补充,有效实现了配电网多业务数据的高效传输与处理。有效的云边卸载策略能够进一步提升网络服务质量,但由于云边卸载过程中突发干扰、紧急任务处理等因素所引起的时延不确定性,导致现有技术在实际场景中不适用。提出了一种配电网多业务数据云边卸载框架以及系统模型;基于该系统模型,以最小化不确定性的卸载总时延为目标,将问题描述为随机组合优化问题,并提出基于不确定性时延感知的配电网云边协同数据卸载策略。实验结果表明,与现有的两种数据卸载方法相比,所提方法的时延分别降低了38.47%和23.87%。In the context of new-type power systems,edge computing and cloud computing complement each other,effectively achieving efficient multi-service data transmission and processing in distribution networks.An effective edge-cloud offloading strategy can further improve the network service quality.However,due to the uncertain delay in the cloud-edge offloading process caused by burst interference,emergent task and other factors,the existing technology is not applicable in practical scenarios.To address this challenge,this paper proposes a multi-service cloud-edge offloading framework and system model for distribution networks.Based on the the proposed system model,with the goal of minimizing the total delay under uncertainty,the problem is formulated into a stochastic combination optimization issue,and an uncertain delay awareness based cloud-edge offloading method for distribution networks is proposed.The experimental results show that compared with existing data offloading methods,the proposed method reduces the delay by 31.38%and 22.02%,respectively.

关 键 词：配电网 云边卸载 不确定性时延感知 多业务差异化需求 

分 类 号：TM73[电气工程—电力系统及自动化]