基于边缘计算与深度强化学习的主动配电网实时优化调度策略

李武; 高奇; 杨慧; 闫凯文; 阮玉园; 赵英男; 刘俊

李武,高奇,杨慧,闫凯文,阮玉园,赵英男,刘俊.基于边缘计算与深度强化学习的主动配电网实时优化调度策略[J].电测与仪表,2026,63(1):105-114.
LI Wu,GAO Qi,YANG Hui,YAN Kaiwen,RUAN Yuyuan,ZHAO Yingnan,LIU Jun.Real-time optimization scheduling strategy for active distribution network based on edge computing and deep reinforcement learning[J].Electrical Measurement & Instrumentation,2026,63(1):105-114.

基于边缘计算与深度强化学习的主动配电网实时优化调度策略

Real-time optimization scheduling strategy for active distribution network based on edge computing and deep reinforcement learning

DOI：10.19753/j.issn1001-1390.2026.01.011

中文关键词: 主动配电网实时调度边缘计算深度强化学习

英文关键词:active distribution network, real-time scheduling, edge computing, deep reinforcement learning

基金项目:国家电网科技计划项目（5108-202318054A-1-1-ZN）；国电南瑞控制有限公司项目（4561655965）

作者中文名	作者英文名	单位
李武	LI Wu	国网宁夏电力有限公司石嘴山供电公司, 宁夏石嘴山 753000;
高奇	GAO Qi	国网宁夏电力有限公司石嘴山供电公司, 宁夏石嘴山 753000;
杨慧	YANG Hui	国网宁夏电力有限公司石嘴山供电公司, 宁夏石嘴山 753000;
闫凯文	YAN Kaiwen	国网宁夏电力有限公司石嘴山供电公司, 宁夏石嘴山 753000;
阮玉园	RUAN Yuyuan	南京信息工程大学计算机学院, 南京 210044;
赵英男	ZHAO Yingnan	南京信息工程大学计算机学院, 南京 210044;
刘俊	LIU Jun	中国电力科学研究院自动化所, 南京 211106

摘要点击次数: 47

中文摘要:

主动配电网中新能源渗透比例的不断增加，导致运行数据激增，而新能源的间歇特性等因素也对调度策略产生了重大挑战。基于此，文中提出VMD-BiLSTM-PPO的实时优化调度模型。该模型基于边缘计算，构建多区域能源自治框架，采用深度强化学习的近端策略优化(proximal policy optimization, PPO)算法，以运行调度成本最小为目标，实现配电网云-边协同的优化调度。该模型将大量计算和数据存储任务下放至边缘侧，可以有效减少调度中心的计算量和数据传输量。在PPO算法中，采用基于变分模态分解( variational mode decomposition, VMD)和双向长短期记忆网络(Bi-directional long short-term memory, BiLSTM)的新能源出力预测，可以有效缓解新能源波动性带来的影响。仿真实验结果表明该模型能够提高新能源的消纳率，并提升配电网实时调度的经济性。

英文摘要:

The continuous increase in the penetration ratio of new energy in active distribution network has led to a sharp increase in operational data. While, coupled with the intermittent nature of new energy sources and other factors, has posed significant challenges to dispatching strategies. Therefore, a real-time optimization scheduling model called VMD-BiLSTM-PPO is proposed. Based on edge computing, this model constructs a multi-region energy autonomous framework, adopts the proximal policy optimization (PPO) algorithm of deep reinforcement learning to minimize operating scheduling costs and achieve optimized scheduling of the distribution network with cloud-edge collaboration. It decentralizes a large amount of computing and data storage tasks to the edge, effectively reducing the computing and data transmission loads at the scheduling center. Furthermore, in order to effectively alleviate the impact of new energy fluctuation, it adopts a new energy output prediction framework based on variational mode decomposition (VMD) decomposition and bi-directional long short-term memory (BiLSTM) in the PPO algorithm. Simulation experiments indicate that the model can improve the utilization rate of new energy and enhance the economic performance of real-time distribution network scheduling.

查看全文查看/发表评论下载PDF阅读器

关闭