电力需求侧管理2025，Vol.27Issue(5)：36-42,7.DOI:10.3969/j.issn.1009-1831.2025.05.006
考虑互负荷相关特性的低压配电网拓扑识别
Low-voltage distribution grid topology identification considering mutual load dependent characteristics
摘要
Abstract
The topology of low-voltage distribution grids(LVDGs)depicts how various electrical components are physically interconnect-ed within the distribution system.Due to the use of distributed energy resources(DERs),there is an overlooked mutual load dependent characteristics among end users,which brings great challenges to node correlation analysis and topology identification.In this regard,a low-voltage topology identification method focusing on the mutual load dependent characteristics of DERs is proposed.First,a user classifi-cation method based on support vector machineis proposed to classify users according to usage of DERs at different times.Then,convolu-tional recurrent neural network is applied for distributed feature extraction among load data to decrease load dependency.Finally,the sib-ling pair search algorithm with residuals resistance is proposed to hierarchically identify the topology.Test results in different simulation scenarios and practical LVDGs demonstrate the effectiveness and robustness of the proposed method.关键词
低压配电网/拓扑识别/互负荷相关性/分布式特征提取/卷积循环神经网络/同胞对搜索Key words
low-voltage distribution grid/topology identification/mutual load dependency/distributed feature extraction/convolutional re-current neural network/sibling pair search分类
信息技术与安全科学引用本文复制引用
李嘉睿,高源..考虑互负荷相关特性的低压配电网拓扑识别[J].电力需求侧管理,2025,27(5):36-42,7.基金项目
国家自然科学基金项目(51907114) （51907114）
