基于图卷积网络的电能质量评估  

Comprehensive Evaluation of Power Quality Based on Graph Convolutional Network

作　　者：黄宏清 倪道宏 刘雪松 HUANG Hongqing;NI Daohong;LIU Xuesong(College of Software Engineering,Southeast University,Nanjing 210096,China;Nanzi Tonghua Intelligent Electric Co.,Nanjing 210000,China)

机构地区：[1]东南大学软件学院,江苏南京210096 [2]南自通华(南京)智能电气有限公司,江苏南京210000

出　　处：《电子科技》2024年第9期43-47,共5页Electronic Science and Technology

基　　金：江苏省重点研发计划(BE2020116,BE2022154)。

摘　　要：新型电力设备的广泛使用给电力系统带来了新的干扰因素,同时也对电能质量提出了更高要求。为充分利用国家标准中各项电能质量指标,对电能质量进行更全面、更综合地评估,文中提出一种基于图卷积网络的电能质量评估方法。根据现行国家标准提出了指标分级的电能质量评估体系,对各项电能质量评估指标间的关联性进行初步确定。在此基础上确定指标关系图,搭建图神经网络模型并进行训练,测试集误差率为9.02%。以某电力系统实测数据为例与其他评估方法进行对比分析,证明了所提方法在对长时间跨度的电能质量进行评估时效果更优。The increasingly widespread use of new power equipment has brought new disturbances to the power system and has placed increasing demands on power quality.In order to make full use of the power quality indicators in the national standards and to make a more comprehensive and integrated evaluation of power quality,this study proposes a power quality evaluation method based on graph convolutional network.A power quality assessment system with graded indicators is proposed according to the current national standards.The correlation between the various power quality assessment indicators is initially determined,and on this basis the indicator relationship diagram is determined,a graph neural network model is built and trained,and the error rate of the test set is 9.02%.A comparison and analysis with other assessment methods using actual measurement data of a power system proves that the proposed method is more effective in assessing power quality over a long time span.

关 键 词：电能质量 综合评估 图卷积网络 指标 关联性 图 邻接矩阵 半监督训练 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]