郭祥富,张旭,刘书铭,王得道,李琼林,贾子昊,孙媛媛
GUO Xiangfu,ZHANG Xu,LIU Shuming,WANG Dedao,LI Qionglin,JIA Zihao,SUN Yuanyuan

• 1:国网河南省电力公司
• 2:国网河南省电力公司平顶山供电公司
• 3:国网河南省电力公司电力科学研究院
• 4:山东大学电气工程学院

摘要(Abstract)：

为准确高效地评价配电网关键节点的稳态电能质量，提出一种计及动态相关性的电能质量稳态指标分层智能评价方法。首先，利用MIC（最大信息系数）分析配电网关键节点电能质量稳态指标之间的相关性，建立配电网关键节点稳态电能质量综合评价体系。其次，利用CRITIC权重法和指标相关性分析结果，计算评价体系中各指标的综合权重。最后，将综合评价得分作为期望值，结合LSTM（长短期记忆）神经网络建立配电网关键节点稳态电能质量智能综合评价模型，并利用实测样本数据对神经网络进行优化训练。实测数据仿真结果表明，提出的评价方法可以在保证准确性的同时降低评价过程的复杂度，极大提高了评价效率。
To accurately and efficiently evaluate the steady-state power quality at key nodes in a distribution network, a hierarchical intelligent evaluation method for steady-state power quality metrics incorporating dynamic correlations is proposed. First, the maximum information coefficient(MIC) is used to analyze the relationships among steady-state power quality metrics at these key nodes; then an integrated evaluation system for steady-state power quality is developed. Next, the CRITIC, an objective weighting method, along with the results from the correlation analysis, is employed to calculate the overall weights of each metric in the evaluation system. Finally, the aggregated evaluation score is used as the expected value, and an integrated intelligent evaluation model for steady-state power quality at key nodes is developed using a long short-term memory(LSTM). The LSTM is optimized with the measured sample data. Simulation results demonstrate that the proposed method significantly reduces the complexity of the evaluation process while maintaining accuracy, thereby greatly enhancing evaluation efficiency.

关键词(KeyWords)： 配电网关键节点;稳态电能质量;最大信息系数;CRITIC;LSTM
key nodes in distribution network;steady-state power quality;MIC;CRITIC;LSTM

Abstract:

Keywords:

基金项目(Foundation): 国家电网公司总部科技项目（5400-202124153A-0-0-00）

作者(Author): 郭祥富,张旭,刘书铭,王得道,李琼林,贾子昊,孙媛媛
GUO Xiangfu,ZHANG Xu,LIU Shuming,WANG Dedao,LI Qionglin,JIA Zihao,SUN Yuanyuan

DOI: 10.19585/j.zjdl.202412003

参考文献(References)：

• [1]祁炜雯，张俊，吴洋，等.基于改进BP-Bagging算法的光伏电站故障诊断方法[J].浙江电力，2024,43(3):65-74.QI Weiwen,ZHANG Jun,WU Yang,et al.A fault diagnosis method for photovoltaic power plants based on an enhanced BP-Bagging algorithm[J].Zhejiang Electric Power,2024,43(3):65-74.
• [2]韩雪姣，屈鲁，王长永，等.数据中心全直流供电系统的构建及其综合评价[J].浙江电力，2024,43(3):75-83.HAN Xuejiao,QU Lu,WANG Changyong,et al. Construction and comprehensive evaluation of a full DC power supply system in data centers[J].Zhejiang Electric Power,2024,43(3):75-83.
• [3]张敏，祗会强，张世锋，等.考虑配电网电能质量改善的分布式光伏优化调度方法[J].电力建设，2022,43(10):147-157.ZHANG Min,ZHI Huiqiang,ZHANG Shifeng,et al.Optimal scheduling method for distributed photovoltaic generation in distribution network considering power quality improvement[J].Electric Power Construction,2022,43(10):147-157.
• [4]孙媛媛，许庆燊，马钊，等.数字化背景下新型电力系统谐波溯源关键技术[J].电力系统自动化，2024,48(6):154-169.SUN Yuanyuan,XU Qingshen,MA Zhao,et al.Key technologies for harmonic source tracing in new power system in background of digitalization[J].Automation of Electric Power Systems,2024,48(6):154-169.
• [5]邱冬，贾勇勇，韩少华，等.基于区间-概率潮流分析的配电网调压手段适应性评估方法[J].浙江电力，2024,43(4):85-94.QIU Dong,JIA Yongyong,HAN Shaohua,et al.An adaptability evaluation method for voltage regulation measures in distribution networks based on interval and probability power flow analysis[J].Zhejiang Electric Power,2024,43(4):85-94.
• [6] LI Y H,SUN Y Y,WANG Q Y,et al.Probabilistic harmonic forecasting of the distribution system considering time-varying uncertainties of the distributed energy resources and electrical loads[J]. Applied Energy,2023,329:120298.
• [7] YU T K,LI X J,LI X M,et al.Comprehensive evaluation of substation power supply scheme based on LCC and power quality[C]//2022 China International Conference on Electricity Distribution(CICED). September 7-8,2022,Changsha,China.IEEE,2022:772-776.
• [8]赵宏大，陈琛，王哲，等.基于配电网网格边缘代理的电能质量感知技术[J].电力电容器与无功补偿，2022,43(2):134-140.ZHAO Hongda,CHEN Chen,WANG Zhe,et al.Power quality perception technology based on grid edge agent in distribution network[J]. Power Capacitor&Reactive Power Compensation,2022,43(2):134-140.
• [9]赵伟，袁至，王维庆，等.考虑电能质量优化的MMC-SST输入级控制策略[J].电力工程技术，2022,41(6):211-220.ZHAO Wei,YUAN Zhi,WANG Weiqing,et al. MMCSST input-level control strategy considering power quality optimization[J].Electric Power Engineering Technology,2022,41(6):211-220.
• [10]王倍倍，蒋建东.计及复合电能质量的配电网附加损耗量化计算与建模仿真[J].电力电容器与无功补偿，2022,43(4):52-59.WANG Beibei,JIANG Jiandong.Quantitative calculation and modeling simulation of additional loss in distribution network considering composite power quality[J]. Power Capacitor&Reactive Power Compensation,2022,43(4):52-59.
• [11]陈肖，方学智，肖建华，等.基于多源异构数据融合的变电站风险评估研究[J].电工技术，2023(21):42-44.CHEN Xiao,FANG Xuezhi,XIAO Jianhua,et al. Study on state evaluation of substation based on multi-source heterogeneous data fusion[J]. Electric Engineering,2023(21):42-44.
• [12]宋丽，李鹏，许文韬，等.基于云模型的输电线路运维检修风险评估[J].浙江电力，2023,42(9):108-116.SONG Li,LI Peng,XU Wentao,et al.Risk assessment of transmission line operation and maintenance based on a cloud model[J]. Zhejiang Electric Power,2023,42(9):108-116.
• [13]李振坤，王艺龙，季亮，等.基于虚拟变电站的配电网薄弱区域集群双层规划研究[J].电力建设，2022,43(8):53-65.LI Zhenkun,WANG Yilong,JI Liang,et al.Research on cluster bi-level planning based on virtual substation for weak areas of distribution network[J].Electric Power Construction,2022,43(8):53-65.
• [14] YAO N,FAN Q,LIU Z Q,et al.Application of artificial intelligence technology in the event analysis of substation monitoring information[C]//2023 3rd International Conference on Energy,Power and Electrical Engineering(EPEE). September 15-17,2023,Wuhan,China. IEEE,2023:931-934.
• [15]尹相国，张文，胡柏华，等.基于BP神经网络算法的新一代智能变电站控制障碍分析与定位技术研究[J].自动化与仪器仪表，2023(8):144-149.YIN Xiangguo,ZHANG Wen,HU Bohua,et al.Research on control obstacle analysis and location technology of new generation intelligent substation based on BP neural network[J]. Automation&Instrumentation,2023(8):144-149.
• [16]周柯，王晓明，李肖博，等.基于ARIMA-BP组合模型的智能变电站遥测数据趋势性分析预警技术研究[J].哈尔滨理工大学学报，2023,28(1):97-104.ZHOU Ke,WANG Xiaoming,LI Xiaobo,et al.Research on trend analysis and early warning technology of smart substation telemetry data based on ARIMA-BP combined model[J]. Journal of Harbin University of Science and Technology,2023,28(1):97-104.
• [17] CAI C C,TAO Y,ZHU T Q,et al.Short-term load forecasting based on deep learning bidirectional LSTM neural network[J].Applied Sciences,2021,11(17):8129.
• [18] CHIAM D H,LIM K H,LAW K H. Global attentionbased LSTM for noisy power quality disturbance classification[J]. International Journal of Systems,Control and Communications,2023,14(1):22.
• [19]梁海峰，刘子嫣.基于AHP—熵权法—模糊综合分析的智能配电网综合效益评估[J].华北电力大学学报（自然科学版），2023,50(1):48-55.LIANG Haifeng,LIU Ziyan.Comprehensive benefit evaluation of smart distribution network based on analytic hierarchy process-entropy method-fuzzy comprehensive analysis[J].Journal of North China Electric Power University(Natural Science Edition),2023,50(1):48-55.