赵长伟,骈睿珺,杜天硕,葛磊蛟

• 1:国网天津市电力公司城东供电分公司
• 2:天津大学电气自动化与信息工程学院

摘要(Abstract)：

为精确掌握重要用户电能质量的变化趋势规律，进而有效实现对其高品质的电能质量供应，文中提出一种基于距离相关系数与长短时记忆LSTM(long short-term memory)网络的重要用户电能质量趋势预测分析方法。首先，对可表征重要电力用户电能质量的多维度特征原始数据进行标准化处理，进一步利用距离相关系数过滤低相关特征实现特征降维，从而完成趋势变化基础样本数据集的筛选；其次，将训练集样本输入到双层LSTM网络中进行训练；最终得到重要用户电能质量趋势变化预测模型，并以重要电力用户的电压偏差、电压总谐波畸变率、短时间闪变等电能质量指标进行性能评估。最后，在实例分析中验证了所提出的方法的实用性和有效性，可为重要用户高品质电能质量的供应保障提供重要技术支撑。

关键词(KeyWords)： 距离相关系数;电能质量;长短时记忆网络;趋势变化

Abstract:

Keywords:

基金项目(Foundation): 国网天津市电力公司科技项目（KJ21-1-18）

作者(Author): 赵长伟,骈睿珺,杜天硕,葛磊蛟

DOI: 10.19635/j.cnki.csu-epsa.000949

参考文献(References)：

• [1]汪颖，罗代军，肖先勇，等(Wang Ying,Luo Daijun,Xiao Xianyong,et al).IEEE ICHQP2018与电能质量发展方向(IEEE ICHQP2018 and the development direction of power quality)[J].电力自动化设备(Electric Power Automation Equipment),2019,39(4):197-203.
• [2]张宇帆，艾芊，肖斐，等(Zhang Yufan,Ai Qian,Xiao Fei,et al).数据驱动电能质量分析现状及其支撑技术与展望(Present situation,supporting technologies and prospect of data driven power quality analysis)[J].电力自动化设备(Electric Power Automation Equipment),2018,38(11):187-196.
• [3]Sun Xuri,Li Yanzhen,Shen Pengfei.Research on power quality prediction of fluctuating load[J].IOP Conference Series:Materials Science and Engineering,2020,768(6):062013.
• [4]Bai Jingjing,Gu Wei,Yuan Xiaodong,et al.Power quality prediction,early warning,and control for points of common coupling with wind farms[J].Energies,2015,8(9):9365-9382.
• [5]Dou Chun-Xia,Gui Ting,Bi Ye-Fei,et al.Assessment of power quality based on D-S evidence theory[J].International Journal of Automation and Computing,2014,11(6):635-643.
• [6]林顺富，汤继开，汤波，等(Lin Shunfu,Tang Jikai,Tang Bo,et al).典型电能质量稳态指标预测模型研究(Study on forecasting model of typical power quality steady state indices)[J].电网技术(Power System Technology),2018,42(2):614-620.
• [7]丁泽俊，刘平，欧阳森，等(Ding Zejun,Liu Ping,Ouyang Sen,et al).电能质量预测与预警机制及其应用(Mechanism of power quality forecast and early warning and their application)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2015,27(10):87-92.
• [8]杨朝赟，夏圣峰，江南，等(Yang Chaoyun,Xia Shengfeng,Jiang Nan,et al).基于相关性分析和长短时记忆网络的稳态电压质量指标预测(Prediction of steadystate indices of voltage quality based on correlation analysis and long short-term memory network)[J].电力建设(Electric Power Construction),2021,42(4):9-16.
• [9]翁国庆，龚阳光，舒俊鹏，等(Weng Guoqing,Gong Yangguang,Shu Junpeng,et al).基于聚类LSTM深度学习模型的主动配电网电能质量预测(Power quality prediction of active distribution network based on clustering LSTM deep learning model)[J].高技术通讯(Chinese High Technology Letters),2020,30(7):687-697.
• [10]于西西，杨秀，王知芳，等(Yu Xixi,Yang Xiu,Wang Zhifang,et al).基于改进KPCA和GA-BP神经网络的电能质量稳态指标预测(Power quality steady state indices forecasting based on improved Kernel Principal Component Analysis and GA-BP neural network)[J].水电能源科学(Water Resources and Power),2019,37(5):189-193.
• [11]马世龙，乌尼日其其格，李小平(Ma Shilong,Unni Riqiqige,Li Xiaoping).大数据与深度学习综述(Deep Learning with Big Data:state of the art and development)[J].智能系统学报(CAAI Transactions on Intelligent Systems),2016,11(6):728-742.
• [12]孙影影，贾振堂，朱昊宇(Sun Yingying,Jia Zhentang,Zhu Haoyu).多模态深度学习综述(Survey of multimodal deep learning)[J].计算机工程与应用(Computer Engineering and Application),2020,56(21):1-10.
• [13]刘建伟，刘媛，罗雄麟(Liu Jianwei,Liu Yuan,Luo Xionglin).深度学习研究进展(Research progress of deep learning)[J].计算机应用研究(Application Research of Computers),2014,31(7):1921-1930,1942.
• [14]朱桂萍，王树民(Zhu Guiping,Wang Shumin).电能质量控制技术综述(A survey on power quality control technology)[J].电力系统自动化(Automation of Electric Power Systems),2002,26(19):28-31,40.
• [15]刘建华，刘艳梅，冯纯纯，等(Liu Jianhua,Liu Yanmei,Feng Chunchun,et al).基于k中心点聚类的稳态电能质量预警阈值研究(Early warning thresholding of steady-state power quality based on k-medoids clustering)[J].电测与仪表(Electrical Measurement&Instrumentation),2018,55(23):41-45.
• [16]王凌云，李开成，肖厦颖，等(Wang Lingyun,Li Kaicheng,Xiao Xiaying,et al).基于稀疏分解的复合电能质量扰动分类(Classification for multiple power quality disturbances based on sparse decomposition)[J].电测与仪表(Electrical Measurement&Instrumentation),2018,55(1):14-20,33.
• [17]林顺富，谢潮，汤波，等(Lin Shunfu,Xie Chao,Tang Bo,et al).数据挖掘在电能质量监测数据分析中的应用(The data mining application in the power quality monitoring data analysis)[J].电测与仪表(Electrical Measurement&Instrumentation),2017,54(9):46-51.
• [18]彭湃，刘敏(Peng Pai,Liu Min).基于Prophet-LSTM组合模型的短期负荷预测方法(Short-term load forecasting method based on Prophet-LSTM combination model)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2021,33(11):15-20.