基于深度学习的光伏并网系统谐波预测研究  

Research on Harmonic Prediction of the Grid-Connected Photovoltaic System Based on Deep Learning

作　　者：杨鹏兴 王秀丽[1] 赵兴勇[1] 胡莹洁 YANG Pengxing;WANG Xiuli;ZHAO Xingyong;HU Yingjie(School of Electric Power and Architecture,Shanxi University,Taiyuan 030013,Shanxi,China;School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,Jiangsu,China)

机构地区：[1]山西大学电力与建筑学院,山西太原030013 [2]中国矿业大学信息与控制工程学院,江苏徐州221116

出　　处：《电网与清洁能源》2022年第7期71-80,共10页Power System and Clean Energy

基　　金：甘肃省省青年科技基金(17JR5RA346);山西省科技基础条件平台建设基金(2014091034)。

摘　　要：“双碳”目标下,针对温度及光照的变化对光伏系统并网引起的谐波影响问题,提出一种基于ip-iq谐波提取法与改进双向长短期记忆网络(Bi-LSTM)相结合的谐波预测方法,旨在为谐波抑制提供新的解决方案。首先使用MATLAB/SIMULINK工具建立光伏并网系统,利用基于瞬时无功理论的ip-iq谐波提取法得到实际谐波变化数据,并采用微分插值将数据进行化简;然后,利用网格搜索优化的Bi-LSTM神经网络算法进行谐波数据的预测,并与BP、LSTM、GRU、BiLSTM多种时间序列型深度学习方法进行比较,得出MSE、MAE、MAPE损失函数与预测结果图;最后,以陇东地区实际算例进行光伏并网仿真,结果表明,该方法可实现谐波的准确预测。Under the goal of carbon peak and neutrality,for the problem of harmonic influence caused by temperature and illumination changes on the grid-connected photovoltaic system,we propose a harmonic prediction method based on ip-iq harmonic extraction method and improved bi-directional long and short-term memory network(BI-LSTM)to provide a new solution for harmonic suppression.Firstly,the grid-connected photovoltaic system is established by MATLAB/SIMULINK tool,and the actual harmonic variation data are obtained by ip-iq harmonic extraction method based on instantaneous reactive power theory,and the data are simplified by differential interpolation.Secondly,the grid search optimization BI-LSTM neural network algorithm is used to predict harmonic data,and compared with BP,LSTM,GRU and BI-LSTM deep learning methods,and the LOSS function and prediction results of MSE,MAE and MAPE are obtained.Finally,a practical example in Longdong area is used to simulate the grid connection of PV,and the results show that the method can accurately predict the harmonic.

关 键 词：光伏并网 电能质量 谐波预测 双向长短期记忆网络(Bi-LSTM) 

分 类 号：TM933[电气工程—电力电子与电力传动]