基于PRSGMD-XGBoost的光伏直流电能质量扰动识别  

Photovoltaic DC Power Quality Disturbance Identification Based on PRSGMD-XGBoost

作　　者：朱宪宇 熊婕 李庆先 刘良江 左从瑞 刘青 ZHU Xian-yu;XIONG Jie;LI Qing-xian;LIU Liang-jiang;ZUO Cong-rui;LIU Qing(Hunan Institute of Metrology and Test,Changsha 410018,China)

机构地区：[1]湖南省计量检测研究院,湖南长沙410018

出　　处：《电工电气》2024年第7期61-67,共7页Electrotechnics Electric

基　　金：长沙市杰出创新青年培养计划项目(kq2206066)。

摘　　要：光伏电网受天气因素和非线性负载等影响,直流电信号中存在的扰动成分使得电能质量评估的准确性难以保障。利用复合多尺度模糊熵可克服光伏直流电信号初始单分量相似性度量突变的问题,构建了正则化CMFE算子评估各初始单分量重构后的复杂度并约束残余量能量最小,从而实现电信号和噪声等扰动的准确分离,在此基础上,提出了基于部分重构辛几何模态分解(PRSGMD)的光伏直流电信号自适应去噪方法,结合极限梯度提升机(XGBoost)可有效挖掘特征与暂态稳定性之间关系的优势,实现了光伏直流电信号中复合扰动的分离和识别。The photovoltaic(PV)grid is affected by weather factors and nonlinear loads,and the disturbance components in the direct current(DC)signal make it difficult to ensure the accuracy of power quality assessment.Therefore,in this paper the problem that the composite multiscale fuzzy entropy(CMFE)can overcome the sudden change of the initial single component similarity measure of the photovoltai DC signal is utilized,then the regularized CMFE operator is constructed to evaluate the complexity of each initial single component after reconstruction,while constraining the residual energy to be minimized,and finally the separation of electrical signals and noise and other disturbance is realized.On this basis,an adaptive denoising method for photovoltai DC signal based on partial reconstruction of symplectic geometry mode decomposition(PRSGMD)is proposed,and combined with the advantage that extreme gradient boosting(XGBoost)can effectively mine the relationship between features and transient stability,the separation and identification of compound disturbance in photovoltaic DC signals is realized.

关 键 词：光伏 电能质量扰动识别 部分重构辛几何模态分解 极限梯度提升机 

分 类 号：TM615[电气工程—电力系统及自动化]