Open AccessGeneralized Load Modeling Considering Inverter Capacity Limitation
Author(s) -
Haojing Wang,
Zhipeng Yu,
Yu Zhang,
Qiuhong Zheng,
Chen Fang
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1346/1/012015
Subject(s) - generalization , inverter , piecewise , artificial neural network , computer science , fault (geology) , control theory (sociology) , stability (learning theory) , point (geometry) , class (philosophy) , grid , process (computing) , function (biology) , activation function , mathematics , artificial intelligence , engineering , machine learning , control (management) , voltage , mathematical analysis , geometry , electrical engineering , seismology , evolutionary biology , biology , geology , operating system
This paper aims at the problem of the generalized modeling considering the capacity limitation of inverter. Firstly, how the inverter capacity limitation can influence the generalized load fault response of the grid-connected point was analyzed. Then, the idea of fitting the piecewise function was proposed and applied to the training process of the generalized load artificial with neural network class model. To be clearer, fault samples were jointly trained at the same time to learn different segmentation characteristics. The modeling and simulation results show that the proposed method can improve the generalization ability and stability of the artificial neural network class model in generalized load modeling.