Photovoltaic Output Power Prediction Based on Weather Type

2018 1st International Conference on Environment Prevention and Pollution Control Technology

生态环境科学

Shi, Nan^1 ; Zhu, Xianhui^2 ; Yuan, Pengtao^1 ; Hao, Jiaoxia^2 ; Wang, Qinnan^2

Engineering Training and Basic Experimental Center, Heilongjiang University of Science and Technology, Harbin, China^1

School of Electrical and Control Engineering, Heilongjiang University of Science and Technology, Harbin, China^2

关键词: Extreme learning machine;    Grey correlation analysis methods;    Model-based OPC;    Neural network prediction model;    Prediction model;    PV power generation;    Stable operation;    Weather types;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/199/5/052043/pdf
DOI  :  10.1088/1755-1315/199/5/052043

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Precise prediction of photovoltaic (PV) output power can effectively improve the safe and stable operation of power grids. In this paper, the influence of weather types on the output of PV output power is analyzed. Based on extreme learning machine (ELM) neural network, a prediction model of PV power generation output taking into account weather types is established. The grey correlation analysis method is used to process the weather types, and the established ELM neural network prediction model is trained by using the prediction results of the improved equal-dimension grey (IEDG) model, and the trained model is used to predict the output of PV output power. Compared results show that the prediction model presented in this paper can predict the output of each day in different weather types. The results show that the proposed model based weather type is of high accuracy and reliability in predicting the output power of PV.