Power forecast research of photovoltaic system based on double-level neural network

2018 International Conference on New Energy and Future Energy System

Cheng, K.^1 ; Sun, Q.Q.^2 ; Ma, X.Y.^2

Solar Energy Research Institute, Northwestern Polytechnical University, Xi'an

710072, China^1

School of Power and Energy, Northwestern Polytechnical University, Xi'An, 710072, China^2

关键词: Double level;    Highest temperature;    Photovoltaic generation system;    Photovoltaic power generation;    Photovoltaic systems;    Power forecast;    Second level;    Single level;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/188/1/012007/pdf
DOI  :  10.1088/1755-1315/188/1/012007

来源: IOP

【 摘 要 】

A photovoltaic generation system is affected by many factors. The traditional method of forecasting photovoltaic power generation is more complicated. A double-level neural network is designed with consideration of these factors: the first level network calculates a real solar radiation with input of theory radiation and weather coefficient; the second level network calculates the final result generation power with input of real solar radiation which comes from the first network and the highest temperature which comes from weather forecast. The final power results indicate this method has good forecast capacity, calculate results are very close to measure value and errors are less than single level network.