Research on power generation prediction of photovoltaic power station based on improved neural network

Read full text Summarise with VIRAT
Authors: Yuan Hu, Qin Xie, Zhao Liu, Mengjin Hu, Hongwei Li, Yuan Bo, Yaping Wang
Cited by: 0
References: 3

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The large-scale construction of photovoltaic power plants makes more and more green power connected and utilized, which also brings great impact on the carrying capacity of the power grid. Forecasting the power generation of photovoltaic power plants can better promote the stable regulation of the power grid and promote the consumption of new energy. In this paper, the influence of main environmental factors on photovoltaic power generation is analyzed by Pearson similarity, and a photovoltaic prediction model is established. The model is solved by combining adaptive genetic algorithm and improved Drosophila algorithm to optimize neural network. Finally, the historical sample data of photovoltaic power plants are used for simulation. By comparing the photovoltaic power generation prediction effects of single BP algorithm, GA-BP combined algorithm and GA-FOA-BP intelligent algorithm, it is proved that the method of combining improved Drosophila algorithm to optimize neural network and genetic algorithm to solve the prediction model can reduce the instability of photovoltaic output prediction to some extent and has good application value.

Fields of Study & Subjects

Solar Radiation and Photovoltaics Energy Load and Power Forecasting Photovoltaic System Optimization Techniques

Publication details

Journal / source
EAI Endorsed Transactions on Energy Web
Volume
12
Publication date
31 March 2026
Language
EN