Open AccessDistributed Photovoltaic Short-Term Power Prediction Based On Genetic Algorithm Optimized BP Neural Network
Author(s) -
Baili Zhou,
Dandan Yan,
Lianying Xiong,
Yumei Li,
Yufan Zhang
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/692/2/022104
Subject(s) - photovoltaic system , renewable energy , electricity generation , artificial neural network , computer science , power (physics) , electric power system , genetic algorithm , grid connected photovoltaic power system , maximum power point tracking , electronic engineering , engineering , electrical engineering , machine learning , voltage , physics , quantum mechanics , inverter
With the rapid development of the world economy, energy demand is increasing.Photovoltaic power generation has the advantages of green, environmental protection and renewable, and the proportion of photovoltaic power generation, a new reusable clean energy in the power generation system, has shown a steady increase;However, the power output of photovoltaic power generation systems is affected by many factors, presenting a high degree of uncertainty and volatility, which brings high difficulties to the large-scale grid-connected operation of photovoltaic power generation.Aiming at the shortcomings of existing photovoltaic power generation forecasting, this paper builds a photovoltaic power station power prediction model based on genetic algorithm and BP neural network algorithm, and uses photovoltaic power station operation examples to verify the validity of the model.By using the global search capability of genetic algorithm to optimize the initial weights and thresholds of BP neural network, the prediction accuracy of photovoltaic power generation is improved, which can provide a reference for photovoltaic power generation prediction engineering practice.