Power generation forecasting model for photovoltaic array based on generic algorithm and BP neural network

• Published in: IEEE ... International Conference on Cloud Computing and Intelligence Systems pp. 380 - 383
• Main Authors: Zhengqiu Yang, Yapei Cao, Jiapeng Xiu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2014
• Subjects: BP Neural network; Forecasting; Genetic algorithm; Genetic algorithms; Neural networks; Photovoltaic generation (PV); Photovoltaic systems; Predictive models; Short-term forecasting
• ISBN: 1479947202; 9781479947201
• ISSN: 2376-5933
• DOI: 10.1109/CCIS.2014.7175764

High concentration photovoltaic is a new type of solar power generation mode, which has better photoelectric conversion rate but is more vulnerable to weather factors. Therefore, accurate and efficient forecasting methods have important significance of increasing the security and stability of the solar power station. This paper focuses on the short-term forecasting method which aims at forecasting power generation in five minutes. This paper uses BP neural network(BP-NN) as the basic forecasting model and applies generic algorithm(GA) to optimize the weights and thresholds of BP-NN. The experimental results show that, the prediction effect of this method is ideal.