Aiming at the conventional BP neural network model in the prediction of solar power generation, which has the drawback of low prediction accuracy and slow convergence speed, this paper comes up with an improving BP neural network model for the prediction of photovoltaic power generation. In the paper, an improved BP neural network model is proposed to improve the conventional BP model by increasing the momentum term and adaptive selecting the best hidden layer. In this paper, an improved BP neural network model is proposed. In this paper, the six meteorological factors that most effect PV power are extracted and used as the network model meteorological factors, as inputs to the network model, and then built an improved BP network model, to make direct prediction of the power data; Finally, the BP network model is used to improve the conventional BP model.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Application of Improved Neural Network Models in Photovoltaic Power Generation Forecasting


    Contributors:
    Xue, Jianli (author) / Chen, Libo (author) / Hu, Pengtao (author) / Liu, Shuai (author) / Wu, Yi (author)


    Publication date :

    2024-10-23


    Size :

    633409 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English






    A review of some main improved models for neural network forecasting on time series

    Ming-liang Chai, / Su Song, / Ning-ning Li, | IEEE | 2005


    A review of some main improved models for Neural Network forecasting on time series

    Chai, M. L. / Song, S. / Li, N. N. et al. | British Library Conference Proceedings | 2005