A Gray RBF Model Improved by Genetic Algorithm for Electrical Power Forecasting

In order to improve electrical power forecasting accuracy of the Energy Internet, this paper proposes a gray RBF model improved by genetic algorithm. This method forecasts power of the micro-grid using the characteristics that gray model can weaken data randomness and RBF neural network is highly nonlinear. Considering the problem of local optimum and convergence, the paper uses genetic algorithm for net optimization. The micro-grid monitoring data are utilized to forecast the electricity load and the renewable energy output power in the proposed method. Compared to the traditional RBF model prediction, the undying method can provide higher precision and more excellent adaptability.

[1]  Ye Li.  Photovoltaic Power Forecasting Model Based on Genetic Algorithm and Fuzzy Radial Basis Function Neural Network , 2015 .

[2]  Huang Mei,et al.  Short-term wind power prediction based on statistical clustering analysis , 2011 .

[3]  Wen Bu-ying.  Overview on Prediction Methods of Wind Speed and Wind Power , 2011 .

[4]  Wu Jun-ji,et al.  Application of gray system theory in load forecasting , 2004 .

[5]  Changhao Xia,et al.  A New Model for Short-Term Power System Load Forecasting Using Wavelet Transform Fuzzy RBF Neural Network , 2014 .

[6]  Zhang Suxian.  Short-term Power Load Forecasting Based on Big Data , 2015 .

[7]  Sifeng Liu,et al.  Comparison of China's primary energy consumption forecasting by using ARIMA (the autoregressive integrated moving average) model and GM(1,1) model , 2016 .

[8]  Chen Xingying.  Multi-objective unit commitment modeling and optimization for energy-saving and emission reduction in wind power integrated system , 2011 .

[9]  Dong-Xiao Niu,et al.  Support Vector Machine Model in Electricity Load Forecasting , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[10]  Pang Qingle.  A Rough Set-Based Neural Network Load Forecasting Algorithm and Its Application in Short-Term Load Forecasting , 2010 .

[11]  Tian Jie,et al.  Wavelet neural network embedded expert system used in short-term load forecasting , 2011, 2011 2nd IEEE International Conference on Emergency Management and Management Sciences.