A GA-BP hybrid algorithm based ANN model for wind power prediction

This paper deals with a hybrid GA-BP ANN approach for wind power prediction. Wind energy is one of the renewable energy options recently being developed significantly throughout the world in order to achieve low-emission targets, and it keeps extending its penetration in electric power generation. However, there are important issues emerging in the integration of wind power resulting from its intermittent and uncertain nature. An accurate wind power generation forecasting tool is necessary for planning efficient operation of power systems and to ensure reliability of supply. In this paper, a multi-layered feed-forward artificial neural network optimized by the genetic algorithm and trained by the back propagation (BP) learning algorithm has been used to develop a model for prediction of wind power generation. To demonstrate the effectiveness of the proposed method, it is tested based on practical information of wind power generation profile of the 2.5 MW wind turbine installed at a case study microgrid in Beijing. The proposed model is compared with BP neural network based model. Evaluation of forecasting performance is made with the persistence forecasting method as a reference model. Comparison of the results with actual scenario demonstrated that the proposed approach is accurate and reliable.