Short term wind power prediction using ANFIS

This paper proposes an ANFIS based approach for one-day-ahead hourly wind power generation prediction. The increasing penetration of wind energy to electric power generation systems imposes important issues to address resulting from its intermittent and uncertain nature. These challenges necessitate an accurate wind power generation forecasting tool for planning efficient operation of power systems and to ensure reliability of supply. In this paper, adaptive neuro-fuzzy inference systems based approach is used to develop wind power prediction model. To demonstrate the effectiveness of the proposed method, it is tested based on practical information of wind power generation profile a wind turbine installed at a practical case study microgrid in Beijing. The proposed model is compared with BP neural network based and a hybrid GA-BP NN based models. Evaluation of forecasting performance is made with the persistence forecasting method as a reference model, and results are compared with actual scenario. The proposed approach outperformed both the BP-NN and hybrid models demonstrating its favorable accuracy and reliability.