Prediction of Short-Term Power Output of Wind Farms Based on Extreme Learning Machine

Abstract

Due to the fluctuation and intermittency of wind power, wind power forecasting is an effective way to reduce its impact on power system. This chapter introduces extreme learning machine (ELM) for wind power generation prediction of a wind farm. ELM has the advantages of small training error, small weight norm, fast training speed, and high generalization performance. The weather forecast data and power output of wind farm were set as samples to build the neural network model of predicting wind power based on ELM. In order to verify the advantages of the ELM model, the estimation results of ELM and BP neural network were compared. Finally, it was found that the prediction accuracy and generalization ability of ELM in wind power prediction was satisfactory, and it had the superiority of simple implement and fast estimate.KeywordsWind TurbineWind PowerExtreme Learning MachineWind FarmExtreme Learning Machine AlgorithmThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.