Wind Prediction Based on Improved BP Artificial Neural Network in Wind Farm

• Published in: 2010 International Conference on Electrical and Control Engineering pp. 2548 - 2551
• Main Authors: Keyuan Huang, Lang Dai, Shoudao Huang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2010
• Subjects: Adaptation model; Artificial neural networks; Biological system modeling; BP neural networks; Data models; Predictive models; wind farm; Wind forecasting; wind power generation; Wind speed; wind speed prediction
• ISBN: 1424468809; 9781424468805
• DOI: 10.1109/iCECE.2010.630

Wind power prediction is important to the operation of power system with comparatively large mount of wind power. It can relieve or avoid the disadvantageous impact of wind farm on power systems. Because the traditional neural network may fall into local convergence, so it will be effective to improve the training algorithm to improve its convergence and accuracy of prediction. In this paper, a model for wind speed prediction was constructed based on adaptive learning rate of BP neural network, the selected historical wind speed data of a certain time were use as model inputs, so that we can predict the wind speed of the same time in the future and its accuracy analysis. Research shows that the improved BP neural network model can effectively achieve the long-term wind speed prediction.