Very short-term wind speed prediction: A new artificial neural network–Markov chain model

• Published in: Energy conversion and management Vol. 52; no. 1; pp. 738 - 745
• Main Authors: Pourmousavi Kani, S.A., Ardehali, M.M.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 2011; Elsevier
• Subjects: Applied sciences; Artificial neural network; Artificial neural networks; Chains; Direct power generation; Energy; Exact sciences and technology; Learning theory; Management; Markov chain approach; Mathematical models; Natural energy; Neural networks; Very short-term prediction; Wind energy; Wind speed; Wind speed prediction; Very short-term prediction; Wind speed prediction; Artificial neural network; Markov chain approach
• ISSN: 0196-8904; 1879-2227
• DOI: 10.1016/j.enconman.2010.07.053

As the objective of this study, artificial neural network (ANN) and Markov chain (MC) are used to develop a new ANN–MC model for forecasting wind speed in very short-term time scale. For prediction of very short-term wind speed in a few seconds in the future, data patterns for short-term (about an hour) and very short-term (about minutes or seconds) recorded prior to current time are considered. In this study, the short-term patterns in wind speed data are captured by ANN and the long-term patterns are considered utilizing MC approach and four neighborhood indices. The results are validated and the effectiveness of the new ANN–MC model is demonstrated. It is found that the prediction errors can be decreased, while the uncertainty of the predictions and calculation time are reduced.