Short-Term Wind Speed Forecasting Based On Fuzzy Artmap

Abstract

Wind energy is an important cornerstone of a non-polluting and sustainable electricity supply. In practice, the integration of significant wind energy into the existing electricity supply system is a challenge due to the stochastic nature of wind power. To be able to effectively integrate wind power into existing grid systems, accurate short-term wind speed forecasting is essential. Statistical and soft computing models are mainly used for short-term forecasting and a physical fluid model is used for long-term forecasting. Soft computing models are commonly suggested for wind forecasting due to data independency and handling of non-linear nature systems. Fuzzy ARTMAP, which is a combination of fuzzy logic and adaptive resonance theory, has been shown to be superior to basic neural network models in terms of the stability–plasticity dilemma. This paper presents a novel approach to short-term wind forecasting (i.e., 12- and 24-hr forecasting) using a Fuzzy ARTMAP technique, and the results are compared to a recently proposed linear prediction technique and a conventional neural network backpropagation algorithm.