A generalized dynamic fuzzy neural network based on singular spectrum analysis optimized by brain storm optimization for short-term wind speed forecasting

• Published in: Applied soft computing Vol. 54; pp. 296 - 312
• Main Authors: Ma, Xuejiao, Jin, Yu, Dong, Qingli
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.05.2017
• Subjects: Brain storm optimization; Generalized dynamic fuzzy neural network; Short-term wind speed forecasting; Singular spectrum analysis; Singular spectrum analysis; Generalized dynamic fuzzy neural network; Short-term wind speed forecasting; Brain storm optimization
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2017.01.033

•An effective hybrid model is proposed to forecast the short-term wind speed.•A new data preprocessing method is put forward.•The fuzzy neural network is modified.•Three comparative experiments are performed to prove the validity of the hybrid model. Wind speed forecasting plays a pivotal role in power dispatching and normal operations of power grids. However, it is both a difficult and challenging problem to achieve high-precision forecasting for the wind speed because the original sequence includes many nonlinear stochastic signals. The current conventional forecasting methods are more suitable for capturing linear trends, and artificial neural networks easily fall into a local optimum. This paper proposes a model that combines a denoising method with a dynamic fuzzy neural network to address the problems above. Singular spectrum analysis optimized by brain storm optimization is applied to preprocess the original wind speed data to obtain a smoother sequence, and a generalized dynamic fuzzy neural network is utilized to perform the forecasting. With a smaller and simpler structure of the neural network, the model can effectively achieve a rapid learning rate and accurate forecasting. Three experimental results, which cover 10-min, 30-min and 60-min interval wind speed time series data, demonstrate that the model can both satisfactorily approximates the actual value and be used as an effective and simple tool for the planning of smart grids.