Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine. (15th June 2017)

• Record Type: Journal Article
• Authors: Yuan, Xiaohui; Tan, Qingxiong; Lei, Xiaohui; Yuan, Yanbin; Wu, Xiaotao
• Is Part Of: Energy. Volume 129(2017)
• Page Start: 122
• Page End: 137
• Publication Date: 2017-06-15
• Subjects: Wind power prediction -- Autoregressive fractionally integrated moving average -- Least square support vector machine -- Autocorrelation function -- Long memory characteristics; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2017.04.094
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Precise prediction of wind power can not only conduct wind turbine's operation, but also reduce the impact on power systems when wind energy is injected into the grid. A hybrid autoregressive fractionally integrated moving average and least square support vector machine model is proposed to forecast short-term wind power. The proposed hybrid model takes advantage of the respective superiority of autoregressive fractionally integrated moving average and least square support vector machine. First, the autocorrelation function analysis is used to detect the long memory characteristics of wind power series, and the autoregressive fractionally integrated moving average model is applied to forecast linear component of wind power series. Then the least square support vector machine model is established to forecast nonlinear component of wind power series by making use of wind speed, wind direction and residual error series of the autoregressive fractionally integrated moving average model. Finally, the prediction of wind power is obtained by integrating the prediction results of autoregressive fractionally integrated moving average and least square support vector machine. Compared with other models, the results of two examples demonstrate that the proposed hybrid model has higher accuracy of wind power prediction in terms of three performance indicators. Highlights: Autocorrelation function is applied to detect long memory characteristics of wind power. Autoregressive fractionally integrated moving average is used to model linear part in wind power. Least square support vector machine is adopted to model nonlinear component in wind power. Prediction accuracy of wind power is improved by comparison of other models.