Deterministic and probabilistic wind power forecasting using a variational Bayesian-based adaptive robust multi-kernel regression model

Abstract

Accurate wind power forecasting has great practical significance for the safe and economical operation of power systems. In reality, wind power data are recorded at high time resolution (5s, etc.). The original high-resolution data are averaged to produce the low-resolution time series (10min, etc.) used in wind power forecasts. Therefore, the current wind power forecasting models neglect certain information in the high-resolution data. Moreover, the common Gaussian assumption used for the error term in the current wind power forecasting model is not consistent with the real, complex wind power forecasting error distribution. In this paper, an adaptive robust multi-kernel regression model is proposed to deal with the two disadvantages mentioned above. First, a multi-kernel regression model is constructed to process the multi-resolution wind power data. Second, a Gaussian mixture model is employed to model the complex wind power forecasting error. Finally, a variational Bayesian method is introduced to optimize the proposed model and to cause the simultaneous output of both the deterministic and probabilistic forecasts. Two case studies have been conducted on real wind power data from Chinese wind farms. The results show that the proposed model provides more accurate deterministic forecasts and more useful probabilistic forecasts, and has great potential for practical application in power systems.