Short-term wind power forecasting based on Maximum Correntropy Criterion

In order to improve the accuracy of the wind power forecasting, aiming at the high volatility and weak Gaussion distribution feature of the wind power output, this paper proposes a new criterion - Maximum Correntropy Criterion (MCC) to guide the parameter optimization process of least square support vector machine (LSSVM). In the model, firstly, the measured data of wind farm is filtered and normalized and the best dimension of input variables is determined by a fixed parameter set, then we separately use Grid Search and particle swarm optimization (PSO) to optimize the parameter set with MCC. Finally, we forecast the short-term wind power with the optimized parameter set and evaluate the result with four assessment criteria. The parameter optimization process with MCC is more responsive with the wind power output character so the prediction accuracy could be improved about 5%-10% compared with the traditional parameter optimization method.