ABSTRACT:Short term forecasting of wind power is of great significance for the safe and stable operation of power system. This paper presents a new method for predicting the wind power based on the optimal weight coefficient,which synthesizes the ARIMA time series,BP neural network,RBF neural network and support vector regression. According to the forecasting error information matrix,the optimal weight coefficient in the com-bination forecasting model is obtained by using the principle of minimizing the error square. The method can effectively synthe-size the advantages of each single forecasting model, and reduce the risk of forecasting. Simulations of the real case suggest that the proposed combination forecasting model has a high accuracy,which can quickly determine the optimal weight coefficient and reduce the prediction error.%风电功率的短期预测对于电力系统的安全稳定运行具有重要意义。提出了一种基于最优权系数的风电功率短期预测组合方法,该方法将ARIMA时间序列、BP神经网络、RBF神经网络和支持向量回归机这4种单一预测模型进行综合,并根据预测误差信息矩阵,以误差平方和最小为原则得到组合预测模型中的最优权系数,以此构成组合预测模型,该模型能够有效地综合各单一预测模型的优势,降低预测风险。仿真实例表明:所提组合预测模型预测精度高,能够方便快速地确定最优权重系数值,降低预测误差。
展开▼