Abstract：Aiming at the limitations of single forecasting method, a combined method was proposed which considers the power rationing plan, based on physical methods and statistical methods. The theoretical power method, BP network method based on improved similar days and support vector machine method based on improved similar days are used to predict PV power for predicting daily, and uses the combination weighting approach of game theory method to calculate the weight of single method. The method is validated by photovoltaic system data and the forecast error is calculated and analyzed. The results show the combination weighting method, compared with a single weight that is unilateral, are more reasonable and scientific, and the method has high accuracy even in the station of the power rationing plan, which has good academic value and practical value to forecast power for PV generation system.
李贞, 崔丽艳, 陶颍军, 邱俊宏, 陈斌. 基于博弈论赋权的光伏功率组合预测模型[J]. 电气技术, 2017, 18(5): 24-29.
Li Zhen, Cui Liyan, Tao Yingjun, Qiu Junhong, Chen Bin. The Combined Model for PV Power Forecasting based on Combination Weighting Approach of Game Theory. Electrical Engineering, 2017, 18(5): 24-29.
2017, Vol. 18 
