Abstract：In order to improve the prediction accuracy, according to the characteristics of daily load curve of electric power system and the sensitivity of different period load to meteorological factors, the daily load of 96 points is divided into four periods, respectively. Based on the day before the forecasting day, the multivariate linear regression modelsare set up by taking the average load change at each period as the output variable and taking daily type, month, maximum temperature change and minimum temperature change of the forecasting day and maximum temperature change, minimum temperature changeof the day before the forecasting day as input variables. The model can calculate the ratio of the average load of the forecasting day to the average load of the previous day. The correlation analysis shows that the load curve of adjacent days has a high linear correlation, so the load of forecast day can be calculated based on the previous day's load data. Taking the load in Dongguan area as an example, the results show that the method has higher stability and accuracy, and is better than the traditional method.
李汉巨. 考虑气象因素累积效应的电力系统96点日负荷预测方法[J]. 电气技术, 2018, 19(4): 28-32.
Li Hanju. The 96 point daily load forecasting method for power system considering the cumulative effect of meteorological factors. Electrical Engineering, 2018, 19(4): 28-32.
2018, Vol. 19 
