Combination Forecasting Model of Daily Electricity Consumption in Summer Based on Daily Characteristic Meteorological Factors

Abstract

Daily electricity consumption in summer is affected by numerous meteorological factors. In order to improve the accuracy of daily electricity consumption forecasting, a summer daily electricity consumption combination forecasting model based on daily characteristic meteorological factors is proposed in this paper. Firstly, the relationship between various meteorological indexes and daily electricity consumption is analysed considering the coupling effect and accumulative effect of meteorological factors on daily electricity consumption, and a single forecast model of daily electricity consumption is established. Then the meteorological mapping function is designed to evaluate the impact of each meteorological index on daily electricity consumption, and the weight of each single forecasting model is calculated. Finally, a combination forecasting model of daily electricity consumption in summer is established. The parameters of meteorological mapping function are optimized by adaptive training and virtual forecasting, and solved by genetic algorithm. Taking the daily electricity consumption in Chongqing in the summer of 2018 as an example, the results have shown that the proposed combination forecasting model can effectively improve the accuracy of daily electricity consumption forecasting.