Research on Short-term Load Forecast of Shopping Mall Based on Similar Day Selection and BP Neural Network

Abstract

This paper presents a load forecasting model and the way it was applied to a real case study to forecast the electrical consumption of a shopping mall in Shanghai. Firstly, the meteorological factors were normalized, and mutual information was used to select the key meteorological factor. Then, based on the key meteorological factor, the Euclidean distance was used to select the similarity days and the similarity days were sorted in descending order according to the Euclidean distance. Finally, the datas of similar daily load and key meteorological factor were input into the BP neural network model to forecast the short-term load of the shopping mall in summer 2017. The results show that the proposed method, which combines the similarity day selection and the BP neural network is of great practicality.