Construction of Electricity Load Forecasting Model Based on Electricity Data Analysis

Abstract

Abstract This paper builds a time series prediction model of recurrent neural networks based on time series electricity load forecasting. In this paper, the household electricity consumption record data of some residents in urban area S is taken as the research object, and the laws and characteristics of users’ electricity consumption behavior are analyzed in depth based on the real residential electricity consumption data. External factors such as temperature conditions, holidays, etc. The arithmetic cases are also analyzed using real load data sets. In the short-term continuous electricity data analysis, the smaller the time interval is, the closer its corresponding electricity consumption ratio is to 1. There is a negative correlation between long-term continuous electricity consumption. When the temperature is 30~35oC versus -5~0oC, electricity consumption rises significantly. Comparing and analyzing the time series decomposition-RNN with several models, the time series decomposition-RNN model has the highest fit at 10:00-12:00 and 12:00-14:00, and the result verifies the validity of the model proposed in this paper.