Comprehensive Forecasting Method of Monthly Electricity Consumption Based on Time Series Decomposition and Regression Analysis

Abstract

Power consumption prediction is the basis of implementing planned power consumption and preparing production plan. It is one of the main projects in the design of industrial and mining enterprises. It is also an important link to ensure the balance between national economic needs and power supply. Due to the influence of distributed energy and the change of power demand and load characteristics of the user side compared with the past, the power consumption prediction starts to face small-scale users and is more easily disturbed by various influencing factors, so the traditional prediction method is not fully suitable for today's power consumption prediction. Firstly, STL is used to decompose the power consumption sequence of corresponding month into trend component, season component and random component. Secondly, the BP neural network model is used to predict the seasonal component of the month when the seasonal mutation and major festivals are located. ARIMA model is used to predict the trend component. The average value is used to predict the random components. Then, the predicted values of the three components are reconstructed into the final predicted values. Finally, the algorithm is compiled by R language, and the validity of the proposed method is verified by the actual monthly electricity sales data of a University Park in the north. And further consider the prediction method of economic factors.