Analysis and Research on Forecasting Electricity Demand Based on ARMA and VAR Model

Abstract

This paper uses the relevant data from the official website of the National Bureau of Statistics of China from 1980 to 2017, and uses the ARMA model and VAR-based co-integration analysis to predict the electricity demand from 2018 to 2020, making the forecast data more convincing. Besides, this paper uses unit root test, Granger causality analysis, Johansen test and other co-integration analysis methods to empirically study the determinants of China's electricity demand, and establish a longterm equilibrium and its fluctuation relationship between electricity demand and GDP, urbanization rate, industrialization rate, and electricity use efficiency. The forecast results were compared and analyzed, and corresponding policy recommendations were put forward to provide data support and reference for the future development of China's power industry.