In order to consider the influence of multiple factors on electricity and improve the accuracy of monthly electricity forecasting. A monthly electricity forecasting method is proposed based on the K-L information method and ARIMA error correction. Based on screening relevant indicators, the correlation analysis method is used to make regression modeling on the influence indicators and electricity, calculate of fitting errors, and construct a new non - stationary time series, combined with the ARIMA model to modify this series. Monthly electricity predictions obtained with better accuracy, have higher application value.