Forecasting Electricity Consumption using ARIMA Model

Autoregressive integrated moving average, ARIMA, is a popular technique, which is used to fit time series data for prediction and forecasting. This paper proposes ARIMA models with different sets of parameters for forecasting electricity consumption. The three ARIMA models, which are quite good and robust to develop a reliable model, are investigated to forecast electricity consumption for providing the required level of performance. The best fitted model, effective and reliable approach, and network structure are determined according to the prediction performance. For this purpose, we use synthetic dataset and electricity consumption data in industries at Guangdong province in China. The experimental results show that the ARIMA(1,1,1) has high precision, stable predictions and suitable for predicting electricity consumption. The forecasting results are essential to manage the required electricity demand in various kind of industries and other sectors.