Forecasting Electricity Consumption: A Comparative Analysis of ARIMA and Artificial Neural Network

This research investigates the accurate forecasting of electricity consumption across various sectors in India. The study employs two prominent time series forecasting models: Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN). The performance of these models is evaluated using various error metrics, such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The results demonstrate that the ANN model outperforms the ARIMA model in terms of accuracy and forecast reliability. This research provides valuable insights into electricity consumption patterns in India and contributes to more effective energy planning and resource management.