This study aims to analyze the impact of the pandemic on electricity consumption and forecast electricity demand in indonesia from 2021 to 2045 using the autoregressive integrated moving. The models are trained, predictions are made, and their performance is. In this study, the time series model used is arima.
Based on the sample size and data characteristics, arima, mlr, and prophet models were constructed and compared, and the optimum model was selected to predict the. Autoarima is employed to automatically select the best parameters for the arima, ma, ar, and sarima models. This method consists of four major stages:.
Our work applies arima models to a case study using data from recife, the capital of pernambuco, brazil, collected between march and september 2020.