Predicting Electricity Consumption in Baghdad Governorate Using SARIMA and FB Prophet Models: A Comparative Study

Abstract

Electricity represents the important and vital nerve of both economic and social activities, as its consumption is one of the essential matters that has gained great importance, and it is also an important indicator of the level of development in modern societies. Through this, this research aimed to build highly accurate predictive models to analyze the electricity consumption data in Baghdad Governorate. This study relied on consumption data on a daily basis for the period from 1/1/2024 to 12/31/2024, which was obtained from the Operations and Control Department of the Ministry of Electricity. Two predictive models were used to achieve the research goal, including: the SARIMA model and the Facebook Prophet (FB Prophet) model. To compare the performance of each of the two models, the following comparison criteria were used: the Mean Absolute Error (MAE), the Mean Absolute Percentage Error (MAPE), and the Root Mean Square Error (RMSE). The results showed the superiority of the SARIMA model, as it obtained the lowest values ​​of the above comparison criteria. Accordingly, the future values ​​of the electricity consumption data in Baghdad Governorate were predicted by the model SARIMA.