A comparative study to obtain an adequate model in prediction of electricity requirements for a given future period

Recent years have seen an increasing interest in providing accurate prediction models for electrical energy consumption. In Smart Grids, energy consumption optimization is critical to enhance power grid reliability, and avoid supply-demand mismatches. Additional economic and environmental benefits can be obtained if a proper and reliable description and forecast of energy absorption is available. This research presents fits for neural network model, and comparative resulting forecasts with those obtained from Box- Jenkins Method. We use time series data of monthly electrical energy consumption, into Basra city (Iraq) from 2007-2016, to perform a comparative. The result of the data analysis show that the proper and efficient model for representing time series data is the multiplicative seasonal model of order: SARIMA (3, 1, 3) × (0, 1, 1). According to this model the Research forecast the monthly electricity consumption for January 2017 to December 2018. As for application, Box-Jenkins Method has given more appropriate forecasts than those given by Back propagation artificial neural network. We used Minitab program in the statistical aspect and Alyuda program in the neural network aspect.