Electricity Demand Prediction by a Transformer-Based Model

Mahmood, Ahmed Mohammed; Abdul Zahra, Musaddak Maher; Hamed, Waleed; Bashar, Bashar S.; Abdulaal, Alaa Hussein; Alawsi, Taif; Adhab, Ali Hussein

doi:10.30486/mjee.2022.696520

Original Article

Electricity Demand Prediction by a Transformer-Based Model

Authors

Department of Optical Techniques, AlNoor University College, Iraq
Al-Nisour University College, Baghdad, Iraq
Medical technical college, Al-Farahidi University, Baghdad, Iraq
Department of Medical instruments engineering techniques, Al-Farahidi University, Baghdad,10021, Iraq
Medical Device Engineering, Ashur University College, Baghdad, Iraq
Mazaya University College/ Dhi Qar, Iraq
Department of Medical Laboratory Technics, Al-Zahrawi University College, Karbala, Iraq

Abstract

The frighteningly high levels of power consumption at present are caused mainly by the expanding global population and the accessibility of energy-hungry smart technologies. So far, various simulation tools, engineering- and AI-based methodologies have been utilized to anticipate power consumption effectively. While engineering approaches forecast using dynamic equations, AI-based methods forecast using historical data. The modeling of nonlinear electrical demand patterns is still lacking for durable solutions, however, the available approaches are only effective for resolving transient dependencies. Furthermore, because they are only based on historical data, the current methodologies are static in nature. In this research, we present a system based on deep learning to anticipate power consumption while accounting for long-term historical relationships. In our approach, a transformer-based model is used for the prediction of electricity demand on data collected from the regional facilities in Iraq. According to the conducted experiments, our approach claims competitive performance, achieving an error rate of 2.0 in predicting 1-day-ahead of electricity demand in the test samples.