Short-Term Electricity Generation Forecasting Using Machine Learning Algorithms: A Case Study of the Benin Electricity Community (C.E.B)

Mawugno Koffi Kodjo,Agbassou Guenoupkati,Adekunlé Akim Salami,Kossi Napo

doi:10.52825/thwildauensp.v1i.25

Mawugno Koffi Kodjo, Agbassou Guenoupkati + Show 2 more

Open Access

https://doi.org/10.52825/thwildauensp.v1i.25

Copy DOI

Abstract

Time series forecasting in the energy sector is important to power utilities for decision making to ensure the sustainability and quality of electricity supply, and the stability of the power grid. Unfortunately, the presence of certain exogenous factors such as weather conditions, electricity price complicate the task using linear regression models that are becoming unsuitable. The search for a robust predictor would be an invaluable asset for electricity companies. To overcome this difficulty, Artificial Intelligence differs from these prediction methods through the Machine Learning algorithms which have been performing over the last decades in predicting time series on several levels. This work proposes the deployment of three univariate Machine Learning models: Support Vector Regression, Multi-Layer Perceptron, and the Long Short-Term Memory Recurrent Neural Network to predict the electricity production of Benin Electricity Community. In order to validate the performance of these different methods, against the Autoregressive Integrated Mobile Average and Multiple Regression model, performance metrics were used. Overall, the results show that the Machine Learning models outperform the linear regression methods. Consequently, Machine Learning methods offer a perspective for short-term electric power generation forecasting of Benin Electricity Community sources.

Highlights

Nowadays, with the liberalization and technological advances in the energy sector, several electric companies are in perpetual competition in the energy market to satisfy customer demand
Time series forecasting in the energy sector is important for utilities for decision making to ensure the sustainability and quality of electricity supply, and the stability of the power system
Artificial Intelligence is distinguished from these prediction methods by Machine Learning algorithms that have been successful in the last decades in predicting multilevel time series

Summary

Introduction

With the liberalization and technological advances in the energy sector, several electric companies are in perpetual competition in the energy market to satisfy customer demand. The evolution of demand has huge uncertainties and follows stochastic processes due to several complex factors such as the time, weather, seasonality, economic activity, days, preferential tariffs, occasional events, etc. Unbalanced demands for electricity generation lead to economic losses and user dissatisfaction. It is important for electricity providers to maintain this balance. Underestimation of future demand can result in certain malfunctions or failures that may influence the long-term stability of the power system [1]. In this context, a robust forecasting tool remains essential for decision-

Objectives

Methods

Findings

Discussion

Conclusion