Forecasting Electricity Consumption in France Using a Hybrid Method Based on Artificial Intelligence and Statistical Approaches - Université de Picardie Jules Verne Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Forecasting Electricity Consumption in France Using a Hybrid Method Based on Artificial Intelligence and Statistical Approaches

Résumé

This work proposes an innovative hybrid method for accurate one-day electricity consumption forecasting. By combining artificial intelligence (AI) and statistical techniques, our hybrid model optimizes electricity production forecasting. Unlike methods used by RTE, our approach relies solely on consumption data, eliminating the need for additional variables. By preprocessing historical data and employing neural networks and statistical models, our hybrid method achieves exceptional accuracy, closely approaching RTE's performance, while significantly reducing data usage and computational demands. This promising approach streamlines electricity production planning, offering an efficient and environmentally friendly solution to environmental and economic challenges.
Fichier non déposé

Dates et versions

hal-04520446 , version 1 (25-03-2024)

Identifiants

Citer

Mohamed Hamza Kermia, Konstantinos Aiwansedo, Oussama Djadane, Jérôme Bosche, Dhaker Abbes. Forecasting Electricity Consumption in France Using a Hybrid Method Based on Artificial Intelligence and Statistical Approaches. 2023 IEEE 11th International Conference on Systems and Control (ICSC), Dec 2023, Sousse, Tunisia. pp.348-353, ⟨10.1109/ICSC58660.2023.10449779⟩. ⟨hal-04520446⟩
5 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More