Prediction of energy consumption based on LSTM Artificial Neural Network - Université de Picardie Jules Verne Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Prediction of energy consumption based on LSTM Artificial Neural Network

Sameh Mahjoub
Jean-Baptiste Masson

Résumé

Short term power consumption forecasting has recently gained increasing attention due to the increasing development of smart grids and the advent of advanced measuring infrastructure. In fact, prediction of future power loads turns out to be a key issue to avoid energy wastage and to build effective power management strategies. Energy consumption information can be considered as historical time se-ries data that are required to extract all meaningful knowledge and then forecast the future consumption. This paper proposes a novel approach based on Long Short-Term Memory (LSTM) network for predicting the periodic energy consumption. The LSTM network has been favored in this work to predict future load consumption and prevent consumption peaks. This network is constructed to model and forecast sequential data. To provide a comprehensive evaluation of this method, we have performed several experiments using real measurement data power consumption in a French city. The experimental results on various time horizons demonstrate that the proposed method has a higher prediction performance compared to several traditional forecasting methods, such as the autoregressive moving average model (ARMA), Therefore, these predictions allow us to make decisions in advance and trigger load shedding in cases where consumption exceeds the authorized threshold in order to protect the electricity network.
Fichier non déposé

Dates et versions

hal-04012384 , version 1 (02-03-2023)

Identifiants

Citer

Sameh Mahjoub, Larbi Chrifi-Alaoui, Bruno Marhic, Laurent Delahoche, Jean-Baptiste Masson, et al.. Prediction of energy consumption based on LSTM Artificial Neural Network. 2022 19th International Multi-Conference on Systems, Signals & Devices (SSD), May 2022, Sétif, Algeria. pp.521-526, ⟨10.1109/SSD54932.2022.9955883⟩. ⟨hal-04012384⟩

Collections

U-PICARDIE LTI
5 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More