Electricity Demand Forecasting through Natural Language Processing with Long Short-Term Memory Networks - Mines Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Electricity Demand Forecasting through Natural Language Processing with Long Short-Term Memory Networks

Résumé

Electricity demand forecasting is a well established research field. Usually this task is performed considering historical loads, weather forecasts, calendar information and known major events. Recently attention has been given on the possible use of new sources of information from textual news in order to improve the performance of these predictions. This paper proposes a Long and Short-Term Memory (LSTM) network incorporating textual news features that successfully predicts the deterministic and probabilistic tasks of the UK national electricity demand. The study finds that public sentiment and word vector representations related to transport and geopolitics have timecontinuity effects on electricity demand. The experimental results show that the LSTM with textual features improves by more than 3% compared to the pure LSTM benchmark and by close to 10% over the official benchmark. Furthermore, the proposed model effectively reduces forecasting uncertainty by narrowing the confidence interval and bringing the forecast distribution closer to the truth.
Fichier principal
Vignette du fichier
ISGT2023-YunBai.pdf (4 Mo) Télécharger le fichier
ISGT-paper.pdf (861.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04205841 , version 1 (13-09-2023)

Identifiants

  • HAL Id : hal-04205841 , version 1

Citer

Yun Bai, Simon Camal, Andrea Michiorri. Electricity Demand Forecasting through Natural Language Processing with Long Short-Term Memory Networks. 2023 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), IEEE Power & Energy Society (PES); Université Grenoble Alpes, Oct 2023, Grenoble, France. ⟨hal-04205841⟩
51 Consultations
36 Téléchargements

Partager

Gmail Facebook X LinkedIn More