Early classification of individual electricity consumptions - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Early classification of individual electricity consumptions

Résumé

EDF3 hires special contracts with costumers to flatten the consumption peaks. Smart meters are able to record consumptions and will be set up over 35 millions households. In this paper, we highlight the interest of early classification for detecting the households which probably contribute to the evening peak. The proposed approach is based on a collection of classifiers. In our experiments, we “early classified” the consumption of 1000 irish households and we obtained promising results.
Fichier non déposé

Dates et versions

hal-01565545 , version 1 (19-07-2017)

Identifiants

  • HAL Id : hal-01565545 , version 1
  • PRODINRA : 399110

Citer

Asma Dachraoui, Alexis Bondu, Antoine Cornuéjols. Early classification of individual electricity consumptions. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD 2013), Sep 2013, Prague, France. ⟨hal-01565545⟩
89 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More