Identifying Daily Electric Consumption Patterns from Smart Meter Data by Means of Clustering Algorithms

Résumé : This paper presents clustering approaches applied on daily energy consumption curves of buildings. Our aim is to identify a reduced set of consumption patterns for a tertiary building during one year. These patterns depend on the temperature throughout the year as well as the type of the day (working day, work-free day and school holidays). Two clustering approaches are used independently, namely the functional K-means algorithm, that takes into account the functional aspect of data and the Expectation-Maximization algorithm based on Gaussian Mixture Model (EM-GMM). The clustering results of the two algorithms are analyzed and compared. This study represents the first step towards the development of prediction models for energy consumption.
Type de document :
Communication dans un congrès
ICMLA 2015 - IEEE International Conference on Machine Learning and Applications, Dec 2015, MIAMI, United States. 6p, 2015
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01215017
Contributeur : Ifsttar Cadic <>
Soumis le : mardi 13 octobre 2015 - 14:56:14
Dernière modification le : mercredi 11 avril 2018 - 12:10:02

Identifiants

  • HAL Id : hal-01215017, version 1

Collections

Citation

Fateh Nassim Melzi, Mohamed Haykel Zayani, Amira Ben Hamida, Allou Same, Latifa Oukhellou. Identifying Daily Electric Consumption Patterns from Smart Meter Data by Means of Clustering Algorithms. ICMLA 2015 - IEEE International Conference on Machine Learning and Applications, Dec 2015, MIAMI, United States. 6p, 2015. 〈hal-01215017〉

Partager

Métriques

Consultations de la notice

330