Towards Smart City Energy Analytics: Identification of Electric Consumption Patterns Based on Clustering Approaches

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 Kmeans 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.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01212957
Contributor : Ifsttar Cadic <>
Submitted on : Wednesday, October 7, 2015 - 3:30:51 PM
Last modification on : Wednesday, April 11, 2018 - 12:10:02 PM

Identifiers

  • HAL Id : hal-01212957, version 1

Collections

Citation

Fateh Nassim Melzi, Mohamed Haykel Zayani, Amira Benhamida, François Stephan, Allou Same, et al.. Towards Smart City Energy Analytics: Identification of Electric Consumption Patterns Based on Clustering Approaches. CSD&M 2015 - 6th International Conference on Complex Systems Design and Management, Nov 2015, PARIS, France. 12p. ⟨hal-01212957⟩

Share

Metrics

Record views

133