The increasing availability of data gathered from smart meters makes it possible to develop specific data analytics procedures to extract knowledge from data. The analysis of huge amounts of data coming from millions of users needs appropriate platforms and efficient algorithms. The platform SHAPE (Statistical Hybrid Analysis for load ProfilE), set up by e-distribuzione, has enabled to determine, for the first time in Italy, the consumption classes at national level based on the behaviour of low-voltage customers. This paper discusses the data handling process in SHAPE, based on customer sampling by macro-categories, definition of consistent time periods, and clustering-based load profiling, and addresses specific applications such as customer classification, load prediction, probabilistic aggregation of residential loads, and sharing of the energy not supplied by macro-categories of users.

Unveil the Shape: Data Analytics for Extracting Knowledge from Smart Meters / Chicco, Gianfranco; Notaristefano, Antonio; Piglione, Federico. - In: L'ENERGIA ELETTRICA. - ISSN 1590-7651. - ELETTRONICO. - 96, no. 6:(2019), pp. 1-15. [10.36156/ENERGIA06_01]

Unveil the Shape: Data Analytics for Extracting Knowledge from Smart Meters

Gianfranco Chicco;Antonio Notaristefano;Federico Piglione
2019

Abstract

The increasing availability of data gathered from smart meters makes it possible to develop specific data analytics procedures to extract knowledge from data. The analysis of huge amounts of data coming from millions of users needs appropriate platforms and efficient algorithms. The platform SHAPE (Statistical Hybrid Analysis for load ProfilE), set up by e-distribuzione, has enabled to determine, for the first time in Italy, the consumption classes at national level based on the behaviour of low-voltage customers. This paper discusses the data handling process in SHAPE, based on customer sampling by macro-categories, definition of consistent time periods, and clustering-based load profiling, and addresses specific applications such as customer classification, load prediction, probabilistic aggregation of residential loads, and sharing of the energy not supplied by macro-categories of users.
File in questo prodotto:
File Dimensione Formato  
COP 6 2006 (Page 1) - ee2019_06_riv.pdf

non disponibili

Descrizione: Articolo principale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 2.89 MB
Formato Adobe PDF
2.89 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2831636