In this paper we use clustering algorithms to compute the typical Italian load profile in different days of the week in different seasons. This result can be exploited by energy providers to tailor more attractive time-varying tariffs for their customers. We find out that better results are obtained if the clustering is not performed directly on the data, but on some features extracted from the data. Thus, we compare some conventional features to identify the most informative ones in the Italian case.
Electrical load clustering: The Italian case
CRISOSTOMI, EMANUELE;FRANCO, ALESSANDRO;LANDI, ALBERTO;RAUGI, MARCO;TUCCI, MAURO;
2014-01-01
Abstract
In this paper we use clustering algorithms to compute the typical Italian load profile in different days of the week in different seasons. This result can be exploited by energy providers to tailor more attractive time-varying tariffs for their customers. We find out that better results are obtained if the clustering is not performed directly on the data, but on some features extracted from the data. Thus, we compare some conventional features to identify the most informative ones in the Italian case.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
ISGT_2014_Clustering.pdf
solo utenti autorizzati
Tipologia:
Versione finale editoriale
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
226.36 kB
Formato
Adobe PDF
|
226.36 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.