Load forecasting is a useful resource for electric systems security, in order to provide valuable information to detect many vulnerable situations in advance. This resource become essential in a hospital reality, because of the continuous use of new technological instruments that require electricity. In this work a hospital energy load forecast is illustrated. The adopted approach is based on the Artificial Neural Networks, with the support of an opportune pre-training classification. The data sources are the University Eye Clinic of Genoa, S. Martino Hospital, Genoa, Italy, and the Department of Internal Medicine and Medical Specialties of the University of Genoa, Italy; in order to have different methodologies in patient treatment to determine if the same tool is advantageous in load forecasting for both wards. The presented approach results reached more than 75% of correct forecasts for the two applications

Energy load forecasting in two hospital systems through the use of Artificial Neural Networks

BERTOLINI, SIMONA;MASSUCCO, STEFANO;SILVESTRO, FEDERICO;GRILLO, SAMUELE;GIACOMINI, MAURO
2012-01-01

Abstract

Load forecasting is a useful resource for electric systems security, in order to provide valuable information to detect many vulnerable situations in advance. This resource become essential in a hospital reality, because of the continuous use of new technological instruments that require electricity. In this work a hospital energy load forecast is illustrated. The adopted approach is based on the Artificial Neural Networks, with the support of an opportune pre-training classification. The data sources are the University Eye Clinic of Genoa, S. Martino Hospital, Genoa, Italy, and the Department of Internal Medicine and Medical Specialties of the University of Genoa, Italy; in order to have different methodologies in patient treatment to determine if the same tool is advantageous in load forecasting for both wards. The presented approach results reached more than 75% of correct forecasts for the two applications
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11567/453717
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact