A comparison between the hybrid method (PHANN – Physical Hybrid Artificial Neural Network) and the 5 parameter Physical model, which have been determined by the particle filter algorithm, is presented here. These methods have been employed to perform the dayahead forecast of the output power of a photovoltaic plant. The aim of this work is to assess the forecast accuracy of the two methods.

Day-ahead PV power forecast by hybrid ANN compared to the five parameters model estimated by particle filter algorithm

OGLIARI, EMANUELE GIOVANNI CARLO;BOLZONI, ALBERTO;LEVA, SONIA;MUSSETTA, MARCO
2016-01-01

Abstract

A comparison between the hybrid method (PHANN – Physical Hybrid Artificial Neural Network) and the 5 parameter Physical model, which have been determined by the particle filter algorithm, is presented here. These methods have been employed to perform the dayahead forecast of the output power of a photovoltaic plant. The aim of this work is to assess the forecast accuracy of the two methods.
2016
Artificial Neural Networks and Machine Learning – ICANN 2016
9783319447803
978-3-319-44781-0
Artificial neural networks; Day-ahead energy forecast; Particle filter algorithm; Theoretical Computer Science; Computer Science (all)
File in questo prodotto:
File Dimensione Formato  
chp%3A10.1007%2F978-3-319-44781-0_35.pdf

Accesso riservato

: Publisher’s version
Dimensione 540.26 kB
Formato Adobe PDF
540.26 kB Adobe PDF   Visualizza/Apri

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/11311/1007632
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 6
social impact