This paper introduces an evolutionary optimization algorithm as a tool for training an Artificial Neural Network used for production forecasting of solar energy PV plants. This optimized procedure essentially represent a bio-inspired heuristic search technique which is used to solve complex forecasting problems modeled on the concepts of biological neurons. Some simulation results are reported to highlight advantages and drawbacks of the proposed method in order to suitably apply this algorithm to a neuro-fuzzy system application in solar energy production. The weather forecast data related to the PV plants are supplied by the airport service close to the production site and relative data are pre-processed using Fuzzy Logic techniques.
Neuro-fuzzy predictive model for PV energy production based on weather forecast
GRIMACCIA, FRANCESCO;MUSSETTA, MARCO;ZICH, RICCARDO
2011-01-01
Abstract
This paper introduces an evolutionary optimization algorithm as a tool for training an Artificial Neural Network used for production forecasting of solar energy PV plants. This optimized procedure essentially represent a bio-inspired heuristic search technique which is used to solve complex forecasting problems modeled on the concepts of biological neurons. Some simulation results are reported to highlight advantages and drawbacks of the proposed method in order to suitably apply this algorithm to a neuro-fuzzy system application in solar energy production. The weather forecast data related to the PV plants are supplied by the airport service close to the production site and relative data are pre-processed using Fuzzy Logic techniques.File | Dimensione | Formato | |
---|---|---|---|
FUZZ11_solar_published.pdf
Accesso riservato
:
Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione
149.03 kB
Formato
Adobe PDF
|
149.03 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.