Solar photovoltaic plants power output forecasting using machine learning techniques can be of a great advantage to energy producers when they are implemented with day-ahead energy market data. In this work a model was developed using a supervised learning algorithm of multilayer perceptron feedforward artificial neural network to predict the next twenty-four hours (day-ahead) power of a solar facility using fetched weather forecast of the following day. Each set of tested network configuration was trained by the historical power output of the plant as a target. For each configuration, one hundred networks ensembles was averaged to give the ability to generalize a better forecast. The trained ensembles performances were analyzed using statistical indicators. The best-performing model ensembles were eventually used to predict power from the automatically fetched weather data
Lingua originale
English
Pagine
1152-1157
Numero di pagine
6
Stato di pubblicazione
Published - 2017
Fingerprint
All Science Journal Classification (ASJC) codes
Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
title = "Day-ahead forecasting for photovoltaic power using artificial neural networks ensembles",
abstract = "Solar photovoltaic plants power output forecasting using machine learning techniques can be of a great advantage to energy producers when they are implemented with day-ahead energy market data. In this work a model was developed using a supervised learning algorithm of multilayer perceptron feedforward artificial neural network to predict the next twenty-four hours (day-ahead) power of a solar facility using fetched weather forecast of the following day. Each set of tested network configuration was trained by the historical power output of the plant as a target. For each configuration, one hundred networks ensembles was averaged to give the ability to generalize a better forecast. The trained ensembles performances were analyzed using statistical indicators. The best-performing model ensembles were eventually used to predict power from the automatically fetched weather data",
author = "Fabio Viola and Dolara and Ogliari and Magistrati and Omar and Mussetta",
year = "2017",
language = "English",
pages = "1152--1157",
}
TY - CONF
T1 - Day-ahead forecasting for photovoltaic power using artificial neural networks ensembles
AU - Viola, Fabio
AU - Dolara, null
AU - Ogliari, null
AU - Magistrati, null
AU - Omar, null
AU - Mussetta, null
PY - 2017
Y1 - 2017
N2 - Solar photovoltaic plants power output forecasting using machine learning techniques can be of a great advantage to energy producers when they are implemented with day-ahead energy market data. In this work a model was developed using a supervised learning algorithm of multilayer perceptron feedforward artificial neural network to predict the next twenty-four hours (day-ahead) power of a solar facility using fetched weather forecast of the following day. Each set of tested network configuration was trained by the historical power output of the plant as a target. For each configuration, one hundred networks ensembles was averaged to give the ability to generalize a better forecast. The trained ensembles performances were analyzed using statistical indicators. The best-performing model ensembles were eventually used to predict power from the automatically fetched weather data
AB - Solar photovoltaic plants power output forecasting using machine learning techniques can be of a great advantage to energy producers when they are implemented with day-ahead energy market data. In this work a model was developed using a supervised learning algorithm of multilayer perceptron feedforward artificial neural network to predict the next twenty-four hours (day-ahead) power of a solar facility using fetched weather forecast of the following day. Each set of tested network configuration was trained by the historical power output of the plant as a target. For each configuration, one hundred networks ensembles was averaged to give the ability to generalize a better forecast. The trained ensembles performances were analyzed using statistical indicators. The best-performing model ensembles were eventually used to predict power from the automatically fetched weather data