Probabilistic reference model for hourly PV power generation forecasting
Autor: | Alberto Falces, Pedro J. Zorzano-Santamaria, Pedro M. Lara-Santillan, Sonia Terreros-Olarte, Enrique Zorzano-Alba, L. Alfredo Fernandez-Jimenez |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
lcsh:GE1-350
Computer science 020209 energy Photovoltaic system Probabilistic logic 02 engineering and technology Benchmarking Reliability engineering Power (physics) 0202 electrical engineering electronic engineering information engineering Production (economics) Probabilistic forecasting Reference model lcsh:Environmental sciences Quantile |
Zdroj: | E3S Web of Conferences, Vol 152, p 01002 (2020) RIUR. Repositorio Institucional de la Universidad de La Rioja instname |
ISSN: | 2267-1242 |
Popis: | This paper presents a new probabilistic forecasting model of the hourly mean power production in a Photovoltaic (PV) plant. It uses the minimal information and it can provide probabilistic forecasts in the form of quantiles for the desired horizon, which ranges from the next hours to any day in the future. The proposed model only needs a time series of hourly mean power production in the PV plant, and it is intended to fill a gap in international literature where hardly any model has been proposed as a reference for comparison or benchmarking purposes with other probabilistic forecasting models. The performance of the proposed forecasting model is tested, in a case study, with the time series of hourly mean power production in a PV plant with 1.9 MW capacity. The results show an improvement with respect to the reference probabilistic PV power forecasting models reported in the literature. |
Databáze: | OpenAIRE |
Externí odkaz: |