Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations

Photovoltaic (PV) generation is potentially uncertain. Probabilistic PV generation forecasting methods have been proposed with prediction intervals (PIs) to evaluate the uncertainty quantitively. However, few studies have applied PIs to geographically distributed PVs in a specific area. In this stud...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Daisuke Kodaira, Kazuki Tsukazaki, Taiki Kure, Junji Kondoh
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	photovoltaic generation forecast probabilistic forecast prediction interval ensemble forecast day ahead forecasting multiple PV forecasting Technology T
Acceso en línea:	https://doaj.org/article/b31495775995402982834372755bc926
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b31495775995402982834372755bc926
record_format	dspace
spelling	oai:doaj.org-article:b31495775995402982834372755bc9262021-11-11T16:03:48ZImproving Forecast Reliability for Geographically Distributed Photovoltaic Generations10.3390/en142173401996-1073https://doaj.org/article/b31495775995402982834372755bc9262021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7340https://doaj.org/toc/1996-1073Photovoltaic (PV) generation is potentially uncertain. Probabilistic PV generation forecasting methods have been proposed with prediction intervals (PIs) to evaluate the uncertainty quantitively. However, few studies have applied PIs to geographically distributed PVs in a specific area. In this study, a two-step probabilistic forecast scheme is proposed for geographically distributed PV generation forecasting. Each step of the proposed scheme adopts ensemble forecasting based on three different machine-learning methods. When individual PV generation is forecasted, the proposed scheme utilizes surrounding PVs’ past data to train the ensemble forecasting model. In this case study, the proposed scheme was compared with conventional non-multistep forecasting. The proposed scheme improved the reliability of the PIs and deterministic PV forecasting results through 30 days of continuous operation with real data in Japan.Daisuke KodairaKazuki TsukazakiTaiki KureJunji KondohMDPI AGarticlephotovoltaic generation forecastprobabilistic forecastprediction intervalensemble forecastday ahead forecastingmultiple PV forecastingTechnologyTENEnergies, Vol 14, Iss 7340, p 7340 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	photovoltaic generation forecast probabilistic forecast prediction interval ensemble forecast day ahead forecasting multiple PV forecasting Technology T
spellingShingle	photovoltaic generation forecast probabilistic forecast prediction interval ensemble forecast day ahead forecasting multiple PV forecasting Technology T Daisuke Kodaira Kazuki Tsukazaki Taiki Kure Junji Kondoh Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations
description	Photovoltaic (PV) generation is potentially uncertain. Probabilistic PV generation forecasting methods have been proposed with prediction intervals (PIs) to evaluate the uncertainty quantitively. However, few studies have applied PIs to geographically distributed PVs in a specific area. In this study, a two-step probabilistic forecast scheme is proposed for geographically distributed PV generation forecasting. Each step of the proposed scheme adopts ensemble forecasting based on three different machine-learning methods. When individual PV generation is forecasted, the proposed scheme utilizes surrounding PVs’ past data to train the ensemble forecasting model. In this case study, the proposed scheme was compared with conventional non-multistep forecasting. The proposed scheme improved the reliability of the PIs and deterministic PV forecasting results through 30 days of continuous operation with real data in Japan.
format	article
author	Daisuke Kodaira Kazuki Tsukazaki Taiki Kure Junji Kondoh
author_facet	Daisuke Kodaira Kazuki Tsukazaki Taiki Kure Junji Kondoh
author_sort	Daisuke Kodaira
title	Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations
title_short	Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations
title_full	Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations
title_fullStr	Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations
title_full_unstemmed	Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations
title_sort	improving forecast reliability for geographically distributed photovoltaic generations
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b31495775995402982834372755bc926
work_keys_str_mv	AT daisukekodaira improvingforecastreliabilityforgeographicallydistributedphotovoltaicgenerations AT kazukitsukazaki improvingforecastreliabilityforgeographicallydistributedphotovoltaicgenerations AT taikikure improvingforecastreliabilityforgeographicallydistributedphotovoltaicgenerations AT junjikondoh improvingforecastreliabilityforgeographicallydistributedphotovoltaicgenerations
_version_	1718432435794870272

Improving Forecast Reliability for Geographically Distributed Photovoltaic Generations

Ejemplares similares