Scenario forecasting for wind power using flow-based generative networks

Wind power prediction is an integral part of power system operations and planning. Due to rising penetrations of wind turbines, fluctuation and intermittence of wind powers seriously limit the accuracy of power forecasts. A popular way to mitigate this challenge is to provide a range of possible sce...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shifeng Hu, Ruijin Zhu, Guoguang Li, Like Song
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Deep learning Generative network Wind power Scenario forecasting Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/b209ff7a0e5140c398193f5e1de63966
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b209ff7a0e5140c398193f5e1de63966
record_format	dspace
spelling	oai:doaj.org-article:b209ff7a0e5140c398193f5e1de639662021-11-26T04:32:54ZScenario forecasting for wind power using flow-based generative networks2352-484710.1016/j.egyr.2021.08.036https://doaj.org/article/b209ff7a0e5140c398193f5e1de639662021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2352484721006387https://doaj.org/toc/2352-4847Wind power prediction is an integral part of power system operations and planning. Due to rising penetrations of wind turbines, fluctuation and intermittence of wind powers seriously limit the accuracy of power forecasts. A popular way to mitigate this challenge is to provide a range of possible scenarios instead of deterministic point forecasting values, so operators can account for the uncertainties. This paper proposes a model-free scenario forecasting approach for wind powers using flow-based generative networks, which generate a set of high-quality scenarios to represent possible behaviors based on historical wind powers and deterministic point forecasting values. Firstly, an unsupervised deep learning framework is proposed to learn the latent patterns in historical wind power curves. Then, a large number of possible future scenarios are obtained by solving an optimization problem. Simulation results show that the proposed approach has better performance than popular baselines such as variational auto-encoder and generative adversarial networks.Shifeng HuRuijin ZhuGuoguang LiLike SongElsevierarticleDeep learningGenerative networkWind powerScenario forecastingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENEnergy Reports, Vol 7, Iss , Pp 369-377 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning Generative network Wind power Scenario forecasting Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Deep learning Generative network Wind power Scenario forecasting Electrical engineering. Electronics. Nuclear engineering TK1-9971 Shifeng Hu Ruijin Zhu Guoguang Li Like Song Scenario forecasting for wind power using flow-based generative networks
description	Wind power prediction is an integral part of power system operations and planning. Due to rising penetrations of wind turbines, fluctuation and intermittence of wind powers seriously limit the accuracy of power forecasts. A popular way to mitigate this challenge is to provide a range of possible scenarios instead of deterministic point forecasting values, so operators can account for the uncertainties. This paper proposes a model-free scenario forecasting approach for wind powers using flow-based generative networks, which generate a set of high-quality scenarios to represent possible behaviors based on historical wind powers and deterministic point forecasting values. Firstly, an unsupervised deep learning framework is proposed to learn the latent patterns in historical wind power curves. Then, a large number of possible future scenarios are obtained by solving an optimization problem. Simulation results show that the proposed approach has better performance than popular baselines such as variational auto-encoder and generative adversarial networks.
format	article
author	Shifeng Hu Ruijin Zhu Guoguang Li Like Song
author_facet	Shifeng Hu Ruijin Zhu Guoguang Li Like Song
author_sort	Shifeng Hu
title	Scenario forecasting for wind power using flow-based generative networks
title_short	Scenario forecasting for wind power using flow-based generative networks
title_full	Scenario forecasting for wind power using flow-based generative networks
title_fullStr	Scenario forecasting for wind power using flow-based generative networks
title_full_unstemmed	Scenario forecasting for wind power using flow-based generative networks
title_sort	scenario forecasting for wind power using flow-based generative networks
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/b209ff7a0e5140c398193f5e1de63966
work_keys_str_mv	AT shifenghu scenarioforecastingforwindpowerusingflowbasedgenerativenetworks AT ruijinzhu scenarioforecastingforwindpowerusingflowbasedgenerativenetworks AT guoguangli scenarioforecastingforwindpowerusingflowbasedgenerativenetworks AT likesong scenarioforecastingforwindpowerusingflowbasedgenerativenetworks
_version_	1718409861742460928

Scenario forecasting for wind power using flow-based generative networks

Ejemplares similares