A Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources

Probabilistic forecasts of electrical loads and photovoltaic generation provide a family of methods able to incorporate uncertainty estimations in predictions. This paper aims to extend the literature on these methods by proposing a novel deep-learning model based on a mixture of convolutional neura...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Markus Loschenbrand
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Deep learning generation forecasting load forecasting neural networks probabilistic methods renewable power Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/0373dab8d2c44356b1f51940e950d2ed
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0373dab8d2c44356b1f51940e950d2ed
record_format	dspace
spelling	oai:doaj.org-article:0373dab8d2c44356b1f51940e950d2ed2021-11-10T00:01:09ZA Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources2169-353610.1109/ACCESS.2021.3121988https://doaj.org/article/0373dab8d2c44356b1f51940e950d2ed2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9583253/https://doaj.org/toc/2169-3536Probabilistic forecasts of electrical loads and photovoltaic generation provide a family of methods able to incorporate uncertainty estimations in predictions. This paper aims to extend the literature on these methods by proposing a novel deep-learning model based on a mixture of convolutional neural networks, transformer models and dynamic Bayesian networks. Further, the paper also illustrates how to utilize Stochastic Variational Inference for training output distributions that allow time series sampling, a possibility not given for most state-of-the-art methods which do not use distributions. On top of this, the model also proposes an encoder-decoder topology that uses matrix transposes in order to both train on the sequential and the feature dimension. The performance of the work is illustrated on both load and generation time series obtained from a site representative of distributed energy resources in Norway and compared to state-of-the-art methods such as long-short-term memory. With a single-minute prediction resolution and a single-second computation time for an update with a batch size of 100 and a horizon of 24 hours, the model promises performance capable of real-time application. In summary, this paper provides a novel model that allows generating future scenarios for time series of distributed energy resources in real-time, which can be used to generate profiles for control problems under uncertainty.Markus LoschenbrandIEEEarticleDeep learninggeneration forecastingload forecastingneural networksprobabilistic methodsrenewable powerElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 147029-147041 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning generation forecasting load forecasting neural networks probabilistic methods renewable power Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Deep learning generation forecasting load forecasting neural networks probabilistic methods renewable power Electrical engineering. Electronics. Nuclear engineering TK1-9971 Markus Loschenbrand A Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources
description	Probabilistic forecasts of electrical loads and photovoltaic generation provide a family of methods able to incorporate uncertainty estimations in predictions. This paper aims to extend the literature on these methods by proposing a novel deep-learning model based on a mixture of convolutional neural networks, transformer models and dynamic Bayesian networks. Further, the paper also illustrates how to utilize Stochastic Variational Inference for training output distributions that allow time series sampling, a possibility not given for most state-of-the-art methods which do not use distributions. On top of this, the model also proposes an encoder-decoder topology that uses matrix transposes in order to both train on the sequential and the feature dimension. The performance of the work is illustrated on both load and generation time series obtained from a site representative of distributed energy resources in Norway and compared to state-of-the-art methods such as long-short-term memory. With a single-minute prediction resolution and a single-second computation time for an update with a batch size of 100 and a horizon of 24 hours, the model promises performance capable of real-time application. In summary, this paper provides a novel model that allows generating future scenarios for time series of distributed energy resources in real-time, which can be used to generate profiles for control problems under uncertainty.
format	article
author	Markus Loschenbrand
author_facet	Markus Loschenbrand
author_sort	Markus Loschenbrand
title	A Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources
title_short	A Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources
title_full	A Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources
title_fullStr	A Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources
title_full_unstemmed	A Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources
title_sort	temporal neural network model for probabilistic multi-period forecasting of distributed energy resources
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/0373dab8d2c44356b1f51940e950d2ed
work_keys_str_mv	AT markusloschenbrand atemporalneuralnetworkmodelforprobabilisticmultiperiodforecastingofdistributedenergyresources AT markusloschenbrand temporalneuralnetworkmodelforprobabilisticmultiperiodforecastingofdistributedenergyresources
_version_	1718440715959140352

A Temporal Neural Network Model for Probabilistic Multi-Period Forecasting of Distributed Energy Resources

Ejemplares similares