Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting

Studies have demonstrated that changes in the climate affect wind power forecasting under different weather conditions. Theoretically, accurate prediction of both wind power output and weather changes using statistics-based prediction models is difficult. In practice, traditional machine learning mo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wen-Hui Lin, Ping Wang, Kuo-Ming Chao, Hsiao-Chung Lin, Zong-Yu Yang, Yu-Huang Lai
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	renewable energy wind power forecasting deep learning network temporal convolutional network long short-term memory Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/76f14cb35b3b4ddc91491d89be934c58
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:76f14cb35b3b4ddc91491d89be934c58
record_format	dspace
spelling	oai:doaj.org-article:76f14cb35b3b4ddc91491d89be934c582021-11-11T15:21:39ZWind Power Forecasting with Deep Learning Networks: Time-Series Forecasting10.3390/app1121103352076-3417https://doaj.org/article/76f14cb35b3b4ddc91491d89be934c582021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10335https://doaj.org/toc/2076-3417Studies have demonstrated that changes in the climate affect wind power forecasting under different weather conditions. Theoretically, accurate prediction of both wind power output and weather changes using statistics-based prediction models is difficult. In practice, traditional machine learning models can perform long-term wind power forecasting with a mean absolute percentage error (MAPE) of 10% to 17%, which does not meet the engineering requirements for our renewable energy project. Deep learning networks (DLNs) have been employed to obtain the correlations between meteorological features and power generation using a multilayer neural convolutional architecture with gradient descent algorithms to minimize estimation errors. This has wide applicability to the field of wind power forecasting. Therefore, this study aimed at the long-term (24–72-h ahead) prediction of wind power with an MAPE of less than 10% by using the Temporal Convolutional Network (TCN) algorithm of DLNs. In our experiment, we performed TCN model pretraining using historical weather data and the power generation outputs of a wind turbine from a Scada wind power plant in Turkey. The experimental results indicated an MAPE of 5.13% for 72-h wind power prediction, which is adequate within the constraints of our project. Finally, we compared the performance of four DLN-based prediction models for power forecasting, namely, the TCN, long short-term memory (LSTM), recurrent neural network (RNN), and gated recurrence unit (GRU) models. We validated that the TCN outperforms the other three models for wind power prediction in terms of data input volume, stability of error reduction, and forecast accuracy.Wen-Hui LinPing WangKuo-Ming ChaoHsiao-Chung LinZong-Yu YangYu-Huang LaiMDPI AGarticlerenewable energywind power forecastingdeep learning networktemporal convolutional networklong short-term memoryTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10335, p 10335 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	renewable energy wind power forecasting deep learning network temporal convolutional network long short-term memory Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	renewable energy wind power forecasting deep learning network temporal convolutional network long short-term memory Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Wen-Hui Lin Ping Wang Kuo-Ming Chao Hsiao-Chung Lin Zong-Yu Yang Yu-Huang Lai Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting
description	Studies have demonstrated that changes in the climate affect wind power forecasting under different weather conditions. Theoretically, accurate prediction of both wind power output and weather changes using statistics-based prediction models is difficult. In practice, traditional machine learning models can perform long-term wind power forecasting with a mean absolute percentage error (MAPE) of 10% to 17%, which does not meet the engineering requirements for our renewable energy project. Deep learning networks (DLNs) have been employed to obtain the correlations between meteorological features and power generation using a multilayer neural convolutional architecture with gradient descent algorithms to minimize estimation errors. This has wide applicability to the field of wind power forecasting. Therefore, this study aimed at the long-term (24–72-h ahead) prediction of wind power with an MAPE of less than 10% by using the Temporal Convolutional Network (TCN) algorithm of DLNs. In our experiment, we performed TCN model pretraining using historical weather data and the power generation outputs of a wind turbine from a Scada wind power plant in Turkey. The experimental results indicated an MAPE of 5.13% for 72-h wind power prediction, which is adequate within the constraints of our project. Finally, we compared the performance of four DLN-based prediction models for power forecasting, namely, the TCN, long short-term memory (LSTM), recurrent neural network (RNN), and gated recurrence unit (GRU) models. We validated that the TCN outperforms the other three models for wind power prediction in terms of data input volume, stability of error reduction, and forecast accuracy.
format	article
author	Wen-Hui Lin Ping Wang Kuo-Ming Chao Hsiao-Chung Lin Zong-Yu Yang Yu-Huang Lai
author_facet	Wen-Hui Lin Ping Wang Kuo-Ming Chao Hsiao-Chung Lin Zong-Yu Yang Yu-Huang Lai
author_sort	Wen-Hui Lin
title	Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting
title_short	Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting
title_full	Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting
title_fullStr	Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting
title_full_unstemmed	Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting
title_sort	wind power forecasting with deep learning networks: time-series forecasting
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/76f14cb35b3b4ddc91491d89be934c58
work_keys_str_mv	AT wenhuilin windpowerforecastingwithdeeplearningnetworkstimeseriesforecasting AT pingwang windpowerforecastingwithdeeplearningnetworkstimeseriesforecasting AT kuomingchao windpowerforecastingwithdeeplearningnetworkstimeseriesforecasting AT hsiaochunglin windpowerforecastingwithdeeplearningnetworkstimeseriesforecasting AT zongyuyang windpowerforecastingwithdeeplearningnetworkstimeseriesforecasting AT yuhuanglai windpowerforecastingwithdeeplearningnetworkstimeseriesforecasting
_version_	1718435372021579776

Wind Power Forecasting with Deep Learning Networks: Time-Series Forecasting

Ejemplares similares