Load forecasting of hybrid deep learning model considering accumulated temperature effect

Considering the non-linear, multi-dimensionality and time-series of load data, a short-term power load forecasting method based on TCN-DNN hybrid deep learning model is proposed. Firstly, considering the common influencing factors of short-term load, and analysing the correlation, the temperature va...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Haihong Bian, Qian Wang, Guozheng Xu, Xiu Zhao
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2022
Materias:	Short-term load forecasting Temperature correction Temporal Convolutional Network Deep Neural Network TCN-DNN Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/450c6fdd4d0f49dc91a33c709c42c59c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:450c6fdd4d0f49dc91a33c709c42c59c
record_format	dspace
spelling	oai:doaj.org-article:450c6fdd4d0f49dc91a33c709c42c59c2021-12-04T04:34:56ZLoad forecasting of hybrid deep learning model considering accumulated temperature effect2352-484710.1016/j.egyr.2021.11.082https://doaj.org/article/450c6fdd4d0f49dc91a33c709c42c59c2022-04-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2352484721012270https://doaj.org/toc/2352-4847Considering the non-linear, multi-dimensionality and time-series of load data, a short-term power load forecasting method based on TCN-DNN hybrid deep learning model is proposed. Firstly, considering the common influencing factors of short-term load, and analysing the correlation, the temperature variable quantitative model considering the accumulated temperature effect is established. Secondly, based on the deep learning, the load influencing factors are classified and processed; In order to study the internal dynamics of the data, the Temporal Convolutional Network (TCN) is used to extract and construct time-series feature vector; The outputs integrate with non-time-series data factors (date type) into new input features. Finally, the internal relationship between the characteristics and load changes is analysed as a whole by the Deep Neural Network (DNN), and the load forecasting is finally completed. Taking the actual load data of the power grid in a certain area of East China as practical example, the forecasting accuracy of the proposed method is 97.92%. The proposed method is compared with Long Short-Term Memory (LSTM), TCN, DNN and the hybrid TCN-DNN model without temperature correction, the experimental results show that the proposed method has higher optimization efficiency and forecasting accuracy.Haihong BianQian WangGuozheng XuXiu ZhaoElsevierarticleShort-term load forecastingTemperature correctionTemporal Convolutional NetworkDeep Neural NetworkTCN-DNNElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENEnergy Reports, Vol 8, Iss , Pp 205-215 (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	Short-term load forecasting Temperature correction Temporal Convolutional Network Deep Neural Network TCN-DNN Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Short-term load forecasting Temperature correction Temporal Convolutional Network Deep Neural Network TCN-DNN Electrical engineering. Electronics. Nuclear engineering TK1-9971 Haihong Bian Qian Wang Guozheng Xu Xiu Zhao Load forecasting of hybrid deep learning model considering accumulated temperature effect
description	Considering the non-linear, multi-dimensionality and time-series of load data, a short-term power load forecasting method based on TCN-DNN hybrid deep learning model is proposed. Firstly, considering the common influencing factors of short-term load, and analysing the correlation, the temperature variable quantitative model considering the accumulated temperature effect is established. Secondly, based on the deep learning, the load influencing factors are classified and processed; In order to study the internal dynamics of the data, the Temporal Convolutional Network (TCN) is used to extract and construct time-series feature vector; The outputs integrate with non-time-series data factors (date type) into new input features. Finally, the internal relationship between the characteristics and load changes is analysed as a whole by the Deep Neural Network (DNN), and the load forecasting is finally completed. Taking the actual load data of the power grid in a certain area of East China as practical example, the forecasting accuracy of the proposed method is 97.92%. The proposed method is compared with Long Short-Term Memory (LSTM), TCN, DNN and the hybrid TCN-DNN model without temperature correction, the experimental results show that the proposed method has higher optimization efficiency and forecasting accuracy.
format	article
author	Haihong Bian Qian Wang Guozheng Xu Xiu Zhao
author_facet	Haihong Bian Qian Wang Guozheng Xu Xiu Zhao
author_sort	Haihong Bian
title	Load forecasting of hybrid deep learning model considering accumulated temperature effect
title_short	Load forecasting of hybrid deep learning model considering accumulated temperature effect
title_full	Load forecasting of hybrid deep learning model considering accumulated temperature effect
title_fullStr	Load forecasting of hybrid deep learning model considering accumulated temperature effect
title_full_unstemmed	Load forecasting of hybrid deep learning model considering accumulated temperature effect
title_sort	load forecasting of hybrid deep learning model considering accumulated temperature effect
publisher	Elsevier
publishDate	2022
url	https://doaj.org/article/450c6fdd4d0f49dc91a33c709c42c59c
work_keys_str_mv	AT haihongbian loadforecastingofhybriddeeplearningmodelconsideringaccumulatedtemperatureeffect AT qianwang loadforecastingofhybriddeeplearningmodelconsideringaccumulatedtemperatureeffect AT guozhengxu loadforecastingofhybriddeeplearningmodelconsideringaccumulatedtemperatureeffect AT xiuzhao loadforecastingofhybriddeeplearningmodelconsideringaccumulatedtemperatureeffect
_version_	1718372963532668928

Load forecasting of hybrid deep learning model considering accumulated temperature effect

Ejemplares similares