Load data recovery method based on SOM-LSTM neural network

In the collection and transmission of power big data, the problem of data missing exists. In response to this problem, this paper proposes a power data detection and repair method based on SOM-LSTM. Firstly, a large amount of collected power data is analyzed and the type of missing data is determine...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yiming Ma, Junyou Yang, Jiawei Feng, Haixin Wang, Yunlu Li, Yingying Li
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2022
Materias:	Power system SOM neural network LSTM neural network Data missing Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/141c36bd4c034a11bfb0fc0ec12f8f19
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:141c36bd4c034a11bfb0fc0ec12f8f19
record_format	dspace
spelling	oai:doaj.org-article:141c36bd4c034a11bfb0fc0ec12f8f192021-12-04T04:34:55ZLoad data recovery method based on SOM-LSTM neural network2352-484710.1016/j.egyr.2021.11.070https://doaj.org/article/141c36bd4c034a11bfb0fc0ec12f8f192022-04-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2352484721012154https://doaj.org/toc/2352-4847In the collection and transmission of power big data, the problem of data missing exists. In response to this problem, this paper proposes a power data detection and repair method based on SOM-LSTM. Firstly, a large amount of collected power data is analyzed and the type of missing data is determined. Then, the SOM is used to classify the power data. The LSTM is trained according to the characteristic values of different users to complete the detection and repair of different types of missing power data. Finally, the analysis is based on actual data in some regional loads of China. Experimental results show that, compared with the extreme learning machine (ELM) and LSTM, the proposed SOM-LSTM model reduces the mean absolute error (MAE) by 0.2498 and 0.3425, and the root mean square error (RMSE) by 0.1048 and 0.1469, respectively.Yiming MaJunyou YangJiawei FengHaixin WangYunlu LiYingying LiElsevierarticlePower systemSOM neural networkLSTM neural networkData missingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENEnergy Reports, Vol 8, Iss , Pp 129-136 (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	Power system SOM neural network LSTM neural network Data missing Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Power system SOM neural network LSTM neural network Data missing Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yiming Ma Junyou Yang Jiawei Feng Haixin Wang Yunlu Li Yingying Li Load data recovery method based on SOM-LSTM neural network
description	In the collection and transmission of power big data, the problem of data missing exists. In response to this problem, this paper proposes a power data detection and repair method based on SOM-LSTM. Firstly, a large amount of collected power data is analyzed and the type of missing data is determined. Then, the SOM is used to classify the power data. The LSTM is trained according to the characteristic values of different users to complete the detection and repair of different types of missing power data. Finally, the analysis is based on actual data in some regional loads of China. Experimental results show that, compared with the extreme learning machine (ELM) and LSTM, the proposed SOM-LSTM model reduces the mean absolute error (MAE) by 0.2498 and 0.3425, and the root mean square error (RMSE) by 0.1048 and 0.1469, respectively.
format	article
author	Yiming Ma Junyou Yang Jiawei Feng Haixin Wang Yunlu Li Yingying Li
author_facet	Yiming Ma Junyou Yang Jiawei Feng Haixin Wang Yunlu Li Yingying Li
author_sort	Yiming Ma
title	Load data recovery method based on SOM-LSTM neural network
title_short	Load data recovery method based on SOM-LSTM neural network
title_full	Load data recovery method based on SOM-LSTM neural network
title_fullStr	Load data recovery method based on SOM-LSTM neural network
title_full_unstemmed	Load data recovery method based on SOM-LSTM neural network
title_sort	load data recovery method based on som-lstm neural network
publisher	Elsevier
publishDate	2022
url	https://doaj.org/article/141c36bd4c034a11bfb0fc0ec12f8f19
work_keys_str_mv	AT yimingma loaddatarecoverymethodbasedonsomlstmneuralnetwork AT junyouyang loaddatarecoverymethodbasedonsomlstmneuralnetwork AT jiaweifeng loaddatarecoverymethodbasedonsomlstmneuralnetwork AT haixinwang loaddatarecoverymethodbasedonsomlstmneuralnetwork AT yunluli loaddatarecoverymethodbasedonsomlstmneuralnetwork AT yingyingli loaddatarecoverymethodbasedonsomlstmneuralnetwork
_version_	1718372953271304192

Load data recovery method based on SOM-LSTM neural network

Ejemplares similares