Multifeature Short-Term Power Load Forecasting Based on GCN-LSTM

With the construction of a new-type power system under the China “double carbon” target and the increasing diversification of the energy demand on the user side, the short-term load forecasting of the power system is facing new challenges. To fully exploit the massive information contained in data,...

Full description

Saved in:
Bibliographic Details
Main Authors: Houhe Chen, Mingyang Zhu, Xiao Hu, Jiarui Wang, Yong Sun, Jinduo Yang, Baoju Li, Xiangdong Meng
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:International Transactions on Electrical Energy Systems
Online Access:http://dx.doi.org/10.1155/2023/8846554
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832547833080709120
author Houhe Chen
Mingyang Zhu
Xiao Hu
Jiarui Wang
Yong Sun
Jinduo Yang
Baoju Li
Xiangdong Meng
author_facet Houhe Chen
Mingyang Zhu
Xiao Hu
Jiarui Wang
Yong Sun
Jinduo Yang
Baoju Li
Xiangdong Meng
author_sort Houhe Chen
collection DOAJ
description With the construction of a new-type power system under the China “double carbon” target and the increasing diversification of the energy demand on the user side, the short-term load forecasting of the power system is facing new challenges. To fully exploit the massive information contained in data, based on the graph convolutional network (GCN) and long short-term memory network (LSTM), this paper presents a new short-term load forecasting method for power systems considering multiple factors. The Spearman rank correlation coefficient was used to analyse the correlation between load and meteorological factors, and a model including meteorology, dates, and regions was established. Secondly, GCN and LSTM are jointly used to extract the spatial and temporal characteristics of massive data, respectively, and finally achieve short-term power load prediction. Historical electrical load data from 2020 to 2022 public data of a real industrial park in southern China were selected to verify the validity of the proposed method from the aspects of forecasting accuracy, feature dimension, and training time.
format Article
id doaj-art-348b18c4d98c484f89fe501cbd0c0de9
institution Kabale University
issn 2050-7038
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series International Transactions on Electrical Energy Systems
spelling doaj-art-348b18c4d98c484f89fe501cbd0c0de92025-02-03T06:43:03ZengWileyInternational Transactions on Electrical Energy Systems2050-70382023-01-01202310.1155/2023/8846554Multifeature Short-Term Power Load Forecasting Based on GCN-LSTMHouhe Chen0Mingyang Zhu1Xiao Hu2Jiarui Wang3Yong Sun4Jinduo Yang5Baoju Li6Xiangdong Meng7Northeast Electric Power UniversityNortheast Electric Power UniversityNortheast Electric Power UniversityState Grid Jilin Electric Power Research InstituteState Grid Jilinsheng Electric Power Supply CompanyNortheast Electric Power UniversityState Grid Jilinsheng Electric Power Supply CompanyState Grid Jilin Electric Power Research InstituteWith the construction of a new-type power system under the China “double carbon” target and the increasing diversification of the energy demand on the user side, the short-term load forecasting of the power system is facing new challenges. To fully exploit the massive information contained in data, based on the graph convolutional network (GCN) and long short-term memory network (LSTM), this paper presents a new short-term load forecasting method for power systems considering multiple factors. The Spearman rank correlation coefficient was used to analyse the correlation between load and meteorological factors, and a model including meteorology, dates, and regions was established. Secondly, GCN and LSTM are jointly used to extract the spatial and temporal characteristics of massive data, respectively, and finally achieve short-term power load prediction. Historical electrical load data from 2020 to 2022 public data of a real industrial park in southern China were selected to verify the validity of the proposed method from the aspects of forecasting accuracy, feature dimension, and training time.http://dx.doi.org/10.1155/2023/8846554
spellingShingle Houhe Chen
Mingyang Zhu
Xiao Hu
Jiarui Wang
Yong Sun
Jinduo Yang
Baoju Li
Xiangdong Meng
Multifeature Short-Term Power Load Forecasting Based on GCN-LSTM
International Transactions on Electrical Energy Systems
title Multifeature Short-Term Power Load Forecasting Based on GCN-LSTM
title_full Multifeature Short-Term Power Load Forecasting Based on GCN-LSTM
title_fullStr Multifeature Short-Term Power Load Forecasting Based on GCN-LSTM
title_full_unstemmed Multifeature Short-Term Power Load Forecasting Based on GCN-LSTM
title_short Multifeature Short-Term Power Load Forecasting Based on GCN-LSTM
title_sort multifeature short term power load forecasting based on gcn lstm
url http://dx.doi.org/10.1155/2023/8846554
work_keys_str_mv AT houhechen multifeatureshorttermpowerloadforecastingbasedongcnlstm
AT mingyangzhu multifeatureshorttermpowerloadforecastingbasedongcnlstm
AT xiaohu multifeatureshorttermpowerloadforecastingbasedongcnlstm
AT jiaruiwang multifeatureshorttermpowerloadforecastingbasedongcnlstm
AT yongsun multifeatureshorttermpowerloadforecastingbasedongcnlstm
AT jinduoyang multifeatureshorttermpowerloadforecastingbasedongcnlstm
AT baojuli multifeatureshorttermpowerloadforecastingbasedongcnlstm
AT xiangdongmeng multifeatureshorttermpowerloadforecastingbasedongcnlstm