A robust spatio‐temporal prediction approach for wind power generation based on spectral temporal graph neural network
Abstract At present, the penetration of wind power generation is increasing remarkably worldwide, and the accurate wind power forecasting (WPF) is essential to ensure the reliability and economy of the power system. Most of the current work of WPF only capture temporal correlation in the time domain...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2022-09-01
|
Series: | IET Renewable Power Generation |
Online Access: | https://doi.org/10.1049/rpg2.12449 |
_version_ | 1811310091488460800 |
---|---|
author | Yuqin He Songjian Chai Jian Zhao Yuxin Sun Xian Zhang |
author_facet | Yuqin He Songjian Chai Jian Zhao Yuxin Sun Xian Zhang |
author_sort | Yuqin He |
collection | DOAJ |
description | Abstract At present, the penetration of wind power generation is increasing remarkably worldwide, and the accurate wind power forecasting (WPF) is essential to ensure the reliability and economy of the power system. Most of the current work of WPF only capture temporal correlation in the time domain but ignore the spatial correlation. In this study, a spectral time graph neural network based on the maximum correlation criterion (MCC‐Stem‐GNN) is proposed to improve the accuracy of WPF for multiple sites and horizons. The self‐attentive mechanism in the MCC‐Stem‐GNN automatically learns the correlations between the multivariate sequences. Besides, this model combines the Graph Fourier Transform (GFT) to model spatial correlation and the Discrete Fourier Transform (DFT) to model temporal correlation. The effectiveness of the proposed robust deep learning framework is verified on the simulated wind energy dataset over 16 locations in Ohio, US through considering different sample contamination types and levels, comprehensive case study is carried out to show the superiority of the MCC‐Stem‐GNN over the benchmarks. |
first_indexed | 2024-04-13T09:53:30Z |
format | Article |
id | doaj.art-14173e1561a743e893331eba5db63ff5 |
institution | Directory Open Access Journal |
issn | 1752-1416 1752-1424 |
language | English |
last_indexed | 2024-04-13T09:53:30Z |
publishDate | 2022-09-01 |
publisher | Wiley |
record_format | Article |
series | IET Renewable Power Generation |
spelling | doaj.art-14173e1561a743e893331eba5db63ff52022-12-22T02:51:31ZengWileyIET Renewable Power Generation1752-14161752-14242022-09-0116122556256510.1049/rpg2.12449A robust spatio‐temporal prediction approach for wind power generation based on spectral temporal graph neural networkYuqin He0Songjian Chai1Jian Zhao2Yuxin Sun3Xian Zhang4College of Mechatronics and Control Engineering Shenzhen University Shenzhen 518060 ChinaCollege of Mechatronics and Control Engineering Shenzhen University Shenzhen 518060 ChinaCollege of Electrical Engineering Shanghai University of Electric Power Shanghai 200090 ChinaDepartment of Electrical Engineering and Electronics University of Liverpool Liverpool L69 7ZX UKSchool of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen 518055 ChinaAbstract At present, the penetration of wind power generation is increasing remarkably worldwide, and the accurate wind power forecasting (WPF) is essential to ensure the reliability and economy of the power system. Most of the current work of WPF only capture temporal correlation in the time domain but ignore the spatial correlation. In this study, a spectral time graph neural network based on the maximum correlation criterion (MCC‐Stem‐GNN) is proposed to improve the accuracy of WPF for multiple sites and horizons. The self‐attentive mechanism in the MCC‐Stem‐GNN automatically learns the correlations between the multivariate sequences. Besides, this model combines the Graph Fourier Transform (GFT) to model spatial correlation and the Discrete Fourier Transform (DFT) to model temporal correlation. The effectiveness of the proposed robust deep learning framework is verified on the simulated wind energy dataset over 16 locations in Ohio, US through considering different sample contamination types and levels, comprehensive case study is carried out to show the superiority of the MCC‐Stem‐GNN over the benchmarks.https://doi.org/10.1049/rpg2.12449 |
spellingShingle | Yuqin He Songjian Chai Jian Zhao Yuxin Sun Xian Zhang A robust spatio‐temporal prediction approach for wind power generation based on spectral temporal graph neural network IET Renewable Power Generation |
title | A robust spatio‐temporal prediction approach for wind power generation based on spectral temporal graph neural network |
title_full | A robust spatio‐temporal prediction approach for wind power generation based on spectral temporal graph neural network |
title_fullStr | A robust spatio‐temporal prediction approach for wind power generation based on spectral temporal graph neural network |
title_full_unstemmed | A robust spatio‐temporal prediction approach for wind power generation based on spectral temporal graph neural network |
title_short | A robust spatio‐temporal prediction approach for wind power generation based on spectral temporal graph neural network |
title_sort | robust spatio temporal prediction approach for wind power generation based on spectral temporal graph neural network |
url | https://doi.org/10.1049/rpg2.12449 |
work_keys_str_mv | AT yuqinhe arobustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT songjianchai arobustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT jianzhao arobustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT yuxinsun arobustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT xianzhang arobustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT yuqinhe robustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT songjianchai robustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT jianzhao robustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT yuxinsun robustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork AT xianzhang robustspatiotemporalpredictionapproachforwindpowergenerationbasedonspectraltemporalgraphneuralnetwork |