Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks

Haris Mansoor; Madiha Shabbir; Muhammad Yasir Ali; Huzaifa Rauf; Muhammad Khalid; Naveed Arshad

doi:10.1109/ICRERA59003.2023.10269401

Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks

Haris Mansoor, Madiha Shabbir, Muhammad Yasir Ali, Huzaifa Rauf, Muhammad Khalid, Naveed Arshad

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

Accurate short-term load forecasting (STLF) is essential for the efficient operation of the power sector. Due to heightened volatility and intrinsic stochasticity, forecasting load at a fine resolution, such as weekly load, is difficult. Existing STLF techniques only rely on temporal data and auto-regressive processes to forecast load. However, the power grid has a graphical structure that provides spatial information too. This paper proposes an innovative STLF method fusing both spatial and temporal information. We propose a creative way to convert load data into graphical form, which is fed into graph convolutional networks (GCN) to learn spatial embeddings. The GCN embeddings are used along with temporal features to predict the load. We perform extensive experiments using state-of-the-art machine learning and deep learning techniques to validate our approach. The results demonstrate that by using spatial information, we can sub-stantially improve the forecasting performance.

Original language	English
Title of host publication	12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	320-323
Number of pages	4
ISBN (Electronic)	9798350337938
DOIs	https://doi.org/10.1109/ICRERA59003.2023.10269401
State	Published - 2023
Event	12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023 - Oshawa, Canada Duration: 29 Aug 2023 → 1 Sep 2023

Publication series

Name	12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023

Conference

Conference	12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023
Country/Territory	Canada
City	Oshawa
Period	29/08/23 → 1/09/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

graph convolutional networks
graph neural networks
load forecasting
machine learning
short term load forecasting
spatio-temporal load forecasting

ASJC Scopus subject areas

Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering
Mechanical Engineering
Control and Optimization

Access to Document

10.1109/ICRERA59003.2023.10269401

Cite this

Mansoor, H., Shabbir, M., Ali, M. Y., Rauf, H., Khalid, M., & Arshad, N. (2023). Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks. In 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023 (pp. 320-323). (12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRERA59003.2023.10269401

Mansoor, Haris ; Shabbir, Madiha ; Ali, Muhammad Yasir et al. / Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks. 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 320-323 (12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023).

@inproceedings{bca5a6db9369427a8fd2a9e94c93b300,

title = "Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks",

abstract = "Accurate short-term load forecasting (STLF) is essential for the efficient operation of the power sector. Due to heightened volatility and intrinsic stochasticity, forecasting load at a fine resolution, such as weekly load, is difficult. Existing STLF techniques only rely on temporal data and auto-regressive processes to forecast load. However, the power grid has a graphical structure that provides spatial information too. This paper proposes an innovative STLF method fusing both spatial and temporal information. We propose a creative way to convert load data into graphical form, which is fed into graph convolutional networks (GCN) to learn spatial embeddings. The GCN embeddings are used along with temporal features to predict the load. We perform extensive experiments using state-of-the-art machine learning and deep learning techniques to validate our approach. The results demonstrate that by using spatial information, we can sub-stantially improve the forecasting performance.",

keywords = "graph convolutional networks, graph neural networks, load forecasting, machine learning, short term load forecasting, spatio-temporal load forecasting",

author = "Haris Mansoor and Madiha Shabbir and Ali, \{Muhammad Yasir\} and Huzaifa Rauf and Muhammad Khalid and Naveed Arshad",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023 ; Conference date: 29-08-2023 Through 01-09-2023",

year = "2023",

doi = "10.1109/ICRERA59003.2023.10269401",

language = "English",

series = "12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "320--323",

booktitle = "12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023",

address = "United States",

}

Mansoor, H, Shabbir, M, Ali, MY, Rauf, H, Khalid, M & Arshad, N 2023, Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks. in 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023. 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023, Institute of Electrical and Electronics Engineers Inc., pp. 320-323, 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023, Oshawa, Canada, 29/08/23. https://doi.org/10.1109/ICRERA59003.2023.10269401

Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks. / Mansoor, Haris; Shabbir, Madiha; Ali, Muhammad Yasir et al.
12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 320-323 (12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks

AU - Mansoor, Haris

AU - Shabbir, Madiha

AU - Ali, Muhammad Yasir

AU - Rauf, Huzaifa

AU - Khalid, Muhammad

AU - Arshad, Naveed

PY - 2023

Y1 - 2023

N2 - Accurate short-term load forecasting (STLF) is essential for the efficient operation of the power sector. Due to heightened volatility and intrinsic stochasticity, forecasting load at a fine resolution, such as weekly load, is difficult. Existing STLF techniques only rely on temporal data and auto-regressive processes to forecast load. However, the power grid has a graphical structure that provides spatial information too. This paper proposes an innovative STLF method fusing both spatial and temporal information. We propose a creative way to convert load data into graphical form, which is fed into graph convolutional networks (GCN) to learn spatial embeddings. The GCN embeddings are used along with temporal features to predict the load. We perform extensive experiments using state-of-the-art machine learning and deep learning techniques to validate our approach. The results demonstrate that by using spatial information, we can sub-stantially improve the forecasting performance.

AB - Accurate short-term load forecasting (STLF) is essential for the efficient operation of the power sector. Due to heightened volatility and intrinsic stochasticity, forecasting load at a fine resolution, such as weekly load, is difficult. Existing STLF techniques only rely on temporal data and auto-regressive processes to forecast load. However, the power grid has a graphical structure that provides spatial information too. This paper proposes an innovative STLF method fusing both spatial and temporal information. We propose a creative way to convert load data into graphical form, which is fed into graph convolutional networks (GCN) to learn spatial embeddings. The GCN embeddings are used along with temporal features to predict the load. We perform extensive experiments using state-of-the-art machine learning and deep learning techniques to validate our approach. The results demonstrate that by using spatial information, we can sub-stantially improve the forecasting performance.

KW - graph convolutional networks

KW - graph neural networks

KW - load forecasting

KW - machine learning

KW - short term load forecasting

KW - spatio-temporal load forecasting

UR - https://www.scopus.com/pages/publications/85175655711

U2 - 10.1109/ICRERA59003.2023.10269401

DO - 10.1109/ICRERA59003.2023.10269401

M3 - Conference contribution

AN - SCOPUS:85175655711

T3 - 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023

SP - 320

EP - 323

BT - 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023

Y2 - 29 August 2023 through 1 September 2023

ER -

Mansoor H, Shabbir M, Ali MY, Rauf H, Khalid M, Arshad N. Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks. In 12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 320-323. (12th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2023). doi: 10.1109/ICRERA59003.2023.10269401

Spatio-Temporal Short Term Load Forecasting Using Graph Neural Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this