Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder

Hai Li; Jianfeng Feng; Huangjing Gu; Xiangyang Xue; Nannan Yan; Yu Cao; Haosheng Lv; Xiaodi Wang; Tianyu Yang

doi:10.1117/12.3050488

Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder

Hai Li^*
, Jianfeng Feng
, Huangjing Gu
, Xiangyang Xue
, Nannan Yan
, Yu Cao
, Haosheng Lv
, Xiaodi Wang
, Tianyu Yang

^*Corresponding author for this work

State Grid Shanghai Electric Power Company
Fudan University

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

Abstract

Energy demand in modern cities is becoming more and more complex. Knowing its pattern can help managers make proper decisions. However, finding the pattern of large-scale spatial coverage fields, such as a whole city, is not easy. In this paper, a data-driven stacked autoencoder-based framework is proposed to capture the spatio-temporal pattern for electricity consumption. The data can be organized as a one-time series and the geography coverage of the analysis can be determined by the collected data. An experiment with collected data proves the feasibility of the framework.

Original language	English
Title of host publication	Tenth International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024
Editors	Yuanhao Wang, Cristian Paul Chioncel
Publisher	SPIE
ISBN (Electronic)	9781510686243
DOIs	https://doi.org/10.1117/12.3050488
Publication status	Published - 2024
Externally published	Yes
Event	10th International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024 - Lhasa, China Duration: 16 Aug 2024 → 18 Aug 2024

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	13419
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	10th International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024
Country/Territory	China
City	Lhasa
Period	16/08/24 → 18/08/24

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

autoencoder
electricity consumption
spatial coverage field
time series

Access to Document

10.1117/12.3050488

Cite this

Li, H., Feng, J., Gu, H., Xue, X., Yan, N., Cao, Y., Lv, H., Wang, X., & Yang, T. (2024). Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder. In Y. Wang, & C. P. Chioncel (Eds.), Tenth International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024 Article 134191T (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13419). SPIE. https://doi.org/10.1117/12.3050488

@inproceedings{e734bd94460c42408236d3aa2d92ff3b,

title = "Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder",

abstract = "Energy demand in modern cities is becoming more and more complex. Knowing its pattern can help managers make proper decisions. However, finding the pattern of large-scale spatial coverage fields, such as a whole city, is not easy. In this paper, a data-driven stacked autoencoder-based framework is proposed to capture the spatio-temporal pattern for electricity consumption. The data can be organized as a one-time series and the geography coverage of the analysis can be determined by the collected data. An experiment with collected data proves the feasibility of the framework.",

keywords = "autoencoder, electricity consumption, spatial coverage field, time series",

author = "Hai Li and Jianfeng Feng and Huangjing Gu and Xiangyang Xue and Nannan Yan and Yu Cao and Haosheng Lv and Xiaodi Wang and Tianyu Yang",

note = "Publisher Copyright: {\textcopyright} 2024 SPIE.; 10th International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024 ; Conference date: 16-08-2024 Through 18-08-2024",

year = "2024",

doi = "10.1117/12.3050488",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Yuanhao Wang and Chioncel, \{Cristian Paul\}",

booktitle = "Tenth International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024",

address = "United States",

}

Li, H, Feng, J, Gu, H, Xue, X, Yan, N, Cao, Y, Lv, H, Wang, X & Yang, T 2024, Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder. in Y Wang & CP Chioncel (eds), Tenth International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024., 134191T, Proceedings of SPIE - The International Society for Optical Engineering, vol. 13419, SPIE, 10th International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024, Lhasa, China, 16/08/24. https://doi.org/10.1117/12.3050488

Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder. / Li, Hai; Feng, Jianfeng; Gu, Huangjing et al.
Tenth International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024. ed. / Yuanhao Wang; Cristian Paul Chioncel. SPIE, 2024. 134191T (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 13419).

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

TY - GEN

T1 - Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder

AU - Li, Hai

AU - Feng, Jianfeng

AU - Gu, Huangjing

AU - Xue, Xiangyang

AU - Yan, Nannan

AU - Cao, Yu

AU - Lv, Haosheng

AU - Wang, Xiaodi

AU - Yang, Tianyu

PY - 2024

Y1 - 2024

N2 - Energy demand in modern cities is becoming more and more complex. Knowing its pattern can help managers make proper decisions. However, finding the pattern of large-scale spatial coverage fields, such as a whole city, is not easy. In this paper, a data-driven stacked autoencoder-based framework is proposed to capture the spatio-temporal pattern for electricity consumption. The data can be organized as a one-time series and the geography coverage of the analysis can be determined by the collected data. An experiment with collected data proves the feasibility of the framework.

AB - Energy demand in modern cities is becoming more and more complex. Knowing its pattern can help managers make proper decisions. However, finding the pattern of large-scale spatial coverage fields, such as a whole city, is not easy. In this paper, a data-driven stacked autoencoder-based framework is proposed to capture the spatio-temporal pattern for electricity consumption. The data can be organized as a one-time series and the geography coverage of the analysis can be determined by the collected data. An experiment with collected data proves the feasibility of the framework.

KW - autoencoder

KW - electricity consumption

KW - spatial coverage field

KW - time series

UR - https://www.scopus.com/pages/publications/85213964774

U2 - 10.1117/12.3050488

DO - 10.1117/12.3050488

M3 - Conference contribution

AN - SCOPUS:85213964774

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Tenth International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024

A2 - Wang, Yuanhao

A2 - Chioncel, Cristian Paul

PB - SPIE

T2 - 10th International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024

Y2 - 16 August 2024 through 18 August 2024

ER -

Li H, Feng J, Gu H, Xue X, Yan N, Cao Y et al. Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder. In Wang Y, Chioncel CP, editors, Tenth International Conference on Energy Materials and Electrical Engineering, ICEMEE 2024. SPIE. 2024. 134191T. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.3050488

Spatio-temporal analysis of power demand in smart grid based on stacked autoencoder

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this