LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid

Huayanran Zhou; Yihong Zhou; Haijing Zhang; Junjie Hu; Lars Nordströmd; Guangya Yang

doi:10.1007/978-981-15-9746-6_72

LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid

Huayanran Zhou
, Yihong Zhou
, Haijing Zhang
, Junjie Hu^*
, Lars Nordströmd
, Guangya Yang

^*Corresponding author for this work

North China Electric Power University
KTH Royal Institute of Technology

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

Abstract

The flexibility of Demand Response (DR) resources in grid operations has become a valuable solution to respond to the several problems brought about by the growth of intermittent renewable generation. However, the flexibility prediction of the DR resources has not yet been fully addressed in the available literature. This paper trained a long short-term memory (LSTM) recurrent neural network to predict the aggregated flexibility of electric vehicles (EVs). The prediction is based on the historical charging behavior of EVs and the DR signal (DS) which is proposed to facilitate prediction and DR management. Both the size and the maintaining time of the aggregated flexibility can be obtained from the prediction results. The accuracy of the flexibility prediction is verified through the simulation of case studies. The simulation results reveal that the size of flexibility changes under different maintaining time. The proposed flexibility prediction method may be of great assistance for DR management as well as the reserve of the gird.

Original language	English
Title of host publication	Proceedings of 2020 International Top-Level Forum on Engineering Science and Technology Development Strategy and The 5th PURPLE MOUNTAIN FORUM, PMF2020
Editors	Yusheng Xue, Yuping Zheng, Anjan Bose
Publisher	Springer
Publication date	2021
Pages	962-974
ISBN (Print)	9789811597459
DOIs	https://doi.org/10.1007/978-981-15-9746-6_72
Publication status	Published - 2021
Event	International Top-Level Forum on Engineering Science and Technology Development Strategy and 5^th PURPLE MOUNTAIN FORUM on Smart Grid Protection and Control - Nanjing, China Duration: 15 Aug 2020 → 16 Aug 2020

Conference

Conference	International Top-Level Forum on Engineering Science and Technology Development Strategy and 5^th PURPLE MOUNTAIN FORUM on Smart Grid Protection and Control
Country/Territory	China
City	Nanjing
Period	15/08/2020 → 16/08/2020

Series	Lecture Notes in Electrical Engineering
Volume	718
ISSN	1876-1100

Bibliographical note

Funding Information:
Funding Information.. This work was supported by the State Key Laboratory of smart grid protection and operation control open project (SGNR0000KJJS1907535).

Publisher Copyright:
© 2021, Springer Nature Singapore Pte Ltd.

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Deep learning (DL)
Demand response (DR)
Electric vehicles (EVs)
Load flexibility
Long short-term memory (LSTM)

Access to Document

10.1007/978-981-15-9746-6_72

OpenUrl availability

Check availability in DTU Findit

Cite this

Zhou, H., Zhou, Y., Zhang, H., Hu, J., Nordströmd, L., & Yang, G. (2021). LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid. In Y. Xue, Y. Zheng, & A. Bose (Eds.), Proceedings of 2020 International Top-Level Forum on Engineering Science and Technology Development Strategy and The 5th PURPLE MOUNTAIN FORUM, PMF2020 (pp. 962-974). Springer. https://doi.org/10.1007/978-981-15-9746-6_72

Zhou, Huayanran ; Zhou, Yihong ; Zhang, Haijing et al. / LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid. Proceedings of 2020 International Top-Level Forum on Engineering Science and Technology Development Strategy and The 5th PURPLE MOUNTAIN FORUM, PMF2020. editor / Yusheng Xue ; Yuping Zheng ; Anjan Bose. Springer, 2021. pp. 962-974 (Lecture Notes in Electrical Engineering, Vol. 718).

@inproceedings{4a191cdb59074acaabf23904d089ae4a,

title = "LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid",

abstract = "The flexibility of Demand Response (DR) resources in grid operations has become a valuable solution to respond to the several problems brought about by the growth of intermittent renewable generation. However, the flexibility prediction of the DR resources has not yet been fully addressed in the available literature. This paper trained a long short-term memory (LSTM) recurrent neural network to predict the aggregated flexibility of electric vehicles (EVs). The prediction is based on the historical charging behavior of EVs and the DR signal (DS) which is proposed to facilitate prediction and DR management. Both the size and the maintaining time of the aggregated flexibility can be obtained from the prediction results. The accuracy of the flexibility prediction is verified through the simulation of case studies. The simulation results reveal that the size of flexibility changes under different maintaining time. The proposed flexibility prediction method may be of great assistance for DR management as well as the reserve of the gird.",

keywords = "Deep learning (DL), Demand response (DR), Electric vehicles (EVs), Load flexibility, Long short-term memory (LSTM)",

author = "Huayanran Zhou and Yihong Zhou and Haijing Zhang and Junjie Hu and Lars Nordstr{\"o}md and Guangya Yang",

note = "Funding Information: Funding Information.. This work was supported by the State Key Laboratory of smart grid protection and operation control open project (SGNR0000KJJS1907535). Publisher Copyright: {\textcopyright} 2021, Springer Nature Singapore Pte Ltd.; International Top-Level Forum on Engineering Science and Technology Development Strategy and 5<sup>th</sup> PURPLE MOUNTAIN FORUM on Smart Grid Protection and Control ; Conference date: 15-08-2020 Through 16-08-2020",

year = "2021",

doi = "10.1007/978-981-15-9746-6\_72",

language = "English",

isbn = "9789811597459",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer",

pages = "962--974",

editor = "Yusheng Xue and Yuping Zheng and Anjan Bose",

booktitle = "Proceedings of 2020 International Top-Level Forum on Engineering Science and Technology Development Strategy and The 5th PURPLE MOUNTAIN FORUM, PMF2020",

}

Zhou, H, Zhou, Y, Zhang, H, Hu, J, Nordströmd, L & Yang, G 2021, LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid. in Y Xue, Y Zheng & A Bose (eds), Proceedings of 2020 International Top-Level Forum on Engineering Science and Technology Development Strategy and The 5th PURPLE MOUNTAIN FORUM, PMF2020. Springer, Lecture Notes in Electrical Engineering, vol. 718, pp. 962-974, International Top-Level Forum on Engineering Science and Technology Development Strategy and 5^th PURPLE MOUNTAIN FORUM on Smart Grid Protection and Control, Nanjing, China, 15/08/2020. https://doi.org/10.1007/978-981-15-9746-6_72

LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid. / Zhou, Huayanran; Zhou, Yihong; Zhang, Haijing et al.
Proceedings of 2020 International Top-Level Forum on Engineering Science and Technology Development Strategy and The 5th PURPLE MOUNTAIN FORUM, PMF2020. ed. / Yusheng Xue; Yuping Zheng; Anjan Bose. Springer, 2021. p. 962-974 (Lecture Notes in Electrical Engineering, Vol. 718).

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

TY - GEN

T1 - LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid

AU - Zhou, Huayanran

AU - Zhou, Yihong

AU - Zhang, Haijing

AU - Hu, Junjie

AU - Nordströmd, Lars

AU - Yang, Guangya

N1 - Funding Information: Funding Information.. This work was supported by the State Key Laboratory of smart grid protection and operation control open project (SGNR0000KJJS1907535). Publisher Copyright: © 2021, Springer Nature Singapore Pte Ltd.

PY - 2021

Y1 - 2021

N2 - The flexibility of Demand Response (DR) resources in grid operations has become a valuable solution to respond to the several problems brought about by the growth of intermittent renewable generation. However, the flexibility prediction of the DR resources has not yet been fully addressed in the available literature. This paper trained a long short-term memory (LSTM) recurrent neural network to predict the aggregated flexibility of electric vehicles (EVs). The prediction is based on the historical charging behavior of EVs and the DR signal (DS) which is proposed to facilitate prediction and DR management. Both the size and the maintaining time of the aggregated flexibility can be obtained from the prediction results. The accuracy of the flexibility prediction is verified through the simulation of case studies. The simulation results reveal that the size of flexibility changes under different maintaining time. The proposed flexibility prediction method may be of great assistance for DR management as well as the reserve of the gird.

AB - The flexibility of Demand Response (DR) resources in grid operations has become a valuable solution to respond to the several problems brought about by the growth of intermittent renewable generation. However, the flexibility prediction of the DR resources has not yet been fully addressed in the available literature. This paper trained a long short-term memory (LSTM) recurrent neural network to predict the aggregated flexibility of electric vehicles (EVs). The prediction is based on the historical charging behavior of EVs and the DR signal (DS) which is proposed to facilitate prediction and DR management. Both the size and the maintaining time of the aggregated flexibility can be obtained from the prediction results. The accuracy of the flexibility prediction is verified through the simulation of case studies. The simulation results reveal that the size of flexibility changes under different maintaining time. The proposed flexibility prediction method may be of great assistance for DR management as well as the reserve of the gird.

KW - Deep learning (DL)

KW - Demand response (DR)

KW - Electric vehicles (EVs)

KW - Load flexibility

KW - Long short-term memory (LSTM)

U2 - 10.1007/978-981-15-9746-6_72

DO - 10.1007/978-981-15-9746-6_72

M3 - Article in proceedings

AN - SCOPUS:85101524001

SN - 9789811597459

T3 - Lecture Notes in Electrical Engineering

SP - 962

EP - 974

BT - Proceedings of 2020 International Top-Level Forum on Engineering Science and Technology Development Strategy and The 5th PURPLE MOUNTAIN FORUM, PMF2020

A2 - Xue, Yusheng

A2 - Zheng, Yuping

A2 - Bose, Anjan

PB - Springer

T2 - International Top-Level Forum on Engineering Science and Technology Development Strategy and 5<sup>th</sup> PURPLE MOUNTAIN FORUM on Smart Grid Protection and Control

Y2 - 15 August 2020 through 16 August 2020

ER -

Zhou H, Zhou Y, Zhang H, Hu J, Nordströmd L, Yang G. LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid. In Xue Y, Zheng Y, Bose A, editors, Proceedings of 2020 International Top-Level Forum on Engineering Science and Technology Development Strategy and The 5th PURPLE MOUNTAIN FORUM, PMF2020. Springer. 2021. p. 962-974. (Lecture Notes in Electrical Engineering, Vol. 718). doi: 10.1007/978-981-15-9746-6_72

LSTM Network-Based Method for Flexibility Prediction of Aggregated Electric Vehicles in Smart Grid

Abstract

Conference

Bibliographical note

UN SDGs

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this