Quantum Renewable Scenario Generation

Zefan Tang; Peng Zhang; Yifan Zhou

doi:10.1109/PESGM48719.2022.9916926

Quantum Renewable Scenario Generation

Zefan Tang
, Peng Zhang
, Yifan Zhou

Stony Brook University

Brookhaven National Laboratory

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

6 Scopus citations

Abstract

This paper underpins the potential of quantum generative adversarial networks (QGANs) for renewable scenario generation in power grids. A single QGAN with either amplitude or angle encoding is hard to construct. To bridge the gaps, this paper devises a Multi-QGAN framework utilizing multiple QGANs. A correlation-based Multi-QGAN (CMulti-QGAN) approach is further established to improve the Multi-QGAN performance. Data from real solar systems in Connecticut are collected for numerical studies. Results demonstrate the effectiveness and robustness of Multi-QGAN and CMulti-QGAN, and also validate the superiority of CMulti-QGAN over Multi-QGAN.

Original language	English
Title of host publication	2022 IEEE Power and Energy Society General Meeting, PESGM 2022
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665408233
DOIs	https://doi.org/10.1109/PESGM48719.2022.9916926
State	Published - 2022
Event	2022 IEEE Power and Energy Society General Meeting, PESGM 2022 - Denver, United States Duration: Jul 17 2022 → Jul 21 2022

Publication series

Name	IEEE Power and Energy Society General Meeting
Volume	2022-July

Conference

Conference	2022 IEEE Power and Energy Society General Meeting, PESGM 2022
Country/Territory	United States
City	Denver
Period	07/17/22 → 07/21/22

Keywords

Quantum generative adversarial network
quantum computing
renewable scenario generation

Access to Document

10.1109/PESGM48719.2022.9916926

Cite this

@inproceedings{cc3e17b3fa1b40ab8df47621472bc175,

title = "Quantum Renewable Scenario Generation",

abstract = "This paper underpins the potential of quantum generative adversarial networks (QGANs) for renewable scenario generation in power grids. A single QGAN with either amplitude or angle encoding is hard to construct. To bridge the gaps, this paper devises a Multi-QGAN framework utilizing multiple QGANs. A correlation-based Multi-QGAN (CMulti-QGAN) approach is further established to improve the Multi-QGAN performance. Data from real solar systems in Connecticut are collected for numerical studies. Results demonstrate the effectiveness and robustness of Multi-QGAN and CMulti-QGAN, and also validate the superiority of CMulti-QGAN over Multi-QGAN.",

keywords = "Quantum generative adversarial network, quantum computing, renewable scenario generation",

author = "Zefan Tang and Peng Zhang and Yifan Zhou",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Power and Energy Society General Meeting, PESGM 2022 ; Conference date: 17-07-2022 Through 21-07-2022",

year = "2022",

doi = "10.1109/PESGM48719.2022.9916926",

language = "English",

series = "IEEE Power and Energy Society General Meeting",

publisher = "IEEE Computer Society",

booktitle = "2022 IEEE Power and Energy Society General Meeting, PESGM 2022",

}

Tang, Z, Zhang, P & Zhou, Y 2022, Quantum Renewable Scenario Generation. in 2022 IEEE Power and Energy Society General Meeting, PESGM 2022. IEEE Power and Energy Society General Meeting, vol. 2022-July, IEEE Computer Society, 2022 IEEE Power and Energy Society General Meeting, PESGM 2022, Denver, United States, 07/17/22. https://doi.org/10.1109/PESGM48719.2022.9916926

TY - GEN

T1 - Quantum Renewable Scenario Generation

AU - Tang, Zefan

AU - Zhang, Peng

AU - Zhou, Yifan

PY - 2022

Y1 - 2022

N2 - This paper underpins the potential of quantum generative adversarial networks (QGANs) for renewable scenario generation in power grids. A single QGAN with either amplitude or angle encoding is hard to construct. To bridge the gaps, this paper devises a Multi-QGAN framework utilizing multiple QGANs. A correlation-based Multi-QGAN (CMulti-QGAN) approach is further established to improve the Multi-QGAN performance. Data from real solar systems in Connecticut are collected for numerical studies. Results demonstrate the effectiveness and robustness of Multi-QGAN and CMulti-QGAN, and also validate the superiority of CMulti-QGAN over Multi-QGAN.

AB - This paper underpins the potential of quantum generative adversarial networks (QGANs) for renewable scenario generation in power grids. A single QGAN with either amplitude or angle encoding is hard to construct. To bridge the gaps, this paper devises a Multi-QGAN framework utilizing multiple QGANs. A correlation-based Multi-QGAN (CMulti-QGAN) approach is further established to improve the Multi-QGAN performance. Data from real solar systems in Connecticut are collected for numerical studies. Results demonstrate the effectiveness and robustness of Multi-QGAN and CMulti-QGAN, and also validate the superiority of CMulti-QGAN over Multi-QGAN.

KW - Quantum generative adversarial network

KW - quantum computing

KW - renewable scenario generation

UR - https://www.scopus.com/pages/publications/85141445517

U2 - 10.1109/PESGM48719.2022.9916926

DO - 10.1109/PESGM48719.2022.9916926

M3 - Conference contribution

T3 - IEEE Power and Energy Society General Meeting

BT - 2022 IEEE Power and Energy Society General Meeting, PESGM 2022

PB - IEEE Computer Society

T2 - 2022 IEEE Power and Energy Society General Meeting, PESGM 2022

Y2 - 17 July 2022 through 21 July 2022

ER -

Quantum Renewable Scenario Generation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this