Robust machine-learned algorithms for efficient grid operation

Increasing penetration of variable and intermittent renewable energy resources on the energy grid poses a challenge for reliable and efficient grid operation, necessitating the development of algorithms that are robust to this uncertainty. However, standard algorithms incorporating uncertainty for g...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Environmental Data Science Ročník 4
Hlavní autori: Christianson, Nicolas, Yeh, Christopher, Li, Tongxin, Hosseini, Mehdi, Torabi Rad, Mahdi, Golmohammadi, Azarang, Wierman, Adam
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cambridge University Press 22.04.2025
Predmet:
ISSN:2634-4602, 2634-4602
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Increasing penetration of variable and intermittent renewable energy resources on the energy grid poses a challenge for reliable and efficient grid operation, necessitating the development of algorithms that are robust to this uncertainty. However, standard algorithms incorporating uncertainty for generation dispatch are computationally intractable when costs are nonconvex, and machine learning-based approaches lack worst-case guarantees on their performance. In this work, we propose a learning-augmented algorithm, R obust ML, that exploits the good average-case performance of a machine-learned algorithm for minimizing dispatch and ramping costs of dispatchable generation resources while providing provable worst-case guarantees on cost. We evaluate the algorithm on a realistic model of a combined cycle cogeneration plant, where it exhibits robustness to distribution shift while enabling improved efficiency as renewables penetration increases.
AbstractList Increasing penetration of variable and intermittent renewable energy resources on the energy grid poses a challenge for reliable and efficient grid operation, necessitating the development of algorithms that are robust to this uncertainty. However, standard algorithms incorporating uncertainty for generation dispatch are computationally intractable when costs are nonconvex, and machine learning-based approaches lack worst-case guarantees on their performance. In this work, we propose a learning-augmented algorithm, R obust ML, that exploits the good average-case performance of a machine-learned algorithm for minimizing dispatch and ramping costs of dispatchable generation resources while providing provable worst-case guarantees on cost. We evaluate the algorithm on a realistic model of a combined cycle cogeneration plant, where it exhibits robustness to distribution shift while enabling improved efficiency as renewables penetration increases.
Increasing penetration of variable and intermittent renewable energy resources on the energy grid poses a challenge for reliable and efficient grid operation, necessitating the development of algorithms that are robust to this uncertainty. However, standard algorithms incorporating uncertainty for generation dispatch are computationally intractable when costs are nonconvex, and machine learning-based approaches lack worst-case guarantees on their performance. In this work, we propose a learning-augmented algorithm, RobustML, that exploits the good average-case performance of a machine-learned algorithm for minimizing dispatch and ramping costs of dispatchable generation resources while providing provable worst-case guarantees on cost. We evaluate the algorithm on a realistic model of a combined cycle cogeneration plant, where it exhibits robustness to distribution shift while enabling improved efficiency as renewables penetration increases.
ArticleNumber e24
Author Wierman, Adam
Torabi Rad, Mahdi
Yeh, Christopher
Li, Tongxin
Christianson, Nicolas
Hosseini, Mehdi
Golmohammadi, Azarang
Author_xml – sequence: 1
  givenname: Nicolas
  orcidid: 0000-0001-8330-8964
  surname: Christianson
  fullname: Christianson, Nicolas
– sequence: 2
  givenname: Christopher
  surname: Yeh
  fullname: Yeh, Christopher
– sequence: 3
  givenname: Tongxin
  surname: Li
  fullname: Li, Tongxin
– sequence: 4
  givenname: Mehdi
  surname: Hosseini
  fullname: Hosseini, Mehdi
– sequence: 5
  givenname: Mahdi
  surname: Torabi Rad
  fullname: Torabi Rad, Mahdi
– sequence: 6
  givenname: Azarang
  surname: Golmohammadi
  fullname: Golmohammadi, Azarang
– sequence: 7
  givenname: Adam
  surname: Wierman
  fullname: Wierman, Adam
BookMark eNpNkEtLw0AURgepYK1d-Qeyl9R5J9kIUnwUCoLoeriZe9NOSTNlJi7897Yq4ur7OIuzOJdsMsSBGLsWfCG4qG4J80JyqReyPmNTaZUuteVy8u9fsHnOO865kkJW2kzZ3WtsP_JY7MFvw0BlT5AGwgL6TUxh3O5z0cVUUNcFH2gYi00KWMQDJRhDHK7YeQd9pvnvztj748Pb8rlcvzytlvfr0svGjqWpGiBDDaISyL23ujVdI6paSzAesALLCaFRtjLWSJIdtcq2Go9UGqzVjK1-vBhh5w4p7CF9ugjBfYOYNg7SGHxPzosKRAtIqm00IgJwo7ipqcVaW5JH182Py6eYc6Luzye4O5V0x5LuVNLJWn0B7mRpKg
Cites_doi 10.1038/s41592-019-0686-2
10.1080/19401493.2012.671959
10.1609/aaai.v35i12.17294
10.1145/3579442
10.1016/j.automatica.2003.08.009
10.1002/aic.690450811
10.48550/arXiv.2007.01002
10.1109/TPWRS.2019.2891541
10.1109/TSG.2015.2449760
10.1109/CONTROL.2014.6915220
10.1145/3447555.3464860
10.1109/TPWRS.2019.2963022
10.1016/j.ifacol.2018.09.373
10.1016/j.rser.2017.03.058
10.1016/j.epsr.2022.108597
10.1007/BFb0109870
10.1016/j.buildenv.2016.05.034
10.1109/SmartGridComm.2018.8587550
10.1049/iet-cta.2016.1061
10.1109/TCST.2017.2699159
10.1109/TASE.2014.2352280
10.1109/TPWRS.2009.2037326
10.1109/TPWRS.2015.2461535
10.1145/3489048.3530961
10.3390/s20030781
10.1109/ADCONIP.2017.7983780
10.1145/2896377.2901464
10.1609/aaai.v34i01.5403
10.1109/PESS.2000.867469
10.1609/aaai.v37i4.25520
10.1016/j.epsr.2022.108412
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.1017/eds.2024.28
DatabaseName CrossRef
DOAJ: Directory of Open Access Journal (DOAJ)
DatabaseTitle CrossRef
DatabaseTitleList CrossRef

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
EISSN 2634-4602
ExternalDocumentID oai_doaj_org_article_c17a1bade3b94dddaa053058ebd846e2
10_1017_eds_2024_28
GroupedDBID 09C
09E
0R~
AANRG
AASVR
AAYXX
ABGDZ
ABVZP
ABXHF
ACAJB
ACDLN
ACFCP
ACZWT
ADDNB
ADKIL
ADVJH
AEBAK
AFRIC
AFZFC
AGABE
AGBYD
AGJUD
AHIPN
AHRGI
AKMAY
ALMA_UNASSIGNED_HOLDINGS
AQJOH
ARCSS
BLZWO
CCQAD
CITATION
CJCSC
GROUPED_DOAJ
IKXGN
IPYYG
M~E
OK1
RCA
ROL
WFFJZ
ID FETCH-LOGICAL-c296t-579ae5e9dd31d0cc64b5f917842a5cad7a60eda93675652e2feb36b4d0ed25d83
IEDL.DBID DOA
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001501742200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2634-4602
IngestDate Tue Oct 14 15:03:31 EDT 2025
Sat Nov 29 08:01:19 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License http://creativecommons.org/licenses/by-nc-sa/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c296t-579ae5e9dd31d0cc64b5f917842a5cad7a60eda93675652e2feb36b4d0ed25d83
ORCID 0000-0001-8330-8964
OpenAccessLink https://doaj.org/article/c17a1bade3b94dddaa053058ebd846e2
ParticipantIDs doaj_primary_oai_doaj_org_article_c17a1bade3b94dddaa053058ebd846e2
crossref_primary_10_1017_eds_2024_28
PublicationCentury 2000
PublicationDate 2025-04-22
PublicationDateYYYYMMDD 2025-04-22
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-22
  day: 22
PublicationDecade 2020
PublicationTitle Environmental Data Science
PublicationYear 2025
Publisher Cambridge University Press
Publisher_xml – name: Cambridge University Press
References Kotary (S2634460224000281_r18) 2021; 34
S2634460224000281_r21
S2634460224000281_r43
S2634460224000281_r20
S2634460224000281_r42
S2634460224000281_r41
S2634460224000281_r40
S2634460224000281_r25
S2634460224000281_r46
Morari (S2634460224000281_r28) 1999; 16
S2634460224000281_r45
S2634460224000281_r22
Zhang (S2634460224000281_r44) 2021; 34
Lin (S2634460224000281_r24) 2021; 34
S2634460224000281_r29
S2634460224000281_r27
S2634460224000281_r26
S2634460224000281_r32
S2634460224000281_r4
S2634460224000281_r10
S2634460224000281_r5
S2634460224000281_r31
S2634460224000281_r6
S2634460224000281_r30
S2634460224000281_r7
S2634460224000281_r8
S2634460224000281_r36
S2634460224000281_r14
S2634460224000281_r9
S2634460224000281_r35
S2634460224000281_r13
S2634460224000281_r34
S2634460224000281_r12
S2634460224000281_r11
S2634460224000281_r33
S2634460224000281_r1
S2634460224000281_r2
S2634460224000281_r3
S2634460224000281_r17
S2634460224000281_r39
S2634460224000281_r38
S2634460224000281_r16
S2634460224000281_r15
Li (S2634460224000281_r23) 2022; 6
S2634460224000281_r19
References_xml – volume: 34
  start-page: 5174
  year: 2021
  ident: S2634460224000281_r24
  article-title: Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems
  publication-title: Advances in Neural Information Processing Systems
– ident: S2634460224000281_r41
  doi: 10.1038/s41592-019-0686-2
– ident: S2634460224000281_r15
  doi: 10.1080/19401493.2012.671959
– ident: S2634460224000281_r43
  doi: 10.1609/aaai.v35i12.17294
– ident: S2634460224000281_r35
  doi: 10.1145/3579442
– ident: S2634460224000281_r19
  doi: 10.1016/j.automatica.2003.08.009
– ident: S2634460224000281_r36
  doi: 10.1002/aic.690450811
– ident: S2634460224000281_r31
  doi: 10.48550/arXiv.2007.01002
– ident: S2634460224000281_r14
  doi: 10.1109/TPWRS.2019.2891541
– ident: S2634460224000281_r27
  doi: 10.1109/TSG.2015.2449760
– ident: S2634460224000281_r25
  doi: 10.1109/CONTROL.2014.6915220
– ident: S2634460224000281_r20
  doi: 10.1145/3447555.3464860
– ident: S2634460224000281_r16
– volume: 34
  start-page: 13599
  year: 2021
  ident: S2634460224000281_r44
  article-title: Revisiting Smoothed Online Learning
  publication-title: Advances in Neural Information Processing Systems
– ident: S2634460224000281_r46
  doi: 10.1109/TPWRS.2019.2963022
– ident: S2634460224000281_r33
  doi: 10.1016/j.ifacol.2018.09.373
– volume: 34
  start-page: 24981
  year: 2021
  ident: S2634460224000281_r18
  article-title: Learning Hard Optimization Problems: A Data Generation Perspective
  publication-title: Advances in Neural Information Processing Systems
– ident: S2634460224000281_r39
  doi: 10.1016/j.rser.2017.03.058
– volume: 6
  start-page: 1
  year: 2022
  ident: S2634460224000281_r23
  article-title: Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions
  publication-title: Proceedings of the ACM on Measurement and Analysis of Computing Systems
– ident: S2634460224000281_r45
– ident: S2634460224000281_r7
– ident: S2634460224000281_r9
  doi: 10.1016/j.epsr.2022.108597
– ident: S2634460224000281_r2
  doi: 10.1007/BFb0109870
– ident: S2634460224000281_r1
– ident: S2634460224000281_r17
  doi: 10.1016/j.buildenv.2016.05.034
– ident: S2634460224000281_r21
  doi: 10.1109/SmartGridComm.2018.8587550
– volume: 16
  year: 1999
  ident: S2634460224000281_r28
  article-title: Model predictive control: Past, present and future
  publication-title: Computers and Chemical Engineering
– ident: S2634460224000281_r4
  doi: 10.1049/iet-cta.2016.1061
– ident: S2634460224000281_r29
  doi: 10.1109/TCST.2017.2699159
– ident: S2634460224000281_r10
  doi: 10.1109/TASE.2014.2352280
– ident: S2634460224000281_r26
– ident: S2634460224000281_r40
  doi: 10.1109/TPWRS.2009.2037326
– ident: S2634460224000281_r12
  doi: 10.1109/TPWRS.2015.2461535
– ident: S2634460224000281_r22
  doi: 10.1145/3489048.3530961
– ident: S2634460224000281_r5
  doi: 10.3390/s20030781
– ident: S2634460224000281_r42
– ident: S2634460224000281_r8
– ident: S2634460224000281_r34
– ident: S2634460224000281_r38
  doi: 10.1109/ADCONIP.2017.7983780
– ident: S2634460224000281_r6
  doi: 10.1145/2896377.2901464
– ident: S2634460224000281_r13
  doi: 10.1609/aaai.v34i01.5403
– ident: S2634460224000281_r11
– ident: S2634460224000281_r3
  doi: 10.1109/PESS.2000.867469
– ident: S2634460224000281_r32
  doi: 10.1609/aaai.v37i4.25520
– ident: S2634460224000281_r30
  doi: 10.1016/j.epsr.2022.108412
SSID ssj0003212745
Score 2.2892342
Snippet Increasing penetration of variable and intermittent renewable energy resources on the energy grid poses a challenge for reliable and efficient grid operation,...
SourceID doaj
crossref
SourceType Open Website
Index Database
SubjectTerms energy systems
learning-augmented algorithms
machine learning robustness
online algorithms
Title Robust machine-learned algorithms for efficient grid operation
URI https://doaj.org/article/c17a1bade3b94dddaa053058ebd846e2
Volume 4
WOSCitedRecordID wos001501742200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAEN
  databaseName: Cambridge University Press Wholly Gold Open Access Journals
  customDbUrl:
  eissn: 2634-4602
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003212745
  issn: 2634-4602
  databaseCode: IKXGN
  dateStart: 20220101
  isFulltext: true
  titleUrlDefault: http://journals.cambridge.org/action/login
  providerName: Cambridge University Press
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2634-4602
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003212745
  issn: 2634-4602
  databaseCode: DOA
  dateStart: 20220101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2634-4602
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003212745
  issn: 2634-4602
  databaseCode: M~E
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NS8NAEF2kevAiior1o-TQazTZz-xFULEqQhFR6C3s7kxqwTalTf397iZRcvPidQlLMm-ZmRdm3yNkmGhXmIza8HuJxZxBEWunPOdJlSw4y6TUrjabUONxNpnol47VV5gJa-SBm8BduVSZ1BpAZjUHAGP8sUlEhhZ86cQ6-_qup0OmQg5mQbici_ZCXtCIRgji3JRfBt_1TgnqKPXXJWW0T_baXjC6ad7hgGzh4pBcv5Z2s66ieT3liHFt64AQmc9p6Yn8x3wd-T4zwlr6wVeMaLqaQVQusYHyiLyP7t_uHuPW5CB2VMsqFkobFKgBWAqJc5JbUXgOlXFqhDOgjEwQjGa-s5eCIi08_ZWWg1-lAjJ2THqLcoEnJLIAgqfAQaENwmWZUVAopJ4EqRQN75Phz3fny0bLIm-GvFTuw5OH8OQ065PbEJPfR4IAdb3gYclbWPK_YDn9j03OyC4NdrsJjyk9J71qtcELsuO-qtl6NagRH5Dtp-fJw_gbvHa1VA
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Robust+machine-learned+algorithms+for+efficient+grid+operation&rft.jtitle=Environmental+Data+Science&rft.au=Christianson%2C+Nicolas&rft.au=Yeh%2C+Christopher&rft.au=Li%2C+Tongxin&rft.au=Hosseini%2C+Mehdi&rft.date=2025-04-22&rft.issn=2634-4602&rft.eissn=2634-4602&rft.volume=4&rft_id=info:doi/10.1017%2Feds.2024.28&rft.externalDBID=n%2Fa&rft.externalDocID=10_1017_eds_2024_28
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2634-4602&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2634-4602&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2634-4602&client=summon