Gaussian Process Approximate Dynamic Programming for Energy-Optimal Supervisory Control of Parallel Hybrid Electric Vehicles

We propose an energy-efficient supervisory control method for the power management of parallel hybrid electric vehicles (HEVs) to improve the fuel economy and reduce exhaust gas emissions. Plug-in HEVs ((P)HEVs) have multiple power sources (e.g., an engine and motor) that should be cooperatively ope...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on vehicular technology Ročník 71; číslo 8; s. 8367 - 8380
Hlavní autori:	Bae, Jin Woo, Kim, Kwang-Ki K.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.08.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Approximate dynamic programming Batteries Control methods Dynamic programming Electric vehicles Energy conversion efficiency Energy efficiency Energy management Engines Exhaust gases Feedback control Fuel consumption Fuel economy Gaussian process gaussian process regression Hybrid electric vehicles Mathematical models Maximum power Optimal control Parallel hybrid electric vehicles Power management Power sources Statistical analysis Supervisory control Traffic speed value function approximation Vehicle dynamics
ISSN:	0018-9545, 1939-9359
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	We propose an energy-efficient supervisory control method for the power management of parallel hybrid electric vehicles (HEVs) to improve the fuel economy and reduce exhaust gas emissions. Plug-in HEVs ((P)HEVs) have multiple power sources (e.g., an engine and motor) that should be cooperatively operated to meet the required instantaneous traction power for the desired vehicle speed while satisfying their physical limits. Because the efficiencies of the engine and motor vary with different operating speeds and torques, the main issue of energy-efficient power management is to allocate the power demand among the power sources by achieving maximum power conversion efficiencies and satisfy the operating limits. For an efficient power allocation, an optimal control problem is formulated, and a global solution is found through deterministic dynamic programming (DP). Owing to the curse of dimensionality and uncertainties in real driving, DP solutions are not directly applicable in real time. To resolve the limitations of DP, we employ a non-parametric Bayesian function approximation technique using a Gaussian process (GP). The offline DP solutions obtained from a set of real vehicle driving test data were used to learn a state-dependent probabilistic value function through Gaussian process regression. For online implementations, a receding horizon control scheme was applied for the feedback control of the power management. In comparison with the existing charge sustaining strategy and charge depleting and charge sustaining mixed controllers, we recorded fuel efficiency improvements of over 4.8% and 7.3%, respectively, in a mixed urban-suburban route.
AbstractList	We propose an energy-efficient supervisory control method for the power management of parallel hybrid electric vehicles (HEVs) to improve the fuel economy and reduce exhaust gas emissions. Plug-in HEVs ((P)HEVs) have multiple power sources (e.g., an engine and motor) that should be cooperatively operated to meet the required instantaneous traction power for the desired vehicle speed while satisfying their physical limits. Because the efficiencies of the engine and motor vary with different operating speeds and torques, the main issue of energy-efficient power management is to allocate the power demand among the power sources by achieving maximum power conversion efficiencies and satisfy the operating limits. For an efficient power allocation, an optimal control problem is formulated, and a global solution is found through deterministic dynamic programming (DP). Owing to the curse of dimensionality and uncertainties in real driving, DP solutions are not directly applicable in real time. To resolve the limitations of DP, we employ a non-parametric Bayesian function approximation technique using a Gaussian process (GP). The offline DP solutions obtained from a set of real vehicle driving test data were used to learn a state-dependent probabilistic value function through Gaussian process regression. For online implementations, a receding horizon control scheme was applied for the feedback control of the power management. In comparison with the existing charge sustaining strategy and charge depleting and charge sustaining mixed controllers, we recorded fuel efficiency improvements of over 4.8% and 7.3%, respectively, in a mixed urban-suburban route.
Author	Kim, Kwang-Ki K. Bae, Jin Woo
Author_xml	– sequence: 1 givenname: Jin Woo surname: Bae fullname: Bae, Jin Woo email: jinwoo.bae@tamu.edu organization: Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA – sequence: 2 givenname: Kwang-Ki K. orcidid: 0000-0002-0499-7253 surname: Kim fullname: Kim, Kwang-Ki K. email: kwangki.kim@inha.ac.kr organization: Department of Electrical and Computer Engineering, Inha University, Incheon, South Korea
BookMark	eNp9kM1Lw0AQxRepYFu9C14WPKfuR9Jkj6XWVihYsPYaNttJ3bLNxt1UDPjHu6HFgwdPM8O8N8P7DVCvshUgdEvJiFIiHtab9YgRxkacphmNxxeoTwUXkeCJ6KE-ITSLRBInV2jg_T6McSxoH33P5dF7LSu8claB93hS185-6YNsAD-2lTxo1e12Th4Outrh0jo8q8Dt2uilboLO4NdjDe5Te-taPLVV46zBtsQr6aQxYPCiLZze4pkB1bhwbgPvWhnw1-iylMbDzbkO0dvTbD1dRMuX-fN0sowUE7SJgCupUhb6QnBVFFvORUYoT8YJjzMqhCQiYSnPQDFVylTSlBNVxoqQsiBM8iG6P90NyT6O4Jt8b4-uCi9zlhJOOYtDGaLxSaWc9d5BmSvdyEZ3gaQ2OSV5RzoPpPOOdH4mHYzkj7F2gYtr_7PcnSwaAH7lIs1Ywsb8B3A6jMA
CODEN	ITVTAB
CitedBy_id	crossref_primary_10_1109_TPWRS_2022_3227345 crossref_primary_10_1049_gtd2_70145 crossref_primary_10_1109_TITS_2023_3327380 crossref_primary_10_1109_TTE_2024_3356196 crossref_primary_10_3390_app13105947 crossref_primary_10_1109_TTE_2023_3290024 crossref_primary_10_3390_math11224662 crossref_primary_10_3390_a18060354 crossref_primary_10_1016_j_energy_2025_136292 crossref_primary_10_1016_j_est_2023_108392 crossref_primary_10_7467_KSAE_2023_31_1_019 crossref_primary_10_1109_TVT_2024_3417714 crossref_primary_10_1109_TIV_2023_3346300 crossref_primary_10_1016_j_energy_2023_127588 crossref_primary_10_1016_j_est_2024_112132
Cites_doi	10.4271/2013-01-1470 10.1109/TVT.2021.3075729 10.2139/ssrn.3251551 10.1109/TITS.2021.3099812 10.1090/s0002-9904-1954-09848-8 10.1109/ACC.2008.4587201 10.1002/9781118122631 10.1109/TITS.2014.2319812 10.1109/ACCESS.2020.3036033 10.7551/mitpress/10187.001.0001 10.1109/ACCESS.2020.3027024 10.1109/MCS.2007.338280 10.1016/j.trd.2019.10.024 10.1109/WCICA.2008.4594156 10.1109/MCS.2015.2449688 10.1002/9781118970553 10.1109/TITS.2014.2309674 10.3390/app8020187 10.1109/TVT.2015.2405347 10.1016/j.rser.2015.03.093 10.1016/j.jpowsour.2016.11.106 10.3390/wevj8010274 10.2516/ogst/2014006 10.1016/j.energy.2014.03.020 10.1109/TIV.2020.3011954 10.1109/ACCESS.2021.3098807 10.1016/j.apenergy.2015.12.035 10.1109/MED.2019.8798496 10.1155/2014/160510 10.1002/9781119278924.ch6 10.3390/wevj12020085 10.1109/TVT.2018.2866569 10.1002/SERIES1345 10.3182/20080706-5-KR-1001.00573 10.1109/TVT.2009.2027709 10.1016/j.apenergy.2016.08.085 10.3390/en13133352 10.1109/JPROC.2007.892489 10.1016/j.neucom.2008.12.019 10.1109/IVS.2016.7535426 10.1016/j.ifacol.2019.09.089 10.1016/j.rser.2015.09.036 10.3390/en12142750 10.1109/ACCESS.2019.2941399 10.1007/978-3-642-35913-2 10.1016/j.apenergy.2017.11.072 10.35833/MPCE.2018.000374
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD FR3 KR7 L7M
DOI	10.1109/TVT.2022.3178146
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Technology Research Database Engineering Research Database Civil Engineering Abstracts Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Civil Engineering Abstracts Engineering Research Database Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Civil Engineering Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1939-9359
EndPage	8380
ExternalDocumentID	10_1109_TVT_2022_3178146 9782526
Genre	orig-research
GrantInformation_xml	– fundername: National Research Foundation of Korea grantid: NRF-2020R1F1A1076404 funderid: 10.13039/501100003725 – fundername: Ministry of Education(MOE, Korea)
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 5GY 5VS 6IK 97E AAIKC AAJGR AAMNW AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IAAWW IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION 7SP 8FD FR3 KR7 L7M
ID	FETCH-LOGICAL-c291t-e3cac72291b93cbbd3398013565348199a0952738ec2cfa7a1730cf4c00fb02a3
IEDL.DBID	RIE
ISICitedReferencesCount	13
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000846892800032&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9545
IngestDate	Mon Jun 30 10:18:30 EDT 2025 Tue Nov 18 21:09:36 EST 2025 Sat Nov 29 02:59:02 EST 2025 Wed Aug 27 02:23:00 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c291t-e3cac72291b93cbbd3398013565348199a0952738ec2cfa7a1730cf4c00fb02a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-0499-7253
PQID	2703132470
PQPubID	85454
PageCount	14
ParticipantIDs	crossref_citationtrail_10_1109_TVT_2022_3178146 proquest_journals_2703132470 ieee_primary_9782526 crossref_primary_10_1109_TVT_2022_3178146
PublicationCentury	2000
PublicationDate	2022-08-01
PublicationDateYYYYMMDD	2022-08-01
PublicationDate_xml	– month: 08 year: 2022 text: 2022-08-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on vehicular technology
PublicationTitleAbbrev	TVT
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref15 ref14 ref11 ref10 ref17 ref16 Bertsekas (ref49) 1996 Rasmussen (ref52) 2010; 11 ref19 ref18 Lee (ref3) 2018 Lin (ref51) 2009; 2 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref8 ref7 ref9 ref4 ref6 ref5 ref40 Bertsekas (ref37) 2005 ref35 ref34 ref36 ref31 ref30 ref33 ref32 ref2 ref39 ref38 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 Bae (ref1) 2020
References_xml	– ident: ref9 doi: 10.4271/2013-01-1470 – start-page: 559 volume-title: Proc. 20th Int. Conf. Control Automat. Syst. year: 2020 ident: ref1 article-title: Gaussian process approximate dynamic programming for energy management of parallel hybrid electric vehicles – ident: ref16 doi: 10.1109/TVT.2021.3075729 – year: 2018 ident: ref3 article-title: Charging the future: Challenges and opportunities for electric vehicle adoption doi: 10.2139/ssrn.3251551 – ident: ref8 doi: 10.1109/TITS.2021.3099812 – ident: ref38 doi: 10.1090/s0002-9904-1954-09848-8 – ident: ref41 doi: 10.1109/ACC.2008.4587201 – ident: ref48 doi: 10.1002/9781118122631 – volume: 2 start-page: 396 year: 2009 ident: ref51 article-title: A survey of approximate dynamic programming publication-title: Intell. Hum. Mach. Syst. Cybern. – ident: ref13 doi: 10.1109/TITS.2014.2319812 – ident: ref21 doi: 10.1109/ACCESS.2020.3036033 – ident: ref50 doi: 10.7551/mitpress/10187.001.0001 – ident: ref25 doi: 10.1109/ACCESS.2020.3027024 – ident: ref6 doi: 10.1109/MCS.2007.338280 – ident: ref5 doi: 10.1016/j.trd.2019.10.024 – ident: ref32 doi: 10.1109/WCICA.2008.4594156 – volume-title: Neuro-Dynamic Programming year: 1996 ident: ref49 – ident: ref17 doi: 10.1109/MCS.2015.2449688 – volume: 11 start-page: 3011 issue: 100 year: 2010 ident: ref52 article-title: Gaussian processes for machine learning (GPML) toolbox publication-title: J. Mac. Learn. Res. – ident: ref43 doi: 10.1002/9781118970553 – ident: ref47 doi: 10.1109/TITS.2014.2309674 – ident: ref35 doi: 10.3390/app8020187 – ident: ref12 doi: 10.1109/TVT.2015.2405347 – ident: ref14 doi: 10.1016/j.rser.2015.03.093 – ident: ref22 doi: 10.1016/j.jpowsour.2016.11.106 – ident: ref34 doi: 10.3390/wevj8010274 – ident: ref19 doi: 10.2516/ogst/2014006 – ident: ref27 doi: 10.1016/j.energy.2014.03.020 – ident: ref28 doi: 10.1109/TIV.2020.3011954 – ident: ref7 doi: 10.1109/ACCESS.2021.3098807 – ident: ref24 doi: 10.1016/j.apenergy.2015.12.035 – ident: ref26 doi: 10.1109/MED.2019.8798496 – ident: ref30 doi: 10.1155/2014/160510 – ident: ref44 doi: 10.1002/9781119278924.ch6 – ident: ref11 doi: 10.3390/wevj12020085 – ident: ref20 doi: 10.1109/TVT.2018.2866569 – ident: ref39 doi: 10.1002/SERIES1345 – ident: ref40 doi: 10.3182/20080706-5-KR-1001.00573 – ident: ref46 doi: 10.1109/TVT.2009.2027709 – ident: ref23 doi: 10.1016/j.apenergy.2016.08.085 – ident: ref29 doi: 10.3390/en13133352 – ident: ref2 doi: 10.1109/JPROC.2007.892489 – ident: ref42 doi: 10.1016/j.neucom.2008.12.019 – ident: ref18 doi: 10.1109/IVS.2016.7535426 – ident: ref33 doi: 10.1016/j.ifacol.2019.09.089 – ident: ref31 doi: 10.1016/j.rser.2015.09.036 – ident: ref45 doi: 10.3390/en12142750 – volume-title: Dynamic Programming and Optimal Control year: 2005 ident: ref37 – ident: ref15 doi: 10.1109/ACCESS.2019.2941399 – ident: ref10 doi: 10.1007/978-3-642-35913-2 – ident: ref36 doi: 10.1016/j.apenergy.2017.11.072 – ident: ref4 doi: 10.35833/MPCE.2018.000374
SSID	ssj0014491
Score	2.4480941
Snippet	We propose an energy-efficient supervisory control method for the power management of parallel hybrid electric vehicles (HEVs) to improve the fuel economy and...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	8367
SubjectTerms	Approximate dynamic programming Batteries Control methods Dynamic programming Electric vehicles Energy conversion efficiency Energy efficiency Energy management Engines Exhaust gases Feedback control Fuel consumption Fuel economy Gaussian process gaussian process regression Hybrid electric vehicles Mathematical models Maximum power Optimal control Parallel hybrid electric vehicles Power management Power sources Statistical analysis Supervisory control Traffic speed value function approximation Vehicle dynamics
Title	Gaussian Process Approximate Dynamic Programming for Energy-Optimal Supervisory Control of Parallel Hybrid Electric Vehicles
URI	https://ieeexplore.ieee.org/document/9782526 https://www.proquest.com/docview/2703132470
Volume	71
WOSCitedRecordID	wos000846892800032&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1939-9359 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014491 issn: 0018-9545 databaseCode: RIE dateStart: 19670101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH5M8aAHf4vTKTl4Eaxmadc0xzGnO8gUnMNbSdMEBd1kP0TBP9730m4oimBPgSZt6de8fK9533sAR0KKHHm5C-rGiQAZsQx0zHWgwoaL8EhyH-3ev5LdbnJ_r24qcDLXwlhrffCZPaWm38vPh2ZKv8ooG6xoiHgBFqSMC63WfMcgisrqeHWcwEgLZluSXJ31-j10BIVA_5QSPMXfliBfU-WHIfary8Xa_55rHVZLFsmaBewbULGDTVj5kltwCz4u9XRMCklWagFYk9KHvz0iRbXsvChET-coPOsZhzCkr6ztpYDBNRqSZ7zB7fSFbMl4OHpnrSKonQ0du9EjKsHyxDrvJPhibV9LBy_Xtw8-zG4b7i7avVYnKEstBEao-iSwodFGCmxnKjRZloehwrUrRLpHSl2lNFIxUvFYI4zTUtfRMhgXGc5dxoUOd2BxMBzYXWCJzbluNFyeo6uSCJ0h6kK62Clt84SLKpzN3n5qyjzkVA7jKfX-CFcp4pUSXmmJVxWO5yNeihwcf_TdInzm_UpoqlCbAZyWk3ScCukTV0aS7_0-ah-W6dpFvF8NFiejqT2AJfM6eRyPDv339wmFl9la
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD54A_XBuzivefBFsC5L27V5FJ1OnFNwDt9KmiYo6Ca7iII_3nPSbiiKYJ8CTdrSrzn5TnO-cwD2RSQy5OXWq2grPGTEkaeqXHnSD22AR5y5aPd2I2o24_t7eTMBh2MtjDHGBZ-ZI2q6vfysq4f0q4yywYpQVCdhOgwCwXO11njPIAiK-ngVnMJIDEabklyWW-0WuoJCoIdKKZ6q3xYhV1Xlhyl268vZ4v-ebAkWCh7JjnPgl2HCdFZg_kt2wVX4OFfDPmkkWaEGYMeUQPztEUmqYad5KXo6RwFazziEIYFlNScG9K7RlDzjDW6HL2RN-t3eOzvJw9pZ17Ib1aMiLE-s_k6SL1Zz1XTwcm3z4ALt1uDurNY6qXtFsQVPC1kZeMbXSkcC26n0dZpmvi9x9fKR8JFWV0qFZIx0PEYLbVWkKmgbtA005zblQvnrMNXpdswGsNhkXIWhzTJ0VmKhUsRdRLZqpTJZzEUJyqO3n-giEzkVxHhKnEfCZYJ4JYRXUuBVgoPxiJc8C8cffVcJn3G_ApoSbI8ATopp2k9E5FJXBhHf_H3UHszWW1eNpHHRvNyCObpPHv23DVOD3tDswIx-HTz2e7vuW_wE987coQ
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=Gaussian+Process+Approximate+Dynamic+Programming+for+Energy-Optimal+Supervisory+Control+of+Parallel+Hybrid+Electric+Vehicles&rft.jtitle=IEEE+transactions+on+vehicular+technology&rft.au=Bae%2C+Jin+Woo&rft.au=Kim%2C+Kwang-Ki+K.&rft.date=2022-08-01&rft.issn=0018-9545&rft.eissn=1939-9359&rft.volume=71&rft.issue=8&rft.spage=8367&rft.epage=8380&rft_id=info:doi/10.1109%2FTVT.2022.3178146&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TVT_2022_3178146
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9545&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9545&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9545&client=summon