Learning-Aided Evolutionary Algorithm for Solving Energy-Minimized Deadline-Constrained Task Scheduling Problem in Human-Cyber-Physical Systems
This work addresses an energy-minimized deadline-constrained task scheduling problem in human-cyber-physical systems. It consists of three subproblems: processor allocation, task sequencing, and processor frequency scaling. A Learning-aided Evolutionary Algorithm (LEA) is proposed to efficiently fin...
Uložené v:
| Vydané v: | IEEE transactions on automation science and engineering Ročník 22; s. 22729 - 22741 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
IEEE
2025
|
| Predmet: | |
| ISSN: | 1545-5955, 1558-3783 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | This work addresses an energy-minimized deadline-constrained task scheduling problem in human-cyber-physical systems. It consists of three subproblems: processor allocation, task sequencing, and processor frequency scaling. A Learning-aided Evolutionary Algorithm (LEA) is proposed to efficiently find its reliable and high-quality solutions. It incorporates a bidirectional long short-term memory network-embedded autoencoder trained via end-to-end self-supervised learning. The model extracts the interconnections among the three strongly-coupled subproblems, enabling effective global search in a low-dimensional feature space. A parallel framework with two co-evolved subpopulations, one using the autoencoder and another undergoing regular evaluation in the original search space, is constructed. To balance LEA's exploration and exploitation, a deep reinforcement learning-based search operator selection scheme is introduced, using a novel feedback-based reward function to guide operator selection for each subpopulation. Numerical experiments demonstrate that LEA surpasses several recently developed methods in finding high-quality schedules in a reasonable time. Note to Practitioners-In a human-cyber-physical system, heuristics are commonly used to solve task scheduling problems. However, fast dispatching rules tend to perform poorly. Evolutionary algorithms can identify relatively high-quality schedules but are highly time-consuming, especially for population-based methods that iteratively evaluate fitness functions. To balance computational burden and solution quality, our idea is to combine two machine learning methods with evolutionary algorithms. First, a self-supervised autoencoder enhances global search capability by reducing the complexity of the search space. Second, a deep reinforcement learning-based operator selection scheme balances exploration and exploitation. This hybrid approach enables engineers to find high-quality schedules for the considered problems in a short time. Theoretical analysis and experimental results demonstrate that our proposed method outperforms its competitive peers. |
|---|---|
| AbstractList | This work addresses an energy-minimized deadline-constrained task scheduling problem in human-cyber-physical systems. It consists of three subproblems: processor allocation, task sequencing, and processor frequency scaling. A Learning-aided Evolutionary Algorithm (LEA) is proposed to efficiently find its reliable and high-quality solutions. It incorporates a bidirectional long short-term memory network-embedded autoencoder trained via end-to-end self-supervised learning. The model extracts the interconnections among the three strongly-coupled subproblems, enabling effective global search in a low-dimensional feature space. A parallel framework with two co-evolved subpopulations, one using the autoencoder and another undergoing regular evaluation in the original search space, is constructed. To balance LEA's exploration and exploitation, a deep reinforcement learning-based search operator selection scheme is introduced, using a novel feedback-based reward function to guide operator selection for each subpopulation. Numerical experiments demonstrate that LEA surpasses several recently developed methods in finding high-quality schedules in a reasonable time. Note to Practitioners-In a human-cyber-physical system, heuristics are commonly used to solve task scheduling problems. However, fast dispatching rules tend to perform poorly. Evolutionary algorithms can identify relatively high-quality schedules but are highly time-consuming, especially for population-based methods that iteratively evaluate fitness functions. To balance computational burden and solution quality, our idea is to combine two machine learning methods with evolutionary algorithms. First, a self-supervised autoencoder enhances global search capability by reducing the complexity of the search space. Second, a deep reinforcement learning-based operator selection scheme balances exploration and exploitation. This hybrid approach enables engineers to find high-quality schedules for the considered problems in a short time. Theoretical analysis and experimental results demonstrate that our proposed method outperforms its competitive peers. |
| Author | Lin, ChengRan Cao, ZhengCai Zhou, HaoRan |
| Author_xml | – sequence: 1 givenname: ZhengCai orcidid: 0000-0003-0344-0207 surname: Cao fullname: Cao, ZhengCai email: giftczc@163.com organization: College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China – sequence: 2 givenname: HaoRan orcidid: 0009-0003-2869-7794 surname: Zhou fullname: Zhou, HaoRan email: zhr530629@163.com organization: College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China – sequence: 3 givenname: ChengRan orcidid: 0000-0001-9924-4408 surname: Lin fullname: Lin, ChengRan email: chranlin@163.com organization: State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China |
| BookMark | eNpFkN1OwjAYhhuDiYBegIkHvYFif-hYDwmimGAkAY-Xbv0G1a017SCZN-EtuwUSj7734H3e5HtGaOC8A4TuGZ0wRtXjbr5dTjjlciISxhIur9CQSZkSMUvFoM9TSaSS8gaNYvyklE9TRYfodw06OOv2ZG4NGLw8-erYWO90aPG82vtgm0ONSx_w1lenroiXDsK-JW_W2dr-dMwTaFNZB2ThXWyC7qLBOx2_8LY4gDlWPbUJPq-gxtbh1bHWjizaHALZHNpoC13hbRsbqOMtui51FeHucsfo43m5W6zI-v3ldTFfk4Jz2pCZKRnkCTWgytSoaQEyF1AWJmGJ5rmacapTECmnUjKm0kIzmZQmV32QTIkxYufdIvgYA5TZd7B193TGaNYbzXqjWW80uxjtmIczYwHgv8_YTHCRij9FfXe1 |
| CODEN | ITASC7 |
| Cites_doi | 10.1109/TASE.2021.3129439 10.1109/TSMC.2024.3352522 10.1109/MRA.2023.3265515 10.23919/CSMS.2021.0027 10.1109/TCC.2018.2889482 10.1109/TASE.2020.3047924 10.1109/TNN.2004.842673 10.1109/TASE.2024.3360476 10.1109/tevc.2024.3415368 10.1109/TIE.2021.3135629 10.1109/ICNSC48988.2020.9238110 10.1109/TCYB.2022.3222101 10.1109/TASE.2020.3042409 10.1109/TMM.2020.3047552 10.1109/TASE.2022.3178126 10.1109/TASE.2020.2978917 10.1002/spe.2876 10.1109/TEVC.2021.3113923 10.1109/TPDS.2017.2730876 10.1007/s12599-019-00590-7 10.1109/TIM.2022.3152856 10.1109/TEVC.2013.2248012 10.1109/JAS.2022.105425 10.1109/TASE.2023.3267714 10.1109/TSMC.2022.3195239 10.1109/tevc.2023.3278132 10.1109/71.993206 10.1109/TASE.2019.2909866 10.1109/TCYB.2021.3065340 10.1109/TASE.2018.2862380 10.1109/TCSS.2020.3029569 10.1109/TASE.2019.2945717 10.1109/TMECH.2020.2996911 10.1109/ACCESS.2021.3058328 10.1109/MWC.01.1900543 10.1109/TEVC.2022.3232776 10.1109/TASE.2019.2953669 10.1016/j.jii.2019.08.002 10.1109/TASE.2025.3562191 10.1007/s40747-021-00288-y 10.1109/TEVC.2022.3194349 10.1038/s41551-020-00635-3 10.1109/TASE.2020.3046673 10.1109/TASE.2024.3486919 10.1109/TASE.2022.3200073 10.1109/TCYB.2024.3413054 10.1109/TASE.2024.3477982 10.1016/j.ejor.2015.06.023 10.1109/TCYB.2022.3210228 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION |
| DOI | 10.1109/TASE.2025.3611625 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) Online IEEE Electronic Library (IEL) CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-3783 |
| EndPage | 22741 |
| ExternalDocumentID | 10_1109_TASE_2025_3611625 11173238 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China; Joint Funds of the National Natural Science Foundation of China grantid: 62561160096 funderid: 10.13039/501100001809 – fundername: National Natural Science Foundation of China grantid: 52175002; 52305523 funderid: 10.13039/501100001809 – fundername: Beijing Natural Science Foundation grantid: L243017 – fundername: Aeronautical Science Foundation of China grantid: 2024M071077001 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION |
| ID | FETCH-LOGICAL-c220t-7df1eb60de9f8d94ce5b3efcd616a2b9720a8e3820551198ca156fdb9ca155193 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001605059200009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1545-5955 |
| IngestDate | Sat Nov 29 06:58:13 EST 2025 Wed Nov 19 08:27:07 EST 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| 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-c220t-7df1eb60de9f8d94ce5b3efcd616a2b9720a8e3820551198ca156fdb9ca155193 |
| ORCID | 0000-0003-0344-0207 0009-0003-2869-7794 0000-0001-9924-4408 |
| PageCount | 13 |
| ParticipantIDs | ieee_primary_11173238 crossref_primary_10_1109_TASE_2025_3611625 |
| PublicationCentury | 2000 |
| PublicationDate | 20250000 2025-00-00 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – year: 2025 text: 20250000 |
| PublicationDecade | 2020 |
| PublicationTitle | IEEE transactions on automation science and engineering |
| PublicationTitleAbbrev | TASE |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref13 ref12 ref15 ref14 ref11 ref10 ref17 ref16 ref19 ref18 ref50 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 Srivastava (ref46); 37 ref27 ref29 |
| References_xml | – ident: ref49 doi: 10.1109/TASE.2021.3129439 – ident: ref38 doi: 10.1109/TSMC.2024.3352522 – volume: 37 start-page: 843 volume-title: Proc. 32nd Int. Conf. Int. Conf. Mach. Learn. ident: ref46 article-title: Unsupervised learning of video representations using LSTMs – ident: ref43 doi: 10.1109/MRA.2023.3265515 – ident: ref14 doi: 10.23919/CSMS.2021.0027 – ident: ref32 doi: 10.1109/TCC.2018.2889482 – ident: ref19 doi: 10.1109/TASE.2020.3047924 – ident: ref47 doi: 10.1109/TNN.2004.842673 – ident: ref3 doi: 10.1109/TASE.2024.3360476 – ident: ref35 doi: 10.1109/tevc.2024.3415368 – ident: ref24 doi: 10.1109/TIE.2021.3135629 – ident: ref1 doi: 10.1109/ICNSC48988.2020.9238110 – ident: ref34 doi: 10.1109/TCYB.2022.3222101 – ident: ref10 doi: 10.1109/TASE.2020.3042409 – ident: ref22 doi: 10.1109/TMM.2020.3047552 – ident: ref18 doi: 10.1109/TASE.2022.3178126 – ident: ref5 doi: 10.1109/TASE.2020.2978917 – ident: ref23 doi: 10.1002/spe.2876 – ident: ref26 doi: 10.1109/TEVC.2021.3113923 – ident: ref30 doi: 10.1109/TPDS.2017.2730876 – ident: ref48 doi: 10.1007/s12599-019-00590-7 – ident: ref44 doi: 10.1109/TIM.2022.3152856 – ident: ref21 doi: 10.1109/TEVC.2013.2248012 – ident: ref25 doi: 10.1109/JAS.2022.105425 – ident: ref6 doi: 10.1109/TASE.2023.3267714 – ident: ref9 doi: 10.1109/TSMC.2022.3195239 – ident: ref12 doi: 10.1109/tevc.2023.3278132 – ident: ref29 doi: 10.1109/71.993206 – ident: ref33 doi: 10.1109/TASE.2019.2909866 – ident: ref13 doi: 10.1109/TCYB.2021.3065340 – ident: ref39 doi: 10.1109/TASE.2018.2862380 – ident: ref2 doi: 10.1109/TCSS.2020.3029569 – ident: ref41 doi: 10.1109/TASE.2019.2945717 – ident: ref17 doi: 10.1109/TMECH.2020.2996911 – ident: ref16 doi: 10.1109/ACCESS.2021.3058328 – ident: ref4 doi: 10.1109/MWC.01.1900543 – ident: ref28 doi: 10.1109/TEVC.2022.3232776 – ident: ref8 doi: 10.1109/TASE.2019.2953669 – ident: ref15 doi: 10.1016/j.jii.2019.08.002 – ident: ref36 doi: 10.1109/TASE.2025.3562191 – ident: ref42 doi: 10.1007/s40747-021-00288-y – ident: ref11 doi: 10.1109/TEVC.2022.3194349 – ident: ref20 doi: 10.1038/s41551-020-00635-3 – ident: ref31 doi: 10.1109/TASE.2020.3046673 – ident: ref37 doi: 10.1109/TASE.2024.3486919 – ident: ref45 doi: 10.1109/TASE.2022.3200073 – ident: ref27 doi: 10.1109/TCYB.2024.3413054 – ident: ref40 doi: 10.1109/TASE.2024.3477982 – ident: ref7 doi: 10.1016/j.ejor.2015.06.023 – ident: ref50 doi: 10.1109/TCYB.2022.3210228 |
| SSID | ssj0024890 |
| Score | 2.3892753 |
| Snippet | This work addresses an energy-minimized deadline-constrained task scheduling problem in human-cyber-physical systems. It consists of three subproblems:... |
| SourceID | crossref ieee |
| SourceType | Index Database Publisher |
| StartPage | 22729 |
| SubjectTerms | autoencoder Autoencoders evolutionary algorithm Evolutionary computation human-cyber-physical systems Job shop scheduling Machine learning Optimization Processor scheduling Radio spectrum management Resource management Schedules Sequential analysis Task scheduling |
| Title | Learning-Aided Evolutionary Algorithm for Solving Energy-Minimized Deadline-Constrained Task Scheduling Problem in Human-Cyber-Physical Systems |
| URI | https://ieeexplore.ieee.org/document/11173238 |
| Volume | 22 |
| WOSCitedRecordID | wos001605059200009&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: 1558-3783 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024890 issn: 1545-5955 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8QwEA0qHvTgt_hNDp6EaJs2bXJcdMWDysKu4q0kzWQtrl2p68L6J_zLJmnEvXjwFkICJS9l3sxk5iF0qlJOhTWtRKaGWQdFCMKt3SM0VsYkiRTMV3g_3ub39_zpSfRCsbqvhQEA__gMzt3Q5_L1uPxwobIL-1_mibUxi2gxz7O2WOu3sR73ARVHCQgTjIUUZhyJi0Gn37WuIGXnSRbHmZPFnjNCc6oq3qhcr__zczbQWmCPuNPCvYkWoN5Cq3M9BbfRV-iYOiSdSoPG3Wm4XLKZ4c5oOG6qyfMrtlwV98cjF07AXV__R-6qunqtPu2eKwu8o5_EyXl6EQk7OZDvL7hvMdbu8foQ91opGlzV2GcCyOVMQUN6AXgceqHvoIfr7uDyhgTVBVJSGk1Irk0MKos0CMO1SEtgKgFT6izOJFUip5HkkFjmwFwOkpfSuoBGK-EGjg_uoqV6XMMewjRJDE9VZnIOqY6YzGJJBaSxlCovOeyjsx8Yire2uUbhnZJIFA6zwmFWBMz20Y6D4HdhOP2DP-YP0Yrb3oZLjtDSpPmAY7RcTifVe3Pi7843GVLEOw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-MwELZ4SSwHWF7ivT5wQjIkTpzYxwqKQJSqUrsrbpEdj0sEpKtQkNg_wV9e2zGiFw7cLCuxrHyO5psZz3wIHauUU2FNK5GpYdZBEYJwa_cIjZUxSSIF8xXef3p5v8_v7sQgFKv7WhgA8JfP4NQNfS5fT8oXFyo7s_9lnlgbM48WWZrSqC3X-mytx31IxZECwgRjIYkZR-Js1Bl2rTNI2WmSxXHmhLFnzNCMroo3K5dr39zQT7Qa-CPutICvozmoN9DKTFfBTfQeeqaOSafSoHH3NRwv2bzhzuN40lTT-yds2SoeTh5dQAF3fQUgua3q6qn6Z9-5sNA7AkqcoKeXkbCTI_n8gIcWZe2ur4_xoBWjwVWNfS6AnL8paMggQI9DN_Qt9PuyOzq_IkF3gZSURlOSaxODyiINwnAt0hKYSsCUOoszSZXIaSQ5JJY7MJeF5KW0TqDRSriBY4TbaKGe1LCDME0Sw1OVmZxDqiMms1hSAWkspcpLDrvo5AOG4m_bXqPwbkkkCodZ4TArAma7aMtB8Plg-Pp7X8z_QstXo9te0bvu3-yjH26pNnhygBamzQscoqXydVo9N0f-HP0HdWDHgg |
| 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=Learning-Aided+Evolutionary+Algorithm+for+Solving+Energy-Minimized+Deadline-Constrained+Task+Scheduling+Problem+in+Human-Cyber-Physical+Systems&rft.jtitle=IEEE+transactions+on+automation+science+and+engineering&rft.au=Cao%2C+ZhengCai&rft.au=Zhou%2C+HaoRan&rft.au=Lin%2C+ChengRan&rft.date=2025&rft.pub=IEEE&rft.issn=1545-5955&rft.volume=22&rft.spage=22729&rft.epage=22741&rft_id=info:doi/10.1109%2FTASE.2025.3611625&rft.externalDocID=11173238 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5955&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5955&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5955&client=summon |