DDRM: An SLO-aware Deep Dynamic Resource Management Framework for Microservices

Loosely coupled microservice architectures have been widely adopted in cloud-native applications due to their inherent advantages in modularity, development agility, and scalability. However, the resulting complex and dynamic service topologies introduce intricate inter-service dependencies, which o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / IEEE International Conference on Cluster Computing S. 1 - 12
Hauptverfasser: Tang, Liangping, Wang, Jin, Wang, Wanyou, Shi, Gaotao, Li, Zhijun
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 02.09.2025
Schlagworte:
ISSN:2168-9253
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Loosely coupled microservice architectures have been widely adopted in cloud-native applications due to their inherent advantages in modularity, development agility, and scalability. However, the resulting complex and dynamic service topologies introduce intricate inter-service dependencies, which often lead to backpressure effects and queuing delays. These phenomena significantly challenge traditional monolithic and rule-based resource management approaches, which struggle to capture the non-linear performance characteristics and long-term effects of resource allocation decisions in such environments. To address these challenges, we propose DDRM, a two-stage predictor-decider collaborative framework for dynamic resource management in microservice systems. DDRM integrates deep learning to model inter-service interactions and predict the probability of Service Level Objective (SLO) violations, and employs reinforcement learning to optimize resource allocation decisions by maximizing long-term cumulative rewards while meeting SLO targets. Extensive evaluations demonstrate that DDRM outperforms state-of-the-art baselines by up to 29.8 %, while exhibiting strong stability and adaptability under highly varying workloads.
AbstractList Loosely coupled microservice architectures have been widely adopted in cloud-native applications due to their inherent advantages in modularity, development agility, and scalability. However, the resulting complex and dynamic service topologies introduce intricate inter-service dependencies, which often lead to backpressure effects and queuing delays. These phenomena significantly challenge traditional monolithic and rule-based resource management approaches, which struggle to capture the non-linear performance characteristics and long-term effects of resource allocation decisions in such environments. To address these challenges, we propose DDRM, a two-stage predictor-decider collaborative framework for dynamic resource management in microservice systems. DDRM integrates deep learning to model inter-service interactions and predict the probability of Service Level Objective (SLO) violations, and employs reinforcement learning to optimize resource allocation decisions by maximizing long-term cumulative rewards while meeting SLO targets. Extensive evaluations demonstrate that DDRM outperforms state-of-the-art baselines by up to 29.8 %, while exhibiting strong stability and adaptability under highly varying workloads.
Author Li, Zhijun
Wang, Jin
Wang, Wanyou
Tang, Liangping
Shi, Gaotao
Author_xml – sequence: 1
  givenname: Liangping
  surname: Tang
  fullname: Tang, Liangping
  email: lptang@stu.suda.edu.cn
  organization: School of Future Science and Engineering,NEIC Laboratory, Soochow University,Soochow,China
– sequence: 2
  givenname: Jin
  surname: Wang
  fullname: Wang, Jin
  email: wjin1985@suda.edu.cn
  organization: School of Future Science and Engineering,NEIC Laboratory, Soochow University,Soochow,China
– sequence: 3
  givenname: Wanyou
  surname: Wang
  fullname: Wang, Wanyou
  email: wangwanyou@stu.hit.edu.cn
  organization: Harbin Institute of Technology,Faculty of Computing,Harbin,China
– sequence: 4
  givenname: Gaotao
  surname: Shi
  fullname: Shi, Gaotao
  email: shgt@tju.edu.cn
  organization: College of Intelligence and Computing, Tianjin University,Tianjin,China
– sequence: 5
  givenname: Zhijun
  surname: Li
  fullname: Li, Zhijun
  email: lizhijun_os@hit.edu.cn
  organization: Harbin Institute of Technology,Faculty of Computing,Harbin,China
BookMark eNo1j81Kw0AURkdRsK19AxeD-9R7ZyY_4640rQoJgbSuy8z0jkRNUibV0re3oK6-w1kc-Mbsqus7YuweYYYI-mFRvK43yzrWUomZABGfNWaJSsUFm-pUZ1JiLAF1dslGApMs0iKWN2w8DO8AMpWQjFiV53X5yOcdXxdVZI4mEM-J9jw_daZtHK9p6L-CI16azrxRS92Br4Jp6diHD-77wMvGhX6g8N04Gm7ZtTefA03_dsI2q-Vm8RwV1dPLYl5EjZaHyLp4t7PKCgEKTIJgNWYKSdozOJ9aVE54FNIBOUUEJpPKg0_EzsQWvZywu99sQ0TbfWhaE07b___yB6iOUj8
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CLUSTER59342.2025.11186472
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9798331530198
EISSN 2168-9253
EndPage 12
ExternalDocumentID 11186472
Genre orig-research
GrantInformation_xml – fundername: National Key R&D Program of China
  grantid: 2023YFB4503100
  funderid: 10.13039/501100012166
– fundername: National Natural Science Foundation of China
  grantid: 62072321
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i93t-bc5ddb4b22040a610b91841e3bb91cf7b14c2f123c0ec4ee0a834f0f62da5b1f3
IEDL.DBID RIE
IngestDate Wed Nov 05 07:06:02 EST 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-bc5ddb4b22040a610b91841e3bb91cf7b14c2f123c0ec4ee0a834f0f62da5b1f3
PageCount 12
ParticipantIDs ieee_primary_11186472
PublicationCentury 2000
PublicationDate 2025-Sept.-2
PublicationDateYYYYMMDD 2025-09-02
PublicationDate_xml – month: 09
  year: 2025
  text: 2025-Sept.-2
  day: 02
PublicationDecade 2020
PublicationTitle Proceedings / IEEE International Conference on Cluster Computing
PublicationTitleAbbrev CLUSTER
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0037306
Score 2.3022075
Snippet Loosely coupled microservice architectures have been widely adopted in cloud-native applications due to their inherent advantages in modularity, development...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Adaptation models
Cloud computing
Collaboration
Deep learning
deep learning for systems
Dynamic scheduling
Microservice architectures
microservices
resource efficiency
resource man-agement
Resource management
Scalability
Stability analysis
Thermal stability
Title DDRM: An SLO-aware Deep Dynamic Resource Management Framework for Microservices
URI https://ieeexplore.ieee.org/document/11186472
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05b8MgGEVN1KFTeqTqLYauJDYGY3er4kYdcqlJpWwRx4eUxYlytH-_QOxWHTp0QQjJEgJ_B_De9xB6NCoz1ghNaCqAMO4a6Y4pBEQUW6kUZ1oGsQkxGmXzeT6pyOqBCwMAAXwGHd8Nb_lmpff-qqzr7DLz5c4bqCFEeiBr1W43cb9qWlUVjaO82xu8T11CyPOEeb4V5Z366186KiGM9Fv_nMApav8Q8vDkO9ScoSMoz1GrVmTAlYFeoHFRvA2f8HOJp4MxkZ9yA7gAWOPiIDyP69t6_AN7wf0an4VdAouHHqG3rTxIG836L7PeK6kkE8gyT3ZEaW6MYopSZ5vSZUYqdye4GBLlOtoKFTNNrQtWOgLNACKZJcxGNqVGchXb5BI1y1UJVwjzPAapnPNjLsjrVCspEyGZMS4jsYaba9T267NYH4piLOqluflj_Bad-F0I8Cx6h5q7zR7u0bH-2C23m4ewlV8UE6DP
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFH6CggRTOYq48cCaNnHsHGyooSoiPUSL1K3y8Sx1Sase8Pdx0oSKgYHFsixFsuy8w_b3vQ_gUctIGx0qhwYhOozbRthjioOh6xkhJWdKFGITYb8fTSbxsCSrF1wYRCzAZ9jMu8Vbvp6rTX5V1rJ2GeXlzvfhgDNG3S1dq3K8vv1Zg7KuqOfGrXb6MbIpIY99ljOuKG9W3_9SUikCSaf-zymcQGNHySPDn2BzCnuYnUG90mQgpYmewyBJ3ntP5Dkjo3TgiC-xRJIgLkiylZ4n1X092QFfSKdCaBGbwpJejtFblT6kAePOy7jddUrRBGcW-2tHKq61ZJJSa53C5kYytmc4D31pO8qE0mOKGhuulIuKIboi8plxTUC14NIz_gXUsnmGl0B47KGQ1v0xG-ZVoKQQfiiY1jYnMZrrK2jk6zNdbMtiTKuluf5j_AGOuuNeOk1f-283cJzvSAHWordQWy83eAeH6nM9Wy3vi239BqC8pBY
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+%2F+IEEE+International+Conference+on+Cluster+Computing&rft.atitle=DDRM%3A+An+SLO-aware+Deep+Dynamic+Resource+Management+Framework+for+Microservices&rft.au=Tang%2C+Liangping&rft.au=Wang%2C+Jin&rft.au=Wang%2C+Wanyou&rft.au=Shi%2C+Gaotao&rft.date=2025-09-02&rft.pub=IEEE&rft.eissn=2168-9253&rft.spage=1&rft.epage=12&rft_id=info:doi/10.1109%2FCLUSTER59342.2025.11186472&rft.externalDocID=11186472