计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (6): 346-354.doi: 10.11896/jsjkx.240900154

• 计算机网络 • 上一篇    下一篇

基于GMM的容器定制化调度策略

周凯, 王凯, 朱宇航, 普黎明, 刘树新, 周德强   

  1. 信息工程大学国家数字交换系统工程技术研究中心 郑州 450003
  • 收稿日期:2024-09-25 修回日期:2024-12-06 出版日期:2025-06-15 发布日期:2025-06-11
  • 通讯作者: 王凯(wangkai0508@126.com)
  • 作者简介:(zhoukai1247@126.com)
  • 基金资助:
    河南省重大科技专项(221100210700-2)

Customized Container Scheduling Strategy Based on GMM

ZHOU Kai, WANG Kai, ZHU Yuhang, PU Liming, LIU Shuxin, ZHOU Deqiang   

  1. National Digital Switching System Engineering & Technological R&D Center,Information Engineering University,Zhengzhou 450003,China
  • Received:2024-09-25 Revised:2024-12-06 Online:2025-06-15 Published:2025-06-11
  • About author:ZHOU Kai,born in 1999,postgra-duate.His main research interests include cloud computing and embedded system resource virtualization.
    WANG Kai,born in 1980,Ph.D,professor,Ph.D supervisor.His main research interests include network security go-vernance and communication network security.
  • Supported by:
    Major Science and Technology Program in Henan Province(221100210700-2).

PDF (PC)

125

摘要： 在云计算环境中,随着容器数量和类型的不断增加,资源管理和调度复杂性也增加,如何有效地调度容器,优化资源利用率和集群性能成为一个重要的研究课题。现有的容器集群调度策略没有充分考虑容器的多样化需求,缺乏灵活性,难以实现针对不同场景的容器进行定制化调度,容易出现集群资源利用率低下、集群资源负载失衡等问题。为了满足容器多样化需求,提高集群资源负载均衡性,提出了一种基于GMM(高斯混合模型)的容器定制化调度策略(Customized Container Scheduling Strategy Based on GMM,CS-GMM)。首先,根据容器的资源和属性需求进行分类,将其划分为不同的类型。其次,对于每一类容器,分别计算并分配不同的独立权重,依次将容器根据其类型调度到合适的节点,从而实现定制化调度。通过这种方式,满足了容器多样化需求,使不同类型的容器可以根据其特定需求得到最优的资源配置,避免了资源竞争和冲突,从而提高了集群资源的整体利用率和负载均衡度。实验结果表明,与Kubernetes Scheduler相比,该调度策略在多种容器调度场景下均表现出优越的性能,集群节点之间最大资源利用率差值降低17.1%,容器调度成功率提升19%,集群节点负载均衡度提升57.51%。

关键词: 云计算, 容器调度, 多样化, 定制化, 负载均衡

Abstract: In cloud computing environments,as the number and types of containers continue to increase,resource management and scheduling complexity are increased.How to effectively schedule containers and optimize resource utilization and cluster perfor-mance has become an important research topic.The existing container cluster scheduling strategies do not fully consider the diverseneeds of containers,lack flexibility,and are difficult to customize scheduling for containers in different scenarios.This can easily lead to problems such as low cluster resource utilization and imbalanced cluster resource load.In order to meet the diverse needs of containers and improve the load balancing of cluster resources,this paper proposes a customized container scheduling strategy based on GMM(Gaussian Mixture Model).Firstly,classify according to the resources and attribute requirements of the container,and divide it into different types.Secondly,for each type of container,different independent weights are calculated and assigned separately,and the containers are scheduled to appropriate nodes according to their types in turn,thereby achieving customized scheduling.In this way,the diverse needs of containers are met,so that different types of containers can get the optimal resource allocation according to their specific needs,avoiding resource competition and conflicts,thereby improving the overall utilization and load balancing of cluster resources.Experimental results show that compared with Kubernetes Scheduler,this scheduling strategy has shown superior performance in various container scheduling scenarios,with the maximum resource utilization diffe-rence between cluster nodes reduced by 17.1%,the container scheduling success rate increased by 19%,and the cluster node load balancing increased by 57.51%.

Key words: Cloud computing, Container scheduling, Diversification, Customization, Load balancing

中图分类号: 

  • TP391
[1]CARRIÓN C.Kubernetes scheduling:Taxonomy,ongoing issues and challenges[J].ACM Computing Surveys,2022,55(7):1-37.
[2]WU Y W,ZHANG Y,WANG T,et al.The Development ofContainer Technology from the Perspective of Docker Containers:A Systematic Literature Review Perspective[J].Journal of Software,2023,34(12):5527-5551.
[3]HASSAN M,CUSTODE L L,YILDIRIM K S,et al.FedEdge:Federated Learning with Docker and Kubernetes for Scalable and Efficient Edge Computing[C]//Proceedings of the 2023 International Conference on Embedded Wireless Systems and Networks.New York:ACM,2023:339-344.
[4]NICOLAESCU A C,MASTORAKIS S,PSARAS I.Store edge networked data(SEND):A data and performance driven edge storage framework[C]//IEEE INFOCOM 2021－IEEE Conference on Computer Communications.IEEE,2021:1-10.
[5]SINGHAL S,ALI S,AWASTHY M,et al.Rock-hyrax:An energy efficient job scheduling using cluster of resources in cloud computing environment[J].Sustainable Computing:Informatics and Systems,2024,42:100985.
[6]KATAL A,CHOUDHURY T,DAHIYA S.Energy optimizedcontainer placement for cloud data centers:a meta-heuristic approach[J].The Journal of Supercomputing,2024,80(1):98-140.
[7]CHEN X,XIAO S.Multi-objective and parallel particle swarm optimization algorithm for container-based microservice scheduling[J].Sensors,2021,21(18):6212.
[8]LIU B,LI J,LIN W,et al.K-PSO:An improved PSO-based container scheduling algorithm for big data applications[J].International Journal of Network Management,2021,31(2):e2092.
[9]BOUVEYRON C,BRUNET-SAUMARD C.Model-based clustering of high-dimensional data:A review[J].Computational Statistics & Data Analysis,2014,71:52-78.
[10]WANG Z,WANG P H,WANG B C,et al.GPU Shared Scheduling System Under Deep Learning Container Cloud Platform[J].Computer Science,2023,50(6):86-91.
[11]SINGH N,HAMID Y,JUNEJA S,et al.Load balancing andservice discovery using Docker Swarm for microservice based big data applications[J].Journal of Cloud Computing,2023,12(1):4.
[12]MUNISWAMY S,VIGNESH R.Joint optimization of load balancing and resource allocation in cloud environment using optimal container management strategy[J].Concurrency and Computation:Practice and Experience,2021,124:253-262.
[13]AL RESHAN M S,SYED D,ISLAM N,et al.A fast converging and globally optimized approach for load balancing in cloud computing[J].IEEE Access,2023,11:11390-11404.
[14]ZHU L,HUANG K,FU K,et al.A priority-aware scheduling framework for heterogeneous workloads in container-based cloud[J].Applied Intelligence,2023,53(12):15222-15245.
[15]XIAO Z,LIU K,HU M,et al.DeepCTS:A Deep Reinforcement Learning Approach for AI Container Task Scheduling[C]//Proceedings of the 2024 3rd Asia Conference on Algorithms,Computing and Machine Learning.ACM,2024:342-347.
[16]MAO Y,FU Y,ZHENG W,et al.Speculative container scheduling for deep learning applications in a kubernetes cluster[J].IEEE Systems Journal,2021,16(3):3770-3781.
[17]XIE Y S,HUANG X H,CHEN N J.Self-balanced Scheduling Strategy for Container Cluster Based on Improved DQN Algorithm[J].Computer Science,2023,50(4):233-240.
[18]CHEN Y,HE S,JIN X,et al.Resource utilization and cost optimization oriented container placement for edge computing in industrial internet[J].The Journal of Supercomputing,2023,79(4):3821-3849.
[19]MOHAMMADZADEH A,MASDARI M,GHAREHCHO-POGH F S.Energy and cost-aware workflow scheduling in cloud computing data centers using a multi-objective optimization algorithm[J].Journal of Network and Systems Management,2021,29(3):31.
[20]LIU R,YANG P,LYU H,et al.Multi-objective multi-factorial evolutionary algorithm for container placement[J].IEEE Transactions on Cloud Computing,2021,11(2):1430-1445.
[21]ZHANG W,CHEN L,LUO J,et al.A two-stage container management in the cloud for optimizing the load balancing and migration cost[J].Future Generation Computer Systems,2022,135:303-314.
[22]SHEGANAKU G,SCHULTE S,WAIBEL P,et al.Cost-effi-cient auto-scaling of container-based elastic processes[J].Future Generation Computer Systems,2023,138:296-312.
[23]AGGARWAL A,DIMRI P,AGARWAL A,et al.Self adaptive fruit fly algorithm for multiple workflow scheduling in cloud computing environment[J].Kybernetes,2021,50(6):1704-1730.
[24]SONG Y,LIANG W F,ZHAO J,et al.Cloud Resource Scheduling Performance of Water Wave Optimization Algorithm Improved by Artificial Bee Colony Algorithm[J].Journal of University of Jinan(Science and Technology),2023,37(4):472-477.
[25]YAN J,HUANG Y,GUPTA A,et al.Energy-aware systems for real-time job scheduling in cloud data centers:A deep reinforcement learning approach[J].Computers and Electrical Engineering,2022,99:107688.
[26]DENG L,WANG Z,SUN H,et al.A deep reinforcement learning-based optimization method for long-running applications container deployment[J].International Journal of Computers Communications & Control,2023,18(4):108-125.
[27]TANG Z,LOU J,JIA W.Layer dependency-aware learningscheduling algorithms for containers in mobile edge computing[J].IEEE Transactions on Mobile Computing,2022,22(6):3444-3459.
[28]AHMED M,SERAJ R,ISLAM S M S.The k-means algorithm:A comprehensive survey and performance evaluation[J].Electronics,2020,9(8):1295.
[29]DO C B,BATZOGLOU S.What is the expectation maximization algorithm?[J].Nature Biotechnology,2008,26(8):897-899.
[30]WAN H,WANG H,SCOTNEY B,et al.A novel gaussian mixture model for classification[C]//2019 IEEE International Conference on Systems,Man and Cybernetics(SMC).IEEE,2019:3298-3303.
[31]LAI W K,WANG Y C,WEI S C.Delay-aware container scheduling in kubernetes[J].IEEE Internet of Things Journal,2023,10(13):11813-11824.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发