计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (2): 291-298.doi: 10.11896/jsjkx.241000027

• 计算机网络 • 上一篇    下一篇

基于数据流分割和能耗感知的异构服务器系统任务调度

杨晨1, 肖晶2, 王密3   

  1. 1 武汉大学国家网络安全学院空天信息安全与可信计算教育部重点实验室 武汉 430072
    2 武汉大学计算机学院 武汉 430072
    3 武汉大学测绘遥感信息工程国家重点实验室 武汉 430072
  • 收稿日期:2024-10-08 修回日期:2024-12-03 出版日期:2025-02-15 发布日期:2025-02-17
  • 通讯作者: 王密(wangmi@whu.edu.cn)
  • 作者简介:(2020202210004@whu.edu.cn)
  • 基金资助:
    国家重点研发计划(2022YFB3902804)

Task Scheduling in Heterogeneous Server Systems Based on Data Splitting and Energy-aware Strategies

YANG Chen1, XIAO Jing2, WANG Mi3   

  1. 1 Key Laboratory of Aerospace Information Security,Trusted Computing,Ministry of Education,School of Cyber Science,Engineering,Wuhan University,Wuhan 430072,China
    2 School of Computer Science,Wuhan University,Wuhan 430072,China
    3 State Key Laboratory of Surveying,Mapping and Remote Sensing Information Engineering,Wuhan University,Wuhan 430072,China
  • Received:2024-10-08 Revised:2024-12-03 Online:2025-02-15 Published:2025-02-17
  • About author:YANG Chen,born in 1998,postgra-duate.His main research interests include edge computing and task scheduling.
    WANG Mi,born in 1974,Ph.D,professor,Ph.D supervisor,recipient of the National Science Fund for Distinguish Young Scholars.His main research interests include high-precision remote-sensing image processing and so on.
  • Supported by:
    National Key Research and Development Program of China(2022YFB3902804).

PDF (PC)

106

摘要： 异构服务器平台为大型系统提供了强大的计算能力,但也带来了系统复杂性和能耗管理方面的挑战。针对异构服务器系统中的依赖任务,深入探讨了基于数据流分割的能耗感知调度问题。首先,对系统环境、依赖任务及数据流传输模式进行了建模,并将能耗感知调度问题表述为一个约束优化问题,以最小化任务的调度完成时间。随后,提出了一种基于数据流分割和任务优先级策略的能耗感知调度算法DSEA。该算法通过优化数据流分割策略、任务优先级和基于权重的能耗分配,为每个任务寻找近似最优的启动时间和服务器分配方案。为了验证所提方法的有效性,从阿里巴巴集群数据集中随机选取了1000个不同长度范围的作业进行仿真实验。实验结果表明,DSEA算法在不同应用场景下较3种现有算法表现出显著的性能优势。

关键词: 异构服务器, 能耗感知, 数据流分割, 依赖任务调度, 任务优先级

Abstract: Heterogeneous server platforms provide powerful computing capabilities for large systems but also pose challenges in system complexity and energy consumption management.This study delves into the energy-aware scheduling problem based on data splitting for dependent tasks in heterogeneous server systems.First,the system environment,dependent tasks,and data transmission patterns are modeled,and the energy-aware scheduling problem is formulated as a constrained optimization problem aimed at minimizing the completion time of task scheduling.Subsequently,an energy-aware scheduling algorithm(DSEA)based on data splitting and task prioritization strategies is proposed.This algorithm seeks approximate optimal startup times and server allocation plans for each task by optimizing data splitting strategies,task priorities,and weight-based energy allocation.To validate the effectiveness of the proposed method,1 000 jobs of varying lengths are randomly selected from the Alibaba cluster dataset for simulation experiments.Experimental results demonstrate that the DSEA algorithm exhibits significant performance advantages over three existing algorithms in various application scenarios.

Key words: Heterogeneous servers, Energy-aware, Data splitting, Dependent task scheduling, Task prioritization

中图分类号: 

  • TP311
[1]ANDRAE A S G.New perspectives on internet electricity use in 2030[J].Engineering and Applied Science Letter,2020,3(2):19-31.
[2]SAHNI J,VIDYARTHI D P.A cost-effective deadline-con-strained dynamic scheduling algorithm for scientific workflows in a cloud environment[J].IEEE Transactions on Cloud Computing,2015,6(1):2-18.
[3]LI C,CHEN L.Optimization for energy-aware design of taskscheduling in heterogeneous distributed systems:a meta-heuristic based approach[J].Computing,2024,106(6):2007-2031.
[4]WANG Z,WANG H,SONG X,et al.Communication-aware energy consumption model in heterogeneous computing systems[J].The Computer Journal,2024,67(1):78-94.
[5]ZHANG P,LI Z,GUIZANI M,et al.Energy Aware Space-Air-Ground Integrated Network Resource Orchestration Algorithm[J/OL].https://ieeexplore.ieee.org/document/10631705.
[6]DAS A,GHOSH S K,RAHA A,et al.Towards Energy-Efficient Collaborative Inference Using Multi-System Approximations[J].IEEE Internet of Things Journal,2024,11(10):17989-18004.
[7]NOORIANTALOUKI R,SHIRVANI M H,MOTAMENI H.A heuristic-based task scheduling algorithm for scientific workflows in heterogeneous cloud computing platforms[J].Journal of King Saud University-Computer and Information Sciences,2022,34(8):4902-4913.
[8]GUPTA P,SAHOO P K,VEERAVALLI B.Dynamic fault to-lerant scheduling with response time minimization for multiple failures in cloud[J].Journal of Parallel and Distributed Computing,2021,158:80-93.
[9]ABUALIGAH L,HUSSEIN A M A,ALMOMANI M H,et al.Improved Jaya Synergistic Swarm Optimization Algorithm to Optimize Task Scheduling Problems in Cloud Computing[J].Sustainable Computing:Informatics and Systems,2024,43:101012.
[10]FU X,SUN Y,WANG H,et al.Task scheduling of cloud computing based on hybrid particle swarm algorithm and genetic algorithm[J].Cluster Computing,2023,26(5):2479-2488.
[11]WU H,SHEN W,LIN W,et al.End-Edge-Cloud Heterogeneous Resources Scheduling Method Based on RNN and Particle Swarm Optimization[J/OL].https://ieeexplore.ieee.org/document/10769501.
[12]ZHANG Y W.DVFS-based energy-aware scheduling of imprecise mixed-criticality real-time tasks[J].Journal of Systems Architecture,2023,137:102849.
[13]DENG S,ZHAO H,XIANG Z,et al.Dependent function embedding for distributed serverless edge computing[J].IEEE Tran-sactions on Parallel and Distributed Systems,2021,33(10):2346-2357.
[14]CHEN J,HE Y,ZHANG Y,et al.Energy-aware scheduling for dependent tasks in heterogeneous multiprocessor systems[J].Journal of Systems Architecture,2022,129:102598.
[15]CHEN W,XIE G,LI R,et al.Efficient task scheduling for bu-dget constrained parallel applications on heterogeneous cloud computing systems[J].Future Generation Computer Systems,2017,74:1-11.
[16]QUAN Z,WANG Z J,YE T,et al.Task scheduling for energy consumption constrained parallel applications on heterogeneous computing systems[J].IEEE Transactions on Parallel and Distributed Systems,2019,31(5):1165-1182.
[17]HU W,CHEN Z,WU J,et al.An energy-conscious task scheduling algorithm for minimizing energy consumption and makespan in heterogeneous distributed systems[C]//International Confe-rence on Intelligent Computing.Singapore:Springer Nature Singapore,2023:109-121.
[18]SHIRVANI M H,TALOUKI R N.A novel hybrid heuristic-based list scheduling algorithm in heterogeneous cloud computing environment for makespan optimization[J].Parallel Computing,2021,108:102828.
[19]XIE G,JIANG J,LIU Y,et al.Minimizing energy consumption of real-time parallel applications using downward and upward approaches on heterogeneous systems[J].IEEE Transactions on Industrial Informatics,2017,13(3):1068-1078.
[20]DENG Z,CAO D,SHEN H,et al.Reliability-aware task scheduling for energy efficiency on heterogeneous multiprocessor systems[J].The Journal of Supercomputing,2021,77:11643-11681.
[21]XU H,ZHANG B,PAN C,et al.Energy-efficient scheduling for parallel applications with reliability and time constraints on he-terogeneous distributed systems[J].Journal of Systems Architecture,2024,152:103173.
[22]CHENG M,LI J,NAZARIAN S.DRL-cloud:Deep reinforcement learning-based resource provisioning and task scheduling for cloud service providers[C]//2018 23rd Asia and South Pacific Design Automation Conference(ASP-DAC).IEEE,2018:129-134.
[23]DUAN R,PRODAN R,LI X.Multi-objective game theoreticscheduling of bag-of-tasks workflows on hybrid clouds[J].IEEE Transactions on Cloud Computing,2014,2(1):29-42.
[24]JIANG J,LIN Y,XIE G,et al.Time and energy optimization algorithms for the static scheduling of multiple workflows in he-terogeneous computing system[J].Journal of Grid Computing,2017,15:435-456.
[25]ZHANG L,LI K,LI C,et al.Bi-objective workflow scheduling of the energy consumption and reliability in heterogeneous computing systems[J].Information Sciences,2017,379:241-256.
[26]BEHERA I,SOBHANAYAK S.Task scheduling optimizationin heterogeneous cloud computing environments:A hybrid GA-GWO approach[J].Journal of Parallel and Distributed Computing,2024,183:104766.
[27]LIU Z,LIWANG M,HOSSEINALIPOUR S,et al.RFID:Towards low latency and reliable DAG task scheduling over dynamic vehicular clouds[J].IEEE Transactions on Vehicular Technology,2023,72(9):12139-12153.
[28]TOPCUOGLU H,HARIRI S,WU M Y.Performance-effective and low-complexity task scheduling for heterogeneous computing[J].IEEE Transactions on Parallel and Distributed Systems,2002,13(3):260-274.
[29]ARABNEJAD H,BARBOSA J G.List scheduling algorithm for heterogeneous systems by an optimistic cost table[J].IEEE Transactions on Parallel and Distributed Systems,2013,25(3):682-694.
[30]CAO Z,DENG X,YUE S,et al.Dependent Task Offloading in Edge Computing Using GNN and Deep Reinforcement Learning[J].IEEE Internet of Things Journal,2024,11(12):21632-21646.
[31]HU Y,LI J,HE L.A reformed task scheduling algorithm forheterogeneous distributed systems with energy consumption constraints[J].Neural Computing and Applications,2020,32(10):5681-5693.
[32]Alibaba.Cluster-trace-v2018[EB/OL].(2018-03-12)[2024-10-05].https://github.com/alibaba/clusterdata/blob/master/clus-ter-trace-v2018.
[33]XIAO X,XIE G,LI R,et al.Minimizing schedule length of energy consumption constrained parallel applications on heterogeneous distributed systems[C]//2016 IEEE Trustcom/BigDataSE/ISPA.Tianjin:IEEE,2016:1471-1476.
[34]LI H,WU J,LU J,et al.A Task Level-Aware Scheduling Algorithm for Energy Consumption Constrained Parallel Applications on Heterogeneous Computing Systems[C]//International Conference on Intelligent Computing.Singapore:Springer Nature Singapore,2023:97-108.
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