云中多媒体应用中基于混合DAG的最优任务调度研究

计算机科学 ›› 2015, Vol. 42 ›› Issue (Z11): 413-416.

云中多媒体应用中基于混合DAG的最优任务调度研究

郭雅琼,宋建新

南京邮电大学江苏省图像传输与处理重点实验室南京210003,南京邮电大学江苏省图像传输与处理重点实验室南京210003

出版日期:2018-11-14 发布日期:2018-11-14

Optimal Task-level Scheduling Based on Multimedia Applications in Cloud

GUO Ya-qiong and SONG Jian-xin

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 云计算的平台优势使得它在多媒体应用中得到广泛使用。由于多媒体服务的多样性和异构性,如何将多媒体任务有效地调度至虚拟机进行处理成为当前多媒体应用的研究重点。对此,研究了云中多媒体最优任务调度问题,首先引入有向无环图来模拟任务中的优先级及任务之间的依赖性,分别对串行、并行、混合结构任务调度模型进行任务调度研究,根据有限资源成本将关键路径中任务节点融合,提出一种实用的启发式近似最优调度方法。实验结果表明,所提调度方法能够以最短的执行时间在有限的资源成本下完成最优的任务分配。

关键词: 关键路径,有限无环图,任务级调度,启发式调度

Abstract: As an emerging computing paradigm,cloud computing has been increasingly used in multimedia applications.Because of the diversity and heterogeneity of multimedia services,how to effectively schedule multimedia tasks to multiple virtual machines for processing has become one fundamental challenge for application providers.So we studied task-level scheduling problem for cloud based multimedia applications.Firstly,we introduced a directed acyclic graph to mo-del precedence constraints and dependency among tasks in the hybrid structure.Based on the model,we studied the optimal task scheduling problem for the sequential,the parallel,and the mixed structures.Moreover,we combined the task nodes in the critical path according to the cost of limited resources.Lastly,we proposed a heuristic method to perform the near optimal task scheduling in a practical way.Experimental results demonstrate that the proposed scheduling scheme can optimally assign tasks to virtual machines to minimize the execution time.

Key words: Critical path,Directed acyclic graph,Task-level scheduling,Heuristic scheduling

郭雅琼,宋建新. 云中多媒体应用中基于混合DAG的最优任务调度研究[J]. 计算机科学, 2015, 42(Z11): 413-416. https://doi.org/

GUO Ya-qiong and SONG Jian-xin. Optimal Task-level Scheduling Based on Multimedia Applications in Cloud[J]. Computer Science, 2015, 42(Z11): 413-416. https://doi.org/

参考文献

[1] 刘培松.云计算环境下任务调度和资源分配策略的研究[D].上海:华东师范大学,2013
[2] Zhu W,Luo C,Li S.Multimedia cloud computing [J].IEEE Signal Processing Magazine,2011,28(3):59-69
[3] 晏婧.适用于实例密集型云工作流的调度算法[J].计算机应用,2011,0(11):1-3
[4] 晏婧.云环境下基于QoS约束的工作流任务调度算法研究与实现[D].重庆:重庆大学,2011
[5] Nan X,He Y,Guan L.Optimization of workload scheduling for multimedia cloud computing [C]∥IEEE International Symposiumon Circuits and Systems(ISCAS).2013:2872-2875
[6] Nan X,He Y,Guan L.Optimal resource allocation for multimedia cloud based on queuing model[C]∥IEEE International Workshop on Multimedia Signal Processing(MMSP).2011:1-6
[7] Zhang T J,Li J J,et al.Adaptive resource allocation for cloudcomputing environments under bursty workloads[C]∥IEEE Performance Computing and Communications Conference.2011:1-8
[8] Hong B,Tang R,Zhai Y.A resources allocation algorithm based on media task Qos in cloud Computing[C]∥IEEE Software Engineering and Service Science(ICSESS).2013:841-844
[9] Guo L,Zhao S,Shen S.Task Scheduling Optimization in Cloud Computing Based on Heuristic Algorithm [J].Journal of Networks,2012,7(3):547-553
[10] Zhao Z,Zhao Y,Gao Z,et al.BUPT-MCPRL at TRECVID 2009[C]∥Proceedings of TRECVID 2009 Workshop.2009:1-11
[11] 袁浩.基于社会力群智能优化算法的云计算资源调度[J].计算机科学,2015,2(4):206-208
[12] 王波,张晓磊.基于粒子群遗传算法的云计算任务调度研究[J].计算机工程与应用,2015,1(6):84-88
[13] Kelley J E.The critical-path method:Resources planning andscheduling [J].Journal of Industrial Scheduling,1963 ,37(11):108-111
[14] Gao Y,Ma H,Zhang H.Concurrency Optimized Task Scheduling for Workflows in cloud [C]∥IEEE Sixth International Conference on Cloud Computing.2013:709-716
[15] Amazon EC2.http://aws.amazon.com/ec2/
[16] Over P,Awad G M,Fiscus,et al.TRECVID 2009-goals,tasks,data,evaluation mechanisms and metrics.http://www-nlpir.nist.gov/projects/tvpubs/tv.pubs.org.html

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed