An Improved Max-Min Task-Scheduling Algorithm for Elastic Cloud
Authors:
- Xiaofang LiXLXiaofang Li
- Yingchi MaoYMYingchi Mao
- Xianjian XiaoXXXianjian Xiao
- Yanbin ZhuangYZYanbin Zhuang
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 340-343
Abstract
In cloud computing, load balancing aids in minimizing resource consumption and avoids bottlenecks. Although many load balancing schemes have been presented, there is no scheme providing the elasticity in cloud computing. A Max-Min task-scheduling algorithm for load balance in the elastic cloud is proposed in this paper. To realize the load balancing, the proposed algorithm maintains a task status table to estimate the real-time load of virtual machines and the expected completion time of tasks, which can allocate the workload among nodes and realize the load balance. The extensive experiments demonstrate that the proposed Max-Min task-scheduling algorithm can improve the resource utilization as well as reduce the response time of tasks.Keywords
This publication has 5 references indexed in Scilit:
- Cloud computing and its key techniquesJournal of Computer Applications, 2009
- QoS-guaranteed load-balancing dynamic spectrum access algorithm2008
- Effective load balancing for cluster-based servers employing job preemptionPerformance Evaluation, 2008
- Towards SLA-based optimal workload distribution in SANs2008
- Comparison of Load Balancing Strategies on Cluster-based Web ServersSIMULATION, 2001