User-priority guided Min-Min scheduling algorithm for load balancing in cloud computing

Abstract

Cloud computing is emerging as a new paradigm of large-scale distributed computing. In order to utilize the power of cloud computing completely, we need an efficient task scheduling algorithm. The traditional Min-Min algorithm is a simple, efficient algorithm that produces a better schedule that minimizes the total completion time of tasks than other algorithms in the literature [7]. However the biggest drawback of it is load imbalanced, which is one of the central issues for cloud providers. In this paper, an improved load balanced algorithm is introduced on the ground of Min-Min algorithm in order to reduce the makespan and increase the resource utilization (LBIMM). At the same time, Cloud providers offer computer resources to users on a pay-per-use base. In order to accommodate the demands of different users, they may offer different levels of quality for services. Then the cost per resource unit depends on the services selected by the user. In return, the user receives guarantees regarding the provided resources. To observe the promised guarantees, user-priority was considered in our proposed PA-LBIMM so that user's demand could be satisfied more completely. At last, the introduced algorithm is simulated using Matlab toolbox. The simulation results show that the improved algorithm can lead to significant performance gain and achieve over 20% improvement on both VIP user satisfaction and resource utilization ratio.