Deadline-guaranteed scheduling algorithm with improved resource utilization for cloud computing

Abstract

Cloud computing is computing in which large groups of remote servers are networked to allow centralized data storage and on-line access to computer services. Cloud computing providers install and operate application software in the cloud through Software as a Service (SaaS) model. Cloud users access the software and utilizes the services by cloning tasks onto multiple virtual machines (VMs). In recent years, offering high-performance computing capacity reminds cloud providers to utilize resources fully due to limitation of resource. Enhancing resource utilization is also essential for achieving cost effectiveness. In addition, SaaS applications support various services such as email, FTP, and multimedia services with different delay requirement. Among these application multimedia service has relatively low delay requirements. Therefore, in this paper, we propose a scheduling algorithm to enhance both deadline guarantee and resource utilization. We modified the conservative backfilling algorithm by utilizing the earliest deadline first (EDF) algorithm and the largest weight first (LWF) algorithm. The proposed algorithm first score all the jobs arrived at the data center(DC) and sort the jobs in ascending order to serve high priority job first. The proposed algorithm then select the largest possible backfill job as guaranteeing deadline. Simulation results show that the proposed algorithm significantly improve the performance in terms of resource utilization and deadline guarantee.