SLA-based scheduling of applications for geographically secluded clouds

With recent advances in technology, resource control is a significant challenge for geographically distributed clouds. Users geographically close to the server get better services due to low latency. A few existing scheduling algorithms can provide better strategies through efficient job scheduling and resource allocation techniques. However, these algorithms are not efficient enough for distanced clouds. In order to gain maximum profits with optimized scheduling algorithms, it is necessary to utilize resources efficiently and also prioritize the tasks that are near to the servers. This paper proposes job scheduling algorithms in a distributed datacenter (DC) network, where the algorithms assign user's workloads to Virtual Machines (VMs) hosted to DC close to the users to reduce response time. The aspect of the proposed algorithms is the use of delay to evaluate if a VM provide a low or a high delay, it is required that the location of the end user generating the tasks should be known. Our results show that prioritizing tasks for the nearest servers not only improve the quality of service (QoS) but also demonstrates better utilization of the resources.