AN EFFICIENT SCHEDULING ALGORITHM FOR CLOUD SERVICE REQUESTS

Abstract

Cloud computing provides scalable and cost-effective computing services, but efficient scheduling of service requests remains a major challenge due to dynamic and heterogeneous workloads. Inefficient scheduling leads to increased execution time, poor resource utilization, and higher service costs.

This thesis proposes a Priority-based Batch Scheduling algorithm to reduce overall service utilization time in cloud computing environments. Service requests are classified into three priority levels based on Service Level Agreement (SLA) parameters. High-priority requests are executed immediately using FCFS scheduling, while medium- and low-priority requests are grouped into batches based on similar resource requirements to minimize communication and initialization delays.

Experimental results demonstrate that the proposed approach outperforms existing priority-based scheduling algorithms in terms of execution time, with performance improvements becoming more significant as the number of service requests increases. The proposed algorithm effectively enhances scheduling efficiency, reduces execution cost, and improves overall cloud system performance.