Optimizing Task Scheduling in Cloud Computing: Development of a Refined Round Robin Algorithm with Dynamic Time Quantum Adjustment

Abstract

Cloud computing has transformed the landscape of modern computing by providing scalable and on-demand access to computational resources. Efficient task scheduling is a critical aspect of cloud computing, directly impacting system performance and resource utilization. The conventional Round Robin algorithm, while commonly used, suffers from limitations such as fixed time quantum and inability to adapt to varying task priorities, leading to suboptimal scheduling outcomes. This research addresses these limitations by developing a Refined Round Robin Algorithm (RRRA) that introduces a dynamic time quantum adjustment mechanism based on task priority and system load conditions. The proposed algorithm calculates the time quantum dynamically using a formula that incorporates an initial time quantum, a system-determined constant, and the task's priority level. The study evaluates the performance of the RRRA in a simulated cloud computing environment using MATLAB, with three scenarios representing different task arrival and priority conditions. Key performance metrics, including waiting time, turnaround time, throughput, and the number of context switches, were analyzed and compared with traditional scheduling algorithms, such as the Standard Round Robin, Round Robin with Adaptive Priority Scheduling (RRAPS), and Dynamic Round-Robin Heuristic Algorithm (DRRHA). The results demonstrate that the Refined Round Robin Algorithm significantly improves scheduling efficiency, particularly in reducing waiting time and context switches while enhancing system throughput. The findings suggest that the RRRA can serve as an effective scheduling solution in cloud environments, providing a balanced approach to task prioritization and dynamic resource allocation.