Lower and Upper Quartiles Enhanced Round Robin Algorithm for Scheduling of Outlier Tasks in Cloud Computing

Abstract

Cloud computing is one of the top emerging technologies with
 huge market and enterprise potential as it provides on-demand, -based access
 to large-scale shared computing resources. Task scheduling is one of the most
 important issues in cloud computing in order to enhance performance and
 resource utilization while minimizing costs. Because of its simplicity and
 fairness, the round-robin algorithm is the ideal task scheduling algorithm,
 although it suffers from time complexity and cannot handle outlier tasks.
 Several modifications of Round Robin have been introduced to enhance time
 complexity. To ensure sufficient deal with time complexity and outlier tasks,
 this paper introduces a novel enhanced round-robin heuristic algorithm by
 utilizing the round-robin algorithm and updating its time quantum
 dynamically based on the lower and upper quartiles of the time quantum for
 all the tasks in the ready queue. The experimental results on four datasets
 showed that the proposed algorithm significantly outperformed baseline
 algorithms in terms of the average waiting time, turnaround time, and
 response time. The results show that, when compared to the baseline
 algorithm in cases 3 and 4, the proposed algorithm enhances the average
 waiting time's time complexity by 50% with datasets containing random and
 outlier tasks.