Deadline division-based heuristic for cost optimization in workflow scheduling

Ant colony based constrained workflow scheduling for heterogeneous computing systems

“…One category focuses on satisfaction of deadline/budget per activity [30,31]. The other, however, studies satisfaction of deadline/budget for the whole workflow [13][14][15][16][32][33][34].…”

“…Here, those cheaper resources that can complete the activities within their sub-deadline are selected. The authors of [13] minimize the cost of workflow execution through a combination of dynamic programming method for critical activities and a local cost optimization method for noncritical activities. The performance and reliability analysis has been utilized in [15] to schedule a batch of workflows such that at least some of them satisfy the associated deadline while minimizing the cost.…”

“…Similar to what discussed about makespan, using the statistics rule, the mean and variance are computed using (12) and (13). Note that the execution and data transmission costs for all activities are involved in the mean and variance computation.…”

“…However, few studies have been done in the area of constrained workflow scheduling [13][14][15][16][17]. In this problem, the goal is to find scheduling such that the execution of workflow is completed within the user defined deadline and/or the cost of execution be within the predefined budget.…”

“…The studies in [13][14][15] find schedules that meet deadline while minimize the cost of workflow execution. In order to minimize the cost, low speed resources are selected.…”