Towards Better Workflow Execution Time Estimation

Authors highlight the importance of estimating workflow execution time in the scheduling problem and in pricing models in Clouds. Claim that better approaches need to be developed to obtain precise estimates of execution time. Describe straightforward regression for stochastic execution time estimation. Propose a combination of Chebyshev-like distribution-free inequalities and distribution-based approaches to calculate better confidence bounds on runtime based on results of statistical tests. Finally, authors explain the need of developing better algorithm to compute workflow execution time based on stochastic estimates of tasks’ execution time. Explain the need of developing better workflow runtime estimation algorithm. Finally, authors present an approach to estimating workflow execution time based on stochastic estimates of tasks’ execution time.