2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum (2012)
Shanghai, China China
May 21, 2012 to May 25, 2012
The robustness of a schedule, with respect to its probability of successful execution, becomes an indispensable requirement in open and dynamic service-oriented environment, such as grids or clouds. We design a fine-grained risk assessment model customized for workflows to precisely compute the cost of failure of a schedule. In comparison with current course-grained model, ours takes the relation of task dependency into consideration and assigns higher impact factor to tasks at the end. Thereafter, we design the utility function with the model and apply a genetic algorithm to find the optimized schedule, thereby maximizing the robustness of the schedule while minimizing the possible risk of failure. Experiments and analysis show that the application of customized risk assessment model into scheduling can generally improve the successful probability of a schedule while reducing its exposure to the risk.
Schedules, Computational modeling, Robustness, Risk management, Synchronization, Scheduling, risk assessment, workflow schedule, robustness
M. Wang, K. Ramamohanarao and J. Chen, "Dependency-based Risk Evaluation for Robust Workflow Scheduling," 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum(IPDPSW), Shanghai, China China, 2012, pp. 2328-2335.