Dynamic Scheduling of Scientific Experiments on Clouds using Ant Colony Optimization

ELINA PACINI; CRISTIAN MATEOS; CARLOS GARCÍA GARINO

Pécs

Conferencia; Proceedings of the Third International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering (PARENG'2013); 2013

Pollack Mihály Faculty of Engineering University of Pécs

Scientists and engineers often require huge amounts of computing power for performing their experiments. For example, PSEs allow scientists to perform simulations by running the same scientific code with different input data, which results in many CPU-intensive jobs and thus computing environments such as Clouds must be used. In general, however, job scheduling is NP-complete, and therefore many heuristics have been developed. We describe a Cloud scheduler based on ant colony optimization (ACO), to allocate virtual machines (VM) to physical Cloud resources. The main performance metrics to study are the number of serviced users by the Cloud and the number of executed jobs per unit time in dynamic (non-batch) scheduling scenarios. Another contribution is the evaluation of an exponential back-off strategy to retry the allocation of failing VMs that aims at servicing as many users as possible. Simulatedexperiments performed by using CloudSim and real PSE job data suggest that our scheduler achieves a fair assignment of VMs and performs competitively with respect to the number of executed jobs per unit time.