On Simulated Annealing for the Scheduling of Parallel Applications

Abstract

A grid scheduling algorithm inspired on the simulated annealing meta-heuristic (SA) is presented. Guided by predictions about parallel applications resource usage, the algorithm uses SA to find a near-optimal solution which minimizes the overall execution time for scheduling problems on heterogeneous grids. The scheduling algorithm is validated by simulations, using a model which considers the mainly details about the distributed computers and the jobs, and is compared with other scheduling algorithms. The results allows identify the best SA parameters values, that are the learning rate and the iteration size, for each grid size. We found good results when simulating the scheduling algorithm for grid sizes near by 512 computers. We also observed that the SA computing cost do not jeopardize the scheduling results, which are better when compared with the performance of other scheduling disciplines.

Chemical Reaction Optimization for the Grid Scheduling Problem

“…we compare the CRO approach with four popular metaheuristics, namely, PSO, TA, SA, and GA, which have been shown to have good performance in solving similar grid scheduling problems (with formulations similar to that given in Section II) [18], [20], [23]- [26]. We follow [24] to program PSO, [25] for TA, [22] and [23] for SA, and [19] and [26] for GA. All algorithms are coded in C++ and the simulations are performed on the same PC with an Intel Core 2 Duo-E6700 @ 2.66GHz CPU and 2 GB RAM.…”

“…As in [18], we employ the vector-based representation for the schedules (solutions). Let ω be a vector denoting a solution.…”