Conference Paper

Dynamic Task Scheduling using Genetic Algorithms for Heterogeneous Distributed Computing.

DOI: 10.1109/IPDPS.2005.184 Conference: 19th International Parallel and Distributed Processing Symposium (IPDPS 2005), CD-ROM / Abstracts Proceedings, 4-8 April 2005, Denver, CO, USA
Source: DBLP

ABSTRACT An algorithm has been developed to dynamically sched- ule heterogeneous tasks on heterogeneous processors in a distributed system. The scheduler operates in an environ- ment with dynamically changing resources and adapts to variable system resources. It operates in a batch fashion and utilises a genetic algorithm to minimise the total exe- cution time. We have compared our scheduler to six other schedulers, three batch-mode and three immediate-mode schedulers. We have performed simulations with randomly generated task sets, using uniform, normal, and Poisson dis- tributions, whilst varying the communication overheads be- tween the clients and scheduler. We have achieved more effi- cient results than all other schedulers across a range of dif- ferent scenarios while scheduling 10,000 tasks on up to 50 heterogeneous processors.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Multiprocessor task scheduling is an important problem in parallel applications and distributed systems. In this way, solving the multiprocessor task scheduling problem (MTSP) by heuristic, meta-heuristic, and hybrid algorithms have been proposed in literature. Although the problem has been addressed by many researchers, challenges to improve the convergence speed and the reliability of methods for solving the problem are still continued especially in the case that the communication cost is added to the problem frame work. In this paper, an Immune-based Genetic algorithm (IGA), a meta-heuristic approach, with a new coding scheme is proposed to solve MTSP. It is shown that the proposed coding reduces the search space of MTSP in many practical problems, which effectively influences the convergence speed of the optimization process. In addition to the reduced search space offered by the proposed coding that eventuate in exploring better solutions at a shorter time frame, it guarantees the validity of solutions by using any crossover and mutation operators. Furthermore, to overcome the regeneration phenomena in the proposed GA (generating similar chromosomes) which leads to premature convergence, an affinity based approach inspired from Artificial Immune system is employed which results in better exploration in the searching process. Experimental results showed that the proposed IGA surpasses related works in terms of found makespan (20% improvement in average) while it needs less iterations to find the solutions (90% improvement in average) when it is applied to standard test benches.
    International Journal of Parallel Programming 01/2012; 40:225-257. · 0.40 Impact Factor
  • Source
    12/2012: pages 135-144;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We consider the problem of admitting sets of possibly heterogenous, virtual machines (VMs) with stochastic resource demands onto physical machines (PMs) in a Cloud environment. The objective is to achieve a specified quality-ofservice related to the probability of resource over-utilization in an uncertain loading condition, while minimizing the rejection probability of VM requests. We introduce a method which relies on approximating the probability distribution of the total resource demand on PMs and estimating the probability of overutilization. We compare our method to two simple admission policies: admission based on maximum demand and admission based on average demand. We investigate the efficiency of the results of using our method on a simulated Cloud environment where we analyze the effects of various parameters (commitment factor, coefficient of variation etc.) on the solution for highly variate demands.
    MASCOTS Conference, 2013 IEEE 21th International Symposium on, San Francisco; 08/2013


Available from

Similar Publications