Distributed Systems (DS) have a collection of heterogeneous computing resources to process user tasks. Task scheduling in DS has become prime research case, not only due of finding an optimal schedule, but also becaus...Distributed Systems (DS) have a collection of heterogeneous computing resources to process user tasks. Task scheduling in DS has become prime research case, not only due of finding an optimal schedule, but also because of the time taken to find the optimal schedule. The users of Ds services are more attentive about time to complete their task. Several algorithms are implemented to find the optimal schedule. Evolutionary kind of algorithms is one of the best, but the time taken to find the optimal schedule is more. This paper presents a distance-based Pareto genetic algorithm (DPGA) with the Map Reduce model for scheduling independent tasks in a DS environment. In DS, most of the task scheduling problem is formulated as multi-objective optimization problem. This paper aims to develop the optimal schedules by minimizing makespan and flow time simultaneously. The algorithm is tested on a set of benchmark instances. MapReduce model is used to parallelize the execution of DPGA automatically. Experimental results show that DPGA with MapReduce model achieves a reduction in makespan, mean flow time and execution time by 12%, 14% and 13% than non-dominated sorting genetic algorithm (NSGA-II) with MapReduce model is also implemented in this paper.展开更多
文摘Distributed Systems (DS) have a collection of heterogeneous computing resources to process user tasks. Task scheduling in DS has become prime research case, not only due of finding an optimal schedule, but also because of the time taken to find the optimal schedule. The users of Ds services are more attentive about time to complete their task. Several algorithms are implemented to find the optimal schedule. Evolutionary kind of algorithms is one of the best, but the time taken to find the optimal schedule is more. This paper presents a distance-based Pareto genetic algorithm (DPGA) with the Map Reduce model for scheduling independent tasks in a DS environment. In DS, most of the task scheduling problem is formulated as multi-objective optimization problem. This paper aims to develop the optimal schedules by minimizing makespan and flow time simultaneously. The algorithm is tested on a set of benchmark instances. MapReduce model is used to parallelize the execution of DPGA automatically. Experimental results show that DPGA with MapReduce model achieves a reduction in makespan, mean flow time and execution time by 12%, 14% and 13% than non-dominated sorting genetic algorithm (NSGA-II) with MapReduce model is also implemented in this paper.
