摘要
针对云计算环境下大量并行计算节点容易产生计算节点之间的负载不均问题,提出了一种基于任务类型匹配的负载均衡方案。该方案针对任务集中的多种不同长度的子任务类型情况进行判定,并对当前主流的Max-Min和Min-Min两种启发式负载均衡算法进行分析,综合其优缺点,并针对任务集的类型采用不同的算法进行任务调度。实验结果表明在该负载均衡的策略下,提出的方案具有比单一应用Max-Min或者Min-Min算法具有更好的负载均衡特性和更短的完成时间。
According to the load imbalance problem of a large number of parallel computing nodes under the cloud computing environment, in this paper, a novel load balance scheme based on task type matching is proposed. This scheme focus on the judgement of task type among multiple different lengths of the subtasks, and an analysis is done on the advantages and disadvantages of two kinds of heuristic load balancing algorithms named Max-Min and Min-Min. Then, task scheduling with different algorithm is executed according to the type of the task set. The experimental results show that the proposed scheme has better load balancing features and shorter completion time than only using the algorithm of Max-Min or Min-Min
出处
《电视技术》
北大核心
2015年第19期43-46,共4页
Video Engineering
基金
重庆市教委科学技术研究项目(KJ130533)