多任务优化算法在各任务单独优化的同时进行任务间的知识迁移,从而提升多个任务的综合性能。然而,在相似度较低的任务间进行负向知识迁移反而会导致整体性能下降,且为难度不同的任务分配同等的计算资源会造成资源浪费。此外,在任务的不...多任务优化算法在各任务单独优化的同时进行任务间的知识迁移,从而提升多个任务的综合性能。然而,在相似度较低的任务间进行负向知识迁移反而会导致整体性能下降,且为难度不同的任务分配同等的计算资源会造成资源浪费。此外,在任务的不同阶段采用固定的搜索步长容易陷入局部最优。为解决上述问题,提出了一种基于自适应知识迁移与动态资源分配的多任务协同优化(Multitask Cooperative Optimization Algorithm Based on Adaptive Knowledge Transfer and Resource Allocation,AMTO)算法。首先,每个任务用一个单独的种群进行优化,并将一个种群分成3个子种群,采用3种不同的搜索策略,增加搜索行为的多样性,并且在单个任务内根据个体成功率来动态更新搜索步长,增强自适应搜索能力,避免陷入局部最优;其次,利用多个任务间知识迁移的反馈结果在线计算任务间相似度,并依据相似度自适应地调整迁移概率,同时,在相似度较低的任务间进行迁移时还需减去任务偏差,减小负向知识迁移造成的性能下降程度,提升算法对任务间差异的感知能力;然后,通过评估任务性能的提升度来估计任务难度与优化状态,对不同难度与状态的任务动态按需分配资源,最大限度地提升资源的利用率,减少资源浪费;最后,在简单与复杂两类多任务优化函数上,将本文算法与经典的多任务算法进行对比实验,验证了本文算法中自适应迁移策略、动态资源分配策略及其综合的有效性。展开更多
Heterogeneous computing (HC) environment utilizes diverse resources with different computational capabilities to solve computing-intensive applications having diverse computational requirements and constraints. The ta...Heterogeneous computing (HC) environment utilizes diverse resources with different computational capabilities to solve computing-intensive applications having diverse computational requirements and constraints. The task assignment problem in HC environment can be formally defined as for a given set of tasks and machines, assigning tasks to machines to achieve the minimum makespan. In this paper we propose a new task scheduling heuristic, high standard deviation first (HSTDF), which considers the standard deviation of the expected execution time of a task as a selection criterion. Standard deviation of the ex- pected execution time of a task represents the amount of variation in task execution time on different machines. Our conclusion is that tasks having high standard deviation must be assigned first for scheduling. A large number of experiments were carried out to check the effectiveness of the proposed heuristic in different scenarios, and the comparison with the existing heuristics (Max-min, Sufferage, Segmented Min-average, Segmented Min-min, and Segmented Max-min) clearly reveals that the proposed heuristic outperforms all existing heuristics in terms of average makespan.展开更多
文摘多任务优化算法在各任务单独优化的同时进行任务间的知识迁移,从而提升多个任务的综合性能。然而,在相似度较低的任务间进行负向知识迁移反而会导致整体性能下降,且为难度不同的任务分配同等的计算资源会造成资源浪费。此外,在任务的不同阶段采用固定的搜索步长容易陷入局部最优。为解决上述问题,提出了一种基于自适应知识迁移与动态资源分配的多任务协同优化(Multitask Cooperative Optimization Algorithm Based on Adaptive Knowledge Transfer and Resource Allocation,AMTO)算法。首先,每个任务用一个单独的种群进行优化,并将一个种群分成3个子种群,采用3种不同的搜索策略,增加搜索行为的多样性,并且在单个任务内根据个体成功率来动态更新搜索步长,增强自适应搜索能力,避免陷入局部最优;其次,利用多个任务间知识迁移的反馈结果在线计算任务间相似度,并依据相似度自适应地调整迁移概率,同时,在相似度较低的任务间进行迁移时还需减去任务偏差,减小负向知识迁移造成的性能下降程度,提升算法对任务间差异的感知能力;然后,通过评估任务性能的提升度来估计任务难度与优化状态,对不同难度与状态的任务动态按需分配资源,最大限度地提升资源的利用率,减少资源浪费;最后,在简单与复杂两类多任务优化函数上,将本文算法与经典的多任务算法进行对比实验,验证了本文算法中自适应迁移策略、动态资源分配策略及其综合的有效性。
基金Project supported by the National Natural Science Foundation of China (No. 60703012)the National Basic Research Program (973) of China (No. 2006CB303000)the Heilongjiang Provincial Scientific and Technological Special Fund for Young Scholars (No. QC06C033),China
文摘Heterogeneous computing (HC) environment utilizes diverse resources with different computational capabilities to solve computing-intensive applications having diverse computational requirements and constraints. The task assignment problem in HC environment can be formally defined as for a given set of tasks and machines, assigning tasks to machines to achieve the minimum makespan. In this paper we propose a new task scheduling heuristic, high standard deviation first (HSTDF), which considers the standard deviation of the expected execution time of a task as a selection criterion. Standard deviation of the ex- pected execution time of a task represents the amount of variation in task execution time on different machines. Our conclusion is that tasks having high standard deviation must be assigned first for scheduling. A large number of experiments were carried out to check the effectiveness of the proposed heuristic in different scenarios, and the comparison with the existing heuristics (Max-min, Sufferage, Segmented Min-average, Segmented Min-min, and Segmented Max-min) clearly reveals that the proposed heuristic outperforms all existing heuristics in terms of average makespan.
