【摘要】 芝加哥大学提出了一个网格资源选择算法,能够同时满足单一资源选择和多个资源选择的要求。但是,由于算法一开始就选择了资源集合中单机最强的节点,所以很容易陷入局部最优,且算法不具备容错能力。针对这种情况,本文对该算法进行改进,提出了基于基版本/副版本技术的容错资源选择算法。模拟实验表明,算法是有效的。更多还原

【Abstract】 The university of Chicago presents a grid resource selection algorithm, which supports both single resource and multiple resource selection. Because the algorithm selects the most powerful node in Grid at first, it is very easy to fall into partial optimization. Moreover, the algorithm has no fault-tolerant ability. According to the characteristics of Grid and the technique of primary/backup copies, a fault-tolerant resource selection algorithm is proposed in this paper. Experimental results show that new algorithm is effective.更多还原