Abstract: An important aspect in implementing grid computing is the implement of unified description method for the geographically distributed，heterogeneous resource，so that the grid system can give users the virtual unified resource interface and execute the task scheduling by the users on the fittest resource node dynamically.Aiming at the conditions and characteristic of application of task scheduling，a parallel clone genetic algorithm is introduced.Application of the algorithm dramatically reduces the computing complexity in resource allocating meeting the requests of real time schedule.From the experiment result，it concludes that this algorithm is superior to other algorithm.

摘要： 实现网格计算的一个重要目的在于实现地理分布、异构资源的统一描述方法，提供用户虚拟的统一资源界面，并将用户提出的服务要求透明、动态地分配给最适应的资源上执行。针对目前任务调度的应用现状，提出了一种既能使资源负载均衡又能充分利用系统资源的并行克隆遗传算法，该启发式算法能显著地降低资源最优分配中的计算复杂度，使其能满足实时调度的需要。实验结果表明这种算法优于其他调度算法。