【摘要】 针对异构网格资源下任务的调度最小化执行时间问题(NP难题),提出了一种基于云模型的自适应蚁群调度算法.该算法在定性知识的指导下,权衡提高收敛速度和保持解的多样性之间的矛盾,能够自适应控制搜索范围,较好地避免了传统蚁群算法易陷入局部最优解和选择压力过大造成的早熟收敛等问题,提高其快速寻优能力.实验结果表明该算法在保证有效的加速比的同时具有精度高、收敛速度快等优点,极大地提高了网格任务调度的规模和效率.更多还原

【Abstract】 Aiming at the problems of task scheduling which minimize the total task execution time for heterogeneous grid resources(a NP hard problem),an adaptive ant colony task scheduling algorithm based on cloud models theory is presented.With the instructions of qualitative knowledge,the extent of searching space is adaptively adjusted and the possibility of premature and the probability of trapping in local best optimization are greatly reduced by appeasing the contradiction between the convergent speed and the searching scope,so the algorithm can find high accurate numerical solution with in a short time.By the experiments on typical test functions,the precision,stability and convergence rate were well proved.更多还原