The optimizing resource allocation and task scheduling based on cloud computing and Ant Colony Optimization Algorithm

The purposes is to promote the intelligent fusion of Ant Colony Optimization Algorithm (ACOA) and the cloud computing for resource allocation and task scheduling. First, the analysis is conducted on the problems in the resource allocation and task scheduling via cloud computing and the limitations of ACOA. Second, the ACOA is optimized to meet the expected time and expected cost, which is denoted by Q-ACOA. Besides, the settings of pheromone heuristic factor alpha and the expected heuristic factor beta are determined. Finally, Q-ACOA is compared with the Round-Robin scheduling (RR) algorithm, the Min Min (MM) algorithm, and the Time, Cost, and Load Balance-Enhanced Ant Colony Optimization (TCLB-EACO) algorithm. The adopted evaluation indicators in task scheduling of cloud computing include the task completion time, the total time of data migration, the cost of task completion, and the satisfaction of participating users. Results demonstrate that the values of alpha and beta have comparatively large influences on the algorithms' iteration times and the task completion time. Ultimately, alpha is determined as 3, and beta is determined as 4.5. Compared with other algorithms, Q-ACOA shows the best performance on several evaluation indicators under multiple tasks. When the number of tasks exceeds 500, Q-ACOA has definite advantages in task completion time. Moreover, its average time of data migration is 2.5% less than the TCLB-EACO algorithm and 2.7% less than the MM algorithm. The overall cost consumption of Q-ACOA is lower than other algorithms, providing users a good experience. The above results can provide a data reference for the improvement of resource allocation and task scheduling based on cloud computing in the future.