Research on cloud computing adaptive task scheduling based on ant colony algorithm

Abstract

In order to solve the shortcomings of ant colony algorithm in solving large-scale task scheduling problems in cloud computing, the convergence speed is slow and easy to fall into local optimal solutions. This paper designs an adaptive task scheduling algorithm for cloud computing based on ant colony algorithm. On the basis of the polymorphic ant colony algorithm, a pheromone adaptive update adjustment mechanism is added to improve the convergence speed of the algorithm and effectively avoid the emergence of local optimal solutions. The improved algorithm aims to solve a distribution plan with shorter execution time, lower cost and balanced load rate based on the tasks submitted by users. The traditional ant colony algorithm is compared with the improved adaptive ant colony algorithm through the cloud computing platform. Experimental data shows that the improved adaptive ant colony algorithm can quickly find the optimal solution to the cloud computing resource scheduling problem, shorten the task completion time, reduce the execution cost, and maintain the load balance of the entire cloud system center. The performance of this algorithm is better when solving large-scale task scheduling problems.