Cloud Computing Task Scheduling Based on Improved Bat Algorithm

For cloud computing resource allocation imbalance exists in the virtual machine scheduling, bat algorithm slow convergence speed and optimization accuracy is not high shortcomings, a method is proposed for calculating the virtual machine scheduling algorithm and K-means algorithm based on cloud bat. Algorithm using the K-means clustering initialized to bat population data, improve the quality of the initial solution of the sample data; By Powell local search algorithm for the optimal solution for the current local search and improve the convergence speed and accuracy; when using the improved bat algorithm to allocate the virtual machine, algorithm make full use of the resources on the physical machine to achieve the optimization goal.Simulation results show that the improved algorithm has faster convergence speed and higher searching accuracy compared with other standard bat algorithm and particle swarm optimization algorithm; in the virtual machine scheduling, this paper improves the scheduling algorithm compared with the K-means mean scheduling algorithm, the number of the physical quantity node is reduced by about 12%, and the comprehensive utilization rate of system resources is increased by about 11%.