Research And Simulation Of Cloud Platform Resource Scheduling Algorithm

The cloud computing service provider integrates the computer system resources and provides the resources to consumer with certain rules through resource sharing.On the cloud platform,consumers pay a certain fee to the service provider for the resources according to their own needs,without paying attention to the implementation of the underlying infrastructure.A good resource scheduling algorithm can improve resource utilization,reduce energy consumption,and reduce operating costs of enterprises.Therefore,it is of great significance to study cloud resource scheduling algorithms.This paper introduces the architecture,service model,deployment model,key technologies and common scheduling algorithms of the cloud platform.It studies the resource scheduling problem of cloud platform to reduce the resource idle rate of the physical server and the power consumption of the data center.The genetic algorithm is used to solve the multi-objective optimization problem.Besides,the principles,characteristics and shortcomings of genetic algorithm and simulated annealing algorithm are studied.The simulated annealing algorithm is used to improve the genetic algorithm to control the convergence of the algorithm so that the genetic algorithm can focus on searching for excellent solutions.In order to solve the multi-objective optimization problem,the evaluation function in the genetic algorithm is designed,and the genetic algorithm,the improved genetic algorithm,the first fit algorithm,the best fit algorithm,the worst fit algorithm is implemented on simulation platform CloudSim.The real energy consumption data provided by the Standard Performance Evaluation Corporation(SPEC)is used when model the physical server.The experimental results show that the improved genetic algorithm has certain advantages in reducing data center resource idle rate and power consumption per unit time.