Load Balancing Based On Genetic Algorithms And Coral Reef Algorithms

In view of the need for frequent data exchange and sharing between operators' innovative business order system and government contract security protection record system,high data often occurs and the server cannot respond in time due to the high data transmission,which leads to the failure of real-time and efficient data transmission and processing,resulting in the failure of government supervision to implement more normally,effectively and safely.However,the optimized load balancing system can solve the problem that massive data are sent at the same time and the server response is not timely.It can also reduce the efficiency of data sharing while reducing the risk of data exchange and sharing,and can effectively guarantee the security of data sharing.At the same time,it is conducive to the stable and orderly development of supervision business by the government,the docking of innovative business between operators and government enterprises,the steady development of the market and the development of smart cities.Initial load balancing can effectively solve the problem of congestion caused by uneven task scheduling in server cluster.Now with the deepening of the Internet and the arrival of the era of big data,especially cloud computing has begun to move towards our life.More and more people recognize and use it,and load balancing has gradually become an integral part of cloud computing and also research.A key direction in the field.Therefore,this paper proposes a load balancing method which integrates genetic algorithm and coral reef algorithm,which improves the utilization of network resources and makes load balancing more reasonable.The idea of the algorithm proposed in this paper is mainly to apply crossover,selection and mutation in genetic algorithm to coral reef algorithm,and then propose a genetic coral reef optimization algorithm.Because the basic idea of genetic algorithm is to apply genetic concepts in biology to evolutionary computation,divide each generation of individuals in evolutionary computation into several categories,and select a number of individuals with larger adaptability.As a group of excellent representatives,the genetic selection operation in genetic algorithm is more optimized.Then in the population,as well as among different populations,the operation of crossover and mutation produces a generation of new individuals,so the global search ability of genetic algorithm has been improved and the diversity of population in genetic algorithm has also increased,thus improving the utilization rate of network resources,aiming at the situation of network load imbalance,there is a significant improvement.Regardless of the traditional genetic algorithm or the optimization algorithm based on the fusion of genetic algorithm and coral reef algorithm proposed in this paper,the fitness function plays an important role in the research of load balancing.In view of this phenomenon,all servers are treated as computing servers in this paper.When concurrent requests for massive tasks need optimal allocation combination,load balancing can be achieved by minimizing the maximum utilization of servers and time,optimizing resource allocation and efficiency,which is called load balancing mechanism.Secondly,the concepts of cloud computing and load balancing are described and analyzed.The process of combining genetic algorithm with coral reef algorithm is introduced.The fitness function is the criterion for evaluating load balancing.At the same time,the accuracy of fitness function is improved.Finally,CloudSim,a cloud computing simulation platform,is extended to complete the comparative experiments among different algorithms.The experiments start with iteration times,time,power cost and load balancing.The experimental results show that the improved algorithm is superior to genetic algorithm,coral reef algorithm and other fusion swarm intelligence algorithms.