| In the context of the rapid development of 5G technology,application scenarios such as the Industrial Internet are also emerging.The applications of these scenarios often have higher requirements for network latency and data transmission.The emergence of edge computing just fills the shortage of cloud computing centers.Edge nodes with computing resources can be closer to the user terminal side,which has the characteristics of low latency,low energy consumption,and less bandwidth pressure.Therefore,cloud computing and edge computing are combined.Collaboration has become an important research direction.In the process of service optimization deployment in the cloud-edge collaboration environment,more influencing factors and constraints need to be considered.If it is deployed according to an unreasonable scheme,it will not only waste the limited resources on the edge nodes,but also bring unnecessary network communication costs and reduce the quality of service.On the other hand,if the resources on the edge node are only passively monitored in real time,when the resources required for the service requested to be deployed increase rapidly,it may cause the resource overload situation on the edge node.Especially in the case of industrial Internet for large-scale industrial production,it will lead to unnecessary economic losses.In view of the above problems,this paper will propose corresponding solutions.This paper first comprehensively considers the impact of resource utilization,delay and network communication cost between services on service optimization deployment in the process of service optimization deployment in the cloud-edge collaboration environment.Then,Establish a service optimization deployment problem model in the cloud-edge collaboration environment.Under the constraints of resources and delay,the service deployment can achieve the goals of maximizing resource utilization and minimizing network communication costs.Then,aiming at the service optimization deployment problem... |
PDF Full Text Request