Service optimization in programmable cloud network  

作　　者：丁浩 Yang Yang Mi Zhenqiang 

机构地区：[1]School of Computer and Communication Engineering,University of Science and Technology Beijing

出　　处：《High Technology Letters》2015年第4期485-493,共9页高技术通讯（英文版）

基　　金：Supported by the National Natural Science Foundation of China(No.61272508,61472033,61202432)

摘　　要：With the rapid development in cloud data centers and cloud service customers,the demand for high quality cloud service has been grown rapidly.To face this reality,this paper focuses on service optimization issues in cloud computing environment.First,a service-oriented architecture is proposed and programmable network facilities are utilized in it to optimize specific cloud services.Then various cloud services are categorized into two subcategories;static services and dynamic services.Furthermore,the concepts of cloud service quality and cloud resource idle rate are defined,and the aforementioned concepts have also been taken into consideration as parameters in the service optimization algorithm to improve the cloud service quality and optimize system workload simultaneously.Numerical simulations are conducted to verify the effectiveness of the proposed algorithm in balancing the workload of all servers.With the rapid development in cloud data centers and cloud service customers, the demand for high quality cloud service has been grown rapidly. To face this reality, this paper focuses on service optimization issues in cloud computing environment. First, a service-oriented architecture is pro- posed and programmable network facilities are utilized in it to optimize specific cloud services. Then various cloud services are categorized into two subcategories： static services and dynamic services. Furthermore, the concepts of cloud service quality and cloud resource idle rate are defined, and the aforementioned concepts have also been taken into consideration as parameters in the service optimi- zation algorithm to improve the cloud service quality and optimize system workload simultaneously. Numerical simulations are conducted to verify the effectiveness of the proposed algorithm in balan- cing the workload of all servers.

关 键 词：distributed cloud architecture programmable network cloud service quality LOADBALANCING 

分 类 号：TP393.09[自动化与计算机技术—计算机应用技术]