Research On Green Service Composition Method In Cloud Environment

In recent years, with the rapid development of Web services technology and the growing popularity of cloud computing, more and more large-scale IT companies are for small and medium enterprises and individual developers to provide cloud services. With the popularization and application of cloud services, service selection and combinatorial approaches have become an important research hotspot. At the same time,due to the large number of network services deployed in the cloud data center, the choice of services and the inevitable will be affected by the underlying data center performance, and thus affect the service portfolio performance. However, most of the existing service composition schemes in the traditional cloud computing Web services composition technology focus only on the specific services that seek the optimal value of aggregate QoS value (such as response time, throughput, etc.) at the user's point of view, but Without considering the cost of service composition and the energy consumption and network resource consumption that depend on the cloud data center topology and underlying parameters. For cloud computing infrastructure service providers, energy consumption and network resource consumption are directly related to operating costs, by reducing resource consumption can improve the economic benefits of cloud computing infrastructure service providers, but also accord with the national energy-saving emission reduction policies.This paper studies the trade-offs between QoS utility, power consumption and network resource consumption in the service composition target, and further propose a green service composition method in cloud environment. This method introduces the power consumption model and network resource Consumption model, designed to maximize the QoS utility while reducing the power consumption of cloud data centers and network resource consumption. In order to evaluate the method, CloudSim, an open source cloud computing simulation engine, is extended and compared with the traditional service composition method. Then, the simulation results are analyzed and the results are discussed. It is verified that the method is effective for cloud data center energy consumption and network resource consumption control effectiveness. The paper concludes the relevant work, and puts forward the research direction of the next step.