Research On Service Selection Approach Based On QoS And Load Balance In Cloud Environment

In cloud environment, more and more Web services are deployed by users, which havethe same or similar functions but different non-functions. QoS (Quality of Service) is a keynon-functional aspect for service providers to win the market in the Web service selection.With the increasing development of cloud computing, it is desired to select qualified servicesthat meet users’ requirements, and the services with expected high QoS are usually preferredby users. However, service requests in a cloud environment are typically real-time,concurrent and large-scale. It is probable that load of services will become unbalanced whilemany users are invoking the same service, and so user’s requests aren’t satisfied and serviceprovision capability will decline rapidly. To solve this problem, only a few researcherspointed out that service’s load will affect the performance of the service system, and they alsohave made some research about this field. However, there are many unsolved and challengingproblem. How to provide satisfactory services when the users are accessing the same serviceor multiple services, which can ensure load balancing of the service system. Meanwhile, howto consider load balance of the service system to compose these services, when the servicewith simple or finite functions that cannot satisfy a user’s requirements. To solve the problem,the research work of this paper as follows:(1) This paper presents a load-aware service selection method in cloud environmentconsidering load balance of services. Currently, the most of service selection approaches canselect high qualified services from the user’s perspective. However, in cloud environment,with the increasing of the users, It is probable that multiple users are invoking the sameservice, and so user’s requests aren’t satisfied and service provision capability will declinerapidly. Therefore, they show that load-aware service selection approach can effectively helpuser select high qualified services while keeping load balance of services.(2) This paper presents a global optimal service selection approach based on QoS andload-aware in cloud environment. In cloud environment, there are many service providers andusers at the same time. In this environment, the service selection should not only provide thesatisfactory services to the users, but also ensure the load balance of the entire service system.Therefore, it is very important problem how to get a tradeoff between the users’ satisfiedrequirement and service load balance.(3) This paper adds the load balance in the service composition. We present a PSOservice composition model and algorithm based on service’s QoS and capacity. In cloudenvironment, it is not necessarily that a service can satisfy a user’s requirements in theservice selection. It also maybe a service composition. The existing serivce compositionapproaches consider the service’s QoS, for example, price and response tile. There are manyservice composition approached based on the service’s QoS, but only few approaches consider that the service load balance affect the performance of the service composition. Thisapproach not only provide the high qualified service compositions to users, but also promotethe success rates of service compositions according to keeping load balance of services.