Various services have been deployed on the Internet, and the role of Internet services as a societal infrastructure is becoming increasingly important. As demand for services on the Internet increases, the burdens placed on servers that provide those services increase, which leads to reductions in the quality of services, such as service delays, or temporary stoppage of services in the worst case. Methods of distributing the demand for a service among multiple computers by preparing multiple computers that are capable of providing the same service is commonly employed as a way of minimizing reduction in the quality of service. However, since the demand for a service on the Internet continually fluctuates, it is difficult to predict the demand in order to have computing resources in place ahead of time. In this paper, a basis is therefore proposed for automatically adjusting the total amount of computing resources for providing a service according to the variation in demand for the service. The server group formed according to this basis is referred to as an elastic server group. In an elastic server group, several computers are working that communicate with each other using a Peer-to-Peer system, and the number of computers for providing the service is increased or decreased. In this paper, an elastic server group and a basic mechanism for increasing or decreasing the number of computers for providing a server in the elastic server group are proposed, and the effectiveness of this approach is verified using a simulation.
ASJC Scopus subject areas