Distributed server selection with imprecise state for replicated server group

Abstract

Server replication is an approach often used to improve service access efficiency and availability for a large number of clients. This paper adopts a simple service model and investigates a set of efficient algorithms for server selection in an anycast group under the condition of imprecise network delay. The algorithms use ticket-based probing approach to search the path with short delay and probe the server load at the same time and try to optimize the server and path delay at the same time. The simulation results demonstrate that our algorithms are efficient in terms of server response time for sever selection compared with several other server selection algorithms.