Anycast service model and its QoS routing algorithm

作     者：WANG Jian xin, CHEN Song qiao, CHEN Jian er (College of Information Science and Engineering, Central South University, Changsha 410083, China) 

作者机构：1. College of Information Science and Engineering Central South University 410083 Changsha China 

出 版 物：《Journal of Central South University》 (中南大学学报(英文版))

年 卷 期：2001年第8卷第2期

页      面：135-139页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：TheNationalScienceFundforOverseasDistinguishedYoungScholars (No .6 992 82 0 1) FoundationforUniversity KeyTeacherbytheMinist 

主　　题：QoS anycast service network routing randomized algorithm 

摘      要：In the Internet, a group of replicated servers is commonly used in order to improve the scalability of network service. Anycast service is a new network service that can improve network load distribution and simplify certain applications. In this paper, the authors described a simple anycast service model in the Internet without significant affecting the routing and protocol processing infrastructure that was already in place, and proposed an anycast QoS routing algorithm for this model. The algorithm used randomized method to balance network load and improve its performance. Several new techniques are proposed in the algorithm, first, theminimum hops for each node are used in the algorithm, which are used as metric for computing the probability of possible out links. The metric is pre computed for each node in the network, which can simplify the network complexity and provide the routing process with useful information. Second, randomness is used at the link level and depends dynamically on the routing configuration. This provides great flexibility for the routing process, prevents the routing process from overusing certain fixed routing paths, and adequately balances the delay of the routing path. the authors assess the quality of QoS algorithm in terms of the acceptance ratio on anycast QoS requests, and the simulation results on a variety of network topologies and on various parameters show that the algorithm has good performances and can balance network load effectively.