On the Internet delay-based clustering

Abstract

The scalability of routing in large scale networks, such as the Internet, is critical to achieve low delay and high throughput. The lack of scalability of routing protocols in large-scale networks results from the prohibitive overhead incurred during dissemination of path metric values across the network. This paper addresses this problem and proposes a cluster-based scheme, referred to as d-median, which strikes a balance between scalability and routing efficiency. In this scheme, the link metric information is exchanged on a per-cluster basis, rather than on a per-node basis thereby reducing considerably the routing overhead. The simulation results show that the scheme exhibits better performance compared to existing models.