Lightweight Distributed Method for Connectivity-based Clustering Based on Schelling's Model

Abstract

In the literature, there exist connectivity-based distributed clustering methods called CDC (Connectivity-based Distributed node Clustering scheme) and SDC (SCM-based Distributed Clustering). CDC and SDC have mechanisms for maintaining clusters against nodes join and leave, but both methods do not assume frequent changes in the network topology. In this paper, we propose a lightweight distributed clustering method called SBDC (Schelling-Based Distributed Clustering), which is inspired by Schelling's model -- a popular segregation model in sociology. We also evaluate the effectiveness of our proposed SBDC in environment with frequent changes in the network topology. Our simulation results show that SBDC outperforms CDC and SDC under frequent changes in the network topology caused by high node mobility.