Load Balanced Clustering Algorithm for Cognitive Radio Ad Hoc Networks

Clustering is emerged as an efficient technique to enhance the stability and scalability of wireless ad hoc network. However, clustering in cognitive radio ad hoc networks (CRAHNs) is challenging due to an intrinsic feature of CRNs, known as the dynamicity of channel availability. In literature clustering in CRAHNs concentrated on forming a Minimum dominating set (MDS), a stable clustered network or energy efficient clusters by adopting the homogenous channel model. In this paper, by jointly considering the presence of channel heterogeneity in terms of transmission range and the load balance, a greedy heuristic algorithm called Load Balanced Spectrum and Transmission Range Aware Clustering (LB-STRAC) is proposed. LB-STRAC aims to distribute the load fairly between the cluster-heads as well as to allocate the spectrum fairly among the constructed clusters. It includes of two phases. The initial cluster construction phase performs initial partitioning of a network into clusters, and the cluster membership clarification phase associates the normal nodes into clusters in a way that supporting the load balancing. The simulation results show that LB-STRAC constructs a minimum number of clusters and significantly reduces the inequality of load distribution, as well as the spectrum allocation among the constructed clusters, while keep the average number of common channels per clusters at reasonable value.