A novel wireless sensor network topology with fewer links

Abstract: This paper, based on $k$-NN graph, presents symmetric $(k,j)$-NN graph $(1 \leq j < k)$, a brand new topology which could be adopted by a series of network-based structures. We show that the $k$ nearest neighbors of a node exert disparate influence on guaranteeing network connectivity, and connections with the farthest $j$ ones among these $k$ neighbors are competent to build up a connected network, contrast to the current popular strategy of connecting all these $k$ neighbors. In particular, for a network with node amount $n$ up to $10^3$, as experiments demonstrate, connecting with the farthest three, rather than all, of the five nearest neighbor nodes, i.e. $(k,j)=(5,3)$, can guarantee the network connectivity in high probabilities. We further reveal that more than $0.75n$ links or edges in $5$-NN graph are not necessary for the connectivity. Moreover, a composite topology combining symmetric $(k,j)$-NN and random geometric graph (RGG) is constructed for constrained transmission radii in wireless sensor networks (WSNs) application.