Adaptive Fractal-like Network Structure for Efficient Search of Inhomogeneously Distributed Targets at Unknown Positions

TL;DR

This paper introduces a scalable, self-organized geographical network inspired by biological foraging, which adaptively arranges nodes based on population distribution to improve search efficiency for targets in inhomogeneous environments.

Contribution

It presents a novel fractal-like network structure that adapts node placement and topology according to population, enhancing decentralized search efficiency in wireless networks.

Findings

Routing efficiency is higher in population-based fractal structures than in square lattice strategies.

The network self-organizes through iterative rectangle divisions for load balancing.

Decentralized routing using local information achieves superior search performance.

Abstract

Since a spatial distribution of communication requests is inhomogeneous and related to a population, in constructing a network, it is crucial for delivering packets on short paths through the links between proximity nodes and for distributing the load of nodes how to locate the nodes as base-stations on a realistic wireless environment. In this paper, from viewpoints of complex network science and biological foraging, we propose a scalably self-organized geographical network, in which the proper positions of nodes and the network topology are simultaneously determined according to the population, by iterative divisions of rectangles for load balancing of nodes in the adaptive change of their territories. In particular, we consider a decentralized routing by using only local information,and show that, for searching targets around high population areas, the routing on the naturally embedded fractal-like structure by population has higher efficiency than the conventionally optimal strategy on a square lattice.