Learning Automaton-Based Neighbor Discovery for Wireless Networks Using Directional Antennas

摘要

This letter studies the problem of neighbor discovery (i.e., finding 1-hop neighbor nodes) in a wireless adhoc network, with exclusive use of directional antennas. We model the neighbor discovery process as a learning automaton, operating in a non-stationary learning environment with unknown dynamics. The node learns about its environment from its past observations and adjusts its strategy to achieve a faster discovery rate. The asymptotic behavior of the proposed learning scheme is analyzed and is shown to converge to an equi-probable probability distribution. The proposed scheme achieves significantly faster network-wide neighbor discovery in densely populated networks.