Distributed Learning Algorithms for Opportunistic Spectrum Access in Infrastructure-less Networks

Abstract

An opportunistic spectrum access (OSA) for the infrastructure-less (or cognitive ad-hoc) network has received significant attention thanks to emerging paradigms such as the Internet of Things (IoTs) and smart grids. Research in this area has evolved from the \r{ho}rand algorithm requiring prior knowledge of the number of active secondary users (SUs) to the musical chair (MC) algorithm where the number of SUs are unknown and estimated independently at each SU. These works ignore the number of collisions in the network leading to wastage of power and bring down the effective life of battery operated SUs. In this paper, we develop algorithms for OSA that learn faster and incurs fewer number of collisions i.e. energy efficient. We consider two types of infrastructure-less decentralized networks: 1) static network where the number of SUs are fixed but unknown, and 2) dynamic network where SUs can independently enter or leave the network. We set up the problem as a multi-player mult-armed bandit and develop two distributed algorithms. The analysis shows that when all the SUs independently implement the proposed algorithms, the loss in throughput compared to the optimal throughput, i.e. regret, is a constant with high probability and significantly outperforms existing algorithms both in terms of regret and number of collisions. Fewer collisions make them ideally suitable for battery operated SU terminals. We validate our claims through exhaustive simulated experiments as well as through a realistic USRP based experiments in a real radio environment.