Distributed interference mitigation in two-tier wireless networks using correlated equilibrium and regret-matching learning

In this paper we study the interference management in two-tier cellular system from a game theoretic perspective. We extend the work given in [1], [2] to apply the game theoretic approach based on correlated equilibrium and regret-matching learning to multi-tier decentralized interference mitigation. The proposed approach requires periodic information exchange between coordinating base stations (BSs), thus several simplifications to the original algorithm are proposed. Numerical results of Monte Carlo simulations of Long Term Evolution - Advanced (LTE-A) like system are presented, with the proposed solution providing significant increase in terms of average cell throughput and user rate comparing to the state-of-the-art schemes.