This article addresses the autonomy of joint radio resource management （JRRM） between heterogeneous radio access technologies（RATs） owned by multiple operators. By modeling the inter-operator competition as a general-sum Markov game, correlated-Q learning（CE-Q） is introduced to generate the operators＇ pricing and admission policies at the correlated equilibrium autonomically. The heterogeneity in terms of coverage, service suitability, and cell capacity amongst different RATs are considered in the input state space, which is generalized using multi-layer feed-forward neural networks for less memory requirement. Simulation results indicate that the proposed algorithm can produce rational JRRM polices for each network under different load conditions through the autonomic learning process. Such policies guide the traffic toward an optimized distribution and improved resource utilization, which results in the highest network profits and lowest blocking probability compared to other self-learning algorithms.
Bargaining based mechanism for sharing spectrum between radio access networks （RANs） belonging to multioperators is studied, to improve spectrum utilization efficiency and maximize network revenue. By introducing an intelligent agent, each RAN has the ability, which includes trading information exchanging, final decision making, and so on, to trade the spectrum with other RANs. The proposed inter-operator spectrum sharing mechanism is modeled as an infinite-horizon bargaining game with incomplete information, and the resulting bargaining game has unique sequential equilibrium. Consequently, the implementation is refined based on the analysis. Simulation results show that the proposed mechanism outperforms the conventional fixed spectrum management （FSM） method in network revenue, spectrum efficiency, and call blocking rate.
