A Learning-Based Coexistence Mechanism for LAA-LTE Based HetNets

License-assisted access LTE (LAA-LTE) has been proposed to deal with the intense contradiction between tremendous mobile traffic demands and crowded licensed spectrums. In this paper, we investigate the coexistence mechanism for LAA-LTE based heterogenous networks (HetNets). A joint resource allocation and network access problem is considered to maximize the normalized throughput of the unlicensed band while guaranteeing the quality-of-service requirements of incumbent WiFi users. A two-level learning-based framework is proposed to solve the problem by decomposing it into two subproblems. In the master level, a Q-learning based method is developed for the LAA-LTE system to determine the proper transmission time. In the slave one, a game-theory based learning method is adopted by each user to autonomously perform network access. Simulation results demonstrate the effectiveness of the proposed solution.

[1]  Geoffrey Ye Li,et al.  LBT-Based Adaptive Channel Access for LTE-U Systems , 2016, IEEE Transactions on Wireless Communications.

[2]  Ying-Chang Liang,et al.  Licensed-Assisted Access for LTE in Unlicensed Spectrum: A MAC Protocol Design , 2016, IEEE Journal on Selected Areas in Communications.

[3]  Youngnam Han,et al.  Coexistence of Wi-Fi and Cellular With Listen-Before-Talk in Unlicensed Spectrum , 2016, IEEE Communications Letters.

[4]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[5]  Mehul Motani,et al.  A Two-Level MAC Protocol Strategy for Opportunistic Spectrum Access in Cognitive Radio Networks , 2011, IEEE Transactions on Vehicular Technology.

[6]  Kwang-Cheng Chen,et al.  Resource-Optimal Licensed-Assisted Access in Heterogeneous Cloud Radio Access Networks With Heterogeneous Carrier Communications , 2016, IEEE Transactions on Vehicular Technology.

[7]  Yong Huat Chew,et al.  Potential Game Theory: Applications in Radio Resource Allocation , 2016 .

[8]  Jie Zhang,et al.  Coexistence of LTE-LAA and Wi-Fi on 5 GHz With Corresponding Deployment Scenarios: A Survey , 2017, IEEE Communications Surveys & Tutorials.

[9]  V. V. Phansalkar,et al.  Decentralized Learning of Nash Equilibria in Multi-Person Stochastic Games With Incomplete Information , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[10]  Daniel Kudenko,et al.  Reinforcement learning of coordination in cooperative multi-agent systems , 2002, AAAI/IAAI.