A Learning-Based Coexistence Mechanism for LAA-LTE Based HetNets
Abstract
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.
Cite
@article{arxiv.1807.06754,
title = {A Learning-Based Coexistence Mechanism for LAA-LTE Based HetNets},
author = {Junjie Tan and Sa Xiao and Shiying Han and Ying-Chang Liang},
journal= {arXiv preprint arXiv:1807.06754},
year = {2018}
}
Comments
This paper has been presented in IEEE ICC 2018, Kansas City, MO, US. To appear in Proc. IEEE ICC'18