Dynamic resource allocation using reinforcement learning for LTE-U and WiFi in the unlicensed spectrum

Abstract

The growing demand for spectrum resources and the limited licensed spectrum have led to widespread concern about the coexistence of LTE and WiFi in the unlicensed spectrum. Since LTE and WiFi are two different systems, many solutions have been proposed to solve their coexistence problems, including the coexistence scheme based on blank subframe allocation. This paper presents a scheme that uses Q-learning algorithm to dynamically allocate blank subframes so that both LTE-U and WiFi system can successfully coexist. To support the proposed scheme, we introduce a new LTE-U frame structure, which can not only allocate blank subframes but also reduce the LTE delay. Simulation results show that the proposed approach can effectively improve the overall system performance in terms of the utilization of spectrum.