Learning-Based Channel Selection of VDSA Networks in Shared TV Whitespace

In this paper, we propose a reinforcement learning-based approach for enabling vehicles to make intelligent channel selection choices across TV whitespace spectrum. In order for vehicle communication networks to dynamically access TV whitespace in a secondary manner, it is imperative that these communication systems be capable of coexisting with other types of secondary wireless networks operating within the same frequency range. Consequently, we first propose a TV whitespace channel sharing scheme that would facilitate the coexistence between WLAN, WRAN, and vehicular communication networks. Using the channel utilization variations observed by a collection of mobile vehicular communication systems, we then devised a reinforcement learning-based adaptive channel selection algorithm that employs channel utilization sensing in order to reinforce the decisions made by the vehicular communication system. Moreover, the parameters of the proposed learning approach are adaptively tuned in order to achieve better adaptation to a particular environment. A computer emulation environment composed of actual real-world sensing measurement data and a simulated TV whitespace network is created in order to accurately model the characteristics of future wireless environment, as well as to test the proposed learning-based channel access approach. Experimental results show a significant performance improvement with respect to vehicle communication.