A relay selection scheme using Q-learning algorithm in cooperative wireless communications

As a scheme to efficiently reduce the effects of multipath fading in next generation wireless communication systems, cooperative communication systems have recently come into the spotlight. Since these cooperative communication systems use cooperative relays with diverse fading coefficients to transmit information, having all relays participate in cooperative communication may result in unnecessary waste of resources, and thus relay selection schemes are required to efficiently use wireless resources. In this paper, we propose an efficient relay selection scheme through self-learning in cooperative wireless networks using Q-learning algorithm. In this scheme, we define states, actions and a reward to achieve good SER (Symbol Error Rate) performance, while selecting a small number of cooperative relays. When these parameters are well-defined, we can obtain good performance. The simulation results show that, compared to a scheme that obtains optimum numbers of relays through a mathematical analysis, the proposed scheme uses resources efficiently by using smaller numbers of relays with comparable SER performance. In particular, whereas the number of cooperative relays linearly increases as the number of relays that can participate increases in the case of the scheme modeled by a mathematical analysis, the proposed scheme selects 2.5 relays on average for cooperative communication. According to these simulation results, the proposed scheme can be considered as a good attempt for future communication.