Q-Learning Based Scheduling With Successive Interference Cancellation

Abstract

This work studies the problem of scheduling using Q-learning, which is a reinforcement learning algorithm, in a Successive Interference Cancellation (SIC) - enabled wireless ad hoc network. Distributed Q-learning algorithm tries to find the best schedule for the transmission of maximum number of packets in the presence of the SIC technique. Performance of the algorithm is compared to the case where Q-learning is applied to a wireless network without SIC. In addition to that, the number of successful transmissions of our algorithm is compared to the optimal solution with and without SIC. Numerical results reveal that Q-learning based scheduling with SIC shows an improved performance compared to Q-learning scheduling without SIC and the optimal solution without SIC. Also, Q-learning scheduling with SIC shows similar performance to optimal scheduling with SIC when transmitting a reasonable number of packets. Thus, combining Q-learning and the SIC technique in wireless ad hoc networks is an effective approach to increase the number of transmitted packets.