Throughput Analysis of Multi-Channel TD-CSMA System and Reinforcement Learning
This paper generates a cognitive radio scenario based on non-persistent Carrier Sense Multiple Access (CSMA) and Time Division Multiple Access (TDMA) systems sharing a multi-channel wireless network. TDMA users are considered as primary users who can access the channel at any time, and non-persistent CSMA users are considered as secondary users who can share the channel when it is free. Then system performance is evaluated for a variety of proportions of non-persistent CSMA and TDMA traffic levels. Simulation results are presented and effect on throughput for different traffic ratio is shown. Further effect of reinforcement learning on system model is shown how throughput increases.