A Q-Learning Based Downlink Scheduling Algorithm for Multiple Traffics in 5G NR Systems

Nowadays, due to the rapid growth and popularity of IoT devices, current wireless networks suffer from the huge traffic produced by these devices. On the other hand, with the availably of 5G networks, people expect to have high quality streaming mechanisms. In a 5G network, data transmission between BS and UE is one of the biggest challenges for high-quality streaming since the bandwidth that a BS can provide is limited. To enlarge the bandwidth efficiency for a BS, in this study, we propose a downlink scheduling mechanism, named the Q-learning based Scheduling and Resource Allocation Scheme (QSRAS). This scheme dynamically adjusts radio resource allocation by referring to QoS parameters. Our simulation and analysis show that the system’s throughputs, fairness and average delays, all outperform those of state-of-the-art systems.