A QoS Fair Assurance Scheduling Algorithm Based on Q-Learning

Packet scheduling algorithm is one of the core technologies to guarantee the QoS requirements of wireless sensor networks, but traditional scheduling algorithms, including DWRR(Deficit Weighted Round-Robin) and other fair scheduling algorithms, can not effectively guarantee the delay requirements of non-real-time traffic. To solve the above problems, this paper proposes a QoS fairness guarantee scheduling algorithm based on Q-learning, which aims to balance the relationship between fairness and delay and effectively guarantee the QoS requirements of different traffic flows. Simulation results show that compared with DWRR algorithm, the scheduling algorithm proposed in this paper can effectively guarantee the delay requirements of traffic with different priorities, and balance the queue delay and fairness well.