QX-MAC: Improving QoS and Energy Performance of IoT-based WSNs using Q-Learning

Low-power wireless sensor networks (WSNs) play a vital role in different IoT applications. In WSNs, MAC protocols are of paramount importance to improve energy efficiency and quality of service (QoS). This paper proposes a traffic-adaptive, energy-efficient MAC protocol, which combines the Q-Learning algorithm and the more bit scheme to provide low energy consumption together with better QoS without introducing additional overhead to the network. Simulation results show that, on average, QX-MAC offers an energy savings of 23.23% and 79.91% over the X-MAC and the B-MAC protocols respectively. QX-MAC can carry up to 92.78% of traffic, whilst X-MAC and B-MAC can transfer a maximum of 88.5%, and 67.3% traffic respectively. Furthermore, QX-MAC reduces the mean end-to-end packet delivery delay, even in the presence of high traffic loads, and improves the throughput up to 41.67% and 65.05% compared to X-MAC and B-MAC, respectively.