Contention Resolution in Wi-Fi 6-Enabled Internet of Things Based on Deep Learning

Internet of Things (IoT) is expected to vastly increase the number connected devices. As a result, multitude IoT devices transmit various information through wireless communication technology, such as Wi-Fi cellular mobile low-power wide-area network (LPWAN) technology. However, even latest technology still ready accommodate these large amounts data. Accurately setting contention window (CW) value significantly affects efficiency network. Unfortunately, standard collision resolution used by IEEE 802.11ax networks nonscalable; thus, it cannot maintain stable throughput for an increasing stations, when 6 has been designed improve performance in dense scenarios. To this end, we propose CW control strategy systems. This leverages deep learning search optimal configuration under different conditions. Our neural trained data generated from simulation system with some varying key parameters, e.g., nodes, short interframe space (SIFS), distributed (DIFS), and transmission rate. Numerical results demonstrated that our scheme could always find adjustment multiple adaptively perceiving channel competition status. The finalized model improved terms throughput, average delay, packet retransmission makes better adapted access