Q-Learning Based Scheduling With Successive Interference Cancellation

Abstract

This work studies the problem of scheduling using Q-learning, which is a reinforcement learning algorithm, in a Successive Interference Cancellation (SIC)-enabled wireless ad hoc network. Distributed Q-learning algorithm tries to find the best schedule for the transmission of maximum number of packets in the presence of the SIC technique. Performance of the algorithm is compared to the case where Q-learning is applied to a wireless network without SIC. In addition to that, the number of successful transmissions of our algorithm is compared to the optimal solution with and without SIC. Numerical results reveal that Q-learning based scheduling with SIC shows an improved performance compared to Q-learning scheduling without SIC and the optimal solution without SIC. Also, Q-learning scheduling with SIC shows similar performance to optimal scheduling with SIC when transmitting a reasonable number of packets. Thus, combining Q-learning and the SIC technique in wireless ad hoc networks is an effective approach to increase the number of transmitted packets.

A Comprehensive Review on Artificial Intelligence/Machine Learning Algorithms for Empowering the Future IoT Toward 6G Era

“…Offloading performance analysis as a function of data, number of servers and available bandwidth [132] Data offloading framework Analysis of total payment for service request and remaining data after expiration of transmission time Q-learning [133] Routing protocol QoS analysis with the proposed, VBF, QELAR, MU-RAO schemes [134] Resource management schemes Learning the behavior of the primary user and provide good channel to the secondary user with satisfactory QoS [135] Spectrum access Throughput, power efficiency and collision probability analysis [136] Random access approach Analysis of system throughput, effect of clustering and cluster size and frame size adaptation [137] Packet transmission scheduling algorithm Analysis of the number of packet transmission with and without SIC [138] Cluster formation in CR-ad hoc networks Network lifetime extension, reliable service provision and interference mitigation [14] Power control scheme for wireless energy harvesting…”

“…The Q-learning assisted random access approach for clustering-based and (Non-orthogonal multiple access) NOMA-based mMTC, proposed in [136], uses pre-clustering mechanism to allow the network devices to operate with small Q-table which accelerates the convergence mechanism of the Q-learning algorithm. Packet transmission scheduling mechanism in wireless ad hoc networks with SIC is studied in [137] which uses Q-learning approach. Cluster formation in CR based ad hoc network, studied in [138], uses the Qvalues by considering channel quality, energy and condition of the network nodes' conditions.…”

Wi-Fi Meets ML: A Survey on Improving IEEE 802.11 Performance With Machine Learning

“…Similarly, research on applying Q-learning to interference cancellation in ad hoc networks also does not consider Wi-Fi [297].…”

D2D Assisted Q-Learning Random Access for NOMA-Based MTC Networks

“…However, using the BLER as a reward can make the feedback longer; while it is not clear how in practice, one could perfectly estimate the BLER of the devices in an interference scenario. In [23], the authors also introduce a Q-Learning scheduling method with SIC. However, they do so in an ad-hoc scenario.…”