Abstract
A mmWave-enabled integrated access backhaul (IAB) network for the 6G cellular Internet of Things (IoT) is necessary to handle the escalating wideband communications needs. A decreased sum rate and low successful transmission probability were the results of the mmWave-enabled IAB network's significant interference problems between access links and differentiated small-cell base stations' backhaul capacities. This article suggests the Q-learn JUP algorithm, which stands for joint user equipment association and power allocation. In order to establish the UA and PA problem, we first investigate how the SBSs-UE association and transmit power are related. Second, using the interference and backhaul burden as the state, UA and PA as the action, and the overall sum rate increment as the reward function of Q-learning, we determine the best joint optimization framework through off-line training. In order to lessen interference and backhaul load, a new backhaul capacity and cautious matching approach utility function has also been designed. Simulation results demonstrate that, in contrast to existing algorithms, the proposed algorithm may vastly enhance the network sum rate and successful transmission probability.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
