Recurrent Neural Network Based RACH Scheme Minimizing Collisions in 5G and Beyond Networks

Abstract

Limited preambles in 5G New Radio (NR) can be a bottleneck on the performance of network access procedures. Due to the limited number of preambles, there is a non-zero probability that two mobile User Equipments (UEs) selecting same preamble signatures leading to collisions. Consequently, the base stations (gNBs) in 5G Radio Access Network (RAN) are unable to send a response to the UEs. Furthermore, with the increase in the number of cellular UEs and Machine Type Communication (MTC) devices, the probability of such preamble collisions further increases, thereby leading to reattempts by UEs. This in turn, results in increased latency and reduced channel utilization. In order to reduce contention during preamble access, we propose to use deep learning based models to design a Random Access Channel (RACH) procedure that predicts the incoming connection requests in advance and proactively allocates uplink resources to UEs. We have used Recurrent Neural Network (RNN) which is provided with the history of connection requests to predict UEs which are going to participate in contention based RACH procedure. Finally, we propose a RNN based RACH scheme where the gNB uses RNN model along with the standard RACH process to reduce preamble collisions. On doing extensive simulations, it is observed that there is a significant reduction in the number of collisions when the proposed scheme is employed in a dense user scenario thereby proving the efficacy of the proposed scheme in enabling massive access of users to 5G network.