Random access channel (RACH) procedure is critical to support a multitude of devices transmitting small data payloads while ensuring low-latency access. In 3GPP Release 16, a two-step RACH is proposed to alleviate signaling overhead and access latency. While benefits are noticeable, collisions still persist. In this article, we propose a novel nonorthogonal multiple access (NOMA)-enhanced two-step RACH scheme (NOMA-RACH) that jointly leverages the benefits of access class barring (ACB), two-step RACH, and NOMA random access (NOMA-RA) to further enhance the performance. We conduct a holistic study that accounts for entire access latency. The scheme optimizes NOMA access probabilities, utilizes an adjustable barring mechanism for delay-sensitive devices, and identifies the optimal barring rate for low latency. We develop a Markov chain model to analyze NOMA access and derive the optimal access probabilities and throughput of NOMA blocks. To cope with the practical scenarios with constantly changing user equipment (UE) traffic, we propose a deep contextual multiarmed bandit (DCMAB) model that optimizes the NOMA throughput and dynamically adjusts the barring rate based on the observable channel feedback. Our simulation results demonstrate that the DCMAB model performs better than benchmark schemes and remains close to the optimal latency confirming the effectiveness of our proposed scheme under changing UE traffic.

Spectrum sensing is a key technique for dynamically detecting available spectrum in cognitive radio networks (CRNs), which can introduce high resource demands such as energy consumption. In this paper, we propose a novel cluster-based cooperative sensing-after-prediction scheme where a learning cluster and a sensing cluster are jointly considered to perform cooperative prediction and sensing efficiently. This enables us to skip the complex physical sensing to reduce the demands when the spectrum availability can be simply predicted using cooperative prediction. Furthermore, the clustering is flexible, in order to meet different performance requirements. We then formulate two optimization problems to minimize the total number of users in the two clusters or to minimize the total energy consumption, to meet different performance requirements, while in both cases guaranteeing the system accuracy requirement and individual energy constraints. To solve the two challenging integer programming problems, the unconstrained problems are mathematically solved first by relaxing the integer variable and fixing the cluster size. Such analytical solutions serve as a foundation for solving the original optimization problems. Then, two low-complexity search algorithms are proposed to achieve the global optimum, as they can obtain the same performance with exhaustive search. Simulation results validate the accuracy of the derived analytical expressions and demonstrate that the total energy consumption and the number of users contributing to learning and sensing can be greatly reduced by applying our optimized clustered sensing-after-prediction scheme.