DDI: A Novel Architecture for Joint Active User Detection and IoT Device Identification in Grant-Free NOMA Systems for 6G and Beyond Networks

Nonorthogonal multiple access (NOMA) with a grant-free access has received a lot of attention due to its support to massive machine-type communication (mMTC) devices. The devices in grant-free systems are allowed to transmit information without undergoing an authentication process. Therefore, in such systems, the base station needs to distinguish between active and nonactive devices, called the active user detection (AUD) process. This process is challenging as the active device needs to be detected from the received signals that are superimposed. Furthermore, the identification of the Internet of Things (IoT) devices from these signals also poses a great challenge, which could help allocate resources in future generation communication systems. Motivated from the aforementioned facts, this article proposes a device detection and identification (DDI) architecture for joint AUD and IoT device identification from the received superimposed signals. The architecture extracts the Fourier patterns as the representative feature vector, which results in an improved detection and identification process. Experimental results show that the architecture not only outperforms the conventional schemes and deep neural network-based approaches in terms of success probability for the AUD task but also yields lower computational complexity. The evaluation of the DDI architecture for IoT device identification problems has also been performed and compared to various shallow learning methods to prove its efficacy.

Automated summary

This article proposes a device detection and identification architecture for joint active user detection (AUD) and IoT device identification. The architecture improves the detection and identification process by extracting Fourier patterns as the representative feature vector. Experimental results demonstrate that this architecture outperforms conventional schemes and deep neural network-based approaches in terms of success probability for the AUD task, while also having lower computational complexity.