Non Orthogonal Multiple Access
Non-orthogonal multiple access (NOMA) is a multiple access scheme allowing multiple users to share the same time, frequency, and/or spatial resources, aiming to improve spectral efficiency and connectivity compared to orthogonal methods. Current research heavily focuses on mitigating inter-user interference through techniques like successive interference cancellation, interference-aware modulation, and rate-splitting multiple access, often employing deep learning models (e.g., autoencoders, deep reinforcement learning) for optimal resource allocation and signal processing. NOMA's potential impact lies in enhancing the performance of various applications, including federated learning, machine-type communication, and beyond 5G/6G networks, by enabling more efficient use of scarce wireless resources.