Artificial Intelligence Enabled NOMA Toward Next Generation Multiple Access
Xiaoxia Xu, Yuanwei Liu, Xidong Mu, Qimei Chen, Hao Jiang, Zhiguo Ding
Abstract
This article focuses on the application of artificial intelligence (AI) in non-orthogonal multiple access (NOMA), which aims to achieve automated, adaptive, and high-efficiency multi-user communications toward next generation multiple access (NGMA). First, the limitations of current scenario-specific multiple-antenna NOMA schemes are discussed, and the importance of AI for NGMA is highlighted. Then, to achieve the vision of NGMA, a novel cluster-free NOMA framework is proposed for providing scenario-adaptive NOMA communications, and several promising machine learning solutions are identified. To elaborate further, novel centralized and distributed machine learning paradigms are conceived for efficiently employing the proposed cluster-free NOMA framework in single-cell and multi-cell networks, where numerical results are provided to demonstrate the effectiveness. Furthermore, the interplays between the proposed cluster-free NOMA and emerging wireless techniques are presented. Finally, several open research issues of AI enabled NGMA are discussed.