Artificial Intelligence for Wireless Physical-Layer Technologies (AI4PHY): A Comprehensive Survey

• DOI: 10.1109/tccn.2024.3382973
• Publication Date: 2024-03-29T18:24:28Z
• Authors: Neng Ye; Sirui Miao; Jianxiong Pan; Qiaolin Ouyang; Xiangming Li; Xiaolin Hou

Artificial intelligence (AI) has become a promising solution for meeting the stringent performance requirements on wireless physical layer in sixth-generation (6G) communication systems, due to its strong ability learn complex model, achieve end-to-end optimization and adapt dynamic environments. This article provides comprehensive review with respect artificial physical-layer technologies (AI4PHY). Specifically, we first analyze characteristics of classic AI techniques their potential applications technologies. Then study AI-enhanced designs from point view basic modules, including coding, modulation, multiple access, multiple-input-multiple-output (MIMO), channel estimation, as well relay transmission. The standardization progress AI4PHY 3GPP is also discussed. Based current researches, propose some future research directions inspire encourage further exploration.