On the Combination of AI and Wireless Technologies: 3GPP Standardization Progress
Chen Sun, Tao Cui, Wenqi Zhang, Yingshuang Bai, Shuo Wang, Haojin Li
TL;DR
The paper surveys 3GPP progress at the intersection of AI and wireless technologies, emphasizing AI model transfer (AMMT) and Beam Management (BM) as focal points for standardization. It highlights how Network Data Analytics Function (NWDAF), Federated Learning (FL), and Device-to-Device (D2D) collaboration are being considered to enable distributed AI across gNBs and UEs, while AI-driven BM and positioning aim to reduce measurement overhead and improve accuracy. Key contributions include detailing Release 18/19 milestones, the challenges of AI model management within RAN, and the potential of knowledge distillation and D2D-aided FL to address resource constraints. The work underscores the importance of translating academic innovations into robust, scalable standards that can support reliable AI/ML deployment over 5G/6G networks and guide future research and development.
Abstract
Combing Artificial Intelligence (AI) and wireless communication technologies has become one of the major technologies trends towards 2030. This includes using AI to improve the efficiency of the wireless transmission and supporting AI deployment with wireless networks. In this article, the latest progress of the Third Generation Partnership Project (3GPP) standards development is introduced. Concentrating on AI model distributed transfer and AI for Beam Management (BM) with wireless network, we introduce the latest studies and explain how the existing standards should be modified to incorporate the results from academia.