Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI/ML for mobile networks: Current status in Rel. 19 and challenges ahead

Yuan Gao, Xinyi Wu, Jun Jiang, Bintao Hu, Jianbo Du, Qiang Ye, Shunqing Zhang, F. Richard Yu, Shugong Xu

Abstract

The transformative power of artificial intelligence (AI) and machine learning (ML) is recognized as a key enabler for sixth generation (6G) mobile networks by both academia and industry. Research on AI/ML in mobile networks has been ongoing for years, and the 3rd generation partnership project (3GPP) launched standardization efforts to integrate AI into mobile networks. However, a comprehensive review of the current status and challenges of the standardization of AI/ML for mobile networks is still missing. To this end, we provided a comprehensive review of the standardization efforts by 3GPP on AI/ML for mobile networks. This includes an overview of the general AI/ML framework, representative use cases (i.e., CSI feedback, beam management and positioning), and corresponding evaluation matrices. We emphasized the key research challenges on dataset preparation, generalization evaluation and baseline AI/ML models selection. Using CSI feedback as a case study, given the test dataset 2, we demonstrated that the pre-training-fine-tuning paradigm (i.e., pre-training using dataset 1 and fine-tuning using dataset 2) outperforms training on dataset 2. Moreover, we observed the highest performance enhancements in Transformer-based models through fine-tuning, showing its great generalization potential at large floating-point operations (FLOPs). Finally, we outlined future research directions for the application of AI/ML in mobile networks.

AI/ML for mobile networks: Current status in Rel. 19 and challenges ahead

Abstract

The transformative power of artificial intelligence (AI) and machine learning (ML) is recognized as a key enabler for sixth generation (6G) mobile networks by both academia and industry. Research on AI/ML in mobile networks has been ongoing for years, and the 3rd generation partnership project (3GPP) launched standardization efforts to integrate AI into mobile networks. However, a comprehensive review of the current status and challenges of the standardization of AI/ML for mobile networks is still missing. To this end, we provided a comprehensive review of the standardization efforts by 3GPP on AI/ML for mobile networks. This includes an overview of the general AI/ML framework, representative use cases (i.e., CSI feedback, beam management and positioning), and corresponding evaluation matrices. We emphasized the key research challenges on dataset preparation, generalization evaluation and baseline AI/ML models selection. Using CSI feedback as a case study, given the test dataset 2, we demonstrated that the pre-training-fine-tuning paradigm (i.e., pre-training using dataset 1 and fine-tuning using dataset 2) outperforms training on dataset 2. Moreover, we observed the highest performance enhancements in Transformer-based models through fine-tuning, showing its great generalization potential at large floating-point operations (FLOPs). Finally, we outlined future research directions for the application of AI/ML in mobile networks.
Paper Structure (26 sections, 3 figures, 2 tables)

This paper contains 26 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. A Holistic Picture of AI/ML in 3GPP
  3. General AI/ML framework
  4. LCM of AI Models
  5. Collaboration between the network and the UE
  6. Use Cases
  7. CSI Feedback
  8. Beam Management
  9. Positioning
  10. Evaluations
  11. Common KPIs
  12. Use Case-Specific KPIs
  13. Key Research Problems: Opportunities and Challenges
  14. Dataset Preparation
  15. Parameter settings of 3GPP
  16. ...and 11 more sections

Figures (3)

  • Figure 1: The architecture of LCM of AI/ML models at UE and NW sides, and the collaboration between UE and NW side models. *: 3GPP launched the standardization of application of AI/ML in physical layer, higher layers will be considered in the subsequent Release.
  • Figure 2: Outdoor and indoor scenarios to generate CSI data using DeepMIMO.
  • Figure 3: Comparisons of various models for CSI feedback, including CsiNetguo2022ai, MNetyu2023m, DCRNetTangDRCNet and TransNetTransNet in terms of performance, generalization and computational complexity. Indoor (outdoor) Case 1 indicates that the indoor (outdoor) dataset is used for both training and test. Indoor (outdoor) Case 2 indicates that the models are trained using indoor (outdoor) dataset and tested using outdoor (indoor) dataset. Indoor (outdoor) Case 3 indicates that models are trained using indoor (outdoor) dataset, fine-tuned and tested using outdoor (indoor) dataset.