Content for TR 37.817 Word version: 17.0.0
4 General Framework
4.1 High-level Principles
4.2 Functional Framework
5 Use Cases and Solutions for Artificial Intelligence in RAN
5.1 Network Energy Saving
5.2 Load Balancing
5.3 Mobility Optimization
6 Conclusion
$ Change history
4 General Framework p. 6
5 Use Cases and Solutions for Artificial Intelligence in RAN p. 7
5.1 Network Energy Saving p. 7
5.1.1 Use case description p. 7
5.1.2 Solutions and standard impacts p. 8
5.1.2.1 Locations for AI/ML Model Training and AI/ML Model Inference p. 8
5.1.2.2 AI/ML Model Training at OAM and AI/ML Model Inference at NG-RAN p. 8
5.1.2.3 AI/ML Model Training and AI/ML Model Inference at NG-RAN p. 10
5.1.2.4 Input of AI/ML-based Network Energy Saving p. 11
5.1.2.5 Output of AI/ML-based Network Energy Saving p. 11
5.1.2.6 Feedback of AI/ML-based Network Energy Saving p. 12
5.1.2.7 Standard Impact p. 12
5.2 Load Balancing p. 12
5.2.1 Use case description p. 12
5.2.2 Solutions and standard impacts p. 13
5.2.2.1 Locations for AI/ML Model Training and AI/ML Model Inference p. 13
5.2.2.2 AI/ML Model Training in OAM and AI/ML Model Inference in a NG-RAN node p. 13
5.2.2.3 AI/ML Model Training and AI/ML Model Inference in a NG-RAN node p. 14
5.2.2.4 Input of AI/ML-based Load Balancing p. 15
5.2.2.5 Output of AI/ML-based Load Balancing p. 16
5.2.2.6 Feedback of AI/ML-based Load Balancing p. 16
5.2.2.7 Standard impact p. 16
5.3 Mobility Optimization p. 17
5.3.1 Use case description p. 17
5.3.2 Solutions and standard impacts p. 18
5.3.2.1 Locations for AI/ML Model Training and AI/ML Model Inference p. 18
5.3.2.2 AI/ML Model Training in OAM and AI/ML Model Inference in NG-RAN node p. 19
5.3.2.3 AI/ML Model Training and AI/ML Model Inference in a NG-RAN node p. 20
5.3.2.4 Input of AI/ML-based Mobility Optimization p. 21
5.3.2.5 Output of AI/ML-based Mobility Optimization p. 21
5.3.2.6 Feedback of AI/ML-based Mobility Optimization p. 22
5.3.2.7 Standard impact p. 22
6 Conclusion p. 22
$ Change history p. 23
