R1-2410248 discussion

Discussion on consistency of training / inference for AI/ML-based CSI prediction

From Panasonic
Status: not treated
WI: NR_AIML_air
Agenda: 9.1.3
Release: Rel-19
Source: 3gpp.org ↗

Summary

Panasonic presents their view on ensuring consistency between training and inference for AI/ML-based CSI prediction in NR, focusing on UE-side model development and proposing solutions for handling network-side additional conditions. The document contains 1 observation and 6 proposals addressing data collection, configuration identification, and information sharing mechanisms.

Position

Panasonic advocates FOR UE-side only training/development for CSI prediction models and proposes using configuration IDs instead of actual network configurations to preserve proprietary information. They push FOR reusing beam prediction conclusions and implementing data-transfer-based methods, while arguing AGAINST requiring RAN1 to handle data transfer mechanisms to UE-side servers, which should be left to RAN2 and SA working groups.

Key proposals

Your notes

Private to your account