R1-2409583
discussion
Views on AI/ML based CSI prediction
From Samsung
Summary
Samsung presents observations and proposals for AI/ML-based CSI prediction in NR, highlighting the performance degradation when models are trained on mismatched TRP antenna settings and the need for network assistance to ensure training/inference consistency. The document contains 2 key observations regarding site-specific model benefits and TXRU mapping impacts, and 5 proposals covering network-side condition indication, data collection frameworks, and specific configurations for Type 1, 2, and 3 model monitoring.
Position
Samsung argues that site-specific AI/ML models significantly outperform generic models, particularly at large prediction horizons, and demonstrates that data distribution mismatch due to different TRP antenna settings (e.g., [2,8,2] vs [4,4,2] TXRU mapping) causes up to 77% performance loss. They propose considering TRP-related aspects for network-side additional condition indication to ensure consistency between training and inference, noting that TCI frameworks are insufficient due to flexible mapping changes over time. Samsung proposes studying specific data collection procedures, including distinguishing resources for CSI reporting versus internal data collection, and addressing the unfair advantage periodic measurements give to linear baselines like Kalman filters. For model monitoring, they propose detailed configurations for Type 1 (UE-side metric calculation with baseline/thresholds), Type 3 (CMR/MMR separation and window configuration), and Type 2 (network-side monitoring using enhanced Type II CSI for ground truth across multiple time instances) to handle complexity and performance verification.
Key proposals
- Proposal 1 (Sec 2.1): Consider TRP related aspects for network-side additional condition indication in CSI prediction use cases using UE-sided models to assist data collection and categorization.
- Proposal 2 (Sec 2.1.1): Consider aspects for data collection including the CSI measurement and reporting framework, as well as data collection procedure and priority.
- Proposal 3 (Sec 2.1.2): For Type 1 monitoring, consider configuration of CSI-RS resources for performance monitoring, baseline CSI and threshold configuration for UE metric calculation, and time-domain properties for monitoring outcome reporting.
- Proposal 4 (Sec 2.1.2): For Type 1 and Type 3 monitoring, consider configuration of CSI-RS resources for channel measurement resources (CMR) and monitoring measurement resources (MMR), their time-domain properties, prediction/monitoring windows, and restrictions on ports/power offset.
- Proposal 5 (Sec 2.1.2): For Type 2 monitoring, consider configuration of CSI-RS resources for performance monitoring, potential enhancements on Type II CSI for ground truth reporting across multiple time instances, and priority/CSI processing timeline.