Sony · 9.1.3
Specification support for CSI prediction ·
RAN1#120 · Source verification
the AI's delta
new
vs RAN1#119
Sony is a new contributor. They propose a framework allowing the UE to perform predictions for [N] time slots simultaneously to address scheduler uncertainty. They present options for slot selection (gNB-configured or UE-independent). They propose specifying either CSI-RS values with NMSE monitoring or channel matrices with NMSE/SGCS monitoring, emphasizing that ground truth measurements must be available in the prediction slot.
AI-synthesized from contributions · all text is paraphrased
Every position summary on this site is generated by an AI from the actual Tdoc contributions. This page shows you the exact source documents the AI read to produce the summary above, so you can verify it yourself. Click any Tdoc ID to view its detail page, or click "3gpp.org ↗" to read the original on the official 3GPP server.
Contributions at RAN1#120 · 1 doc
Specification Support for AI/ML CSI prediction
Position extracted by AI
Sony proposes that RAN1 specify a CSI prediction framework allowing the UE to carry out predictions for [N] prediction time slots simultaneously, addressing the uncertainty of gNB scheduler decisions regarding k0 and SLIV. They present two options for slot selection: gNB-configured candidate slots or UE-independent selection within an implied maximum time. Regarding model inputs, Sony proposes specifying either CSI-RS values with NMSE monitoring or channel matrices with NMSE/SGCS monitoring, emphasizing that ground truth measurements must be available in the prediction slot. They further propose that RAN1 specify the configuration of measurement resources for both model inference inputs and the related ground truths required for monitoring. Sony argues that model training inputs may need to include the prediction slot itself to ensure accurate temporal alignment.
Summary
Sony presents a technical contribution for 3GPP RAN1 regarding specification support for AI/ML-based CSI prediction in the NR Air Interface. The document identifies three key areas requiring standardization: the temporal framework for prediction slots, the specific form of channel data inputs/outputs, and the configuration of measurement resources for monitoring. It contains 1 observation and 3 proposals aimed at defining how UEs should predict CSI for future time slots and how network monitoring metrics should be applied.
Prior contributions at RAN1#119 · 1 doc · Nov 18, 2024
Further views on consistency issues in CSI prediction
Position extracted by AI
Sony advocates FOR comprehensive study of training-inference consistency issues in AI/ML CSI prediction models, pushing for systematic characterization and resolution of inconsistencies caused by UE capability differences, network configuration mismatches, and functionality configuration variations. They are advocating AGAINST proceeding with normative work without properly addressing these fundamental consistency challenges that can cause significant performance degradation.
Summary
Sony's contribution addresses consistency issues between AI/ML model training and inference for CSI prediction in NR systems, presenting 2 specific proposals for RAN1 study. The document identifies how differences in UE capabilities, network configurations, and model functionality configurations can cause performance degradation during inference.
How this was derived
The AI extracted the "position extracted" field above directly from each Tdoc during summarization.
For the delta summary at the top, the AI compared Sony's consolidated stance at RAN1#120
against their stance at RAN1#119 and classified the change as
new.
Always verify critical claims against the original Tdocs linked above.