Identification of the cause of performance degradation of channel state information compression with history-dependent quantization
A mode-switching mechanism with a history-independent CSI encoder and history-dependent recurrent quantizer improves CSI compression efficiency by adapting to channel conditions, reducing errors, and maintaining accurate channel state information transmission.
WO2026114623A1PCT designated stage Publication Date: 2026-06-04NOKIA TECHNOLOGIES OY
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- NOKIA TECHNOLOGIES OY
- Filing Date
- 2025-11-07
- Publication Date
- 2026-06-04
AI Technical Summary
Technical Problem
Existing channel state information (CSI) compression methods suffer from performance degradation due to history-dependent quantization, leading to inefficiencies in channel estimation and communication systems.
Method used
Implement a mode-switching mechanism that utilizes a history-independent CSI encoder and a history-dependent recurrent quantizer, adjusting modes based on mean squared error thresholds to optimize quantization, and synchronize quantizer state machines for improved CSI compression.
Benefits of technology
Enhances CSI compression efficiency by adapting to varying channel conditions, reducing errors, and maintaining accurate channel state information transmission.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure EP2025082228_04062026_PF_FP_ABST
Abstract
An apparatus comprising means for: i) receiving, from a network node, at least one reference signal; ii) inputting target Channel State Information acquired from channel estimates based on the at least one reference signal into a history-independent CSI encoder to provide at least one latent vector; iii) using the at least one latent vector to provide an input into a history-dependent recurrent quantizer to provide a quantized output; iv) sending the quantized output to the network node; repeating steps i) to iv) to provide a plurality of inputs and a corresponding plurality of quantized outputs; sending the plurality of quantized outputs to the network node; sending, to the network node, a plurality of Squared Generalized Cosine Similarity, SGCS, scores and / or a plurality of Mean Squared Error, MSE, values between each of the inputs and the corresponding quantized outputs.
Need to check novelty before this filing date? Find Prior Art