Search

EP-4740335-A1 - METHODS AND APPARATUSES FOR VARIABLE LENGTH CHANNEL STATE INFORMATION FEEDBACK OBTAINED THROUGH COMPRESSION WITH AN ENCODER AND OUTPUT MASKS

EP4740335A1EP 4740335 A1EP4740335 A1EP 4740335A1EP-4740335-A1

Abstract

In an embodiment, a method, implemented in a WTRU for CSI comprises: receiving, from a network node, a first message comprising information for compression configuration indicating AIML model to generate a CSI feedback, wherein the AIML model outputs a latent vector with N parts that satisfy a preconfigured property; receiving, from the network node, a second message comprising information indicating a masking configuration and a post processing configuration; generating a latent vector with N parts; determining k parts out of the N parts of the latent vector for CSI feedback; performing post processing for the k parts according to the preconfigured association between each of the k parts and the corresponding post processing configuration; and transmitting, to the network node, a third message comprising the CSI feedback with k selected parts of the latent vector.

Inventors

  • Malhotra, Akshay
  • NARAYANAN THANGARAJ, Yugeswar Deenoo
  • IBRAHIM, Mohamed Salah
  • HAMIDI-RAD, SHAHAB
  • DINESHA, Ujwal

Assignees

  • InterDigital Patent Holdings, Inc.

Dates

Publication Date
20260513
Application Date
20240701

Claims (20)

  1. 1. A method, implemented in a wireless transmit/receive unit (WTRU) the method comprising: receiving, from a network node, at least a first message comprising first information for compression configuration indicating a model of an encoder to generate a channel state information (CSI) feedback, said first message further comprising second information indicating a plurality of masking configurations and a plurality of post processing configurations; selecting one masking configuration from the plurality of masking configurations; generating, by the encoder, a vector comprising a set of parts based on the selected masking configuration; determining a first subset of parts out of the set of parts of the vector; performing at least one or more post processing of the first subset of parts using at least one or more post processing configurations; wherein each post processing configuration of the at least one or more post processing configurations is associated with each part of the first subset of parts; generating a CSI feedback based on the post processed first subset of parts; and transmitting, to the network node, a second message comprising third information indicating any of the generated CSI feedback, the determined first subset of parts of the vector, and the selected masking configuration.
  2. 2. The method of claim 1, wherein the selection of one masking configuration is based on any of uplink (UL) resources associated with CSI feedback, prioritization rules for CSI feedback, compression factor for CSI feedback, and reconstruction factor for CSI feedback.
  3. 3. The method of any of the claims 1 and 2, wherein the at least one or more post processing configurations indicate an association between each part of the set of parts and a post processing configuration corresponding to each part of the set of parts.
  4. 4. The method of any of the claims 1 and 2, wherein performing at least one or more post processing of the first subset of parts comprises performing quantization on each part of the first subset of parts and performing error protection and redundancy for each part of the first subset of parts.
  5. 5. The method of claim 4, wherein performing quantization on each part of the first subset of parts comprises a first quantization of a first part of the first subset of parts and a second quantization of a second part of the first subset of parts.
  6. 6. The method of any of the preceding claims, wherein post processing of the first subset of parts comprises using a first encoding configuration for a first part of the first subset of parts and using a second encoding configuration for a second part of the first subset of parts.
  7. 7. The method of any of the preceding claims, wherein the masking configuration includes any of a masking type, a masking domain, a mask length, and mask sets.
  8. 8. The method of any of the preceding claims, wherein determining the first subset of parts comprises selecting the subset of parts out of the set of parts based on UL resources.
  9. 9. The method of any of the preceding claims, wherein the set of parts satisfy preconfigured one or more properties.
  10. 10. The method of claim 9, wherein the preconfigured one or more properties include any of an additive property, an ordering property, and associated performance threshold preconfigured for each part of the set of parts.
  11. 11. The method of any of the preceding claims, wherein the vector is a latent vector.
  12. 12. A wireless transmit/receive unit (WTRU) comprising a processor, a transmitter, a receiver and memory, configured to: receive, from a network node, at least a first message comprising first information for compression configuration indicating a model of an encoder to generate a channel state information (CSI) feedback, said first message further comprising second information indicating a plurality of masking configurations and a plurality of post processing configurations; select one masking configuration from the plurality of masking configurations; generate, by the encoder, a vector comprising a set of parts based on the selected masking configuration; determine a first subset of parts out of the set of parts of the vector; perform at least one or more post processing of the first subset of parts using at least one or more post processing configurations; wherein each post processing configuration of the at least one or more post processing configurations is associated with each part of the first subset of parts; generate a CSI feedback based on the post processed first subset of parts; and transmit, to the network node, a second message comprising third information indicating any of the generated CSI feedback, the determined first subset of parts of the vector, and the selected masking configuration.
  13. 13. The WTRU of claim 12, wherein the selection of one masking configuration is based on any of uplink (UL) resources associated with CSI feedback, prioritization rules for CSI feedback, compression factor for CSI feedback, and reconstruction factor for CSI feedback.
  14. 14. The WTRU of any of the claims 12 and 13, wherein the at least one or more post processing configurations indicate an association between each part of the set of parts and a post processing configuration corresponding to each part of the set of parts.
  15. 15. The WTRU of any of the claims 12 and 13, wherein performing at least one or more post processing of the first subset of parts comprises performing quantization on each part of the first subset of parts and performing error protection and redundancy for each part of the first subset of parts.
  16. 16. The WTRU of claim 12, wherein performing quantization on each part of the first subset of parts comprises a first quantization of a first part of the first subset of parts and a second quantization of a second part of the first subset of parts.
  17. 17. The WTRU of any of the claims 12 to 16, wherein post processing of the first subset of parts comprises using a first encoding configuration for a first part of the first subset of parts and using a second encoding configuration for a second part of the first subset of parts.
  18. 18. The WTRU of any of the claims 12 to 17, wherein the masking configuration includes any of a masking type, a masking domain, a mask length, and mask sets.
  19. 19. The WTRU of any of the claims 12 to 18, wherein determining the first subset of parts comprises selecting the subset of parts out of the set of parts based on UL resources.
  20. 20. The WTRU of any of the claims 12 to 19, wherein the set of parts satisfy preconfigured one or more properties.

Description

METHODS AND APPARATUSES FOR VARIABLE LENGTH CHANNEL STATE INFORMATION FEEDBACK OBTAINED THROUGH COMPRESSION WITH AN ENCODER AND OUTPUT MASKS CROSS-REFERENCE TO RELATED APPLICATIONS [0001] The present application claims the benefit of US Provisional Patent Application No. 63/525,413 filed July 7, 2023, which is incorporated herein by reference. FIELD OF THE INVENTION [0002] The present disclosure is generally directed to the fields of communications, software and encoding, including, for example, to methods, architectures, apparatuses, systems directed to variable rate compression and variable length feedback. More particularly, the present disclosure relates to methods for a user equipment to enable variable length feedback for resource constrained transmission. BACKGROUND [0003] In channel state information (CSI) autoencoder setup, the output of an encoder may be unstructured. For example, all the elements of latent vector may be equally important from a reconstruction perspective. This may lead to inflexibility for adapting the compressed CSI, e.g., to variable payload size, inefficient quantization, inefficient error protection. [0004] There is a need to improve methods for CSI compression. SUMMARY [0005] In an embodiment, a method, implemented in a wireless transmit/receive unit, WTRU, for compressing channel state information, CSI, may comprise a step of receiving, from a network node, a first message comprising information for compression configuration indicating artificial intelligence/machine learning, AIML, model to generate a CSI feedback, wherein the AIML model outputs a latent vector with N parts that satisfy a preconfigured property. The method may further comprise a step of receiving, from the network node, a second message comprising information indicating a masking configuration and a post processing configuration. The method may further comprise a step of generating a latent vector with N parts. The method may further comprise a step of determining k parts out of the N parts of the latent vector for CSI feedback. The method may further comprise a step of performing post processing for the k parts according to the preconfigured association between each of the k parts and the corresponding post processing configuration; and a step of transmitting, to the network node, a third message comprising the CSI feedback with k selected parts of the latent vector. [0006] In an embodiment, a method, implemented in a wireless transmit/receive unit (WTRU) for compressing channel state information (CSI), may comprise a step of receiving, from a network node, a first message comprising information for compression configuration indicating artificial intelligence/machine learning, AIML, model to generate CSI feedback, wherein the AIML model outputs a latent vector with N parts that satisfy a preconfigured property. The method may further comprise a step of receiving, from the network node, a second message comprising information indicating a masking configuration including a base mask and additional masks. The method may further comprise a step of generating a latent vector with N parts. The method may further comprise a step of determining k parts of the latent vector to be included in a first CSI report by applying the base mask on the latent vector. The method may further comprise a step of receiving an aperiodic CSI trigger including an implicit/explicit indication of a linked periodic CSI report and an additional mask. The method may further comprise a step of determining m parts of the latent vector to be included in a second CSI report by applying the addition al mask. On condition that the aperiodic CSI reporting resource may collide with the linked periodic CSI reporting resource, and on condition that the aperiodic CSI reporting resource size may fit with the m parts, the method may comprise a step of transmitting, to the network node, the m parts associated with the linked CSI report in a single CSI report. [0007] In another embodiment, a method, implemented in a wireless transmit/receive unit (WTRU) the method may comprise a step of receiving, from a network node, at least a first message comprising first information for compression configuration indicating a model of an encoder to generate a channel state information (CSI) feedback, said first message further comprising second information indicating a plurality of masking configurations and a plurality of post processing configurations. The method may further comprise a step of selecting one masking configuration from the plurality of masking configurations. The method may further comprise a step of generating, by the encoder, a vector comprising a set of parts based on the selected masking configuration. The method may further comprise a step of determining a first subset of parts out of the set of parts of the vector. The method may further comprise a step of performing at least one or more post processing of the first subset of parts using a