Search

US-20260129473-A1 - INTERFERENCE PREDICTION FOR AIML BM

US20260129473A1US 20260129473 A1US20260129473 A1US 20260129473A1US-20260129473-A1

Abstract

A wireless transmit/receive unit (WTRU) may be configured with configuration information for interference prediction. The configuration information may indicate one or more resources for interference measurement, and one or more resources for interference prediction. The WTRU may determine, based on the configuration information, to perform interference measurements for one or more of the resources indicated as being for interference measurement. The WTRU may determine interference predictions based at least in part on the interference measurements. The interference predictions may be made using an artificial intelligence or machine learning (AIML) model. The WTRU may create and send a report indicating a result of the interference predictions.

Inventors

  • Young Woo Kwak
  • Yugeswar Deenoo Narayanan Thangaraj
  • Haseeb Ur Rehman

Assignees

  • INTERDIGITAL PATENT HOLDINGS, INC.

Dates

Publication Date
20260507
Application Date
20241104

Claims (20)

  1. 1 . A wireless transmit/receive unit (WTRU) comprising: a processor, wherein the processor is configured to: receive configuration information for interference prediction, wherein the configuration information comprises an indication of a first set of reference signal (RS) resources and a second set of RS resources, wherein the first set of RS resources is for interference measurement, and wherein the second set of RS resources is for interference prediction; determine interference measurements for one or more RSs indicated by the first set of RS resources; determine an interference prediction for a RS resource in the second set of RS resources based on the interference measurements; and send an interference prediction report, the interference prediction report indicating the interference prediction.
  2. 2 . The WTRU of claim 1 , wherein the processor is configured to determine the interference prediction using an artificial intelligence or machine learning (AIML) model, wherein the interference measurements are used as input to the AIML model.
  3. 3 . The WTRU of claim 1 , wherein the interference measurements are based on a reference signal received power (RSRP) measurement, a received signal strength indicator (RSSI) measurement, or a signal to noise and interference ratio (SINR) measurement.
  4. 4 . The WTRU of claim 1 , wherein the one or more RSs indicated by the first set of RS resources are channel state information RSs for interference (CSI-IMs) or non-zero power channel state information RSs (NZP CSI-RSs) for interference.
  5. 5 . The WTRU of claim 1 , wherein the processor is configured to determine an interference prediction for each RS resource in the second set of RS resources.
  6. 6 . The WTRU of claim 5 , wherein the interference prediction report includes all of the interference predictions determined for each RS resource in the second set of RS resources.
  7. 7 . The WTRU of claim 5 , wherein the interference prediction report includes a subset of the interference predictions determined for each RS resource in the second set of RS resources.
  8. 8 . The WTRU of claim 7 , wherein the subset of the interference predictions included in the interference prediction report comprises a quantity, L, of interference predictions, wherein the interference predictions comprised in the report are the best L interference predictions or the worst L interference predictions.
  9. 9 . The WTRU of claim 7 , wherein the processor is configured to determine the subset of interference predictions to be included in the interference prediction report based on a comparison of the interference predictions determined for each RS resource in the second set of RS resources with a threshold value for reporting.
  10. 10 . The WTRU of claim 1 , wherein the interference prediction is in decibels (dB).
  11. 11 . A method for use by a wireless transmit/receive unit (WTRU), the method comprising: receiving configuration information for interference prediction, wherein the configuration information comprises an indication of a first set of reference signal (RS) resources and a second set of RS resources, wherein the first set of RS resources is for interference measurement, and wherein the second set of RS resources is for interference prediction; determining interference measurements for one or more RSs indicated by the first set of RS resources; determining an interference prediction for a RS resource in the second set of RS resources based on the interference measurements; and sending an interference prediction report, the interference prediction report indicating the interference prediction.
  12. 12 . The method of claim 11 , further comprising determining the interference prediction using an artificial intelligence or machine learning (AIML) model, wherein the interference measurements are used as input to the AIML model.
  13. 13 . The method of claim 11 , wherein the interference measurements are based on a reference signal received power (RSRP) measurement, a received signal strength indicator (RSSI) measurement, or a signal to noise and interference ratio (SINR) measurement.
  14. 14 . The method of claim 11 , wherein the one or more RSs indicated by the first set of RS resources are channel state information RSs for interference (CSI-IMs) or non-zero power channel state information RSs (NZP CSI-RSs) for interference.
  15. 15 . The method of claim 11 , further comprising determining an interference prediction for each RS resource in the second set of RS resources.
  16. 16 . The method of claim 15 , wherein the interference prediction report includes all of the interference predictions determined for each RS resource in the second set of RS resources.
  17. 17 . The method of claim 15 , wherein the interference prediction report includes a subset of the interference predictions determined for each RS resource in the second set of RS resources.
  18. 18 . The method of claim 17 , wherein the subset of the interference predictions included in the interference prediction report comprises a quantity, L, of interference predictions, wherein the L interference predictions comprised in the interference prediction report are the best L interference predictions or the worst L interference predictions.
  19. 19 . The method of claim 17 , further comprising determining the subset of interference predictions to be included in the interference prediction report based on a comparison of the interference predictions determined for each RS resource in the second set of RS resources with a threshold value for reporting.
  20. 20 . The method of claim 11 , wherein the interference prediction is in decibels (dB).

Description

BACKGROUND Artificial intelligence may be broadly defined as behaviors exhibited by machines that mimic cognitive functions to sense, reason, adapt and/or act. Machine learning may refer to type of algorithms that solve a problem based on learning through experience (e.g., data), without explicitly being programmed (e.g., by configuring a set of rules). Machine learning can be considered as a subset of AI. Different machine learning paradigms may be envisioned based on the nature of data or feedback available to the learning algorithm. For example, a supervised learning approach may involve learning a function that maps input to an output based on labeled training example. In such cases, each training example may be a pair consisting of input and the corresponding output. Unsupervised learning approaches may involve detecting patterns in the data with no pre-existing labels. For example, a reinforcement learning approach may involve performing a sequence of actions in an environment to maximize a cumulative reward. In some solutions, machine learning algorithms may use a combination or interpolation of the above-mentioned approaches. For example, semi-supervised learning approach may use a combination of a small amount of labeled data with a large amount of unlabeled data during training. In this regard, semi-supervised learning falls between unsupervised learning (e.g., with no labeled training data) and supervised learning (e.g. with only labeled training data). Deep learning may refer to a class of machine learning algorithms that employ artificial neural networks (e.g., Deep Neural Networks (DNNs) which were loosely inspired from biological systems. The Deep Neural Networks (DNNs) are a special class of machine learning models inspired by human brain wherein the input is linearly transformed and pass-through non-linear activation function multiple times. DNNs typically consists of multiple layers. Each layer may include linear transformation and/or a given non-linear activation function. The DNNs can be trained using the training data (e.g., via a back-propagation algorithm). DNNs have shown state-of-the-art performance in variety of domains, such as speech, vision, natural language etc., and for various machine learning settings such as supervised, un-supervised, and semi-supervised. The term AIML based methods/processing may refer to the realization of behaviors and/or conformance to requirements by learning based on data, without explicit configuration of sequence of steps of actions. Such methods may enable learning complex behaviors which might be difficult to specify and/or implement when using legacy methods. SUMMARY A WTRU may predict interference for different interference hypotheses based on measurements of resources for a subset of hypotheses according to a measurement beam. A WTRU can dynamically switch its reporting mode based on beam prediction and/or interference prediction. The WTRU can be configured with multiple reference signal (RS) resources for interference measurement (e.g., Set B for interference measurement). Each RS resource for signal measurement may be associated with a quantity, M, of RS resources for interference measurement. A WTRU may report one or more interference hypotheses (e.g., the best and/or worst interference hypotheses by indicating IMRs with lowest/highest interferences). Based on the determined qualities, the WTRU may indicate one or more resources in Set B and one or more resources of the multiple RS resources for interference prediction (e.g., Set A for interference prediction). For example, the WTRU may indicate the Top K resources and Top L resources for each of the Top K resources. A WTRU may perform dynamic switching of its reporting mode. The WTRU may evaluate the prediction accuracy of signal prediction and interference prediction and determines a reporting mode between signal prediction reporting and interference prediction reporting. A WTRU may receive configuration information for interference prediction. The configuration information may indicate a set of RS resources for interference measurement and a set of RS resources for interference prediction. The RSs indicated by the RS resources may, for example, be channel state information RSs (CSI-RSs), channel state information RSs for interference (CSI-IMs), and/or non-zero power channel state information RSs (NZP CSI-RSs) for interference. The WTRU may determine interference measurements for one or more (e.g., all) of the RS resources in the set of RS resources for interference measurement. The WTRU may determine interference predictions for one or more (e.g., all) of the RS resources in the set of RS resources for interference prediction. The WTRU may send a report indicating a result of the interference prediction. The interference predictions may be in decibels or another unit. The interference predictions may be generated using an AIML model. The interference measurements may be used as input to t