US-12621109-B2 - ML based dynamic bit loading and rate control

US12621109B2US 12621109 B2US12621109 B2US 12621109B2US-12621109-B2

Abstract

Apparatuses and methods for ML based dynamic bit loading and rate control are described. An apparatus obtains NN model coefficient information associated with communication channel information, between a UE and network, and the UE capabilities. The apparatus generates, using the NN model and based on the coefficient information, a communication configuration including a constellation or a CB channel coding rate. The apparatus communicates, with the network and based on the CB of a TB, using the NN-generated channel coding rate or constellation. Another apparatus obtains NN model coefficient information, associated with communication channel information, between a UE and network, and the UE capabilities. The apparatus generates, using the NN model and based on the coefficient information, a communication configuration including a constellation or a CB channel coding rate. The apparatus communicates, with the UE and based on the CB of a TB, using the NN-generated channel coding rate or constellation.

Inventors

Shay Landis
Amit BAR-OR TILLINGER
Yehonatan Dallal
Idan Michael Horn

Assignees

QUALCOMM INCORPORATED

Dates

Publication Date: 20260505
Application Date: 20230620

Claims (20)

1 . An apparatus for wireless communication at a user equipment (UE), comprising: at least one memory; and at least one processor coupled to the at least one memory and, based at least in part on information stored in the at least one memory, the at least one processor, individually or in any combination, is configured to: obtain coefficient information for a neural network (NN) model, wherein the coefficient information is associated with communication information of a communication channel, between the UE and a network node, and at least one capability of the UE; generate, using the NN model and based on the coefficient information, a communication configuration including at least one of a constellation or a code block (CB) channel coding rate; and communicate, with the network node and based on the CB of a transport block (TB), using the CB channel coding rate or the constellation generated using the NN model; wherein to communicate, with the network node and based on the communication configuration, the CB of the TB, the at least one processor, individually or in any combination, is configured to: receive the CB of the TB from the network node, wherein the CB of the TB is received based on the communication configuration that is also associated with another instance of the NN model for the network node; or transmit the CB of the TB to the network node, wherein the CB of the TB is transmitted based on the communication configuration in association with the another instance of the NN model for the network node; and wherein to transmit the CB of the TB to the network node, the at least one processor, individually or in any combination, is configured to: transmit an additional CB of the TB to the network node, wherein the additional CB of the TB includes at least one of: a different CB channel coding rate or a different coding rate generated using the NN model; or at least one of an additional layer, an additional RE, an additional RB, or an additional PRG, of the additional CB having a different constellation generated using the NN model.
2 . The apparatus of claim 1 , wherein to generate the communication configuration, the at least one processor, individually or in any combination, is configured to generate a set of CB channel coding rates for the CB of the TB, and the CB of the TB uses a first CB channel coding rate or a second coding rate of the set of CB channel coding rates for the CB.
3 . The apparatus of claim 1 , wherein to generate the communication configuration, the at least one processor, individually or in any combination, is configured to generate a constellations for each layer of multiple layers, for each resource element (RE) of multiple REs, for each resource block (RB) of multiple RBs, or for each physical resource block group (PRG) of multiple PRGs.
4 . The apparatus of claim 1 , wherein to generate the communication configuration, the at least one processor, individually or in any combination, is configured to: provide, to the NN model as inputs, at least one of a channel estimation associated with a reference signal or a noise indication for the communication channel; and obtain, from the NN model as outputs, at least one of the constellation or the CB channel coding rate for the communication configuration.
5 . The apparatus of claim 4 , wherein at least one of the channel estimation or the noise indication for the communication channel are associated with at least one signal transmitted by the network node to the UE using the communication channel.
6 . The apparatus of claim 1 , wherein the at least one processor, individually or in any combination, is further configured to: transmit, to the network node, an indication of support for the at least one capability of the UE, wherein the at least one capability of the UE includes a capability of the UE associated with an optimization or a restriction for execution of the NN model.
7 . The apparatus of claim 1 , wherein to obtain the coefficient information for the NN model, the at least one processor, individually or in any combination, is configured to: receive the coefficient information for the NN model from the network node using first radio resource control (RRC) signaling.
8 . The apparatus of claim 7 , wherein the at least one processor, individually or in any combination, is further configured to: receive, from the network node using second RRC signaling, updated coefficient information for the NN model.
9 . The apparatus of claim 1 , wherein to obtain the coefficient information for the NN model, the at least one processor, individually or in any combination, is configured to generate or select, at the UE, the coefficient information for the NN model based on a machine learning (ML) training associated with the communication information of the communication channel and the at least one capability of the UE.
10 . The apparatus of claim 9 , wherein the at least one processor, individually or in any combination, is further configured to: transmit, for the network node and subsequent to obtaining the coefficient information for the NN model, the coefficient information associated with the NN model.
11 . The apparatus of claim 10 , wherein to obtain the coefficient information for the NN model, the at least one processor, individually or in any combination, is configured to: transmit, for the network node using first radio resource control (RRC) signaling, an initial set of coefficient options for the coefficient information associated with the NN model, wherein the initial set of coefficient options includes at least one option for the coefficient information; receive, from the network node, at least a portion of the initial set of coefficient options for the coefficient information associated with the NN model; and select the coefficient information from at least the portion of the initial set of coefficient options for the coefficient information associated with the NN model; wherein the coefficient information associated with the NN model is transmitted using second RRC.
12 . The apparatus of claim 11 , wherein at least the portion of the initial set of coefficient options for the coefficient information associated with the NN model includes a subset of the initial set of coefficient options that is down-selected from the initial set of coefficient options, and wherein at least the portion of the initial set of coefficient options for the coefficient information associated with the NN model is received using at least one of a medium access control (MAC) control element (MAC-CE) or downlink control information (DCI); or wherein each coefficient option of the initial set of coefficient options corresponds to a respective index of a trained or defined coefficient option.
13 . An apparatus for wireless communication at a network node, comprising: at least one memory; and at least one processor coupled to the at least one memory and, based at least in part on information stored in the at least one memory, the at least one processor, individually or in any combination, is configured to: obtain coefficient information for a neural network (NN) model, wherein the coefficient information is associated with communication information of a communication channel, between a user equipment (UE) and the network node, and at least one capability of the UE; generate, using the NN model and based on the coefficient information, a communication configuration including at least one of a constellation or a code block (CB) channel coding rate; and communicate, with the UE and based on the CB of a transport block (TB), using the channel coding rate or the constellation generated using the NN; wherein to communicate, with the UE and based on the communication configuration, the CB of the TB, the at least one processor, individually or in any combination, is configured to: transmit the CB of the TB to the UE, wherein the CB of the TB is transmitted based on the communication configuration that is also associated with another instance of the NN model for the UE; or receive the CB of the TB from the UE, wherein the CB of the TB is received based on the communication configuration in association with the another instance of the NN model for the UE; and wherein to transmit the CB of the TB to the UE, the at least one processor, individually or in any combination, is configured to: transmit an additional CB of the TB to the UE, wherein the additional CB of the TB includes at least one of: a different CB channel coding rate or a different coding rate generated using the NN model; or at least one of an additional layer, an additional RE, an additional RB, or an additional PRG, of the additional CB having a different constellation generated using the NN model.
14 . The apparatus of claim 13 , wherein to generate the communication configuration, the at least one processor, individually or in any combination, is configured to generate a set of CB channel coding rates for the CB of the TB, and the CB of the TB uses a first CB channel coding rate or a second coding rate of the set of CB channel coding rates for the CB.
15 . The apparatus of claim 13 , wherein to generate the communication configuration, the at least one processor, individually or in any combination, is configured to generate a constellations for each layer of multiple layers, for each resource element (RE) of multiple REs, for each resource block (RB) of multiple RBs, or for each physical resource block group (PRG) of multiple PRGs.
16 . The apparatus of claim 13 , wherein to generate the communication configuration, the at least one processor, individually or in any combination, is configured to: provide, to the NN model as inputs, at least one of a channel estimation associated with a reference signal or a noise indication for the communication channel; and obtain, from the NN model as outputs, at least one of the constellation or the CB channel coding rate for the communication configuration.
17 . The apparatus of claim 16 , wherein at least one of the channel estimation or the noise indication for the communication channel are associated with at least one signal transmitted by the UE to the network node using the communication channel.
18 . The apparatus of claim 13 , wherein the at least one processor, individually or in any combination, is further configured to: receive, from the UE, an indication of support for the at least one capability of the UE, wherein the at least one capability of the UE includes a capability of the UE associated with an optimization or a restriction for execution of the NN model.
19 . The apparatus of claim 13 , wherein the at least one processor, individually or in any combination, is further configured to: transmit the coefficient information for the NN model, for the UE and subsequent to obtaining the coefficient information for the NN model, using first radio resource control (RRC) signaling.
20 . The apparatus of claim 19 , wherein the at least one processor, individually or in any combination, is configured to: transmit, for the UE using second RRC signaling, updated coefficient information for the NN model.

Description

TECHNICAL FIELD The present disclosure relates generally to communication systems, and more particularly, to wireless communications utilizing bit loading and channel coding rates. INTRODUCTION Wireless communication systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, and broadcasts. Typical wireless communication systems may employ multiple-access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple-access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single-carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems. These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate on a municipal, national, regional, and even global level. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of a continuous mobile broadband evolution promulgated by Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with Internet of Things (IoT)), and other requirements. 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine type communications (mMTC), and ultra-reliable low latency communications (URLLC). Some aspects of 5G NR may be based on the 4G Long Term Evolution (LTE) standard. There exists a need for further improvements in 5G NR technology. These improvements may also be applicable to other multi-access technologies and the telecommunication standards that employ these technologies. BRIEF SUMMARY The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects. This summary neither identifies key or critical elements of all aspects nor delineates the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later. In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus is configured to obtain coefficient information for a neural network (NN) model, where the coefficient information is associated with communication information of a communication channel, between the UE and a network node, and at least one capability of the UE. The apparatus is configured to generate, using the NN model and based on the coefficient information, a communication configuration including at least one of a constellation or a code block (CB) channel coding rate. The apparatus is configured to communicate, with the network node and based on the CB of a transport block (TB), using the CB channel coding rate or the constellation generated using the NN model. In the aspect, the method includes obtaining coefficient information for a NN model, where the coefficient information is associated with communication information of a communication channel, between the UE and a network node, and at least one capability of the UE. The method includes generating, using the NN model and based on the coefficient information, a communication configuration including at least one of a constellation or a CB channel coding rate. The method includes communicating, with the network node and based on the CB of a TB, using the CB channel coding rate or the constellation generated using the NN model. In another aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus is configured to obtain coefficient information for a NN model, where the coefficient information is associated with communication information of a communication channel, between a UE and the network node, and at least one capability of the UE. The apparatus is configured to generate, using the NN model and based on the coefficient information, a communication configuration including at least one of a constellation or a CB channel coding rate. The apparatus is configured to communicate, with the UE and based on the CB of a TB, using the channel coding rate or the constellation generated using the NN. In the aspect, the method includes obtaining coefficient information for a NN model, where the coefficient information is associated with communication information of a communication channel, between a UE and the network node, and at least one capability of the UE. The method includes generating, using the NN model and based on the coefficient information, a communication configuration including at le