Model inference configuration for ai / ML based dpod

Abstract

A method, transmitter and receiver for model inference configurations for artificial intelligence / machine language (AI / ML)- based digital post distortion (DPoD) are disclosed. According to one aspect, a method in a transmitter includes receiving from a receiver a transmission modification parameter, the transmission modification parameter being based at least in part on a power amplifier (PA) compensation mode applied at the receiver. The method also includes transmitting a signal to the receiver based at least in part on the transmission modification parameter.

Description

[0001] MODEL INFERENCE CONFIGURATION FOR AI / ML BASED DPOD

[0002] TECHNICAL FIELD

[0003] The present disclosure relates to wireless communications, and in particular, to model inference configurations for artificial intelligence / machine language (AI / ML)- based digital post distortion (DPoD).

[0004] BACKGROUND

[0005] The Third Generation Partnership Project (3GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile user equipments (UE), as well as communication between network nodes and between UEs. The 3GPP is also developing standards for Sixth Generation (6G) wireless communication networks.

[0006] The Institute of Electrical and Electronic Engineers (IEEE) has developed and continues to develop standards for wireless communication networks, including Wireless Local Area Networks (WLANs), branded as “Wi-Fi” networks by the Wi-Fi Alliance. WLANs include wireless communication between access points (AP STAs) and non-access point stations (non-AP STAs). Such IEEE standards include IEEE 802.11a / b / g / n / ac / ax / be / bn and IEEE 802.15.

[0007] Machine learning (ML) algorithms refer to techniques that use a set of training data for training models and use the trained models for various applications including inference, classification and prediction. Machine learning algorithms may be classified into online and offline algorithms, where the offline algorithms rely on pre-trained models while the online algorithms may train the model on the fly while receiving new data samples. Another fundamental distinction is between supervised, unsupervised and reinforcement learning. In the supervised learning paradigm, during the training phase, each input data sample to the learning algorithm (feature) is paired with a corresponding labeled output (label).

[0008] Artificial neural networks are a class of machine learning algorithms that are widely used due to their capability to approximate any general function based on training data sets, and their inherent parallel processing which make these techniques attractive candidates for implementation on emerging Al accelerator hardware. A neural network is based on interconnected processing units called neurons, an example of which is depicted in FIG. 1, where each neuron receives weighted version of the other neuron’s outputs and compute the output based on a nonlinear transformation of the aggregated inputs using an activation function.

[0009] Machine learning methods may be used at the receiver to optimize one or more functionalities at the receiver. For example, a machine learning receiver method based on neural networks (NN) is proposed to optimize the demapper (a single functionality) to compensate the hardware impairments due to oscillator phase noise. This is illustrated in the example of FIG. 2.

[0010] One possible implementation of a neural network receiver is illustrated in the example of FIG. 3. The structure in FIG. 3 performs soft symbol -by-symbol demapping, taking the real (I) and imaginary (Q) components of a complex baseband sample, context information and signal to noise ratio (SNR.) estimates as inputs and generates soft bits as the output. Such a demapper will help improve the performance of a system that is under the influence of radio frequency (RF) impairments such as power amplifier (PA) nonlinearity. The performance of this ML / AI-based method in comparison with a baseline method is illustrated in the example of FIG. 4. With respect to FIG. 4, reference is made to "A Deep Learning Receiver for Non- Linear Transmitter," in IEEE Access, vol. 11, pp. 2796-2803, 2023, doi: 10.1109 / ACCESS.2023.3234501.

[0011] SUMMARY

[0012] Methods for power amplifier nonlinearity compensation, so called digital post distortion compensation (DPoD) methods, at the receiver (e.g., network node in UL transmissions) have been proposed. This method enables signal detection at the receiver in the presence of higher distortions due to PA nonlinearities. The adaptation of signal quality at the transmitter (e.g., UE in UL transmissions) according to the PA nonlinearity compensation capability at the receiver has been considered, and a method for DPoD with adaptive capability has also been considered. However, the network node may have different parameter settings, each leading to certain a DPoD capability for specific types of transmitted signals. The UE may support certain sets of parameter settings that lead to specific types of signals.

[0013] Some embodiments advantageously provide transmitting node and / or receiving node for model inference configurations for artificial intelligence / machine language (AI / ML)- based digital post distortion (DPoD).

[0014] According to certain embodiments, , a method by transmitting node for model inference configurations for artificial intelligence / machine language, AI / ML, based digital post distortion, DPoD, includes receiving, from the receiving node, a transmission modification parameter, the transmission modification parameter being based at least in part on a power amplifier, PA, compensation mode applied at the receiving node. The transmitting node transmits a signal to the receiving node. The signal transmitted is based at least in part on the transmission modification parameter.

[0015] According to certain embodiments, a transmitting node for model inference configurations for artificial intelligence / machine language, AI / ML, based digital post distortion, DPoD, is adapted to receive from the receiving node a transmission modification parameter, the transmission modification parameter being based at least in part on a power amplifier (PA) compensation mode applied at the receiving node. The transmitting node is adapted to transmit a signal to the receiving node. The signal transmitted is based at least in part on the transmission modification parameter.

[0016] According to certain embodiments a method by a receiving node for artificial intelligence / machine language, AI / ML, based digital post distortion, DPoD, includes applying a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model. The AI / ML model configured to determine a transmission modification parameter. The receiving node transmits to the transmitting node the transmission modification parameter.

[0017] According to certain embodiments, a receiving node for model inference configurations for artificial intelligence / machine language, AI / ML, based digital post distortion, DPoD, is adapted to apply a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model. The AI / ML model configured to determine a transmission modification parameter. The receiving node is adapted to transmit to the transmitting node the transmission modification parameter.

[0018] According to certain embodiments, the UE and network node may coordinate configurations regarding signal transmission and DPoD. In some embodiments, configuration parameters are provided, taking into account factors specific to dealing with power amplifier imperfections. Methods and arrangements are provided for the UE and network node to coordinate the configurations regarding signal transmission and DPoD.

[0019] In certain embodiments, the AI / ML based DPoD disclosed herein may provide one or more of the following technical advantage(s)for the wireless network.

[0020] For example, certain embodiments may provide a technical advantage of increasing uplink coverage by increasing transmit power when there is capability to compensate for the additional signal distortions. As another example, certain embodiments may provide a technical advantage of lowering power consumption for signal detection with a given throughput leveraging on the DPoD capability in the network for compensating PA nonlinearity. As further examples, certain embodiments may provide may provide technical advantages of enabling the UE to operate with higher energy efficiency by operating in a more nonlinear PA regime when there is DPoD capability at the network node.

[0021] BRIEF DESCRIPTION OF THE DRAWINGS

[0022] For a more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings, in which:

[0023] FIG. 1 illustrates a model of an artificial neural network;

[0024] FIG. 2 illustrates a receiver chain with a soft demapper replaced by machine learning;

[0025] FIG. 3 illustrates a neural network for soft demapping;

[0026] FIG. 4 illustrates a graph of performance of a neural network based demapper;

[0027] FIG. 5 illustrates a schematic diagram of an example network architecture illustrating a communication system according to principles disclosed herein;

[0028] FIG. 6 illustrates a block diagram of a network node in communication with a user equipment over a wireless connection according to some embodiments of the present disclosure;

[0029] FIG. 7 illustrates a flowchart of an example process in a network node for model inference configurations for artificial intelligence / machine language (AI / ML)- based DPoD according to some embodiments of the present disclosure;

[0030] FIG. 8 illustrates a flowchart of an example process in a user equipment for model inference configurations for artificial intelligence / machine language (AI / ML)- based DPoD according to some embodiments of the present disclosure; and

[0031] FIG. 9 illustrates parameter combinations that may be configured for activation.

[0032] DETAILED DESCRIPTION

[0033] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Before describing in detail example embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to model inference configurations for AI / ML based DPoD. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0034] In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The UE herein may be any type of user equipment capable of communicating with a network node or another UE over radio signals, such as a wireless device (WD). The UE may also be a radio communication device, target device, device to device (D2D) UE, non-AP station, machine type UE or UE capable of machine to machine communication (M2M), low-cost and / or low-complexity UE, a sensor equipped with UE, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device etc.

[0035] Also, in some embodiments the generic term “radio network node” is used. It may be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, Multi-cell / multicast Coordination Entity (MCE), relay node, access point, radio access point, Remote Radio Unit (RRU) Remote Radio Head (RRH).

[0036] Note that although terminology from one particular wireless system, such as, for example, 3GPP LTE and / or New Radio (NR), and / or Wi-Fi, may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.

[0037] Note further, that functions described herein as being performed by a user equipment or a network node may be distributed over a plurality of user equipments and / or network nodes. In other words, it is contemplated that the functions of the network node and user equipment described herein are not limited to performance by a single physical device and, in fact, may be distributed among several physical devices.

[0038] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0039] Some embodiments are directed to model inference configurations for artificial intelligence / machine language (AI / ML)- based DPoD.

[0040] Returning to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 5 a schematic diagram of a communication system 10, according to an embodiment, such as a 3 GPP -type cellular network that may support standards such as LTE and / or NR (5G), which comprises an access network 12, such as a radio access network, and a core network 14. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). Each network node 16a, 16b, 16c is connectable to the core network 14 over a wired or wireless connection 20. A first user equipment (UE) 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second UE 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of UEs 22a, 22b (collectively referred to as user equipments 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding network node 16. Note that although only two UEs 22 and three network nodes 16 are shown for convenience, the communication system may include many more UEs 22 and network nodes 16.

[0041] Also, it is contemplated that a UE 22 may be in simultaneous communication and / or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a UE 22 may have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, UE 22 may be in communication with an eNB for LTEZE-UTRAN and a gNB for NR / NG-RAN, and / or an access point of a Wi-Fi network.

[0042] As used herein the term “transmitter” or “transmitting node” refers to a transmitter that may reside in the UE 22 or the network node 16 and the term “receiver” or “receiving node” refers to a receiver that may reside in the UE 22 or the network node 16. The following discussion is based on the assumption that the transmitter is in the UE 22, and that the receiver is in the network node 16. In some embodiments, the location of the receiver may be in another UE 22. A receiver (e.g., at an eNB or gNB) may be configured to include an AI / ML unit 24 which is configured to apply a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model. A transmitter (e.g., at a UE) may be configured to include a modification unit 26 which is configured to configure a signal to be transmitted based on a transmission modification parameter.

[0043] Example implementations, in accordance with an embodiment, of the UE 22 and receiver, e.g., network node 16, discussed in the preceding paragraphs will now be described with reference to FIG. 6.

[0044] The communication system 10 includes a receiver, e.g., network node 16, provided in a communication system 10 and including hardware 28 enabling it to communicate with the UE 22. The hardware 28 may include a radio interface 30 for setting up and maintaining at least a wireless connection 32 with a transmitter, e.g., UE 22, located in a coverage area 18 served by the receiver, e.g., network node 16. The radio interface 30 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 30 includes an array of antennas 34 to radiate and receive signal(s) carrying electromagnetic waves.

[0045] In the embodiment shown, the hardware 28 of the receiver, e.g., network node 16 further includes processing circuitry 36. The processing circuitry 36 may include a processor 38 and a memory 40. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 36 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or Field Programmable Gate Array (FPGAs) and / or Application Specific Integrated Circuitry (ASICs) adapted to execute instructions. The processor 38 may be configured to access (e.g., write to and / or read from) the memory 40, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or Random Access Memory (RAM) and / or Read-Only Memory (ROM) and / or optical memory and / or Erasable Programmable Read-Only Memory (EPROM).

[0046] Thus, the receiver, e.g., network node 16, further has software 42 stored internally in, for example, memory 40, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the receiver, e.g., network node 16, via an external connection. The software 42 may be executable by the processing circuitry 36. The processing circuitry 36 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by receiver, e.g., network node 16. Processor 38 corresponds to one or more processors 38 for performing receiver, e.g., network node 16, functions described herein. The memory 40 is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 42 may include instructions that, when executed by the processor 38 and / or processing circuitry 36, causes the processor 38 and / or processing circuitry 36 to perform the processes described herein with respect to receiver, e.g., network node 16. For example, processing circuitry 36 of the receiver, e.g., network node 16, may include an AI / ML unit 24 which is configured to apply a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model.

[0047] The communication system 10 further includes the transmitter, e.g., UE 22, already referred to. The transmitter, e.g., UE 22, may have hardware 44 that may include a radio interface 46 configured to set up and maintain a wireless connection 32 with a receiver, e.g., network node 16, serving a coverage area 18 in which the transmitter, e.g., UE 22, is currently located. The radio interface 46 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 46 includes an array of antennas 48 to radiate and receive signal(s) carrying electromagnetic waves.

[0048] The hardware 44 of the transmitter, e.g., UE 22, further includes processing circuitry 50. The processing circuitry 50 may include a processor 52 and memory 54. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 50 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or Field Programmable Gate Array (FPGAs) and / or Application Specific Integrated Circuitry (ASICs) adapted to execute instructions. The processor 52 may be configured to access (e.g., write to and / or read from) memory 54, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or Random Access Memory (RAM) and / or Read-Only Memory (ROM) and / or optical memory and / or Erasable Programmable Read-Only Memory (EPROM).

[0049] Thus, the transmitter, e.g., UE 22, may further comprise software 56, which is stored in, for example, memory 54 at the transmitter, e.g., UE 22,, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the transmitter, e.g., UE 22,. The software 56 may be executable by the processing circuitry 50. The software 56 may include a client application 58. The client application 58 may be operable to provide a service to a human or non-human user via the transmitter, e.g., UE 22,. The processing circuitry 50 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by transmitter, e.g., UE 22,. The processor 52 corresponds to one or more processors 52 for performing transmitter, e.g., UE 22, functions described herein. The transmitter, e.g., UE 22, includes memory 54 that is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 56 and / or the client application 58 may include instructions that, when executed by the processor 52 and / or processing circuitry 50, causes the processor 52 and / or processing circuitry 50 to perform the processes described herein with respect to transmitter, e.g., UE 22,. For example, the processing circuitry 50 of the user equipment 22 may include a modification unit 26 which is configured to configure a signal to be transmitted based on a transmission modification parameter.

[0050] In some embodiments, the inner workings of the receiver, e.g., network node 16, and transmitter, e.g., UE 22, may be as shown in FIG. 6 and independently, the surrounding network topology may be that of FIG. 5.

[0051] The wireless connection 32 between the transmitter, e.g., UE 22, and the receiver, e.g., network node 16, is in accordance with the teachings of the embodiments described throughout this disclosure. More precisely, the teachings of some of these embodiments may improve the data rate, latency, and / or power consumption and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime, etc. In some embodiments, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve.

[0052] Although FIGS. 5 and 6 show various “units” such as AI / ML unit 24 and modification unit 26 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry.

[0053] FIG. 7 illustrates a method 700 in a receiving node 16 for model inference configurations for artificial intelligence / machine language (AI / ML)- based DPoD. One or more blocks described herein may be performed by one or more elements of a network node 16 such as by one or more of processing circuitry 36 (including the AI / ML unit 24), processor 38, and / or radio interface 30. Receiver such as via processing circuitry 36 and / or processor 38 and / or radio interface 30 is configured to apply a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model, the AI / ML model configured to determine a transmission modification parameter. The process also includes transmitting to the transmitter the transmission modification parameter (702).

[0054] In some embodiments, the method includes that the transmission modification parameter includes at least one of a power backoff relaxation value, a PA backoff value, a permissible PA non-linearity metric value, and a permissible in-band distortion metric value (702). In some embodiments, the method includes receiving from the transmitting node, transmission characteristics and modification capability information. In some embodiments, the modification capability information includes at least one of a maximum power reduction relaxation ability and a power backoff relaxation adaptation ability. In some embodiments, the modification capability information is based at least in part on at least one of modulation, waveform, frequency range and resource allocation. In some embodiments, the amount of power backoff relaxation is different for different frequency ranges. In some embodiments, the amount of power backoff relaxation is different for different resource allocations. In some embodiments, the amount of power backoff relaxation is different based at least in part on at least one of full duplex operation, in-device coexistence (IDC), waveform used by the transmitter. In some embodiments the amount of power backoff relaxation is provided for each modulation order and does not vary. In some embodiments, the transmission characteristics include at least one of power amplifier type, a non-linearity curve, a parametric description, a non-parametric description, a closed predefined category and a default distortion metric value. In some embodiments, the transmitted transmission modification parameter is based at least in part on the modification capability information. In some embodiments, the transmission modification parameter is based at least in part on at least one of a modulation, a frequency range, a transmitter power amplifier (PA) type and power class, a multi-carrier configuration, a scheduled physical resource block location, a spatial multiplexing mode and a transmission waveform. In some embodiments, the transmission modification parameter is indicated by UE assistance information (UAI) that includes at least one of an explicit parameter value, a lookup index to a parameter list and a lookup index to a preconfigured radio resource control (RRC) configuration. In some embodiments, the PA compensation mode includes DPoD.

[0055] FIG. 8 illustrates a method in transmitting node 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of user equipment 22 such as by one or more of processing circuitry 50 (including the modification unit 26), processor 52, and / or radio interface 46. The transmitting node such as via processing circuitry 50 and / or processor 52 and / or radio interface 46 is configured to receive from the receiving node a transmission modification parameter, the transmission modification parameter being based at least in part on a power amplifier (PA) compensation mode applied at the receiver (802). The process also includes transmitting a signal to the receiver based at least in part on the transmission modification parameter (804).

[0056] In some embodiments, the method includes that the transmission modification parameter includes one or more of a power backoff relaxation value, a power backoff value. In some embodiments, the method includes transmitting to the receiving node transmission characteristics and modification capability information. In some embodiments, the modification capability information includes at least one of a maximum power reduction relaxation ability and a backoff adaptation ability. In some embodiments, the modification capability information is based at least in part on at least one of modulation, waveform, frequency range and resource allocation. In some embodiments, the amount of power backoff relaxation is different for different frequency ranges. In some embodiments, the amount of power backoff relaxation is different for different resource allocations. In some embodiments, the amount of power backoff relaxation is different based at least in part on at least one of full duplex operation, in-device coexistence (IDC), waveform used by the transmitter. In some embodiments the amount of power backoff relaxation is provided for each modulation order and does not vary. In some embodiments, the transmission characteristics include at least one of power amplifier type, a non-linearity curve, a parametric description, a nonparametric description, a closed predefined category and a default distortion metric value. In some embodiments, the received transmission modification parameter is based at least in part on the modification capability information. In some embodiments, the transmission modification parameter includes one or more of a power amplifier (PA) backoff relaxation value, a PA backoff value, a permissible PA non-linearity metric value, and a permissible in- band distortion metric value. In some embodiments, the transmission modification parameter is based at least in part on at least one of a modulation, a frequency range, a transmitter power amplifier (PA) type and power class, a multi-carrier configuration, a scheduled physical resource block location, a spatial multiplexing mode and a transmission waveform. In some embodiments, the transmission modification parameter is indicated by UE assistance information (UAI) that includes at least one of an explicit parameter value, a lookup index to a parameter list and a lookup index to a preconfigured radio resource control (RRC) configuration. In some embodiments, the method includes initiating a transmission modification based at least in part on at least one of the transmission modification parameters and a delay value for starting the transmission modification. In some embodiments, the PA compensation mode includes digital pre-distortion (DPD).

[0057] Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for model inference configurations for artificial intelligence / machine language (AI / ML)- based DPoD.

[0058] Methods and arrangements to configure transmit power backoff to compensate power amplifier distortion, either at the transmitter (e.g., using a digital pre distortion, DPD) or the receiver (e.g., using a digital post distortion, DPoD), are disclosed.

[0059] In the following description, the terms “transmitter” and “receiver” are used. It is noted that the transmitter may be a UE 22 or at a UE 22, and the receiver may be a network node 16 or at a network node 16. However, the receiver could also be another UE 22 or at another UE 22, as in the case of sidelink communications between UEs 22. Also, the terms transmitting node and receiving node may be used interchangeably.

[0060] Also, the terms Al model, AI / ML model and DPoD model may be used interchangeably. The Al model is performed by the AI / ML unit 24.

[0061] Principles and methodologies disclosed herein may be applied to:

[0062] • Uplink, where the transmitter is a device (e.g., a UE 22) and the receiver is a base station (e.g., a network node 16);

[0063] • Downlink, where the transmitter is a network node 16 and the receiver is a UE 22; and / or

[0064] • Sidelink, where the transmitter and receiver are two peer UEs 22.

[0065] Without loss of generality, the methods are explained below using uplink transmission as a non-limiting example.

[0066] The node for compensating for power amplifier distortion may be either the transmitter or the receiver. For the transmitter, methods such as digital pre-distortion (DPD) may be applied. For the receiver, methods such as DPoD may be applied. The methods may be realized via an AI / ML model or a conventional (non- Al) method. Without loss of generality, the methods are explained below using a non-limiting example where AI / ML model based DPoD is applied at the receiver of the uplink transmission. It is understood by those skilled in the art that the disclosed methods and arrangements may be applied to other setups as well.

[0067] Methods and arrangements for configuration and signaling for power backoff relaxation, when using DPoD at the receiver, for model inference are disclosed.

[0068] For uplink transmission, when a DPoD feature is activated at the receiver, e.g., the network node 16, the receiver may perform signal detection in the presence of higher in-band distortions. Hence, the receiver may configure the transmitter to relax power backoff and transmit a signal with higher power and possibly higher distortions.

[0069] Similarly, for uplink transmission, when digital pre-distortion (DPD) is activated at the transmitter, e.g., the UE 22, the transmitter may also be configured to relax power backoff, so that the transmitter may transmit uplink signals with higher power without excessive distortions. In some embodiments, the amount of power backoff relaxation is provided for each modulation order, and does not vary due to other factors.

[0070] Alternatively, with a more sophisticated design, the amount of power backoff relaxation may vary with other factors, including one or more of the following:

[0071] • Different frequency ranges;

[0072] • Different channel bandwidth sizes, e.g., BWchannei < 200 MHz, or BWchannei >= 400 MHz, etc.;

[0073] • Different transmitter power class, e.g., Class 1 for fixed wireless and high-power use case such as public safety or backhaul links; Class 3 for handheld UEs 22; Class 6 for High-Speed Train Roof-Mounted UE 22; Class 7 for RedCap (reduced capability) UE 22, etc.;

[0074] • Different resource block location within the band, e.g., inner band, outer band, outer region 1 and outer region 2, etc.;

[0075] • Single carrier vs carrier aggregation (CA);

[0076] • Single-layer uplink transmission vs multi-layer uplink (UL) multiple input multiple output (MIMO) transmission; and / or

[0077] • A UE 22 configured for uplink transmission at a single direction at a time, versus a UE 22 configured for simultaneous uplink transmission to multiple directions.

[0078] Some of the factors above are discussed in further details below. In some embodiments, the UE 22 may be configured to operate in a half-duplex transmission mode. In some embodiments, the UE 22 may be configured for uplink transmission and downlink reception in full duplex mode.

[0079] Certain embodiments may provide defining a different amount of relaxation for different frequency ranges.

[0080] The relaxation of power backoff may generally be different across different frequency ranges (FR). This includes:

[0081] • FR1 : frequency range of 410 MHz - 7125 MHz;

[0082] • FR2: frequency range of 24250 MHz - 71000 MHz. FR2 may be further divided as: o FR2-1 : 24250 MHz - 52600 MHz; o FR2-2: 52600 MHz - 71000 MHz; and / or

[0083] • FR3 : frequency range of 7125 MHz - 24250 MHz. FR3 may be further divided, for example, it might include the following subcategories: o FR3-1 : 7125 MHz - 8400 MHz; and / or o FR3-2: 8400 MHz - 24250 MHz

[0084] Note that the exact subdivisions of FR3 have not yet been defined and remain subject to ongoing discussion.

[0085] • sub-THz range: 92-300 GHz

[0086] For power backoff relaxation supported by DPoD, a different amount of relaxation may be defined for the different frequency ranges (and subcategories) above.

[0087] There may be requirements on in-band distortion (measured using e.g., error vector magnitude (EVM)) and out-of-band distortion (measured using, e.g., adjacent channel leakage ratio (ACER)) for each frequency band. The in-band distortion causes inter-carrier inference and affects the signal reception quality itself. The out-of-band distortion causes adjacent channel inference and affects other users in the system. For example, this may be the result of transmissions for the same UE 22, but on neighboring channels or frequency bands. The requirements on out of band distortions are stricter in low frequency bands (e.g. FR1), e.g., due to scarcity of the spectrum and the co-existence of different services in this band. The DPoD feature enables relaxation of the requirements on in-band distortions to achieve similar performance.

[0088] The inband distortion requirements in terms of transmitter EVM for FR1 / FR2 in some current Standards specifications, and the relaxed EVM requirements when the DPoD feature is activated for different modulation orders, for a specific implementation of the Al- based DPoD, are shown Tablel below. This demonstrates that DPoD allows relaxed EVM (i.e., higher EVM %) for transmitting signals with higher order modulation, since the receiver with a DPoD feature is able to detect signals experiencing worse distortion.

[0089] Table 1 : Example of transmitter EVM requirements in FR1 / FR2

[0090] Certain embodiments may provide defining different amounts of relaxation for different resource allocations

[0091] In some embodiments, the same amount of power backoff relaxation is applied regardless of resource allocation.

[0092] In some embodiments, a different amount of power backoff relaxation is applied depending on the resource allocation. The different resource allocations include the location of the allocated resources in the band, e.g., inner physical resource block (PRB) (i.e., Inner contiguous allocation, or Inner non-contiguous RB allocation), edge PRB (i.e., Outer contiguous RB allocation, or Outer non-contiguous RB allocation), and / or different regions of the outer band (Outer 1 or Outer 2 RB allocation). The maximum applied power relaxation may be limited by the requirements on the out of band distortion. Hence, it may depend on the location of the resource allocation. For example, if edge PRBs are scheduled, then the maximum power backoff relaxation may be set to PBO relax max edge, and if inner PRBs are scheduled, then the maximum power backoff relaxation may be set to PBO relax max in. In general, the allowable maximum power for outer RB allocation is lower than that of inner RB allocation. Hence the maximum power reduction allowed for outer RB allocation may be larger than that of inner RB allocation.

[0093] Alternatively, or additionally, the different resource allocation may include the different amount of RBs allocated, including allocating a percentage of a full PRB (e.g., allocating a fraction of a PRB to serve low-cost low-complexity Internet of things (loT) UEs 22). The power backoff relaxation may be higher when a lower percentage of PRBs is scheduled.

[0094] Certain embodiments may provide defining different amounts of relaxation for other example factors. In different embodiments, this includes:

[0095] • Full duplex: o Full duplex operation may cause additional interference to the received signal, e.g., due to the leakage from the transmitter’s RF chain to the receiver’s RF chain. Hence, less additional distortions, e.g., due to the out of band emissions, may be tolerated. Therefore, PA backoff relaxation may be limited while operating in full duplex mode to limit the distortions to the signal;

[0096] • In-device co-existence (IDC): o Often a transmitter may support different radio access technologies (RAT) simultaneously. For example, the transmitter may be equipped with multiple radio transceivers so that it may operate with a wireless local area network (e.g., WiFi) and a cellular network at the same time. In this case, in-device coexistence (IDC) interference should be mitigated carefully. Thus, the power backoff amount may be different depending on the IDC needs of the transmitter. For example, a smaller relaxation amount (thus, higher transmission power) may be used for transmitters without an IDC issue, compared to a transmitter with an IDC issue;

[0097] • Waveform impact due to the difference between cyclic prefix orthogonal frequency division multiplexing (CP-OFDM) and discrete Fourier transform (DFT)-s-OFDM: o PA nonlinearity impacts signals with CP-OFDM waveforms and DFT- s-OFDM waveforms differently. In general DFT-s-OFDM is more robust to PA nonlinearity compared to CP-OFDM due to DFT-s-OFDM creating a lower peak to average power ratio (PAPR). In addition, the DPoD operation at the receiver should be configured to perform differently depending on whether a CP-OFDM or a DFT-s- OFDM waveform is used by the transmitter. For example, in the case of Al-based DPoD, different AI / ML models may be deployed at the receiver depending on the waveform that is applied by the transmitter. Hence, the applied backoff relaxation may be different depending on the waveform.

[0098] Before AI / ML model inference for DPoD is activated, the receiver, e.g., network node 16, and the transmitter, e.g., UE 22, may go through a list of preparation procedures, which may include one or more of the following steps for model activation: Step 1. The transmitter sends its capability to the receiver. The capability includes:

[0099] • Maximum Power Reduction (MPR) relaxation support for various modulations. This indicates a list of modulation orders that the transmitter may apply. Alternatively, this is indicated by a list of MCS (modulation and coding scheme);

[0100] • MPR relaxation support for various waveforms. This indicates whether the transmitter supports MPR relaxation for DFT-s-OFDM and / or CP-OFDM;

[0101] • MPR relaxation support for various frequency ranges. This indicates whether the transmitter supports MPR relaxation for FR1, FR2 (including FR2-1, FR2-2), FR3 (including FR3-1, FR3-2); and / or

[0102] • MPR relaxation report. This reports whether the transmitter supports the reporting of MPR relaxation. The reporting may be via medium access control (MAC) control element (CE), e.g., enhanced power headroom (PHR).

[0103] The capability information may additionally indicate transmitter PA characteristics, so that the receiver may determine whether its DPoD models are applicable, what degree of MPR may be supported, etc. This info may be included as part of ParamSetuE in the next step.

[0104] Step 2. After receiving the transmitter capability report, the receiver may decide on the set of parameters to be applied to the uplink transmission with relaxed MPR. For this, the receiver should take into consideration at least the reported transmitter capability and the receiver AI / ML capability. That is, the receiver may activate AI / ML for DPoD for the parameter settings that are supported by both transmitter capability (denoted as ParamSetuE) and receiver AI / ML capability (denoted as ParamSetgNB,Ai). For example, in some embodiments:

[0105] • ParamSetuE: the transmitter supports relaxed MPR in FR1 for the quadrature amplitude modulation (QAM) range of {quadrature phase shift keying (QPSK), 16-QAM, 64-QAM, 256-QAM} and FR2 for the QAM range of {QPSK, 16- QAM}; and / or

[0106] • Param SetgNB.Ai: the base station AI / ML model support DPoD of {QPSK, 16-QAM, 64-QAM} for both FR1 and FR2:

[0107] For either of these two conditions, the parameter combinations available for activation (denoted as Param Setavaii.Ai) are the intersections of both, i.e.: Param Setavail, AI = FR1 with {QPSK, 16-QAM, 64-QAM }, and FR2 with {QPSK, 16-QAM},

[0108] Param Setavaii.Ai = ParamSetgNB,Ai ParamSetuE Then the receiver may decide parameter combinations to activate (denoted as ParamSetactivate). ParamSetactivate is a subset of ParamSetavaii,Ai (including the same as ParamSetavaii,Ai): ParamSetactivate £ ParamSetavaii,Ai. For example, the receiver may decide to configure activation of its AI / ML model for DPoD for these combination of parameters, ParamSetactivate = FR1 with { 16-QAM, 64-QAM}. That is, the receiver may not configure activation of FR1 with QPSK, for example, due to the relatively small, anticipated performance gain. In addition, the decision may be optimized by considering a secondary objective, such as selecting the parameter combination that results in lower energy consumption, higher throughput, or reduced latency. The specific objective should be determined based on the requirements of the application from higher layers.

[0109] Step 3. The receiver may then send ParamSetactivate and other related configurations to the transmitter, and may signal activation of MPR relaxation. Other configurations may include an MPR relaxation value for each scenario combination in ParamSetactivate, and additional conditions for applying or not applying relaxation (traffic type, channel condition), etc. FIG. 9 is a diagram of an example relationship between ParamSetgNB,Ai, ParamSetuE, ParamSetavaii.Ai, ParamSetactivate.

[0110] Step 4. After a delay TMPR>reiax, the transmitter may begin to carry out UL transmission with relaxed MPR. Here, the delay TMPR>reiax is the maximum time duration between the transmitter receiving the activation signal from the receiver, and the transmitter being prepared to apply the relaxed MPR as configured.

[0111] Additionally, an uncertainty or further delay in the timing of applying relaxed MPR may be supported for the transmitter. In one example, if it is required that the transmitter not stop current time-critical and / or quality-critical data transmission before changing transmission configuration, then the transmitter may continue transmission with the current procedure, i.e., delay the application of relaxed MPR till the current data transmission is completed. In another example, the application of relaxed MPR is delayed if the transmitter is experiencing poor channel conditions and the transmitter determines to wait for improved channel condition before carrying out UL transmission with relaxed MPR. These may be considered as additional conditions that must be satisfied before relaxed MPR may be activated, in some embodiments.

[0112] Step 5. After receiving UL transmissions from the given transmitter with relaxed MPR (e.g., a PUSCH at FR1 with 64-QAM), the receiver applies AI / ML based DPoD to obtain the information bits carried by the UL transmission. In some embodiments, configuration parameters are provided, taking into account factors specific to dealing with power amplifier imperfections.

[0113] Embodiment 1. Method in a UE 22 for UL transmission adaptation, the UE 22 operating in a transmission arrangement incorporating PA nonlinearity (NL) compensation [e.g., DPoD] in a network node 16, the method comprising: a. receiving from the network node 16 a transmission modification parameter, e.g., PA backoff relaxation value, based on a PA compensation mode applied in the network node 16, b. transmitting a signal to the network node 16 based on the transmission modification parameter. c. + further signaling to the network node 16 a transmission characteristics and modification capability information. d. + the capability signaling includes one or more of the following modification aspects: MPR relaxation ability, backoff adaptation ability, etc., determined by factors such as modulation, waveform, FR, resource allocation, etc. e. + the capability signaling includes one or more of the following transmission characteristics aspects: PA type / technology, default non-linearity curve [parametric description, non-parametric description, closest predefined category], default distortion metric value, these curves / metrics when different degree of PA linearization, e.g. DPD, is applied etc. f. + the received transmission modification parameter (of Embodiment 1) is based on the capability information.

[0114] Embodiment 2. Embodiment 1 + the transmission modification parameter comprises one or more of: PA backoff relaxation value, PA backoff value, permissible PA non-linearity metric value, permissible in-band distortion metric value, . . . a. + the modification parameter depends on one or more of: modulation, frequency range, UE 22 PA type and power class, multi -carrier configuration, scheduled PRB location in the carrier, spatial multiplexing mode, transmission waveform, ... b. + the modification parameter is expressed as one or more of: an explicit parameter value, a lookup index to predefined [specified] configuration or parameter list, a lookup index to preconfigured [RRC] configuration or parameter list, . . .

[0115] Embodiment 3. Embodiments 1 and / or 2, + further receiving from the network node 16, a command to initiate the transmission modification, and starting the transmission modification based on the transmission modification parameter [previously obtained].

[0116] Embodiment 4. One or more of Embodiments 1-3, + further receiving from the network node 16 a delay value for initiating the transmission modification, and starting the transmission modification based on the delay value after receiving the transmission modification parameter or a command to initiate the transmission modification.

[0117] Embodiment 5. One or more of Embodiments 1-4,+ (also mirror embodiments on parameter types, capability signaling, triggering command, delay, etc.)

[0118] Embodiment 6. One or more of Embodiments 1-5,+ applying the PA nonlinearity compensation mode to the received signal.

[0119] Embodiment 7. One or more of Embodiments 1-6,+ the PA compensation mode is activated if it is supported by the network node 16 implementation, and it is indicated in the capability signaling by the UE 22, i.e., the intersection figure.

[0120] As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and / or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step, action and / or functionality described herein may be performed by, and / or associated to, a corresponding module, which may be implemented in software and / or firmware and / or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that may be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD-ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.

[0121] Some embodiments are described herein with reference to flowchart illustrations and / or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a special purpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0122] These computer program instructions may also be stored in a computer readable memory or storage medium that may direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0123] The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0124] It is to be understood that the functions / acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality / acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows.

[0125] Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, Java® or C++. However, the computer program code for carrying out operations of the disclosure may also be written in conventional procedural programming languages, such as the "C" programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0126] Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments may be combined in any way and / or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.

[0127] It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings.

[0128] EXAMPLE EMBODIMENTS

[0129] Embodiment Al . A transmitter configured to communicate with a receiver, the transmitter configured to, and / or comprising a radio interface and / or comprising processing circuitry configured to: receive from the receiver a transmission modification parameter, the transmission modification parameter being based at least in part on a power amplifier (PA) compensation mode applied at the receiver; and transmit a signal to the receiver based at least in part on the transmission modification parameter.

[0130] Embodiment A2. The transmitter of Embodiment Al, wherein the transmitter, radio interface and / or processing circuitry are configured to transmit to the receiver transmission characteristics and modification capability information.

[0131] Embodiment A3. The transmitter of Embodiment A2, wherein the modification capability information includes at least one of a maximum power reduction relaxation ability and a backoff adaptation ability. Embodiment A4. The transmitter of any of Embodiments A2 and A3, wherein the modification capability information is based at least in part on at least one of modulation, waveform, frequency range and resource allocation.

[0132] Embodiment A5. The transmitter of any of Embodiments A2-A4, wherein the transmission characteristics include at least one of power amplifier type, a non-linearity technique, a parametric description, a non-parametric description, a closed predefined category and a default distortion metric value.

[0133] Embodiment A6. The transmitter of any of Embodiments A2-A5, wherein the received transmission modification parameter is based at least in part on the modification capability information.

[0134] Embodiment A7. The transmitter of any of Embodiments A1-A6, wherein the transmission modification parameter includes one or more of a power amplifier (PA) backoff relaxation value, a PA backoff value, a permissible PA non-linearity metric value, and a permissible in-band distortion metric value.

[0135] Embodiment A8. The transmitter of any of Embodiments A1-A7, wherein the transmission modification parameter is based at least in part on at least one of a modulation, a frequency range, a transmitter power amplifier (PA) type and power class, a multi -carrier configuration, a scheduled physical resource block location, a spatial multiplexing mode and a transmission waveform.

[0136] Embodiment A9. The transmitter of any of Embodiments A1-A8, wherein the transmission modification parameter is indicated by UE assistance information (UAI) that includes at least one of an explicit parameter value, a lookup index to a parameter list and a lookup index to a preconfigured radio resource control (RRC) configuration.

[0137] Embodiment A10. The transmitter of any of Embodiments A1-A9, wherein the transmitter, radio interface and / or processing circuitry are configured to initiate a transmission modification based at least in part on at least one of the transmission modification parameter and a delay value for starting the transmission modification. Embodiment Al 1. The transmitter of any of Embodiments A1-A10, wherein the PA compensation mode includes digital pre-distortion (DPD).

[0138] Embodiment Bl. A method implemented in a transmitter that is configured to communicate with a receiver, the method comprising: receiving from the receiver a transmission modification parameter, the transmission modification parameter being based at least in part on a power amplifier (PA) compensation mode applied at the receiver; and transmitting a signal to the receiver based at least in part on the transmission modification parameter.

[0139] Embodiment B2. The method of Embodiment Bl, further comprising transmitting to the receiver transmission characteristics and modification capability information.

[0140] Embodiment B3. The method of Embodiment B2, wherein the modification capability information includes at least one of a maximum power reduction relaxation ability and a backoff adaptation ability.

[0141] Embodiment B4. The method of any of Embodiments B2 and B3, wherein the modification capability information is based at least in part on at least one of modulation, waveform, frequency range and resource allocation.

[0142] Embodiment B5. The method of any of Embodiments B2-B4, wherein the transmission characteristics include at least one of power amplifier type, a non-linearity curve, a parametric description, a non-parametric description, a closed predefined category and a default distortion metric value.

[0143] Embodiment B6. The method of any of Embodiments B2-B5, wherein the received transmission modification parameter is based at least in part on the modification capability information. Embodiment B7. The method of any of Embodiments B1-B6, wherein the transmission modification parameter includes one or more of a power amplifier (PA) backoff relaxation value, a PA backoff value, a permissible PA non-linearity metric value, and a permissible in-band distortion metric value.

[0144] Embodiment B8. The method of any of Embodiments B1-B7, wherein the transmission modification parameter is based at least in part on at least one of a modulation, a frequency range, a transmitter power amplifier (PA) type and power class, a multi -carrier configuration, a scheduled physical resource block location, a spatial multiplexing mode and a transmission waveform.

[0145] Embodiment B9. The method of any of Embodiments B1-B8, wherein the transmission modification parameter is indicated by UE assistance information (UAI) that includes at least one of an explicit parameter value, a lookup index to a parameter list and a lookup index to a preconfigured radio resource control (RRC) configuration.

[0146] Embodiment BIO. The method of any of Embodiments B1-B9, further comprising initiating a transmission modification based at least in part on at least one of the transmission modification parameter and a delay value for starting the transmission modification.

[0147] Embodiment B 11. The transmitter of any of Embodiments B 1 -B 10, wherein the

[0148] PA compensation mode includes digital pre-distortion (DPD).

[0149] Embodiment Cl . A receiver configured to communicate with a transmitter, the receiver configured to, and / or comprising a radio interface and / or processing circuitry configured to: apply a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model, the AI / ML model configured to determine a transmission modification parameter, the transmission modification parameter including at least one of a backoff relaxation value, a PA backoff value, a permissible PA non-linearity metric value, and a permissible in-band distortion metric value; and transmit to the transmitter the transmission modification parameter. Embodiment C2. The receiver of Embodiment Cl, wherein the receiver, radio interface and / or processing circuitry are configured to receive from the transmitter, transmission characteristics and modification capability information.

[0150] Embodiment C3. The receiver of Embodiment C2, wherein the modification capability information includes at least one of a maximum power reduction relaxation ability and a backoff adaptation ability.

[0151] Embodiment C4. The receiver of any of Embodiments C2 and C3, wherein the modification capability information is based at least in part on at least one of modulation, waveform, frequency range and resource allocation.

[0152] Embodiment C5. The receiver of any of Embodiments C2-C4, wherein the transmission characteristics include at least one of power amplifier type, a non-linearity curve, a parametric description, a non-parametric description, a closed predefined category and a default distortion metric value.

[0153] Embodiment C6. The receiver of any of Embodiments C2-C5, wherein the transmitted transmission modification parameter is based at least in part on the modification capability information.

[0154] Embodiment C7. The receiver of any of Embodiments C1-C6, wherein the transmission modification parameter is based at least in part on at least one of a modulation, a frequency range, a transmitter power amplifier (PA) type and power class, a multi -carrier configuration, a scheduled physical resource block location, a spatial multiplexing mode and a transmission waveform.

[0155] Embodiment C8. The receiver of any of Embodiments C1-C7, wherein the transmission modification parameter is indicated by UE assistance information (UAI) that includes at least one of an explicit parameter value, a lookup index to a parameter list and a lookup index to a preconfigured radio resource control (RRC) configuration.

[0156] Embodiment C9. The receiver of any of Embodiments C1-C8, wherein the PA compensation mode includes digital post-distortion (DPoD). Embodiment DI . A method implemented in a receiver that is configured to communicate with a transmitter, the method comprising: applying a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model, the AI / ML model configured to determine a transmission modification parameter, the transmission modification parameter including at least one of a backoff relaxation value, a PA backoff value, a permissible PA non-linearity metric value, and a permissible in-band distortion metric value; and transmitting to the transmitter the transmission modification parameter.

[0157] Embodiment D2. The method of Embodiment DI, further comprising receiving from the transmitter, transmission characteristics and modification capability information.

[0158] Embodiment D3. The method of Embodiment D2, wherein the modification capability information includes at least one of a maximum power reduction relaxation ability and a backoff adaptation ability.

[0159] Embodiment D4. The method of any of Embodiments D2 and D3, wherein the modification capability information is based at least in part on at least one of modulation, waveform, frequency range and resource allocation.

[0160] Embodiment D5. The method of any of Embodiments D2-D4, wherein the transmission characteristics include at least one of power amplifier type, a non-linearity curve, a parametric description, a non-parametric description, a closed predefined category and a default distortion metric value.

[0161] Embodiment D6. The method of any of Embodiments D2-D5, wherein the transmitted transmission modification parameter is based at least in part on the modification capability information.

[0162] Embodiment D7. The method of any of Embodiments D1-D6, wherein the transmission modification parameter is based at least in part on at least one of a modulation, a frequency range, a transmitter power amplifier (PA) type and power class, a multi -carrier configuration, a scheduled physical resource block location, a spatial multiplexing mode and a transmission waveform.

[0163] Embodiment D8. The method of any of Embodiments D1-D7, wherein the transmission modification parameter is indicated by UE assistance information (UAI) that includes at least one of an explicit parameter value, a lookup index to a parameter list and a lookup index to a preconfigured radio resource control (RRC) configuration.

[0164] Embodiment D9. The receiver of any of Embodiments D1-D8, wherein the PA compensation mode includes digital post-distortion (DPoD).

Claims

CLAIMS1. A method (800) implemented in a transmitting node (22) that is configured to communicate with a receiving node (16) for model inference configurations for artificial intelligence / machine language, AI / ML, based digital post distortion, DPoD, the method comprising: receiving (802) from the receiving node (16) a transmission modification parameter, the transmission modification parameter being based at least in part on a power amplifier, PA, compensation mode applied at the receiving node; and transmitting (804) a signal to the receiving node, the signal transmitted is based at least in part on the transmission modification parameter.

2. The method of claim 1, wherein the transmission modification parameter includes one or more of a power backoff relaxation value, a power backoff value.

3. The method of claim 1, wherein transmitting the signal to the receiving node further comprising transmitting to the receiving node transmission characteristics and modification capability information.

4. The method of claim 3, wherein the modification capability information includes at least one of a maximum power reduction relaxation ability and a power backoff relaxation adaptation ability.

5. The method of claim 3 or 4, wherein the modification capability information is based at least in part on at least one of modulation, waveform, frequency range and resource allocation.

6. The method of claim 2 or 4, wherein the amount of power backoff relaxation is different for different frequency ranges.

7. The method of claim 2 or 4, wherein the amount of power backoff relaxation is different for different resource allocations.

8. The method of claim 2 or 4, wherein the amount of power backoff relaxation is different based at least in part on at least one of full duplex operation, in-device coexistence (IDC), waveform used by the transmitter.

9. The method of claim 2 or 4, wherein the amount of power backoff relaxation is provided for each modulation order and does not vary.

10. The method of any of Claims 3-9, wherein the transmission characteristics include at least one of power amplifier type, a non-linearity curve, a parametric description, a non-parametric description, a closed predefined category and a default distortion metric value.

11. The method of any of Claims 1-10, wherein the received transmission modification parameter is based at least in part on modification capability information.

12. The method of any of Claims 1-11, wherein the transmission modification parameter includes one or more of a power amplifier (PA) backoff relaxation value, a PA backoff value, a permissible PA non-linearity metric value, and a permissible in- band distortion metric value.

13. The method of any of Claims 1-12, wherein the transmission modification parameter is based at least in part on at least one of a modulation, a frequency range, a transmitter power amplifier (PA) type and power class, a multi-carrier configuration, a scheduled physical resource block location, a spatial multiplexing mode and a transmission waveform.

14. The method of any of Claims 1-13, wherein the transmission modification parameter is indicated by UE assistance information (UAI) that includes at least one of an explicit parameter value, a lookup index to a parameter list and a lookup index to a preconfigured radio resource control (RRC) configuration.

15. The method of any of Claims 1-14, further comprising initiating a transmission modification based at least in part on at least one of the transmission modification parameter and a delay value for starting the transmission modification.

16. A transmitting node (22), for model inference configurations for artificial intelligence / machine language, AI / ML, based digital post distortion, DPoD, configured to communicate with a receiving node (16), the transmitting node comprising a radio interface and / or comprising processing circuitry configured to: receive from the receiving node a transmission modification parameter, the transmission modification parameter being based at least in part on a power amplifier (PA) compensation mode applied at the receiving node; andtransmit a signal to the receiving node based at least in part on the transmission modification parameter.

17. The transmitting node of Claim 15, further adapted to perform any of the methods of Claims 2 to 15.

18. A method (700) implemented in a receiving node (16) that is configured to communicate with a transmitting node (22), for model inference configurations for artificial intelligence / machine language, AI / ML, based digital post distortion, DPoD, the method comprising: applying (702) a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model, the AI / ML model configured to determine a transmission modification parameter; and transmitting (704) to the transmitting node (22) the transmission modification parameter.

19. The method of claim 18 wherein, the transmission modification parameter includes at least one of a power backoff relaxation value, a PA backoff value, a permissible PA non-linearity metric value, and a permissible in-band distortion metric value.

20. The method of claim 18, further comprising receiving from the transmitting node, transmission characteristics and modification capability information.

21. The method of Claim 20, wherein the modification capability information includes at least one of a maximum power reduction relaxation ability and a power backoff relaxation adaptation ability.

22. The method of any of Claims 20-21, wherein the modification capability information is based at least in part on at least one of modulation, waveform, frequency range and resource allocation.

23. The method of claim 19 or 21, wherein the amount of power backoff relaxation is different for different frequency ranges.

24. The method of claim 19 or 21, wherein the amount of power backoff relaxation is different for different resource allocations.

25. The method of claim 19 or 21, wherein the amount of power backoff relaxation is different based at least in part on at least one of: full duplex operation, in-device coexistence (IDC), waveform used by the transmitter.

26. The method of claim 19 or 21, wherein the amount of power backoff relaxation is provided for each modulation order and does not vary.

27. The method of any of Claims 20-26, wherein the transmission characteristics include at least one of power amplifier type, a non-linearity curve, a parametric description, a non-parametric description, a closed predefined category and a default distortion metric value.

28. The method of any of Claims 18-27, wherein the transmitted transmission modification parameter is based at least in part on modification capability information.

29. The method of any of Claims 18-28 wherein the transmission modification parameter is based at least in part on at least one of a modulation, a frequency range, a transmitter power amplifier (PA) type and power class, a multi-carrier configuration, a scheduled physical resource block location, a spatial multiplexing mode and a transmission waveform.

30. The method of any of Claims 18-29, wherein the transmission modification parameter is indicated by UE assistance information (UAI) that includes at least one of an explicit parameter value, a lookup index to a parameter list and a lookup index to a preconfigured radio resource control (RRC) configuration.

31. A receiving node (16), for model inference configurations for artificial intelligence / machine language, AI / ML, based digital post distortion, DPoD, configured to communicate with a transmitter, the receiving node comprising a radio interface and / or processing circuitry configured to: apply a power amplifier (PA) compensation mode based at least in part on an artificial intelligence / machine learning (AI / ML) model, the AI / ML model configured to determine a transmission modification parameter; and transmit to the transmitting node the transmission modification parameter.

32. The receiving node of Claim 31, further adapted to perform any of the methods of Claims 19 to 30.

Images