Transmitter and receiver for dpod compensation and methods thereof

Abstract

A method, transmitter and receiver for lowering out of band emissions and power amplifier post distortion compensation are disclosed According to one aspect, a method in a receiver includes receiving from a transmitter an orthogonal frequency division multiplexed (OFDM) signal. The method also includes implementing an Artificial Intelligence (AI) model, the AI model configured to adapt digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter.

Description

[0001] TRANSMITTER AND RECEIVER FOR DPOD COMPENSATION AND METHODS THEREOF

[0002] This application claims the benefit of and priority to U.S. provisional patent application No. 63 / 690617, filed 9 / 4 / 2024, entitled “METHOD FOR LOWERING OUT OF BAND EMISSION AND POWER AMPLIFIER POST DISTORTION COMPENSATION”, the disclosure of which is hereby incorporated herein by reference in its entirety.

[0003] TECHNICAL FIELD

[0004] The present disclosure relates to wireless communications, and in particular, to methods for digital post distortion compensation adapting for out-of-band emission suppression.

[0005] BACKGROUND

[0006] 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.

[0007] Receiver methods

[0008] A receiver, as this term is used in this disclosure may refer to an entity that receives certain transmitted data and detects the transmitted data. The data may be transmitted over a wireless channel, through an optical fiber, or through wired channel, for example. The received data may be subject to some distortions depending on the transmission medium and the hardware at transmitter and receiver. The receivers usually experience conditions over time and / or frequency and / or space that are unknown and need to be estimated to achieve optimal performance. These conditions may also vary, over e.g., time or frequency. Under each condition, the receiver may possibly operate in different ways to cope with underlying conditions.

[0009] Machine learning

[0010] 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. The machine learning algorithms are classified into online and offline algorithms, where the offline algorithms are relying 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 is paired with a corresponding labeled output .

[0011] Artificial neural networks

[0012] 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 Artificial Intelligence (Al) accelerator hardware. A neural network is based on interconnected processing units called neurons as depicted in FIG. 1, where each neuron (shown as a circle) receives a 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.

[0013] Machine learning methods may be used at the receiver to optimize one or multiple functionalities at the receiver. For example, a machine learning receiver method based on neural networks (NN) has been 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.

[0014] A 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.) estimate 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. 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. Spectrally pre-coded OFDM

[0015] Orthogonal Frequency Division Multiplexing (OFDM) is a digital multi-carrier modulation technique widely used in modem telecommunications, including Wi-Fi, LTE, and 5G networks. OFDM splits the available spectrum into numerous orthogonal subcarriers, each modulated with a portion of the user's data stream, allowing efficient utilization of bandwidth and reducing interference. OFDM's resistance to channel fading and ability to handle high data rates make it ideal for environments with multipath propagation. The implementation of OFDM involves an inverse fast Fourier transform (IFFT) at the transmitter and a fast Fourier transform (FFT) at the receiver, to provide efficient signal processing.

[0016] One of the drawbacks of traditional OFDM is its relatively high levels of out-of- band (OOB) emissions, leading to significant interference with adjacent frequency bands. This issue is related to the viability of OFDM in future communication systems and standards, particularly with multi radio access technology (RAT) in midband, where multiple radio systems must coexist harmoniously within densely packed spectrum bands.

[0017] There have been several approaches to reduce OOB of the OFDM signal. Several precoding schemes are discussed in the literature to suppress OOB emissions by modulating subcarriers with carefully selected pre-coded data symbols. Pre-coding schemes both in the time domain and also in the frequency domain are considered, where in time domain precoding an objective is to make the OFDM signal continuous in time, along with its N-derivatives, by forcing the edges of the OFDM symbol to zero. A goal of frequency-domain precoding is to introduce nulls at specific frequencies in the OFDM spectrum. The OOB emission characteristics of different pre-coded OFDM schemes compared with the plain OFDM scheme are shown in the example of FIG. 5.

[0018] With respect to FIGS. 5-7, reference is made to "An analysis of out-of-band emission and in-band interference for precoded and classical OFDM systems," Proceedings of European Wireless 2015; 21st European Wireless Conference, Budapest, Hungary, 2015, pp. 1-5.

[0019] The pre-coded OFDM schemes, however, lead to additional in-band distortion to the signal. FIG. 6 shows the in-band distortion for different pre-coded OFDM schemes. This leads to the degraded performance as shown in FIG. 7 for different schemes.

[0020] SUMMARY Some embodiments advantageously provide methods, transmitters and receivers for post distortion compensation at the receivers dealing with PA nonlinearity caused by precoding for lowering out of band emissions at the transmitters.

[0021] Some embodiments include a method for coordinated precoding of the transmit signal at a transmitter (for example, a UE) to lower the out of band (OOB) emission and performing digital post distortion (DPoD) at a receiver (for example, a network node) to compensate for in-band distortions. Some methods disclosed include compensating for in- band distortions while limiting the out of band distortions caused by OOB emission. This may enable the transmitter to increase transmit power and operate in a more nonlinear regime and benefit from enhance coverage and power efficiency.

[0022] For uplink transmissions, some embodiments enable the transmitter to lower the out of band (OOB) emissions and support digital post distortion (DPoD) at the receiver to compensate for in-band distortions. This may include compensating for in-band distortions contributed by the methods at the transmitter to lower OOB emission. In some embodiments, in-band distortions are compensated while limiting the out of band emission. This may enable the transmitter to increase transmit power and operate in more nonlinear regime and benefit from enhanced coverage and power efficiency. Some embodiments include methods at the transmitter to lower OOB emission, DPoD methods at the receiver to compensate for in band distortion, and a method to coordinate these operations.

[0023] In one aspect, a method implemented in a transmitter of wireless signals is provided by the present disclosure. The transmitter obtains a precoding approach to be applied for suppressing OOB emission, and performs the precoding approach on scheduled data to be transmitted. Then, it performs OFDM modulation on the precoded data to form OFDM data symbols and transmit them to a receiver.

[0024] In another aspect, a method implemented in a receiver of wireless signals is provided by the present disclosure. The receiver receives OFDM data symbols which have been precoded for suppressing OOB emission. It then applies to an Al model of DPoD compensation for compensating in-band distortion caused by the precoding for the OFDM data symbols.

[0025] In yet another aspect, the present disclosure provides a transmitter configured to implement the methods described in the disclosure. The transmitter applies a precoder prior to OFDM modulation for scheduled data where the precoder is applied for OOB emission suppression. In meanwhile, by providing indication information of the precoder to an Al model at the receiver, it provides training datasets for training the Al model.

[0026] In yet another aspect, the present disclosure provides a receiver configured to implement the methods described in the disclosure, wherein ODFM symbols have been precoded prior to the OFDM modulation for suppressing OOB emission. And the Al model deployed by the receiver can provide DPoD compensation for in-band distortion caused by the precoding at the transmitter side.

[0027] This disclosure provides a coordinated approach for precoding of the transmitted signals to lower OOB emission by using Al model for DPoD compensation for the precoding method. The transmitter can thus increase its transmission power and gain benefit from enhanced coverage and power efficiency.

[0028] BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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 wherein:

[0030] FIG. 1 is an artificial neural network according to known approaches;

[0031] FIG. 2 is an example receiver chain with machine learning according to known approaches;

[0032] FIG. 3 is a neural network for soft demapping according to known approaches;

[0033] FIG. 4 is one illustration of a neural network based demapper performance according to known disclosure;

[0034] FIG. 5 is an illustration of out of band (OOB) emission characteristics of different pre-coded orthogonal frequency division multiplexing (OFDM) schemes according to known disclosure;

[0035] FIG. 6 shows in-band distortion for different pre-coded OFDM schemes which lead to degraded performances as shown in FIG. 7 according to known disclosure;

[0036] FIG. 7 shows degraded performances lead by different pre-coded OFDM schemes corresponding to FIG. 6 according to known disclosure;

[0037] FIG. 8 is a schematic diagram of an example network architecture illustrating a communication system according to principles disclosed herein; FIG. 9 is 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;

[0038] FIG. 10 is a flowchart of an example process in a transmitter for methods for lowering out of band emissions and power amplifier post distortion compensation according to some embodiments of the present disclosure;

[0039] FIG. 11 is a flowchart of an example process in a receiver for methods for lowering out of band emissions and power amplifier post distortion compensation according to some embodiments of the present disclosure;

[0040] FIG. 12 is a flowchart of another example process in a transmitter for methods for lowering out of band emissions and power amplifier post distortion compensation according to some embodiments of the present disclosure;

[0041] FIG. 13 is a flowchart of another example process in a receiver for methods for lowering out of band emissions and power amplifier post distortion compensation according to some embodiments of the present disclosure; and

[0042] FIG. 14 is a timing diagram of a process for the realization of some embodiments disclosed herein.

[0043] DETAILED DESCRIPTION

[0044] Before describing in detail example embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to methods for lowering out of band emissions and power amplifier post distortion compensation. 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.

[0045] As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0046] In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate electrical or data communication, which may be accomplished by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling or optical signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate, and modifications and variations are possible of achieving the electrical and data communication.

[0047] The term “network node” used herein may be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, base transceiver station (BTS), base station controller (BSC), radio network controller (RNC), g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multistandard radio (MSR) radio node such as MSR BS, multi-cell / multicast coordination entity (MCE), relay node, donor node controlling relay, radio access point (AP), AP STA, transmission points, transmission nodes, Remote Radio Unit (RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), self-organizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also comprise test equipment. The term “radio node” used herein may be used to also denote a user equipment (UE) such as a wireless device (WD) or a radio network node. Thus, the term “network node” as used herein, includes 3GPP radio base stations, such as gNBs, and includes Wi-Fi AP STAs.

[0048] 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) and / or non-AP STA. The UE may also be a radio communication device, target device, device to device (D2D) UE, 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. Thus, the term “UE” as used herein, includes 3GPP UEs and / or Wi-Fi non-AP STAs.

[0049] 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).

[0050] Note that although terminology from one particular wireless system, such as, for example, 3GPP LTE and / or New Radio (NR), may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system.

[0051] 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.

[0052] 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.

[0053] Digital post distortion (DPoD) compensation has been shown to be effective to compensate for the in-band distortions due to power amplifier (PA) nonlinearity at a receiver (e.g., a gNB receiving uplink transmissions from a UE). This enables the PA to increase transmit power and operate in a more nonlinear regime. This may lead to enhanced coverage and higher power efficiency (e.g., UE power efficiency in UL transmission). However, in some scenarios, the requirements on out of band (OOB) emissions are limiting a transmitter (e.g., a UE transmitting on the UL) to increase the transmit power and push the PA to the nonlinear operating regime. Hence, the transmitter (e.g., UE) may not benefit from the DPoD capability in the receiver.

[0054] Embodiments in the present disclosure present a solution that a method for lowering OOB emission at a transmitter, e.g., precoding, that increases in-band distortion can work together with a method at a receiver, e.g., DPoD, to compensate the in-band distortion. Some embodiments are directed to methods at the receivers dealing with PA nonlinearity caused by precoding for suppressing out of band emissions at the transmitters.

[0055] In some embodiments, application of methods disclosed herein to UL transmissions may provide one or more of the following advantages:

[0056] • Enable the transmitter to increase its output power and hence operate in a more nonlinear operating regime while complying with out of band emission requirements;

[0057] • The increased output power of the transmitter which may be enabled by this feature would lead to enhanced coverage;

[0058] • The operation of the transmitter in a more nonlinear regime enabled by this feature may lead to higher power efficiency, and hence increased transmitter battery lifetime;

[0059] • Lowering OOB emission enabled by this feature may enable scheduling the UEs on adjacent physical resource blocks (PRBs) and hence may enhance the spectral efficiency of the system.

[0060] Returning to the figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 8 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), or a Wi-Fi Fi network, 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, AP STAs, 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.

[0061] 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 and / or a Wi-Fi network. 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 AP STA.

[0062] A network node 16 may be configured to include an Al unit 24 which is configured to implement an Artificial Intelligence (Al) model. The Al model implemented by Al unit 24 is configured to adapt digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter. A user equipment 22 may be configured to include an OOB unit 26 which is configured to modify an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions. When operating in a sidelink mode, the UE 22 may also include the Al unit 24 to suppress in-band distortion in an OFDM signal received from another UE 22.

[0063] Example implementations, in accordance with an embodiment, of the UE 22 and network node 16 discussed in the preceding paragraphs will now be described with reference to FIG. 9.

[0064] The communication system 10 includes a 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 UE 22 located in a coverage area 18 served by the 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.

[0065] In the embodiment shown, the hardware 28 of the 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 FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) 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 RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0066] Thus, the 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 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 network node 16. Processor 38 corresponds to one or more processors 38 for performing 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 network node 16. For example, processing circuitry 36 of the network node 16 may include Al unit 24 which is configured to implement an Artificial Intelligence (Al) model in which the Al model is configured to adapt digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter.

[0067] The communication system 10 further includes the UE 22 already referred to. The 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 network node 16 serving a coverage area 18 in which the 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.

[0068] The hardware 44 of the 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 FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) 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 RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0069] Thus, the UE 22 may further comprise software 56, which is stored in, for example, memory 54 at the UE 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the 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 UE 22.

[0070] 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 UE 22. The processor 52 corresponds to one or more processors 52 for performing UE 22 functions described herein. The 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 UE 22. For example, the processing circuitry 50 of the user equipment 22 may include OOB unit 26 which is configured to modify an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions. As noted above, when operating in a sidelink mode, the UE 22 may also include the Al unit 24 to suppress in-band distortion in an OFDM signal received from another UE 22.

[0071] In some embodiments, the inner workings of the network node 16 and UE 22 may be as shown in FIG. 9 and independently, the surrounding network topology may be that of FIG. 8.

[0072] The wireless connection 32 between the UE 22 and the 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.

[0073] Although FIGS. 8 and 9 show various “units” such as Al unit 24 and OOB 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.

[0074] FIG. 10 is a flowchart of an example process in a transmitter, e.g., a UE 22, configured according to principles disclosed herein. One or more blocks described herein may be performed by one or more elements of the transmitter, e.g., user equipment 22, such as by one or more of processing circuitry 50 (including the OOB unit 26), processor 52, and / or radio interface 46. The transmitter, e.g., UE 22 such as via processing circuitry 50 and / or processor 52 and / or radio interface 46 is configured to modifying an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions (Block S10). The process includes transmitting the modified OFDM signal to a receiver (Block S12). The process further includes transmitting information to the receiver to be used in an Artificial Intelligence (Al) model implemented at the receiver to suppress in- band distortion in the transmitted modified OFDM signal caused by modifying the OFDM signal to suppress OOB emissions (Block S14).

[0075] In general, if the OOB emission suppression method requires the receiver to know the transmitter operation, then either (1) the receiver (e.g., at the network node) makes the transmission operation choice for the transmitter (e.g., at the UE) and signal the choice to the transmitter (at the UE), or (2) the transmitter (at the UE) makes its own transmission operation choice and signals its choice to the receiver (at the network node). The transmitted information would be included in those signals, either being used as input for training the Al model, or input for deployment of the Al model.

[0076] In some embodiments, the information includes an indication of a precoding choice of the transmitter. In some embodiments, the precoding choice is one of time domain precoding, frequency precoding, spectral decoding and no precoding. In some embodiments, the information includes an indication of a level of distortion caused by modifying the OFDM signal to suppress OOB emissions. In some embodiments, the information includes an indication of a method used by the transmitter to modify the OFDM signal to suppress OOB emissions. FIG. 11 is a flowchart of an example process in a receiver, e.g., a network node 16, according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of the receiver, e.g., network node 16, such as by one or more of processing circuitry 36 (including the Al unit 24), processor 38, and / or radio interface 30. The receiver, e.g., network node 16, such as via processing circuitry 36 and / or processor 38 and / or radio interface 30 is configured to receive from a transmitter an orthogonal frequency division multiplexed (OFDM) signal (Block SI 6). The process includes implementing an Artificial Intelligence (Al) model, the Al model configured to adapt digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter (Block SI 8). In some arrangements, such as for sidelink communications, the receiver can be a UE 22, and the functions performed by one or more of processing circuitry 50 (including the OOB unit 26), processor 52, and / or radio interface 46.

[0077] In some embodiments, the process includes training the Al model based at least in part on a training data set that includes effects of a plurality of OOB emission suppression techniques. In some embodiments, inputs to the Al model include an OOB suppression method applied by at least one transmitter. In some embodiments, inputs to the Al model include at least one precoding choice of at least one transmitter, a precoding choice being one of time domain precoding, frequency precoding, spectral decoding and no precoding. In some embodiments, inputs to the Al model include indications of distortion levels received from at least one transmitter. In some embodiments, inputs to the Al model include subcarrier indices indicating subcarriers to which an OOB emission method is applied at a transmitter, for at least one transmitter. In some embodiments, inputs to the Al model include an indication of subcarrier location within a frequency band for at least one transmitter.

[0078] FIG. 12 is a flowchart of another example process in a transmitter (e.g., UE 22) configured according to principles disclosed herein. One or more blocks described herein may be performed by one or more elements of the transmitter such as by one or more of processing circuitry 50 (including the OOB unit 26), processor 52, and / or radio interface 46 of UE 22. The transmitter, such as via processing circuitry 50 and / or processor 52 and / or radio interface 46 is configured to modify an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions (Block S10). The process includes modifying an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions (Block S20). The process includes transmitting the modified OFDM signal to a receiver (Block S22). The process further optionally includes transmitting information to the receiver, wherein the information indicates a precoding matrix applied by the transmitter for modifying the OFDM signal (Block S24).

[0079] FIG. 13 is a flowchart of another example process in a receiver (e.g., network node 16) according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of the receiver such as by one or more of processing circuitry 36 (including the Al unit 24), processor 38, and / or radio interface 30 of network node 16. The receiver, such as via processing circuitry 36 and / or processor 38 and / or radio interface 30 is configured to receive from a transmitter an orthogonal frequency division multiplexed (OFDM) signal (Block S26). The process further optionally includes receiving from the transmitter information indicating a precoding matrix applied by the transmitter for modifying the OFDM signal (Block S28). The process includes implementing digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter (Block S30). In some arrangements, such as for sidelink communications, the receiver can be a UE 22, and the functions performed by one or more of processing circuitry 50 (including the OOB unit 26), processor 52, and / or radio interface 46.

[0080] 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 methods for lowering out of band emissions and power amplifier post distortion compensation.

[0081] 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 Al model, AEML model and DPoD model may be used interchangeably. The Al model is performed by the Al unit 24.

[0082] In the following embodiments, a transmitter is configured to suppress OOB emission when transmitting an OFDM signal. This may be done with or without the coordination of a receiver. Suppression of OOB emission may cause a loss of orthogonality between subcarriers of the OFDM signal. This loss of orthogonality causes inter-carrier interference, which causes in-band distortion of the transmitted OFDM signal. The in-band distortion has been treated as noise in known approaches, but known approaches do not adequately mitigate or compensate for the in-band distortion. In the following embodiments, methods for in-band distortion compensation using an Al model at the receiver are described. Compensation of in-band distortion enables the transmitter power amplifier to operate in a more non-linear regime, thereby increasing output power and coverage. Methods disclosed herein compensate for the in-band distortions due to transmitter power amplifier (PA) nonlinearity and also compensate for the loss of orthogonality of the OFDM subcarriers. Known methods for compensating for PA nonlinearity do not also compensate for the nonorthogonality of the OFDM subcarriers. Also, embodiments described below enable DPoD in midband where the OOB is a limiting factor.

[0083] In some embodiments, compensation for this in-band distortion is achieved by coordination between the transmitter and receiver, such that the Al model used for DPoD compensation may be of lower complexity. In some embodiments, the Al model is trained with a range of precoding types, subcarrier locations and quality indicators. Then, during an inference stage, values of these parameters, which may be referred to generally as contextual information, are received from one or more UEs and used as inputs to the Al model.

[0084] Embodiment 1 : Coordinated DPoD and precoding for OOB emission suppression with a codebook

[0085] In the following, a method is provided for coordinated DPoD and precoding for out-of-band (OOB) emission suppression. The precoding for OOB emission suppression is applied at the transmitter, and the digital post distortion (DPoD) compensation is applied at the receiver. The DPoD compensation attempts to remove signal distortion caused by the transmitter chain, including the distortion caused by the precoding for OOB emission suppression.

[0086] While in general, the method may be applied to any transmission-reception link, the method is described below using uplink transmission as a non-limiting example, where the transmitter is a device (called UE 22 in the discussion), and the receiver is a base station (called network node 16 in the discussion). It is understood that the same methodology may be applied to other scenarios, including:

[0087] • Downlink, where the transmitter is a base station network node 16, and the receiver is a device. Side link, the transmitter and the receiver are two peer devices, e.g.,

[0088] UEs 22.

[0089] A method for coordinated precoding of the transmit signal at the UE 22 and performing digital post distortion (DPoD) compensation at the network node 16 is provided, where:

[0090] • the precoding is performed to suppress the out-of-band (OOB) emission through precoding of the symbols that modulate the subcarriers for OFDM symbols. In the case of precoding in the frequency domain, controlled weights are applied to the data symbols before modulating the subcarriers. The ith pre-coded OFDM symbol may be computed as follows:

[0091] T where at= [a^, a2 i, ... , is the pre-coded data symbol vector constructed as follows: at= Gdi and where dtis the data symbol vector and G is the precoding matrix. The precoder matrix G may be designed to achieve nulling of the power spectral density of the modulated signal at a certain set of frequencies. The pre-coded OFDM modulations is illustrated in the following: o A set of precoding matrices may be designed, G , G2, ... GM, where the precoding matrices have different capabilities to lower the OOB emissions. For example, each precoding matrix may lead to a certain number of nulls in the spectrum of the modulated signal, where the number of nulls is different across different precoding matrices. For example, applying G-j C n create one null in the spectrum of the signal and create relatively the largest OOB emissions among these matrices, and GMmay create M nulls (M»l) in the spectrum of the signal and create the lowest OOB emissions among the precoding matrices; o The precoding is not limited to the frequency domain and certain precoding may be applied in the time domain to lower the OOB emissions; o The precoding of the data symbols causes in-band distortion in the OFDM system. This contributes to additional in-band distortions to the signal e.g., the ones due to PA nonlinearity; o The precoding matrix to be applied may be determined by the scheduler (e.g., in the network node 16) depending on the OOB emission reduction that is required to comply with the co-existence requirements:

[0092] ■ The precoding matrix to be applied may also depend on the level of relaxation in PA power back-off. For example, if a large PA back-off relaxation is applied, then a precoding matrix may be selected to provide higher OOB emission reduction. In this case, a large PA back-off relaxation may be applied to increase UE power efficiency (e.g., due to the UE low battery condition), or to increase coverage (e.g., by increasing UE output power);

[0093] • The DPoD may be applied at the network node 16 to perform signal detection in the presence of in-band distortions including the distortion contributed by the linear precoder and the ones due to PA nonlinearity. o The capability to perform DPoD, e.g., the model to be applied, may be adapted to the precoding matrix that is applied at the UE 22. For example, if Gris applied, then the contributed in-band distortion due to precoding is expected to be relatively low and hence, a small AI / ML model implemented by the Al unit 24 (e.g., a fully connected neural network model with a few layers) for DPoD may be applied. When GMis applied, M»l, more in-band distortion would be contributed to the signal and hence, a more capable Al model for DPoD (e.g., a larger neural network model) may be applied; and / or o the capability to perform DPoD may be also adapted according to the PA back-off relaxation that is applied. For example, if a large PA back-off relaxation is applied, then a more capable Al model for DPoD may be deployed to compensate for the larger distortions due to the PA nonlinearity.

[0094] As described above, this method assumes that the precoding matrix to suppress OOB emission is determined by the scheduler at the network node 16. For example, the network node 16 may select a precoding matrix from a set of candidate matrices (i.e., a predefined codebook for the precoding matrix), and send the index of the selected precoding matrix to the UE 22. Since the UE 22 and the network node 16 both have knowledge of the codebook, the UE 22 may look up the precoding matrix from the codebook using the index. When the UE 22 needs to transmit an uplink data packet, the UE 22 applies the selected precoding matrix in the transmission processing chain.

[0095] The network node 16 and UE 22 coordinate activation of the OFDM precoding and DPoD capability is illustrated in FIG. 14 and described in the following:

[0096] Capability reporting:

[0097] • UE 22 may report the capability to perform pre-coded signal transmission, and the capability to co-operate with DPoD at receiver.

[0098] Network operation:

[0099] • the network node 16 may send a request and configurations to the UE 22 (e.g., using downlink control information (DCI)) to apply precoding to the OFDM signals: o the network node 16 may send the request when the out of band emissions are higher than the requirements in the current operating scenario. An example is when there are co-existing devices in adjacent frequency bands. Another example is when there is a need to push the UE PA operation to the nonlinear regime, e.g., to extend the coverage, but it may cause the OOB emissions to exceed what is specified in the regulations; o The configuration may include the index of the precoding matrix to be applied; o The configuration may include the transmit power to be applied;

[0100] • The UE 22 may apply the precoding and sends an acknowledgment to the network node 16 that the signal is pre-coded;

[0101] • the network node 16 may activate or deactivate DPoD for signal reception;

[0102] • the network node 16 may configure the UE 22 for the physical uplink shared channel (PUSCH) transmission;

[0103] • the UE 22 may perform PUSCH transmission; and / or

[0104] • the UE 22 may apply configurations and performs PUSCH transmission.

[0105] While the method is described above using the network node 16-selected precoding matrix as an example, the method may be extended to cover any transmitter operation for unwanted emission suppression, where the receiver should know the transmitter operation so that a corresponding procedure may be applied at the receiver to detect the payload data correctly. Other than precoding matrix choice, other examples of such transmitter operation may include:

[0106] • The modulation constellation points used in the transmission. The OOB emission suppression method may be: if multiple choices of modulation constellation points are available for a subcarrier, then the one with the lowest OOB emission is selected for transmission. In this case, at the receiver (e.g., the network node 16), the network node 16 should have information on the selected constellation points in order to detect the payload data. This may be achieved by either (1) the network node 16 making the constellation point choice for the UE 22 and signaling the choice to the UE 22, or (2) the UE 22 making its own constellation point choice and signaling its choice to the network node 16;

[0107] • The vector used in the transmission. The OOB emission suppression method may be: if the payload data symbol is mapped to a vector for transmission, and multiple choices of vectors are available, then the one having the lowest OOB emission is selected for transmission. In this case, at the receiver (e.g.., the network node 16), the network node 16 should have information on the selected constellation points in order to detect the payload data. This may be achieved by either (1) the network node 16 making the transmission vector choice for the UE 22 and signaling the choice to the UE 22, or (2) the UE 22 making its own transmission vector choice and signaling its choice to the network node 16.

[0108] In general, if the OOB emission suppression method requires the receiver to know the transmitter operation, then either (1) the receiver (e.g., the network node 16) makes the transmission operation choice for the transmitter (e.g., the UE 22) and signals the choice to the transmitter (e.g., the UE 22), or (2) the transmitter (e.g., the UE 22) makes its own transmission operation choice and signals its choice to the receiver (e.g., the network node 16). In some embodiments, the transmitter (e.g., UE 22) may indicate its selected precoding matrix to the receiver (e.g., the network node 16), in which case an Al model may not require training.

[0109] Embodiment 2: Coordinated DPoD and precoding for OOB emission suppression without a codebook

[0110] In Embodiment 1 above, it was assumed that the transmitter and receiver should exchange information on the transmission operation that suppresses OOB emission. For example, the precoding matrix to suppress OOB emission is determined by the scheduler at the network node 16, and signaled to the UE 22.

[0111] However, it is not necessary that the receiver have knowledge of the transmission operation that suppresses OOB emission. For example, in some embodiments, the precoder to be applied by the transmitter to suppress OOB emission is not signaled from the network node 16. Thus, the transmitter may choose its preferred precoding matrix. For uplink, this means that it is up to UE 22 implementation to choose the precoding matrix to suppress OOB emission if the UE 22 decides to use the pre-coding approach. The UE 22 may apply a pre-coding matrix to satisfy the requirements for unwanted emission without being limited to any codebook of the precoding matrix, and without signaling the information on the precoding matrix to the network node 16 as well.

[0112] While the pre-coding matrix may be up to UE implementation, this operation may affect the receiver. In terms of AI / ML-based DPoD to combat signal distortion, the DPoD model performance may be affected by: (a) whether or not the UE 22 applied the precoding matrix to suppress OOB emission; and (b) if applied, the type of precoding used. The type of precoding may include:

[0113] • Time domain precoding approach which manages the discontinuity property of the OFDM signal;

[0114] • Frequency domain precoding approach which nulls the spectrum at certain set of frequencies;

[0115] • Subcarrier weighting which multiplies all the data subcarriers with certain weighting coefficients; and / or

[0116] • Spectral precoding which uses new orthogonal basis sets to replace the rectangular pulse for each conventional OFDM symbol so that the new sidelobes fall off faster.

[0117] It may be expected that different amounts of distortion (e.g., inter-carrier- interference (ICI)) would result from the precoding choice (including not to apply any precoding matrix). Thus, this could affects the DPoD operation at the receiver. Methods disclosed herein may mitigate the impact from the UE's precoding choice.

[0118] In an example, the AI / ML model is trained with a training dataset that includes the effect from a wide range of UE's precoding choices. The AI / ML model is also referred to herein as an Al model or a DPoD model that may be performed by, for example Al unit 24. During training data collection, when a UE 22 is designated to provide training data for the AI / ML model, the UL signal may be transmitted with the UE's applied precoding choice (e.g., frequency domain precoding approach). Different UEs 22 may make different precoding choices. For example, UE#1 transmits OFDM symbols without precoding, UE#2 transmits OFDM symbols with precoding matrix, where the precoding matrix follows the frequency domain precoding approach, UE#3 transmits OFDM symbols with precoding matrix where the precoding matrix follows the time domain precoding approach, etc. When the training dataset contains data samples from the variety of the UE implementations (UE#1, UE#2, UE#3. . .), the AI / ML model for DPoD may learn to extract data from the distorted signals, even though the distortion may vary due to the UE implementation choice on precoding matrix.

[0119] During model deployment (i.e., model inference using the trained model), each UE 22 (or each group of UEs 22, e.g., a group of UEs 22 of the same manufacturer and / or same device category) is expected to apply the same precoding choice as the one it used for training data collection. Thus, the AI / ML model is expected to function properly, since it has been "shown" the training data from such UE 22. UE 22 can also dynamically adjust precoding choice in case that the AI / ML model have been trained on sufficiently diverse dataset.

[0120] In another example, the AI / ML based DPoD takes into account that different precoding matrices are likely to cause different amounts of distortion to the various subcarriers in the channel bandwidth. It is known that subcarriers located at the edge of the transmission bandwidth suffer worse distortion in the transmission chain, while subcarriers located at the center are only relatively lightly distorted. The amount of distortion suffered by edge subcarriers is likely to vary with the UEs precoding choice. Thus, the AI / ML based DPoD may take this into account. For example, the model input includes an indication on the subcarrier location of the transmitted symbol. The indication on the subcarrier location may be for one of the following options:

[0121] • Subcarrier location in a component carrier;

[0122] • Subcarrier location in assigned channel bandwidth;

[0123] • Subcarrier location in the aggregated uplink channel bandwidth;

[0124] • Subcarrier location in the operating band; and / or

[0125] • Subcarrier location in the frequency range.

[0126] Variants for indicating the subcarrier location qualitatively may be applied. As an example, the indication value may be {"upper edge", "lower edge", "center or simply {"edge", "center Alternatively, the indication value may be {“outer 1”, “outer 2”, “inner”}, etc. Note that the information on the subcarrier location is known to the receiver. Thus, the receiver may determine the indication for model input without any extra signaling from the transmitter.

[0127] When the training data is collected from a variety of UEs 22 (each with its own precoding choice), different distortions experienced by symbols located on edge subcarriers may be included in the collected training data. This ensures that the trained model may be robust to the variety of distortions to the edge subcarriers due to UE implementation choice. The same applies to subcarriers located at the center.

[0128] Additionally, a quality indicator may be attached to the collected training data samples to indicate the level of distortion caused by transmitter side signal processing (e.g., for OOB emission suppression):

[0129] • In one example, the quality indicator may be numerical. One alternative to calculate the quality indicator is to calculate the Euclidean distance between the symbol ) without the transmitter side signal processing, and the symbol (y^ ) with the transmitter side signal processing:

[0130] Another alternative to calculate the quality indicator is to calculate the cosine similarity between

[0131] • In another example, the quality indicator is qualitative, for example, {“high distortion”, “medium distortion”, “low distortion”).

[0132] In some embodiments, a quality indicator is obtained for the list of transmitted symbols without differentiating the location of the allocated resources. In some embodiments, the quality indicator is calculated for the different subcarrier locations differently, e.g., one indicator for inner resources, another indicator for outer resources.

[0133] With the quality indicator provided for the training data samples, there is no need to share between the UE 22 and the network node 16 the exact implementation details of the transmitter side signal processing (e.g., time-domain or frequency-domain precoding approach for OOB emission suppression).

[0134] The training data samples' quality indicators may be considered in the AI / ML model training. For example, the quality indicator is included as an input to the AI / ML model. Embodiment 3 : AI / ML based DPoD in the presence of other techniques for suppressing unwanted emissions

[0135] In the above, the discussion focused on using a precoding matrix to suppress OOB emissions, which is a representative approach for the transmitter to satisfy RF requirements for the device.

[0136] In general, other methods may be used by the transmitter, e.g., network node 16, to suppress OOB emission. These include:

[0137] • Symbol mapping, which maps the payload data symbol(s) to new symbol(s);

[0138] • Windowing;

[0139] • Filtering;

[0140] • Inserting samples between two time blocks; and / or

[0141] • Applying a perturbation vector.

[0142] Similar to embodiments that use a precoding matrix, other methods used in the transmitter to suppress OOB emission may fall into two categories:

[0143] Category A. The method requires the receiver to know the transmitter operation, then either (1) the receiver (e.g., the network node 16) makes the transmission operation choice for the transmitter (e.g., UE 22) and signal the choice to the transmitter (e.g., UE 22), or (2) the transmitter (e.g., UE 22) makes its own transmission operation choice and signals its choice to the receiver (e.g., the network node 16): a. The receiver applies a procedure which counteracts the transmitter operation to recover the symbol. For example, the receiver applies an inverse matrix if the transmitter has applied a matrix to the transmitted symbol. In this case, the AI / ML model for DPoD at the receiver side may be agnostic of the transmitter-side operation. Thus, the training data collection for the AI / ML model is less challenging. For example, it may not need to include a large amount of data on all possible transmitter implementations.

[0144] Category B. The method does not require the receiver to know the transmitter operation, i.e., the receiver performs symbol detection as is: a. At the receiver side, the AI / ML model for DPoD may need to handle varying amount of distortion, where the distortion amount is affected by the method implemented by the transmitter. As discussed, this is likely to make the training data collection and model training more challenging. The training data collection for the AI / ML model need to be comprehensive so that a wide variety of transmitter implementation choices are included in the training data. This then allows the AI / ML model to be robust to transmitter implementation choice.

[0145] In some embodiments, the following aspects may be specified in a wireless communication standard for coordinated operation of the UE 22 and the network node 16:

[0146] • The precoding matrices to be applied by the UE 22 for creating precoded OFDM signals. The list of pre-designed pre-coders may be specified in the form of a look up table, where each precoding matrix has an index;

[0147] • The signaling from the network node 16 to the UE 22 to configure precoding of OFDM, e.g., using DCI;

[0148] • The signaling from the UE 22 to the network node 16 to acknowledge precoding of the OFDM signal, e.g., using uplink control information (UCI).

[0149] Some embodiments may include one or more of the following:

[0150] 1. A method in UE 22 for lowering out of band (OOB) emission, where the method comprises one or a combination of any of the following: a. applying a precoding to suppress OOB emission, where the type of precoding may be one or a combination of the following: i. Time domain precoding approach which manages the discontinuity property of the OFDM signal; ii. Frequency domain precoding approach which nulls the spectrum at certain set of frequencies; iii. Spectral precoding which uses new orthogonal basis sets to replace the rectangular pulse for each conventional OFDM symbol so that the new sidelobes fall off faster. b. subcarrier weighting which multiplies the data subcarriers with certain weighting coefficients; c. symbol mapping, which maps the payload data symbol(s) to new symbol(s) for transmission; 2. Based on the above item 1, further includes obtaining the configurations for OOB emission suppression [e.g., the required level of OOB emission reduction, or the type of OOB emission reduction to apply],

[0151] 3. Based on the above item 2, futher reporting the applied OOB emission suppression [e.g., whether OOB emission suppression is activated, and the type of the applied method] and request / trigger signal to apply DPoD to compensate for additional in band distortions.

[0152] 4. A method in the network node 16 to compensate for in band distortion, where the method comprises: a. applying a DPoD for signal detection in the presence of distortions, where the DPoD may be an Al-based DPoD, e.g., a received with an Al-based Demapper for demapping signals in the presence of distortions,, or a non-AI DPoD, e.g., a method to inverse the impact of the transmitter side distortions at the receiver side, where for the Al-based DPoD: i. the AI / ML model is trained with training dataset that includes the effect from a wide range of UE's OOB emission suppression techniques, e.g., different precoding choices; ii. the model input includes information regarding the applied OOB emission reductions, e.g., an indication on the subcarrier location of the transmitted symbol, the type of the applied OOB emission suppression; b. the compensation capability of the DPoD may be adapted, e.g., by selecting proper AI / ML model from a set of pre-trained models, according to the level of the in band distortions.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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. 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).

[0158] 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.

[0159] Abbreviations that may be used in the preceding description include:

[0160] 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.

[0161] Embodiments:

[0162] Embodiment Al . A transmitter configured to, and / or comprising a radio interface and / or comprising processing circuitry configured to: modify an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions; transmit the modified OFDM signal to a receiver; and transmit information to the receiver to be used in an Artificial Intelligence (Al) model implemented at the receiver to suppress in-band distortion in the transmitted modified OFDM signal caused by modifying the OFDM signal to suppress OOB emissions.

[0163] Embodiment A2. The transmitter of Embodiment Al, wherein the information includes an indication of a precoding choice of the transmitter.

[0164] Embodiment A3. The transmitter of Embodiment A2, wherein the precoding choice is one of time domain precoding, frequency precoding, spectral decoding and no precoding.

[0165] Embodiment A4. The transmitter of any of Embodiments A1-A3, wherein the information includes an indication of a level of distortion caused by modifying the OFDM signal to suppress OOB emissions.

[0166] Embodiment A5. The transmitter of any of Embodiments A1-A4, wherein the information includes an indication of a method used by the transmitter to modify the OFDM signal to suppress OOB emissions.

[0167] Embodiment A6. The transmitter of any of Embodiments A1-A5, wherein the transmitter is located in a UE and the receiver is at one of a network node and another UE.

[0168] Embodiment Bl. A method implemented in a transmitter that is configured to communicate with a user equipment, the method comprising: modifying an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions; transmitting the modified OFDM signal to a receiver; and transmitting information to the receiver to be used in an Artificial Intelligence (Al) model implemented at the receiver to suppress in-band distortion in the transmitted modified OFDM signal caused by modifying the OFDM signal to suppress OOB emissions. Embodiment B2. The method of Embodiment Bl, wherein the information includes an indication of a precoding choice of the transmitter.

[0169] Embodiment B3. The method of Embodiment B2, wherein the precoding choice is one of time domain precoding, frequency precoding, spectral decoding and no precoding.

[0170] Embodiment B4. The method of any of Embodiments B 1-B3, wherein the information includes an indication of a level of distortion caused by modifying the OFDM signal to suppress OOB emissions.

[0171] Embodiment B5. The method of any of Embodiments B 1-B4, wherein the information includes an indication of a method used by the transmitter to modify the OFDM signal to suppress OOB emissions.

[0172] Embodiment B6. The method of any of Embodiments B 1-B5, wherein the transmitter is located in a user equipment (UE) and the receiver is at one of a network node and another UE.

[0173] Embodiment Cl . A receiver configured to, and / or comprising a radio interface and / or processing circuitry configured to: receive from a transmitter an orthogonal frequency division multiplexed (OFDM) signal; and implement an Artificial Intelligence (Al) model, the Al model configured to adapt digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter.

[0174] Embodiment C2. The receiver of Embodiment Cl, further comprising training the Al model based at least in part on a training data set that includes effects of a plurality of OOB emission suppression techniques.

[0175] Embodiment C3. The receiver of any of Embodiments Cl and C2, wherein inputs to the Al model include an OOB suppression method applied by at least one transmitter.

[0176] Embodiment C4. The receiver of any of Embodiments C1-C3, wherein inputs to the Al model include at least one precoding choice of at least one transmitter, a precoding choice being one of time domain precoding, frequency precoding, spectral decoding and no precoding. Embodiment C5. The receiver of any of Embodiments C1-C4, wherein inputs to the Al model include indications of distortion levels received from at least one transmitter.

[0177] Embodiment C6. The receiver of any of Embodiments C1-C5, wherein inputs to the Al model include subcarrier indices indicating subcarriers to which an OOB method is applied at a transmitter, for at least one transmitter.

[0178] Embodiment C7. The receiver of any of Embodiments C1-C6, wherein inputs to the Al model include an indication of subcarrier location within a frequency band for at least one transmitter.

[0179] Embodiment C8. The receiver of any of Embodiments C1-C7, wherein the receiver is at a network node or in a user equipment (UE) and the transmitter is a UE.

[0180] Embodiment DI . A method implemented in a receiver configured to communicate with a transmitter, the method comprising: receiving from a transmitter an orthogonal frequency division multiplexed (OFDM) signal; and implementing an Artificial Intelligence (Al) model, the Al model configured to adapt digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter.

[0181] Embodiment D2. The method of Embodiment DI, further comprising training the Al model based at least in part on a training data set that includes effects of a plurality of OOB emission suppression techniques.

[0182] Embodiment D3. The method of any of Embodiments DI and D2, wherein inputs to the Al model include an OOB suppression method applied by at least one transmitter.

[0183] Embodiment D4. The method of any of Embodiments D1-D3, wherein inputs to the Al model include at least one precoding choice of at least one transmitter, a precoding choice being one of time domain precoding, frequency precoding, spectral decoding and no precoding.

[0184] Embodiment D5. The method of any of Embodiments D1-D4, wherein inputs to the Al model include indications of distortion levels received from at least one transmitter. Embodiment D6. The method of any of Embodiments D1-D5, wherein inputs to the Al model include subcarrier indices indicating subcarriers to which an OOB method is applied at a transmitter, for at least one transmitter.

[0185] Embodiment D7. The method of any of Embodiments D1-D6, wherein inputs to the Al model include an indication of subcarrier location within a frequency band for at least one transmitter.

[0186] Embodiment D8. The method of any of Embodiments D1-D7, wherein the receiver is at a network node or in a user equipment (UE) and the transmitter is a UE.

[0187] Embodiment El . A method implemented in a transmitter that is configured to communicate with a user equipment, the method comprising: modifying an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions; transmitting the modified OFDM signal to a receiver; and transmitting information to the receiver, wherein the information indicates a precoding matrix applied by the transmitter for modifying the OFDM signal.

[0188] Embodiment Fl . A transmitter that is configured to communicate with a user equipment, the transmitter configured to: modify an orthogonal frequency division multiplexed (OFDM) signal to suppress out-of-band (OOB) emissions; transmit the modified OFDM signal to a receiver; and transmit information to the receiver, wherein the information indicates a precoding matrix applied by the transmitter for modifying the OFDM signal.

[0189] Embodiment G1. A method implemented in a receiver configured to communicate with a transmitter, the method comprising: receiving from a transmitter an orthogonal frequency division multiplexed (OFDM) signal; receiving from the transmitter information indicating a precoding matrix applied by the transmitter for modifying the OFDM signal; and implementing digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter. Embodiment Hl . A receiver configured to communicate with a transmitter, the receiver configured to: receive from a transmitter an orthogonal frequency division multiplexed (OFDM) signal; receive from the transmitter information indicating a precoding matrix applied by the transmitter for modifying the OFDM signal; and implement digital post distortion (DPoD) compensation to suppress in-band distortion in the OFDM signal caused by out of band (OOB) emission suppression at the transmitter.

Claims

CLAIMS1. A method implemented in a transmitter of wireless signals configured to communicate with a receiver, comprising: obtaining a precoding approach to be applied by the transmitter for suppressing out of band, OOB, emission; performing (S20) the precoding approach on scheduled data to be transmitted; performing orthogonal frequency division multiplexed, OFDM, modulation on the precoded data to form OFDM data symbols; and transmitting (S22) the OFDM data symbols to the receiver.

2. The method of Claim 1, further comprising: receiving OOB level acceptable by the receiver; wherein the obtaining a precoding approach comprises: determining a precoding type to be applied for the precoding approach to satisfy the OOB level requirement.

3. The method of Claim 1, further comprising: receiving configuration for a codebook for suppressing OOB emission; receiving OOB level acceptable by the receiver; and sending (S24), to the receiver, an indication of an index to a precoding matrix among a plurality of precoding matrices comprised in the codebook, or an indication of modulation constellation points or vectors, determined for precoding the scheduled data; wherein obtaining the precoding approach comprises: determining the precoding matrix, the constellation points or vectors from the codebook to be applied to satisfy the OOB level requirement.

4. The method of Claim 1, further comprising: transmitting its capability on preforming precoding for suppressing OOB emission; and receiving configuration for a codebook comprising precoding matrices for suppressing OOB emission; wherein obtaining the precoding approach comprises: receiving an indication of an index to a precoding matrix for precoding the scheduled data.

5. The method of any of Claims 1 to 3, further comprising:determining a necessity for the precoding; and transmitting, to the receiver of the OFDM data symbols, an indication that the OFDM data symbols have been precoded and an indication of the precoding type applied for them.

6. The method of Claim 5, wherein the precoding type is one or combination of: frequency domain precoding, time domain precoding, spectral precoding with orthogonal basis sets; and subcarrier weighting for individual data subcarriers.

7. The method of any of Claims 1 to 6, future comprising: transmitting, to the receiver, an indication of level of distortion caused by the precoding approach for suppressing OOB emission.

8. A method implemented in a receiver configured to communicate with a transmitter of wireless signals, comprising: receiving (SI 6; S26) OFDM data symbols from the transmitter, wherein the OFDM data symbols have been precoded for suppressing out of band, OOB, emission; and applying (SI 8; S30) an artificial intelligence, Al, or machine learning, ML, model of digital post distortion, DPoD, compensation for compensating in-band distortion caused by the precoding for the OFDM data symbols.

9. The method of Claim 8, further comprising: transmitting acceptable OOB level to the transmitter.

10. The method of Claim 9, further comprising: transmitting a configuration for a codebook comprising precoding matrices for suppressing OOB emission; andReceiving (S28) an indication of an index to a precoding matrix for the precoding determined by the transmitter among a plurality of matrices comprised in the codebook; or receiving an indication of modulation constellation points or vectors for the precoding, wherein the constellation points each of which corresponding to a subcarrier or the vectors are determined by the transmitter from the codebook.

11. The method of Claim 8, further comprising: receiving the transmitter’s capability on preforming precoding for suppressing OOB emission; transmitting configuration for a codebook for suppressing OOB emission; and transmitting an indication of an index to a precoding matrix among a plurality of precoding matrices comprised in the codebook for the precoding; or transmitting an indication of modulation constellation points or vectors determined from the codebook for the precoding.

12. The method of any of Claims 8 to 10, further comprising: receiving, from the transmitter, an indication that the OFDM data symbols have been precoded and an indication of a procoding type applied for it; and activating the AI / ML model for compensating the in-band distortion.

13. The method of Claim 12, wherein the precoding type is one or combination of: frequency domain precoding, time domain precoding, spectral precoding with orthogonal basis sets; and subcarrier weighting for individual data subcarriers.

14. The method of any of Claims 8 to 13, further comprising collecting dataset for training the AI / ML model, wherein the dataset comprising one or more of: quality indicators indicating level of distortion caused by precoding for suppressing OOB emission; subcarrier locations of OFDM data symbols; and precoding types or precoding matrices applied for the received signals; wherein the received signals are received from variety of transmitters, wherein the precoding types including no precoding is taken.

15. A transmitter (22) configured to communicate in a wireless system, comprising a radio interface (46) and a processing circuitry (50), the radio interface (46) being configured to transmit wireless signals to a receiver (16); the processing circuitry (50) comprising: one or more processors (52), and a memory (54) including instructions which, when executed by the one or more processors (52), cause the transmitter (22) to perform the method according to any of the claims 1 to 7.

16. A receiver (16) configured to communicate in a wireless system, comprising a radio interface (30) and a processing circuitry (36), the radio interface (30) being configured to receive wireless signals from a transmitter (22); the processing circuitry (36) comprising: one or more processors (38), and a memory (40) including instructions which, when executed by the one or more processors (38), cause the receiver (16) to perform the method according to any of the claims 8 to 13.

Images