Apparatus and method for enhanced parameter management for accurate digital post-distortion model

Abstract

This application relates to post-distortion digital (DPoD) processing at a base station / network element 202. The base-station uses an artificial intelligence (AI) / machine learning (ML) model to estimate 207 DPoD parameters. The model uses received uplink reference signals 205 as input. The base station sends a configuration message 203 to a UE to configure such reference signals. The configuration message includes at least one transmit-receive beam pair, i.e. a beam the UE is to use to transmit a reference signal and a complementary beam the base station is to use to receive the reference signal. The uplink reference signals are preferably sounding reference signals (SRS). There are separate claims to a network element and to a UE, but the UE claims do not refer to the AI / ML model. The UE may optionally send a capability message 201 indicating DPoD readiness, number of beam pairs or AI / ML capabilities. The beam pairs my be identified by a beam management procedure which uses downlink reference signals, such as SSB (see Figure 3).

Description

[0002] This section is intended to provide a background or context to the invention that is recited in the claims. The description herein may include concepts that could be pursued, but are not necessarily ones that have been previously conceived, implemented or described. Therefore, unless otherwise indicated herein, what is described in this section is not prior art to the description and claims in this application.

[0003] A communication system can be seen as a facility that enables communication sessions between two or more communication devices, or provides communication devices access to a network. A mobile or wireless communication network is one example of a communication network. Examples of mobile or wireless telecommunication systems may include the Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (UTRAN), Long Term Evolution (LTE) Evolved UTRAN (E-UTRAN), LTE-Advanced (LTE-A), MulteFire, LTE-A Pro, fifth generation (5G) radio access technology or new radio (NR) access technology and / or sixth generation (6G) radio access technology. SUMMARY

[0004] Example embodiments of the present disclosure can thus provide apparatuses, methods, computer programs, computer program products, or computer readable media for improving various aspects of mobility measurements. Any example embodiment may be combined with one or more other example embodiments. These and other aspects of the present disclosure will be apparent from the example embodiments) 1 described below. According to some aspects, there is provided the subject matter of the independent claims. Some further aspects are defined in the dependent claims.

[0005] In some aspects, the techniques described herein relate to an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: send to a user equipment a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; receive from the user equipment a reference signal generated based on the configuration; collect reference signal data of the indicated at least one beam pair from the received reference signal; and estimate digital post-distortion parameters with an artificial intelligence / machine learning model based on the collected reference signal data.

[0006] In some aspects, the techniques described herein relate to an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive from a network element a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; and transmit to the network element a reference signal generated based on the configuration.

[0007] In some aspects, the techniques described herein relate to a method including: sending to a user equipment a configuration of a reference signal for digital postdistortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; receiving from the user equipment a reference signal generated based on the configuration; collecting reference signal data of the indicated at least one beam pair from the received reference signal; and estimating digital post-distortion parameters with an artificial intelligence / machine learning model based on the collected reference signal data.

[0008] In some aspects, the techniques described herein relate to a method including: receiving from a network element a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; and transmitting to the network element a reference signal generated based on the configuration.

[0009] Other example embodiments are provided or described for each of the example methods, including: means for performing any of the example methods; a non-transitory computer-readable storage medium comprising instructions stored thereon that, 2 when executed by at least one processor, are configured to cause a computing system to perform any of the example methods; and an apparatus including at least one processor, and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform any of the example methods. BRIEF DESCRIPTION OF THE DRAWINGS

[00010] For a more complete understanding of example embodiments of the present invention, reference is now made to the following descriptions taken in connection with the accompanying drawings in which:

[00011] Figure 1 illustrates an example communication system in which various example embodiments of the application implement.

[00012] Figure 2 illustrates a signaling diagram between a user equipment (UE) and a network element (NE) according to an example embodiment.

[00013] Figure 3 describes another signaling diagram between a user equipment (UE) and a network element (NE) according to an example embodiment.

[00014] Figure 4 describes a block diagram for some operation of a NE according to an example embodiment.

[00015] Figure 5 describes a block diagram for some operation of a UE according to an example embodiment.

[00016] Figure 6 illustrates a simplified block diagram of various example apparatuses that are suitable for use in practicing various example embodiments of this application. DETAILED DESCRIPTON

[00017] It will be readily understood that the components of certain example embodiments, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of some example embodiments of systems, methods, apparatuses, and computer program products for enhanced parameter management for accurate digital post-distortion model, is not intended to limit the scope of certain embodiments but is representative of selected example embodiments.

[00018] The features, structures, or characteristics of example embodiments described throughout this specification may be combined in any suitable manner in one or 3 more example embodiments. For example, the usage of the phrases “an example embodiment” “certain example embodiments,” “various example embodiments,” or other similar language, throughout this specification refers to the fact that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment. Thus, appearances of the phrases “in an example embodiment”, “in certain embodiments,” “in some embodiments,” “in other embodiments,” or other similar language, throughout this specification do not necessarily all refer to the same group of embodiments, and the described features, structures, or characteristics may be combined in any suitable manner in one or more example embodiments. In addition, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. The phrase “set of’ refers to a set that includes one or more of the referenced set members. As such, the phrases “set of,” “one or more of,” and “at least one of,” or equivalent phrases, may be used interchangeably. Further, “or” is intended to mean “and / or”, unless explicitly stated otherwise.

[00019] Figure 1 illustrates an example communication system 100 in which various embodiments of the application can be implemented. The example communication system 100 comprises a network element (NE), 101, such as for example, an access point (AP), an enhanced Node B (eNB), a 5G Node B (gNB) or a next generation eNB (NG-eNB), or a 6G base station connecting to a core network that is not shown for brevity. Part of the functionalities of the NE 101 may be also carried out by any node, server or host which may be operably coupled to a transceiver, such as a remote radio head. NE 101 provides wireless coverage within a cell 103, including the user equipments (UEs) 102, 104 and 106, which may communicate with the NE 101 via wireless links 105, 107 and 109 respectively. The UEs may communication with each other via a sidelink channel, e.g., between UEs 104 and 106 via sidelink 111. Although just one NE, and three UEs are shown in Figure 1, it is only for the purpose of illustration and the example communication system 100 may comprise any number of NE(s), and UE(s).

[00020] The various example implementations may be applied to a wide variety of wireless technologies or wireless networks, such as long term evolution (LTE), LTE-advanced (LTE-A), fifth generation (5G) or new radio (NR), sixth generation (6G), cmWave, and / or mmWave band networks, or any other wireless network / technology or use case. The various example implementations may also be applied to a variety of different applications, services or use cases, such as, for example, ultra reliable low latency communication (URLLC), internet of things (loT), time sensitive communications (TSC), 4 enhanced mobile broadband (eMBB), massive machine type communication (mMTC), vehicle to vehicle (V2V), vehicle to device (V2D), etc. Each of these use cases, or types of UEs, may have its own set of requirements.

[00021] In communication systems, power amplifier (PA) nonlinearity may significantly limit system performance, especially when system band is expanded to frequency range 2 (FR2) or even higher sub-THz (normally in the range of 300GHz to 3000GHz) band. Various example embodiments relate to the transmission and reception of reference signals for effectively mitigating PA-introduced nonlinearities, specifically adjacent channel leakage power ratio (ACER) and error vector magnitude (EVM), using native-air interfaces. ACLR is the ratio of the filtered mean power centered on the assigned channel frequency to the filtered mean power centered on an adjacent channel frequency at nominal channel spacing, while EVM is a measure of the difference (the so-called error vector) between the reference waveform and the measured waveform.

[00022] Digital post-distortion (DPoD) is a receiver (RX) based approach where the primary target is to enhance the received signal EVM, and thereon, to improve the bit or symbol detection. In existing DPoD solutions for multibeam when beamforming technique is deployed, achieving extended coverage with DPoD is hindered by the complexities of accurately maintaining DPoD models. These challenges arise from the specific contributions of PA responses and the particular transmit and receive beam patterns utilized during transmission. For example, it may be challenging to ensure the DPoD model’s applicability across various beam pair combinations when utilizing beamed demodulation reference signals (DMRS) to estimate DPoD parameters. Hence, the existing DPoD solutions may result in performance degradation with changes in beam directions due to the beamdependent nature of said parameters.

[00023] Various example embodiments address the need for a DPoD technique that remains effective regardless of beam steering angles and directions. An artificial intelligence / machine learning (AI / ML) model capable of accurately predicting DPoD parameters for any beam pairs is designed and validated. This model aims to leverage the mutual correlation among beam directions to predict and compensate for nonlinear distortion characteristics across all beamforming directions, eliminating the need for continuous parameter relearning.

[00024] In an example embodiment, a set of beam pairs (btx, brx) is defined, where btx represents the transmitter beamforming vector and brx represents the receiver beamforming vector, respectively. The DPoD parameter c(btx, brx) is specific to each beam 5 pair and aims to compensate for nonlinear distortions. A procedure is described below in detail to enable a NE such as for example, the NE 101 in Figure 1, to obtain a model M that can predict the DPoD parameters c for any new beam pair (btx, brx) without requiring retraining or exhaustive measurement for each beam. The introduced procedure can achieve accurate DPoD model that is relevant across beam sweeping pairs. The approach ensures that the DPoD model accounts for the complex interactions between PA responses and beamforming patterns, enhancing the accuracy and reliability of communication.

[00025] The DMRS is utilized to estimate the digital post-distortion (DPoD) parameters, essential for compensating the nonlinear distortion and channel effects in the received signal. This estimation is conducted by applying a least-squares (LS) method on the received DMRS-bearing orthogonal frequency division multiplexing (OFDM) symbol. The mathematical representation of the DPoD output during DMRS transmission is given by: Xref(n) = SpRpoddS=0 Cp,d • QrefCn “ d) ' |qref(n - gOI^1), where cp d is the complex nonlinear parameter for p-th order and d-th delayed nonlinearity estimated by the LS method, qKt(n) denotes the upsampled DMRS signal, and PRX and DRX represent the nonlinearity order and memory depth, respectively.

[00026] To find the parameters, the estimation problem is cast into a vector-matrix form for computational efficiency. Let c be the (PRX + 1)(DRX + 1) / 2 x 1 vector of complex nonlinear parameters to be estimated, and Y the N x (PRX + 1)(ORX + 1) / 2 matrix. Each column of Y is represented by associated with a complex parameter c^d, with: = ^(n ~ d)|qref(n - d)p“1.

[00027] Given this, the LS estimation ofc is obtained by: c = (Y^^Y"*^, where xref is an Ax 1 vector of received samples.

[00028] This equation minimizes the error between the actual received beamed DMRS-bearing OFDM samples and the DMRS samples, allowing for the precise determination of DPoD parameters to mitigate nonlinear distortion effects and enhance receiver performance.

[00029] However, this way of estimating DPoD parameter will require a new parameter for each beam pair used for receiving DMRS (i.e., each received DMRS beam pair) and will require very frequent updating to be able to compensate for the DPoD update. In various example embodiments, an AIZML parameter finder that can create parameters that can be used on a broader range of beamed DMRS beam pairs is utilized. To successfully post-distort the received non-linear signal at the RX side, the DPoD method first acquires enough beam pair to perform DPoD. Once a DPoD model is obtained, a compensation equalizer is utilized to post distort the channel equalized signal.

[00030] In various example embodiments, A DPoD method is as follows: 1. Gather a dataset D = {(b^,b®,cW^^of beam pairs and their corresponding DPoD parameters. 2. Identify or engineer features f(btx, brx)that capture the relationship between the beam and the DPoD parameters. 3. Train a machine learning model M(f(btx, brx)) = c to predict DPoD parameters based on the features of the current beam pair used for receiving reference signal (i.e., received beam pair) and previous received beams. 4. Validate the model on a test set of beam pairs and DPoD parameters not used (or seen) during training to ensure generalization.

[00031] In various example embodiments, different models can be trained and coordinated between UE and network. For example: (1) Cl) 1. One model may be trained only for a first beam pair (b^ , b^ )i 2. One model may give equal importance to multiple pairs (b^\ b^), (b^\ b^^), etc. 3. One model may take different beam pairs as input with an identifier that indicates the beam pairs. For example, for each (b^\ b^), (b®, b®),..., (b®to b®) each beam pair will have an identifier that is embedded into a vector which is used to indicate the beam pairs that are used at the input and the model is being trained for. 4. Another implementation solution would be to create a bipartite graph that represents the correlation between b®, b® for i G {1,2,..., N} and utilize a graph representation learning approach to solve the problem. Every beam b^ could be regarded as a node in the left side of the bipartite graph and every beam of the b® would be a node in the right side of the bipartite graph. The relationship between each beam at the TX and each beam at the RX side will be shown by an edge in the graph. The problem can be then formulated as a graph generation problem.

[00032] In various example embodiments, to obtain the needed beam pairs, uplink (UL) sounding reference signal (SRS) is utilized instead of DMRS. Current SRS is a Zadoff-Chu sequence, i.e. a sequence with constant amplitude and zero autocorrelation (CAZAC). This sequence has a low peak to average ratio (PAPR) compared to data symbols, therefore it cannot be used to estimate the DPoD parameters. Moreover, the current UL SRS is configured with a frequency comb, i.e., some resources are purposely muted. This is also suboptimal for DPoD derivation.

[00033] In various example embodiments, a new type of UL SRS is proposed. The new UL SRS may be configured for specific bandwidth, TX power (e.g., PAPR being same as or similar to that of data signal), repetition rate, periodicity, code of the SRS sequence, no frequency comb, etc. This can enable the network to optimally derive the parameters of the DPoD equalizer that is applied in the network to recover the PA nonlinearity.

[00034] In an example embodiment, a UE may indicate to a network element, such as for example, a gNB, the UE’s capability of AI / ML based beam DPoD operation, including e.g., how many different beam pairs it can form, its ability to participate in AI / ML based DPoD parameter estimation, the AI / ML model(s) the it supports, etc.

[00035] A signaling diagram for a UE 200, such as for example, the UE 102 of Figure 1, and a gNB 202, such as for example, the NE 101 of Figure 1 according to an example embodiment is presented in Figure 2. At 201, the UE 200 may report its beamforming and DPoD capabilities, including, for example, the number of beams it can form, its ability to participate in AI / ML based DPoD parameter estimation, AI / ML model(s) it supports, etc. At 203, the gNB 202 may configure the UE with initial SRS settings, including e.g., periodicity and resources for SRS transmission. This configuration may also specify parameters for DPoD parameter estimation, such as preferred beam pairs, TX power, etc.

[00036] At 205 of Figure 2, the UE 200 may transmit SRS according to the gNB's scheduling, utilizing the configured beam pairs, TX power etc., so the SRS data for DPoD parameter estimation can be collected by the gNB 202. The gNB 202 may perform AI / ML processing of collected SRS data for estimating DPoD parameters at 207. In various example embodiments, the DPoD method and model described above can be applied. At 209, the UE 200 may transmit UL data using the configured parameters of SRS such that the data symbols can have substantially same PAPR as the SRS. The gNB 202 may apply estimated DPoD parameters on the received UL data to compensate the nonlinearity of the UE’s PA. At 211, the gNB 202 may monitor the DPoD efficacy and continuously refine the DPoD model and parameters with a feedback loop. In various example embodiments, the gNB 202 may monitor at least one of a quality of the link between the gNB and the UE, an accuracy of the AI / ML model, or an effectiveness of the compensation based on the applied post-distortion parameters.

[00037] The gNB 202 may, based on ongoing DPoD parameter estimation, dynamically adjust the SRS configuration (e.g., changing periodicity, resources, or beam pairs) to improve the accuracy of the DPoD model or to adapt to changing channel conditions or hardware variations. At 213, the gNB 202 may send the SRS configuration adjustment to the UE 202.

[00038] In various example embodiments, the AI / ML model may be trained to be phase-agnostic, enabling it to predict DPoD parameters that are effective across various beam pairs and channel conditions. The signaling and DPoD parameters estimation processes may be designed to minimize overhead and ensure scalability across multiple UEs and varying network densities.

[00039] In various example embodiments, if coverage extension is not wanted or the battery level is low, the UE may reject the configuration request from the gNB. Here a fallback mode in simple backoff transmission configuration may be used to make DPoD not have to be updated.

[00040] In various example embodiments, a gNB may use the downlink (DL) beam management (BM) procedure to obtain estimates of the DL beamformed channel responses (BCR) for a set of beam pairs. Then, after finalizing BM, the gNB may trigger an UL SRS transmission for the same set of beam pairs with the purpose of estimating the PA response, since the UL BCR is now known by extension i.e., since the DL BCR which has been obtained earlier can be used to infer the UL BCR e.g. by assuming full reciprocity, or by filtering the DL BCR in time / frequency / space to obtain a prediction of the subsequent UL BCR. Such a procedure is shown in Figure 3.

[00041] Alternatively or additionally, Figure 3 describes a signaling diagram for a UE 300, such as for example, the UE 102 of Figure 1, and a gNB 302, such as for example, the NE 101 of Figure 1 according to an example embodiment. At 301, the gNB 302 may transmit synchronization signal block (SSB) with K TX beams to the UE 300 as beam sweeping. At 303, the UE 300 may measure the K TX beams and report the best gNB TX beam(s) to the gNB 302 at 305. In response, the gNB 302 may transmit SSB with the best gNB TX beam(s) to the UE 300 at 307. At 309, the UE 300 may measure the SSB transmitted with the best gNB TX beam(s) with its J RX beams and determine the best beam pair(s). The determined best beam pair(s) together with DL BCR may be sent to the gNB 302 at 311.

[00042] In various example embodiments, the DL BCR for best beam pair(s) (k, j), i.e., H_dl(k,j) is sent to the gNB which may select at 313 one or more beam pairs (1, m) for PA DPoD tuning. The selected one or more beam pairs may be indicated to the UE in the configuration of UL SRS. At 315, for these pairs, the gNB may predict the UL BCR H_ul(l,m), by filtering the DL BCR H_dl(l,m) with e.g. a time domain filter, to account for the time difference (dt) between the estimation of H dl and the future UL transmission: H_ul(l,m) = filter(H_dl(l,m), dt).

[00043] Next, the UL SRS beamed transmission is configured by the gNB at 317 for the selected beam pairs and performed by the UE at 319, similarly as described in Figure 2. The beamed UL SRS (l,m) is measured and the combined channel response G(l,m) is obtained based on the UL SRS at 321. This response is assumed to be a combination between the PA response V(l,m) and the propagation channel response H_ul(l,m) as: G(l,m) = V(l,m)H_ul(l,m).

[00044] Finally, the gNB may at 321 use the obtained G(l,m), the predicted H ul(l,m) to estimate the PA response V(l,m) and derive the DPoD parameters.

[00045] Figure 4 describes a block diagram for some operation of a NE according to an example embodiment. In Figure 4, a NE, such as for example, the gNB 101 of Figure 1, the gNB 202 of Figure 2, or the gNB 302 of Figure 3, may send at 401 to a user equipment a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam. In various example embodiments, the configuration may further comprise at least one of a periodicity, resource allocation, or transmission power of the reference signal. At 402, the NE may also receive from the user equipment a reference signal generated based on the configuration.

[00046] At 403, the NE may collect reference signal data of the indicated at least one beam pair from the received reference signal. The NE may at 404 estimate digital postdistortion parameters with an artificial intelligence / machine learning model based on the collected reference signal data.

[00047] Figure 5 describes a block diagram for some operation of a UE according to an example embodiment. In Figure 5, a UE, such as for example, the UE 102 of Figure 1, the UE 200 of Figure 2, or the UE 300 of Figure 3, may receive at 501 from a network element a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam. In various example embodiments, the configuration may further comprise at least one of a periodicity, resource allocation, or transmission power of the reference signal. At 502, the UE may transmit to the network element a reference signal generated based on the configuration.

[00048] Reference is made to Figure 6 for illustrating a simplified block diagram of various example apparatuses that are suitable for use in practicing various example embodiments of this application. In Figure 6, a network element, NE, 601, such as for example, the gNB 101 of Figure 1, the gNB 202 of Figure 2, or the gNB 302 of Figure 3, is adapted for communication with a UE 611, such as for example, the UE 102, 104 or 106 of Figure 1, the UE 200 of Figure 2, or the UE 300 of Figure 3. The UE 611 includes at least one processor 615, at least one memory, MEM, 614 coupled to the at least one processor 615, and a suitable transceiver, TRANS, 613 (having a transmitter, TX, and a receiver, RX) coupled to the at least one processor 615. The at least one MEM 614 stores a program instructions, PROG, 612. The TRANS 613 may include or be coupled to one or more antennas 616 and is for bidirectional wireless communications with the NE 601. The at least one processor 615 and the PROG 612, may be utilized by the UE 611 in conjunction with various example embodiments of the application, as described herein.

[00049] The NE 601 includes at least one processor 605, at least one MEM 604 coupled to the at least one processor 605, and a suitable TRANS 603 (having a TX and a RX) coupled to the at least one processor 605. The at least one MEM 604 stores a PROG 602. The TRANS 603 may include or be coupled to one or more antennas 606 and is for bidirectional wireless communications with the UE 611. The NE 601 may be coupled to one or more cellular networks or systems, which is not shown in this figure. The at least one processor 605 and the PROG 602, may be utilized by the NE 601 in conjunction with various example embodiments of the application, as described herein.

[00050] In general, the various example embodiments of the apparatus 601 can include a node, host, or server in a communications network or serving such a network. For example, apparatus 601 may be a network node, satellite, base station, a Node B, an evolved Node B, eNB, 5G Node B or access point, next generation Node B, NG-NB or gNB, 6G base station, or a WLAN access point, associated with a radio access network, such as a LTE, 5G or NR, or 6G network.

[00051] It should be understood that, in some example embodiments, apparatus 601 may be comprised of an edge cloud server as a distributed computing system where the server and the radio node may be stand-alone apparatuses communicating with each other via a radio path or via a wired connection, or they may be located in a same entity 11 communicating via a wired connection. For instance, in certain example embodiments where apparatus 601 represents a gNB, it may be configured in a central unit, CU, and distributed unit, DU, architecture that divides the gNB functionality. In such an architecture, the CU may be a logical node that includes gNB functions such as transfer of user data, mobility control, radio access network sharing, positioning, or session management, etc. The CU may control the operation of DU(s) over a front-haul interface. The DU may be a logical node that includes a subset of the gNB functions, depending on the functional split option. In another example, a gNB may comprise multiple TRPs. It should be noted that one of ordinary skill in the art would understand that apparatus 601 may include components or features not shown in Figure 6.

[00052] In general, the various example embodiments of the apparatus 611 can include, but are not limited to, cellular phones, personal digital assistants having wireless communication capabilities, portable computers having wireless communication capabilities, image capture devices such as digital cameras having wireless communication capabilities, gaming devices having wireless communication capabilities, music storage and playback appliances having wireless communication capabilities, Internet appliances permitting wireless Internet access and browsing, as well as portable units or terminals that incorporate combinations of such functions. In an embodiment, apparatus 611 may be a node or element in a communications network or associated with such a network, such as a UE, mobile equipment, ME, mobile station, mobile device, stationary device, loT device, or other device. As described herein, a UE may alternatively be referred to as, for example, a mobile station, mobile equipment, mobile unit, mobile device, user device, subscriber station, wireless terminal, tablet, smart phone, loT device, sensor or NB-IoT device, a watch or other wearable, a head-mounted display, a vehicle, a drone, a medical device and applications thereof (e.g., remote surgery), an industrial device and applications thereof (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain context), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, or the like. As one example, apparatus 611 may be implemented in, for instance, a wireless handheld device, a wireless plug-in accessory, or the like. It should be noted that one of ordinary skill in the art would understand that apparatus 611 may include components or features not shown in Figure 6.

[00053] The example embodiments of this disclosure may be implemented by computer software or computer program code executable by one or more of the processors 605, 615 of the NE 601 and the UE 611, or by hardware, or by a combination of software and hardware.

[00054] At least one of the PROGs 602 and 612 is assumed to include program instructions that, when executed by the associated processor, enable the electronic apparatus to operate in accordance with the example embodiments of this disclosure, as discussed herein.

[00055] The TRANS 603 and 613 may include, for example, a plurality of radio interfaces that may be coupled to the antenna(s) 606 and 616, respectively. The radio interfaces may correspond to a plurality of radio access technologies including one or more of GSM, WCDMA, NB-IoT, LTE, 5G, 6G, WLAN, Bluetooth, BT-LE, NFC, radio frequency identifier, ultrawideband, MulteFire, and the like. The radio interface may include components, such as filters, converters (for example, digital-to-analog converters and the like), mappers, a Fast Fourier Transform module, and the like, to generate symbols for a transmission and to receive symbols. As such, TRANS 603 and 613 may be configured to modulate information on to a carrier waveform for transmission by the antenna(s) and demodulate information received via the antenna(s) for further processing by other elements of apparatus 601 and 611, respectively. In other embodiments, TRANS 603 and 613 may be capable of transmitting and receiving signals or data directly. Additionally or alternatively, in some embodiments, apparatus 601 and / or 611 may include an input and / or output device.

[00056] The MEMs 604 and 614 may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. For example, memory 604 and 614 can be comprised of any combination of random access memory, read only memory, static storage such as a magnetic or optical disk, hard disk drive, or any other type of non-transitory machine or computer readable media. The instructions stored in memory 604 or 614 may include program instructions or computer program code that, when executed by processor 605 or 615, enable the apparatus 601 or 611 to perform tasks as described herein.

[00057] In an embodiment, apparatus 601 or 611 may further include or be coupled to (internal or external) a drive or port that is configured to accept and read an external computer readable storage medium, such as an optical disc, USB drive, flash drive, or any other storage medium. For example, the external computer readable storage medium may store a computer program or software for execution by processor 605 / 615 or apparatus 601 / 611.

[00058] The processors 605 and 615 may be of any type suitable to the local technical environment, and may include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors, field-programmable gate arrays, application-specific integrated circuits, and processors based on multi-core processor architecture, as non-limiting examples. While a single processor 605 and 615 is shown in NE and UE of Figure 6, respectively, multiple processors may be utilized according to other embodiments. For example, it should be understood that, in certain embodiments, apparatus 601 or 611 may include two or more processors that may form a multiprocessor system (e g., in this case processor 605 or 615 may represent a multiprocessor) that may support multiprocessing. In certain embodiments, the multiprocessor system may be tightly coupled or loosely coupled (e.g., to form a computer cluster).

[00059] Without in any way limiting the scope, interpretation, or application of the claims appearing below, technical effects of one or more of the example embodiments disclosed herein may be dynamically adjusting the DPoD parameters for different beam pairs and enhancing the accuracy and efficiency of DPoD parameter estimation in beamforming wireless communication systems. This is substantial improvement over traditional methods that rely solely on estimations pr DMRS. The AI / ML model is able to be trained for multiple beams and therefore parameter estimation time is reduced.

[00060] The following are additional examples.

[00061] Example 1-1. A method, comprises: at a network element, sending to a user equipment a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; receiving from the user equipment a reference signal generated based on the configuration; collecting reference signal data of the indicated at least one beam pair from the received reference signal; and estimating digital post-distortion parameters with an artificial intelligence / machine learning model based on the collected reference signal data.

[00062] Example 1-2. The method of example 1-1, wherein the configuration comprises at least one of a periodicity, resource allocation, or transmission power of the reference signal.

[00063] Example 1-3. The method of any of previous examples, further comprises: receiving from the user equipment information associated with digital post-distortion, wherein the information comprises at least one of a capability of artificial 14 intelligence / machine learning based digital post-distortion operation of the user equipment power amplifier non-linearities, or a number of beam pairs that the user equipment can form.

[00064] Example 1-4. The method of any of previous examples, further comprises: receiving from the user equipment uplink data signal; and applying the digital post-distortion operation with the estimated digital post-distortion parameters on the received uplink data to compensate the nonlinearity of a power amplifier of the user equipment.

[00065] Example 1-5. The method of any of previous examples, further comprises: monitoring at least one of a quality of the link between the network element and the user equipment, an accuracy of the artificial intelligence / machine learning model, or an effectiveness of the compensation based on the applied post-distortion parameters; adjusting the configuration of the reference signal in response to the monitoring result; and sending the adjusted configuration of the reference signal to the user equipment.

[00066] Example 1-6. The method of any of previous examples, further comprises: training or re-training artificial intelligence / machine learning model based on the collected reference signal data.

[00067] Example 1-7. The method of example 1-6, wherein the training or retraining comprises: gathering a set of more than one beam pairs and their corresponding digital post-distortion parameters; identifying a feature that captures the relationship between each beam pair of the set and its corresponding digital post-distortion parameters; training the artificial intelligence / machine learning model to predict digital post-distortion parameters based on the identified feature of received beams; and validating the model on a test set of beam pairs and digital post-distortion parameters not seen during training.

[00068] Example 1-8. The method of example 1-7, wherein the model is trained based on only one beam pair, multiple beam pairs with equal importance, or multiple beam pairs with identifiers of the beam pairs embedded into a vector as an input to the model.

[00069] Example 1-9. The method of any of previous examples, further comprises: receiving a downlink beamformed channel response from the user equipment; selecting at least one beam pair from the received downlink beamed channel response; and predicting an uplink beamformed channel response for the selected at least one beam pair, and wherein the at least one beam pair indicated in the configuration of the reference signal comprises the selected at least one beam pair.

[00070] Example 1-10. The method of any of previous examples, further comprises: obtaining a combined channel response based on the received reference signal; and deriving the digital post-distortion parameters based on the predicted uplink beamformed channel response and the combined channel response.

[00071] Example 2-1. A method, comprises: at a user equipment, receiving from a network element a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; and transmitting to the network element a reference signal generated based on the configuration.

[00072] Example 2-2. The method of example 2-1, wherein the configuration comprises at least one of a periodicity, resource allocation, or transmission power of the reference signal.

[00073] Example 2-3. The method of example 2-1 or 2-2, further comprises: sending to the network element information associated with digital post-distortion, wherein the information comprises at least one of a capability of artificial intelligence / machine learning based digital post-distortion operation of the user equipment power amplifier nonlinearities, or a number of beam pairs that the user equipment can form.

[00074] Example 2-4. The method of any of examples 2-1 to 2-3, further comprises: transmitting to the network element uplink data signal based on the configuration of the reference signal.

[00075] Example 2-5. The method of any of examples 2-1 to 2-4, further comprises: receiving adjusted configuration of the reference signal from the network element.

[00076] Example 2-6. The method of any of examples 2-1 to 2-5, further comprises: transmitting a downlink beamformed channel response to the network element.

[00077] Example 3-1. A computer program, comprising code for performing the method of any of examples 1-1 to 2-6, when the computer program is run on a computer.

[00078] Example 3-2. The computer program according to example 3-1, wherein the computer program is directly loadable into an internal memory of the computer.

[00079] Example 4. A computer program product comprising a computer-readable medium bearing program instructions that, when executed by a processor, cause the processor to perform the method of any of examples 1-1 to 2-6.

[00080] Example 5. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform the method of any of examples 1-1 to 2-6.

[00081] Example 6-1. An apparatus, comprising means for performing the method of any of examples 1-1 to 2-6.

[00082] Example 6-2. The apparatus of example 6-1, wherein the means comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the apparatus.

[00083] Example 7. An apparatus, including circuitry configured to perform the method of any of examples 1-1 to 2-6.

[00084] Embodiments of the present invention may be implemented in software, hardware, application logic or a combination of software, hardware and application logic. The software, application logic and / or hardware may reside on an apparatus such as a user equipment, a gNB or other mobile communication devices. If desired, part of the software, application logic and / or hardware may reside on a NE 601, part of the software, application logic and / or hardware may reside on a UE 611, and part of the software, application logic and / or hardware may reside on other chipset or integrated circuit. In an example embodiment, the application logic, software or an instruction set is maintained on any one of various conventional computer-readable media. In the context of this document, a “computer-readable medium” may be any media or means that can contain, store, communicate, propagate or transport the instructions for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable medium may comprise a non-transitory computer-readable storage medium that may be any media or means that can contain or store the instructions for use by or in connection with an instruction execution system, apparatus, or device.

[00085] It is also noted herein that while the above describes example embodiments of the invention, these descriptions should not be viewed in a limiting sense. Rather, there are several variations and modifications which may be made without departing from the scope of the present invention. For example, while the various example embodiments are illustrated mainly for uplink DPoD operation, they can also be applied for downlink DPoD operation.

[00086] Further, the various names used for the described parameters are not intended to be limiting in any respect, as these parameters may be identified by any suitable names. If desired, the different functions discussed herein may be performed in a different order and / or concurrently with each other. Furthermore, if desired, one or more of the abovedescribed functions may be optional or may be combined. As such, the foregoing description should be considered as merely illustrative of the principles, teachings and example embodiments of this invention, and not in limitation thereof.

Claims

1. An apparatus, comprising:means for sending to a user equipment a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam;means for receiving from the user equipment a reference signal generated based on the configuration;means for collecting reference signal data of the indicated at least one beam pair from the received reference signal; andmeans for estimating digital post-distortion parameters with an artificial intelligence / machine learning model based on the collected reference signal data.

2. The apparatus according to claim 1, wherein the configuration comprises atleast one of a periodicity, resource allocation, or transmission power of the reference signal.

3. The apparatus according to claim 1 or 2, further comprising:means for receiving from the user equipment information associated with digital postdistortion, wherein the information comprises at least one of a capability of artificial intelligence / machine learning based digital post-distortion operation of the user equipment power amplifier non-linearities, or a number of beam pairs that the user equipment can form.

4. The apparatus according to any of claims 1 to 3, further comprising:means for receiving from the user equipment uplink data signal; and means for applying the digital post-distortion operation with the estimated digital postdistortion parameters on the received uplink data to compensate the nonlinearity of a power amplifier of the user equipment.

5. The apparatus according to any of claims 1 to 4, further comprising:means for monitoring at least one of a quality of the link between the apparatus and the user equipment, an accuracy of the artificial intelligence / machine learning model, or an effectiveness of the compensation based on the applied post-distortion parameters;means for adjusting the configuration of the reference signal in response to the monitoring result; andmeans for sending the adjusted configuration of the reference signal to the user equipment.

6. The apparatus according to any of claims 1 to 5, further comprising:means for training or re-training artificial intelligence / machine learning model based on the collected reference signal data.

7. The apparatus according to claim 6, wherein the means for training or retraining comprises:means for gathering a set of more than one beam pairs and their corresponding digital postdistortion parameters;means for identifying a feature that captures the relationship between each beam pair of the set and its corresponding digital post-distortion parameters;means for training the artificial intelligence / machine learning model to predict digital postdistortion parameters based on the identified feature of received beams; and means for validating the model on a test set of beam pairs and digital post-distortion parameters not seen during training.

8. The apparatus according to claim 7, wherein the model is trained based ononly one beam pair, multiple beam pairs with equal importance, or multiple beam pairs with identifiers of the beam pairs embedded into a vector as an input to the model.

9. The apparatus according to any of claims 1 to 8, further comprising:means for receiving a downlink beamformed channel response from the user equipment; selecting at least one beam pair from the received downlink beamed channel response; and means for predicting an uplink beamformed channel response for the selected at least one beam pair, and wherein the at least one beam pair indicated in the configuration of the reference signal comprises the selected at least one beam pair.

10. The apparatus according to claim 9, further comprising:means for obtaining a combined channel response based on the received reference signal; andmeans for deriving the digital post-distortion parameters based on the predicted uplink beamformed channel response and the combined channel response.

11. An apparatus, comprising:means for receiving from a network element a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; andmeans for transmitting to the network element a reference signal generated based on the configuration.

12. The apparatus according to claim 11, wherein the configuration comprises atleast one of a periodicity, resource allocation, or transmission power of the reference signal.

13. The apparatus according to claim 11 or 12, further comprising:means for sending to the network element information associated with digital postdistortion, wherein the information comprises at least one of a capability of artificial intelligence / machine learning based digital post-distortion operation of the apparatus power amplifier non-linearities, or a number of beam pairs that the apparatus can form.

14. The apparatus according to any of claims 11 to 13, further comprising:means for transmitting to the network element uplink data signal based on the configuration of the reference signal.

15. The apparatus according to any of claims 11 to 14, further comprising:means for receiving adjusted configuration of the reference signal from the network element.

16. The apparatus according to any of claims 11 to 15, further comprising:means for transmitting a downlink beamformed channel response to the network element.

17. A method, comprising:at a network element,sending to a user equipment a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam;receiving from the user equipment a reference signal generated based on the configuration; collecting reference signal data of the indicated at least one beam pair from the received reference signal; andestimating digital post-distortion parameters with an artificial intelligence / machine learning model based on the collected reference signal data.

18. A method, comprising:at a user equipment,receiving from a network element a configuration of a reference signal for digital postdistortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; andtransmitting to the network element a reference signal generated based on the configuration.

19. An apparatus, comprising:at least one processor; andat least one memory storing instructions, wherein the instructions, when executed by the at least one processor, cause the apparatus at least tosend to a user equipment a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam;receive from the user equipment a reference signal generated based on the configuration;collect reference signal data of the indicated at least one beam pair from the received reference signal; andestimate digital post-distortion parameters with an artificial intelligence / machine learning model based on the collected reference signal data.

20. An apparatus, comprising:at least one processor; andat least one memory storing instructions, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to21receive from a network element a configuration of a reference signal for digital postdistortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; andtransmit to the network element a reference signal generated based on the configuration.

21. A computer readable medium comprising program instructions stored thereonfor performing:at a network element,sending to a user equipment a configuration of a reference signal for digital post-distortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam;receiving from the user equipment a reference signal generated based on the configuration; collecting reference signal data of the indicated at least one beam pair from the received reference signal; andestimating digital post-distortion parameters with an artificial intelligence / machine learning model based on the collected reference signal data.

22. A computer readable medium comprising program instructions stored thereonfor performing:at a user equipment,receiving from a network element a configuration of a reference signal for digital postdistortion operation, wherein the configuration comprises an indication of at least one pair of transmit beam and receive beam; andtransmitting to the network element a reference signal generated based on the configuration.

Images