6g deep solution for power amplifier compensation in uplink carrier aggragation

Abstract

Various examples of embodiments described herein relate to apparatuses and methods for realizing a power amplifier compensation in uplink carrier aggregation. One such example of an embodiment relates to an apparatus, comprising 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 at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal, receive a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode, determine whether to apply the selected pre-distortion mode based on a condition of the apparatus, and apply the selected pre-distortion mode to the uplink carrier aggregation signal based on determining to apply the selected pre-distortion mode.

Description

[0001] 6G DEEP SOLUTION FOR POWER AMPLIFIER COMPENSATION IN UPLINK CARRIER AGGRAGATION

[0002] Field of the Invention

[0003] The present invention relates to an apparatus, a method and a computer program product for realizing a power amplifier compensation in uplink carrier aggregation (UL CA).

[0004] Related background Art

[0005] The following meanings for the abbreviations used in this specification apply:

[0006] ACLR adjacent channel leakage power ratio

[0007] Al artificial intelligence

[0008] BW bandwidth

[0009] CA carrier aggregation

[0010] CC component carrier

[0011] DL downlink

[0012] DPD digital pre-distortion

[0013] DPoD digital post-distortion

[0014] EVM error vector magnitude

[0015] ML machine learning

[0016] OOBE out-of-band-emission

[0017] PA power amplifier

[0018] UE user equipment

[0019] UL uplink

[0020] Example embodiments, although not limited to this, relate to a compensation of non-linearities introduced by a power amplifier (PA), which amplifies a transmission signal. This is achieved by carrying out a digital pre-distortion (DPD), by which the distortions caused by the power amplifier are cancelled. In such a scenario, it would be beneficial to enable an effective digital predistortion (DPD) depending on the kind of distortions caused by the power amplifier.

[0021] Summary of the Invention

[0022] Example embodiments address this situation aim to provide a more effective digital pre-distortion of a transmission signal.

[0023] Several aspects of the various example embodiments will be described with respect to certain aspects. These aspects are not intended to indicate key or essential features of the various example embodiments, nor are they intended to be used to otherwise limit the scope of the subject disclosure. Other features, aspects and elements of the various example embodiments will be readily apparent to a person skilled in the art in view of the subject disclosure.

[0024] According to a first aspect, an apparatus is provided which comprises 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 at least one predistortion mode to a network device, wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal, receive a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode, determine whether to apply the selected predistortion mode based on a condition of the apparatus, and apply the selected predistortion mode to the uplink carrier aggregation signal based on determining to apply the selected pre-distortion mode.

[0025] According to a second aspect, a method is provided which comprises sending at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal, receiving a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode, determining whether to apply the selected pre-distortion mode based on a condition of the apparatus, and applying the selected pre-distortion mode to the uplink carrier aggregation signal based on determining to apply the selected pre-distortion mode.

[0026] According to a third aspect, an apparatus is provided which comprises 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 at least one available pre-distortion mode from a user equipment, each pre-distortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal, select a pre-distortion mode from the at least one pre-distortion mode received from the user equipment based on a network condition, and send a response to the user equipment, the response indicating the selected pre-distortion mode to be applied by the user equipment.

[0027] According to a fourth aspect, a method is provided which comprises: receiving at least one available pre-distortion mode from a user equipment, each pre-distortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal, selecting a pre-distortion mode from the at least one pre-distortion mode received from the user equipment based on a network condition, and sending a response to the user equipment, the response indicating the selected pre-distortion mode to be applied by the user equipment.

[0028] Brief Description of the Drawings

[0029] These and other objects, features, details and advantages will become more fully apparent from the following detailed description of example embodiments, which is to be taken in conjunction with the appended drawings, in which:

[0030] Fig. 1A shows a UE 1 according to an example embodiment,

[0031] Fig. IB shows a procedure carried out by the UE 1 according to the example embodiment, Fig. 2A shows a gNB 2 according to an example embodiment,

[0032] Fig. 2B shows a procedure carried out by the gNB 2 according to the example embodiment,

[0033] Fig. 3 shows a further procedure carried out by the UE 1 according to an example embodiment,

[0034] Fig. 4 shows a further procedure carried out by the gNB 2 according to an example embodiment,

[0035] Fig. 5 shows a signalling diagram according to a third embodiment,

[0036] Fig. 6 shows a signalling diagram according to a fourth embodiment, and

[0037] Fig. 7 illustrates digital pre-distortion.

[0038] Detailed Description of example embodiments

[0039] In the following, description will be made to example embodiments. It is to be understood, however, that the description is given by way of example only, and that the described example embodiments are by no means to be understood as limiting the present invention thereto.

[0040] Before describing example embodiments, in the following, a technical context of example embodiments and problems of the prior art are discussed in some more detail.

[0041] As mentioned above, some example embodiments relate to transmission and reception of data / reference signals for effectively mitigating PA-introduced nonlinearities in communication systems, specifically ACLR and EVM, using native- air interfaces. To limit the ACLR and EVM, 5G NR defines requirements for NR transmissions as described in the following.

[0042] In the following, challenges with existing DPD are described. The proposed wide bandwidth (BW) of up to 400 MHz for 6G necessitates an ADC oversampling rate exceeding 1.2 GHz, posing a significant challenge. This wide BW introduces heightened memory effects in the PA. The concept of highly compressed PAs, sometimes referred to as digital PAs, is suggested to enhance efficiency, adding to the complexity. The added complexity of oversampling makes the feedback loop of DPD costly. AI / ML DPD as well as MPM solutions require oversampled feedback loops.

[0043] Fig. 7 illustrates digital pre-distortion (DPD). In particular, DPD is applied to a digital transmission signal x(n), which is input into a power amplifier in order to be amplified for transmission. The output of the power amplifier is fed back to DPD, so that it can be trained.

[0044] Without oversampling the PA output it is not possible to compensate for the ACLR and meet the ACLR requirement when the PA is driven in saturation to increase energy efficiency.

[0045] TS 38.101 describes some requirements in connection with ACLR: The Out of band emissions are unwanted emissions immediately outside the assigned channel bandwidth resulting from the modulation process and non-linearity in the transmitter but excluding spurious emissions. This out of band emission limit is specified in terms of a spectrum emission mask and an adjacent channel leakage power ratio.

[0046] To improve measurement accuracy, sensitivity and efficiency, the resolution bandwidth may be smaller than the measurement bandwidth. When the resolution bandwidth is smaller than the measurement bandwidth, the result should be integrated over the measurement bandwidth in order to obtain the equivalent noise bandwidth of the measurement bandwidth. NR Adjacent Channel Leakage power Ratio (NRACLR) is the ratio of the filtered mean power centered on the assigned NR channel frequency to the filtered mean power centered on an adjacent NR channel frequency at nominal channel spacing. The assigned NR channel power and adjacent NR channel power are measured with rectangular filters with measurement bandwidths specified in the following table 1, which reproduces Table 6.5.2.4.1-1 of TS 38.101.

[0047] If the measured adjacent channel power is greater than -50 dBm then the N RACLR shall be higher than the value specified in the following table 2, which reproduces Table 6.5.2.4.1-2 of TS 38.101.

[0048] Table 1 : NR ACLR measurement bandwidth

[0049] Table 2: NR ACLR requirement

[0050] Thus, as mentioned above, in UL CA with a single multi-band PA, the intermodulation distortions resulting from the PA nonlinearity may violate the spectral emissions, unless effective digital pre-distortion (DPD) of the aggregated signal is being applied prior to transmission.

[0051] Obtaining an effective DPD is challenging, since the DPD must effectively cancel the intermodulation products of several orders (3rd and beyond). It has been shown that this depends on:

[0052] - the PA response model i.e. memory size and depth, which are typically unknown and variable, - the number of aggregated carriers, and

[0053] - the carrier frequencies of each signal.

[0054] Some embodiments target on designing a DPD which is robust to the above three items.

[0055] Summarizing, some example embodiments are directed to the problem that in UL CA with a single multi-band power amplifier (PA), nonlinearities in a PA output can cause intermodulation distortions (IMD), potentially violating spectral emission limits. Effective DPD is required to cancel these distortions, but this is challenging due to variable PA memory effects and model variations, the number of aggregated carriers, and differing carrier frequencies. Example embodiments aim to design a robust DPD system to address these challenges.

[0056] In the following, a general overview of some example embodiments is described by referring to Figs. 1A, IB, 2A and 2B.

[0057] Fig. 1A shows a UE 1 according to the present example embodiment. The UE 1 is an example for an apparatus, which may be or be a part of a user equipment, for example. A procedure carried out by the UE 1 is illustrated in Fig. IB. The UE 1 shown in Fig. 1A comprises at least one processor 11 and at least one memory 12 storing instructions that, when executed by the at least one processor 11, cause the apparatus to: send at least one pre-distortion mode to a network device (e.g., gNB 2 shown in Fig. 2A), wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal (Sil in Fig. IB), receive a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode (S12, determine whether to apply the selected pre-distortion mode based on a condition of the apparatus (S12 in Fig. IB), and apply the selected pre-distortion mode to the uplink carrier aggregation signal based on determining to apply the selected pre-distortion mode (S13 in Fig. IB).

[0058] Fig. 2A shows a gNB 2 according to an example embodiment. The gNB 2 is an example for an apparatus, which may be or may be a part of a network device or network control device, for example. A procedure carried out by the gNB 2 is illustrated in Fig. 2B. The gNB 2 shown in Fig. 2A comprises at least one processor 21 and at least one memory 22 storing instructions that, when executed by the at least one processor 21, cause the apparatus to: receive at least one available predistortion mode from a user equipment (e.g., UE 1 shown in Fig. 1A), each predistortion mode indicates a mode of pre-distorting a uplink carrier aggregation (S21 in Fig. 2B); select a pre-distortion mode from the at least one pre-distortion mode received from the user equipment based on a network condition (S22 in Fig. 2B), and send a response to the user equipment, the response indicating the selected pre-distortion mode to be applied by the user equipment (S23 in Fig. 2B).

[0059] Hence, according to several example embodiments, mechanisms are provided by which it is possible to flexibly enable an effective pre-distortion (digital predistortion (DPD)) of an uplink (UL) carrier aggregation (CA) signal.

[0060] The apparatuses 1 and 2 shown in Figs. 1A and 2A may comprise more components than described above, and may further comprise I / O units 13, 23, for example, which are capable of transmitting to and receiving from other network elements.

[0061] According to some example embodiments, the above procedures carried out by the UE 1 and the gNB 2 may modified such that a matched reception is carried out. That is, the network device (e.g., the gNB) may perform a training procedure in order to learn a post-distortion mode which is matched to the pre-distortion mode applied by the UE. These procedures are shown in Figs. 3 and 4.

[0062] In particular, as shown in Fig. 3, the instructions stored in the memory 12 of the UE 1 may, when executed by the at least one processor 11, cause the apparatus to: send at least one pre-distortion mode to a network device (e.g., gNB 2 shown in Fig. 2A), wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal (S31), receive a response from the network device, indicating a pre-distortion mode selected from the at least one predistortion mode and an instruction for performing a training procedure (S32), apply the selected pre-distortion mode (S33), and perform an uplink reference signal transmission (S34). As shown in Fig. 4, the instructions stored in the memory 22 of the gNB 2 may, when executed by the at least one processor 21, cause the apparatus to: receive at least one pre-distortion mode from a user equipment (e.g. UE 1), each predistortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal (S41 in Fig. 4); select a pre-distortion mode from the at least one available pre-distortion mode received from the user equipment based on a network condition (S42 in Fig. 4); send an instruction for a training procedure indicating that the selected pre-distortion mode is to be applied by the user equipment for the training procedure (S43) and receive an uplink reference signal transmission from the user equipment for training a post-distortion mode (S44).

[0063] The uplink carrier aggregation signal may be a signal, into which at least two signals are aggregated. The aggregation signal may be amplified by a power amplifier. In more detail, the uplink carrier aggregation signal may be converted into an analog transmission signal, which is to be amplified by the power amplifier. The UE 1 or the corresponding apparatus may comprise the power amplifier. Moreover, the UE 1 or the corresponding apparatus may comprise an analog-digital converter for converting the uplink carrier aggregation signal into the analog transmission signal.

[0064] Furthermore, the at least one pre-distortion mode may be applied to reduce different distortion types caused by non-linearities of the power amplifier. The power amplifier may be a single multi-band power amplifier.

[0065] The post-distortion mode may be a mode by which a distortion in the received uplink carrier aggregation signal caused by the power amplifier of the user equipment is to be reduced.

[0066] Each of the at least one pre-distortion mode may be indicated by parameter set indicating an importance of the pre-distortion mode, and the at least one predistortion mode may be sent to the network device (e.g., from UE 1 to gNB 2) by reporting at least one parameter set to the network device. In other words, in case a plurality of pre-distortion modes are present, and each pre-distortion mode is indicated by one parameter, and the parameters of all pre-d istortion modes are sent or reported to the network device as one parameter set.

[0067] The pre-distortion modes may comprise at least one of: a mode for reducing an in-band distortion caused by a power amplifier of the user equipment, a mode for reducing an out-of-band distortion caused by the power amplifier of the user equipment, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier of the user equipment, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier of the user equipment.

[0068] The selected pre-distortion mode may be applied to the uplink carrier aggregation signal by applying a compensation signal, which is based on a power amplifier response and characteristics of the transmission signal, to the uplink carrier aggregation signal.

[0069] The user equipment (e.g., UE 1) may reject the selected pre-distortion mode and may send, to the network device (e.g., gNB 2) a proposal for a different predistortion mode, which is different from the selected pre-distortion mode. The network node may determine, based on the network condition, whether to accept the proposal, and send a further response to the user equipment indicating whether the proposal is accepted or not. The network condition may be presence / absence of a network element using a neighbor frequency band, or a frequency range of the transmission signal or the like.

[0070] The network device (e.g., gNB 2) may apply a post-distortion mode to the uplink carrier aggregation signal received from the user equipment. In this way, for example residual in-band distortions can be reduced or canceled.

[0071] Moreover, the network device (e.g., gNB 2) may instruct the user equipment (e.g. UE 1) to carry out a training procedure to the user equipment based on the applied post-distortion mode. The instruction may indicate a pre-distortion mode to be applied by the user equipment during the training procedure. During the training procedure, the user equipment may send an uplink reference signal transmission to the network device for training the post-distortion mode at the network device. The uplink reference signal transmission is pre-distorted by the indicated predistortion mode, and is sent using a uplink carrier aggregation.

[0072] Furthermore, it is noted that, when specifying that a distortion is cancelled, this is to be understood such that the distortion is reduced as much as possible. It does not necessarily mean that the distortion is completely cancelled or completely made to zero.

[0073] By using different modes of pre-distortions, the system can target and compensate for various types of distortions that arise from PA nonlinearity such as in-band, out-band and 3rd order distortions. By allowing the UE to accept or reject the configured pre-distortion mode, the system gains flexibility. This ensures that the UE can adapt to varying network conditions, device capabilities, and user preferences.

[0074] Example embodiments can enable pre-distortions to learn the distortion behavior over multiple / different CC combinations and the use of post distortions at the gNB provides an additional layer of distortion correction, ensuring that any residual distortions not handled by the pre-distortion at the UE are effectively managed.

[0075] In the following, some example embodiments are described more detail.

[0076] In particular, according to some example embodiments, a method and associated signalling are provided to enable a digital pre-distortion (DPD) of an UL CA signal in the UE and correct for the residual distortion in the gNB by means of deep digital post-distortion (DPoD).

[0077] According to some example embodiments, the UE is training and deploying a deep CA DPD which may operate in a multi-mode way, where mode refers to the type of distortion it is capable of compensating for e.g. :

[0078] In-band distortion only, Out-of-band distortion only,

[0079] 3rd order intermodulation product of the OOB distortion only, Both in- and out-of band distortion, etc.

[0080] The deep CA DPD functionality is then disclosed to the gNB which may enable a specific mode at a time. After the DPD mode is configured, a matched deep CA DPoD mode may be optionally / additionally configured at the gNB to cope with the residual distortion. Lastly, when the matched deep CA DPoD needs additional training, then a training-specific protocol is triggered between the UE and the gNB.

[0081] In the following, some more detailed embodiments are described.

[0082] According to a first embodiment, a procedure for learning or training a DPD at the UE is provided. In order to successfully attenuate the intermodulation distortion resulting from using a multi-component carrier (mCC) PA when transmitting intraband non-contiguous UL CA with N> 1 aggregated carriers, either the PA response should be known, or a feedback loop from the PA output should be used to capture and model the intermodulation distortion of various orders (e.g. 3 and higher). Once a model of the distortion is obtained, a compensation signal (also called henceforth an injection signal) is derived and injected into the UL CA signal to effectively reduce the intermodulation distortion at the output of the PA.

[0083] The injection signal parameters depend at least on the following:

[0084] The coefficients of the PA response

[0085] The characteristics of the signals that have been aggregated into the UL CA signal i.e. their number, respective carriers, bandwidths.

[0086] It is assumed that the PA is excited with a dual carrier UL signal : and that the PA response is:

[0087] Where P is the unknown polynomial order and M is the unknown memory length.

[0088] By substituting (1) in (2), one can see that the intermodulation distortion is caused by: terms weighted by the unknown PA coefficients apm.

[0089] To successfully cancel these terms, the coefficients, the memory, and polynomial sizes should be known. Instead of estimating these parameters by standard DPD processing like described above, it is proposed to train an AIML enhanced DPD block, called deep CA DPD.

[0090] In the following, a deep CA DPD input is described.

[0091] In particular, inspired by the modeling shown in equation (3) above, as input to the deep CA DPD, the following is used: a. not only the CA signal x(n) in (1), but also b. the CC components x1(x2and

[0092] C. the products x (n - m)x^~rin - rri) and x2(n - m)x-1(n - rri) in (3).

[0093] Since P (polynomial order) and M (memory length) are unknown, the input is purposely overly dimensioned, and the products for all m = l -. Moverand p = . Pover, are fed to the deep CA DPD, wherein Mover,Poverare chosen arbitrarily large, so as to ensure that Mover> M and Pover> P e.g., Mover= 5,Pover= 5.

[0094] Alternatively, architectures with masking and position embedding for M and P can be used. For each combination of p and m, there is one input with a specific position identification. Every time the combination is expected to be fed into the model, its position will be embedded and utilized. Every time that a combination is not available, it will be treated as a masked item. By doing so, a smaller model which can take a various set of combinations for p and m could be implemented.

[0095] It is noted that the intuition is that by inputting the products, the deep CA DPD is guided to learn faster the distortion and thus also learn faster how to compensate for it.

[0096] In the following, a loss function is described, which is used for the training procedure.

[0097] To train deep CA DPD, the output of the PA response is oversampled, and it collected: the in-band signal called yf(n) the out-of-band signals located at e.g. k times the carrier f, k = 3, 5 etc. called ykf(n) etc.

[0098] It is noted that the oversampling is required only in the training phase, to enable the computation of the loss function.

[0099] Lastly, it is looked at the following tasks:

[0100] Task A: Suppressing the k-th order intermodulation distortion only. In this case, the loss function can be defined as the power of the k-th order distortion: £oka In other words, the deep CA DPD is trained to minimize the k-th order distortion only.

[0101] Task B: In-band linearization. In this case, it is possible to use as the loss function the MSE (mean square error) between the PA output j (n) with gain normalization yf(n) and the PA input

[0102] Task C: Solving both A and B. In this case, the loss function can be provided as a weighted sum £ = ak£ok+ p£i , where a and f> are weighing the importance of suppressing the out-of-band vs the in-band distortions. These weighing factors may be coordinated with the gNB e.g. multiple models may be trained e.g.

[0103] One model trained only for A and third order distortion: a3= 1, p = 0

[0104] One model trained only for B: ak= 0,v / c, p = 1

[0105] One model trained to give equal importance to both A and B: ak= P, kP ak+ p = 1

[0106] One model trained to prioritize third order distortion cancellation: a3> p > 0, etc.

[0107] One model trained to prioritize B: p > a > 0

[0108] Hence, according to the first embodiment, it is possible to train different DPD modes.

[0109] According to a second embodiment, a generalization over multiple intra-band CC combinations is described.

[0110] To enable the deep CA DPD to learn the distortion behaviour over multiple / different CC combinations, the model as described according to the first embodiment above may be extended to receive inputs from a selected list of CCs (and not only two as in first embodiment) which are expected to be aggregated. Thus, the deep CA DPD input may be:

[0111] 1. the CA signal x(n)

[0112] 2. the CC components x1,x2, ...,xvand

[0113] 3. the products Since

[0114] P and M are unknown, the input is purposely overly dimensioned and the products for all m = l-. Moverand p = l-. Poverare fed to the deep CA DPD, where Mover,Poveris chosen arbitrarily large, so as to ensure that Mover> M and Pover> P e.g., Mover=

[0115] Alternatively, it is possible to use architectures with masking and position embedding for the M and P. For each combination of p and m, we have one input with a specific position identification. Every time the combination is expected to be fed into the model, its position will be embedding and utilized. Every time that a combination is not available, it will be treated as a masked item. By doing so, a smaller model which can take a various set of combinations for p and m could be implemented.

[0116] Same loss function as described according to the first embodiment can be used. During training, training data for a variable number of CC combinations can be generated, and the missing CC can be zero padded e.g. generate a CA signal using CC k and j input CA signal x,

[0117] CC signals xk,xjrand

[0118] All their intermodulation products to the deep CA DPD at the corresponding input positions pad with zeros the remaining input entries.

[0119] According to a third embodiment, configuration signals are provided, by which the gNB and the UE may mitigate the use of DPD mode.

[0120] In order to standardize the usage of the deep CA DPD, the UE must disclose to the gNB the capability of the model i.e. if the deep CA DPD can perform tasks A, B and / or C, which are described above in the first embodiment, and to what extent. To that end, the UE may report a deep CA DPD modes by reporting the parameters defined above:

[0121] 1. Mode 1 : 3rdorder distortion cancellation only: a3= 1, p = 0

[0122] 2. Mode 2: in band distortion cancellation only: ak= 0, p = 1

[0123] 3. Mode 3: equal out- and in- band distortion cancellation: ak= p, / k

[0124] 4. Mode 4: prioritize 3rdorder distortion cancellation : a3> p > 0, etc.

[0125] Then, the gNB may configure one of the available UE modes e.g. : if the gNB requests the UE to activate deep CA DPD mode 1, then the gNB undertakes the task of cancelling the in-band distortion fully at reception e.g. by DPoD means. If the gNB requests the UE to activate deep CA DPD mode 4, then the gNB expects some residual in-band distortion and undertakes the task of cancelling the in-band distortion partially at reception.

[0126] Note that Mode 2 can in many cases be most suitable for FR2 frequency range applications, where UE generally does not violate out-of-band-emission (OOBE) because of the beamforming. Whenever in FR2 gNB configures the parameters (at, ... aK), is it for mitigating OOBE in the adjacent channel (to benefit another NW). However, this goal in FR2 has less priority since it is not a gating factor. The main gaiting factor in FR2 is EVM. This means that of the four mentioned Modes, Mode 2 is the most applicable to FR2 frequency band operation.

[0127] It is noted that the UE may receive and reject the configuration e.g. in case of low battery, or other UE temporary limitations. For example, the gNB may configure mode 3, but the UE may not be able to activate it due to low battery. In this case, the UE rejects the configuration and request another mode e.g. may indicate a preferred fall-back deep CA DPD mode.

[0128] Fig. 5 shows a signal exchange between the UE and the gNB.

[0129] In Al, the UE sends a list of available deep CA DPD modes to the gNB, for example by including the parameters (alt... aK, p) described above, in order to disclose which one of the modes 1, 2, 3 and 4 are supported. In A2, the gNB selects one of the modes, in the example indicated as deep CA DPD mode x, and activates this mode. In other words, the gNB configures or instructs the UE to apply the deep CA DPD mode X. In A3, the UE either accepts the selected mode or rejects the selected mode (e.g. due to low battery as described above) and suggests a preferred mode instead. In A4, assuming that the UE accepts the selected mode or assuming that the gNB accepts the suggested preferred mode of the UE, the gNB configures a UL CA combination for the UE, and in A5, the UE sends the UL CA signal, predistorted with the deep CA DPD mode X.

[0130] In A6, the gNB receives the CA signal in accordance to CA DPD mode X, and optionally performs a residual in-band cancellation. That is, the gNB either performs a cancellation (reduction) of residual in-band distortions, which were not cancelled (reduced) by the deep CA DPD at the UE, or does not perform such a cancellation.

[0131] In the following, a fourth embodiment is described, in which signals for a matched reception are exchanged. That is, the gNB may perform a training procedure for training a deep CA DPoD.

[0132] In particular, once the deep CA DPD functionality has been disclosed to the gNB, including available modes, as described above according to the third embodiment, if the gNB decides to train a matched deep CA DPoD to cancel the residual EVM for some of the deep CA DPD modes, then the gNB and UE should handshake on a training procedure in which the UE activates said mode and makes an UL reference signal RS transmission with a selected bandwidth and modulation e.g. 256 QAM may be preferred since gains by DPoD are expected for higher modulations.

[0133] For example, the gNB may train at least 2 matched modes in which it either: Corrects the full EVM - when the UE does not do so, i.e. for deep CA DPD mode 1.

[0134] Corrects a residual EVM - when the UE applies deep CA DPD modes 3 and 4.

[0135] The handshake is shown in Error! Reference source not found.. In Bl, similar to Al of Fig. 5, the UE sends a list of available deep CA DPD modes to the gNB, for example by including the parameters a1, ... aK, p) described above, in order to disclose which one of the modes 1, 2, 3 and 4 are supported. In B2, the gNB selects one of the modes (the selected mode being indicated as deep CA DPD mode X) and trains for the selected deep CA DPD mode X. In particular, the gNB configures an uplink reference signal (UL RS) for training. In B3, the UE activates the selected deep CA DPD mode X, i.e., applies the selected deep CA DPD mode X. In B4, the UE sends the UL RS, predistorted with the deep CA DPD mode X. In B5, the gNB collects (receives) the RS and trains a matched CA DPoD, i.e., a CA DPoD, which is matched to the deep CA DPD mode X applied by the UE. Thus, according to example embodiments as described above, an effective digital pre-distortion (DPD) of an uplink (UL) carrier aggregation signal is achieved.

[0136] The above-described example embodiments are only examples and may be modified.

[0137] Names of network elements, protocols, and methods are based on current standards. In other versions or other technologies, the names of these network elements and / or protocols and / or methods may be different, as long as they provide a corresponding functionality.

[0138] In general, example embodiments may be implemented by computer software stored in the memory (memory resources, memory circuitry) 12, 22 and executable by the processor (processing resources, processing circuitry) 11, 21 or by hardware, or by a combination of software and / or firmware and hardware.

[0139] The terms "connected," "coupled," or any variant thereof, mean any connection or coupling, either direct or indirect, between two or more elements, and may encompass the presence of one or more intermediate elements between two elements that are "connected" or "coupled" together. The coupling or connection between the elements can be physical, logical, or a combination thereof. As employed herein two elements may be considered to be "connected" or "coupled" together by the use of one or more wires, cables and printed electrical connections, as well as by the use of electromagnetic energy, such as electromagnetic energy having wavelengths in the radio frequency region, the microwave region and the optical (both visible and invisible) region, as non-limiting examples.

[0140] The memory (memory resources, memory circuitry) 12, 22 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, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, and non-transitory computer-readable media. The processor (processing resources, processing circuitry) 11, 21 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 (DSPs) and processors based on a multi core processor architecture, as non-limiting examples.

[0141] Further, as used in this application, the term "circuitry" may refer to one or more or all of the following:

[0142] (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and

[0143] (b) combinations of hardware circuits and software, such as (as applicable):

[0144] (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and

[0145] (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and

[0146] (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0147] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in a server, a cellular network device, or other computing or network device.

[0148] The term "non-transitory", as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM). It is noted that, as used herein, "at least one of the following: " and "at least one of " and similar wording, where the list of two or more elements are joined by "and" or "or", mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0149] It is to be understood that the various example embodiments of the subject disclosure are illustrative and non-limiting and are not intended to be construed as limiting. Various modifications and applications may be apparent to those skilled in the art without departing from the spirit and scope of the various example embodiments of the subject disclosure.

[0150] Item 1. An apparatus, comprising 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 at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal, receive a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode, determine whether to apply the selected pre-distortion mode based on a condition of the apparatus, and apply the selected pre-distortion mode to the uplink carrier aggregation signal based on determining to apply the selected pre-distortion mode.

[0151] Item 2. The apparatus according to item 1, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: send the at least one pre-distortion mode to the network device by reporting at least one parameter set to the network device. Item 3. The apparatus according to item 1 or 2, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: in response to determine not to apply the received pre-distortion mode, send a proposal for a different pre-distortion mode from the at least one predistortion mode to the network device based on the condition of the apparatus.

[0152] Item 4. The apparatus according to item 3, wherein the condition of the apparatus comprises at least one of: charging state of a power supply of the apparatus, or a temporary limitation of the apparatus.

[0153] Item 5. The apparatus according to item 1, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier.

[0154] Item 6. The apparatus according to item 5, wherein the at least one pre-distortion mode is applied to reduce different distortion types caused by non-linearities of the power amplifier.

[0155] Item 7. The apparatus according to item 5 or 6, wherein the power amplifier is a single multi-band power amplifier.

[0156] Item 8. The apparatus according to any one of the items 5 to 7, wherein the pre-distortion modes comprise at least one of: a mode for reducing an in-band distortion caused by the power amplifier, a mode for reducing an out-of-band distortion caused by the power amplifier, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier. Item 9. The apparatus according to any one of the items 1 to 8, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: in case the response received from the network device contains an instruction for a training procedure from the network device, apply the selected pre-d istortion mode, and perform an uplink reference signal transmission.

[0157] Item 10. The apparatus according to item 9, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: perform the uplink reference signal transmission within a bandwidth and via a predetermined modulation.

[0158] Item 11. The apparatus according to any one of the items 1 to 10, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: apply the selected pre-distortion mode to the uplink carrier aggregation signal by applying a compensation signal, which is based on a power amplifier response and characteristics of the transmission signal, to the uplink carrier aggregation signal.

[0159] Item 12. The apparatus according to item 1, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive an uplink carrier aggregation combination configuration from the network device, and transmit the uplink carrier aggregation signal, which is based on the received configuration.

[0160] Item 13. The apparatus according to item 1, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: learn a pre-distortion for reducing a distortion caused by the power amplifier by using a loss function suitable for a certain distortion type.

[0161] Item 14. The apparatus according to item 13, wherein the distortion types comprise at least one of: an in-band distortion, an out-of-band distortion, or a distortion of a certain order.

[0162] Item 15. The apparatus according to item 13 or 14, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: use the uplink carrier aggregation signal and at least two component carriers of the uplink carrier aggregation signal as inputs for training the pre-distortion.

[0163] Item 16. The apparatus according to any one of the items 1 to 15, wherein the apparatus comprises the power amplifier and a digital-analog-converter for converting the uplink carrier aggregation signal into the analog transmission signal to be amplified by the power amplifier.

[0164] Item 17. An apparatus, comprising 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 at least one available pre-distortion mode from a user equipment, each pre-distortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal, select a pre-distortion mode from the at least one pre-distortion mode received from the user equipment based on a network condition, and send a response to the user equipment, the response indicating the selected pre-distortion mode to be applied by the user equipment.

[0165] Item 18. The apparatus according to item 17, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive the at least one pre-distortion mode by receiving at least one parameter set from the user equipment.

[0166] Item 19. The apparatus according to item 17 or 18, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive, from the user equipment, a proposal for a different pre-distortion mode, which is different from the selected pre-distortion mode, determine, based on the network condition, whether to accept the proposal, and send a further response to the user equipment indicating whether the proposal is accepted or not.

[0167] Item 20. The apparatus according to any one of the items 17 to 19, wherein the at least one pre-distortion mode comprises at least one of: a mode for reducing an in-band distortion caused by a power amplifier of the user equipment, a mode for reducing an out-of-band distortion caused by the power amplifier of the user equipment, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier of the user equipment, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier of the user equipment.

[0168] Item 21. The apparatus according to item 20, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: select the pre-distortion mode for reducing the out-of-band distortion based on at least one of a determination whether a network element using a neighbor frequency band is present, or a frequency range of the transmission signal.

[0169] Item 22. The apparatus according to any one of the items 17 to 21, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive the uplink carrier aggregation signal from the user equipment, and apply a post-distortion mode to the uplink carrier aggregation signal.

[0170] Item 23. The apparatus according to item 22, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: send an instruction for a training procedure to the user equipment based on the applied post-distortion mode, the instruction indicating a pre-d istortion mode to be applied by the user equipment during the training procedure, and receive an uplink reference signal transmission from the user equipment for training the post-distortion mode.

[0171] Item 24. An apparatus, comprising 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 at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal, receive a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode and an instruction for performing a training procedure, apply the selected pre-distortion mode, and perform an uplink reference signal transmission. Item 25. The apparatus according to item 24, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to determine whether to apply the received pre-distortion mode based on a condition of the apparatus, and, apply the pre-distortion mode during the training procedure based on determining to apply the received pre-distortion mode.

[0172] Item 26. The apparatus according to item 24 or 25, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: perform the uplink reference signal transmission within a bandwidth and via a predetermined modulation.

[0173] Item 27. The apparatus according to item 24, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier.

[0174] Item 28. The apparatus according to item 27, wherein the at least one pre-distortion mode is applied to reduce different distortion types caused by non-linearities of the power amplifier.

[0175] Item 29. The apparatus according to item 27 or 28, wherein the power amplifier is a single multi-band power amplifier.

[0176] Item 30. The apparatus according to any one of the items 27 to 29, wherein the pre-distortion modes comprise at least one of: a mode for reducing an in-band distortion caused by the power amplifier, a mode for reducing an out-of-band distortion caused by the power amplifier, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier. Item 31. The apparatus according to item 24, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: send the at least one pre-distortion mode to the network device by reporting at least one parameter set to the network device.

[0177] Item 32. The apparatus according to item 24, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive an uplink carrier aggregation combination configuration from the network device, and transmit the uplink carrier aggregation signal, which is based on the received configuration.

[0178] Item 33. The apparatus according to item 24, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: learn a pre-distortion for reducing a distortion caused by the power amplifier by using a loss function suitable for a certain distortion type.

[0179] Item 34. The apparatus according to item 33, wherein the distortion types comprise at least one of: an in-band distortion, an out-of-band distortion, or a distortion of a certain order.

[0180] Item 35. The apparatus according to item 33 or 34, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: use the uplink carrier aggregation signal and at least two component carriers of the uplink carrier aggregation signal as inputs for training the pre-distortion. Item 36. An apparatus, comprising 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 at least one pre-distortion mode from a user equipment, each predistortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal, select a pre-distortion mode from the at least one available pre-distortion mode received from the user equipment based on a network condition, send an instruction for a training procedure indicating that the selected predistortion mode is to be applied by the user equipment during the training procedure, and receive an uplink reference signal transmission from the user equipment for training a post-distortion mode.

[0181] Item 37. The apparatus according to item 36, wherein the uplink reference signal transmission is carried out within a bandwidth and via a predetermined modulation.

[0182] Item 38. The apparatus according to item 36 or 37, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: apply the post-distortion mode to the received uplink carrier aggregation signal.

[0183] Item 39. The apparatus according to item 36 or 37, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier of the user equipment, and the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: apply the post-distortion mode to reduce a distortion in the received uplink carrier aggregation signal caused by the power amplifier of the user equipment.

[0184] Item 40. A method, comprising sending, from a user equipment, at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of predistorting an uplink carrier aggregation signal, receiving, by the user equipment, a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode, determining whether to apply the selected pre-distortion mode based on a condition of the user equipment, and applying the selected pre-distortion mode to the uplink carrier aggregation signal based on determining to apply the selected pre-distortion mode.

[0185] Item 41. The method according to item 40, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the method further comprises: sending the at least one pre-distortion mode to the network device by reporting at least one parameter set to the network device.

[0186] Item 42. The method according to item 40 or 41, further comprising: sending, in response to determine not to apply the received pre-distortion mode, a proposal for a different pre-distortion mode from the at least one predistortion mode to the network device based on the condition of the user equipment.

[0187] Item 43. The method according to item 42, wherein the condition of the user equipment comprises at least one of: charging state of a power supply of the user equipment, or a temporary limitation of the user equipment.

[0188] Item 44. The method according to item 40, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier.

[0189] Item 45. The method according to item 44, wherein the at least one pre-distortion mode is applied to reduce different distortion types caused by non-linearities of the power amplifier.

[0190] Item 46. The method according to item 44 or 45, wherein the power amplifier is a single multi-band power amplifier.

[0191] Item 47. The method according to any one of the items 44 to 46, wherein the pre-distortion modes comprise at least one of: a mode for reducing an in-band distortion caused by the power amplifier, a mode for reducing an out-of-band distortion caused by the power amplifier, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier.

[0192] Item 48. The method according to any one of the items 40 to 47, further comprising, in case the response received from the network device contains an instruction for a training procedure from the network device: applying the selected pre-distortion mode, and performing an uplink reference signal transmission.

[0193] Item 49. The method according to item 48, further comprising: performing the uplink reference signal transmission within a bandwidth and via a predetermined modulation.

[0194] Item 50. The method according to any one of the items 40 to 49, further comprising: applying the selected pre-distortion mode to the uplink carrier aggregation signal by applying a compensation signal, which is based on a power amplifier response and characteristics of the transmission signal, to the uplink carrier aggregation signal.

[0195] Item 51. The method according to item 40, further comprising: receiving an uplink carrier aggregation combination configuration from the network device, and transmitting the uplink carrier aggregation signal, which is based on the received configuration.

[0196] Item 52. The method according to item 40, further comprising: learning a pre-distortion for reducing a distortion caused by the power amplifier by using a loss function suitable for a certain distortion type.

[0197] Item 53. The method according to item 52, wherein the distortion types comprise at least one of: an in-band distortion, an out-of-band distortion, or a distortion of a certain order.

[0198] Item 54. The method according to item 52 or 53, further comprising: using the uplink carrier aggregation signal and at least two component carriers of the uplink carrier aggregation signal as inputs for training the predistortion.

[0199] Item 55. The method according to any one of the items 40 to 54, wherein the user equipment comprises the power amplifier and a digital-analog-converter for converting the uplink carrier aggregation signal into the analog transmission signal to be amplified by the power amplifier.

[0200] Item 56. A method, comprising receiving, by a network device, at least one available pre-distortion mode from a user equipment, each pre-distortion mode indicates a mode of predistorting a uplink carrier aggregation signal, selecting a pre-distortion mode from the at least one pre-distortion mode received from the user equipment based on a network condition, and sending a response to the user equipment, the response indicating the selected pre-distortion mode to be applied by the user equipment. Item 57. The method according to item 56, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the method further comprises: receiving the at least one pre-distortion mode by receiving at least one parameter set from the user equipment.

[0201] Item 58. The method according to item 56 or 57, further comprising: receiving, from the user equipment, a proposal for a different pre-distortion mode, which is different from the selected pre-distortion mode, determining, based on the network condition, whether to accept the proposal, and sending a further response to the user equipment indicating whether the proposal is accepted or not.

[0202] Item 59. The method according to any one of the items 56 to 58, wherein the at least one pre-distortion mode comprises at least one of: a mode for reducing an in-band distortion caused by a power amplifier of the user equipment, a mode for reducing an out-of-band distortion caused by the power amplifier of the user equipment, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier of the user equipment, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier of the user equipment.

[0203] Item 60. The method according to item 59, further comprising: selecting the pre-distortion mode for reducing the out-of-band distortion based on at least one of a determination whether a network element using a neighbor frequency band is present, or a frequency range of the transmission signal. Item 61. The method according to any one of the items 56 to 60, further comprising: receiving the uplink carrier aggregation signal from the user equipment, and applying a post-distortion mode to the uplink carrier aggregation signal.

[0204] Item 62. The method according to item 61, further comprising: sending an instruction for a training procedure to the user equipment based on the applied post-distortion mode, the instruction indicating a pre-distortion mode to be applied by the user equipment during the training procedure, and receiving an uplink reference signal transmission from the user equipment for training the post-distortion mode.

[0205] Item 63. A method, comprising sending, from a user equipment, at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of predistorting an uplink carrier aggregation signal, receiving a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode and an instruction for performing a training procedure, applying the selected pre-distortion mode, and performing an uplink reference signal transmission.

[0206] Item 64. The method according to item 63, further comprising: determining whether to apply the received pre-distortion mode based on a condition of the user equipment, and, applying the pre-distortion mode during the training procedure based on determining to apply the received pre-distortion mode.

[0207] Item 65. The method according to item 63 or 64, further comprising: performing the uplink reference signal transmission within a bandwidth and via a predetermined modulation.

[0208] Item 66. The method according to item 65, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier. Item 67. The method according to item 66, wherein the at least one pre-distortion mode is applied to reduce different distortion types caused by non-linearities of the power amplifier.

[0209] Item 68. The method according to item 66 or 67, wherein the power amplifier is a single multi-band power amplifier.

[0210] Item 69. The method according to any one of the items 66 to 68, wherein the pre-distortion modes comprise at least one of: a mode for reducing an in-band distortion caused by the power amplifier, a mode for reducing an out-of-band distortion caused by the power amplifier, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier.

[0211] Item 70. The method according to item 63, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the method further comprises: sending the at least one pre-distortion mode to the network device by reporting at least one parameter set to the network device.

[0212] Item 71. The method according to item 63, further comprising: receiving an uplink carrier aggregation combination configuration from the network device, and transmitting the uplink carrier aggregation signal, which is based on the received configuration.

[0213] Item 72. The method according to item 63, further comprising: learning a pre-distortion for reducing a distortion caused by the power amplifier by using a loss function suitable for a certain distortion type. Item 73. The method according to item 72, wherein the distortion types comprise at least one of: an in-band distortion, an out-of-band distortion, or a distortion of a certain order.

[0214] Item 74. The method according to item 72 or 73, further comprising: using the uplink carrier aggregation signal and at least two component carriers of the uplink carrier aggregation signal as inputs for training the predistortion.

[0215] Item 75. A method, comprising receiving, in a network device, at least one pre-distortion mode from a user equipment, wherein each pre-distortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal, selecting a pre-distortion mode from the at least one available pre-distortion mode received from the user equipment based on a network condition, sending an instruction for a training procedure indicating that the selected pre-distortion mode is to be applied by the user equipment during the training procedure, and receiving an uplink reference signal transmission from the user equipment for training a post-distortion mode.

[0216] Item 76. The method according to item 75, wherein the uplink reference signal transmission is carried out within a bandwidth and via a predetermined modulation.

[0217] Item 77. The method according to item 75 or 76, further comprising: applying the post-distortion mode to the received uplink carrier aggregation signal.

[0218] Item 78. The method according to item 75 or 76, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier of the user equipment, and the method further comprises: applying the post-distortion mode to reduce a distortion in the received uplink carrier aggregation signal caused by the power amplifier of the user equipment.

[0219] Item 79. A computer program product comprising code means for performing a method according to any one of the items 40 to 78 when run on a processing means or module.

[0220] Item 80. The computer program product according to item 79, wherein the computer program product is embodied on a computer-readable medium, and / or the computer program product is directly loadable into the internal memory of the computer and / or transmittable via a network by means of at least one of upload, download and push procedures.

[0221] Item 81. An apparatus, comprising means for sending at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal, means for receiving a response from the network device, indicating a predistortion mode selected from the at least one pre-distortion mode, means for determining whether to apply the selected pre-distortion mode based on a condition of the apparatus, and means for applying the selected pre-distortion mode to the uplink carrier aggregation signal based on determining to apply the selected pre-distortion mode.

[0222] Item 82. The apparatus according to item 81, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the apparatus further comprises: means for sending the at least one pre-distortion mode to the network device by reporting at least one parameter set to the network device.

[0223] Item 83. The apparatus according to item 40 or 41, further comprising: means for sending, in response to determine not to apply the received predistortion mode, a proposal for a different pre-distortion mode from the at least one pre-distortion mode to the network device based on the condition of the apparatus.

[0224] Item 84. The apparatus according to item 83, wherein the condition of the apparatus comprises at least one of: charging state of a power supply of the apparatus, or a temporary limitation of the apparatus.

[0225] Item 85. The apparatus according to item 84, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier.

[0226] Item 86. The apparatus according to item 85, wherein the at least one pre-distortion mode is applied to reduce different distortion types caused by non-linearities of the power amplifier.

[0227] Item 87. The apparatus according to item 85 or 86, wherein the power amplifier is a single multi-band power amplifier.

[0228] Item 88. The apparatus according to any one of the items 85 to 87, wherein the pre-distortion modes comprise at least one of: a mode for reducing an in-band distortion caused by the power amplifier, a mode for reducing an out-of-band distortion caused by the power amplifier, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier. Item 89. The apparatus according to any one of the items 81 to 88, further comprising, in case the response received from the network device contains an instruction for a training procedure from the network device: means for applying the selected pre-distortion mode, and means for performing an uplink reference signal transmission.

[0229] Item 90. The apparatus according to item 89, further comprising: means for performing the uplink reference signal transmission within a bandwidth and via a predetermined modulation.

[0230] Item 91. The apparatus according to any one of the items 81 to 90, further comprising: means for applying the selected pre-distortion mode to the uplink carrier aggregation signal by applying a compensation signal, which is based on a power amplifier response and characteristics of the transmission signal, to the uplink carrier aggregation signal.

[0231] Item 92. The apparatus according to item 81, further comprising: means for receiving an uplink carrier aggregation combination configuration from the network device, and means for transmitting the uplink carrier aggregation signal, which is based on the received configuration.

[0232] Item 93. The apparatus according to item 81, further comprising: means for learning a pre-distortion for reducing a distortion caused by the power amplifier by using a loss function suitable for a certain distortion type.

[0233] Item 94. The apparatus according to item 93, wherein the distortion types comprise at least one of: an in-band distortion, an out-of-band distortion, or a distortion of a certain order.

[0234] Item 95. The apparatus according to item 93 or 94, further comprising: means for using the uplink carrier aggregation signal and at least two component carriers of the uplink carrier aggregation signal as inputs for training the pre-distortion.

[0235] Item 96. The apparatus according to any one of the items 81 to 95, wherein the apparatus comprises the power amplifier and a digital-analog-converter for converting the uplink carrier aggregation signal into the analog transmission signal to be amplified by the power amplifier.

[0236] Item 97. An apparatus, comprising means for receiving at least one available pre-distortion mode from a user equipment, each pre-distortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal, means for selecting a pre-distortion mode from the at least one predistortion mode received from the user equipment based on a network condition, and means for sending a response to the user equipment, the response indicating the selected pre-distortion mode to be applied by the user equipment.

[0237] Item 98. The apparatus according to item 97, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the apparatus further comprises: means for receiving the at least one pre-distortion mode by receiving at least one parameter set from the user equipment.

[0238] Item 99. The apparatus according to item 97 or 98, further comprising: means for receiving, from the user equipment, a proposal for a different pre-distortion mode, which is different from the selected pre-distortion mode, means for determining, based on the network condition, whether to accept the proposal, and means for sending a further response to the user equipment indicating whether the proposal is accepted or not. Item 100. The apparatus according to any one of the items 97 to 99, wherein the at least one pre-distortion mode comprises at least one of: a mode for reducing an in-band distortion caused by a power amplifier of the user equipment, a mode for reducing an out-of-band distortion caused by the power amplifier of the user equipment, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier of the user equipment, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier of the user equipment.

[0239] Item 101. The apparatus according to item 100, further comprising: means for selecting the pre-distortion mode for reducing the out-of-band distortion based on at least one of a determination whether a network element using a neighbor frequency band is present, or a frequency range of the transmission signal.

[0240] Item 102. The apparatus according to any one of the items 97 to 101, further comprising: means for receiving the uplink carrier aggregation signal from the user equipment, and means for applying a post-distortion mode to the uplink carrier aggregation signal.

[0241] Item 103. The apparatus according to item 102, further comprising: means for sending an instruction for a training procedure to the user equipment based on the applied post-distortion mode, the instruction indicating a pre-distortion mode to be applied by the user equipment during the training procedure, and means for receiving an uplink reference signal transmission from the user equipment for training the post-distortion mode. Item 104. An apparatus, comprising means for sending at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal, means for receiving a response from the network device, indicating a predistortion mode selected from the at least one pre-distortion mode and an instruction for performing a training procedure, means for applying the selected pre-distortion mode, and means for performing an uplink reference signal transmission.

[0242] Item 105. The apparats according to item 104, further comprising: means for determining whether to apply the received pre-distortion mode based on a condition of the apparatus, and, means for applying the pre-distortion mode during the training procedure based on determining to apply the received pre-distortion mode.

[0243] Item 106. The apparatus according to item 104 or 105, further comprising: means for performing the uplink reference signal transmission within a bandwidth and via a predetermined modulation.

[0244] Item 107. The apparatus according to item 106, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier.

[0245] Item 108. The apparatus according to item 107, wherein the at least one pre-distortion mode is applied to reduce different distortion types caused by non-linearities of the power amplifier.

[0246] Item 109. The apparatus according to item 107 or 108, wherein the power amplifier is a single multi-band power amplifier.

[0247] Item 110. The apparatus according to any one of the items 107 to 109, wherein the pre-distortion modes comprise at least one of: a mode for reducing an in-band distortion caused by the power amplifier, a mode for reducing an out-of-band distortion caused by the power amplifier, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier.

[0248] Item 111. The apparatus according to item 104, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the apparatus further comprises: means for sending the at least one pre-distortion mode to the network device by reporting at least one parameter set to the network device.

[0249] Item 112. The apparatus according to item 104, further comprising: means for receiving an uplink carrier aggregation combination configuration from the network device, and means for transmitting the uplink carrier aggregation signal, which is based on the received configuration.

[0250] Item 113. The apparatus according to item 104, further comprising: means for learning a pre-distortion for reducing a distortion caused by the power amplifier by using a loss function suitable for a certain distortion type.

[0251] Item 114. The apparatus according to item 113, wherein the distortion types comprise at least one of: an in-band distortion, an out-of-band distortion, or a distortion of a certain order.

[0252] Item 115. The apparatus according to item 113 or 114, further comprising: means for using the uplink carrier aggregation signal and at least two component carriers of the uplink carrier aggregation signal as inputs for training the pre-distortion. Item 116. An apparatus, comprising means for receiving at least one pre-distortion mode from a user equipment, wherein each pre-distortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal, means for selecting a pre-distortion mode from the at least one available pre-distortion mode received from the user equipment based on a network condition, means for sending an instruction for a training procedure indicating that the selected pre-distortion mode is to be applied by the user equipment during the training procedure, and means for receiving an uplink reference signal transmission from the user equipment for training a post-distortion mode.

[0253] Item 117. The apparatus according to item 116, wherein the uplink reference signal transmission is carried out within a bandwidth and via a predetermined modulation.

[0254] Item 118. The apparatus according to item 116 or 117, further comprising: means for applying the post-distortion mode to the received uplink carrier aggregation signal.

[0255] Item 119. The apparatus according to item 116 or 118, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier of the user equipment, and the apparatus further comprises: means for applying the post-distortion mode to reduce a distortion in the received uplink carrier aggregation signal caused by the power amplifier of the user equipment.

Claims

CLAIMS1. An apparatus, comprising 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 at least one pre-distortion mode to a network device, wherein each pre-distortion mode indicates a mode of pre-distorting an uplink carrier aggregation signal, receive a response from the network device, indicating a pre-distortion mode selected from the at least one pre-distortion mode, determine whether to apply the selected pre-distortion mode based on a condition of the apparatus, and apply the selected pre-distortion mode to the uplink carrier aggregation signal based on determining to apply the selected pre-distortion mode.

2. The apparatus according to claim 1, wherein each of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: send the at least one pre-distortion mode to the network device by reporting at least one parameter set to the network device.

3. The apparatus according to claim 1 or 2, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: in response to determine not to apply the received pre-distortion mode, send a proposal for a different pre-distortion mode from the at least one predistortion mode to the network device based on the condition of the apparatus.

4. The apparatus according to claim 1 or 3, wherein the condition of the apparatus comprises at least one of: charging state of a power supply of the apparatus, ora temporary limitation of the apparatus.

5. The apparatus according to claim 1, wherein the pre-distorted uplink carrier aggregation signal is to be amplified by a power amplifier.

6. The apparatus according to claim 5, wherein the pre-distortion modes comprise at least one of: a mode for reducing an in-band distortion caused by the power amplifier, a mode for reducing an out-of-band distortion caused by the power amplifier, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier.

7. The apparatus according to any one of the claims 1 to 6, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: in case the response received from the network device contains an instruction for a training procedure from the network device, apply the selected pre-distortion mode, and perform an uplink reference signal transmission.

8. The apparatus according to claim 7, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: perform the uplink reference signal transmission within a bandwidth and via a predetermined modulation.

9. The apparatus according to claim 1, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive an uplink carrier aggregation combination configuration from the network device, andtransmit the uplink carrier aggregation signal, which is based on the received configuration.

10. The apparatus according to claim 5, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: learn a pre-distortion for reducing a distortion caused by the power amplifier by using a loss function suitable for a certain distortion type.

11. The apparatus according to claim 10, wherein the distortion types comprise at least one of: an in-band distortion, an out-of-band distortion, or a distortion of a certain order.

12. The apparatus according to claim 10 or 11, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: use the uplink carrier aggregation signal and at least two component carriers of the uplink carrier aggregation signal as inputs for training the pre-distortion.

13. An apparatus, comprising 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 at least one available pre-distortion mode from a user equipment, each pre-distortion mode indicates a mode of pre-distorting a uplink carrier aggregation signal, select a pre-distortion mode from the at least one pre-distortion mode received from the user equipment based on a network condition, and send a response to the user equipment, the response indicating the selected pre-distortion mode to be applied by the user equipment.

14. The apparatus according to claim 13, whereineach of the at least one pre-distortion mode is indicated by one parameter set indicating an importance of the pre-distortion mode, and the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive the at least one pre-distortion mode by receiving at least one parameter set from the user equipment.

15. The apparatus according to claim 13 or 14, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive, from the user equipment, a proposal for a different pre-distortion mode, which is different from the selected pre-distortion mode, determine, based on the network condition, whether to accept the proposal, and send a further response to the user equipment indicating whether the proposal is accepted or not.

16. The apparatus according to any one of the claims 13 to 15, wherein the at least one pre-distortion mode comprises at least one of: a mode for reducing an in-band distortion caused by a power amplifier of the user equipment, a mode for reducing an out-of-band distortion caused by the power amplifier of the user equipment, a mode for reducing an in-band distortion and an out-of-band distortion caused by the power amplifier of the user equipment, or a mode for reducing an out-of-band distortion of a certain order caused by the power amplifier of the user equipment.

17. The apparatus according to any one of the claims 13 to 16, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: receive the uplink carrier aggregation signal from the user equipment, and apply a post-distortion mode to the uplink carrier aggregation signal.

18. The apparatus according to claim 17, wherein the instructions stored by the at least one memory further cause the apparatus, when executed by the at least one processor, at least to: send an instruction for a training procedure to the user equipment based on the applied post-distortion mode, the instruction indicating a pre-d istortion mode to be applied by the user equipment during the training procedure, and receive an uplink reference signal transmission from the user equipment for training the post-distortion mode.

Images