Constellation sharing and coordination

Abstract

There are provided measures for constellation sharing and coordination. Such measures exemplarily comprise deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

Description

[0001] DESCRIPTION

[0002] Title

[0003] Constellation sharing and coordination

[0004] Field

[0005] Various example embodiments relate to constellation sharing and coordination. More specifically, various example embodiments exemplarily relate to measures (including methods, apparatuses and computer program products) for realizing constellation sharing and coordination.

[0006] Background

[0007] The present specification generally relates to signal modulation and in particular constellations or constellation diagrams representative of modulated signals and in particular symbols of modulated signals.

[0008] Transmitters using deep learning that learn a new terminal-specific constellation shaped to maximize link performance are foreseen.

[0009] Since 3rdGeneration Partnership Project (3GPP) 6thGeneration (6G) is expected to natively support artificial intelligence (Al), deep waveform learning, deep constellation learning, etc. are expected as new physical layer features that make the 6G design depart from orthogonal frequency division multiplexing (OFDM) based design of 3GPP 5thGeneration (5G).

[0010] Incidentally, such approaches are also expected for 3GPP 5G Rel. 19 in preparation for a native Al support in 6G.

[0011] FIG. 7 is a schematic diagram illustrating an arrangement of an exemplary constellation, and in particular illustrates an example of a learned constellation (e.g. leaned by means of such expected deep constellation learning) with a modulation order of 64 from an end-to-end learning framework.

[0012] Deep multiple input multiple output (MIMO) transceivers are candidates for 6G physical layer design, showing superior performance to their legacy peers.

[0013] Constellation learning (e.g. at a transmission / transmitter (TX) side or at a transceiving / transceiver (TRX) side) is foreseen to be an advance in contrast to legacy transceivers with regular quadrature amplitude modulation (QAM) constellation.

[0014] For example, constellation points of a modulation mapper in an OFDM modulator may be considered as part of training parameters to enable pilotless communication, which results in higher spectral efficiency as there was no need to allocate resources for pilot transmission.

[0015] Presently, regular quadrature phase shift keying (QPSK) and QAM constellations are specified. Based on such specification, vendors can coordinate on used constellation points and corresponding bit mapping without ambiguity.

[0016] Below, a table reflecting an example of specified / standardized 16-QAM constellation points and assigned bits for each constellation point is shown.

[0017] However, to enable deep TRX solutions with irregular learned constellations, the learned constellations have to be shared, and coordination with respect to the shared constellations is necessary.

[0018] The problem arises that constellation sharing and coordination in particular in the context of (artificial intelligence / machine learning (AI / ML)) learned constellations is not arranged.

[0019] Hence, there is a need to provide for constellation sharing and coordination.

[0020] Summary

[0021] Various example embodiments aim at addressing at least part of the above issues and / or problems and drawbacks.

[0022] Various aspects of example embodiments are set out in the appended claims.

[0023] According to an exemplary aspect, there is provided an apparatus, the apparatus comprising means for deciding on at least one signal modulation constellation comprising constellation points, means for generating information for derivation of said at least one signal modulation constellation, and means for transmitting the generated information for derivation of said at least one signal modulation constellation.

[0024] According to an exemplary aspect, there is provided an apparatus, the apparatus comprising means for receiving information for derivation of at least one signal modulation constellation, means for deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and means for conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0025] According to an exemplary aspect, there is provided an apparatus, the 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 perform deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

[0026] According to an exemplary aspect, there is provided an apparatus, the 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 perform receiving information for derivation of at least one signal modulation constellation, deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0027] According to an exemplary aspect, there is provided a method, the method comprising deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

[0028] According to an exemplary aspect, there is provided a method, the method comprising receiving information for derivation of at least one signal modulation constellation, deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0029] According to an exemplary aspect, there is provided a computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out steps: deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

[0030] According to an exemplary aspect, there is provided a computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out steps: receiving information for derivation of at least one signal modulation constellation, deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0031] According to an exemplary aspect, there is provided a non-transitory computer readable medium comprising program instructions stored thereon for performing at least the following: deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

[0032] According to an exemplary aspect, there is provided a non-transitory computer readable medium comprising program instructions stored thereon for performing at least the following: receiving information for derivation of at least one signal modulation constellation, deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0033] Any one of the above aspects enables an efficient exchange of information in relation to (learned) constellations and in relation to constellations to be commonly used to thereby solve at least part of the problems and drawbacks identified in relation to the prior art.

[0034] By way of example embodiments, there is provided constellation sharing and coordination. More specifically, by way of example embodiments, there are provided measures and mechanisms for realizing constellation sharing and coordination.

[0035] Thus, improvement is achieved by methods, apparatuses and computer program products enabling / realizing constellation sharing and coordination.

[0036] Brief description of the drawings

[0037] In the following, the present disclosure will be described in greater detail by way of non-limiting examples with reference to the accompanying drawings, in which

[0038] FIG. 1 is a block diagram illustrating an apparatus according to example embodiments, FIG. 2 is a block diagram illustrating an apparatus according to example embodiments,

[0039] FIG. 3 is a block diagram illustrating an apparatus according to example embodiments,

[0040] FIG. 4 is a block diagram illustrating an apparatus according to example embodiments,

[0041] FIG. 5 is a schematic diagram of a procedure according to example embodiments,

[0042] FIG. 6 is a schematic diagram of a procedure according to example embodiments,

[0043] FIG. 7 is a schematic diagram illustrating an arrangement of an exemplary constellation,

[0044] FIG. 8 shows a schematic diagram of signaling sequences according to example embodiments,

[0045] FIG. 9 shows a schematic diagram of signaling sequences according to example embodiments,

[0046] FIG. 10 shows a schematic diagram of signaling sequences according to example embodiments,

[0047] FIG. 11 shows a schematic diagram of signaling sequences according to example embodiments,

[0048] FIG. 12 is a schematic diagram illustrating an exemplary quantization grid according to example embodiments, FIG. 13 is a schematic diagram illustrating an exemplary quantization grid according to example embodiments,

[0049] FIG. 14 is a schematic diagram illustrating an exemplary quantization grid according to example embodiments,

[0050] FIG. 15 is a schematic diagram illustrating steps of exemplary quantization- aware constellation learning according to example embodiments,

[0051] FIG. 16 (FIG. 16a and FIG. 16b) is a schematic diagram illustrating arrangements of exemplary constellations according to example embodiments, and

[0052] FIG. 17 is a block diagram alternatively illustrating apparatuses according to example embodiments.

[0053] Detailed description

[0054] The present disclosure is described herein with reference to particular nonlimiting examples and to what are presently considered to be conceivable embodiments. A person skilled in the art will appreciate that the disclosure is by no means limited to these examples, and may be more broadly applied.

[0055] It is to be noted that the following description of the present disclosure and its embodiments mainly refers to specifications being used as non-limiting examples for certain exemplary network configurations and deployments. Namely, the present disclosure and its embodiments are mainly described in relation to 3GPP specifications being used as non-limiting examples for certain exemplary network configurations and deployments. As such, the description of example embodiments given herein specifically refers to terminology which is directly related thereto. Such terminology is only used in the context of the presented non-limiting examples, and does naturally not limit the disclosure in any way. Rather, any other communication or communication related system deployment, etc. may also be utilized as long as compliant with the features described herein.

[0056] Hereinafter, various embodiments and implementations of the present disclosure and its aspects or embodiments are described using several variants and / or alternatives. It is generally noted that, according to certain needs and constraints, all of the described variants and / or alternatives may be provided alone or in any conceivable combination (also including combinations of individual features of the various variants and / or alternatives).

[0057] 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.

[0058] According to example embodiments, in general terms, there are provided measures and mechanisms for (enabling / realizing) constellation sharing and coordination.

[0059] As mentioned above, to enable deep TRX solutions with irregular learned constellations, the learned constellations have to be shared, and coordination with respect to the shared constellations is necessary.

[0060] In particular, ways to share constellation points in a constellation are needed.

[0061] Further, ways to efficiently update constellation points in a constellation are needed. As a prerequisite, the overhead of sharing such constellation may be determined, and for efficiency reasons, ways of potentially reducing overhead of constellation sharing particularly in higher modulation orders are needed.

[0062] Hence, in brief, according to example embodiments, information about the used constellation is shared between the network (NW) (e.g. gNodeB (gNB)) and a terminal (e.g. user equipment (UE)) so that both entities know which constellation is being applied.

[0063] According to example embodiments, the constellation coordination can be done by sharing the complete set of constellation points, although this will incur a large overhead. This approach, however, allows for very flexible constellation shapes. To reduce the overhead of constellation sharing, UE / gNB can share a quantized version of the constellation, where real / imaginary part of each symbol is quantized with k-bits.

[0064] According to further example embodiments, a look-up table (LUT) may be used, where there is a large number of predefined constellations, which is shared knowledge between the NW and the terminal. As a result, it suffices to indicate an index of the used constellation in the LUT.

[0065] According to further example embodiments, a parameterized constellation shape (parameterized representation of the constellation) is utilized, in which case only the parameters need to be communicated.

[0066] According to further example embodiments, a neural network is defined which can be considered as a transformation function between a conventional QAM constellation and the new constellation shape.

[0067] In addition, according to example embodiments, the constellation is updated in case of online learning or adapting to a new context. Heretofore, a vector of deltas compared to the previous constellation may be determined as the update, or simply a set of new parameters for a parameterized constellation.

[0068] Example embodiments are specified below in more detail.

[0069] FIG. 1 is a block diagram illustrating an apparatus according to example embodiments. The apparatus 10 may be an entity actively sharing (providing) constellations and may be an access node such as a base station or may be a terminal such as a user equipment, and comprises means for deciding 11, means for generating 12, and means for transmitting 13. The means for deciding 11 decides on at least one signal modulation constellation comprising constellation points The means for generating 12 generates information for derivation of said at least one signal modulation constellation. The means for transmitting 13 transmits the generated information for derivation of said at least one signal modulation constellation. FIG. 5 is a schematic diagram of a procedure according to example embodiments. The apparatus according to FIG. 1 may perform the method of FIG. 5 but is not limited to this method. The method of FIG. 5 may be performed by the apparatus of FIG. 1 but is not limited to being performed by this apparatus.

[0070] As shown in FIG. 5, a procedure according to example embodiments comprises an operation of deciding (S51) on at least one signal modulation constellation comprising constellation points, an operation of generating (S52) information for derivation of said at least one signal modulation constellation, and an operation of transmitting (S53) the generated information for derivation of said at least one signal modulation constellation.

[0071] FIG. 2 is a block diagram illustrating an apparatus according to example embodiments. In particular, FIG. 2 illustrates a variation of the apparatus shown in FIG. 1. The apparatus according to FIG. 2 may thus further comprise a means for selecting 21, a means for receiving 22, a means for demodulating 23, a means for modulating 24, a means for quantizing 25, a means for executing 26, a means for detecting 27, and / or a means for determining 28.

[0072] In an embodiment at least some of the functionalities of the apparatus shown in FIG. 1 (or 2) may be shared between two physically separate devices forming one operational entity. Therefore, the apparatus may be seen to depict the operational entity comprising one or more physically separate devices for executing at least some of the described processes.

[0073] According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of selecting one of said at least one signal modulation constellation out of said at least one signal modulation constellation based on at least one of the following: a modulation order configured for wireless communication between two communication participants including said apparatus, or an experienced channel condition between said two communication participants experienced at one of said two communication participants, or a terminal mobility of one of said two communication participants being a terminal, or a frequency band configured for said wireless communication between said two communication participants, or an experienced signal to noise ratio experienced at one of said two communication participants, and an operation of transmitting information on said one of said at least one signal modulation constellation as a selected signal modulation constellation.

[0074] According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of receiving information on one of said at least one signal modulation constellation as a selected signal modulation constellation. According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of receiving a modulated signal and an operation of demodulating said modulated signal based on one of said at least one signal modulation constellation to a source signal.

[0075] According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of modulating a source signal based on said one of said at least one signal modulation constellation to a modulated signal and an operation of transmitting said modulated signal.

[0076] According to further example embodiments, said constellation points are complex values represented by value pairs, wherein said value pair of complex value comprises one of the following: a real value and an imaginary value of said complex value, or a magnitude value and a phase value of said complex value.

[0077] According to further example embodiments, said information for derivation of said at least one signal modulation constellation comprises information indicative of said value pairs of said constellation points.

[0078] According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of quantizing, based on quantization settings, said value pairs of said constellation points, wherein said information indicative of said value pairs of said constellation points corresponds to quantized value pairs of said constellation points resulting from said quantizing said value pairs of said constellation points. According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of transmitting said quantization settings.

[0079] According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of receiving said quantization settings.

[0080] According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of executing a plurality of learning iterations of interim constellation points, and an operation of quantizing value pairs of said interim constellation points of at least a part of said plurality of learning iterations.

[0081] According to a variation of the procedure shown in FIG. 5, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of detecting a symmetry in said constellation points, wherein said information indicative of said value pairs of said constellation points comprises information indicative of said value pairs of symmetry representative constellation points being a subset of said constellation points, and wherein said information for derivation of said at least one signal modulation constellation comprises information indicative of said symmetry. According to example embodiments, the axis (axes) of symmetry can be axis- x, axis-y, and / or any considered axis in Cartesian coordinate system or in polar / angular coordinate system.

[0082] According to a variation of the procedure shown in FIG. 5, exemplary details of the generating operation (S52) are given, which are inherently independent from each other as such. Such exemplary generating operation (S52) according to example embodiments may comprise an operation of generating differential information indicative of differences between said constellation points and corresponding constellation points of a corresponding previous signal modulation constellation to be replaced by said at least one signal modulation constellation as said information for derivation of said at least one signal modulation constellation.

[0083] According to further example embodiments, said at least one signal modulation constellation includes a plurality of signal modulation constellations corresponding to a plurality of modulation orders.

[0084] According to a variation of the procedure shown in FIG. 5, exemplary details of the deciding operation (S51) are given, which are inherently independent from each other as such. Such exemplary deciding operation (S51) according to example embodiments may comprise an operation of determining said at least one signal modulation constellation as a result of machine learning processing for learning signal modulation constellations or as a result of a solution processing of an optimization problem.

[0085] With respect to the solution processing of an optimization problem, according to example embodiments, an optimization algorithm such as genetic algorithm may, based on e.g. a list of predetermined / potential constellations, explore different constellations e.g. in different channel conditions and evaluate the goodness of each constellation using e.g. a pre-defined key performance indicator (KPI), whereby a best constellation for each scenario / channel conditions can be determined. FIG. 3 is a block diagram illustrating an apparatus according to example embodiments. The apparatus 30 may be an entity passively sharing (receiving) constellations and may be an access node such as a base station or may be a terminal such as a user equipment, and comprises means for receiving 31, means for deriving 32, and means for conducting 33. The means for receiving 31 receives information for derivation of at least one signal modulation constellation. The means for deriving 32 derives said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation. The means for conducting 33 conducts modulated signal communication based on one of said at least one signal modulation constellation to a source signal. FIG. 6 is a schematic diagram of a procedure according to example embodiments. The apparatus according to FIG. 3 may perform the method of FIG. 6 but is not limited to this method. The method of FIG. 6 may be performed by the apparatus of FIG. 3 but is not limited to being performed by this apparatus.

[0086] As shown in FIG. 6, a procedure according to example embodiments comprises an operation of receiving (S61) information for derivation of at least one signal modulation constellation, an operation of deriving (S62) said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and an operation of conducting (S63) modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0087] FIG. 4 is a block diagram illustrating an apparatus according to example embodiments. In particular, FIG. 4 illustrates a variation of the apparatus shown in FIG. 3. The apparatus according to FIG. 4 may thus further comprise a means for selecting 41, a means for transmitting 42, a means for demodulating 43, a means for modulating 44, and / or a means for reconstructing 45. In an embodiment at least some of the functionalities of the apparatus shown in FIG. 3 (or 4) may be shared between two physically separate devices forming one operational entity. Therefore, the apparatus may be seen to depict the operational entity comprising one or more physically separate devices for executing at least some of the described processes.

[0088] According to a variation of the procedure shown in FIG. 6, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of selecting said one of said at least one signal modulation constellation out of said at least one signal modulation constellation based on at least one of the following: a modulation order configured for wireless communication between two communication participants including said apparatus, or an experienced channel condition between said two communication participants experienced at one of said two communication participants, or a terminal mobility of one of said two communication participants being a terminal, or a frequency band configured for said wireless communication between said two communication participants, or an experienced signal to noise ratio experienced at one of said two communication participants, and an operation of transmitting information on said one of said at least one signal modulation constellation as a selected signal modulation constellation.

[0089] According to a variation of the procedure shown in FIG. 6, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of receiving information on said one of said at least one signal modulation constellation as a selected signal modulation constellation.

[0090] According to a variation of the procedure shown in FIG. 6, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of receiving a modulated signal and an operation of demodulating said modulated signal based on said one of said at least one signal modulation constellation to said source signal.

[0091] According to a variation of the procedure shown in FIG. 6, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of modulating said source signal based on said one of said at least one signal modulation constellation to a modulated signal and an operation of transmitting said modulated signal.

[0092] According to further example embodiments, said constellation points are complex values represented by value pairs, wherein said value pair of complex value comprises one of the following: a real value and an imaginary value of said complex value, or a magnitude value and a phase value of said complex value.

[0093] According to further example embodiments, said information for derivation of said at least one signal modulation constellation comprises information indicative of said value pairs of said constellation points.

[0094] According to further example embodiments, said information indicative of said value pairs of said constellation points corresponds to quantized value pairs of said constellation points resulting from quantizing, based on quantization settings, said value pairs of said constellation points.

[0095] According to a variation of the procedure shown in FIG. 6, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of transmitting said quantization settings.

[0096] According to a variation of the procedure shown in FIG. 6, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of receiving said quantization settings.

[0097] According to a variation of the procedure shown in FIG. 6, exemplary details of the deriving operation (S62) are given, which are inherently independent from each other as such. According to such variation, said information for derivation of said at least one signal modulation constellation comprises information indicative of a symmetry in said constellation points, and information indicative of said value pairs of symmetry representative constellation points being a subset of said constellation points, and such exemplary deriving operation (S62) according to example embodiments may comprise an operation of reconstructing constellation points other than said symmetry representative constellation points based on said symmetry representative constellation points and said information indicative of said symmetry.

[0098] According to a variation of the procedure shown in FIG. 6, exemplary details of the deriving operation (S62) are given, which are inherently independent from each other as such. According to such variation, said at least one signal modulation constellation is a replacement of a previous at least one signal modulation constellation, and said information for derivation of said at least one signal modulation constellation includes differential information indicative of differences between said constellation points and corresponding constellation points of a corresponding previous signal modulation constellation, and such exemplary deriving operation (S62) according to example embodiments may comprise an operation of reconstructing said constellation points based on said corresponding constellation points of said corresponding previous signal modulation constellation and said differential information.

[0099] According to further example embodiments, said at least one signal modulation constellation includes a plurality of signal modulation constellations corresponding to a plurality of modulation orders.

[0100] Example embodiments outlined and specified above are explained below in more specific terms.

[0101] According to a specific aspect covered by example embodiments, constellations are shared over the air (OTA).

[0102] In detail, according to example embodiments, all constellation points are shared over the air (OTA). In this case, the real and imaginary parts of each constellation point are communicated. Alternatively, amplitude and phase of each constellation point are communicated.

[0103] In such case, a total overhead of sharing a constellation depends mainly on the following parameters:

[0104] M : Modulation order (or number of points in the constellation), and

[0105] K: Number of allocated bits for sharing the real part or imaginary part of a constellation point (or amplitude or phase of a constellation point), where the total overhead of constellation sharing is 2*K*M. If the floating-point version of the real and imaginary values of the constellation points are shared, K=32, and consequently, 64*M bits are required for constellation sharing.

[0106] FIG. 8 shows a schematic diagram of signaling sequences according to example embodiments, and in particular illustrates example signaling and processing for enabling constellation sharing OTA according to example embodiments. While, in FIG. 8, a case is illustrated in which a gNB shares the constellation with a UE (as an example of a terminal), a similar signaling flowchart would result for the case where the UE shares the constellation with the gNB, which is similarly possible according to example embodiments.

[0107] The bit to symbol mapping may be either standardized or agreed or shared between the UE and gNB.

[0108] While UE is taken as an example for a terminal throughout the present specification, UE may in particular mean a UE of certain type / vendor.

[0109] According to example embodiments, several approaches for reducing the overhead of constellation sharing are proposed.

[0110] According to example embodiments, constellation points are quantized as an approach for reducing the overhead of constellation sharing.

[0111] According thereto, the UE and gNB coordinate on a quantization scheme to quantize the constellation points and reduce the overhead of sharing such information.

[0112] Also, the receiver of such information uses the corresponding de-quantization scheme to reconstruct the constellation based on the received bits.

[0113] The quantization scheme includes at least the type of quantization (uniform or non-uniform quantization), range of quantization (minimum and maximum of quantized values), and the number of allocated bits for reporting a real part or imaginary part of a constellation point (K-bits).

[0114] As an example, a uniform quantization in range of [-1, 1] with K-bits is considered, where the quantized grid with 2Kmembers can be expressed as Each constellation point (based on its real and imaginary values) can be quantized to one of the (2K)2=22Kpossibilities.

[0115] For example, for a constellation with modulation order of 16 (M = 16), UE and gNB may agree to use uniform quantization with K=6 bits, where each constellation point can be selected from the 22K=22*6=4096 possibilities.

[0116] Thus, the example quantization scheme requires 2*K*M = 192 bits, thus significantly reducing the overhead compared to the original constellation sharing with floating-point precision requiring 64*M=1024 bits.

[0117] It is noted that according to example embodiments a signaling can indicate whether the constructed constellation needs to be normalized to have unit power and / or zero mean.

[0118] FIG. 9 shows a schematic diagram of signaling sequences according to example embodiments, and in particular illustrates signaling and processing for enabling quantized constellation sharing OTA according to example embodiments.

[0119] While, in FIG. 9, a case is illustrated in which a UE (as an example of a terminal) shares the constellation with a gNB, a similar signaling flowchart would result for the case where the gNB shares the constellation with the UE, which is similarly possible according to example embodiments.

[0120] According to example embodiments, the quantization can be done in polar coordinate system, where the amplitude and phase of a constellation point is quantized (instead of real and imaginary parts of a constellation point as discussed above).

[0121] According to example embodiments, symmetry in the constellation is utilized as an approach for reducing the overhead of constellation sharing. Namely, In case there is a symmetry in the considered constellation, according to example embodiments, the symmetry is exploited to reduce the constellation sharing overhead.

[0122] For example, if the constellation is symmetric with respect to the X axis, the overhead can be reduced by 50%. In addition, symmetry about both the X and Y axes helps to reduce the overhead by 75%. gNB and UE can coordinate on how to obtain the other constellation points, based on the received constellation points of a segment / part and the indicated symmetry properties.

[0123] FIG. 10 shows a schematic diagram of signaling sequences according to example embodiments, and in particular illustrates signaling and processing for enabling constellation sharing OTA with indicated symmetry.

[0124] While, in FIG. 10, a case is illustrated in which a UE (as an example of a terminal) shares the constellation with a gNB, a similar signaling flowchart would result for the case where the gNB shares the constellation with the UE, which is similarly possible according to example embodiments.

[0125] As an example, the constellation shown in FIG. 7 has symmetry about the X axis, and according to example embodiments, it is possible to only share the constellation points above the X axis and to thereby reduce the constellation sharing overhead by 50 %.

[0126] According to another specific aspect covered by example embodiments, constellations are shared utilizing a look-up table (LUT).

[0127] In detail, according to example embodiments, to prevent high overhead of constellation sharing, constellations in a constellation list can be coordinated offline between UE and gNB in a look-up table (LUT). Because of availability of such shared knowledge between NW and UE, gNB or UE can configure to use a constellation by indicating only the index of the used constellation. In this case, the overhead of coordinating constellation is extremely low, as it requires only few bits for indicating an index from the LUT.

[0128] FIG. 11 shows a schematic diagram of signaling sequences according to example embodiments, and in particular illustrates signaling and processing for enabling LUT-based constellation coordination (LUT-based constellation indication from gNB to UE) according to example embodiments.

[0129] While, in FIG. 11, a case is illustrated in which a gNB shares / indicates the constellation with / to a UE (as an example of a terminal), a similar signaling flowchart would result for the case where the UE shares / indicates the constellation with / to the gNB, which is similarly possible according to example embodiments.

[0130] According to another specific aspect covered by example embodiments, a transformation function between a conventional QAM constellation and the new constellation shape is shared.

[0131] In detail, according to example embodiments, the constellation is defined as a learned transformation between an initial constellation and the target learned constellation.

[0132] According to example embodiments, a conventional QAM constellation is used as the input, and a neural network is trained which transforms the original constellation to the desired new shape. Separate transformations can be used for each modulation order, or, alternatively, a single transformation can be used for all modulation orders.

[0133] According to example embodiments, the transformations can be collected to a LUT, similar to the above specific aspect related to sharing of constellations utilizing a look-up table (LUT) covered by example embodiments (as such, the present specific aspect can be combined with the above specific aspect related to sharing of constellations utilizing a look-up table (LUT) covered by example embodiments). Further, the transformations can then be communicated as shown in FIG. 11.

[0134] Alternatively, according to example embodiments, the transformations are communicated directly as shown in FIG. 8. This is an especially favorable option if the transformation contains less parameters than the actual constellation (a very likely scenario with higher modulation orders).

[0135] To communicate neural network models, a predefined format for sharing the weights and the neural network architecture may be provided according to example embodiments. One approach would be to limit the possible architectures to, e.g., fully connected neural networks (FCNN) and share the weights layer by layer.

[0136] One option for signaling the weights of the transformation neural network is, according to example embodiments, to predefine one or more options for the neural network (NN) architecture, and share the weights for the preferred architecture.

[0137] For example, it can be predefined that the transformation NN is a fully- connected neural network with L hidden layers having M neurons in each, and the input and output are the real and imaginary parts of the constellation points. In this case, according to example embodiments, signaling the NN weights can be done by arranging the weights values in a binary sequence, where the weights of each layer are included sequentially with some predefined precision (e.g., 8-bit integer values). In the considered example case, this would translate to a binary sequence of 8*(3*M + (L- 1)*M*(M + 1)+2*(M + 1)).

[0138] Based on the predefined ordering of the layers and weights, according to example embodiments, the receiver end can assign these weights to the correct layers and neurons. In the case of multiple different transformation NNs, each option can be assigned a separate index, which is signaled together with the weight vector. The index will define the length of the weight binary sequence and the correct interpretation of the weights.

[0139] According to another specific aspect covered by example embodiments, constellation points are updated, updated constellation points are shared.

[0140] In detail, according to example embodiments, in case UE or gNB decide to update a constellation, the update can be done in absolute scheme or in a differential one.

[0141] The updating overhead of the absolute scheme is the same as sharing a constellation in the previous SEP embodiments.

[0142] However, according to example embodiments, UE and gNB can coordinate to use a differential update, where the updated constellation points need to be in a neighborhood of the original constellation point. Using differential update scheme helps to reduce the overhead of constellation update and makes periodic / aperiodic constellation updates more feasible.

[0143] According to example embodiments, a differential update may be expressed using a single bit signaling, like in the example below.

[0144] According to this example, for a single-level update scheme (±<5r, +6i'), the updated k-th constellation point can be expressed as:

[0145] In sum, to enable the differential updating, according to example embodiments, the following parameters are coordinated / signaled between UE and gNB: - Setting / configuring the value of deltas (step size) (±<5r, +6i'), probably from a look-up table defined for step size.

[0146] - Number of bits allocated for updating a constellation point (or equivalently, number of levels). Single-level (1-bit) or multi-level (more than 1 bit) schemes can be configured.

[0147] - Updating the real and imaginary parts separately or jointly. Jointly update scheme gives higher granularity in angular domain.

[0148] - Configuring whether the updates are in Cartesian or polar coordinates. For example, in the joint update scheme, the update value for updating a constellation point can be selected with 3-bits form :

[0149] - Triggering signaling, to configure periodic / aperiodic constellation updates. The constellation update can be requested by the entity that shared the original constellation.

[0150] If the constellation is defined via a transforming neural network, the updates to the constellation points can also be shared as updates to the weights of the neural network. According to example embodiments, the gNB (or UE) can decide to use this option if it results in smaller overhead than signaling explicit updates to the constellation points. According to example embodiments, a binary indicator of whether the updates are considered for the neural network or for the constellation points is provided.

[0151] According to another specific aspect covered by example embodiments, quantization-aware (quantization-friendly) constellations are determined and shared.

[0152] In detail, according to example embodiments, quantization friendly constellations are designed / forced during training.

[0153] FIG. 12 is a schematic diagram illustrating an exemplary quantization grid according to example embodiments, and in particular illustrates an example of a quantization grid (possibilities) for a constellation point, using a uniform quantization with K=4 bits for (i.e., used for quantizing and reporting) the real part and K=4 bits for (i.e., used for quantizing and reporting) the imaginary part (8-bit for complex value quantization).

[0154] FIG. 13 is a schematic diagram illustrating an exemplary quantization grid according to example embodiments, and in particular illustrates an example of a quantization grid (possibilities) for a constellation point, using a uniform quantization with K=6 bits for (i.e., used for quantizing and reporting) the real part and K=6 bits for (i.e., used for quantizing and reporting) the imaginary part (12-bit for complex value quantization).

[0155] FIG. 14 is a schematic diagram illustrating an exemplary quantization grid according to example embodiments, and in particular illustrates an example of a quantization grid (possibilities) for a constellation point in polar coordinate system, where the amplitude and phase components are respectively quantized with K=6 bits.

[0156] Although the quantization error with K=4 (FIG. 12) is significantly larger than the quantization error with K=6 (FIG. 13, FIG. 14), quantization with K=4 (FIG. 12) offers 33% less overhead than quantization with K=6 (FIG. 13, FIG. 14).

[0157] Therefore, there is a strong motivation to enable low-overhead quantized constellation sharing. There are at least two options for obtaining quantized constellation points.

[0158] Namely, on the one hand, post-training quantization of the learned constellation may be performed.

[0159] Further, on the other hand, quantization-aware constellation learning may be performed. Although post-training quantization of the constellation points is the easiest solution, there is no guarantee on the performance of the system after quantization.

[0160] Quantization-aware constellation learning according to example embodiments results in quantization-friendly constellation points, as such quantization impacts are captured during training.

[0161] FIG. 15 is a schematic diagram illustrating steps of exemplary quantization- aware constellation learning according to example embodiments, and in particular illustrates an example of quantization-aware constellation learning for constellation C with modulation order of 4.

[0162] FIG. 15 particularly illustrates exemplarily how quantization-aware constellation learning can be done for learning and updating a constellation C with modulation order of 4 (4 constellation points, or equivalently, 4 rows in the constellation table) according to example embodiments.

[0163] In this example, a uniform quantization with K=4 bits in range of [-1, 1] is considered, which results in 16 quantization levels: [-1.000, -0.867, -0.733, -0.600, -0.467, -0.333, -0.200, -0.067, 0.067, 0.200, 0.333, 0.467, 0.600, 0.733, 0.867, 1.000] for quantizing the real or imaginary parts of a constellation point. It is noted that in the quantization-aware constellation learning, the quantization needs to be used only for the forward pass, as the gradients can be shared with floating point precision during training.

[0164] According to example embodiments, the quantization may be applied only every Z iteration (Z>1) to allow for better training particularly in first training iterations.

[0165] Because of the possibility of enabling normalization after de-quantization at the receiver of constellation information, according to example embodiments, the constellation informant can scale and / or shift the constellation points prior to feeding the constellation points to the quantizer. The scaling and shifting technique may help to reduce the quantization error.

[0166] Embodiments and specific aspects outlined, specified and explained above may be combined with each other even if not explicitly mentioned without departing from the present disclosure.

[0167] In addition, embodiments and specific aspects outlined, specified and explained above may be combined with at least one of the following:

[0168] - Training setup (signal to interference and noise ratio (SINR) regime, transport block (TB) size, bandwidth (BW), channel models, etc.) for the constellation learning may be shared with the gNB so that the gNB derives link adaptation (LA) conditions, meaning that the gNB may or should adapt its LA procedure in a way that the proper transmission parameters are achieved under the target SINR. conditions.

[0169] - Progressive / on-demand sharing of learned constellation, e.g., gNB informs UE about the SINR conditions, and the UE signals back the learned constellations for those SINR conditions only. In this scheme, the gNB triggers the UE to refresh the constellation information by indicating the expected SINR conditions.

[0170] - The constellation is learned in connection to a code rate, i.e., for the same constellation order, the constellation is trained under different code rates (note that this is valid if the loss function is computed using at least the output of the decoder) and the similarity between the resulting constellations is evaluated. If sufficiently different from each other, then each learned constellation is signaled together with the code rate(s) for which it has been obtained. Note that the similarity of two constellations may be measured as the mean of the distances between every pair of points each representing the same bit vector, where first point belongs to the first constellation, and the second point belongs to the second constellations. While the above mainly relates to the exchange of information related to generated and / or used (or to be used) constellations, in the following, information is given on the decision on constellation points / symbols.

[0171] Embodiments and specific aspects outlined, specified and explained above may be combined with the present disclosure related to the decision on constellation points / symbols.

[0172] According to example embodiments, properties of a constellation can be determined at least by a machine learning procedure or optimization procedure.

[0173] According to example embodiments in connection with a machine learning based procedure for determination of properties of a constellation, in such machine learning-based procedure, the real and imaginary values of each point in the constellation are set as a trainable parameter.

[0174] Different loss functions may be defined for learning a proper value for the trainable parameters. For example, cross entropy (CE) over transmitted and received (estimated) bits can be defined as the loss function.

[0175] For a resource grid D and all the B bits in each symbol, considering b((d)and are the transmitted bits at TX and the bit probability estimate at the RX for resource d and symbol I, the CE loss function may be expressed as where ND denotes the number of (data-carrying) resource elements in the resource grid D.

[0176] If other constraints such as symmetry are added to the constellation, then only e.g. one quadrant of points is learned and then these points are projected into the other quadrants according to the symmetry property. According to example embodiments, learning of the constellation points can be done by adding a perturbation to a QAM constellation, in which case the perturbation was the trainable parameter.

[0177] FIG. 16 (FIG. 16a and FIG. 16b) is a schematic diagram illustrating arrangements of exemplary constellations according to example embodiments, and in particular illustrates a zero-mean constellation with MEAN=0+0j (FIG. 16a) and a non-zero-mean constellation with MEAN=0.10+0.01j (FIG. 16b).

[0178] FIG. 16 (FIG. 16a and FIG. 16b) shows two examples of zero-mean and nonzero-mean learned constellations using cross entropy loss function, where each constellation is made of 64 points.

[0179] According to example embodiments in connection with an optimization-based procedure for determination of properties of a constellation, in such optimization-based procedure, a list of potential constellations can be designed e.g. by experts or generated by any means (for example, randomly distributing constellation points in the real-imaginary coordinate system). An optimization algorithm such as genetic algorithm may explore different constellations in different channel conditions and evaluate the goodness of each constellation using a pre-defined key performance indicator (KPI) (e.g., bit error rate (BER) or block error rate (BLER) or throughput). Through the optimization procedure according to example embodiments, better constellations are identified, and the best constellation for each scenario / channel conditions can be determined.

[0180] The above-described procedures and functions may be implemented by respective functional elements, processors, or the like, as described below.

[0181] In the foregoing exemplary description of the network entity, only the units that are relevant for understanding the principles of the disclosure have been described using functional blocks. The network entity may comprise further units that are necessary for its respective operation. However, a description of these units is omitted in this specification. The arrangement of the functional blocks of the devices is not construed to limit the disclosure, and the functions may be performed by one block or further split into sub-blocks.

[0182] When in the foregoing description it is stated that the apparatus, i.e. any means of the apparatus, is configured to perform some function, this is to be construed to be equivalent to a description stating that a (i.e. at least one) processor or corresponding circuitry, potentially in cooperation with computer program code stored in the memory of the respective apparatus, is configured to cause the apparatus to perform at least the thus mentioned function. Also, such function is to be construed to be equivalently implementable by specifically configured circuitry or means for performing the respective function (i.e. the expression "unit configured to" is construed to be equivalent e.g. to an expression such as "means for" and an expression "circuitry configured to").

[0183] In FIG. 17, an alternative illustration of apparatuses according to example embodiments is depicted. As indicated in FIG. 17, according to example embodiments, the apparatus (active sharing / providing entity) 10' (corresponding to the active sharing / providing entity 10) comprises a processor 171, a memory 172 and an interface 173, which are connected by a bus 174 or the like. Further, according to example embodiments, the apparatus (passive sharing / receiving entity) 30' (corresponding to the passive sharing / receiving entity 30) comprises a processor 175, a memory 176 and an interface 177, which are connected by a bus 178 or the like, and the apparatuses may be connected via link 179, respectively.

[0184] The processor 171 / 175 and / or the interface 173 / 177 may also include a modem or the like to facilitate communication over a (hardwire or wireless) link, respectively. The interface 173 / 177 may include a suitable transceiver coupled to one or more antennas or communication means for (hardwire or wireless) communications with the linked or connected device(s), respectively. The interface 173 / 177 is generally configured to communicate with at least one other apparatus, i.e. the interface thereof.

[0185] The memory 172 / 176 may store respective programs assumed to include program instructions or computer program code that, when executed by the respective processor, enables the respective electronic device or apparatus to operate in accordance with the example embodiments.

[0186] In general terms, the respective devices / apparatuses (and / or parts thereof) may represent means for performing respective operations and / or exhibiting respective functionalities, and / or the respective devices (and / or parts thereof) may have functions for performing respective operations and / or exhibiting respective functionalities.

[0187] When in the subsequent description it is stated that the processor (or some other means) is configured to perform some function, this is to be construed to be equivalent to a description stating that at least one processor, potentially in cooperation with computer program code stored in the memory of the respective apparatus, is configured to cause the apparatus to perform at least the thus mentioned function. Also, such function is to be construed to be equivalently implementable by specifically configured means for performing the respective function (i.e. the expression "processor configured to [cause the apparatus to] perform xxx-ing" is construed to be equivalent to an expression such as "means for xxx-ing").

[0188] According to example embodiments, an apparatus representing the active sharing / providing entity 10 comprises at least one processor 171, at least one memory 172 including computer program code, and at least one interface 173 configured for communication with at least another apparatus. The processor (i.e. the at least one processor 171, with the at least one memory 172 and the computer program code) is configured to perform deciding on at least one signal modulation constellation comprising constellation points (thus the apparatus comprising corresponding means for deciding), to perform generating information for derivation of said at least one signal modulation constellation (thus the apparatus comprising corresponding means for generating), and to perform transmitting the generated information for derivation of said at least one signal modulation constellation (thus the apparatus comprising corresponding means for transmitting).

[0189] According to example embodiments, an apparatus representing the passive sharing / receiving entity 30 comprises at least one processor 175, at least one memory 176 including computer program code, and at least one interface 177 configured for communication with at least another apparatus. The processor (i.e. the at least one processor 175, with the at least one memory 176 and the computer program code) is configured to perform receiving information for derivation of at least one signal modulation constellation (thus the apparatus comprising corresponding means for receiving), to perform deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation (thus the apparatus comprising corresponding means for deriving), and to perform conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal (thus the apparatus comprising corresponding means for conducting).

[0190] For further details regarding the operability / functionality of the individual apparatuses, reference is made to the above description in connection with any one of FIGs. 1 to 16, respectively.

[0191] For the purpose of the present disclosure as described herein above, it should be noted that

[0192] - method steps likely to be implemented as software code portions and being run using a processor at a network server or network entity (as examples of devices, apparatuses and / or modules thereof, or as examples of entities including apparatuses and / or modules therefore), are software code independent and can be specified using any known or future developed programming language as long as the functionality defined by the method steps is preserved;

[0193] - generally, any method step is suitable to be implemented as software or by hardware without changing the idea of the embodiments and its modification in terms of the functionality implemented;

[0194] - method steps and / or devices, units or means likely to be implemented as hardware components at the above-defined apparatuses, or any module(s) thereof, (e.g., devices carrying out the functions of the apparatuses according to the embodiments as described above) are hardware independent and can be implemented using any known or future developed hardware technology or any hybrids of these, such as MOS (Metal Oxide Semiconductor), CMOS (Complementary MOS), BiMOS (Bipolar MOS), BiCMOS (Bipolar CMOS), ECL (Emitter Coupled Logic), TTL (Transistor-Transistor Logic), etc., using for example ASIC (Application Specific IC (Integrated Circuit)) components, FPGA (Field-programmable Gate Arrays) components, CPLD (Complex Programmable Logic Device) components or DSP (Digital Signal Processor) components;

[0195] - devices, units or means (e.g. the above-defined network entity or network register, or any one of their respective units / means) can be implemented as individual devices, units or means, but this does not exclude that they are implemented in a distributed fashion throughout the system, as long as the functionality of the device, unit or means is preserved;

[0196] - an apparatus like the user equipment and the network entity / network register may be represented by a semiconductor chip, a chipset, or a (hardware) module comprising such chip or chipset; this, however, does not exclude the possibility that a functionality of an apparatus or module, instead of being hardware implemented, be implemented as software in a (software) module such as a computer program or a computer program product comprising executable software code portions for execution / being run on a processor;

[0197] - a device may be regarded as an apparatus or as an assembly of more than one apparatus, whether functionally in cooperation with each other or functionally independently of each other but in a same device housing, for example.

[0198] In general, it is to be noted that respective functional blocks or elements according to above-described aspects can be implemented by any known means, either in hardware and / or software, respectively, if it is only adapted to perform the described functions of the respective parts. The mentioned method steps can be realized in individual functional blocks or by individual devices, or one or more of the method steps can be realized in a single functional block or by a single device.

[0199] Generally, any method step is suitable to be implemented as software or by hardware without changing the idea of the present disclosure. Devices and means can be implemented as individual devices, but this does not exclude that they are implemented in a distributed fashion throughout the system, as long as the functionality of the device is preserved. Such and similar principles are to be considered as known to a skilled person.

[0200] Software in the sense of the present description comprises software code as such comprising code means or portions or a computer program or a computer program product for performing the respective functions, as well as software (or a computer program or a computer program product) embodied on a tangible medium such as a computer-readable (storage) medium having stored thereon a respective data structure or code means / portions or embodied in a signal or in a chip, potentially during processing thereof.

[0201] The present disclosure also covers any conceivable combination of method steps and operations described above, and any conceivable combination of nodes, apparatuses, modules or elements described above, as long as the above-described concepts of methodology and structural arrangement are applicable. In view of the above, there are provided measures for constellation sharing and coordination. Such measures exemplarily comprise deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

[0202] Even though the disclosure is described above with reference to the examples according to the accompanying drawings, it is to be understood that the disclosure is not restricted thereto. Rather, it is apparent to those skilled in the art that the present disclosure can be modified in many ways without departing from the scope of the inventive idea as disclosed herein.

[0203] Among others, the following Items are covered by the above disclosure:

[0204] Item 1. An apparatus, the 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 perform : deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

[0205] Item 2. The apparatus according to Item 1, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: selecting one of said at least one signal modulation constellation out of said at least one signal modulation constellation based on at least one of the following: a modulation order configured for wireless communication between two communication participants including said apparatus, or an experienced channel condition between said two communication participants experienced at one of said two communication participants, or a terminal mobility of one of said two communication participants being a terminal, or a frequency band configured for said wireless communication between said two communication participants, or an experienced signal to noise ratio experienced at one of said two communication participants, and transmitting information on said one of said at least one signal modulation constellation as a selected signal modulation constellation.

[0206] Item 3. The apparatus according to Item 1, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: receiving information on one of said at least one signal modulation constellation as a selected signal modulation constellation.

[0207] Item 4. The apparatus according to any of Items 1 to 3, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform at least one of the following: receiving a modulated signal and means for demodulating said modulated signal based on one of said at least one signal modulation constellation to a source signal; or modulating a source signal based on said one of said at least one signal modulation constellation to a modulated signal and means for transmitting said modulated signal.

[0208] Item 5. The apparatus according to any of Items 1 to 4, wherein said constellation points are complex values represented by value pairs, wherein said value pair of complex value comprises one of the following: a real value and an imaginary value of said complex value, or a magnitude value and a phase value of said complex value, and wherein said information for derivation of said at least one signal modulation constellation comprises information indicative of said value pairs of said constellation points.

[0209] Item 6. The apparatus according to Item 5, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: quantizing, based on quantization settings, said value pairs of said constellation points, wherein said information indicative of said value pairs of said constellation points corresponds to quantized value pairs of said constellation points resulting from said quantizing said value pairs of said constellation points.

[0210] Item 7. The apparatus according to Item 6, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: transmitting said quantization settings, or receiving said quantization settings.

[0211] Item 8. The apparatus according to Item 6 or 7, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: executing a plurality of learning iterations of interim constellation points, and quantizing value pairs of said interim constellation points of at least a part of said plurality of learning iterations. Item 9. The apparatus according to any of Items 5 to 8, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: detecting a symmetry in said constellation points, wherein said information indicative of said value pairs of said constellation points comprises information indicative of said value pairs of symmetry representative constellation points being a subset of said constellation points, and said information for derivation of said at least one signal modulation constellation comprises information indicative of said symmetry.

[0212] Item 10. The apparatus according to any of Items 1 to 9, wherein in relation to said generating said information for derivation of said at least one signal modulation constellation, the instructions, when executed by the at least one processor, cause the apparatus at least to perform : generating differential information indicative of differences between said constellation points and corresponding constellation points of a corresponding previous signal modulation constellation to be replaced by said at least one signal modulation constellation as said information for derivation of said at least one signal modulation constellation.

[0213] Item 11. The apparatus according to any of Items 1 to 10, wherein said at least one signal modulation constellation includes a plurality of signal modulation constellations corresponding to a plurality of modulation orders.

[0214] Item 12. The apparatus according to any of Items 1 to 11, wherein in relation to said deciding on said at least one signal modulation constellation, the instructions, when executed by the at least one processor, cause the apparatus at least to perform: determining said at least one signal modulation constellation as a result of machine learning processing for learning signal modulation constellations or as a result of a solution processing of an optimization problem.

[0215] Item 13. An apparatus, the 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 perform : receiving information for derivation of at least one signal modulation constellation, deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0216] Item 14. The apparatus according to Item 13, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: selecting said one of said at least one signal modulation constellation out of said at least one signal modulation constellation based on at least one of the following: a modulation order configured for wireless communication between two communication participants including said apparatus, or an experienced channel condition between said two communication participants experienced at one of said two communication participants, or a terminal mobility of one of said two communication participants being a terminal, or a frequency band configured for said wireless communication between said two communication participants, or an experienced signal to noise ratio experienced at one of said two communication participants, and transmitting information on said one of said at least one signal modulation constellation as a selected signal modulation constellation.

[0217] Item 15. The apparatus according to Item 13, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: receiving information on said one of said at least one signal modulation constellation as a selected signal modulation constellation.

[0218] Item 16. The apparatus according to any of Items 13 to 15, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: receiving a modulated signal and an operation of demodulating said modulated signal based on said one of said at least one signal modulation constellation to said source signal.

[0219] Item 17. The apparatus according to any of Items 13 to 16, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: modulating said source signal based on said one of said at least one signal modulation constellation to a modulated signal and an operation of transmitting said modulated signal.

[0220] Item 18. The apparatus according to any of Items 13 to 17, wherein said constellation points are complex values represented by value pairs, wherein said value pair of complex value comprises one of the following: a real value and an imaginary value of said complex value, or a magnitude value and a phase value of said complex value, and wherein said information for derivation of said at least one signal modulation constellation comprises information indicative of said value pairs of said constellation points.

[0221] Item 19. The apparatus according to Item 18, wherein said information indicative of said value pairs of said constellation points corresponds to quantized value pairs of said constellation points resulting from quantizing, based on quantization settings, said value pairs of said constellation points.

[0222] Item 20. The apparatus according to Item 19, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to perform: transmitting said quantization settings, or receiving said quantization settings.

[0223] Item 21. The apparatus according to any of Items 13 to 20, wherein said information for derivation of said at least one signal modulation constellation comprises information indicative of a symmetry in said constellation points, and information indicative of said value pairs of symmetry representative constellation points being a subset of said constellation points, and in relation to said deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, the instructions, when executed by the at least one processor, cause the apparatus at least to perform: reconstructing constellation points other than said symmetry representative constellation points based on said symmetry representative constellation points and said information indicative of said symmetry.

[0224] Item 22. The apparatus according to any of Items 13 to 20, wherein said at least one signal modulation constellation is a replacement of a previous at least one signal modulation constellation, and said information for derivation of said at least one signal modulation constellation includes differential information indicative of differences between said constellation points and corresponding constellation points of a corresponding previous signal modulation constellation, and in relation to said deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, the instructions, when executed by the at least one processor, cause the apparatus at least to perform: reconstructing said constellation points based on said corresponding constellation points of said corresponding previous signal modulation constellation and said differential information.

[0225] Item 23. The apparatus according to any of Items 13 to 22, wherein said at least one signal modulation constellation includes a plurality of signal modulation constellations corresponding to a plurality of modulation orders.

[0226] Item 24. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out steps: deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

[0227] Item 25. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out steps: receiving information for derivation of at least one signal modulation constellation, deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0228] Item 26. A non-transitory computer readable medium comprising program instructions stored thereon for performing at least the following: deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

[0229] Item 27. A non-transitory computer readable medium comprising program instructions stored thereon for performing at least the following: receiving information for derivation of at least one signal modulation constellation, deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

[0230] List of acronyms and abbreviations

[0231] 3GPP 3rd Generation Partnership Project

[0232] 5G 5th Generation

[0233] 6G 6th Generation

[0234] Al artificial intelligence

[0235] AI / ML artificial intelligence / machine learning

[0236] BER bit error rate

[0237] BLER block error rate

[0238] BW bandwidth

[0239] CE cross entropy CQI channel quality indicator

[0240] FCNN fully connected neural network gNB gNodeB

[0241] KPI key performance indicator

[0242] LA link adaptation

[0243] LUT look-up table

[0244] MIMO multiple input multiple output

[0245] ML machine learning

[0246] NN neural network

[0247] NW network

[0248] OFDM orthogonal frequency division multiplexing

[0249] OTA over the air

[0250] QAM quadrature amplitude modulation

[0251] QPSK quadrature phase shift keying

[0252] SINR signal to interference and noise ratio

[0253] TB transport block

[0254] TRX transceiving / transceiver

[0255] TX transmission / transmitter

[0256] UE user equipment

Claims

48Claims1. An apparatus, the apparatus comprising means for deciding on at least one signal modulation constellation comprising constellation points, means for generating information for derivation of said at least one signal modulation constellation, and means for transmitting the generated information for derivation of said at least one signal modulation constellation.

2. The apparatus according to claim 1, further comprising means for selecting one of said at least one signal modulation constellation out of said at least one signal modulation constellation based on at least one of the following: a modulation order configured for wireless communication between two communication participants including said apparatus, or an experienced channel condition between said two communication participants experienced at one of said two communication participants, or a terminal mobility of one of said two communication participants being a terminal, or a frequency band configured for said wireless communication between said two communication participants, or an experienced signal to noise ratio experienced at one of said two communication participants, and means for transmitting information on said one of said at least one signal modulation constellation as a selected signal modulation constellation.

3. The apparatus according to claim 1, further comprising means for receiving information on one of said at least one signal modulation constellation as a selected signal modulation constellation.

494. The apparatus according to any of claims 1 to 3, further comprising at least one of the following: means for receiving a modulated signal and means for demodulating said modulated signal based on one of said at least one signal modulation constellation to a source signal; or means for modulating a source signal based on said one of said at least one signal modulation constellation to a modulated signal and means for transmitting said modulated signal.

5. The apparatus according to any of claims 1 to 4, wherein said constellation points are complex values represented by value pairs, wherein said value pair of complex value comprises one of the following: a real value and an imaginary value of said complex value, or a magnitude value and a phase value of said complex value, and wherein said information for derivation of said at least one signal modulation constellation comprises information indicative of said value pairs of said constellation points.

6. The apparatus according to claim 5, further comprising means for quantizing, based on quantization settings, said value pairs of said constellation points, wherein said information indicative of said value pairs of said constellation points corresponds to quantized value pairs of said constellation points resulting from said quantizing said value pairs of said constellation points.

7. The apparatus according to claim 6, further comprising means for transmitting said quantization settings, or means for receiving said quantization settings.

8. The apparatus according to claim 6 or 7, further comprising50 means for executing a plurality of learning iterations of interim constellation points, and means for quantizing value pairs of said interim constellation points of at least a part of said plurality of learning iterations.

9. The apparatus according to any of claims 5 to 8, further comprising means for detecting a symmetry in said constellation points, wherein said information indicative of said value pairs of said constellation points comprises information indicative of said value pairs of symmetry representative constellation points being a subset of said constellation points, and said information for derivation of said at least one signal modulation constellation comprises information indicative of said symmetry.

10. The apparatus according to any of claims 1 to 9, wherein said means for generating said information for derivation of said at least one signal modulation constellation further comprises means for generating differential information indicative of differences between said constellation points and corresponding constellation points of a corresponding previous signal modulation constellation to be replaced by said at least one signal modulation constellation as said information for derivation of said at least one signal modulation constellation.

11. The apparatus according to any of claims 1 to 10, wherein said at least one signal modulation constellation includes a plurality of signal modulation constellations corresponding to a plurality of modulation orders.

12. The apparatus according to any of claims 1 to 11, wherein said means for deciding on said at least one signal modulation constellation comprises means for determining said at least one signal modulation constellation as a result of machine learning processing for51 learning signal modulation constellations or as a result of a solution processing of an optimization problem.

13. An apparatus, the apparatus comprising means for receiving information for derivation of at least one signal modulation constellation, means for deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and means for conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

14. A method, the method comprising deciding on at least one signal modulation constellation comprising constellation points, generating information for derivation of said at least one signal modulation constellation, and transmitting the generated information for derivation of said at least one signal modulation constellation.

15. A method, the method comprising receiving information for derivation of at least one signal modulation constellation, deriving said at least one signal modulation constellation comprising constellation points based on said information for derivation of said at least one signal modulation constellation, and conducting modulated signal communication based on one of said at least one signal modulation constellation to a source signal.

Images