System and method for generalizable artificial intelligence model for beam management

Abstract

Systems and methods for a generalizable artificial intelligence (AI) model for beam management in a wireless communication system are discussed herein. A user equipment (UE) generates reference signal measurements by measuring reference signals, wherein each reference signal corresponds to a transmit beam b of a set of transmit beams under an antenna polarization p of a set of antenna polarizations. The UE provides the reference signal measurements to an AI model configured to respond to the input with parameters for each transmit beam b at each polarization p. In some cases, the UE uses the parameters to generate a channel matrix, which may be fed back to the network or further analyzed by the UE to determine information corresponding to primary vectors that are subsequently fed back to the network. In other cases, the parameters are fed back to the network for use.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 376,792, filed on September 23, 2022, entitled “GENERALIZABLE AI MODEL FOR BEAMMANAGEMENT,” the contents of which are incorporated herein by reference in their entirety. Technical Field

[0003] The present application generally relates to wireless communication systems, including wireless communication systems that implement beam management mechanisms. Background Art

[0004] Wireless mobile communication technologies use various standards and protocols to send data between base stations and wireless communication devices. For example, wireless communication system standards and protocols may include the Third Generation Partnership Project (3GPP) Long Term Evolution (LTE) (e.g., 4G), 3GPP New Radio (NR) (e.g., 5G), and the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard for wireless local area networks (WLANs) (commonly referred to within industry organizations as WLANs). ).

[0005] As envisioned by 3GPP, different wireless communication system standards and protocols may use various radio access networks (RANs) to communicate between base stations of the RAN (which may also sometimes be referred to as RAN nodes, network nodes, or simply nodes) and wireless communication devices referred to as user equipment (UE). 3GPP RANs may include, for example, Global System for Mobile Communications (GSM), Enhanced Data Rates for GSM Evolution (EDGE) RAN (GERAN), Universal Terrestrial Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRAN), and / or Next Generation Radio Access Network (NG-RAN).

[0006] Each RAN may use one or more radio access technologies (RATs) to perform communications between base stations and UEs. For example, GERAN implements GSM and / or EDGE RAT, UTRAN implements Universal Mobile Telecommunications System (UMTS) RAT or other 3GPP RAT, E-UTRAN implements LTE RAT (sometimes referred to as LTE), and NG-RAN implements NR RAT (sometimes referred to herein as 5G RAT, 5G NR RAT, or NR). In some deployments, E-UTRAN may also implement NR RAT. In some deployments, NG-RAN may also implement LTE RAT.

[0007] The base stations used by the RAN may correspond to the RAN. An example of an E-UTRAN base station is an Evolved Universal Terrestrial Radio Access Network (E-UTRAN) Node B (also commonly denoted as an evolved Node B, enhanced Node B, eNodeB, or eNB). An example of an NG-RAN base station is a Next Generation Node B (sometimes also referred to as a g-Node B or gNB).

[0008] The RAN provides communication services together with external entities through its connection with the Core Network (CN). For example, E-UTRAN may utilize the Evolved Packet Core (EPC) and NG-RAN may utilize the 5G Core Network (5GC). BRIEF DESCRIPTION OF THE DRAWINGS

[0009] To easily identify the discussion of any particular element or action, the most significant digit(s) in a reference number refers to the drawing number that first introduces the element.

[0010] Figure 1 A method of a UE according to the embodiments discussed herein is illustrated.

[0011] Figure 2 A method of a RAN according to the embodiments discussed herein is illustrated.

[0012] Figure 3 A method of a UE according to the embodiments discussed herein is illustrated.

[0013] Figure 4 A method of a UE according to the embodiments discussed herein is illustrated.

[0014] Figure 5 An example architecture of a wireless communication system according to embodiments disclosed herein is illustrated.

[0015] Figure 6 A system for performing signaling between a wireless device and a network device according to embodiments disclosed herein is illustrated. DETAILED DESCRIPTION

[0016] Various embodiments are described with respect to UE. However, reference to UE is provided for illustrative purposes only. The example embodiments may be used with any electronic component that can establish a connection with a network and is configured with hardware, software, and / or firmware for exchanging information and data with the network. Therefore, UE as described herein is used to represent any suitable electronic component.

[0017] The present disclosure establishes a connection between beam management and channel state information (CSI) feedback. Thus, a mechanism for extracting key channel parameters for constructing a channel matrix is ​​proposed. As will be described, the feedback corresponding to the beam management process can be designed using CSI feedback.

[0018] Furthermore, with respect to model generalization aspect, it is proposed to use digital domain beam angle / phase slope instead of actual beam angle in degrees as input to the artificial intelligence (AI) model.

[0019] Discussion on channel model

[0020] Various multiple-input multiple-output (MIMO) channel models are now described.

[0021] It should be noted that in early research on smart antennas, for example, in the book "Smart Antennas for Wireless Communications: Is-95 and Third Generation CDMA Applications" by Joseph C. Liberti and Theodore S. Rappaport, published by Prentice-Hall in 1999, various vector channels were proposed.

[0022] Furthermore, for both beam management and CSI feedback, MIMO channels as discussed in, for example, 3GPP Technical Report (TR) 38.901, “Study on Channel Model for Frequencies from 0.5 to 100 GHz,” Version 17.0.0 (March 2023) (hereinafter “TR 38.901”) may be particularly relevant.

[0023] In some embodiments, channel coefficients are generated for each cluster n and each pair of receiver and transmitter elements u, s.

[0024] In the non-line-of-sight (NLOS) case, the channel coefficient for ray m in cluster n of a link between a receive (Rx) antenna u and a transmit (Tx) antenna s at time t in the kth frequency bin can be calculated as

[0025]

[0026] (See TR 38.901 Section 8.4 Formula 27), where F rx,u,θ and F rx,u,φ They are the spherical basis vectors and The field pattern of the receiving antenna element u in the direction, F tx,s,θ and F tx,s,φ They are the spherical basis vectors and The delay (time of arrival (TOA)) of ray m in cluster n of the link between Rx antenna u and Tx antenna s is given by:

[0027]

[0028] (See TR 38.901 Section 8.4 Formula 28).

[0029] For the mth ray in the nth cluster, is the azimuth angle of arrival and the pitch arrival angle θ n,m,ZOA The spherical unit vector of is given by

[0030]

[0031] (See TR 38.901 Section 8.4 Formula 28), and Azimuth departure angle and the pitch departure angle θ n,m,ZOD The spherical unit vector of is given by

[0032]

[0033] (See TR 38.901 Section 8.4 Formula 30).

[0034] also, is the position vector of the receiving antenna element u, and is the position vector of the transmitting antenna element s, κ n,m is the cross-polarization power ratio in linear scale. If polarization is not considered, the 2x2 polarization matrix can be expressed by the scalar exp(jΦ n,m ) instead, and only the vertical polarization field pattern is applied.

[0035] Based on the angle of arrival (angle of arrival (AOA), zenith angle of arrival (ZOA)), the velocity vector of the user terminal (UT) with velocity v Travel azimuth φ v , elevation angle θ v The Doppler frequency component is calculated and given by

[0036]

[0037] (See TR 38.901 Section 8.4 Formula 31).

[0038] In the case of line of sight (LOS), the channel coefficients are calculated in the same manner as in TR 38.901 section 8.4, equation 27 (as provided above), except that n=1:

[0039]

[0040] (See TR 38.901 Section 8.4 Equation 32), where the corresponding delay (TOA) for cluster n=1 of the link between the Rx antenna u and the Tx antenna s is given by

[0041]

[0042] With respect to the case where the above formulas are used (eg, TR 38.901 Section 8.4 Formula 27 and TR 38.901 Section 8.4 Formula 32), it is possible that the oxygen absorption loss OL for each ray m in cluster n at carrier frequency f is n,m (f) can be modeled as

[0043]

[0044] in:

[0045] α(f) is the frequency-dependent oxygen loss per distance (dB / km) characterized in clause 7.6.1;

[0046] c is the speed of light (m / s); and

[0047] ●τ n is the delay obtained from step 3 for the deterministic cluster and from step 5 for the random cluster. Also note that min(τ n ′) is the output from step 3.

[0048] See TR 38.901 section 8.4 formula 33.

[0049] In some cases (e.g. in the context of TR 38.901 clause 8.4 equation 27 and clause 8.4 equation 32), blocking modelling is an additional feature. If a blocking model is applied, then the blocking loss BL in dB for each ray m in cluster n at carrier frequency f and time t is given, e.g. in the same way as given in TR 38.901 clause 7.6.4. n,m (f, t) is modeled; otherwise, for all f and t, BL n,m (f,t)=0dB.

[0050] Reference term (e.g., as found in TR 38.901 Section 8.4 Equation 27 as described above), it can be seen that the Doppler shift can be different between rays (note that n is the ray index of cluster m). Note that there may be modifications / additions to the channel generation steps with respect to considerations of spatial consistency of the generated MIMO channels, which can be found in TR 38.901. Such modifications / additions do not change the validity of the embodiments discussed herein.

[0051] In the 3GPP NR Release 16 (Rel-16) type IICSI feedback design, the precoder for spatial layer n can be given by the following formula

[0052]

[0053] Where p is the polarization index (e.g., for polarization at +45°, p=0, and for polarization at -45°, p=1), there are B0 significant beams for the Tx antenna at polarization index 0, and there are B1 significant beams for the Tx antenna at polarization index 1. For polarization index p, b is a beam with a departure angle (θ b,p ,φ b,p ) of the ray index, A(θ b,p ,φ b,p ) is the array response of (θ, φ), τ b,p is the relative delay, and a b is the path gain including the amplitude and phase of ray b. Assuming a regular antenna element arrangement, then (θ b,p ,φ b,p ) can be mapped to (i1,i2,p1,p2), where p1,0≤p1≤O1-1 and p2,0≤p2≤O2-1 are the oversampling factors of the vertical domain and the horizontal domain, respectively, and (i1,i2) is the spatial beam index.

[0054] It can be observed that there can be multiple rays with the same departure angle but different relative delays, and when considered from the perspective of relative delays, there can be rays with different departure angles but the same relative delay.

[0055] The following is a discussion of the design of the precoding matrix indicator (PMI) for 3GPP NR Release 18 (Rel-18). b,p is a complex coefficient connecting the spatial beam, delay and Doppler shift, and b is a beam index corresponding roughly to a ray in a cluster as in the TR 38.901 MIMO model. In some cases, it may be proposed that in Rel-18, the precoder may be represented as

[0056]

[0057] (Note that relative to the Rel-16 precoder design discussed above, there is now an additional term f for the Doppler shift b,p ).

[0058] Similar to the design in Rel-16, the linear combination (LC) coefficient with the largest amplitude (the strongest LC coefficient) can be found (from the LC coefficients of both polarizations from all the slices). Possibly related to polarization index is associated, and the corresponding beam index may be (or in the digital domain as ).Then, can be used to normalize the other coefficients, and a constant frequency offset can be added to all beams so that Can be used to shift the frequency offset by other LC coefficients:

[0059]

[0060] also, can be used to further shift the strongest complex coefficient to the first FD component (or first tap):

[0061]

[0062]

[0063] Note however that it is also possible not to shift the strongest coefficient to the DC tone, effectively using the following advanced processing flow:

[0064]

[0065] Therefore, in the discussion of this article, the action of shifting to DC frequency modulation can be considered an optional step. In order to control the feedback overhead, it may be necessary to feedback only the larger and the corresponding (θ b,p ,φ b,p ), and

[0066] In other cases where feedback overhead is not an issue, feedback is possible. Since feedback overhead is indeed a concern in many cases, quantization applied to these quantities can be used. The quantizer can be expressed as

[0067] ●Spatial beam selection and quantization Q 1,1 and Q 1,2 ,

[0068] The delayed tap (also called FD component in RAN1) quantizes Q2,

[0069] ●LC coefficient quantization Q3, and

[0070] ●Doppler component (or time domain (TD) component) selection / quantization Q4.

[0071] Conceptually, it should be understood that if Small, ignoring it (and the corresponding amount) will not ultimately lead to much difference / change in the precoder. In this case, it is also possible to consider indicating a small The way of omitting.

[0072] It has been recognized that the formula for the precoder as discussed above can also be used for the channel response between the network and a single receive antenna at the UE side. This formula can help build an intuitive understanding of channel propagation compared to the MIMO channel model (e.g., as captured in TR 38.901).

[0073] Discussion on beam management: connection with CSI feedback

[0074] There may be two approaches to building an AI model for beam management. Under the first approach, since each cell is different, the cell terrain information can be built into the AI ​​model itself. In this case, the model can be expected to perform well for the cell where the AI ​​was trained, but it may not generalize well at other cells.

[0075] Under the second approach, the AI ​​model can be viewed as a universal estimator based on interpolation through the universal approximation theorem of neural networks (e.g., see, https: / / en.wikipedia.org / wiki / Universal_approximation_theorem. Although such an AI model may not perform as well as a cell-specific AI model for a specific cell because only non-cell-specific interpolation / estimation is performed by the model, it is expected that the model should generalize more easily than in the case of a cell-specific model.

[0076] Conceptually, by using multiple simulated beams (simulated beamforming weight vectors), a channel response matrix can be constructed from various observations. In one approach, the maximum likelihood fit of a single θ can be obtained by fitting |A(θ) at multiple m with the observed reference signal received power (RSRP) at beam m. T W(m)|. In one example, m=1,3,7,8,9,10, and we form the RSRP value as a vector:

[0077]

[0078] where the test vector is given by

[0079]

[0080] where t k =|A(θ) TW(k)|. To match the contours, the normalized inner product of the two vectors, i.e., cosine similarity, can be used. It can be seen that as long as the number of measurements is greater than the number of unknown parameters in the channel model, the channel can be estimated up to the scaling factor (note that g is difficult to estimate).

[0081] Under actual channel propagation conditions, the number of AoD / ZoD can be greater than 1, which can facilitate the use of additional beam measurements to reconstruct the channel. It can be seen that the channel matrix is ​​parameterized as follows:

[0082]

[0083] Key parameters can be extracted from the channel matrix.

[0084] Focusing on beam management case 1 (spatial prediction case), we can assume that f b,p = 0. Then, to construct the channel, the relevant parameter can be θ b,p ,φ b,p , and τ b,p .

[0085] It will be appreciated that estimates of these parameters may be generated by the AI ​​model. Four parameters are required to represent each ray, and the number of rays / clusters may be limited to a relatively small number to avoid unsolvable / overly complex problems for the AI ​​model. Once the parameters of the main ray are known, singular value decomposition (SVD) may be applied to the channel matrix in the subband, or to the wideband covariance matrix established from the channel matrix. The resulting main singular vectors are then the optimal precoder for analog beamforming.

[0086] In some implementations, gain control in analog beamforming can be challenging, so limiting the results to the phase adjustment component has a side benefit. Thus, in some cases, only the phase portion of the main singular vectors may be used.

[0087] Accordingly, for beam management case 1, it is proposed to train the AI ​​model with θ b,p ,φ b,p , and τ b,p as output. The number of rays / clusters (i.e., the range of p) is a hyperparameter. The UE can then use these parameters to reconstruct the channel matrix. In some such cases, the channel matrix can be reconstructed using the following formula

[0088]

[0089] In some cases, the UE may feed back the channel matrix to the network.

[0090] In some cases, the UE may alternatively use the channel matrix to determine the main singular vectors of the wideband covariance matrix based on inferences from the AI ​​model. The main singular vectors may be fed back to the network. Alternatively, the phase portion of the main singular vectors is fed back to the network.

[0091] It is also envisaged that in other alternative cases, instead of reconstructing the channel matrix at the UE side, the UE feeds back the parameters itself to the network (e.g., b,p ,φ b,p , and τ b,p The network may then use these parameters to derive the best beam for itself (e.g., using an AI model and channel reconstruction as described). The network may determine the best beam relative to a period (e.g., 5 ms) after receiving the feedback.

[0092] In a further alternative, instead of feeding back θ for multiple rays b,p ,φ b,p , and τ b,p , the Type IICSI feedback design may be reused instead (e.g., Rel-16 Type IICSI feedback may be reused). However, note that in this case, the measurement resource configuration may be based on a beam management mechanism rather than a mechanism for CSI feedback. For beam management, multiple measurement resources (Channel State Information Reference Signal (CSI-RS) resources and / or Synchronization Signal Blocks (SSBs)) with a single port or two ports may be configured for beam management. However, for CSI feedback, a single CSI-RS resource with multiple ports may be configured. In order to inform the UE of the antenna port configuration, parameters such as N1 / N2 (which specify the number of antenna ports in the vertical and horizontal domains at a given polarization) are used to characterize the antenna array and are signaled as part of the RRC configuration from the network. In order to facilitate the reverse θ b,p ,φ b,p , and τ b,p Parameter estimation and (re)construction of the channel matrix, etc. It is assumed that N1 and N2 can also be transmitted to the UE using signals in the case of AI beam management.

[0093] For beam management case 2, the Doppler shift can also be considered. Therefore, to construct the channel, the relevant parameter can be θ b,p ,φ b,p , τ b,p and (or θ b,p ,φ b,p , τ b,p and fb,p ).

[0094] Accordingly, for beam management case 2, it is proposed to train the AI ​​model with θ b,p ,φ b,p , τ b,p and as output. The number of rays / clusters (i.e., the range of p) is a hyperparameter. The UE can then use these parameters to reconstruct the channel matrix. In some such cases, the channel matrix can be reconstructed using the following formula

[0095]

[0096] Alternatively, again for beam management case 2, it is proposed to train the AI ​​model with θ b,p ,φ b,p , τ b,p and f b,p as output. The number of rays / clusters (i.e., the range of p) is a hyperparameter. The UE can then use these parameters to reconstruct the channel matrix. In some such cases, the channel matrix can be reconstructed using the following formula

[0097] In some cases, the UE may feed back the channel matrix to the network at one or more time instances.

[0098] In some cases, at one or more times, the UE may alternatively use the channel matrix to determine the main singular vectors of the wideband covariance matrix based on inferences from the AI ​​model. The main singular vectors at one or more times may be fed back to the network. Alternatively, the phase portion of the main singular vectors is fed back to the network.

[0099] It is also envisaged that in other alternative cases, instead of reconstructing the channel matrix at the UE side, the UE feeds back the parameters itself to the network (e.g., b,p ,φ b,p , τ b,p and (or θ b,p ,φ b,p , τ b,p and f b,p ) is fed back to the network) for channel construction at the network. The network can then use these parameters to derive the best beam for itself (e.g., using the AI ​​model and channel matrix reconstruction as described). The network can determine the best beam relative to a period (e.g., 5ms) after receiving the feedback.

[0100] In a further alternative, instead of feeding back θ for multiple rays b,p ,φb,p , τ b,p and Type IICSI feedback design may be reused (e.g., Rel-18 Type IICSI feedback may be reused, where the UE feeds back channel parameters according to the Rel-18 design). However, note that in this case, the measurement resource configuration may be according to a beam management mechanism rather than a mechanism for CSI feedback. For beam management, multiple measurement resources (CSI-RS resources and / or SSBs) with a single port or two ports may be configured for beam management. However, for CSI feedback, a single CSI-RS resource with multiple ports may be configured. In order to inform the UE of the antenna port configuration, parameters such as N1 / N2 (which specify the number of antenna ports in the vertical and horizontal domains at a given polarization) are used to characterize the antenna array and are signaled as part of the RRC configuration from the network. In order to facilitate the reverse θ b,p ,φ b,p , and τ b,p Parameter estimation, and (re)construction of the channel matrix, etc. It is conceivable that N1 and N2 can also be transmitted to the UE using signals for AI beam management.

[0101] Relative to generalization considerations

[0102] With respect to the generalization of the methods discussed herein, the antenna element spacing aspect is now discussed. The vertical spacing between antenna elements can be expressed as d V And the horizontal antenna spacing between antenna elements can be expressed as d H .

[0103] It should be noted that in the actual antenna module design, d V and d H is not necessarily at half wavelength (as is often assumed in array signal processing). To illustrate this, we assume that the antenna array is a 1D array rather than a 2D array (as is often assumed for NR). The array response is then given by

[0104]

[0105] where τ k =d H sinθ / c,f c is the carrier frequency in Hertz (Hz), and c is the speed of light in meters per second (m / s).

[0106] Because the UE does not know the antenna spacing d H and d V (In this particular case, only d His relevant), the UE actually uses the DFT vector to match the array response. In a simple setting with a single path from the network to the UE and perfect time synchronization, the channel response matrix from the network to a single UE antenna can be written as

[0107] gA(θ)

[0108] where g is the complex gain factor.

[0109] For type IICSI feedback, the precoder tested by the UE can be written as

[0110]

[0111] Then, the beamformed channel is given by

[0112]

[0113] Amplitude of the composite channel A(θ) T W(m) is maximized at m, so

[0114] mod(d H / λsin(θ)+m / (N1O1),1)≈0 or mod(d H / λsin(θ)+m / (N1O1),1)≈1.

[0115] Consider the case where the propagation conditions between the network and the UE are not modified by using different antenna modules at the network. Then, the optimal beamforming weight vector is given by

[0116] m opt =mod(-(N1O1)d H / λsin(θ),N1O1).

[0117] In one specific implementation, d H =1 / 2λ. Then:

[0118] m opt =mod(-(N1O1)d H / λsin(θ),N1O1)=mod(-(N1O1)1 / 2sin(θ),N1O1).

[0119] In another specific implementation, d H =2 / 5λ. Then:

[0120] m opt =mod(-(N1O1)d H / λsin(θ),N1O1)=mod(-(N1O1)2 / 5sin(θ),N1O1).

[0121] This derivation can be similarly / analogously extended to the 2D case, for example where:

[0122] m opt =mod(-(N1O1)d H / λsin(θ),N1O1)

[0123] and

[0124] n opt =mod(-(N2O2)d V / λsin(φ),N2O2).

[0125] Therefore, it can be understood that for the same network site and UE location, the preferred DFT beam vector as the beamforming weight vector may be different with different antenna spacings at the base station antenna module.

[0126] In addition, it can be understood that in CSI feedback, PMI search does not need to be based on the antenna spacing d H and d V clear information.

[0127] From the above discussion, we can see that for a given beam angle (θ, φ), the corresponding array response vector is characterized by (d H / λsin(θ),d V / λsin(φ)).

[0128] For discussion purposes, let us assume a 1D array and O1=1, then to generate the DFT beam vector, the beam angle needs to satisfy

[0129] d H / λsin(θ)=m / (N1)

[0130] Usually the angle intervals between θ are uneven, such as θ = sin -1 (m / N1·λ / d H ), m=0,±1,±2,….

[0131] Consider using antenna spacing (d H / λ=0.5,d v The AI ​​model is trained for a given set of beam angles at (d / λ = 0.5), but the same AI model is used for H / λ=0.4,d v / λ=0.4) of the cell. In order to make the model relative to d H and d v Thus, first, as input to the AI ​​model, for each measurement using beam k from the set B beams used as input to the AI ​​model, a triplet is generated:

[0132] (RSRP(k),s 1,k ,s 2,k ),

[0133] where s 1,k is the horizontal beam angle of beam k in the digital domain, s 2,k is the vertical beam angle of beam k in the digital domain, and 1≤k≤N B , where N B is the number of beams in set B.

[0134] Then, once the input is converted into digital domain beam angles, different antenna modules (e.g., with different antenna spacings) can be used in the same training session for the AI ​​model.

[0135] Furthermore, assuming that the amplitude profile can be used to fit the AI ​​model (eg, as in the estimation of θ), the RSRP values ​​used as input to the AI ​​model are also normalized in the linear domain.

[0136] Figure 1 A method 100 of a UE according to an embodiment discussed herein is illustrated. The method 100 includes generating 102 reference signal measurements by measuring reference signals sent by a network in a channel, wherein each reference signal corresponds to a transmit beam b in a set of transmit beams used by the network. The method 100 also includes providing 104 the reference signal measurements to an AI model. The method 100 also includes, in response to providing the reference signal measurements to the AI ​​model, receiving 106 parameters for each transmit beam b in the set of transmit beams from the AI ​​model. The method 100 also includes determining 108 a channel matrix for the channel based on the parameters for each transmit beam b. The method 100 also includes determining 110 a wideband covariance matrix based on the channel matrix. The method 100 also includes identifying 112 a primary vector from the wideband covariance matrix. The method 100 also includes transmitting 114 information corresponding to the primary vector to the network.

[0137] In some embodiments of method 100, each transmit beam b uses an antenna polarization p from a set of antenna polarizations used by the network.

[0138] In some embodiments of method 100, the information corresponding to the primary vector includes the primary vector.

[0139] In some embodiments of method 100, the information corresponding to the primary vector includes a phase of the primary vector.

[0140] In some embodiments of method 100, the parameters received from the AI ​​model for each transmit beam b include θ b,p ,φ b,p , and τb,p , where: θ b,p is the zenith departure angle of the transmitted beam b in polarization p; φ b,p is the azimuth departure angle of the transmitted beam b under polarization p; C b,p is a first connection coefficient associating the transmit beam b at polarization p with the corresponding delay and the corresponding first Doppler shift; is a second connection coefficient that is a maximum connection coefficient determined across the set of transmit beams under a set of antenna polarizations used by the network, where The normalized polarization with the polarization of the antenna group The normalized transmit beam of the group of transmit beams under is associated; and τ b,p is the relative delay of the transmitted beam b at polarization p. In some such embodiments, based on the parameter θ b,p ,φ b,p , and τ b,p , use the formula to determine the channel matrix:

[0141]

[0142] In some such embodiments, the parameters for each transmit beam b received from the AI ​​model also include Where: f b,p is the first Doppler shift of transmit beam b at polarization p; and is the normalized transmit beam In the normalized polarization In some of these cases, based on the parameter θ b,p ,φ b,p , τ b,p and Use the formula to determine the channel matrix:

[0143]

[0144] In some such embodiments, the parameters received from the AI ​​model for each transmit beam b also include f b,p , where: f b,p is the first Doppler shift of the transmit beam b at polarization p. In some of these cases, based on the parameter θ b,p ,φ b,p , τ b,p and f b,p , use the formula to determine the channel matrix:

[0145]

[0146] In some embodiments, method 100 also includes: receiving from the network a first horizontal antenna spacing used by the network to send a reference signal and a first vertical antenna spacing used by the network to send a reference signal; and normalizing the reference signal measurement to take into account one or more of the following: a first difference between the first horizontal antenna spacing and the second horizontal antenna spacing assumed by the AI ​​model; and a second difference between the first vertical antenna spacing and the second vertical antenna spacing assumed by the AI ​​model.

[0147] Figure 2 A method 200 of a RAN according to an embodiment discussed herein is illustrated. The method 200 includes sending 202 a reference signal to a UE in a channel, wherein each reference signal corresponds to a transmit beam b in a set of transmit beams used by the RAN. The method 200 also includes receiving 204 a parameter for each transmit beam b in the set of transmit beams from the UE in response to the sending of the reference signal. The method 200 also includes determining 206 a channel matrix for the channel based on the parameters for each transmit beam b. The method 200 also includes identifying 208 a primary vector from the channel matrix. The method 200 also includes performing 210 data transmission to the UE using a transmit precoding corresponding to the primary vector.

[0148] In some embodiments of the method 200, each transmit beam b uses an antenna polarization p from a set of antenna polarizations used by the RAN.

[0149] In some embodiments of method 200, the parameters for each transmit beam b received from the UE include θ b,p ,φ b,p , and τ b,p , where: θ b,p is the zenith departure angle of the transmitted beam b in polarization p; φ b,p is the azimuth departure angle of the transmitted beam b under polarization p; C b,p is a first connection coefficient associating the transmit beam b at polarization p with the corresponding delay and the corresponding first Doppler shift; is a second connection coefficient that is a maximum connection coefficient determined across the set of transmit beams under a set of antenna polarizations used by the network, where The normalized polarization with the polarization of the antenna group The normalized transmit beam of the group of transmit beams under is associated; and τ b,p is the relative delay of the transmitted beam b at polarization p. In some such embodiments, based on the parameter θ b,p ,φ b,p , and τ b,p, use the formula to determine the channel matrix:

[0150]

[0151] In some such embodiments, the parameters received from the UE for each transmit beam b also include Where: f b,p is the first Doppler shift of transmit beam b at polarization p; and is the normalized transmit beam In the normalized polarization In some of these cases, based on the parameter θ b,p ,θ b,p ,φ b,p , τ b,p and Use the formula to determine the channel matrix:

[0152]

[0153] In some such embodiments, the parameters for each transmit beam b received from the UE model also include f b,p , where: f b,p is the first Doppler shift of the transmit beam b at polarization p. In some of these cases, based on the parameter θ b,p ,θ b,p ,φ b,p , τ b,p and f b,p , use the formula to determine the channel matrix:

[0154]

[0155] Figure 3 A method 300 of a UE according to an embodiment discussed herein is illustrated. The method 300 includes generating 302 reference signal measurements by measuring reference signals sent by a network in a channel, wherein each reference signal corresponds to a transmit beam b in a set of transmit beams used by the network. The method 300 also includes providing 304 the reference signal measurements to an AI model. The method 300 also includes, in response to providing the reference signal measurements to the AI ​​model, receiving 306 parameters for each transmit beam b in the set of transmit beams from the AI ​​model. The method 300 also includes transmitting 308 to the network the parameters for each transmit beam b received from the AI ​​model.

[0156] In some embodiments of the method 300, each transmit beam b uses an antenna polarization p from a set of antenna polarizations used by the network.

[0157] In some embodiments of method 300, the parameters received from the AI ​​model for each transmit beam b include θ b,p ,φ b,p , and τ b,p , where: θ b,p is the zenith departure angle of the transmitted beam b in polarization p; φ b,p is the azimuth departure angle of the transmitted beam b under polarization p; C b,p is a first connection coefficient associating the transmit beam b at polarization p with the corresponding delay and the corresponding first Doppler shift; is a second connection coefficient that is a maximum connection coefficient determined across the set of transmit beams under a set of antenna polarizations used by the network, where The normalized polarization with the polarization of the antenna group The normalized transmit beam of the group of transmit beams under is associated; and τ b,p is the relative delay of transmit beam b at polarization p. In some such embodiments, the parameters received from the AI ​​model for each transmit beam b at each polarization p also include Where: f b,p is the first Doppler shift of transmit beam b at polarization p; and is the normalized transmit beam In the normalized polarization In some such embodiments, the parameters received from the AI ​​model for each transmit beam b also include f b,p , where: f b,p is the first Doppler shift of the transmitted beam b at polarization p.

[0158] Figure 4 A method 400 of a UE according to an embodiment discussed herein is illustrated. The method 400 includes generating 402 reference signal measurements by measuring reference signals sent by a network in a channel, wherein each reference signal corresponds to a transmit beam b in a set of transmit beams used by the network. The method 400 also includes providing 404 the reference signal measurements to an AI model. The method 400 also includes, in response to providing the reference signal measurements to the AI ​​model, receiving 406 parameters for each transmit beam b in the set of transmit beams from the AI ​​model. The method 400 also includes determining 408 a channel matrix for the channel based on the parameters for each transmit beam b. The method 400 also includes transmitting 410 the channel matrix to the network.

[0159] In some embodiments of method 400, each transmit beam b uses an antenna polarization p from a set of antenna polarizations used by the network.

[0160] In some embodiments of method 400, the parameters received from the AI ​​model for each transmit beam b include θ b,p ,φ b,p , and τ b,p , where: θ b,p is the zenith departure angle of the transmitted beam b in polarization p; φ b,p is the azimuth departure angle of the transmitted beam b under polarization p; C b,p is a first connection coefficient associating the transmit beam b at polarization p with the corresponding delay and first Doppler shift; is a second connection coefficient that is a maximum connection coefficient determined across the set of transmit beams under a set of antenna polarizations used by the network, where The normalized polarization with the polarization of the antenna group The normalized transmit beam of the group of transmit beams under is associated; and τ b,p is the relative delay of the transmitted beam b at polarization p. In some such embodiments, based on the parameter θ b,p ,φ b,p , and τ b,p , use the formula to determine the channel matrix:

[0161]

[0162] In some such embodiments, the parameters for each transmit beam b received from the AI ​​model also include Where: f b,p is the first Doppler shift of transmit beam b at polarization p; and is the normalized transmit beam In the normalized polarization In some of these cases, based on the parameter θ b,p ,θ b,p ,φ b,p , τ b,p and Use the formula to determine the channel matrix:

[0163]

[0164] In some such embodiments, the parameter model for each transmit beam b received from the AI ​​model also includes f b,p , where: f b,p is the first Doppler shift of the transmit beam b at polarization p. In some of these cases, based on the parameter θ b,p ,θ b,p,φ b,p , τ b,p and f b,p , use the formula to determine the channel matrix:

[0165]

[0166] Figure 5 An example architecture of a wireless communication system 500 according to an embodiment disclosed herein is illustrated. The description provided below is for an example wireless communication system 500 operating in conjunction with the LTE system standard and / or the 5G or NR system standard provided in the 3GPP technical specifications.

[0167] like Figure 5 As shown, wireless communication system 500 includes UE 502 and UE 504 (however, any number of UEs may be used). In this example, UE 502 and UE 504 are illustrated as smartphones (e.g., handheld touch screen mobile computing devices capable of connecting to one or more cellular networks), but may also include any mobile or non-mobile computing device configured for wireless communication.

[0168] UE 502 and UE 504 may be configured to be communicatively coupled to RAN 506. In an embodiment, RAN 506 may be NG-RAN, E-UTRAN, etc. UE 502 and UE 504 utilize connections (or channels) (shown as connection 508 and connection 510, respectively) with RAN 506, each of which includes a physical communication interface. RAN 506 may include one or more base stations (such as base station 512 and base station 514) that implement connection 508 and connection 510.

[0169] In this example, connection 508 and connection 510 are the air interfaces used to enable such communicative coupling and may conform to the RAT used by RAN 506, such as, for example, LTE and / or NR.

[0170] In some embodiments, UE 502 and UE 504 may also directly exchange communication data via side link interface 516. UE 504 is illustrated as being configured to access an access point (illustrated as AP 518) via connection 520. For example, connection 520 may include a local wireless connection, such as a connection conforming to any IEEE 802.11 protocol, wherein AP 518 may include In this example, AP 518 can connect to another network (eg, the Internet) without going through CN 524.

[0171] In an embodiment, UE 502 and UE 504 may be configured to communicate with each other or with base station 512 and / or base station 514 over a multi-carrier communication channel using orthogonal frequency division multiplexing (OFDM) communication signals according to various communication techniques, such as, but not limited to, orthogonal frequency division multiple access (OFDMA) communication techniques (e.g., for downlink communication) or single carrier frequency division multiple access (SC-FDMA) communication techniques (e.g., for uplink and ProSe or sidelink communication), although the scope of the embodiment is not limited in this respect. The OFDM signal may include multiple orthogonal subcarriers.

[0172] In some embodiments, all or part of the base station 512 or the base station 514 may be implemented as one or more software entities running on a server computer as part of a virtual network. In addition, or in other embodiments, the base station 512 or the base station 514 may be configured to communicate with each other via the interface 522. In an embodiment where the wireless communication system 500 is an LTE system (e.g., when the CN 524 is an EPC), the interface 522 may be an X2 interface. The X2 interface may be defined between two or more base stations (e.g., two or more eNBs, etc.) connected to the EPC and / or between two eNBs connected to the EPC. In an embodiment where the wireless communication system 500 is an NR system (e.g., when the CN 524 is a 5GC), the interface 522 may be an Xn interface. The Xn interface is defined between two or more base stations (e.g., two or more gNBs, etc.) connected to the 5GC, between the base station 512 (e.g., gNB) and the eNB connected to the 5GC, and / or between two eNBs connected to the 5GC (e.g., CN 524).

[0173] RAN 506 is illustrated as being communicatively coupled to CN 524. CN 524 may include one or more network elements 526 configured to provide various data and telecommunication services to customers / subscribers (e.g., UE 502 and users of UE 504) connected to CN 524 via RAN 506. The components of CN 524 may be implemented in one physical device or separate physical devices including components for reading and executing instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium).

[0174] In an embodiment, CN 524 may be an EPC, and RAN 506 may be connected to CN 524 via an S1 interface 528. In an embodiment, S1 interface 528 may be divided into two parts: an S1 user plane (S1-U) interface, which carries communication traffic data between base station 512 or base station 514 and a serving gateway (S-GW); and an S1-MME interface, which is a signaling interface between base station 512 or base station 514 and a mobility management entity (MME).

[0175] In an embodiment, CN 524 may be a 5GC, and RAN 506 may be connected to CN 524 via an NG interface 528. In an embodiment, NG interface 528 may be divided into two parts: an NG user plane (NG-U) interface, which carries communication service data between base station 512 or base station 514 and a user plane function (UPF); and an S1 control plane (NG-C) interface, which is a signaling interface between base station 512 or base station 514 and an access and mobility management function (AMF).

[0176] In general, the application server 530 may be an element that provides applications that use Internet Protocol (IP) bearer resources with the CN 524 (e.g., packet-switched data services). The application server 530 may also be configured to support one or more communication services (e.g., VoIP sessions, group communication sessions, etc.) for the UE 502 and UE 504 via the CN 524. The application server 530 may communicate with the CN 524 via an IP communication interface 532.

[0177] Figure 6 A system 600 for performing signaling 634 between a wireless device 602 and a network device 618 according to an embodiment disclosed herein is illustrated. The system 600 may be part of a wireless communication system as described herein. The wireless device 602 may be, for example, a UE of a wireless communication system. The network device 618 may be, for example, a base station (e.g., an eNB or a gNB) of a wireless communication system.

[0178] The wireless device 602 may include one or more processors 604. The processor 604 may execute instructions to perform various operations of the wireless device 602 as described herein. The processor 604 may include one or more baseband processors implemented using, for example, a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a controller, a field programmable gate array (FPGA) device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0179] The wireless device 602 may include a memory 606. The memory 606 may be a non-transitory computer-readable storage medium storing instructions 608 (which may include, for example, instructions executed by the processor 604). The instructions 608 may also be referred to as program code or a computer program. The memory 606 may also store data used by the processor 604 and results calculated by the processor.

[0180] The wireless device 602 may include one or more transceivers 610, which may include radio frequency (RF) transmitter and / or receiver circuitry that uses an antenna 612 of the wireless device 602 to facilitate signaling (e.g., signaling 634) to and / or from the wireless device 602 with other devices (e.g., network device 618) in accordance with a corresponding RAT.

[0181] The wireless device 602 may include one or more antennas 612 (e.g., one, two, four, or more). For embodiments with multiple antennas 612, the wireless device 602 may utilize the spatial diversity of such multiple antennas 612 to transmit and / or receive multiple different data streams on the same time-frequency resources. This behavior may be referred to as, for example, MIMO behavior (referring to multiple antennas used at each of the transmitting device and the receiving device to implement this aspect). The MIMO transmission performed by the wireless device 602 may be implemented based on precoding (or digital beamforming) applied to the wireless device 602, which multiplexes the data streams between the antennas 612 based on known or assumed channel characteristics, so that each data stream is received with appropriate signal strength relative to the other streams and at a desired location in the spatial domain (e.g., the location of the receiver associated with the data stream). Certain embodiments may use a single-user MIMO (SU-MIMO) approach (where data streams are all directed to a single receiver) and / or a multi-user MIMO (MU-MIMO) approach (where separate data streams may be directed to separate (different) receivers in different locations in the spatial domain).

[0182] In certain embodiments with multiple antennas, the wireless device 602 may implement analog beamforming techniques whereby the phases of signals transmitted by antennas 612 are relatively adjusted so that the (joint) transmissions of antennas 612 can be directed (this is sometimes referred to as beam steering).

[0183] The wireless device 602 may include one or more interfaces 614. The interfaces 614 may be used to provide input to or output from the wireless device 602. For example, a wireless device 602 that is a UE may include an interface 614, such as a microphone, a speaker, a touch screen, buttons, etc., to allow a user of the UE to provide input and / or output to the UE. Other interfaces of such a UE may be composed of transmitters, receivers, and other circuits that allow the UE to communicate with other devices (e.g., in addition to the transceiver 610 / antenna 612 described above), and may communicate according to known protocols (e.g., etc.) to perform the operation.

[0184] The wireless device 602 may include a beam management module 616. The beam management module 616 may be implemented via hardware, software, or a combination thereof. For example, the beam management module 616 may be implemented as a processor, circuit, and / or instructions 608 stored in the memory 606 and executed by the processor 604. In some examples, the beam management module 616 may be integrated within the processor 604 and / or the transceiver 610. For example, the beam management module 616 may be implemented by a combination of software components (e.g., executed by a DSP or a general purpose processor) and hardware components (e.g., logic gates and circuits) within the processor 604 or the transceiver 610.

[0185] The beam management module 616 may be used in various aspects of the present disclosure, for example, Figures 1 to 4 The beam management module 616 may be configured, for example, to perform reference signal measurements at the wireless device 602 or to cause reference signal measurements to be performed, provide the reference signal measurements to the AI ​​model, receive corresponding parameters for each transmit beam b in a set of transmit beams for each polarization p from the AI ​​model, and perform further tasks using such parameters (e.g., determining a channel matrix / corresponding main vector to be fed back to the network, feeding these parameters directly back to the network for use at the network, etc.).

[0186] The network device 618 may include one or more processors 620. The processor 620 may execute instructions to perform various operations of the network device 618 as described herein. The processor 620 may include one or more baseband processors implemented using, for example, a CPU, a DSP, an ASIC, a controller, an FPGA device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0187] The network device 618 may include a memory 622. The memory 622 may be a non-transitory computer-readable storage medium storing instructions 624 (which may include, for example, instructions executed by the processor 620). The instructions 624 may also be referred to as program code or a computer program. The memory 622 may also store data used by the processor 620 and results calculated by the processor.

[0188] The network device 618 may include one or more transceivers 626, which may include RF transmitter and / or receiver circuitry that uses an antenna 628 of the network device 618 to facilitate signaling (e.g., signaling 634) sent or received by the network device 618 with other devices (e.g., wireless device 602) according to a corresponding RAT.

[0189] The network device 618 may include one or more antennas 628 (e.g., one, two, four, or more). In embodiments with multiple antennas 628, the network device 618 may perform MIMO, digital beamforming, analog beamforming, beam steering, etc. as described above.

[0190] The network device 618 may include one or more interfaces 630. The interface 630 may be used to provide input to or output from the network device 618. For example, the network device 618 as a base station may include an interface 630 composed of a transmitter, a receiver, and other circuits (e.g., in addition to the transceiver 626 / antenna 628 described above), which enables the base station to communicate with other equipment in the core network and / or enables the base station to communicate with an external network, computer, database, etc., in order to achieve the purpose of performing operations, management, and maintenance of the base station or other equipment operably connected thereto.

[0191] The network device 618 may include a beam management module 632. The beam management module 632 may be implemented via hardware, software, or a combination thereof. For example, the beam management module 632 may be implemented as a processor, circuit, and / or instructions 624 stored in the memory 622 and executed by the processor 620. In some examples, the beam management module 632 may be integrated within the processor 620 and / or the transceiver 626. For example, the beam management module 632 may be implemented by a combination of software components (e.g., executed by a DSP or general purpose processor) and hardware components (e.g., logic gates and circuits) within the processor 620 or the transceiver 626.

[0192] The beam management module 632 may be used in various aspects of the present disclosure, for example, Figures 1 to 4The beam management module 632 may be configured, for example, to send reference signal measurements by the network device 618 or to cause reference signal measurements to be sent, and in response receive from the UE a channel matrix / corresponding principal vector for use by the network device 618, parameters for each transmit beam b in a set of transmit beams for each polarization p (for use at the network to determine the channel matrix / corresponding principal vector for use by itself), etc.

[0193] Embodiments contemplated herein include an apparatus including means for performing one or more elements of any one or more of methods 100, 300, and 400. The apparatus may be, for example, an apparatus of a UE (such as wireless device 602 as a UE, as described herein).

[0194] Embodiments contemplated herein include one or more non-transitory computer-readable media that include instructions to cause the electronic device to perform one or more elements of any one or more of methods 100, 300, and 400 when one or more processors of the electronic device execute the instructions. The non-transitory computer-readable medium may be, for example, a memory of a UE (such as memory 606 of a wireless device 602 as a UE, as described herein).

[0195] Embodiments contemplated herein include an apparatus including logical components, modules, or circuits for performing one or more elements of any one or more of methods 100, 300, and 400. The apparatus may be, for example, an apparatus of a UE (such as wireless device 602 as a UE, as described herein).

[0196] Embodiments contemplated herein include an apparatus comprising: one or more processors; and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of any one or more of methods 100, 300, and 400. The apparatus may be, for example, an apparatus of a UE (such as wireless device 602 as a UE, as described herein).

[0197] Embodiments contemplated herein include signals as described in or associated with one or more elements of any one or more of method 100 , method 300 , and method 400 .

[0198] Embodiments contemplated herein include a computer program or computer program product including instructions, wherein execution of the program by a processor causes the processor to perform one or more elements of any one or more of methods 100, 300, and 400. The processor may be a processor of a UE (such as processor 604 of wireless device 602 as a UE, as described herein). These instructions may be located, for example, in a processor and / or on a memory of a UE (e.g., memory 606 of wireless device 602 as a UE, as described herein).

[0199] Embodiments contemplated herein include an apparatus comprising means for performing one or more elements of method 200. The apparatus may be, for example, an apparatus that is a base station (such as network device 618 that is a base station, as described herein).

[0200] Embodiments contemplated herein include one or more non-transitory computer-readable media including instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform one or more elements of method 200. The non-transitory computer-readable medium may be, for example, a memory of a base station (such as memory 622 of network device 618 acting as a base station, as described herein).

[0201] Embodiments contemplated herein include an apparatus comprising logical components, modules, or circuits operable to perform one or more elements of method 200. The apparatus may be, for example, an apparatus that is a base station (such as network device 618 as a base station, as described herein).

[0202] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of method 200. The apparatus may be, for example, an apparatus that is a base station (such as network device 618 that is a base station, as described herein).

[0203] Embodiments contemplated herein include a signal as described in or in connection with one or more elements of method 200 .

[0204] Embodiments contemplated herein include a computer program or computer program product including instructions, wherein execution of the program by a processing element causes the processing element to perform one or more elements of method 200. The processor may be a processor of a base station (such as processor 620 of network device 618 as a base station, as described herein). These instructions may be located, for example, in a processor and / or on a memory of a base station (such as memory 622 of network device 618 as a base station, as described herein).

[0205] For one or more embodiments, at least one of the components set forth in one or more of the foregoing figures may be configured to perform one or more operations, techniques, processes, and / or methods as described herein. For example, a baseband processor as described herein in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples set forth herein. For another example, a circuit system associated with a UE, a base station, a network element, etc. as described above in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples set forth herein.

[0206] Unless otherwise expressly stated, any of the above embodiments may be combined with any other embodiment (or combination of embodiments). The foregoing description of one or more specific implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of the embodiments to the precise form disclosed. In view of the above teachings, modifications and variations are possible or can be obtained from the practice of various embodiments.

[0207] Embodiments and implementations of the systems and methods described herein may include various operations that may be embodied in machine executable instructions to be executed by a computer system. A computer system may include one or more general or special purpose computers (or other electronic devices). A computer system may include hardware components that include specific logic components for performing operations; or may include a combination of hardware, software, and / or firmware.

[0208] It should be appreciated that the systems described herein include descriptions of specific embodiments. These embodiments may be combined into a single system, partially combined into other systems, separated into multiple systems, or otherwise divided or combined. In addition, it is contemplated that parameters, attributes, aspects, etc. of another embodiment may be used in one embodiment. For clarity, these parameters, attributes, aspects, etc. are described only in one or more embodiments, and it should be appreciated that these parameters, attributes, aspects, etc. may be combined with or substituted for parameters, attributes, aspects, etc. of another embodiment unless expressly stated herein.

[0209] It is understood that the use of personally identifiable information should be subject to privacy policies and practices that are generally recognized to meet or exceed industry or government requirements for maintaining user privacy. Specifically, personally identifiable information data should be managed and processed to minimize the risk of unintentional or unauthorized access or use, and the nature of the authorized use should be clearly stated to users.

[0210] Although the foregoing has been described in considerable detail for the sake of clarity, it will be apparent that certain changes and modifications may be made without departing from the principles of the invention. It should be noted that there are many alternative ways to implement both the processes and the apparatus described herein. Therefore, the embodiments of the present invention should be regarded as illustrative rather than restrictive, and the specification is not limited to the details given herein, but may be modified within the scope and equivalents of the appended claims.

Claims

1. A method of a user equipment (UE), the method comprising: generating reference signal measurements by measuring reference signals transmitted by a network in a channel, wherein each reference signal corresponds to a transmit beam b of a set of transmit beams used by the network; providing the reference signal measurements to an artificial intelligence (AI) model; receiving, from the AI ​​model, parameters for each transmit beam b in the set of transmit beams in response to providing the reference signal measurement to the AI ​​model; determining a channel matrix for said channel based on said parameters for each transmit beam b; determining a wideband covariance matrix based on the channel matrix; identifying a principal vector from the wideband covariance matrix; as well as Information corresponding to the primary vector is transmitted to the network.

2. The method of claim 1, wherein each transmit beam b uses an antenna polarization p from a set of antenna polarizations used by the network. The method according to claim 1 , wherein the information corresponding to the main vector includes the main vector. The method according to claim 1 , wherein the information corresponding to the main vector includes a phase of the main vector.

5. The method according to claim 1, wherein the parameters for each transmit beam b received from the AI ​​model include θ b,p ,φ b,p , and τ b,p ,in: θ b,p is the zenith departure angle of the transmit beam b at polarization p; φ b,p is the azimuth departure angle of the transmit beam b at the polarization p; C b,p is a first connection coefficient associating the transmit beam b at the polarization p with a corresponding delay and a corresponding first Doppler shift; is a second connection coefficient, which is the maximum connection coefficient determined across the set of transmit beams under a set of antenna polarizations used by the network, wherein The normalized polarization of the set of antenna polarizations The normalized transmit beam of the set of transmit beams under is associated with; and τ b,p is the relative delay of the transmitted beam b at the polarization p.

6. The method according to claim 5, wherein based on the parameter θ b,p ,φ b,p , and τ b,p , use the following formula to determine the channel matrix:

7. The method according to claim 5, wherein the parameters for each transmit beam b received from the AI ​​model further include f b,p - in: f b,p is the first Doppler shift of the transmit beam b at the polarization p; and is the normalized transmit beam In the normalized polarization The second Doppler shift under.

8. The method according to claim 7, wherein based on the parameter θ b,p ,φ b,p , τ b,p and f b,p - The channel matrix is ​​determined using the following formula:

9. The method according to claim 5, wherein the parameters for each transmit beam b received from the AI ​​model further include f b,p , where f b,p is the first Doppler frequency shift of the transmit beam b under the polarization p.

10. The method according to claim 9, wherein based on the parameter θ b,p ,φ b,p , τ b,p and f b,p , use the following formula to determine the channel matrix:

11. The method according to claim 1, further comprising: receiving, from the network, a first horizontal antenna spacing used by the network to send the reference signal and a first vertical antenna spacing used by the network to send the reference signal; as well as The reference signal measurement is normalized to account for one or more of the following: a first difference between the first horizontal antenna spacing and a second horizontal antenna spacing assumed by the AI ​​model; and A second difference between the first vertical antenna spacing and a second vertical antenna spacing assumed by the AI ​​model.

12. A method of a Radio Access Network (RAN), the method comprising: transmitting reference signals in a channel to a user equipment (UE), wherein each reference signal corresponds to a transmit beam b in a set of transmit beams used by the RAN; receiving, in response to the sending of the reference signal, parameters for each transmit beam b in the set of transmit beams from the UE; determining a channel matrix for said channel based on said parameters for each transmit beam b; identifying a principal vector from the channel matrix; as well as Data transmission to the UE is performed using transmit precoding corresponding to the primary vector.

13. The method of claim 12, wherein each transmit beam b uses an antenna polarization p from a set of antenna polarizations used by the RAN.

14. The method according to claim 12, wherein the parameters for each transmit beam b received from the UE include θ b,p ,φ b,p , and τ b,p ,in: θ b,p is the zenith departure angle of the transmit beam b at polarization p; φ b,p is the azimuth departure angle of the transmit beam b at the polarization p; C b,p is a first connection coefficient associating the transmit beam b at the polarization p with a corresponding delay and a corresponding first Doppler shift; is a second connection coefficient, which is the maximum connection coefficient determined across the set of transmit beams under a set of antenna polarizations used by the network, wherein The normalized polarization of the set of antenna polarizations The normalized transmit beam of the set of transmit beams under is associated with; and τ b,p is the relative delay of the transmitted beam b at the polarization p.

15. The method according to claim 14, wherein based on the parameter θ b,p ,φ b,p , and τ b,p , use the following formula to determine the channel matrix:

16. The method according to claim 14, wherein the parameters for each transmit beam b received from the UE further include f b,p - in: f b,p is the first Doppler shift of the transmit beam b at the polarization p; and is the normalized transmit beam In the normalized polarization The second Doppler shift under.

17. The method according to claim 16, wherein based on the parameter θ b,p ,φ b,p , τ b,p and f b,p - The channel matrix is ​​determined using the following formula:

18. The method according to claim 14, wherein the parameters for each transmit beam b received from the UE further include f b,p , where f b,p is the first Doppler frequency shift of the transmit beam b under the polarization p.

19. The method according to claim 18, wherein based on the parameter θ b,p ,φ b,p , τ b,p and f b,p , use the following formula to determine the channel matrix:

20. A method of a user equipment (UE), the method comprising: generating reference signal measurements by measuring reference signals transmitted by a network in a channel, wherein each reference signal corresponds to a transmit beam b of a set of transmit beams used by the network; providing the reference signal measurements to an artificial intelligence (AI) model; receiving, from the AI ​​model, parameters for each transmit beam b in the set of transmit beams in response to providing the reference signal measurement to the AI ​​model; as well as The parameters for each transmit beam b received from the AI ​​model are transmitted to the network.

21. The method of claim 20, wherein each transmit beam b uses an antenna polarization p from a set of antenna polarizations used by the network.

22. The method of claim 20, wherein the parameters for each transmit beam b received from the AI ​​model include θ b,p ,φ b,p , and τ b,p ,in: θ b,p is the zenith departure angle of the transmit beam b at polarization p; φ b,p is the azimuth departure angle of the transmit beam b at the polarization p; C b,p is a first connection coefficient associating the transmit beam b at the polarization p with a corresponding delay and a corresponding first Doppler shift; is a second connection coefficient, which is the maximum connection coefficient determined across the set of transmit beams under a set of antenna polarizations used by the network, wherein The normalized polarization of the set of antenna polarizations The normalized transmit beam of the set of transmit beams under is associated with; and τ b,p is the relative delay of the transmitted beam b at the polarization p.

23. The method according to claim 22, wherein the parameters for each transmit beam b received from the AI ​​model further include f b,p - in: f b,p is the first Doppler shift of the transmit beam b at the polarization p; and is the normalized transmit beam In the normalized polarization The second Doppler shift under.

24. The method according to claim 22, wherein the parameters for each transmit beam b received from the AI ​​model further include f b,p , where f b,p is the first Doppler shift of the transmit beam b under the polarization p.

25. A method of a user equipment (UE), the method comprising: generating reference signal measurements by measuring reference signals sent by a network in a channel, wherein each reference signal corresponds to a transmit beam b of a set of transmit beams used by the network at an antenna polarization p of a set of antenna polarizations used by the network; providing the reference signal measurements to an artificial intelligence (AI) model; In response to providing the reference signal measurement to the AI ​​model, receiving from the AI ​​model parameters for each transmit beam b in the set of transmit beams at each polarization p of the set of antenna polarizations; determining a channel matrix for said channel based on said parameters for each transmit beam b at each polarization p; The channel matrix is ​​transmitted to the network.

26. The method of claim 25, wherein each transmit beam b uses an antenna polarization p from a set of antenna polarizations used by the network.

27. The method of claim 25, wherein the parameters received from the AI ​​model for each transmit beam b include θ b,p ,φ b,p , and τ b,p ,in: θ b,p is the zenith departure angle of the transmit beam b at polarization p; φ b,p is the azimuth departure angle of the transmit beam b at the polarization p; C b,p is a first connection coefficient associating the transmit beam b at the polarization p with a corresponding delay and a first Doppler shift; is a second connection coefficient, which is the maximum connection coefficient determined across the set of transmit beams under a set of antenna polarizations used by the network, wherein The normalized polarization of the set of antenna polarizations The normalized transmit beam of the set of transmit beams under is associated with; and τ b,p is the relative delay of the transmitted beam b at the polarization p.

28. The method according to claim 27, wherein based on the parameter θ b,p ,φ b,p , and τ b,p , use the following formula to determine the channel matrix:

29. The method of claim 27, wherein the parameters for each transmit beam b received from the AI ​​model further include f b,p - in: f b,p is the first Doppler shift of the transmit beam b at the polarization p; and is the normalized transmit beam In the normalized polarization The second Doppler shift under.

30. The method according to claim 29, wherein based on the parameter θ b,p ,φ b,p , τ b,p and f b,p - The channel matrix is ​​determined using the following formula:

31. The method of claim 27, wherein the parameters for each transmit beam b received from the AI ​​model further include f b,p , where f b,p is the first Doppler frequency shift of the transmit beam b under the polarization p.

32. The method according to claim 31, wherein based on the parameter θ b,p ,φ b,p , τ b,p and f b,p , use the following formula to determine the channel matrix:

33. An apparatus comprising means for performing the method according to any one of claims 1 to 32.

34. A computer-readable medium comprising instructions, which, when executed by one or more processors of an electronic device, cause the electronic device to perform the method according to any one of claims 1 to 32.

35. An apparatus comprising logic components, modules or circuits for performing the method according to any one of claims 1 to 32.

Images