CN119156801A

CN119156801A - Lattice-reduction-aided disturbance additive demapper for multiple-input multiple-output signal detection

Info

Publication number: CN119156801A
Application number: CN202380032871.9A
Authority: CN
Inventors: M·佩斯赫尔; D·沃勒尔; A·贝赫布迪; R·邦德桑; P·萨德吉; S·巴尔吉
Original assignee: Qualcomm Inc
Current assignee: Qualcomm Inc
Priority date: 2022-04-15
Filing date: 2023-02-17
Publication date: 2024-12-17
Also published as: EP4508807A1; WO2023201134A1; KR20250002209A

Abstract

Certain aspects of the present disclosure provide techniques and apparatus for demapping a signal to a point in a signal constellation. An example method generally includes identifying (410) a seed point in a signal constellation from a received signal. A set of candidate codes for the signal is generated (420) based on the seed point and an additive disturbance applied to the seed point. Points in the signal constellation corresponding to the values of the received signal are identified (430) based on probability distributions generated over the set of candidate codes. Generally, the identified points correspond to the codes in the set of candidate codes that have the highest probability in the probability distribution. The point in the signal constellation is output (440) as the value of the received signal.

Description

Lattice-reduction-aided disturbance additive demapper for multiple-input multiple-output signal detection

Cross Reference to Related Applications

The present application claims the priority and benefit of U.S. patent application Ser. No. 18/155,454 entitled "lattice-aided disturbance additive demapper (Lattice Reduction-Aided Perturbed Additive Demapper for Multiple-Input Multiple-Output Signal Detection)" for multiple-input multiple-output Signal detection," filed on 1 month 17 of 2023, which claims the benefit and priority of U.S. provisional patent application Ser. No. 63/363,031 entitled "lattice-aided disturbance additive demapper (Lattice Reduction-Aided Perturbed Additive Demapper for Multiple-Input Multiple-Output Signal Detection)" for multiple-input multiple-output Signal detection," filed on 15 of 2022, and assigned to the assignee of the present application, the contents of each of which are hereby incorporated by reference in their entirety.

Background

Aspects of the present disclosure relate to signal detection in a wireless communication system.

Multiple-input multiple-output (MIMO) systems typically involve the use of multiple antennas at the transmitter and receiver for communication. Generally, MIMO technology generally allows multiple data streams to be transmitted and received simultaneously by communicating using multiple transmit and receive antennas. By doing so, the capacity and throughput provided by the wireless communication system may be increased relative to a single-input single-output system. MIMO communication may be performed using various techniques such as spatial multiplexing where different signals are transmitted using different transmit antennas, beamforming (or spatial filtering) where signals are directionally transmitted in a particular direction from a transmitting device with the highest radiated power, and so forth.

In general, MIMO signals are recovered by demapping the received signals to points in a signal constellation, such as a Quadrature Amplitude Modulation (QAM) constellation. A signal constellation typically includes a plurality of points in a multidimensional space, where each point represents a discrete value (e.g., of a bit stream). The received signal may be demapped to one of these points in the multidimensional space and the bit values of the point to which the received signal is demapped are typically output for further processing.

Demapping the MIMO signal to points in the signal constellation typically involves probabilistic estimates of the transmitted bits, which can be corrected using various error correction codes such as Low Density Parity Check (LDPC) codes. Due to the computational cost of computing the probability estimates of the transmitted bits, a lower complexity detector is used to demap the received MIMO signal. However, these detectors can still be computationally complex, resulting in high power consumption, and are implemented using a large amount of area in the processing circuitry.

Disclosure of Invention

Certain aspects provide a processor-implemented method for demapping a signal to a point in a signal constellation. An example method generally includes identifying a seed point in a signal constellation from a received signal. A set of candidate codes for the signal is generated based on the seed point and the additive perturbation applied to the seed point. Points in the signal constellation corresponding to the values of the received signal are identified based on probability distributions generated over the set of candidate codes. Generally, the identified points correspond to the codes in the set of candidate codes that have the highest probability in the probability distribution. The point in the signal constellation is output as the value of the received signal.

Other aspects provide a processing system configured to perform the foregoing methods and those described herein, a non-transitory computer-readable medium comprising instructions that, when executed by one or more processors of the processing system, cause the processing system to perform the foregoing methods and those described herein, a computer program product embodied on a computer-readable storage medium comprising code for performing the foregoing methods and those described further herein, and a processing system comprising means for performing the foregoing methods and those described further herein.

The following description and the annexed drawings set forth in detail certain illustrative features of the one or more aspects.

Drawings

The drawings depict certain aspects of the present disclosure and are, therefore, not to be considered limiting of its scope.

Fig. 1 depicts the mapping of decoded signals to points in a signal constellation.

Fig. 2 depicts an example of a region in a signal constellation from which candidate codes for a received signal may be selected in accordance with aspects of the present disclosure.

Fig. 3 depicts an example set of candidate codes for a received signal in a signal constellation in accordance with aspects of the present disclosure.

Fig. 4 depicts example operations for a lattice-aided-based disturbance additive demapper to demap a received signal into points in a signal constellation, in accordance with aspects of the present disclosure.

Fig. 5 depicts an example implementation of a processing system in which a received signal is demapped into points in a signal constellation, in accordance with aspects of the present disclosure.

To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures. It is contemplated that elements and features of one aspect may be beneficially incorporated in other aspects without further recitation.

Detailed Description

Aspects of the present disclosure provide techniques and apparatus for demapping received signaling to corresponding points in a signal constellation in a wireless communication system.

Multiple-input multiple-output (MIMO) technology is commonly used to achieve high data rates by transmitting signals from multiple antennas for reception by the multiple antennas. At the receiver, various demappers may be used to decode the received signal and provide the received signal to an error correction block for further processing. Because calculating probability estimates over the transmitted bits to use as input into the error correction block is typically a computationally complex task, a fixed lower complexity detector is used to attempt to simplify the task of demapping the signal to points in the signal constellation corresponding to a particular set of bit values.

In one example, a linear MIMO detector uses Zero Forcing (ZF) or Minimum Mean Square Error (MMSE) techniques to demap the received signal into points in the signal constellation. However, these linear MIMO detectors do not take into account the inter-stream interference in which one stream interferes with the other stream, and are therefore typically not able to de-map the received signal if the signals carried on the different carriers are highly correlated. In order to solve the problem that the linear MIMO detector based on ZF or MMSE cannot consider inter-stream interference, a tree-based MIMO detector is used to iteratively search for candidate values corresponding to the received signal. However, these tree-based approaches rely on manually designed heuristics, which results in limited flexibility in optimizing the MIMO detector for various channel statistics (e.g., channel signal strength attributes, etc.) and various error correction procedures. Furthermore, as the size of these signal constellations increases, and as the number of antennas via which signaling is sent and received increases, the trees used by the tree-based MIMO detectors may become larger (and unworkable), which may further complicate the implementation of these MIMO detectors in hardware.

Aspects of the present disclosure provide techniques for demapping a signal using a perturbed additive (e.g., linear) demapper that uses machine learning techniques to learn a parameter distribution with signal values centered around seed points in a signal constellation. By using machine learning techniques to demap signals to points in a signal constellation, aspects of the present disclosure may reduce the computational complexity of demapping signals to corresponding points in a signal constellation. Furthermore, these machine learning techniques may allow for increased flexibility in implementing MIMO detectors, as these machine learning techniques may be used for different sized signal constellations (e.g., 64QAM, 128QAM, 256QAM, etc.) and different numbers of antennas involved in a MIMO system. Additionally, these machine learning techniques may improve the accuracy of demapping the received signal to points in the signal constellation by generating more reliable log-likelihood ratios (LLRs) for subsequent error correction. Because these machine learning techniques may improve the accuracy of demapping the received signal to points in the signal constellation, more reliable transmission may be achieved and correspondingly reduce the number of retransmissions required to successfully transmit data in a wireless communication system, reduce power utilization from handling transmissions and retransmissions, and so forth.

Example demapping of signals to points in a Signal constellation

Generally, a MIMO system may be a multi-antenna system having M transmit antennas and N+.M receive antennas. The decoded bit stream may be mapped to a transmitted symbol vector xεΩ ^M, whereIs a2 ^Q -QAM complex constellation, where α >0 and Q is an even number, and x _j represents the number of bits per symbol. Alpha may be selected such that the QAM symbols are normalized to unit power per dimension (e.g., such that). Each symbol vector typically has a corresponding decoded bit value in { -1,1} ^M×Q, where x _j,b is the b-th bit in the j-th dimension/layer of x.

In demapping the MIMO signal to points in the signal constellation, it is generally assumed that the signaling is sent in a flat fading environment with a block fading channel that changes from frame to frame independently (e.g., with constant gain per frame). Thus, for any slot in the time-discrete complex baseband model with a noise vector (e.g., additive White Gaussian Noise (AWGN)), the resulting vector y in the signal constellation can be represented by the equation y = Hx + n. H represents an N M matrix representing complex Gaussian fading gain terms with independent and identical distributionRayleigh fading channel (where σ > 0). n represents a zero-mean circularly symmetric complex gaussian noise vector with constant covariance (i.e.,). In this model, the signal-to-noise ratio (SNR) per stream can be represented by the following equation 10log (1/σ ²), and a perfect channel estimate can be assumed at the receiver.

To detect the value of a signal in a MIMO system using soft output detection, the bitwise LLR may be calculated according to the following equation:

Which may be used as an input into a downstream error correction algorithm. In view of the AWGN-based model discussed above, the LLRs can be rewritten according to the following equation:

And

Wherein the method comprises the steps ofIs a subset of point x with bit x _j,b = 1, andRepresenting a subset of points x with bits x _j,b = -1. The corresponding bit of the larger of the two log-likelihoods (absolute value) is referred to as a hypothesized bit, and the smaller is referred to as an anti-hypothesized bit. A significant portion of the complexity of the soft output demapper is in computing the anti-hypothesis bits, since although a single hypothesis vector x ^* contains all of the hypothesis bits, the anti-hypothesis bits can be spread across as many as MQ anti-hypothesis vectors.

In order to simplify this point of view,The approximation of (a) may be calculated according to the following expression:

Which may be an approximation of the hard output problem defined according to the following equation: y-Hx ². However, even if Can simplify the process of detecting the value of a signal in a MIMO system, calculateThe NP-complete problem for which verifying the correctness of the solution may be performed in polynomial time may still be remained, and a brute force search may be used to find the solution from all possible solutions.

To demap the received vector, the linear detector may demap the received vector y by left multiplying y=hx+n by the linear filter matrix G and then quantizing the result to a point in the signal constellation. Can be based on the equation of scalar variable xTo define quantization for a finite set χ. For complex scalar variables, the real and imaginary components can be quantized independently, and for vectors, each dimension of the vector can be quantized independently.

Mathematically, a linear detector can be represented by the following equation:

Wherein the method comprises the steps of Representing the quantization of Gy and its remapping into the constellation diagram Ω ^M. Generally, different types of linear detectors may define G in different ways. For example, the ZF detector may use the Moore-Penrose pseudo-inverse of the channel matrix G _ZF＝H⁺＝(H^HH)^-1H^H according to the following equation, while the MMSE detector may use the noise statistics of the channel and define G _MMSE＝(H^HH+I)^-1H^H according to the following equation. In some aspects, the MMSE detector may be represented as a ZF detector over an extended channel, where

The identity function is satisfied:

G_MMSEy＝G_MMsEy

Where G _MMSE and y represent vectors in a higher dimension than G _MMSE and y.

The above equations generally produce a hard output, or output of a particular vector. To calculate a soft output (e.g., including some measure of the likelihood that the output is a correct output), the channel model may be rewritten according to the following equation:

Where H ₁,h₂,..represents the column of H, and n _j represents a new noise vector that treats layer i+.j as interference. By marginalizing the symbol x _i≠j, the new channel of y|x _jh_j can have covariance Thus, the problem of demapping the signal to a point in the signal constellation can be reduced to a one-dimensional problem by multiplying the equation by the per-channel decorrelation filter w _j, resulting in the following equation:

In some aspects of the present invention, One-dimensional complex Gao Silai approximation with matching variance can be utilized to produce the following expression:

Wherein the method comprises the steps of Is the variance K projected onto w, andIs a subset of constellation points for which bit b is set to + -1. The expression presented above may implement a soft output ZF detector. To implement a soft output MMSE detector, (H, y) may be used instead of (H, y).

The columns of H may form the basis of a lattice according to the following equation:

The lattice basis may be non-unique and the transformation between different bases may be performed by right multiplication of H with a single-mode matrix U defined according to the following expression:

Wherein the method comprises the steps of I.e., a general linear group on complex integers is a set of all matrices with complex integer terms and unit determinant.Each single-mode matrix, therefore, has an inverse that is also single-mode. Because of the unit determinant, the right-hand multiplication U is volume-preserving.

Single mode matrix may allow changing the basis of the latticeAnd thus may allow channel H to be re-parameterizedIn many cases, using re-parameterization, the MIMO detector may not be unchanged, and thus, some choices of U may provide higher performance than others. If the columns in H are orthogonal, then no inter-stream interference of the channel can be observed, and thus, the linear detector can be the best choice for demapping the signal to a point in the signal constellation. Thus, the optimal U may be a single-mode matrix that approximately orthogonalizes the columns of H, measured in terms of a log-orthogonality defect represented by the following equation:

The log-orthogonality defect may be a non-negative amount that decreases as the orthogonality between the columns of H increases, reaching zero when the columns of H are fully orthogonal. Thus, the lattice reduction implemented by these equations can be used in linear detectors that use the channel HU ^-1 and quantize to the reduction lattice before transforming back to and binding to the original constellation Ω ^M, as discussed above Furthermore, it should be noted that the gridThe trellis quantization operator of (c) may be efficiently calculated using the following equation: Wherein the method comprises the steps of

Fig. 1 illustrates an example of a signal constellation in which received signaling in a MIMO wireless communication system is demapped to points in the signal constellation.

In the constellation 110, the points in the constellation are arranged in a grid defined by vertical lines. In the constellations 120 and 130, the points in the constellation are arranged in a grid with lines drawn at an angle to lines parallel to the axes (the vertical axis in the constellation 120 and the horizontal axis in the constellation 130). The center point within the grid frame represents a particular bit value of the signal. Points within a grid frame may be mapped to center points within the grid frame.

In constellation 110, the received signal is mapped to a seed point 112. Because seed point 112 is located within a grid box having point 114 as its center, the MIMO demapper may map seed point 112 to point 114 and output the bit stream associated with point 114 as bits carried in the received signal. Similarly, in constellation 120, the received signal is mapped to seed point 122 within the grid frame with point 124 as its center, and the MIMO detector may thus output the bit value associated with point 124 as the bit carried in the received signal. In constellation 130, the received signal is mapped to seed point 132 within the grid frame with point 134 as its center, and the MIMO detector may thus output the bit value associated with point 134 as the bit carried in the received signal.

To improve the efficiency of MIMO demapping, aspects of the present disclosure provide techniques for applying a perturbation to a seed point and machine learning techniques for generating a set of candidate codes (or points in a signal constellation) associated with a received signal to determine a value of the received signal. In so doing, the search space over which the received signal is demapped may be reduced from the entire signal constellation to a portion of the signal constellation. Within this portion of the signal constellation, there is typically a high likelihood that a point in the signal constellation corresponds to a received signal. By reducing the search space from the entire signal constellation to a portion of the signal constellation, the computational cost of demapping the received signal to points in the signal constellation can be reduced, which can reduce the amount of power used to process signaling and communicate in a wireless communication network, and can reduce the amount of circuitry used to implement the signal demapper.

Typically, the calculationThe complexity involved is determined by the size of the search space To determine that the size scales exponentially across M and Q. That is, as the number of transmit antennas M increases, and as the number of bits Q represented by points in the signal constellation increases, the size of the search space increases exponentially. As devices implement additional transmit antennas, and as the size of the signal constellation increases to accommodate higher bit rates or other changes in the wireless communication system, these exponential increases may become impractical. To reduce the complexity involved in computing LLRs at points in a signal constellation, aspects of the present disclosure integrate each point setReplacement with smaller candidate set on which LLR is to be computed

Candidate setA perturbed linear model may be used in which the output Gy of the linear receiver is enhanced with several small perturbations δ. The disturbance output is quantized back into the signal constellation such that the candidate set is represented by the following equation:

In generating the candidate set, the seed point gy= [ H ⁺ y ] may be initially selected according to the following equation. The seed point Gy may be referred to as a Babai point or estimate of the value of the bit stream of the signal vector x carried in the received signal y. Included in candidate set Instead of delta, the points in (a) may be selected from the set delta u 0, wherein the perturbation with delta corresponding to the seed point Gy thereon is selected such that the seed point is always included in the candidate setIs included in the region (b). Then, aggregateCan be filtered into candidate sets for each bit j, b set to + -1, e.gIn general, for all j and b,

Selection of inclusion in a candidate set based on seed point GyThe symbol with the highest likelihood corresponding to the signal vector x carried in the received signal y is close to the linear receiver output Gy and can be found in an area centered on Gy across delta. The inverse assumption of the value of the received signal and the point to which the received signal can be mapped can be found within the area around Gy.

Fig. 2 illustrates an area in a signal constellation from which a candidate code for a received signal may be selected using a perturbation applied to a seed point Gy, in accordance with aspects of the present disclosure. As illustrated, the various perturbations may be defined as, for example, but not limited to, a quadrilateral 210 (e.g., square, rectangle, etc.) centered on the seed point 205, a sphere (or circle 220) centered on the seed point 205, an ellipse 230 centered on the seed point 205, a gaussian distribution 240 centered on the seed point 205, and so forth.

To generate candidate sets using perturbations defined within the quadrilateral 210Each perturbation δ may be defined according to the following equation:

δ _e.g. = [0, s,0], where s∈qam

To generate candidate sets using perturbations defined within the circle 220The perturbation may be defined according to the following equation:

δ=αru ^-2Mκ r, where

To generate candidate sets using perturbations defined within ellipses 230The perturbation may be defined according to the following equation:

δ=αrg (u ^-2Mκ r), wherein

Finally, to generate a candidate set using the perturbations defined within the gaussian distribution 240The perturbation may be defined according to the following equation:

δ=α rGg, where

In each of the equations discussed above, α is the minimum separation between QAM constellation points; r >0 radius of complex sphere centered around zero, u is a real uniform random variable in interval [0,1], M is the number of transmit antennas, kappa >0 is a radial weighting factor, r is a slaveI.e. a random vector extracted with uniform distribution on complex sphere of dimension M, g is a complex gaussian vector from unit variance circularly symmetric complex density centered around zero, e _i is a one-hot vector with one in position i, and Ω _K is a 1DK-QAM constellation.

In examples where samples are extracted within circles 220, circles 220 may be defined as spheres having a radius αr. If κ=1, the distribution is uniform, and the density of the sample approaches 0 as κ >1 increases.

In examples where samples are extracted within the ellipse 230, samples may be extracted from the distribution within the ellipse 230 and passed through G, which makes the distribution of samples elliptical. The dimension of the samples may be correlated with G, and as for ZF detectors (or other linear detectors) with H ⁺, the decoded symbol vector may take the form of x=gy-Gn with additive noise Gn centered around Gy.

In examples where samples are extracted from within the gaussian 240, a set of gaussian samples may be defined (e.g., on a density function, where parameters of the gaussian are identified based on bayesian optimization, as discussed in further detail below) and passed through G.

In each of the examples illustrated in fig. 2, it should be appreciated that generation of perturbations may be parallelized in accordance with various aspects, as the values of symbols carried in a signal are generally independent of the values of different symbols carried in the same signal. Thus, for each symbol whose value is to be recovered, the symbols can be processed independently and in parallel to speed up the process of recovering the value carried in the received signal.

In generating candidate setsThe LLR may then be calculated using a maximum log approximation according to the following equation:

in some aspects, the collection Or (b)Is empty and the corresponding lambda defaults to ≡. Because ≡may not be an available value, and because an LLR exceeding the set value may not provide optimal information for error correction and decoding, the LLR may be clipped to the maximum LLR value L _max such thatL _max may be optimized for different signal conditions (e.g., signal-to-noise ratio) and may be stored in a look-up table, with SNR or a range of SNRs being used as a key for any given value of L _max.

Fig. 3 depicts an example set of candidate codes 300 for a received signal in a signal constellation in accordance with aspects of the present disclosure. As illustrated, a set of candidate codesMay be generated from a gaussian distribution 320 centered around the seed point 310.

In some aspects, to generate the candidate setThe perturbation may be randomly selected within the gaussian distribution 320. However, in some aspects, the perturbation may be defined in terms of the parameter L _max and the perturbation distribution parameters r and κ. These parameters may be optimized, for example, using a bayesian optimization model. In general, in a bayesian optimized machine learning model, the parameters r and κ may be globally optimized. For each SNR (or range of SNRs), bit rate (BER) L _BER may be averaged over a subset of B instances of the channel defined by y=hx+n for an input given value θ. The Gaussian process may utilize a Materr covariance kernel to fit to the training data set of input-output pairs { (θ _k,L_BER,k)}_k. The result of the Gaussian process may beA mapped micro-bayesian regression estimator that can be used to select the next value of θ in the optimization process.

In some aspects, bayesian optimization may be performed as an "offline" process to find the optimal value of θ for each SNR (subject to noise and other optimization constraints). During use, θ may be looked up from a look-up table given the SNR of the channel on which the received signal is carried. θ may generally be selected to optimize end-to-end performance and may allow for the performance of the MIMO demapper to be more efficient than performing a grid search on the signal constellation (which may become computationally infeasible).

In some aspects, it should be noted that perturbation is used to generate a set of candidate points for a given received signalThe use of lattice reduction need not be involved. Lattice reduction generally allows identification of hypotheses of sufficient quality about which perturbations may be defined (e.g., identification of seed points that may be assumed to be close to actual points in the signal constellation corresponding to the received signal). When lattice reduction is used, channel H may be replaced with HU ^-1 and quantization operations may be similarly defined. Because lattice reduction is often a computationally complex problem, approximation algorithms such as those involving several iterations of Gram-Schmidt (Gram-Schmidt) (e.g., defined asWhere M corresponds to the number of transmit antennas as described above) to calculate U. In general, U may be calculated once for each H, where H is assumed to be constant, and the cost of calculating U and performing lattice reduction may be split across multiple channels.

In some aspects, where lattice reduction is used to process the received signal, lattice reduction may be performed for each subcarrier. However, lattice reduction may be shared across multiple subcarriers. For example, lattice reduction performed on one subcarrier may be applied to other subcarriers within a coherence bandwidth defined for a wireless communication system in which signaling is received. The coherence bandwidth may include, for example, frequencies over which the channel is constant (e.g., where the signal may have comparable or correlated fading characteristics).

Example operations for demapping a Signal to points in a Signal constellation

Fig. 4 illustrates example operations 400 for demapping a received signal into points in a signal constellation based on a lattice-aided scrambling additive demapper in accordance with aspects of the present disclosure. The operations 400 may be performed, for example, by a receiving wireless device in a wireless communication system, such as, but not limited to, a User Equipment (UE) in a 5G cellular telecommunications system, a wireless station in a Wi-Fi (802.11) network, and so on.

As illustrated, operation 400 includes identifying a seed point in a signal constellation from a received signal at block 410. In some aspects, the seed point may be identified by demapping the received signal based on a linear transformation. The linear transformation may include matrix re-parameterization and de-mapping based on the re-parameterized matrix. The matrix may be re-parameterized based on a lattice reduction using a single-mode matrix, and the received signal may be demapped based on the re-parameterized matrix and a symbol vector representing the received signal. A single-mode matrix (e.g., a square matrix, where each term has a value of-1, 0, or 1) may be a matrix in a set of matrices having complex integer terms and a unit determinant in a general linear group on the set of complex integer terms. When the matrix representing the channel is re-parameterized, the matrix may be transformed from H to HU ^-1.

At block 420, operation 400 continues to generate a set of candidate codes for the signal based on the seed point and the additive perturbation applied to the seed point.

In some aspects, the set of candidate codes may be generated by selecting points in the signal constellation that include points within a quadrilateral defined with a seed point as a center point of the quadrilateral. In some aspects, the set of candidate codes may be generated by selecting points in the signal constellation as a uniform distribution within a circle defined based on a radius from the seed point. In some aspects, the set of candidate codes may be generated by selecting points in the signal constellation as a uniform distribution within an ellipse defined by a seed point as a center point of the ellipse.

In some aspects, generating the set of candidate codes may include selecting points in the signal constellation based on a gaussian distribution calculated from the density function. The gaussian distribution may also use the seed points as the center points of the gaussian distribution, and selected points in the signal constellation may be identified relative to the seed points based on parameters identified according to bayesian optimization. These parameters may include, for example, perturbation distribution parameters r and κ, where r corresponds to the radius from the seed point from which the codes in the candidate set are to be selected, and κ corresponds to the sample density. These parameters may be learned based on a mapping between the input θ and the average bit error rate over several inputs for a given signal-to-noise ratio.

At block 430, operation 400 continues with identifying points in the signal constellation corresponding to the values of the received signal based on the probability distribution generated over the set of candidate codes. The identified points generally correspond to the codes in the candidate code set that have the highest probability in the probability distribution.

In some aspects, to identify points in the signal constellation that correspond to the values of the received signal, log-likelihood ratios on the set of candidate codes may be calculated. The log-likelihood ratio may be calculated based on clipping to a maximum LLR value associated with the signal-to-noise ratio of the received signal, which may be retrieved from a look-up table keyed by the signal-to-noise value, or may be identified based on bayesian optimization.

At block 440, operation 400 continues with outputting points in the signal constellation as the values of the received signal. This point may be output in the forward error correction component of the wireless transceiver along with one or more points from one or more other signals. The forward error correction component may use, for example, a Low Density Parity Check (LDPC) algorithm or other error correction algorithm to correct bit errors in a bit stream generated from the signal and one or more other signals.

In some aspects, operation 400 may comprise performing communication in a wireless communication network based on points in a signal constellation. The wireless communication network may include a cellular wireless communication network (e.g., a 5G network), an IEEE 802.11 wireless communication network, or other wireless communication network in which data may be transmitted and received over wireless channels. The communications may include voice communications and/or data communications carried in a wireless communication network.

Example processing System for demapping a Signal to points in a Signal constellation

Fig. 5 depicts an example processing system 500 for demapping a received signal to points in a signal constellation, such as described herein, for example, with respect to fig. 4.

The processing system 500 includes a Central Processing Unit (CPU) 502, which in some examples may be a multi-core CPU. The instructions executed at the CPU 502 may be loaded, for example, from a program memory associated with the CPU 502, or may be loaded from the memory 524.

The processing system 500 also includes additional processing components tailored for specific functions, such as a Graphics Processing Unit (GPU) 504, a Digital Signal Processor (DSP) 506, a Neural Processing Unit (NPU) 508, a multimedia processing unit 510, and a wireless connection component 512.

NPUs such as NPU 508 are typically dedicated circuits configured to implement control and arithmetic logic for performing machine learning algorithms, such as algorithms for processing Artificial Neural Networks (ANNs), deep Neural Networks (DNNs), random Forests (RF), and the like. The NPU may sometimes alternatively be referred to as a Neural Signal Processor (NSP), tensor Processing Unit (TPU), neural Network Processor (NNP), intelligent Processing Unit (IPU), visual Processing Unit (VPU), or graphics processing unit.

NPUs such as NPU 508 are configured to accelerate performance of common machine learning tasks such as image classification, machine translation, object detection, and various other predictive models. In some examples, multiple NPUs may be instantiated on a single chip, such as a system on a chip (SoC), while in other examples, multiple NPUs may be part of a dedicated neural network accelerator.

The NPU may be optimized for training or inference, or in some cases configured to balance performance between the two. For NPUs that are capable of both training and inferring, these two tasks can still generally be performed independently.

NPUs designed to accelerate training are generally configured to accelerate optimization of new models, which is a highly computationally intensive operation involving inputting an existing dataset (typically labeled or tagged), iterating over the dataset, and then adjusting model parameters (such as weights and biases) in order to improve model performance. Generally, optimizing based on mispredictions involves passing back through layers of the model and determining gradients to reduce prediction errors.

NPUs designed to accelerate inferences are generally configured to operate on a complete model. Thus, such NPUs may be configured to input new pieces of data and process them quickly through a trained model to generate model outputs (e.g., inferences).

In one implementation, NPU 508 is part of one or more of CPU 502, GPU 504, and/or DSP 506.

In some examples, wireless connection component 512 may include, for example, subcomponents for third generation (3G) connections, fourth generation (4G) connections (e.g., 4G LTE), fifth generation connections (e.g., 5G or NR), wi-Fi connections, bluetooth connections, and other wireless data transmission standards. The wireless connection component 512 is further coupled to one or more antennas 514.

The processing system 500 may also include one or more sensor processing units 516 associated with any manner of sensor, one or more Image Signal Processors (ISPs) 518 associated with any manner of image sensor, and/or a navigation component 520, which may include satellite-based positioning system components (e.g., GPS or GLONASS) as well as inertial positioning system components.

The processing system 500 may also include one or more input and/or output devices 522, such as a screen, touch-sensitive surface (including touch-sensitive displays), physical buttons, speakers, microphones, and so forth.

In some examples, one or more of the processors of processing system 500 may be based on an ARM or RISC-V instruction set.

The processing system 500 also includes memory 524, which represents one or more static and/or dynamic memories, such as Dynamic Random Access Memory (DRAM), flash-based static memory, or the like. In this example, memory 524 includes computer-executable components that may be executed by one or more of the aforementioned processors of processing system 500.

Specifically, in this example, the memory 524 includes a seed point identification component 524A, a candidate set generation component 524B, a point identification component 524C, a point output component 524D, and a machine learning model 524E. The depicted components, as well as other non-depicted components, may be configured to perform various aspects of the methods described herein.

In general, the processing system 500 and/or components thereof may be configured to perform the methods described herein.

It is noted that in other aspects of the present disclosure, such as where the processing system 500 is a server computer or the like, various elements of the processing system 500 may be omitted. For example, in other aspects, multimedia processing unit 510, wireless connection component 512, sensor processing unit 516, ISP 518, and/or navigation component 520 may be omitted. Further, the elements of the processing system 500 may be distributed, such as training a model and using the model to generate inferences.

Example clauses

Specific implementation details of various aspects are described in the following numbered clauses.

Clause 1 is a method performed by a wireless device in a wireless communication network, the method comprising identifying a seed point in a signal constellation from a received signal, generating a set of candidate codes for the received signal based on the seed point and an additive perturbation applied to the seed point, identifying a point in the signal constellation corresponding to a value of the received signal based on a probability distribution generated on the set of candidate codes, wherein the identified point corresponds to a code in the set of candidate codes that has a highest probability in the probability distribution, and outputting the point in the signal constellation as the value of the received signal.

Clause 2 the method of clause 1, wherein identifying the seed point comprises demapping the received signal based on a linear transformation.

Clause 3 the method of clause 2, wherein demapping the received signal comprises re-parameterizing a matrix representing a channel over which the received signal was received based on a lattice reduction using a single-mode matrix, and demapping the received signal based on the re-parameterized matrix and a symbol vector representing the received signal.

Clause 4 the method of any of clauses 1-3, wherein generating the set of candidate codes comprises selecting a point in the signal constellation that includes a point within a quadrilateral defined by the seed point as a center point of the quadrilateral.

Clause 5 the method of any of clauses 1 to 4, wherein generating the set of candidate codes comprises selecting points in the signal constellation as a uniform distribution within a circle, the circle being defined based on a radius from the seed point.

Clause 6 the method of any of clauses 1 to 5, wherein generating the set of candidate codes comprises selecting points in the signal constellation as a uniform distribution within an ellipse defined by the seed point as a center point of the ellipse.

Clause 7 the method of any of clauses 1 to 6, wherein generating the set of candidate codes comprises selecting points in the signal constellation based on a gaussian distribution calculated from a density function.

Clause 8 the method of clause 7, wherein the parameters of the gaussian distribution comprise parameters identified based on bayesian optimization.

Clause 9 the method of any of clauses 1 to 8, wherein identifying the point in the signal constellation corresponding to the value of the received signal comprises calculating a log likelihood ratio over the set of candidate codes.

Clause 10 the method of clause 9, wherein the log-likelihood ratio is calculated based on clipping to a maximum value associated with a signal-to-noise ratio of the received signal.

Clause 11 the method of clause 10, further comprising retrieving the maximum value from a look-up table keyed by a signal to noise value.

Clause 12 the method of clause 10 or 11, further comprising identifying the maximum value based on bayesian optimization.

Clause 13 the method of any of clauses 1 to 12, further comprising performing communication in the wireless communication network based on the point in the signal constellation.

The method of any of clauses 1 to 13, wherein the wireless communication network is a 5G network.

Clause 15 the method of clause 13 or 14, wherein the communication comprises a voice communication in the wireless communication network.

Clause 16 the method of any of clauses 13 to 15, wherein the communication comprises a data communication in the wireless communication network.

Clause 17, the method of any of clauses 1 to 16, wherein outputting the point comprises outputting the point for processing with one or more other points from one or more other signals in a forward error correction component of the wireless transceiver.

Clause 18, a processing system comprising a memory comprising computer-executable instructions, and one or more processors configured to execute the computer-executable instructions and cause the processing system to perform the method according to any of clauses 1-17.

Clause 19 is a processing system comprising means for performing the method according to any of clauses 1 to 17.

Clause 20 is a non-transitory computer-readable medium comprising computer-executable instructions that, when executed by one or more processors of a processing system, cause the processing system to perform the method of any of clauses 1-17.

Clause 21 is a computer program product embodied on a computer readable storage medium, the computer program product comprising code for performing the method according to any of clauses 1 to 17.

Additional notes

The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. The examples discussed herein are not limited in scope, applicability, or aspects to the extent set forth in the claims. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. For example, changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure. Various examples may omit, replace, or add various procedures or components as appropriate. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with respect to some examples may be combined in some other examples. For example, an apparatus may be implemented or a method practiced using any number of the aspects set forth herein. In addition, the scope of the present disclosure is intended to cover such an apparatus or method practiced using other structure, functionality, or both in addition to or other than the various aspects of the present disclosure set forth herein. It should be understood that any aspect of the disclosure disclosed herein may be embodied by one or more elements of the claims.

As used herein, the phrase "exemplary" means "serving as an example, instance, or illustration. Any aspect described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects.

As used herein, a phrase referring to "at least one of a list of items" refers to any combination of these items (which includes a single member). By way of example, at least one of "a, b, or c" is intended to cover a, b, c, a-b, a-c, b-c, and a-b-c, as well as any combination having multiple identical elements (e.g., a-a-a, a-a-b, a-a-c, a-b-b, a-c-c, b-b-b, b-b-c, c-c, and c-c-c, or any other ordering of a, b, and c).

As used herein, the term "determining" encompasses a wide variety of actions. For example, "determining" may include calculating, computing, processing, deriving, researching, looking up (e.g., looking up in a table, database, or other data structure), ascertaining, and the like. Further, "determining" may include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), and so forth. Further, "determining" may include parsing, selecting, establishing, and the like.

The methods disclosed herein comprise one or more steps or actions for achieving the method. The steps and/or actions of the methods may be interchanged with one another without departing from the scope of the claims. In other words, unless a specific order of steps or actions is specified, the order and/or use of specific steps and/or actions may be modified without departing from the scope of the claims. Furthermore, the various operations of the methods described above may be performed by any suitable component capable of performing the corresponding functions. The component may include various hardware and/or software components and/or modules including, but not limited to, a circuit, an Application Specific Integrated Circuit (ASIC), or a processor. Generally, where there are operations illustrated in the figures, those operations may have corresponding parts plus functional components with similar numbers.

The following claims are not intended to be limited to the aspects shown herein but are to be accorded the full scope consistent with the language of the claims. Within the claims, reference to an element in the singular is not intended to mean "one and only one" unless explicitly so stated, but rather "one or more". The term "some" refers to one or more unless specifically stated otherwise. No claim element should be construed in accordance with the specification of 35u.s.c. ≡112 (f) unless the phrase "means for..once again" is used to express the element or, in the case of method claims, the phrase "step for..once again" is used to express the element. All structural and functional equivalents to the elements of the aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Furthermore, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims.

Claims

1. A method of wireless communication performed by a wireless device in a wireless communication network, the method comprising:

identifying a seed point in a signal constellation diagram from the received signal;

generating a set of candidate codes for the received signal based on a seed point and an additive perturbation applied to the seed point;

identifying a point in the signal constellation corresponding to a value of the received signal based on a probability distribution generated over the set of candidate codes, wherein the identified point corresponds to a code in the set of candidate codes having a highest probability in the probability distribution; and

The identified point in the signal constellation diagram is output as the value of the received signal.

2 . The method of claim 1 , wherein identifying the seed point comprises demapping the received signal based on a linear transformation.

3. The method of claim 2, wherein demapping the received signal comprises:

reparameterizing a matrix representing a channel over which the received signal was received based on a lattice reduction using a unimodular matrix; and

The received signal is demapped based on the reparameterized matrix and a symbol vector representing the received signal.

4. The method of claim 1, wherein generating the set of candidate codes comprises selecting a point in the signal constellation diagram that includes a point within a quadrilateral defined with the seed point as a center point of the quadrilateral.

5. The method of claim 1, wherein generating the set of candidate codes comprises selecting points in the signal constellation as a uniform distribution within a circle, the circle being defined based on a radius from the seed point.

6. The method of claim 1, wherein generating the set of candidate codes comprises selecting points in the signal constellation diagram as a uniform distribution within an ellipse, the ellipse being defined with the seed point as a center point of the ellipse.

7. The method of claim 1, wherein generating the set of candidate codes comprises selecting points in the signal constellation based on a Gaussian distribution calculated from a density function.

The method of claim 7 , wherein the parameters of the Gaussian distribution include parameters identified based on Bayesian optimization.

9. The method of claim 1, wherein identifying the point in the signal constellation diagram corresponding to the value of the received signal comprises computing a log-likelihood ratio over the set of candidate codes.

10. The method of claim 9, wherein the log likelihood ratio is calculated based on clipping to a maximum value associated with a signal-to-noise ratio of the received signal.

11. The method of claim 10, further comprising retrieving the maximum value from a lookup table keyed by a signal-to-noise ratio value.

12. The method of claim 10, further comprising identifying the maximum value based on Bayesian optimization.

13. The method of claim 1, further comprising performing communications in the wireless communication network based on the identified points in the signal constellation diagram.

14. The method of claim 1, wherein the wireless communication network is a 5G network.

15. The method of claim 1, wherein outputting the identified point comprises outputting the identified point for processing in a forward error correction component of a wireless transceiver along with one or more other points from one or more other signals.

16. A processing system, the processing system comprising:

a memory having computer-executable instructions stored thereon; and

a processor configured to execute the computer executable instructions to cause the processing system to:

17. The processing system of claim 16, wherein to identify the seed point, the processor is configured to cause the processing system to demap the received signal based on a linear transformation.

18. The processing system of claim 17, wherein to demap the received signal, the processor is configured to cause the processing system to:

19. The processing system of claim 16, wherein to generate the set of candidate codes, the processor is configured to cause the processing system to select a point in the signal constellation diagram that includes a point within a quadrilateral, the quadrilateral being defined with the seed point as a center point of the quadrilateral.

20. The processing system of claim 16, wherein to generate the set of candidate codes, the processor is configured to cause the processing system to select points in the signal constellation as a uniform distribution within a circle, the circle being defined based on a radius from the seed point.

21. The processing system of claim 16, wherein to generate the set of candidate codes, the processor is configured to cause the processing system to select points in the signal constellation diagram as a uniform distribution within an ellipse, the ellipse being defined with the seed point as a center point of the ellipse.

22. The processing system of claim 16, wherein to generate the set of candidate codes, the processor is configured to cause the processing system to select points in the signal constellation based on a Gaussian distribution calculated from a density function.

23. The processing system of claim 22, wherein the parameters of the Gaussian distribution include parameters identified based on Bayesian optimization.

24. The processing system of claim 16, wherein to identify the point in the signal constellation diagram corresponding to the value of the received signal, the processor is configured to cause the processing system to calculate a log-likelihood ratio over the set of candidate codes.

25. The processing system of claim 24, wherein the log likelihood ratio is calculated based on clipping to a maximum value associated with a signal-to-noise ratio of the received signal.

26. The processing system of claim 25, wherein the processor is further configured to cause the processing system to retrieve the maximum value from a lookup table keyed by a signal-to-noise ratio value.

27. The processing system of claim 16, wherein the processor is further configured to cause the processing system to perform communications in a wireless communication network based on the identified points in the signal constellation diagram.

28. The processing system of claim 16, wherein to output the identified point, the processor is configured to cause the processing system to output the identified point for processing in a forward error correction component of a wireless transceiver along with one or more other points from one or more other signals.

29. A processing system for wireless communication, the processing system comprising:

means for identifying a seed point in a signal constellation diagram from a received signal;

means for generating a set of candidate codes for the received signal based on a seed point and an additive perturbation applied to the seed point;

means for identifying a point in the signal constellation corresponding to a value of the received signal based on a probability distribution generated over the set of candidate codes, wherein the identified point corresponds to a code in the set of candidate codes having a highest probability in the probability distribution; and

Means for outputting said identified point in said signal constellation as said value of said received signal.

30. A non-transitory computer readable medium comprising: computer executable instructions that, when executed by one or more processors of a processing system, cause the processing system to perform operations comprising: