A PAPR suppression method based on pulse shaping modulation

Abstract

The present invention provides a PAPR suppression method based on pulse shaping modulation, belonging to the field of communications. The method comprises: establishing an end-to-end OFDM communication system model, comprising a transmitter, a channel, and a receiver; the PS module at the transmitting end is implemented by a transmitting DNN, which comprises a transmitting input layer connected to an S / P module and a transmitting output layer; the channel is a multipath fading channel; the receiver comprises an equalization module and a demodulation mapping module connected in sequence; and step S2, jointly training the neural network composed of the transmitter, channel, and receiver using a joint loss function L = α1L1 + α2L2. The present invention can reduce the PAPR at the transmitting end without affecting the transmission rate and bit error rate, and enables flexible configuration of pulse shaping to flexibly support different communication scenarios.

Description

Technical Field

[0001] The present invention relates to the field of communications, and in particular to a PAPR suppression method based on pulse shaping modulation. Background Art

[0002] Orthogonal Frequency Division Multiplexing (OFDM) technology plays a key role in fifth-generation mobile communication systems due to its robustness in multipath transmission and relatively low transceiver design complexity. However, as a multi-carrier modulation technology, OFDM superimposes multiple orthogonal subcarriers, which causes the envelope of the base station's transmitted signal to have large dynamic fluctuations, resulting in a high peak-to-average power ratio. High peak-to-average power ratio signals typically need to be transmitted through linear power amplifiers. However, linear power amplifiers are very expensive and have higher process requirements, which results in high hardware costs. If high peak-to-average power ratio signals are passed through nonlinear power amplifiers, severe nonlinear distortion will be generated, which will cause signal distortion and lead to a serious deterioration in system performance. J. Tellado's tone reservation (TR) technique can be used to reduce the peak-to-average power ratio (PAPR) of each antenna, but its PAPR suppression is not effective and significantly reduces data transmission rates. Jeon HB's selective mapping method improves PAPR suppression, but because each signal group in the selective mapping method requires phase rotation, IFFT calculation, and PAPR calculation and comparison, the computational complexity is closely related to the number of candidate phases. A larger number of candidate phases increases the computational complexity. In practical applications, it is necessary to comprehensively consider the PAPR suppression performance and computational complexity of OFDM communication systems to achieve a balance between the two.

[0003] Therefore, there is an urgent need to find a communication system that can effectively reduce PAPR, control computational complexity, and avoid the defect of single pulse shape without sacrificing transmission rate. Summary of the Invention

[0004] The main purpose of the present invention is to propose a PAPR suppression method based on pulse shaping modulation, which reduces the PAPR of the transmitter without affecting the transmission rate and bit error rate, and can realize flexible configuration of pulse shaping to flexibly support different communication scenarios.

[0005] The present invention is achieved through the following technical solutions:

[0006] A PAPR suppression method based on pulse shaping modulation includes the following steps:

[0007] Step S1: Build an end-to-end OFDM communication system model, which includes a transmitter, a channel, and a receiver. The transmitter includes a constellation modulation module, an S / P module, and a transmitter PS module connected in sequence. The transmitter PS module is implemented by a transmitting DNN. The transmitting DNN includes a transmitting input layer connected to the S / P module and a transmitting output layer. The transmitting output layer is formed by N parallel PS filters. The transmitting PS module outputs a time domain transmission signal s i =(G tx ⊙F H )x i , s i is the main value sequence of the i-th time domain transmitted signal, x i represents the i-th frequency domain signal vector, is a stack of N PS filters corresponding to N subcarriers, F represents the Fourier transform matrix, (·) H represents conjugate transpose, ⊙ represents Hadamard product;

[0008] The channel is a multipath fading channel;

[0009] The receiver includes an equalization module and a demodulation mapping module connected in sequence. The equalization module performs FFT on the time domain received signal and the time domain channel obtained through the channel, and divides the two frequency domain information obtained by the FFT by corresponding points to obtain the equalized frequency domain information. The demodulation mapping module is implemented by a demodulation DNN. The demodulation DNN includes a demodulation input layer connected to the equalization module and a demodulation output layer. The demodulation output layer is composed of the Softmax outputs on N subcarriers to output the final demodulated bit value.

[0010] Step S2: Jointly train the neural network composed of the transmitter, channel, and receiver using the joint loss function L = α1L1 + α2L2, where α1 represents the ratio of the transmitter loss function and α2 represents the ratio of the receiver loss function. s(n) is s i The nth element of represents the probability of symbol demodulation on the kth subcarrier, and M is the modulation order, P k,1 ,...,P k,M Indicates the unique hot encoding used by the label, and its value range is {0, 1}, is the expected function.

[0011] Furthermore, the transmitting DNN also includes a transmitting hidden layer consisting of a layer of N neurons, a first Dropout layer, a layer of 2N neurons, a second Dropout layer, a layer of 2N neurons and a power normalization layer.

[0012] Furthermore, the demodulation DNN also includes a demodulation hidden layer consisting of a layer of 2N neurons, a layer of 4N neurons, a layer of 8N neurons and a layer of 2N neurons, and the first layer and the last layer of the demodulation hidden layer use jump connections.

[0013] Furthermore, the input data of the transmitting DNN and the demodulating DNN need to be preprocessed, and the preprocessing includes splitting the real and imaginary parts of each original data, sorting the real part of each original data to form a real data block, and sorting the imaginary part of each original data to form an imaginary data block.

[0014] Furthermore, in step S1, the transmitting end PS module obtains the signal s i =(G tx ⊙F H )x i Finally, a cyclic prefix is ​​added to the signal to combat frequency selective fading.

[0015] Furthermore, the neuron ratio parameter of the first Dropout layer and the second Dropout layer is set to 0.5.

[0016] Furthermore, the step S2 specifically includes:

[0017] Step S21, obtain 10 6 The group data is used as a dataset, the dataset is divided into a training set and a validation set, the joint loss function L = α1L1 + α2L2 is selected, and the hyperparameters are set;

[0018] Step S22: forward propagation training, calculating the joint loss function, and selecting an appropriate gradient descent algorithm to complete back propagation and parameter update until the training is completed;

[0019] Step S23: Calculate the loss curve and the accuracy fitting curve, and pay attention to the training time. If it does not converge, adjust the hyperparameters and return to step S21. If it converges, proceed to step S24.

[0020] Step S24, obtain 10 5 The group data is used as the test set, and the test set is input. The performance is tested by statistically analyzing the PAPR and BER in the test set.

[0021] Furthermore, in the joint loss function, α1:α2=0.01:3.

[0022] Furthermore, the multipath fading channel is expressed as Where τ represents the maximum delay path number, δ(·) represents the discrete impulse response, and a p is the complex baseband channel coefficient of the pth delay path, τ p represents the delay of the pth delay path.

[0023] From the above description of the present invention, it can be seen that compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. The transmitting DNN of the transmitter PS module of the present invention, the channel and the demodulation DNN of the receiving end constitute an encoder, and a sophisticated pulse shaping mechanism is introduced within the framework of the traditional OFDM system to optimize the transmission waveform and reduce the PAPR of the transmitted signal. The transmitting DNN and the demodulation DNN are jointly trained with a joint loss function to simultaneously achieve the purpose of suppressing the PAPR of the transmitted signal and preventing the deterioration of the system bit error rate. In this way, a balance is achieved between reducing the PAPR and controlling the computational complexity without affecting the transmission rate and bit error rate. In addition, flexible configuration of pulse shaping can be achieved to avoid the defect of a single pulse shape, so as to flexibly support different communication scenarios.

[0025] 2. The present invention preprocesses the input data of the transmitting DNN and the demodulating DNN, which can achieve better performance without affecting the transmission rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0027] Figure 1 It is a principle block diagram of the end-to-end OFDM communication system model of the present invention.

[0028] Figure 2 Schematic diagram of the PS filter of the present invention.

[0029] Figure 3 Schematic diagram of the structure of the launch DNN of the present invention.

[0030] Figure 4 Schematic diagram of data preprocessing of the present invention.

[0031] Figure 5 Schematic diagram before and after using the first dropout layer or the second dropout layer in the present invention.

[0032] Figure 6 This is a graph showing the loss function of the training set and the validation set during the training process of the present invention.

[0033] Figure 7 This is a comparison chart of PAPR performance between the present invention and the CP-OFDM system under different training hyperparameters when 16QAM modulation is adopted.

[0034] Figure 8 This is a comparison chart of the BER performance of the present invention and the CP-OFDM system under different training hyperparameters when using 16QAM modulation. DETAILED DESCRIPTION

[0035] The present invention is further described below through specific embodiments.

[0036] The PAPR suppression method based on pulse shaping modulation includes the following steps:

[0037] Step S1: Build Figure 1 The end-to-end OFDM communication system model shown in Figure 1 includes a transmitter, a channel, and a receiver. The transmitter's function is to convert the bit stream into an actual time-domain transmission signal, and includes a constellation modulation module, an S / P module, a transmitter PS (pulse shaping) module, and a CP module connected in sequence. The constellation modulation module maps the bit stream into a frequency-domain constellation symbol based on the selected modulation mode. When QPSK modulation is selected, the constellation modulation module converts continuous 2-bit information into a frequency-domain symbol. The frequency-domain symbol value range is {0.71+0.71j, 0.71-0.71j, -0.71+0.71j, -0.71-0.71j}. The S / P module is used to convert serial frequency-domain signals into parallel frequency-domain signals.

[0038] The transmitter PS module is used to adjust the power distribution of the transmitted signal in the time-frequency domain, thereby completing the optimization of PAPR. It is implemented by the transmit DNN. The transmit DNN includes a transmit input layer, a transmit hidden layer, and a transmit output layer connected to the output of the S / P module. The input of the transmit input layer is the OFDM time domain signal. The transmit output layer is formed by N parallel PS filters. The transmitter PS module outputs the time domain transmit signal. Where N is the number of subcarriers, X(k,i) is the frequency domain symbol corresponding to the i-th OFDM signal of the k-th subcarrier, and the PS filter corresponding to the i-th subcarrier at the transmitter is is the pulse shape at the transmitting end, T is the duration of the discrete time domain OFDM signal, and n represents the nth sampling point in the discrete time domain. In this embodiment, the length of the PS filter is limited to N, that is, T = N. The time domain transmission signal can be rewritten as a matrix form s i =(G tx ⊙F H )x i , s i is the main value sequence of the i-th time domain transmitted signal, x i represents the i-th frequency domain signal vector, is a stack of N PS filters corresponding to N subcarriers, F represents the Fourier transform matrix, (·) H represents the conjugate transpose, ⊙ represents the Hadamard product, such as Figure 2 Shown is the schematic diagram of the PS filter, Figure 2 middle, is the filter on the kth subcarrier The nth value of .

[0039] The PS module at the transmitting end receives the signal s i =(G tx ⊙F H )x i Finally, the CP module adds a cyclic prefix (CP) of corresponding length to the signal to combat frequency selective fading.

[0040] The structure of the launch DNN is as follows Figure 3 As shown in , the emission hidden layer consists of a layer of N neurons, a first Dropout layer, a layer of 2N neurons, a second Dropout layer, a layer of 2N neurons, and a power normalization layer. The neuron ratio parameter of the first Dropout layer and the second Dropout layer is set to 0.5, indicating that 50% of the neurons will be inactivated in this layer. There are no trainable parameters in the power normalization layer. Figure 5 Shown is a comparison diagram before and after using the Dropout layer.

[0041] The PS module on the transmitter side is actually designed to measure the phase value on a Poly-Phase Network (PPN). Data is input into the neural network to obtain the specific required phase value, which is then implemented by the PPN. This provides a method for digital design and analog device implementation.

[0042] The channel is a multipath fading channel, which is expressed as Where τ represents the maximum delay path number, δ(·) represents the discrete impulse response, and a p is the complex baseband channel coefficient of the pth delay path, τ p represents the delay of the pth delay path. The multipath fading channel can be viewed as a channel layer with no optimizable parameters. It has no internal trainable parameters and only realizes the conversion between the transmitted signal and the received signal.

[0043] For this channel, the conversion between the transmitted signal x and the received signal y can be expressed as: u =ΔHx u ++w u

[0044] Among them, x u Represents the time domain transmitted signal at the current moment, that is, the received signal y at the current moment u In general, due to the influence of multipath and CP, the received signal is the circular convolution of the channel vector and the transmitted signal.

[0045] The receiver does not perform pulse shaping optimization, so it processes the received signal after removing the CP, including a sequentially connected equalization module and a demodulation mapping module. The equalization module performs an N-point FFT on the time-domain received signal and the time-domain channel obtained through the channel. It then divides the two N-point frequency-domain information sequences obtained by the FFT to obtain the equalized frequency-domain information, which is input into the demodulation mapping module along with the frequency-domain channel information. The demodulation mapping module is implemented by a demodulation DNN, which includes a demodulation input layer connected to the equalization module, a demodulation hidden layer, and a demodulation output layer. The demodulation output layer is composed of the concatenation of the Softmax outputs on N subcarriers, with a dimension consistent with the number of information bits, to output the final demodulated bit value. The demodulation hidden layer consists of a layer of 2N neurons, a layer of 4N neurons, a layer of 8N neurons, and a layer of 2N neurons. The first and last layers of the demodulation hidden layer use skip connections to prevent gradient vanishing.

[0046] Step S2: Jointly train the neural network composed of the transmitter, channel, and receiver using the joint loss function L = α1L1 + α2L2, where α1 represents the ratio of the transmitter loss function and α2 represents the ratio of the receiver loss function. x(n) is s i The nth element of corresponds to the output of a Softmax classifier, which represents the probability of symbol demodulation on the kth subcarrier, and M is the modulation order, P k,1 ,...,P k,M Indicates the unique hot encoding used by the label. Since the output purpose is to directly restore the transmission bit quality, P k,1 ,...,P k,M The value range is {0, 1}, is the expected function;

[0047] The specific steps include:

[0048] Step S21, obtain 10 6 The group data is used as a dataset, and the dataset is divided into a training set and a validation set (split into training set and validation set according to 8:2). The labels and datasets are input, and the joint loss function L = α1L1 + α2L2 is selected. The hyperparameters are set as shown in Table 1:

[0049] Table 1

[0050] Hyperparameters illustrate N Number of subcarriers Drop_rate Dropout neuron ratio <![CDATA[α1]]> Transmitter loss function ratio <![CDATA[α2]]> Receiver loss function ratio lr Initial learning rate batch_size Mini-batch values dl Learning rate decay exponential

[0051] The neural network was built using TensorFlow 2.1 and Kreas 2.3.1. For the joint loss function L = α1L1 + α2L2, if α1 accounts for a large proportion, the neural network will focus more on improving the OFDM system's PAPR suppression capabilities during training; if α1 accounts for a small proportion, the neural network will focus more on reducing the system's bit error rate during training.

[0052] Step S22: forward propagation training, calculating the joint loss function, and selecting an appropriate gradient descent algorithm to complete back propagation and parameter update until the training is completed;

[0053] Specifically, the Adam optimization algorithm and small batch data processing method are used to complete the training of the autoencoder, with batch size = 1500 and initial learning rate lr = 0.001;

[0054] Step S23: Calculate the loss curve and the accuracy fitting curve, and pay attention to the training time. If it does not converge, adjust the hyperparameters and return to step S21. If it converges, proceed to step S24.

[0055] Specifically, a learning rate adjustment strategy is adopted in which the learning rate decays every 5 epochs, and the learning rate decay rate dl = 0.8;

[0056] Step S24, obtain 10 5 The group data is used as the test set, and the test set is input. The performance is tested by statistically analyzing the PAPR and BER in the test set.

[0057] In order to ensure the quality of data and prevent the loss of imaginary information and further improve the performance of neural networks, the input data of the transmitting DNN and the demodulating DNN need to be preprocessed, such as Figure 4 As shown, the preprocessing includes splitting the real part and the imaginary part of each original data, sorting and combining the real part of each original data to form a real part data block, and sorting and combining the imaginary part of each original data to form an imaginary part data block.

[0058] Figure 6 This is the loss function curve when α1=0.1, α2=10. Figure 5 The figure visually depicts the changing trends of the loss functions for the training and validation sets during training. This curve shows that the neural network's performance on the training and validation sets is nearly identical, demonstrating its excellent stability and reliability when predicting unknown data. This means that the knowledge learned by the neural network on the training set also applies to the validation set, demonstrating its excellent generalization capabilities.

[0059] Figure 7 and Figure 8The performance of the neural network changes under different loss function weight ratios α1:α2: When α1 accounts for a small proportion, the neural network focuses more on improving the system's bit error rate performance; when α1 accounts for a large proportion, the neural network focuses more on improving the system's PAPR suppression capability. Based on the above data, the present invention finally chooses to complete the training of the neural network when the loss function weight ratio is α1:α2=0.01:3, and obtains the phase value required to achieve the PPN of the analog device. It can be seen that the PAPR suppression capability of the system at this time is relatively good compared to the CP-OFDM system ( Figure 7 and Figure 8 The curve corresponding to the “original signal” in the figure shows a significant improvement, and there is no significant loss in BER performance, and it does not affect the transmission rate of the system. Figure 7 The vertical axis is the complementary cumulative distribution function (CCDF), which is used to represent the statistical characteristics of the peak-to-average PAPR in the OFDM system.

[0060] In the present invention, the terms "first", "second", "third", etc. are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. In the description, the directions or positional relationships indicated by "upper", "lower", "left", "right", "front", and "back" are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention, and are not intended to indicate or imply that the device referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the scope of protection of the present invention. For those skilled in the art, the specific meanings of the above terms in this application can be understood according to the specific circumstances.

[0061] In this application, unless otherwise specified, "plurality" refers to two or more. "And / or" describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0062] The above is only a specific implementation of the present invention, but the design concept of the present invention is not limited to this. Any non-substantial changes to the present invention using this concept shall be deemed as an infringement of the protection scope of the present invention.

Claims

1. A PAPR suppression method based on pulse shaping modulation, characterized by: The steps include: Step S1: Build an end-to-end OFDM communication system model, which includes a transmitter, a channel, and a receiver. The transmitter includes a constellation modulation module, an S / P module, and a transmitter PS module connected in sequence. The transmitter PS module is implemented by a transmitting DNN. The transmitting DNN includes a transmitting input layer connected to the S / P module and a transmitting output layer. The transmitting output layer is formed by N parallel PS filters. The transmitting PS module outputs a time domain transmission signal s i =(G tx ⊙F H )x i , s i is the main value sequence of the i-th time domain transmitted signal, x i represents the i-th frequency domain signal vector, is a stack of N PS filters corresponding to N subcarriers, F represents the Fourier transform matrix, (·) H represents conjugate transpose, ⊙ represents Hadamard product; The channel is a multipath fading channel; The receiver includes an equalization module and a demodulation mapping module connected in sequence. The equalization module performs FFT on the time domain received signal and the time domain channel obtained through the channel, and divides the two frequency domain information obtained by the FFT by corresponding points to obtain the equalized frequency domain information. The demodulation mapping module is implemented by a demodulation DNN. The demodulation DNN includes a demodulation input layer connected to the equalization module and a demodulation output layer. The demodulation output layer is composed of the Softmax outputs on N subcarriers to output the final demodulated bit value. Step S2: Jointly train the neural network composed of the transmitter, channel, and receiver using the joint loss function L = α1L1 + α2L2, where α1 represents the ratio of the transmitter loss function and α2 represents the ratio of the receiver loss function. s(n) is s i The nth element of represents the probability of symbol demodulation on the kth subcarrier, and M is the modulation order, P k,1 ,...,P k,M Indicates the unique hot encoding used by the label, and its value range is {0, 1}, is the expected function.

2. The PAPR suppression method based on pulse shaping modulation according to claim 1, characterized in that: The transmitting DNN also includes a transmitting hidden layer consisting of a layer of N neurons, a first Dropout layer, a layer of 2N neurons, a second Dropout layer, a layer of 2N neurons and a power normalization layer.

3. The PAPR suppression method based on pulse shaping modulation according to claim 2, characterized in that: The demodulation DNN further includes a demodulation hidden layer consisting of a layer of 2N neurons, a layer of 4N neurons, a layer of 8N neurons and a layer of 2N neurons, and the first layer and the last layer of the demodulation hidden layer use skip connections.

4. The PAPR suppression method based on pulse shaping modulation according to claim 1, 2 or 3, characterized in that: The input data of the transmitting DNN and the demodulating DNN need to be preprocessed, which includes splitting the real and imaginary parts of each original data, sorting the real part of each original data to form a real data block, and sorting the imaginary part of each original data to form an imaginary data block.

5. The PAPR suppression method based on pulse shaping modulation according to claim 1, 2 or 3, characterized in that: In step S1, the transmitting end PS module obtains the signal s i =(G tx ⊙F H )x i Finally, a cyclic prefix is ​​added to the signal to combat frequency selective fading.

6. A PAPR suppression method based on pulse shaping modulation according to claim 2 or 3, characterized in that: The neuron ratio parameter of the first Dropout layer and the second Dropout layer is set to 0.

5.

7. The PAPR suppression method based on pulse shaping modulation according to claim 1, 2 or 3, characterized in that: The step S2 specifically includes: Step S21, obtain 10 6 The group data is used as a dataset, the dataset is divided into a training set and a validation set, the joint loss function L = α1L1 + α2L2 is selected, and the hyperparameters are set; Step S22: forward propagation training, calculating the joint loss function, and selecting an appropriate gradient descent algorithm to complete back propagation and parameter update until the training is completed; Step S23: Calculate the loss curve and the accuracy fitting curve, and pay attention to the training time. If it does not converge, adjust the hyperparameters and return to step S21. If it converges, proceed to step S24. Step S24, obtain 10 5 The group data is used as the test set, and the test set is input. The performance is tested by statistically analyzing the PAPR and BER in the test set.

8. The PAPR suppression method based on pulse shaping modulation according to claim 6, characterized in that: In the joint loss function, α1:α2=0.01:

3.

9. The PAPR suppression method based on pulse shaping modulation according to claim 1, 2 or 3, characterized in that: The multipath fading channel is expressed as Where τ represents the maximum delay path number, δ(·) represents the discrete impulse response, and a p is the complex baseband channel coefficient of the pth delay path, τ p represents the delay of the pth delay path.

Images