CN115208731B - Method and device for suppressing peak-to-average power ratio (PAPR) of signal - Google Patents
Method and device for suppressing peak-to-average power ratio (PAPR) of signal Download PDFInfo
- Publication number
- CN115208731B CN115208731B CN202210831928.9A CN202210831928A CN115208731B CN 115208731 B CN115208731 B CN 115208731B CN 202210831928 A CN202210831928 A CN 202210831928A CN 115208731 B CN115208731 B CN 115208731B
- Authority
- CN
- China
- Prior art keywords
- net
- signal
- equal
- papr
- receiving end
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/26—Systems using multi-frequency codes
- H04L27/2601—Multicarrier modulation systems
- H04L27/2614—Peak power aspects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Digital Transmission Methods That Use Modulated Carrier Waves (AREA)
Abstract
The invention relates to the technical field of wireless communication, in particular to a PAPR (peak to average power ratio) suppression method and device for signals. The method comprises the following steps: inputting modulated OFDM transmission signals; the OFDM system with improved DM-Net is used for carrying out adaptive constellation mapping and demapping on the transmission signal to reduce the peak-to-average power ratio, wherein the adaptive constellation mapping refers to that according to PAPR performance, the DM-Net can automatically adjust the position of signal constellation points, the DM-Net is a network structure based on deep learning and comprises M-Net of a transmitting end and D-Net of a receiving end, the M-Net of the transmitting end changes constellation point distribution of the transmission signal through adjustment of the transmission signal on a frequency domain constellation, the purpose that a time domain signal sent by the transmitting end of the system has a lower PAPR value is achieved, and the D-Net of the receiving end is responsible for recovering the signal after the signal is subjected to channel into the original transmitted frequency domain signal, so that the purpose of guaranteeing the overall error rate performance of the system is achieved. By adopting the invention, the effective balance of the error rate performance and the PAPR performance is realized, and the invention has lower complexity.
Description
Technical Field
The invention relates to the technical field of wireless communication, in particular to a PAPR (peak to average power ratio) suppression method and device for signals.
Background
The orthogonal frequency division multiplexing (Orthogonal Frequency Division Multiple, OFDM) has the characteristics of high spectrum utilization rate, strong multipath fading resistance, strong intersymbol interference resistance and the like, and plays an important role in 5G. Peak-to-average power ratio (Peak to Average Power Ratio, PAPR) is one of the main technical bottlenecks of OFDM systems, and excessive peak-to-average power ratio may cause the radio frequency power amplifier to operate in a nonlinear region, resulting in nonlinear distortion of signals and a sharp increase in power consumption. The existing peak-to-average power ratio suppression method of the OFDM system still has the problems that PAPR performance and Bit Error Rate (BER) performance cannot be effectively balanced, complexity is high, spectrum utilization Rate is low and the like.
Disclosure of Invention
The invention mainly aims to provide a method and a device for suppressing peak-to-average power ratio (PAPR) of a signal so as to solve the problems existing in the prior art.
In order to achieve the above object, the present invention provides a method for suppressing a signal peak-to-average power ratio, including:
inputting modulated OFDM transmission signals;
the OFDM system with improved DM-Net is used for carrying out adaptive constellation mapping and demapping on the transmission signal to reduce the peak-to-average power ratio, wherein the adaptive constellation mapping refers to that according to PAPR performance, the DM-Net can automatically adjust the position of signal constellation points, the DM-Net is a network structure based on deep learning and comprises M-Net of a transmitting end and D-Net of a receiving end, the M-Net of the transmitting end changes constellation point distribution of the transmission signal through adjustment of the transmission signal on a frequency domain constellation, the purpose that a time domain signal sent by the transmitting end of the system has a lower PAPR value is achieved, and the D-Net of the receiving end is responsible for recovering the signal after the signal is subjected to channel into the original transmitted frequency domain signal, so that the purpose of guaranteeing the overall error rate performance of the system is achieved.
Optionally, the adaptive constellation mapping and demapping of the transmission signal by the DM-Net improved OFDM system to reduce the peak-to-average power ratio specifically includes:
let the number of sub-carriers of the system be N, the transmitted modulation signal be X= [ X ] 0 ,X 1 ,...,X N-2 ,X N-1 ]X is represented as X K ＝[X R (K)X I (K)]Wherein X is R (K) Represents X K The real part of X I (K) Represents X K K is more than or equal to 0 and less than or equal to N-1, and the input signal X is input at the transmitting end through M-Net K Constellation mapping is carried out, and the mapping relation is T K ＝f(X K ) Which is provided withWherein f (·) represents a mapping function, T K Represents the signal after constellation mapping, K is more than or equal to 0 and less than or equal to N-1,
the expression of the mapping relation function is:
f(X)＝tanh(tanh(conv (tanh(conv(X,W conv1 )+b conv1 ),W conv2 )+b conv2 )*W f +b f ) (1)
wherein W is conv1 ，b conv1 Weight matrix and bias matrix respectively representing the first convolution layer, W conv2 ，b conv2 Weight matrix and bias matrix respectively representing the second convolution layer, W f And b f Respectively representing a weight matrix and a bias matrix of the full connection layer, wherein the tanh function is an activation function utilized by the two convolution layers and the full connection layer;
combining the real part and the imaginary part in T into a complex vector form, and then oversampling the T, wherein the oversampling multiple is L, and the oversampled signal is T L And then obtaining a time domain transmission signal through Inverse Fast Fourier Transform (IFFT):
wherein n is more than or equal to 0 and less than or equal to LN-1, K is more than or equal to 0 and less than or equal to LN-1, and the PAPR calculation formula of the time domain signal is as follows:
wherein max [ |x (n) | 2 ]Representing the maximum power of the signal, E [ |x (n) | 2 ]Represents the average value of signal power, n is more than or equal to 0 and less than or equal to LN-1;
after the transmission signal is subjected to M-Net adaptive constellation mapping, the distribution of signal constellation points ensures that the time domain signal transmitted by a system transmitting end has a lower PAPR value;
the time domain transmission signal reaches the receiving end after passing through the channel, the signal received by the receiving end is r (n), n is more than or equal to 0 and less than or equal to LN-1, fast Fourier transform FFT is carried out to obtain a frequency domain signal, and the frequency domain signal is processedDownsampling the line to obtain R K K is more than or equal to 0 and less than or equal to N-1, R is K Splitting, R K ＝[R R (K)R I (K)]Wherein R is R (K) Represents R K The real part of R I (K) Represents R K Then the received signal is demapped through the D-Net of the receiving end, the mapping relation is thatWherein->Representing the demapping relation function to obtain the final signal +.>
The expression of the demapping relationship function is:
wherein Q is conv1 ，U conv1 A weight matrix and a bias matrix, Q, representing the first convolution layer, respectively conv2 ，U conv2 Respectively representing a weight matrix and a bias matrix of a second convolution layer, Q f And U f Representing the weight matrix and the bias matrix of the fully connected layer, respectively, the tanh function is the activation function utilized by the two convolutional layers and the fully connected layer.
Optionally, the method further comprises: the system bit error rate BER performance and PAPR performance are considered by adjusting the network architecture of the M-Net and the D-Net and training related parameters, and the specific training process comprises the following steps:
firstly, the PAPR performance of the time domain signal of the transmitting end is not considered, the system loss function only comprises the error rate, and the error rate is the signal X transmitted by the transmitting end and the signal recovered by the receiving endCo-determination, and signal recovered at the receiving end +.>The method is jointly determined by M-Net and D-Net, namely, the value of a system loss function is related to the M-Net and the D-Net, in the training process of an OFDM system improved by DM-Net, the system obtains the optimal error rate performance under the condition of a Gaussian white noise channel or a Rayleigh fading channel by adjusting the architecture of the M-Net and the D-Net and continuously iterating parameters of an M-Net model and a D-Net model by utilizing an optimization algorithm so as to reduce the value of the system loss function, namely, the system is subjected to joint optimization of the M-Net of a transmitting end and the D-Net of a receiving end;
secondly, based on the structure and parameters of the DM-Net trained in the first step, PAPR items are added in a system loss function, the M-Net of a transmitting end and the D-Net of a receiving end are jointly trained again, and meanwhile, through proper selection of weight factors, the error rate performance and the required PAPR performance of the system can be ensured under the condition of Gaussian white noise channels or Rayleigh fading channels.
Optionally, the optimal network architecture of the M-Net and the optimal network parameters of the D-Det are obtained through final training, the M-Net and the D-Det comprise two convolution layers and a full connection layer, the convolution kernels of the first convolution layer and the second convolution layer are 3 multiplied by 3, the number of the convolution kernels is 5, the number of nodes of the full connection layer is 512, and the activation functions of the convolution layers and the full connection layer are tanh functions.
Optionally, in the joint training process of the transmitting end M-Det and the receiving end D-Net, an optimization algorithm is adopted to continuously iterate model parameters to reduce the value of a model loss function, wherein the optimization algorithm comprises, but is not limited to, a gradient descent method, an Adam algorithm and an RMSProp algorithm.
The invention also provides a PAPR suppression device for the signal peak-to-average power ratio, which comprises the following steps:
an input unit for inputting the modulated OFDM transmission signal;
the processing unit is used for reducing peak-to-average power ratio by carrying out adaptive constellation mapping and demapping on the transmission signal through an OFDM system with improved DM-Net, wherein the adaptive constellation mapping refers to that according to PAPR performance, DM-Net can automatically adjust the position of signal constellation points, the DM-Net is a network structure based on deep learning and comprises an M-Net part of a transmitting end and a D-Net part of a receiving end, the M-Net part of the transmitting end changes constellation point distribution of the transmission signal through adjustment of the transmission signal on a frequency domain constellation, the purpose that a time domain signal transmitted by the transmitting end of the system has a lower PAPR value is achieved, and the D-Net part of the receiving end is responsible for recovering the signal after the signal is transmitted into the original frequency domain signal, so that the purpose of ensuring the overall error rate performance of the system is achieved.
Optionally, the processing unit is specifically configured to:
let the number of sub-carriers of the system be N, the transmitted modulation signal be X= [ X ] 0 ,X 1 ,...,X N-2 ,X N-1 ]X is represented as X K ＝[X R (K)X I (K)]Wherein X is R (K) Represents X K The real part of X I (K) Represents X K K is more than or equal to 0 and less than or equal to N-1, and the input signal X is input at the transmitting end through M-Net K Constellation mapping is carried out, and the mapping relation is T K ＝f(X K ) Wherein f (·) represents a mapping function, T K Represents the signal after constellation mapping, K is more than or equal to 0 and less than or equal to N-1,
the expression of the mapping relation function is:
f(X)＝tanh(tanh(conv (tanh(conv(X,W conv1 )+b conv1 ),W conv2 )+b conv2 )*W f +b f ) (1)
wherein W is conv1 ，b conv1 Weight matrix and bias matrix respectively representing the first convolution layer, W conv2 ，b conv2 Weight matrix and bias matrix respectively representing the second convolution layer, W f And b f Respectively representing a weight matrix and a bias matrix of the full connection layer, wherein the tanh function is an activation function utilized by the two convolution layers and the full connection layer;
combining the real part and the imaginary part in T into a complex vector form, and then oversampling the T, wherein the oversampling multiple is L, and the oversampled signal is T L And then obtaining a time domain transmission signal through Inverse Fast Fourier Transform (IFFT):
wherein n is more than or equal to 0 and less than or equal to LN-1, K is more than or equal to 0 and less than or equal to LN-1, and the PAPR calculation formula of the time domain signal is as follows:
wherein max [ |x (n) | 2 ]Representing the maximum power of the signal, E [ |x (n) | 2 ]Represents the average value of signal power, n is more than or equal to 0 and less than or equal to LN-1;
after the transmission signal is subjected to M-Net adaptive constellation mapping, the distribution of signal constellation points ensures that the time domain signal transmitted by a system transmitting end has a lower PAPR value;
the time domain transmission signal reaches the receiving end after passing through the channel, the signal received by the receiving end is set as R (n), n is more than or equal to 0 and less than or equal to LN-1, fast Fourier transform FFT is carried out to obtain a frequency domain signal, and downsampling is carried out on the frequency domain signal to obtain R K K is more than or equal to 0 and less than or equal to N-1, R is K Splitting, R K ＝[R R (K) R I (K)]Wherein R is R (K) Represents R K The real part of R I (K) Represents R K Then the received signal is demapped through the D-Net of the receiving end, the mapping relation is thatWherein->Representing the demapping relation function to obtain the final signal +.>
The expression of the demapping relationship function is:
wherein Q is conv1 ，U conv1 A weight matrix and a bias matrix, Q, representing the first convolution layer, respectively conv2 ，U conv2 Respectively representing a weight matrix and a bias matrix of a second convolution layer, Q f And U f Representing the weight matrix and the bias matrix of the fully connected layer, respectively, the tanh function is the activation function utilized by the two convolutional layers and the fully connected layer.
Optionally, the apparatus further comprises: a training unit for realizing the combination of the BER performance and the PAPR performance of the system through the adjustment of the network architecture of the M-Net and the D-Net and the training of related parameters,
the training unit is specifically configured to:
firstly, the PAPR performance of the time domain signal of the transmitting end is not considered, the system loss function only comprises the error rate, and the error rate is the signal X transmitted by the transmitting end and the signal recovered by the receiving endCo-determination, and signal recovered at the receiving end +.>The method is jointly determined by M-Net and D-Net, namely, the value of a system loss function is related to the M-Net and the D-Net, in the training process of an OFDM system improved by DM-Net, the system obtains the optimal error rate performance under the condition of a Gaussian white noise channel or a Rayleigh fading channel by adjusting the architecture of the M-Net and the D-Net and continuously iterating parameters of an M-Net model and a D-Net model by utilizing an optimization algorithm so as to reduce the value of the system loss function, namely, the system is subjected to joint optimization of the M-Net of a transmitting end and the D-Net of a receiving end;
secondly, based on the structure and parameters of the DM-Net trained in the first step, PAPR items are added in a system loss function, the M-Net of a transmitting end and the D-Net of a receiving end are jointly trained again, and meanwhile, through proper selection of weight factors, the error rate performance and the required PAPR performance of the system can be ensured under the condition of Gaussian white noise channels or Rayleigh fading channels.
Optionally, the optimal network architecture of the M-Net and the optimal network parameters of the D-Det are obtained through final training, the M-Net and the D-Det comprise two convolution layers and a full connection layer, the convolution kernels of the first convolution layer and the second convolution layer are 3 multiplied by 3, the number of the convolution kernels is 5, the number of nodes of the full connection layer is 512, and the activation functions of the convolution layers and the full connection layer are tanh functions.
Optionally, the training unit is further configured to continuously iterate model parameters to reduce a value of a model loss function by using an optimization algorithm in a joint training process of the transmitting end M-Det and the receiving end D-Net, where the optimization algorithm includes, but is not limited to, a gradient descent method, an Adam algorithm, and an RMSProp algorithm.
The beneficial effects of the invention at least comprise: an effective balance of bit error rate performance and PAPR performance is achieved with lower complexity.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for suppressing a PAPR of a signal according to an embodiment of the present invention;
FIG. 2 shows a schematic diagram of a DM-Net improved OFDM system in accordance with an embodiment of the present invention;
FIG. 3 shows a schematic diagram of a DM-Net neural network according to an embodiment of the invention;
fig. 4 shows a schematic diagram of PAPR performance of a system according to an embodiment of the invention;
FIG. 5 is a schematic diagram of system error rates according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a PAPR suppressing device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following describes specific embodiments of the present invention in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
As shown in fig. 1, a method for suppressing a peak-to-average power ratio PAPR of a signal according to an embodiment of the present invention includes:
s1, inputting a modulated OFDM transmission signal;
s2, carrying out adaptive constellation mapping and demapping on the transmission signal through an OFDM system improved by a DM-Net to reduce the peak-to-average power ratio, wherein the adaptive constellation mapping refers to that according to PAPR performance, the DM-Net can automatically adjust the position of a signal constellation point, the DM-Net is a network structure based on deep learning and comprises an M-Net part of a transmitting end and a D-Net part of a receiving end, the M-Net part of the transmitting end changes constellation point distribution of the transmission signal through adjustment of the transmission signal on a frequency domain constellation, the purpose that a time domain signal transmitted by the transmitting end of the system has a lower PAPR value is achieved, and the D-Net part of the receiving end is responsible for recovering the signal after the channel into the original transmitted frequency domain signal, so that the purpose of guaranteeing the overall error rate performance of the system is achieved.
Optionally, the adaptive constellation mapping and demapping of the transmission signal by the DM-Net improved OFDM system to reduce the peak-to-average power ratio specifically includes:
let the number of sub-carriers of the system be N, the transmitted modulation signal be X= [ X ] 0 ,X 1 ,...,X N-2 ,X N-1 ]X is represented as X K ＝[X R (K)X I (K)]Wherein X is R (K) Represents X K The real part of X I (K) Represents X K K is more than or equal to 0 and less than or equal to N-1, and the input signal X is input at the transmitting end through M-Net K Constellation mapping is carried out, and the mapping relation is T K ＝f(X K ) Wherein f (·) represents a mapping function，T K Represents the signal after constellation mapping, K is more than or equal to 0 and less than or equal to N-1,
the expression of the mapping relation function is:
f(X)＝tanh(tanh(conv (tanh(conv(X,W conv1 )+b conv1 ),W conv2 )+b conv2 )*W f +b f ) (1)
wherein W is conv1 ，b conv1 Weight matrix and bias matrix respectively representing the first convolution layer, W conv2 ，b conv2 Weight matrix and bias matrix respectively representing the second convolution layer, W f And b f Respectively representing a weight matrix and a bias matrix of the full connection layer, wherein the tanh function is an activation function utilized by the two convolution layers and the full connection layer;
combining the real part and the imaginary part in T into a complex vector form, and then oversampling the T, wherein the oversampling multiple is L, and the oversampled signal is T L And then obtaining a time domain transmission signal through Inverse Fast Fourier Transform (IFFT):
wherein n is more than or equal to 0 and less than or equal to LN-1, K is more than or equal to 0 and less than or equal to LN-1, and the PAPR calculation formula of the time domain signal is as follows:
wherein max [ |x (n) | 2 ]Representing the maximum power of the signal, E [ |x (n) | 2 ]Represents the average value of signal power, n is more than or equal to 0 and less than or equal to LN-1;
after the transmission signal is subjected to M-Net adaptive constellation mapping, the distribution of signal constellation points ensures that the time domain signal transmitted by a system transmitting end has a lower PAPR value;
the time domain transmission signal reaches the receiving end after passing through the channel, the signal received by the receiving end is set as R (n), n is more than or equal to 0 and less than or equal to LN-1, fast Fourier transform FFT is carried out to obtain a frequency domain signal, and downsampling is carried out on the frequency domain signal to obtain R K K is more than or equal to 0 and less than or equal to N-1, R is K Splitting, R K ＝[R R (K)R I (K)]Wherein R is R (K) Represents R K The real part of R I (K) Represents R K Then the received signal is demapped through the D-Net of the receiving end, the mapping relation is thatWherein->Representing the demapping relation function to obtain the final signal +.>
The expression of the demapping relationship function is:
wherein Q is conv1 ，U conv1 A weight matrix and a bias matrix, Q, representing the first convolution layer, respectively conv2 ，U conv2 Respectively representing a weight matrix and a bias matrix of a second convolution layer, Q f And U f Representing the weight matrix and the bias matrix of the fully connected layer, respectively, the tanh function is the activation function utilized by the two convolutional layers and the fully connected layer.
Optionally, the method further comprises: the system bit error rate BER performance and PAPR performance are considered by adjusting the network architecture of the M-Net and the D-Net and training related parameters, and the specific training process comprises the following steps:
firstly, the PAPR performance of the time domain signal of the transmitting end is not considered, the system loss function only comprises the error rate, and the error rate is the signal X transmitted by the transmitting end and the signal recovered by the receiving endCo-determination, and signal recovered at the receiving end +.>The method is jointly determined by M-Net and D-Net, namely, the value of a system loss function is related to the M-Net and the D-Net, in the training process of an OFDM system improved by DM-Net, the system obtains the optimal error rate performance under the condition of a Gaussian white noise channel or a Rayleigh fading channel by adjusting the architecture of the M-Net and the D-Net and continuously iterating parameters of an M-Net model and a D-Net model by utilizing an optimization algorithm so as to reduce the value of the system loss function, namely, the system is subjected to joint optimization of the M-Net of a transmitting end and the D-Net of a receiving end;
secondly, based on the structure and parameters of the DM-Net trained in the first step, PAPR items are added in a system loss function, the M-Net of a transmitting end and the D-Net of a receiving end are jointly trained again, and meanwhile, through proper selection of weight factors, the error rate performance and the required PAPR performance of the system can be ensured under the condition of Gaussian white noise channels or Rayleigh fading channels.
Optionally, the optimal network architecture of the M-Net and the optimal network parameters of the D-Det are obtained through final training, the M-Net and the D-Det comprise two convolution layers and a full connection layer, the convolution kernels of the first convolution layer and the second convolution layer are 3 multiplied by 3, the number of the convolution kernels is 5, the number of nodes of the full connection layer is 512, and the activation functions of the convolution layers and the full connection layer are tanh functions.
Optionally, in the joint training process of the transmitting end M-Det and the receiving end D-Net, an optimization algorithm is adopted to continuously iterate model parameters to reduce the value of a model loss function, wherein the optimization algorithm comprises, but is not limited to, a gradient descent method, an Adam algorithm and an RMSProp algorithm.
The following describes a signal peak-to-average power ratio PAPR suppression method in detail in the embodiment of the present invention: the OFDM system with improved DM-Net carries out adaptive constellation mapping and demapping on the transmission signal to reduce the peak-to-average power ratio, wherein the adaptive constellation mapping refers to that according to PAPR performance, DM-Net can automatically adjust the position of signal constellation points, the DM-Net is a network structure based on deep learning and comprises M-Net of a transmitting end and D-Net of a receiving end, the M-Net of the transmitting end changes constellation point distribution of the transmission signal through adjustment of the transmission signal on a frequency domain constellation, the purpose that a time domain signal transmitted by the transmitting end of the system has a lower PAPR value is achieved, and D-Net of the receiving end is responsible for recovering the signal after the channel into the original transmitted frequency domain signal, so that the purpose of guaranteeing the integral error rate performance of the system is achieved.
The improved OFDM system architecture is shown in FIG. 2, the DM-Net model is shown in FIG. 3, and comprises an input layer, a convolution layer, a full connection layer and an output layer, but the difference from the traditional convolution neural network CNN is that: irrespective of the processes of pooling, normalization and the like;
let the number of sub-carriers of the system be N, the transmitted modulation signal be X= [ X ] 0 ,X 1 ,...,X N-2 ,X N-1 ]X is represented as X K ＝[X R (K)X I (K)]Wherein X is R (K) Represents X K The real part of X I (K) Represents X K K is more than or equal to 0 and less than or equal to N-1, and the input signal X is input at the transmitting end through M-Net K Constellation mapping is carried out, and the mapping relation is T K ＝f(X K ) Wherein f (·) represents a mapping function, T K Represents the signal after constellation mapping, K is more than or equal to 0 and less than or equal to N-1,
the expression of the mapping relation function is:
f(X)＝tanh(tanh(conv (tanh(conv(X,W conv1 )+b conv1 ),W conv2 )+b conv2 )*W f +b f ) (1)
wherein W is conv1 ，b conv1 Weight matrix and bias matrix respectively representing the first convolution layer, W conv2 ，b conv2 Weight matrix and bias matrix respectively representing the second convolution layer, W f And b f Respectively representing a weight matrix and a bias matrix of the full connection layer, wherein the tanh function is an activation function utilized by the two convolution layers and the full connection layer;
the constellation points of the signal T are different from constellation points uniformly distributed in modulation modes such as multi-system quadrature amplitude modulation, the main purpose of constellation mapping by using M-Net is to adjust the positions of original signal constellation points according to PAPR performance requirements, the distribution of the signal constellation points after the M-Net constellation mapping is relatively disordered and irregular, the distribution of the signal constellation points is determined by the M-Net according to the required PAPR performance requirements, and when the PAPR performance requirements of the system are different, the distribution of the signal constellation points after the M-Net constellation mapping is also different;
combining the real part and the imaginary part in T into a complex vector form, and then oversampling the T, wherein the oversampling multiple is L, and the oversampled signal is T L And then the time domain transmission signal is obtained through inverse fast fourier transform (Inverse Fast Fourier Transform, IFFT):
wherein n is more than or equal to 0 and less than or equal to LN-1, K is more than or equal to 0 and less than or equal to LN-1, and the PAPR calculation formula of the time domain signal is as follows:
wherein max [ |x (n) | 2 ]Representing the maximum power of the signal, E [ |x (n) | 2 ]Represents the average value of signal power, n is more than or equal to 0 and less than or equal to LN-1;
after the transmission signal is subjected to M-Net adaptive constellation mapping, the distribution of signal constellation points ensures that the time domain signal transmitted by a system transmitting end has a lower PAPR value;
the PAPR suppression performance of the different algorithms is usually quantitatively described by a complementary cumulative function (Complementary Cumulative Distribution Function, CCDF), which represents the probability that the actual peak-to-average power ratio of the signal exceeds a given peak-to-average power ratio, PAPR 0;
the time domain transmission signal reaches the receiving end after passing through the channel, the signal received by the receiving end is set as R (n), n is more than or equal to 0 and less than or equal to LN-1, fast Fourier transform FFT is carried out to obtain a frequency domain signal, and downsampling is carried out on the frequency domain signal to obtain R K K is more than or equal to 0 and less than or equal to N-1, R is K Splitting, R K ＝[R R (K)R I (K)]Wherein R is R (K) Represents R K The real part of R I (K) Represents R K Then the received signal is demapped through the D-Net of the receiving end, the mapping relation is thatWherein->Representing the demapping relation function to obtain the final signal +.>
The expression of the demapping relationship function is:
wherein Q is conv1 ，U conv1 A weight matrix and a bias matrix, Q, representing the first convolution layer, respectively conv2 ，U conv2 Respectively representing a weight matrix and a bias matrix of a second convolution layer, Q f And U f Representing the weight matrix and the bias matrix of the fully connected layer, respectively, the tanh function is the activation function utilized by the two convolutional layers and the fully connected layer.
The inhibition method of the embodiment of the invention further comprises the following steps: the system bit error rate BER performance and PAPR performance are considered by adjusting the network architecture of the M-Net and the D-Net and training related parameters, and the specific training process comprises the following steps:
firstly, the PAPR performance of the time domain signal of the transmitting end is not considered, the system loss function only comprises the error rate, and the error rate is the signal X transmitted by the transmitting end and the signal recovered by the receiving endCo-determination, and signal recovered at the receiving end +.>Is determined by M-Net and D-Net together, i.e. the system loss functionThe value is related to M-Net and D-Net, in the OFDM system training process of DM-Net improvement, the system obtains the optimal error rate performance under the condition of Gaussian white noise channel or Rayleigh fading channel by adjusting the architecture of M-Net and D-Net and utilizing the optimization algorithm to iterate the parameters of M-Net and D-Net models continuously so as to reduce the value of the system loss function, namely, the M-Net of the transmitting end and the D-Net of the receiving end are jointly optimized;
secondly, based on the structure and parameters of the DM-Net trained in the first step, PAPR items are added in a system loss function, the M-Net of a transmitting end and the D-Net of a receiving end are jointly trained again, and meanwhile, through proper selection of weight factors, the error rate performance and the required PAPR performance of the system can be ensured under the condition of Gaussian white noise channels or Rayleigh fading channels.
In the combined training process of M-Net and D-Net, an optimization algorithm can be adopted to continuously iterate model parameters to reduce the value of a model loss function, wherein the optimization algorithm comprises, but is not limited to, a gradient descent method, an Adam algorithm and an RMSProp algorithm, so that the aim of considering both the error rate performance and the PAPR performance of the system is fulfilled.
The loss function of the system as a whole can be expressed as:
Loss＝Φ 1 +ηΦ 2 (5)
Φ 2 ＝PAPR(x) (7)
wherein phi is 1 Represents the system BER, phi 2 Representing the PAPR value of the system, eta represents the weight factor of the loss function, is used for adjusting the BER and the weight of the PAPR in the loss function, and when eta is larger, the PAPR performance of the system is more focused, otherwise, the BER performance of the system is more focused.
The embodiment of the invention finally trains the network architecture and the network parameters of the optimal M-Net and D-Det, wherein the M-Net and the D-Det comprise two convolution layers and one full-connection layer, the convolution kernels of the first convolution layer and the second convolution layer are 3 multiplied by 3, the number of the convolution kernels is 5, the number of nodes of the full-connection layer is 512, and the activation functions of the convolution layers and the full-connection layer are tanh functions.
Simulation environment and parameter settings:
the overall performance simulation of the system is carried out based on a python tensorflow framework, wherein the number of subcarriers of the system is set to 64, the modulation mode is 4QAM modulation, four times oversampling is carried out, the error rate and PAPR performance simulation of the system are carried out under a Rayleigh fading channel model, the PAPR performance of the obtained system is shown in figure 4, and the obtained system error rate is shown in figure 5.
As shown in fig. 6, the embodiment of the present invention further provides a device for suppressing a peak-to-average power ratio PAPR of a signal, including:
an input unit 610 for inputting the modulated OFDM transmission signal;
the processing unit 620 is configured to reduce a peak-to-average power ratio by performing adaptive constellation mapping and demapping on the transmission signal by using an OFDM system with improved DM-Net, where the adaptive constellation mapping refers to that the DM-Net automatically adjusts the position of a signal constellation point according to the PAPR performance, the DM-Net is a network structure based on deep learning, and includes two parts of M-Net at a transmitting end and D-Net at a receiving end, where the M-Net at the transmitting end changes the constellation point distribution of the transmission signal by adjusting the constellation of the transmission signal in the frequency domain, so as to achieve the purpose that the time domain signal sent by the transmitting end of the system has a lower PAPR value, and the D-Net at the receiving end is responsible for recovering the signal after the channel into the frequency domain signal that is originally sent, so as to achieve the purpose of ensuring the overall error rate performance of the system.
Optionally, the processing unit is specifically configured to:
let the number of sub-carriers of the system be N, the transmitted modulation signal be X= [ X ] 0 ,X 1 ,...,X N-2 ,X N-1 ]X is represented as X K ＝[X R (K)X I (K)]Wherein X is R (K) Represents X K The real part of X I (K) Represents X K K is more than or equal to 0 and less than or equal to N-1, and the input signal X is input at the transmitting end through M-Net K Constellation mapping is carried out, and the mapping relation is T K ＝f(X K ) Which is provided withWherein f (·) represents a mapping function, T K Represents the signal after constellation mapping, K is more than or equal to 0 and less than or equal to N-1,
the expression of the mapping relation function is:
f(X)＝tanh(tanh(conv(tanh(conv(X,W conv1 )+b conv1 ),W conv2 )+b conv2 )*W f +b f ) (1)
wherein W is conv1 ，b conv1 Weight matrix and bias matrix respectively representing the first convolution layer, W conv2 ，b conv2 Weight matrix and bias matrix respectively representing the second convolution layer, W f And b f Respectively representing a weight matrix and a bias matrix of the full connection layer, wherein the tanh function is an activation function utilized by the two convolution layers and the full connection layer;
combining the real part and the imaginary part in T into a complex vector form, and then oversampling the T, wherein the oversampling multiple is L, and the oversampled signal is T L And then obtaining a time domain transmission signal through Inverse Fast Fourier Transform (IFFT):
wherein n is more than or equal to 0 and less than or equal to LN-1, K is more than or equal to 0 and less than or equal to LN-1, and the PAPR calculation formula of the time domain signal is as follows:
wherein max [ |x (n) | 2 ]Representing the maximum power of the signal, E [ |x (n) | 2 ]Represents the average value of signal power, n is more than or equal to 0 and less than or equal to LN-1;
after the transmission signal is subjected to M-Net adaptive constellation mapping, the distribution of signal constellation points ensures that the time domain signal transmitted by a system transmitting end has a lower PAPR value;
the time domain transmission signal reaches the receiving end after passing through the channel, the signal received by the receiving end is r (n), n is more than or equal to 0 and less than or equal to LN-1, fast Fourier transform FFT is carried out to obtain a frequency domain signal, and the frequency domain signal is processedDownsampling the line to obtain R K K is more than or equal to 0 and less than or equal to N-1, R is K Splitting, R K ＝[R R (K) R I (K)]Wherein R is R (K) Represents R K The real part of R I (K) Represents R K Then the received signal is demapped through the D-Net of the receiving end, the mapping relation is thatWherein->Representing the demapping relation function to obtain the final signal +.>
The expression of the demapping relationship function is:
wherein Q is conv1 ，U conv1 A weight matrix and a bias matrix, Q, representing the first convolution layer, respectively conv2 ，U conv2 Respectively representing a weight matrix and a bias matrix of a second convolution layer, Q f And U f Representing the weight matrix and the bias matrix of the fully connected layer, respectively, the tanh function is the activation function utilized by the two convolutional layers and the fully connected layer.
Optionally, the apparatus further comprises: a training unit for realizing the combination of the BER performance and the PAPR performance of the system through the adjustment of the network architecture of the M-Net and the D-Net and the training of related parameters,
the training unit is specifically configured to:
firstly, the PAPR performance of the time domain signal of the transmitting end is not considered, the system loss function only comprises the error rate, and the error rate is the signal X transmitted by the transmitting end and the signal recovered by the receiving endCo-determination, and signal recovered at the receiving end +.>The method is jointly determined by M-Net and D-Net, namely, the value of a system loss function is related to the M-Net and the D-Net, in the training process of an OFDM system improved by DM-Net, the system obtains the optimal error rate performance under the condition of a Gaussian white noise channel or a Rayleigh fading channel by adjusting the architecture of the M-Net and the D-Net and continuously iterating parameters of an M-Net model and a D-Net model by utilizing an optimization algorithm so as to reduce the value of the system loss function, namely, the system is subjected to joint optimization of the M-Net of a transmitting end and the D-Net of a receiving end;
secondly, based on the structure and parameters of the DM-Net trained in the first step, PAPR items are added in a system loss function, the M-Net of a transmitting end and the D-Net of a receiving end are jointly trained again, and meanwhile, through proper selection of weight factors, the error rate performance and the required PAPR performance of the system can be ensured under the condition of Gaussian white noise channels or Rayleigh fading channels.
Optionally, the optimal network architecture of the M-Net and the optimal network parameters of the D-Det are obtained through final training, the M-Net and the D-Det comprise two convolution layers and a full connection layer, the convolution kernels of the first convolution layer and the second convolution layer are 3 multiplied by 3, the number of the convolution kernels is 5, the number of nodes of the full connection layer is 512, and the activation functions of the convolution layers and the full connection layer are tanh functions.
Optionally, the training unit is further configured to continuously iterate model parameters to reduce a value of a model loss function by using an optimization algorithm in a joint training process of the transmitting end M-Det and the receiving end D-Net, where the optimization algorithm includes, but is not limited to, a gradient descent method, an Adam algorithm, and an RMSProp algorithm.
Fig. 7 is a schematic structural diagram of an electronic device 700 according to an embodiment of the present invention, where the electronic device 700 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 701 and one or more memories 702, where at least one instruction is stored in the memories 702, and the at least one instruction is loaded and executed by the processors 701 to implement the steps of the above-described method for suppressing a signal peak-to-average power ratio PAPR.
In an exemplary embodiment, a computer readable storage medium, such as a memory, comprising instructions executable by a processor in a terminal to perform a signal peak-to-average power ratio, PAPR, suppression method as described above is also provided. For example, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The method for suppressing the PAPR of the signal is characterized by comprising the following steps:
inputting modulated OFDM transmission signals;
the method comprises the steps that an OFDM system improved by DM-Net carries out adaptive constellation mapping and demapping on a transmission signal to reduce the peak-to-average power ratio, wherein the adaptive constellation mapping means that according to PAPR performance, the DM-Net can automatically adjust the position of a signal constellation point, the DM-Net is a network structure based on deep learning and comprises an M-Net part of a transmitting end and a D-Net part of a receiving end, the M-Net part of the transmitting end changes constellation point distribution of the transmission signal through adjustment of the transmission signal on a frequency domain constellation, the purpose that a time domain signal sent by the transmitting end of the system has a lower PAPR value is achieved, and the D-Net part of the receiving end is responsible for recovering the signal after the channel into the original transmitted frequency domain signal, so that the purpose of guaranteeing the overall error rate performance of the system is achieved;
the method for reducing peak-to-average power ratio by adaptive constellation mapping and demapping of the transmission signal by the DM-Net improved OFDM system specifically comprises the following steps:
let the number of sub-carriers of the system be N, the transmitted modulation signal be X= [ X ] 0 ,X 1 ,...,X N-2 ,X N-1 ]X is represented as X K ＝[X R (K) X I (K)]Wherein X is R (K) Represents X K The real part of X I (K) Represents X K K is more than or equal to 0 and less than or equal to N-1, and the input signal X is input at the transmitting end through M-Net K Constellation mapping is carried out, and the mapping relation is T K ＝f(X K ) Wherein f (·) represents a mapping function, T K Represents the signal after constellation mapping, K is more than or equal to 0 and less than or equal to N-1,
the expression of the mapping relation function is:
f(X)＝tanh(tanh(conv(tanh(conv(X,W conv1 )+b conv1 ),W conv2 )+b conv2 )*W f +b f ) (1)
wherein W is conv1 ，b conv1 Weight matrix and bias matrix respectively representing the first convolution layer, W conv2 ，b conv2 Weight matrix and bias matrix respectively representing the second convolution layer, W f And b f Respectively representing a weight matrix and a bias matrix of the full connection layer, wherein the tanh function is an activation function utilized by the two convolution layers and the full connection layer;
combining the real part and the imaginary part in T into a complex vector form, and then oversampling the T, wherein the oversampling multiple is L, and the oversampled signal is T L And then obtaining a time domain transmission signal through Inverse Fast Fourier Transform (IFFT):
wherein n is more than or equal to 0 and less than or equal to LN-1, K is more than or equal to 0 and less than or equal to LN - 1, the PAPR calculation formula of the time domain signal is as follows:
wherein the method comprises the steps ofRepresenting the maximum power of the signal, E [ |x (n) | 2 ]Represents the average value of signal power, n is more than or equal to 0 and less than or equal to LN-1;
after the transmission signal is subjected to M-Net adaptive constellation mapping, the distribution of signal constellation points ensures that the time domain signal transmitted by a system transmitting end has a lower PAPR value;
the time domain transmission signal reaches the receiving end after passing through the channel, the signal received by the receiving end is set as R (n), n is more than or equal to 0 and less than or equal to LN-1, fast Fourier transform FFT is carried out to obtain a frequency domain signal, and downsampling is carried out on the frequency domain signal to obtain R K K is more than or equal to 0 and less than or equal to N-1, R is K Splitting, R K ＝[R R (K)R I (K)]Wherein R is R (K) Represents R K The real part of R I (K) Represents R K Then the received signal is demapped through the D-Net of the receiving end, the mapping relation is thatWherein->Representing the demapping relation function to obtain the final signal +.>
The expression of the demapping relationship function is:
wherein Q is conv1 ，U conv1 Weights respectively representing the first convolution layerRe-matrix and bias matrix, Q conv2 ，U conv2 Respectively representing a weight matrix and a bias matrix of a second convolution layer, Q f And U f Representing the weight matrix and the bias matrix of the fully connected layer, respectively, the tanh function is the activation function utilized by the two convolutional layers and the fully connected layer.
2. The method of claim 1, wherein the method further comprises: the system bit error rate BER performance and PAPR performance are considered by adjusting the network architecture of the M-Net and the D-Net and training related parameters, and the specific training process comprises the following steps:
firstly, the PAPR performance of the time domain signal of the transmitting end is not considered, the system loss function only comprises the error rate, and the error rate is the signal X transmitted by the transmitting end and the signal recovered by the receiving endCo-determination, and signal recovered at the receiving end +.>The method is jointly determined by M-Net and D-Net, namely, the value of a system loss function is related to the M-Net and the D-Net, in the training process of an OFDM system improved by DM-Net, the system obtains the optimal error rate performance under the condition of a Gaussian white noise channel or a Rayleigh fading channel by adjusting the architecture of the M-Net and the D-Net and continuously iterating parameters of an M-Net model and a D-Net model by utilizing an optimization algorithm so as to reduce the value of the system loss function, namely, the system is subjected to joint optimization of the M-Net of a transmitting end and the D-Net of a receiving end;
secondly, based on the structure and parameters of the DM-Net trained in the first step, PAPR items are added in a system loss function, the M-Net of a transmitting end and the D-Net of a receiving end are jointly trained again, and meanwhile, through proper selection of weight factors, the error rate performance and the required PAPR performance of the system can be ensured under the condition of Gaussian white noise channels or Rayleigh fading channels.
3. The method of claim 2, wherein the network architecture and network parameters of the M-Net and D-Det are optimized by final training, the M-Net and D-Det each comprise two convolution layers and a full connection layer, the convolution kernels of the first and second convolution layers are 3 x 3, the number of convolution kernels is 5, the number of nodes of the full connection layer is 512, and the activation functions of the convolution layers and the full connection layer are tanh functions.
4. The method of claim 2, wherein during the joint training of the transmitting end M-Det and the receiving end D-Net, an optimization algorithm is used to iterate model parameters continuously to reduce the value of the model loss function, wherein the optimization algorithm includes, but is not limited to, a gradient descent method, an Adam algorithm, and an RMSProp algorithm.
5. A signal peak-to-average power ratio, PAPR, suppression apparatus comprising:
an input unit for inputting the modulated OFDM transmission signal;
the processing unit is used for reducing peak-to-average power ratio by carrying out adaptive constellation mapping and demapping on the transmission signal through an OFDM system with improved DM-Net, wherein the adaptive constellation mapping refers to that according to PAPR performance, DM-Net can automatically adjust the position of signal constellation points, the DM-Net is a network structure based on deep learning and comprises an M-Net part of a transmitting end and a D-Net part of a receiving end, the M-Net part of the transmitting end changes constellation point distribution of the transmission signal through adjustment of the transmission signal on a frequency domain constellation, the purpose that a time domain signal transmitted by the transmitting end of the system has a lower PAPR value is achieved, and the D-Net part of the receiving end is responsible for recovering the signal after the signal is transmitted into the original frequency domain signal, so that the purpose of ensuring the overall error rate performance of the system is achieved;
the processing unit is specifically configured to:
let the number of sub-carriers of the system be N, the transmitted modulation signal be X= [ X ] 0 ,X 1 ,...,X N-2 ,X N-1 ]X is represented as X K ＝[X R (K) X I (K)]Wherein X is R (K) Represents X K The real part of X I (K) Represents X K K is more than or equal to 0 and less than or equal to N-1, and the input signal X is input at the transmitting end through M-Net K Constellation mapping is carried out, and the mapping relation is T K ＝f(X K ) Wherein f (·) represents a mapping function, T K Represents the signal after constellation mapping, K is more than or equal to 0 and less than or equal to N-1,
the expression of the mapping relation function is:
f(X)＝tanh(tanh(conv(tanh(conv(X,W conv1 )+b conv1 ),W conv2 )+b conv2 )*W f +b f ) (1)
wherein W is conv1 ，b conv1 Weight matrix and bias matrix respectively representing the first convolution layer, W conv2 ，b conv2 Weight matrix and bias matrix respectively representing the second convolution layer, W f And b f Respectively representing a weight matrix and a bias matrix of the full connection layer, wherein the tanh function is an activation function utilized by the two convolution layers and the full connection layer;
combining the real part and the imaginary part in T into a complex vector form, and then oversampling the T, wherein the oversampling multiple is L, and the oversampled signal is T L And then obtaining a time domain transmission signal through Inverse Fast Fourier Transform (IFFT):
wherein n is more than or equal to 0 and less than or equal to LN-1, K is more than or equal to 0 and less than or equal to LN-1, and the PAPR calculation formula of the time domain signal is as follows:
wherein the method comprises the steps ofRepresenting the maximum power of the signal, E [ |x (n) 2 The I represents the average value of signal power, and n is more than or equal to 0 and less than or equal to LN-1;
after the transmission signal is subjected to M-Net adaptive constellation mapping, the distribution of signal constellation points ensures that the time domain signal transmitted by a system transmitting end has a lower PAPR value;
the time domain transmission signal reaches the receiving end after passing through the channel, the signal received by the receiving end is set as R (n), n is more than or equal to 0 and less than or equal to LN-1, fast Fourier transform FFT is carried out to obtain a frequency domain signal, and downsampling is carried out on the frequency domain signal to obtain R K K is more than or equal to 0 and less than or equal to N-1, R is K Splitting, R K ＝[R R (K)R I (K)]Wherein R is R (K) Represents R K The real part of R I (K) Represents R K Then the received signal is demapped through the D-Net of the receiving end, the mapping relation is thatWherein->Representing the demapping relation function to obtain the final signal +.>
The expression of the demapping relationship function is:
wherein Q is conv1 ，U conv1 A weight matrix and a bias matrix, Q, representing the first convolution layer, respectively conv2 ，U conv2 Respectively representing a weight matrix and a bias matrix of a second convolution layer, Q f And U f Representing the weight matrix and the bias matrix of the fully connected layer, respectively, the tanh function is the activation function utilized by the two convolutional layers and the fully connected layer.
6. The apparatus of claim 5, wherein the apparatus further comprises: a training unit for realizing the combination of the BER performance and the PAPR performance of the system through the adjustment of the network architecture of the M-Net and the D-Net and the training of related parameters,
the training unit is specifically configured to:
firstly, the PAPR performance of the time domain signal of the transmitting end is not considered, the system loss function only comprises the error rate, and the error rate is the signal X transmitted by the transmitting end and the signal recovered by the receiving endCo-determination, and signal recovered at the receiving end +.>The method is jointly determined by M-Net and D-Net, namely, the value of a system loss function is related to the M-Net and the D-Net, in the training process of an OFDM system improved by DM-Net, the system obtains the optimal error rate performance under the condition of a Gaussian white noise channel or a Rayleigh fading channel by adjusting the architecture of the M-Net and the D-Net and continuously iterating parameters of an M-Net model and a D-Net model by utilizing an optimization algorithm so as to reduce the value of the system loss function, namely, the system is subjected to joint optimization of the M-Net of a transmitting end and the D-Net of a receiving end;
secondly, based on the structure and parameters of the DM-Net trained in the first step, PAPR items are added in a system loss function, the M-Net of a transmitting end and the D-Net of a receiving end are jointly trained again, and meanwhile, through proper selection of weight factors, the error rate performance and the required PAPR performance of the system can be ensured under the condition of Gaussian white noise channels or Rayleigh fading channels.
7. The apparatus of claim 6, wherein the network architecture and its network parameters are optimized for final training, the M-Net and the D-Det each comprise two convolution layers and one full connection layer, the convolution kernels of the first and second convolution layers are 3 x 3, the number of convolution kernels is 5, the number of nodes of the full connection layer is 512, and the activation functions of the convolution layers and the full connection layer are tanh functions.
8. The apparatus of claim 6, wherein the training unit is further configured to use an optimization algorithm to iterate model parameters continuously to reduce a value of a model loss function during joint training of the transmitting end M-Det and the receiving end D-Net, the optimization algorithm including, but not limited to, a gradient descent method, an Adam algorithm, an RMSProp algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210831928.9A CN115208731B (en) | 2022-07-15 | 2022-07-15 | Method and device for suppressing peak-to-average power ratio (PAPR) of signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210831928.9A CN115208731B (en) | 2022-07-15 | 2022-07-15 | Method and device for suppressing peak-to-average power ratio (PAPR) of signal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115208731A CN115208731A (en) | 2022-10-18 |
| CN115208731B true CN115208731B (en) | 2023-08-25 |
Family
ID=83581820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210831928.9A Active CN115208731B (en) | 2022-07-15 | 2022-07-15 | Method and device for suppressing peak-to-average power ratio (PAPR) of signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115208731B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101605120A (en) * | 2009-07-17 | 2009-12-16 | 清华大学 | The iteration inner code decoder and channel estimation methods and the device that are used for ofdm system |
| CN109951412A (en) * | 2019-01-31 | 2019-06-28 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | The method of deep neural network inhibition signal cubic metric |
| CN112118066A (en) * | 2020-11-23 | 2020-12-22 | 西南交通大学 | FBMC-PON demodulation method based on improved convolutional neural network |
| CN114039821A (en) * | 2021-11-06 | 2022-02-11 | 河南工业大学 | Broadband mmWave MIMO-OFDM system beam space channel estimation method |
| CN114745248A (en) * | 2022-04-06 | 2022-07-12 | 山东大学 | DM-GSM signal detection method based on convolutional neural network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3185499A1 (en) * | 2015-12-21 | 2017-06-28 | Thomson Licensing | Receiver including a circular or square limiter for through active constellation extension papr reduced transmitted signal |
| US20220004810A1 (en) * | 2018-09-28 | 2022-01-06 | Pavel Sinha | Machine learning using structurally regularized convolutional neural network architecture |
-
2022
- 2022-07-15 CN CN202210831928.9A patent/CN115208731B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101605120A (en) * | 2009-07-17 | 2009-12-16 | 清华大学 | The iteration inner code decoder and channel estimation methods and the device that are used for ofdm system |
| CN109951412A (en) * | 2019-01-31 | 2019-06-28 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | The method of deep neural network inhibition signal cubic metric |
| CN112118066A (en) * | 2020-11-23 | 2020-12-22 | 西南交通大学 | FBMC-PON demodulation method based on improved convolutional neural network |
| CN114039821A (en) * | 2021-11-06 | 2022-02-11 | 河南工业大学 | Broadband mmWave MIMO-OFDM system beam space channel estimation method |
| CN114745248A (en) * | 2022-04-06 | 2022-07-12 | 山东大学 | DM-GSM signal detection method based on convolutional neural network |
Non-Patent Citations (1)
| Title |
|---|
| Mai, Zhiyuan, Yueyun Chen, and Liping Du. ."A novel blind mmWave channel estimation algorithm based on ML-ELM".《IEEE Communications Letters》.2021,第1549-1553.页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115208731A (en) | 2022-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Anoh et al. | Root-based nonlinear companding technique for reducing PAPR of precoded OFDM signals | |
| Jiang et al. | Curve fitting based tone reservation method with low complexity for PAPR reduction in OFDM systems | |
| US20040005010A1 (en) | Channel estimator and equalizer for OFDM systems | |
| CN110336763B (en) | ACE method and system for restraining peak-to-average power ratio of high-order modulation OFDM signal | |
| CN104468455B (en) | The LTE system ofdm signal method for suppressing peak to average ratio of joint constellation extension and preserved sub-carrier | |
| US8315299B2 (en) | Time-domain equalization for discrete multi-tone systems | |
| CN107592135B (en) | A kind of adaptive impulse noise suppression method of power line communication | |
| EP1157514A1 (en) | Kalman equalisation in mulitcarrier receivers | |
| JP2008516499A (en) | Recover clipped signal peaks at the receiver site | |
| CN104618290B (en) | Wideband OFDM signal method for suppressing peak to average ratio based on clipped noise than preserved sub-carrier | |
| JP7079566B2 (en) | Signal processing circuit | |
| CN115208731B (en) | Method and device for suppressing peak-to-average power ratio (PAPR) of signal | |
| US7864874B2 (en) | OFDM communications system employing crest factor reduction with ISI control | |
| CN114301751A (en) | Frequency domain calculation method for reducing peak-to-average ratio of uplink signal of terminal of Internet of things | |
| CN105516044B (en) | A kind of ofdm system method for suppressing peak to average ratio based on differential evolution algorithm | |
| CN116155673B (en) | Few-mode optical fiber communication method for reducing PAPR of OFDM signal | |
| CN111817997A (en) | Method for suppressing combined rotation precoding and PTS peak-to-average power ratio in OFDM system | |
| Jia et al. | OCDM with Index Modulation for Autonomous Underwater Vehicles Communication | |
| CN114124637B (en) | Low-complexity method suitable for reducing peak-to-average ratio of OFDM (orthogonal frequency division multiplexing) system | |
| OHTA et al. | Asymmetric autoencoder for PAPR reduction of OFDM signals | |
| CN110071889B (en) | Peak-to-average power ratio suppression method suitable for multi-path OFDM system | |
| Zheng et al. | A Novel Single Carrier Frequency Domain Equalization Method in Underwater Acoustic Communications | |
| CN115102587B (en) | Method for reducing PAPR of MIMO-OFDM system | |
| CN115801528B (en) | OTFS waveform peak-to-average ratio suppression method based on time delay grid grouping | |
| Wang et al. | Papr reduction method based on pilot-assisted fbmc in broadband power line communication |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |