Semantic communication method for semantic source channel adaptive coding under parallel channels

Abstract

The invention discloses a semantic communication method for adaptive coding of a semantic source channel under a parallel channel. The method comprises the following steps: S1, constructing a communication model for adaptive coding of the semantic source channel under the parallel channel; s2, at a sending end, encoding semantic information source samples in (X, S), distributing bit streams after encoding each semantic information source sample to an independent channel for transmission, and adopting K channel encoders with different channel rates to protect respective bit streams so as to resist channel errors; s3, at a receiving end, decoding the received signals by using K channel decoders, combining the received signals into a single serial flow, and decoding the single serial flow by using a semantic source decoder based on a deep neural network; s4, determining a source rate and prior information under any given deep neural network model; and S5, constructing an optimization problem, and performing joint optimization of the deep neural network parameter phi and the resource allocation variable # imgabs0 #. According to the invention, resource allocation optimization in a parallel Gaussian channel scene is realized.

Description

Technical Field

[0001] The present invention relates to the field of semantic communication, and in particular to a semantic communication method of semantic source channel adaptive coding under parallel channels. Background Art

[0002] With the rise of intelligent services and the deep integration of artificial intelligence in wireless communications, task-oriented semantic communication technology is seen as an important development direction for future 6G wireless networks. Unlike traditional communication systems that focus on bit-level accurate transmission, semantic communication significantly improves transmission efficiency under limited communication resource conditions by extracting and transmitting intrinsic semantic information of data sources related to specific tasks (such as target detection, edge reasoning, etc.).

[0003] However, existing semantic communication technologies face the following key challenges in practical applications: 1. Compatibility issues with digital hardware. Existing joint source channel coding schemes based on deep neural networks mainly generate analog symbols for transmission, which are difficult to be compatible with modern digital communication systems, limiting their practical deployment; 2. Lack of adaptability. Current deep learning methods rely on end-to-end training for specific tasks and channel conditions. When task requirements or channel conditions change, the entire network needs to be redesigned and trained, which is difficult to achieve in actual communication scenarios; 3. Lack of adaptability to complex channels. Existing research mainly focuses on additive white Gaussian noise channels, and there is insufficient research on resource allocation and rate adaptation strategies in more complex channel scenarios such as frequency selective channels and MIMO channels. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a semantic communication method for semantic source channel adaptive coding under parallel channels. By combining deep neural network semantic source coding with parallel digital channel coding, the problems of poor compatibility between existing semantic communication schemes and digital systems and insufficient channel adaptability are solved, while resource allocation optimization in parallel Gaussian channel scenarios is achieved.

[0005] The object of the present invention is achieved through the following technical solution: a semantic communication method of semantic source channel adaptive coding under parallel channels, comprising the following steps: S1. Construct a communication model for semantic source-channel adaptive coding under parallel channels; Assume that the semantic information source is composed of the joint probability distribution Characterization, where and Represent the external observation and internal semantic state of the source respectively, ( X,S ) represents a semantic source pair, express( X,S ), the sender passes KParallel channel transmission observation X , so that the receiver can obtain the restored semantic source pair ,in, is the external observation of the recovered source, is the semantic state of the recovered source, where K discrete set express; S2. At the sending end, the semantic source encoder is used to encode the semantic source pair ( X,S ), and the bit stream after each semantic source sample is encoded is assigned to an independent channel for transmission. K channel encoders with different channel rates to protect their respective bit streams against channel errors; S3. At the receiving end, the received signals are decoded by K channel decoders and merged into a single serial stream, which is decoded by a semantic source decoder based on a deep neural network; S4. Determine the source rate and prior information according to any given deep neural network model; S5. Construct optimization problems and perform deep neural network parameters Φ and resource allocation variables Joint optimization.

[0006] The beneficial effects of the present invention are as follows: by adopting an architectural design that combines deep neural network semantic source coding with parallel digital channel coding, the problems of poor compatibility between existing semantic communication solutions and digital systems and insufficient channel adaptability are solved, while resource allocation optimization in parallel Gaussian channel scenarios is achieved; at the same time, key network parameters are determined, prior information is given for each model, a lookup table is formed, key performance indicators of each model are characterized, and the difficulty of implementation is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is a schematic diagram of the principle of the present invention; Figure 2 Schematic diagram of the principle of semantic source encoder; Figure 3 It is a schematic diagram of the principle of the semantic source decoder; Figure 4 Schematic diagram of the relationship between the maximum transmit power and the signal-to-noise ratio in the embodiment; Figure 5 Schematic diagram of the relationship between maximum transmission power and accuracy in the embodiment. DETAILED DESCRIPTION

[0008] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0009] like Figure 1 As shown, a semantic communication method for semantic source channel adaptive coding under parallel channels includes the following steps: S1. Construct a communication model for semantic source-channel adaptive coding under parallel channels; Depend on K parallel Gaussian channels, using discrete sets These parallel channels can be equivalently realized by different communication technologies. For example, in OFDM system, the total bandwidth is divided into multiple orthogonal subcarriers, each of which can be regarded as a parallel channel; in multi-antenna system, MIMO channel can be decomposed into parallel channels by singular value decomposition technology. The semantic source is composed of joint probability distribution Characterization, where and Represent the external observation and internal semantic state of the source respectively. The purpose of the system is to K Parallel channel transmission observation X , so that the receiver can jointly recover ,in, is the external observation of the recovered source, is the semantic state of the restored source. To this end, the present invention proposes an adaptive digital source channel coding scheme, which includes a universal semantic source encoder and K parallel channel encoders.

[0010] S2. At the sending end, let ( x,s ) represents the semantic source pair ( X,S ) samples. The specific steps of the semantic source encoder are as follows Figure 2 As shown, the semantic source encoder has access to the observed samples x ,in x Through conditional probability and semantic state s The specific implementation steps are as follows: Step 1: Deep neural network feature extraction: Through the parameters Deep Neural Network x Mapping W dimensional continuous-valued vector y ,Right now: ,in, W Much smaller than x The original dimension ; Indicates that the parameter is Feature extraction function of deep neural network; Step 2: Quantification. y Perform uniform scalar quantization to obtain: ,in Represents a uniform scalar quantization operation.

[0011] Step 3: Arithmetic coding. Based on the quantized vector The probability mass function of , using lossless entropy coding Encoding as bitstream b ,in Representation and The expected source rate for encoding each source sample is defined as Entropy of: .

[0012] After semantic source coding, the encoded bit stream of each semantic source sample is assigned to an independent channel for transmission. Considering the different conditions of these channels, K channel encoders with different channel rates to protect their respective bit streams against channel errors. k Channels ( ), whose allocated bit stream is defined as ,Depend on Block channel code is used for encoding, where Indicates the number of data bits in each block, L is the code block length. Specifically, the total length is Bitstream Divided into blocks, of which Indicates the rounding operation. Each block is encoded as a length of L The symbol sequence , Indicates k The first channel codeword in the block of channels symbol. k The channel rate of a channel is calculated as In addition, the average channel usage times for transmitting one source sample is calculated as: (10) in It is through k The ratio of semantic source samples transmitted by each channel. To evaluate the transmission efficiency, the average bandwidth ratio is defined as , which is used to measure the average number of channel usages required to observe each element of the state.

[0013] Next, the channel transmission part, k In a Gaussian channel t The input and output relationship of each block is: (11) in, l =1,...,L , , ; Indicates the transmitted symbol, the mean is zero, and the average power is 1; is the corresponding received symbol; is an independent and identically distributed zero-mean cyclically symmetric complex Gaussian noise with a variance of ; Assign to channel k The power meets the total power constraint: ,in, is the maximum transmit power of the system. k The received signal-to-noise ratio of a channel is defined as .

[0014] S3. At the receiving end, the received signals are decoded by K channel decoders and merged into a single serial stream, which is decoded by a semantic source decoder based on a deep neural network; At the receiving end, k The received symbol sequence of the channel , first by the channel decoder k Decode to recovered bitstream Due to transmission errors, the recovered bit stream may not be equal to the bit stream sent. Then, K The bit stream of the channel decoder The data is then merged into a single serial stream through a parallel-to-serial converter, waiting to be decoded by a common semantic source decoder based on a deep neural network. Figure 3 As shown, which corresponds to the semantic source sample ( x,s ) is represented as .Notice, May correspond to any decoded bitstream , which depends on the semantic source sample ( x,s ) is transmitted through which parallel channel. Specifically, It is first decoded by the arithmetic decoder into a recovered feature vector .then, Input parameters are θ The deep neural network recovery function Restore observation samples x , the restored observation samples are Finally, the semantic state is recovered by the maximum a posteriori probability scheme s ,Right now: ,in is the restored semantic state, P ( s|x̂,ψ ) is composed of parameters ψThe posterior probability estimated by a deep neural network.

[0015] Accordingly, the restored semantic source sample subject to lossy compression and transmission errors; define k The end-to-end observation distortion and semantic distortion of the channel are: (12) (13) in and denote the observation distortion measure and the semantic distortion measure respectively, Indicates channel k The noise below. and Respectively represent k The end-to-end observed distortion of the channels and semantic distortion To evaluate the average performance of the system under consideration, we define for K The expectation of the weighted sum of two distortions on parallel channels is: (14) in α ∈[0,1] is the observation distortion and semantic distortion The weight coefficient between .

[0016] S4. Determine the source rate and prior information according to any given deep neural network model; First, for any given deep neural network model, the data fitting method can be used to obtain that the logarithmic value of the observation distortion and the semantic distortion can be approximated by the logistic function, that is: (15) (16) in Describe the neural network parameters in the semantic source codec, Indicates channel k The bit error probability in and They represent the logarithm of the observed distortion under a fixed deep neural network model. and semantic distortion These two parameters correspond to the distortion caused by source compression. and It is a parameter that characterizes the maximum distortion increase caused by channel errors. and is the logistic function growth rate parameter, which is used to describe the rate at which distortion changes with the bit error rate. and is the midpoint parameter of the logistic function, indicating the bit error rate corresponding to the midpoint value of the distortion. , , , , , , and All of them can be obtained through data fitting (preliminarily through conventional algorithms, such as minimum mean square error, etc.).

[0017] Then, for the k Gaussian channel, at a signal-to-noise ratio , code block length L and channel rate Under the condition of , the bit error probability under random channel block coding can be approximated as: (17) in, satisfy , The function is defined as , is the channel capacity expression, satisfying .

[0018] S5. Construct optimization problems and perform deep neural network parameters Φ and resource allocation variables Joint optimization.

[0019] Based on the above analysis and modeling, the goal of this invention is to minimize the average distortion by optimizing the following two aspects: : Parameters of semantic source encoder and decoder and K The power allocation and channel rate adaptation strategy of parallel channels. The corresponding optimization problem is: (18) In order to solve the above optimization problem, the present invention proposes an optimization algorithm based on model selection, which combines the deep neural network parameter Φ with the resource allocation variable The joint optimization is decoupled.

[0020] Step 1: Pre-trained model construction. First, build a lookup table containing N pre-trained deep neural network models: 1. The pre-training process refers to training the semantic source codec with parameters By changing some adjustable hyperparameters of the neural network, N deep neural networks with different performances can be trained. The specific training process is as follows: First, consider a semantic dataset consisting of a large number of semantic source samples ( x,s ) and pre-set the hyperparameters of the neural network. Since the semantic source encoder in this patent only inputs the observed samples x , the input of the neural network is just a large number of observation samples x Observation Sample x First, the parameters are input into the semantic encoder. The output is then directly fed into a deep neural network with parameters θ The deep neural network output is the restored observation sample ;at last, Input parameters are The deep neural network output is the restored semantic state . Accordingly, the loss function of the neural network is s and Distortion between x and The weighted sum of distortions, the training goal is to make the loss function as small as possible. The back propagation algorithm is used to calculate the gradient, and the gradient descent method is used to update the network parameter Φ, and the optimization is iterated until convergence or the preset number of training rounds is reached. Convergence means that the loss function is less than the set threshold.

[0021] 2. For each pre-trained model, perform distortion feature fitting. The specific steps are as follows: (1) Setting the bit error rate A set of discrete values ​​of , covering the error conditions under actual channel conditions; (2) For each Value: A large number of source samples ( x,s ) Input semantic source encoder, each sample corresponds to an output bit stream b ,exist b The probability of error caused by random introduction bit error, and use this bit stream with bit errors as the recovery bit stream ,Then After being decoded by the semantic source decoder, the corresponding and . Accordingly, the source rate The calculation method is: calculate the bit stream b The average length of Finally, according to equations (3) and (4), the corresponding observation distortion is obtained and semantic distortion The actual value of .

[0022] (3) For each pre-trained model, based on the experimental data obtained from (1) and (2), the minimum mean square error criterion is used to fit the parameters in the generalized logistic function (6) and (7) , , , , , , and .

[0023] Save each pre-trained deep neural network model and the corresponding source rate in the lookup table , and parameters , , , , , , and ; Step 2: Resource allocation optimization. For each given pre-trained model, i.e., a fixed deep neural network parameter Φ, a classical optimization technique, such as a continuous convex approximation algorithm, is used to solve the optimization problem (P1), thereby obtaining the power allocation and channel rate control scheme under the given pre-trained model.

[0024] Step 3: Search for the optimal solution. Solve the above resource allocation optimization problem for each pre-trained model according to step 2 to obtain the corresponding minimum objective function value. Search the model that can achieve the minimum objective function value in the lookup table. The model and its corresponding resource allocation solution are the optimal solutions to the original optimization problem (P1).

[0025] This section verifies the effectiveness of the proposed parallel Gaussian channel task-oriented semantic source channel adaptive coding (ADSCC) scheme through image restoration and classification tasks. X The sample whose label corresponds to the intrinsic semantic state S The observation distortion is the mean square error distortion, and the semantic distortion is the Hamming distortion. The CUB-200-2011 dataset is used for experiments. The dataset contains 11,788 images of 200 bird species: training set: 5,994 images; test set: 5,794 images; all images are randomly cropped to 256×256 pixels.

[0026] Neural Network Model Architecture: Feature Extraction Function And feature recovery function : A deep neural network model using a classic hyper-prior model; Image classification task: Using the Resnet-152 network; The lookup table contains 23 pre-trained hyper-prior model deep neural network models, with pixel values ​​ranging from 0.02 to 1.41 per bit Channel setup: Parallel Gaussian channels K =8; Different channel conditions have different noise variances Indicates that the specific noise variance values ​​(in ascending order): (0.4819, 0.6354, 0.8098, 1.4888, 1.6768, 2.8978, 8.8339, 9.1324) Comparison scheme: Deep joint source channel coding scheme; Separate source channel coding scheme: Its source coding scheme is BPG and the channel coding scheme is Rate ( ,256) Polar code and Rate ( ,4096)LDPC codes. The power allocation strategy of the comparison scheme is the truncated channel inversion strategy, that is, the total power is allocated to the front Channels: (19) exist Figure 4 In the experiment, we compared the proposed method with the existing separated source channel coding schemes: BPG+LDPC or BPG+Polar, and the deep joint source channel coding scheme. The horizontal axis is the maximum transmit power, and the vertical axis is the peak signal-to-noise ratio, which is used to measure the quality of image restoration. From the figure, we can see that our method has significant performance gains compared with the existing separated source channel coding scheme and the deep joint source channel coding scheme at different maximum transmit powers.

[0027] exist Figure 5 In the experiment, the horizontal axis is the maximum transmit power and the vertical axis is the accuracy, which is used to measure the quality of the image classification task. Compared with the existing separate source channel coding scheme and deep joint source channel coding scheme, our method also has significant performance gains at different maximum transmit powers.

[0028] The above is a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in other combinations, modifications and environments, and can be modified within the scope of the concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art do not depart from the spirit and scope of the present invention, and should be within the scope of protection of the claims attached to the present invention.

Claims

1. A semantic communication method for semantic source channel adaptive coding under parallel channels, characterized by: The following steps are involved: S1. Construct a communication model for semantic source-channel adaptive coding under parallel channels; Assume that the semantic information source is composed of the joint probability distribution Characterization, where and Represent the external observation and internal semantic state of the source respectively, ( X,S ) represents a semantic source pair, express( X,S ), the sender passes K Parallel channel transmission observation X , so that the receiver can obtain the restored semantic source pair ,in, is the external observation of the recovered source, is the semantic state of the recovered source, where K discrete set express; S2. At the sending end, the semantic source encoder is used to encode the semantic source pair ( X,S ), and the bit stream after each semantic source sample is encoded is assigned to an independent channel for transmission. K channel encoders with different channel rates to protect their respective bit streams against channel errors; S3. At the receiving end, the received signals are decoded by K channel decoders and merged into a single serial stream, which is decoded by a semantic source decoder based on a deep neural network; S4. Determine the source rate and prior information according to any given deep neural network model; S5. Construct optimization problems and perform deep neural network parameters Φ and resource allocation variables Joint optimization.

2. The semantic communication method of semantic source channel adaptive coding in parallel channels according to claim 1, characterized in that: In step S2, at the transmitting end, a semantic source encoder is used to encode the semantic source pair ( X,S ) to encode the semantic source samples in, including: set up( x,s ) represents the semantic source pair ( X,S ), the semantic source encoder can access the observed samples x ,in x Through conditional probability and semantic state s The specific implementation steps are as follows: Step 1: Deep neural network feature extraction: Through the parameters Deep Neural Network x Mapping W dimensional continuous-valued vector y ,Right now: ,in, W Much smaller than x The original dimension ; Indicates that the parameter is Feature extraction function of deep neural network; Step 2: Quantification: y Perform uniform scalar quantization to obtain: ,in represents a uniform scalar quantization operation; Step 3: Arithmetic coding: based on quantized vector The probability mass function of , using lossless entropy coding ȳ Encoding as bitstream b ,in Representation and The corresponding random variable is The expected source rate at which each source sample is encoded Defined as Entropy of: ,in Express expectations.

3. The semantic communication method of semantic source channel adaptive coding under parallel channels according to claim 1, characterized in that: In step S2, the bit stream after encoding each semantic source sample is allocated to an independent channel for transmission, and the bit stream is transmitted by K Channel encoders with different channel rates to protect their respective bit streams against channel errors include: After semantic source coding, the encoded bit stream of each semantic source sample is assigned to an independent channel for transmission; considering the different conditions of these channels, K Channel encoders with different channel rates protect their respective bit streams against channel errors: For k channels, , whose allocated bit stream is defined as ,Depend on Block channel code is used for encoding, where Indicates the number of data bits in each block, L is the code block length, specifically: The total length is Bitstream Divided into blocks, of which Indicates the rounding operation, each block is encoded as a length of L The symbol sequence , Indicates k Channel The first Symbol, k The channel rate of a channel is calculated as ; The average channel usage times for transmitting one source sample is calculated as: (1) in It is through k The ratio of semantic source samples transmitted by each channel is defined as the average bandwidth ratio: , used to measure the average number of channel usages required to observe each element of the state; Channel transmission part, k In a Gaussian channel t The input and output relationship of each block is: (2) in, l =1,..., L , , ; Indicates the transmitted symbol, the mean is zero, and the average power is 1; is the corresponding received symbol; is an independent and identically distributed zero-mean cyclically symmetric complex Gaussian noise with a variance of ; Assign to channel k The power meets the total power constraint: ,in, is the maximum transmit power of the system, k The received signal-to-noise ratio of a channel is defined as .

4. The semantic communication method of semantic source channel adaptive coding in parallel channels according to claim 3, characterized in that: The step S3 comprises: At the receiving end, set k The received symbol sequence of the channel , by the channel decoder k Decode to recovered bitstream ; When a transmission error occurs, the recovered bit stream Not equal to the transmitted bit stream; Then, from K The bit stream of the channel decoder Merge into a single serial stream via a parallel-to-serial converter, waiting to be decoded by a common deep neural network-based semantic source decoder; The decoding process of the semantic source is as follows: Assume that the semantic source sample ( x,s ) is represented as , May correspond to any decoded bitstream , which depends on the semantic source sample ( x,s ) through which parallel channel it is transmitted; It is first decoded by the arithmetic decoder into a recovered feature vector ;then, Input parameters are θ Deep neural network recovery function Restore observation samples x , the restored observation sample is ; Finally, the semantic state is restored through the maximum a posteriori probability scheme s ,Right now: ,in is the restored semantic state, P ( s|x̂,ψ ) is composed of parameters ψ The posterior probability estimated by the deep neural network; Recovered semantic source samples subject to lossy compression and transmission errors; define k The end-to-end observed distortion of the channel and semantic distortion They are: (3) (4) in and denote the observation distortion measure and the semantic distortion measure respectively, Indicates channel k Noise below; and Respectively represent k The end-to-end observed distortion of the channel and semantic distortion The mathematical expectation of for K The expectation of the weighted sum of two distortions on parallel channels is: (5) in α ∈[0,1] is the observation distortion and semantic distortion The weight coefficient between .

5. The semantic communication method of semantic source channel adaptive coding in parallel channels according to claim 4, characterized in that: The step S4 comprises: For any given deep neural network model, the logarithmic value of the observation distortion and the semantic distortion are approximated by the logistic function, namely: (6) (7) in, Describe the neural network parameters in the semantic source codec, Indicates channel k The bit error probability in and They represent the logarithm of the observed distortion under a fixed deep neural network model. and semantic distortion The lower asymptote of ; these two parameters correspond to the distortion caused by source compression; and It is a parameter that characterizes the maximum distortion increment caused by channel error; and is the growth rate parameter of the logistic function, which is used to describe the rate at which the distortion changes with the bit error rate; and is the midpoint parameter of the logistic function, indicating the bit error rate corresponding to the intermediate value of the distortion; parameter , , , , , , and The method is to obtain the result by data fitting, wherein the data fitting method includes minimum mean square error; Then, for the k Gaussian channel, at a signal-to-noise ratio , code block length L and channel rate Under the condition of , the bit error probability under random channel block coding is approximately: (8) in, satisfy , The function is defined as , is the channel capacity expression, satisfying .

6. The semantic communication method of semantic source channel adaptive coding in parallel channels according to claim 1, characterized in that: In step S5, the optimization problem objective is to minimize the average distortion by optimizing the following two aspects: : Parameters of semantic source encoder and decoder and K The power allocation and channel rate adaptation strategy of parallel channels, the corresponding optimization problem is: (9) Through the optimization algorithm based on model selection, the deep neural network parameters Φ and resource allocation variables are Joint optimization.

7. The semantic communication method of semantic source channel adaptive coding in parallel channels according to claim 6, characterized in that: The deep neural network parameters Φ and resource allocation variables are optimized by the model selection-based optimization algorithm. Joint optimization of A1. Pre-trained model construction: Build a lookup table containing N pre-trained deep neural network models: A101. The pre-training process refers to training the semantic source codec with parameters By changing the hyperparameters of the neural network, N deep neural networks with different performances are obtained. For any deep neural network, the training process is as follows: Consider a semantic dataset consisting of a large number of semantic source samples ( x,s ) and pre-set the hyperparameters of the neural network; the semantic source encoder only inputs the observed samples x , the input of the neural network is just a large number of observation samples x ; Observation sample x First, the parameters are input into the semantic encoder. The output is then directly fed into a deep neural network with parameters θ The deep neural network output is the restored observation sample ;at last, Input parameters are The deep neural network output is the restored semantic state ; Correspondingly, the loss function of the neural network is s and Distortion between x and The weighted sum between distortions, the training goal is to make the loss function as small as possible; use the back propagation algorithm to calculate the gradient, use the gradient descent method to update the network parameter Φ, and iterate the optimization until convergence or reach the preset number of training rounds; After training N deep neural networks with different performances, N pre-trained deep neural network models are obtained; A102. Fit the distortion characteristics of each pre-trained deep neural network model. The specific steps are as follows: (1) Setting the bit error rate A set of discrete values ​​of , covering the error conditions under actual channel conditions; (2) For each Value: A large number of source samples ( x,s ) Input semantic source encoder, each sample corresponds to an output bit stream b ,exist b The probability of error caused by random introduction bit error, and use this bit stream with bit errors as the recovery bit stream ,Then After being decoded by the semantic source decoder, the corresponding and ; Correspondingly, the source rate The calculation method is: calculate the bit stream b The average length of Finally, according to equations (3) and (4), the corresponding observation distortion is obtained and semantic distortion The actual value of (3) For each pre-trained model, the parameters in generalized logistic functions (6) and (7) are fitted using the minimum mean square error criterion based on the data obtained from (1) and (2). , , , , , , and ; A103. Save each pre-trained deep neural network model and the corresponding source rate in the lookup table , and parameters , , , , , , and ; A2. Resource allocation optimization: For each given pre-trained model, i.e., fixed deep neural network parameter Φ, classical optimization techniques, including continuous convex approximation algorithm, are used to solve the optimization problem P1, thereby obtaining the power allocation and channel rate control scheme under the given pre-trained model; A3. Optimal solution search: Solve the resource allocation optimization problem for each pre-trained model to obtain the corresponding minimum objective function value; search the lookup table for a model that can achieve the minimum objective function value. This model and its corresponding resource allocation solution are the optimal solutions to the original optimization problem P1.

Images