Power distribution network-oriented edge-end collaborative semantic communication method and system

Abstract

The embodiment of the invention provides a power distribution network-oriented edge-end collaborative semantic communication method and system, and belongs to the technical field of communication, the method is executed by terminal side equipment, and the method comprises the following steps: periodically constructing a corresponding image test sample set; performing semantic coding and channel coding on the image test sample set in sequence; the edge server carries out channel decoding and semantic decoding on the received transmission sample set of each terminal side device in sequence; multiple rounds of image test sample set transmission with the edge server are executed, and the edge server executes iteration of each model parameter and establishes communication connection with each terminal side device based on each correspondingly output model parameter; and periodically sending the acquired actual image data to the corresponding edge server based on the established communication connection. According to the scheme of the invention, based on improved semantic communication in the power distribution network, not only is the accuracy of data transmission improved, but also the anti-interference capability of the system to channel interference is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to an edge-end collaborative semantic communication method for a distribution network and an edge-end collaborative semantic communication system for a distribution network. Background Art

[0002] As a key link in power transmission, the stable and efficient operation of the distribution network is directly related to the guarantee of power supply. In modern distribution networks, with the development of intelligent power systems, the number and types of terminal devices are increasing. These terminal devices are widely deployed in various environments to collect a large amount of data such as voltage, current, frequency, equipment status, fault conditions, and safety conditions. The collection and transmission of these data are of great significance for the real-time monitoring, control, and optimization of distribution networks. However, the existing data transmission solutions face many technical problems in practical applications, which seriously affect the overall performance and reliability of the system.

[0003] As the number of terminal devices increases, the amount of data grows exponentially. Traditional data transmission methods require that these data be transmitted to edge servers for processing via wireless communication. This centralized data processing mode brings a huge communication burden, leading to congestion in the transmission channel and increased transmission delays. In addition, centralized data processing also causes the edge server to bear huge computing pressure, which easily forms a processing bottleneck and reduces the response speed of the system. In a complex power distribution environment, data transmission faces multiple threats such as electromagnetic interference, network delays, channel interference, and malicious attacks. These factors not only lead to an increase in the bit error rate during data transmission, but may also cause packet loss and transmission errors, ultimately affecting the accurate recovery of the original data by the edge server. The difficulty of this information recovery directly affects the accuracy of key applications such as fault monitoring and status monitoring, which may lead to delayed fault detection and even pose a hidden danger to the safe operation of the power system.

[0004] Existing data transmission schemes lack sufficient flexibility and robustness when dealing with dynamically changing distribution environments. Faced with uncertain channel conditions and network conditions, traditional transmission methods find it difficult to adaptively adjust transmission strategies, further exacerbating the delay and reliability issues of data transmission. In general, the technical problems of existing schemes in large-scale distribution networks include: heavy communication burden, large transmission delay, obvious processing bottleneck, and high bit error rate and difficulty in data recovery in complex environments. These problems seriously restrict the real-time and accuracy of distribution network monitoring and control, and there is an urgent need for an improved solution that can effectively reduce the communication burden, improve data transmission efficiency and anti-interference ability. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide an edge-end collaborative semantic communication method and system for distribution networks, so as to at least solve the problems of heavy communication burden and large transmission delay existing in the existing distribution network edge-end collaborative communication.

[0006] In order to achieve the above-mentioned purpose, the first aspect of the present invention provides an edge-end collaborative semantic communication method for a distribution network, which is applied to semantic communication between an edge server and a terminal-side device, the edge server is communicatively connected to a plurality of terminal-side devices, and the method is executed by the terminal-side device, the method comprising: periodically collecting image data of a set position, and periodically constructing a corresponding image test sample set; sequentially performing semantic coding and channel coding on the image test sample set to obtain a transmission sample set, and sending the transmission sample set to a corresponding edge server; the edge server sequentially performs channel decoding and semantic decoding on the transmission sample set received from each terminal-side device, correspondingly obtains a decoded image sample set of each terminal-side device, and calculates a transmission loss value based on a comparison relationship between each decoded image sample set and the corresponding image test sample set; with the transmission loss value being minimized as an iteration target, multiple rounds of image test sample set transmission are performed between the edge server, the edge server performs semantic coding model parameter, channel coding model parameter, channel decoding model parameter and semantic decoding model parameter iteration based on a stochastic gradient descent algorithm, and establishes a communication connection with each terminal-side device based on the corresponding output model parameters; based on the established communication connection, the collected actual image data is periodically sent to the corresponding edge server.

[0007] Optionally, the encoding rule for performing semantic encoding on the image test sample set is:

[0008]

[0009] in, is the semantic encoder; α k is the semantic encoding model parameter of the kth terminal side device; I is the image test sample set; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; E I It is the semantic feature after semantic encoding.

[0010] Optionally, a coding rule for performing channel coding on the image test sample set is:

[0011]

[0012] in, is the channel encoder; β k is the channel coding model parameter of the kth terminal side device, I is the image test sample set; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; X Iis the semantic feature after channel coding.

[0013] Optionally, the transmission rule for sending the transmission sample set to the corresponding edge server is: based on an additive white Gaussian noise channel, the corresponding edge server is used as a receiving end to perform the transmission of the transmission sample set, and the transmission rule is:

[0014]

[0015] in, is the semantic feature after interference; X I is the semantic feature after channel coding; N is the noise; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively.

[0016] Optionally, when the edge server performs decoding on the received transmission sample set of each terminal side device, it is configured to:

[0017] Channel decoding and semantic decoding are performed on the received transmission sample sets of each terminal side device in sequence to obtain the corresponding decoded image sample sets; wherein the channel decoding rule is: The semantic decoding rules are: in, represents the channel encoder; χ represents the channel decoding model parameters deployed on the edge server; represents the channel encoder; δ represents the parameters of the semantic decoding model deployed on the edge server; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; Y I is the semantic feature after channel decoding; is a set of decoded image samples.

[0018] Optionally, when executing the first round of iteration, the edge server is configured to: perform parameter aggregation based on the semantic coding model parameters and channel coding model parameters of each terminal side device to obtain global model parameters; based on the global model parameters, complete a transmission sample set decoding, and use the corresponding channel decoding model parameters and semantic decoding model parameters as the initial channel decoding model parameters and initial semantic decoding model parameters of the iteration.

[0019] Optionally, the edge server performs parameter aggregation based on the semantic coding model parameters and channel coding model parameters of each terminal side device to obtain global model parameters, including: the edge server compares the transmission loss values ​​corresponding to each terminal side device respectively, and performs weight allocation on each terminal side device based on the transmission loss values ​​corresponding to each terminal side device, where the smaller the transmission loss value, the greater the corresponding weight; based on the weight allocation result, the semantic coding model parameters and channel coding model parameters of each terminal side device are aggregated to obtain global model parameters, which are expressed as:

[0020]

[0021]

[0022] Among them, α and β are global model parameters; K is the number of devices on the terminal side; ω k is the allocation weight of the kth terminal side device; α k is the semantic encoding model parameter of the kth terminal side device; β k N is the channel coding model parameter of the kth terminal side device; k is the channel noise of wireless communication between the kth terminal-side device and the edge server.

[0023] Optionally, during each round of iteration, the edge server is configured to: send corresponding semantic coding model parameters and channel coding model parameters respectively, and update the semantic coding model parameters and channel coding model parameters of each terminal side device based on the transmission loss value after this round of iteration, as the initial semantic coding model parameters and initial channel coding model parameters of the corresponding terminal side device for the next iteration round; perform sequential learning on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device, and perform channel decoding model parameter and semantic decoding model parameter update once each time the learning of a terminal side device is completed until this round of iteration is completed, and use the channel decoding model parameters and semantic decoding model parameters updated after the last terminal side device is learned as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server for the next iteration round.

[0024] Optionally, the edge server updates the initial coding model parameters and initial channel coding model parameters of each terminal side device in the next iteration round according to the following update rule:

[0025]

[0026]

[0027] in, is the initial semantic coding model parameter of the next iteration round of the k-th terminal side device; is the initial channel coding model parameter of the next iteration round of the k-th terminal side device; are the initial semantic coding model parameters of the kth terminal-side device in this round; is the initial channel coding model parameter of the kth terminal side device in this round; η is the learning rate; is the gradient of the transmission loss value corresponding to the kth terminal-side device in this round.

[0028] Optionally, the edge server performs sequential learning on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device, and performs an update rule for updating the channel decoding model parameters and the semantic decoding model parameters once each time the learning of a terminal side device is completed:

[0029]

[0030]

[0031] in, The channel decoding model parameters corresponding to the channel decoding of the k-th terminal side device performed by the edge server; The semantic decoding model parameters corresponding to the semantic decoding of the k-th terminal-side device performed by the edge server; The channel decoding model parameters corresponding to the channel decoding of the k-1th terminal side device performed by the edge server; is the semantic decoding model parameter corresponding to the semantic decoding of the k-1th terminal side device performed by the edge server; η is the learning rate; is the gradient of the transmission loss value corresponding to the k-1th terminal-side device.

[0032] Optionally, the rule for the edge server to use the channel decoding model parameters and semantic decoding model parameters updated after the last terminal-side device has learned as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server in the next iteration round is:

[0033]

[0034]

[0035] Among them, χ (t+1) is the initial channel decoding model parameter of the edge server in the next iteration; (t+1) Initial semantic decoding model parameters for the edge server in the next iteration; Signal decoding model parameters for the last terminal-side device channel decoding performed by the edge server in this round; The semantic decoding model parameters for the last terminal-side device semantic decoding performed by the edge server in this round; η is the learning rate; It is the gradient of the transmission loss value corresponding to the last terminal-side device in this round.

[0036] A second aspect of the present invention provides an edge-end collaborative semantic communication method for a distribution network, which is applied to semantic communication between an edge server and a terminal-side device, wherein the edge server is communicatively connected to a plurality of terminal-side devices, and the method is executed by the edge server, and the method comprises: periodically receiving a transmission sample set uploaded by each terminal-side device; wherein the transmission sample set is obtained based on each terminal-side device through the following rules: periodically collecting image data of a setting position, and periodically constructing a corresponding image test sample set; sequentially performing semantic coding and channel coding on the image test sample set to obtain a transmission sample set; and performing channel coding on the transmission sample set of each received terminal-side device. This set performs channel decoding and semantic decoding in sequence, obtains the decoded image sample set of each terminal side device accordingly, and calculates the transmission loss value based on the comparison relationship between each decoded image sample set and the corresponding image test sample set; takes the minimum transmission loss value as the iteration goal, performs multiple rounds of image test sample set transmission between each terminal side device, and performs iteration of semantic coding model parameters, channel coding model parameters, channel decoding model parameters and semantic decoding model parameters based on the stochastic gradient descent algorithm, and establishes a communication connection with each edge side device based on the corresponding output model parameters; based on the established communication connection, the actual image data collected by each edge side device is periodically recovered.

[0037] Optionally, during each round of iteration, the method includes: sending corresponding semantic coding model parameters and channel coding model parameters respectively, and updating the semantic coding model parameters and channel coding model parameters of each terminal side device based on the transmission loss value after this round of iteration, as the initial semantic coding model parameters and initial channel coding model parameters of the corresponding terminal side device for the next iteration round; performing sequential learning on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device, and performing a channel decoding model parameter and semantic decoding model parameter update once each time the learning of a terminal side device is completed until this round of iteration is completed, and using the channel decoding model parameters and semantic decoding model parameters updated after the last terminal side device learning as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server for the next iteration round.

[0038] Optionally, the edge server updates the initial coding model parameters and initial channel coding model parameters of each terminal side device in the next iteration round according to the following update rule:

[0039]

[0040]

[0041] in, is the initial semantic coding model parameter of the next iteration round of the k-th terminal side device; is the initial channel coding model parameter of the next iteration round of the k-th terminal side device; are the initial semantic coding model parameters of the kth terminal-side device in this round; is the initial channel coding model parameter of the kth terminal side device in this round; η is the learning rate; is the gradient of the transmission loss value corresponding to the kth terminal-side device in this round.

[0042] Optionally, the edge server performs sequential learning on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device, and performs an update rule for updating the channel decoding model parameters and the semantic decoding model parameters once each time the learning of a terminal side device is completed:

[0043]

[0044]

[0045] in, The channel decoding model parameters corresponding to the channel decoding of the k-th terminal side device performed by the edge server; The semantic decoding model parameters corresponding to the semantic decoding of the k-th terminal-side device performed by the edge server; The channel decoding model parameters corresponding to the channel decoding of the k-1th terminal side device performed by the edge server; is the semantic decoding model parameter corresponding to the semantic decoding of the k-1th terminal side device performed by the edge server; η is the learning rate; is the gradient of the transmission loss value corresponding to the k-1th terminal-side device.

[0046] Optionally, the rule for the edge server to use the channel decoding model parameters and semantic decoding model parameters updated after the last terminal-side device has learned as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server in the next iteration round is:

[0047]

[0048]

[0049] Among them, χ (t+1) is the initial channel decoding model parameter of the edge server in the next iteration; (t+1) Initial semantic decoding model parameters for the edge server in the next iteration; Signal decoding model parameters for the last terminal-side device channel decoding performed by the edge server in this round; The semantic decoding model parameters for the last terminal-side device semantic decoding performed by the edge server in this round; η is the learning rate; It is the gradient of the transmission loss value corresponding to the last terminal-side device in this round.

[0050] The third aspect of the present invention provides an edge-end collaborative semantic communication system for distribution networks, which is applied to semantic communication between an edge server and a terminal-side device. The edge server is communicatively connected to multiple terminal-side devices. The system includes: a terminal-side device for executing the above-mentioned edge-end collaborative semantic communication method for distribution networks, and an edge server for executing the above-mentioned edge-end collaborative semantic communication method for distribution networks.

[0051] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, enables the computer to execute the above-mentioned edge collaborative semantic communication method for distribution networks.

[0052] A fifth aspect of the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the above-mentioned edge collaborative semantic communication method for distribution networks.

[0053] Through the above technical scheme, the edge-end collaborative semantic communication method for distribution network proposed in the scheme of the present invention significantly improves the efficiency and reliability of data transmission in distribution network by applying semantic communication technology between edge servers and multiple terminal devices. First, the terminal device periodically collects image data and performs semantic coding and channel coding locally, which greatly reduces the data dimension, thereby reducing the communication burden of data transmission. Subsequently, the encoded data is sent to the edge server, which performs channel decoding and semantic decoding on the received sample set, restores the original image data, and calculates the transmission loss value. Through multiple rounds of iterative optimization, the edge server uses the stochastic gradient descent algorithm to continuously adjust and optimize the model parameters of semantic coding, channel coding, channel decoding, and semantic decoding, so that the system can adaptively reduce the transmission loss value. This collaborative optimization process not only improves the accuracy of data transmission, but also enhances the system's ability to resist channel interference.

[0054] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0056] Figure 1 It is a flowchart of the steps of an edge collaborative semantic communication method for a distribution network provided by an embodiment of the present invention;

[0057] Figure 2 It is a system structure diagram of an edge collaborative semantic communication system for distribution networks provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0059] The core of the semantic communication method is to extract the semantic information from the original information through the deployed semantic extraction model at the sending end, and restore it through the wireless channel, and then restore it by using the semantic recovery model at the receiving end. This method can not only retain the core meaning of the information, but also significantly reduce the amount of data and maintain high transmission performance in a low signal-to-noise ratio environment. In addition, the receiving end can also directly apply the received semantic information to specific tasks, such as fault detection, which improves the efficiency and adaptability of the communication system.

[0060] In recent years, research on semantic communication has made significant progress. For example, the end-to-end semantic communication system proposed by Bourtsoulatze et al. in 2019 proved that semantic communication based on deep learning can improve the transmission performance of image data under low signal-to-noise ratio conditions, overcoming the "steep wall effect" in traditional digital communication. In 2021, Xie et al. further used the Transformer codec to realize an end-to-end semantic communication system for text data transmission, demonstrating the great potential of deep learning in semantic communication. In addition, the neural network-based semantic communication system for image transmission proposed by Zhang et al. in 2022 can adapt to dynamic data sets while maintaining high performance of data recovery and task execution under the condition that the sending end is unknown to the task and channel environment.

[0061] However, although semantic communication has shown great potential in reducing data volume and anti-interference performance, existing research mainly focuses on single-task or centralized scenarios. In the actual application of distribution networks, terminal sensing devices are usually deployed in various locations in a distributed manner, collecting different types of data and sending them to centralized servers via wireless transmission. This distributed scenario poses new challenges to semantic communication, and existing methods are difficult to effectively support edge-to-edge collaborative semantic communication. Therefore, the development of an edge-to-edge collaborative semantic communication method for distribution networks suitable for distribution network scenarios has become an urgent problem to be solved.

[0062] Figure 1 1 is a method flow chart of a method for edge-end collaborative semantic communication for distribution network provided by an embodiment of the present invention. Figure 1As shown, an embodiment of the present invention provides an edge-end collaborative semantic communication method for a distribution network, the method comprising:

[0063] Step S10: Each terminal-side device periodically collects image data of a set location and periodically constructs a corresponding image test sample set.

[0064] Specifically, multiple terminal-side devices are distributed in different physical locations and are responsible for periodically collecting image data at their locations. These image data are usually used to monitor and evaluate the operating status of the distribution network, such as the working condition of the equipment, changes in the environment, and possible signs of failure. In order to ensure the timeliness and accuracy of the data, the terminal device will periodically build the corresponding image test sample set. These sample sets not only contain image data of the current environment, but also historical data collected over a period of time for further pattern recognition and predictive analysis. After completing the collection of image data, the terminal device will pre-process the data. This step includes denoising the original image, removing redundant information, and format standardization to ensure that the data occupies the minimum bandwidth resources during transmission.

[0065] In one possible implementation, the construction of the image test sample set is not just a simple data collection, but also involves data preprocessing and screening. The terminal device will perform preliminary processing on the collected raw image data, such as removing noise, enhancing image clarity, and converting the image format for subsequent transmission and processing. These operations can significantly reduce redundant information in the data, ensuring that when constructing the image test sample set, only the key information that best reflects the current environment is retained.

[0066] Step S20: Each terminal-side device sequentially performs semantic coding and channel coding on the image test sample set to obtain a transmission sample set, and sends the transmission sample set to a corresponding edge server.

[0067] Specifically, the encoding rule for performing semantic encoding on the image test sample set is:

[0068]

[0069] in, is the semantic encoder; α k is the semantic encoding model parameter of the kth terminal side device; I is the image test sample set; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; E I It is the semantic feature after semantic encoding.

[0070] Further, the coding rule of channel coding is performed on the image test sample set:

[0071]

[0072] in, is the channel encoder; β k is the channel coding model parameter of the kth terminal side device; I is the image test sample set; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; X I is the semantic feature after channel coding.

[0073] In an embodiment of the present invention, the collected image data is processed by a semantic encoder of a terminal device. The semantic encoder extracts features from the image data through a deep learning model to generate semantic features of the image. The process of semantic encoding greatly reduces the data dimension, retaining only the semantic features that can represent the core information of the image, making the data more concise and efficient during transmission. In addition, the application of deep learning models enhances the accuracy and generalization ability of feature extraction, so that the extracted semantic features can better adapt to different image data.

[0074] Furthermore, the semantic features are further channel-encoded. Based on the convolutional neural network architecture, the channel encoder further maps the semantic features to low-dimensional features, thereby reducing the bandwidth required for data transmission and enhancing the data's ability to resist noise interference during transmission. Through channel coding, the data is further compressed and has a stronger anti-interference ability, providing a guarantee for subsequent data transmission.

[0075] Based on the solution of the present invention, by performing semantic coding and channel coding on the terminal device side, the data has been greatly compressed before transmission, retaining key semantic information. This allows more effective information to be transmitted under limited bandwidth conditions, reducing the communication burden. The application of channel coding not only reduces the data dimension, but also increases the anti-interference ability of the data during transmission. Even in complex communication environments (such as electromagnetic interference, signal attenuation, etc.), the data can still maintain a high degree of integrity and accuracy. The introduction of deep learning models makes the semantic coding process more flexible and can adapt to different image types and features. Regardless of the complexity of the image or the detailed information it contains, the encoder can effectively extract features that are useful for the task, thereby enhancing the adaptability of the system.

[0076] Furthermore, the transmission rule for sending the transmission sample set to the corresponding edge server is:

[0077] Based on the additive white Gaussian noise channel, the corresponding edge server is used as the receiving end to perform the transmission of the transmission sample set, and the transmission rule is:

[0078]

[0079] in, is the semantic feature after interference; X I is the semantic feature after channel coding; N is the noise; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively.

[0080] In an embodiment of the present invention, considering that wireless communication is usually adopted between the terminal side device and the edge server, the additive white Gaussian noise channel (Additive White Gaussian Noise, AWGN) is selected as the channel model. The AWGN channel model is a basic channel model commonly used in wireless communication. It simulates the interference in the wireless channel by additive noise. Its characteristics are that the noise is evenly distributed over the entire spectrum and has zero mean and constant power spectrum density. In this model, the edge server, as the receiving end, receives the semantic feature signal from the terminal device. These signals will inevitably be interfered by noise during transmission, causing signal distortion or distortion. The introduction of this noise model enables the system to take into account the interference in the actual communication environment when designing and optimizing the channel decoder, so that the decoder can better process the received signal affected by noise. The use of the AWGN channel model, although an idealized model, can effectively simulate the basic interference characteristics in the wireless channel and is an important basis for designing a robust decoding algorithm.

[0081] Step S30: The edge server performs channel decoding and semantic decoding on the received transmission sample sets of each terminal side device in sequence, obtains the corresponding decoded image sample sets of each terminal side device, and calculates the transmission loss value based on the comparison relationship between each decoded image sample set and the corresponding image test sample set.

[0082] Specifically, channel decoding and semantic decoding are performed on the received transmission sample sets of each terminal side device in sequence to obtain a corresponding decoded image sample set; wherein the channel decoding rule is: The semantic decoding rules are: in, represents the channel encoder; χ represents the channel decoding model parameters deployed on the edge server; represents the channel encoder; δ represents the parameters of the semantic decoding model deployed on the edge server; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; Y I is the semantic feature after channel decoding; is a set of decoded image samples.

[0083] In an embodiment of the present invention, after receiving the transmission sample set from each terminal side device, the edge server will perform channel decoding and semantic decoding in sequence to obtain the corresponding decoded image sample set. The edge server performs channel decoding on the received transmission sample. The channel decoder is used to eliminate interference introduced by noise, channel fading, etc. during the data transmission process, and restore the encoded semantic features to a signal close to the original transmission features. The success or failure of channel decoding directly affects the accuracy of subsequent semantic decoding. Therefore, the design of the channel decoder must have a strong anti-interference ability to restore the original semantic features to the greatest extent.

[0084] Furthermore, the edge server performs semantic decoding on the decoded signal. The semantic decoder uses the model parameters deployed on the edge server to convert the features after channel decoding into the final decoded image sample set. The process of semantic decoding is actually to reconstruct the semantic information in the data and restore it to image data similar to the original image sample. This step not only requires the decoder to have strong feature extraction and restoration capabilities, but also requires training to ensure that the decoded image sample set is highly consistent with the original data in terms of visual effects and semantic expression.

[0085] Based on the scheme of the present invention, through channel decoding, the edge server can effectively eliminate noise and interference in the transmission process to ensure the integrity of the data. The efficiency of channel decoding directly determines whether the transmitted data can be accurately restored, thereby providing a solid foundation for subsequent semantic decoding. When processing the decoded data, the semantic decoder can reconstruct the semantic features of the original image with high accuracy according to the model parameters. This efficient semantic restoration ensures that the final decoded image sample set has good visual effects and semantic consistency while retaining the original information. The dual processing of channel decoding and semantic decoding not only enhances the system's adaptability to noise and signal fading, but also improves the robustness and reliability of data transmission. This dual decoding strategy enables the system to maintain high decoding accuracy and data recovery capabilities in a complex communication environment.

[0086] Furthermore, after completing channel decoding and semantic decoding, the edge server will obtain a decoded image sample set. In order to evaluate the fidelity of information during data transmission, the system needs to compare the decoded image sample set with the original image test sample set to calculate the transmission loss value. The transmission loss value is usually calculated using a loss function that measures the difference between images, such as Mean Squared Error (MSE) or Structural Similarity Index (SSIM). These loss functions can accurately capture the subtle differences between the decoded image and the original image at the pixel level or structural level. The smaller the calculated loss value, the closer the decoded image is to the original image, indicating that the quality of the data transmission and decoding process is higher; on the contrary, the larger the loss value, the more information loss or distortion occurs during the transmission process, and the encoding and decoding process needs to be further optimized.

[0087] Furthermore, by regularly calculating the transmission loss value, the edge server can monitor the transmission quality in real time and adjust the model parameters of the channel encoder, channel decoder, semantic encoder and semantic decoder according to the change of the loss value. This feedback-based optimization mechanism can significantly improve the system's adaptive ability, enabling the system to continuously maintain efficient data transmission and recovery performance in a dynamically changing communication environment.

[0088] Based on the solution of the present invention, by comparing the decoded image with the original image, the transmission loss value provides an objective measure of data recovery accuracy. This quantitative indicator enables the system to accurately identify problems in the transmission process and make targeted improvements, thereby improving the data restoration accuracy of the entire system. Based on the feedback mechanism of the transmission loss value, the system can continuously adjust the encoding and decoding parameters for iterative optimization. This dynamic adjustment process enables the system to quickly adapt to different communication conditions and environmental changes, thereby maintaining stable performance in various complex scenarios. The transmission loss value not only helps the system identify errors and noise effects during the transmission process, but also promotes the system's adaptability and recovery capabilities in noisy and interfering environments. This process enhances the robustness of the system, enabling the system to provide higher reliability in practical applications.

[0089] Step S30: The edge server performs multiple rounds of image test sample set transmission between the terminal side device and the edge server with the minimum transmission loss value as the iteration target. The edge server performs iteration of semantic coding model parameters, channel coding model parameters, channel decoding model parameters and semantic decoding model parameters based on the stochastic gradient descent algorithm, and establishes a communication connection with each terminal side device based on the corresponding output model parameters.

[0090] Specifically, when executing the first round of iteration, the edge server is configured to: perform parameter aggregation based on the semantic coding model parameters and channel coding model parameters of each terminal side device to obtain global model parameters; based on the global model parameters, complete a transmission sample set decoding, and use the corresponding channel decoding model parameters and semantic decoding model parameters as the initial channel decoding model parameters and initial semantic decoding model parameters of the iteration.

[0091] Furthermore, the edge server performs parameter aggregation based on the semantic coding model parameters and channel coding model parameters of each terminal side device to obtain global model parameters, including:

[0092] The edge server compares the transmission loss values ​​corresponding to each terminal side device respectively, and performs weight allocation for each terminal side device based on the transmission loss values ​​corresponding to each terminal side device. The smaller the transmission loss value, the greater the corresponding weight. Based on the weight allocation result, the semantic coding model parameters and channel coding model parameters of each terminal side device are aggregated to obtain the global model parameters, which are expressed as:

[0093]

[0094]

[0095] Among them, α and β are global model parameters; K is the number of devices on the terminal side; ω k is the allocation weight of the kth terminal side device; α k is the semantic encoding model parameter of the kth terminal side device; β k N is the channel coding model parameter of the kth terminal side device; k is the channel noise of wireless communication between the kth terminal-side device and the edge server.

[0096] In an embodiment of the present invention, the edge server receives the model parameters of the semantic encoder and channel encoder of multiple terminal devices. Each terminal device independently trains and adjusts these parameters according to its own environment and data characteristics. Due to the different environmental complexity and data characteristics of different terminal devices, their model parameters may be different. Therefore, the task of the edge server is to generate a set of general model parameters that can adapt to the global situation by aggregating these model parameters.

[0097] Furthermore, during the aggregation process, the edge server will consider the transmission loss value (loss) of each terminal device and assign corresponding weights based on this. The calculation of weights takes into account the contribution of each terminal device to the model performance. If the model of a terminal device performs well in image restoration and has a low loss value, it means that the model parameters of the device are highly representative and should be given a higher weight; otherwise, its weight should be reduced. The weight calculation process includes two main parts. The first part is to normalize the loss values ​​of all terminal devices to ensure that the sum of all weights is 1; the second part ensures that there is a linear relationship between the weight and the loss value. The specific calculation formula is:

[0098]

[0099] Through this weight distribution method, the system can more accurately reflect the model contribution of each terminal device, making the aggregated global model parameters more adaptable to the characteristics of global data.

[0100] Furthermore, after the aggregation of the global model parameters is completed, the edge server will perform the first decoding of the transmitted sample set based on these parameters. After the decoding is completed, the channel decoding model parameters and the semantic decoding model parameters will be initialized and used for the subsequent decoding process. This process ensures that in the subsequent decoding process, the system can start from an optimized initial state and reduce the number of iterations.

[0101] Furthermore, during each round of iteration, the edge server is configured to: send the corresponding semantic coding model parameters and channel coding model parameters respectively, and update the semantic coding model parameters and channel coding model parameters of each terminal side device based on the transmission loss value after this round of iteration, as the initial semantic coding model parameters and initial channel coding model parameters of the corresponding terminal side device for the next iteration round; perform sequential learning on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device, and perform a channel decoding model parameter and semantic decoding model parameter update once each time the learning of a terminal side device is completed until this round of iteration is completed, and use the channel decoding model parameters and semantic decoding model parameters updated after the last terminal side device is learned as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server for the next iteration round.

[0102] In an embodiment of the present invention, at the beginning of each round of iteration, the edge server sends the semantic coding model parameters and channel coding model parameters aggregated in the previous round to each terminal device. After receiving these parameters, the terminal device will use them as initial parameters, and further learn and adjust them in combination with its own local data and environmental characteristics. This method ensures that each terminal device can be trained under more optimized initial conditions in the new round of iteration, thereby improving the convergence speed and model accuracy of the entire system. During each iteration, the edge server updates the semantic coding model parameters and channel coding model parameters of each terminal device in real time based on the transmission loss value of the current round. These updated parameters are not only used for the optimization of this round of iteration, but also as the initial conditions for the next round of iteration, gradually approaching the optimal solution. The edge server performs sequential learning on each terminal device, that is, processes the data of each terminal device in sequence, and updates the channel decoding model parameters and semantic decoding model parameters. The edge server updates the model parameters once each time the learning of a terminal device is completed. Such sequential learning ensures that the learning results of each terminal device can be gradually accumulated and optimized. Ultimately, the updated results after learning of the last terminal device will be used as the initial parameters for the next round of iterations, allowing the system to start from a better state in each round and continuously improve system performance.

[0103] Furthermore, the edge server updates the initial coding model parameters and initial channel coding model parameters of each terminal side device in the next iteration round according to the following update rule:

[0104]

[0105]

[0106] in, is the initial semantic coding model parameter of the next iteration round of the k-th terminal side device; is the initial channel coding model parameter of the next iteration round of the k-th terminal side device; are the initial semantic coding model parameters of the kth terminal-side device in this round; is the initial channel coding model parameter of the kth terminal side device in this round; η is the learning rate; is the gradient of the transmission loss value corresponding to the kth terminal-side device in this round. and The calculation rules are:

[0107]

[0108]

[0109] in, is the channel noise of the downlink wireless link.

[0110] In an embodiment of the present invention, the edge server first calculates the transmission loss value by comparing the decoded image sample with the original image sample, and then adjusts the model parameters according to the loss value. Specifically, the loss value reflects the size of the error introduced by the current model in the process of processing the transmission. Therefore, by optimizing the loss value, the model can gradually converge to a better state. After each round of training, the updated semantic coding model parameters and channel coding model parameters will be used as the initial parameters for the next round of training. This gradual update mechanism enables the system to continuously reduce transmission errors and improve the accuracy of data transmission in multiple rounds of iterations.

[0111] Furthermore, the edge server will perform sequential learning on each terminal device in each iteration. After completing the learning of a terminal device, the edge server will update its channel decoding model parameters and semantic decoding model parameters, and use these updated parameters as initial parameters to continue training the next terminal device. This sequential learning method ensures that the training results of each terminal device can be gradually accumulated, and finally form a more accurate global model.

[0112] Furthermore, the edge server performs sequential learning on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device. After each learning of a terminal side device is completed, the update rule for performing a channel decoding model parameter and a semantic decoding model parameter update is as follows:

[0113]

[0114]

[0115] in, The channel decoding model parameters corresponding to the channel decoding of the k-th terminal side device performed by the edge server; The semantic decoding model parameters corresponding to the semantic decoding of the k-th terminal-side device performed by the edge server; The channel decoding model parameters corresponding to the channel decoding of the k-1th terminal side device performed by the edge server; is the semantic decoding model parameter corresponding to the semantic decoding of the k-1th terminal side device performed by the edge server; η is the learning rate; is the gradient of the transmission loss value corresponding to the k-1th terminal-side device.

[0116] Furthermore, the rule that the edge server uses the channel decoding model parameters and semantic decoding model parameters updated after the last terminal-side device learning as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server in the next iteration round is:

[0117]

[0118]

[0119] Among them, χ (t+1) is the initial channel decoding model parameter of the edge server in the next iteration; (t+1) Initial semantic decoding model parameters for the edge server in the next iteration; Signal decoding model parameters for the last terminal-side device channel decoding performed by the edge server in this round; The semantic decoding model parameters for the last terminal-side device semantic decoding performed by the edge server in this round; η is the learning rate; It is the gradient of the transmission loss value corresponding to the last terminal-side device in this round.

[0120] In an embodiment of the present invention, in each round of iteration, the edge server will first receive and process the data transmitted by each terminal side device, and calculate the transmission loss value of the current round. Based on this loss value, the edge server updates the channel decoding model parameters and the semantic decoding model parameters in sequence through the stochastic gradient descent (SGD) algorithm. In this sequential learning process, the model parameter adjustment of each terminal side device is not only limited to the local area, but also affects the global model parameters of the edge server. Each time the learning of a terminal device is completed, the edge server will update the channel decoding model parameters and the semantic decoding model parameters, and use this as the basis for the next terminal device learning. This sequential update strategy ensures that the system can gradually optimize the model parameters in multiple rounds of iterations, thereby continuously improving the accuracy and efficiency of decoding.

[0121] Furthermore, at the end of a round, the edge server will determine the channel decoding model parameters and semantic decoding model parameters based on the learning results of the last terminal device. These parameters will be used as initial parameters in the next round to start a new iteration. This cyclic process will continue until the transmission loss value of the system reaches the minimum and tends to be stable, indicating that the system has reached the optimal state.

[0122] Preferably, in each round of iteration, the edge server updates the model parameters of channel decoding and semantic decoding by sequentially processing the data of each terminal device. After each update, the system calculates the transmission loss value of the current round, that is, the difference between the decoded image and the original image. Since the model parameter update of each round is based on the optimization results of the previous round, the transmission loss value usually decreases gradually with the increase of rounds. This cycle does not proceed indefinitely, but stops after certain conditions are met. For example, a threshold or convergence criterion is preset. When the transmission loss value drops to a certain level and no longer changes significantly in consecutive rounds of iterations, the system considers that the model has converged, that is, the transmission loss value of the system has reached a minimum and stabilized. At this point, the model parameters of the system have been fully optimized and no further adjustment is required. The system can be considered to have reached the global optimal state.

[0123] Step S50: Each terminal-side device periodically sends the collected actual image data to the corresponding edge server based on the established communication connection.

[0124] Specifically, after the iteration is completed, the system will output the optimal semantic coding model parameters and channel coding model parameters for each terminal device. These parameters are responsible for efficiently encoding the actual image data on the terminal device side so as to retain key information and reduce the amount of data during transmission. At the same time, the edge server will also output the globally optimal channel decoding model parameters and semantic decoding model parameters for decoding and restoring the semantic information received from the terminal device to ensure that the restored data is close to the accuracy of the original data. After obtaining these optimal parameters, the system will re-establish the communication connection between each terminal device and the edge server based on these parameters. This connection is not only a physical link establishment, but more importantly, it is based on optimized model parameters to ensure the efficiency and accuracy of data transmission and decoding. Specifically, the application of these optimal parameters enables the terminal device to achieve efficient image data encoding and transmission with minimal communication resource consumption in subsequent operations. At the same time, the edge server can also process and restore the received data with higher decoding accuracy and speed.

[0125] Furthermore, in the subsequent use process, each terminal device will periodically send the actual image data collected to the corresponding edge server based on these optimal model parameters through the established communication connection. Since these connections and parameters are obtained through iterative optimization, they can minimize information loss and errors in the transmission process and ensure data transmission efficiency and accuracy.

[0126] Based on the solution of the present invention, the optimal semantic coding model parameters and channel coding model parameters enable the terminal device to transmit data with a higher compression rate and stronger anti-interference ability. This greatly reduces the bandwidth required for transmission and improves the overall transmission efficiency. The globally optimal channel decoding model parameters and semantic decoding model parameters adopted by the edge server ensure the accurate restoration of the received encoded data. Even in the case of large noise and interference, the system can still maintain a high decoding accuracy, so that the restored data is highly consistent with the original data. The communication connection established based on the optimal parameters not only ensures the reliability of data transmission, but also enables the system to maintain stable performance in long-term operation.

[0127] Figure 2 1 is a system structure diagram of an edge-end collaborative semantic communication system for a distribution network provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an edge-end collaborative semantic communication system for distribution networks, the system comprising: a terminal-side device for executing the above-mentioned edge-end collaborative semantic communication method for distribution networks, and an edge server for executing the above-mentioned edge-end collaborative semantic communication method for distribution networks.

[0128] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, enables the computer to execute the above-mentioned edge collaborative semantic communication method for distribution networks.

[0129] A fifth aspect of the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the above-mentioned edge collaborative semantic communication method for distribution networks.

[0130] Those skilled in the art will understand that all or part of the steps in the method for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor (processor) perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0131] The optional embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the technical concept of the embodiments of the present invention, the technical scheme of the embodiments of the present invention can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0132] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A method for edge-end collaborative semantic communication for distribution networks, applied to semantic communication between an edge server and a terminal-side device, wherein the edge server is communicatively connected with a plurality of terminal-side devices, characterized in that: The method is performed by a terminal side device, and the method includes: Periodically collecting image data of a set position and periodically constructing a corresponding image test sample set; Sequentially perform semantic coding and channel coding on the image test sample set to obtain a transmission sample set, and send the transmission sample set to a corresponding edge server; The edge server sequentially performs channel decoding and semantic decoding on the received transmission sample sets of each terminal side device, obtains a corresponding decoded image sample set of each terminal side device, and calculates a transmission loss value based on a comparison relationship between each decoded image sample set and a corresponding image test sample set; Taking the minimum transmission loss value as the iteration goal, multiple rounds of image test sample set transmission are performed between the edge server, and the edge server performs semantic coding model parameter, channel coding model parameter, channel decoding model parameter and semantic decoding model parameter iteration based on the stochastic gradient descent algorithm, and establishes a communication connection with each terminal side device based on the corresponding output model parameters; The collected actual image data is periodically sent to the corresponding edge server based on the established communication connection.

2. The method according to claim 1, characterized in that The encoding rule for performing semantic encoding on the image test sample set is: in, is the semantic encoder; α k is the semantic coding model parameter of the kth terminal side device; I is the image test sample set; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; E I It is the semantic feature after semantic encoding.

3. The method according to claim 2, characterized in that The coding rule for performing channel coding on the image test sample set is: in, is a channel encoder; β k is the channel coding model parameter of the k-th terminal side device; I is the image test sample set; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; X I is the semantic feature after channel coding.

4. The method according to claim 1, characterized in that The transmission rule for sending the transmission sample set to the corresponding edge server is: Based on the additive white Gaussian noise channel, the corresponding edge server is used as the receiving end to perform the transmission of the transmission sample set, and the transmission rule is: in, is the semantic feature after interference; X I is the semantic feature after channel coding; N is the noise; R is the feature embedding dimension of the image; H and W are the height and width of each image, respectively.

5. The method according to claim 1, characterized in that When the edge server performs decoding on the transmission sample set received from each terminal side device, the edge server is configured as follows: Channel decoding and semantic decoding are sequentially performed on the transmission sample sets received from each terminal side device to obtain corresponding decoded image sample sets; wherein, The channel decoding rules are: The semantic decoding rules are: in, represents a channel encoder; χ represents the channel decoding model parameters deployed on the edge server; represents a channel encoder; δ represents the parameters of the semantic decoding model deployed on the edge server; R is the feature embedding dimension of the image; H and W are the height and width of each image respectively; Y I is the semantic feature after channel decoding; is a set of decoded image samples.

6. The method according to claim 1, characterized in that When performing the first iteration, the edge server is configured as follows: Perform parameter aggregation based on semantic coding model parameters and channel coding model parameters of each terminal side device to obtain global model parameters; Based on the global model parameters, decoding of a transmission sample set is completed once, and the corresponding channel decoding model parameters and semantic decoding model parameters are used as iterative initial channel decoding model parameters and initial semantic decoding model parameters.

7. The method according to claim 6, characterized in that The edge server performs parameter aggregation based on the semantic coding model parameters and channel coding model parameters of each terminal side device to obtain global model parameters, including: The edge server compares the transmission loss values ​​corresponding to each terminal side device respectively, and performs weight allocation for each terminal side device based on the transmission loss values ​​corresponding to each terminal side device. The smaller the transmission loss value, the greater the corresponding weight. Based on the weight distribution result, the semantic coding model parameters and channel coding model parameters of each terminal side device are aggregated to obtain the global model parameters, which are expressed as: Among them, α and β are global model parameters; K is the number of devices on the terminal side; ω k is the allocation weight of the kth terminal side device; α k is the semantic coding model parameter of the kth terminal side device; β k is the channel coding model parameter of the k-th terminal side device; N k is the channel noise of wireless communication between the kth terminal-side device and the edge server.

8. The method according to claim 1, characterized in that In each round of iteration, the edge server is configured as follows: Send the corresponding semantic coding model parameters and channel coding model parameters respectively, and update the semantic coding model parameters and channel coding model parameters of each terminal side device based on the transmission loss value after the current iteration, as the initial semantic coding model parameters and initial channel coding model parameters of the terminal side device corresponding to the next iteration round; Sequential learning is performed on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device. After each learning of a terminal side device is completed, the channel decoding model parameters and the semantic decoding model parameters are updated once until this round of iteration is completed. The channel decoding model parameters and the semantic decoding model parameters updated after the last terminal side device learning are used as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server in the next iteration round.

9. The method according to claim 8, characterized in that The update rule for the edge server to update the initial coding model parameters and initial channel coding model parameters of each terminal side device in the next iteration round is: in, is the initial semantic coding model parameter of the next iteration round of the k-th terminal side device; is the initial channel coding model parameter of the next iteration round of the k-th terminal side device; are the initial semantic coding model parameters of the kth terminal-side device in this round; are the initial channel coding model parameters of the kth terminal side device in this round; η is the learning rate; is the gradient of the transmission loss value corresponding to the kth terminal-side device in this round.

10. The method according to claim 8, characterized in that The edge server performs sequential learning on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device. After each learning of a terminal side device is completed, the update rule for performing a channel decoding model parameter and a semantic decoding model parameter update is as follows: in, The channel decoding model parameters corresponding to the channel decoding of the k-th terminal side device performed by the edge server; The semantic decoding model parameters corresponding to the semantic decoding of the k-th terminal-side device performed by the edge server; The channel decoding model parameters corresponding to the channel decoding of the k-1th terminal side device performed by the edge server; The semantic decoding model parameters corresponding to the semantic decoding of the k-1th terminal-side device performed by the edge server; η is the learning rate; is the gradient of the transmission loss value corresponding to the k-1th terminal-side device.

11. The method according to claim 8, characterized in that The rule for the edge server to use the channel decoding model parameters and semantic decoding model parameters updated after the last terminal-side device learning as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server in the next iteration round is: Among them, χ (t+1) The initial channel decoding model parameters of the edge server in the next iteration round; δ (t+1) Initial semantic decoding model parameters for the edge server in the next iteration; Signal decoding model parameters for the last terminal-side device channel decoding performed by the edge server in this round; The semantic decoding model parameters for the last terminal-side device semantic decoding performed by the edge server in this round; η is the learning rate; It is the gradient of the transmission loss value corresponding to the last terminal-side device in this round.

12. A method for edge-end collaborative semantic communication for distribution networks, applied to semantic communication between an edge server and a terminal-side device, wherein the edge server is communicatively connected with a plurality of terminal-side devices, characterized in that: The method is performed by an edge server, and the method includes: Periodically receiving the transmission sample set uploaded by each terminal side device; wherein, The transmission sample set is obtained based on each terminal side device through the following rules: Periodically collecting image data of a set position and periodically constructing a corresponding image test sample set; performing semantic coding and channel coding on the image test sample set in sequence to obtain a transmission sample set; Perform channel decoding and semantic decoding on the received transmission sample sets of each terminal side device in sequence, obtain the decoded image sample sets of each terminal side device accordingly, and calculate the transmission loss value based on the comparison relationship between each decoded image sample set and the corresponding image test sample set; Taking the minimum transmission loss value as the iteration goal, perform multiple rounds of image test sample set transmission between each terminal side device, perform semantic coding model parameter, channel coding model parameter, channel decoding model parameter and semantic decoding model parameter iteration based on the stochastic gradient descent algorithm, and establish a communication connection with each edge side device based on the corresponding output model parameters; The actual image data collected by each edge-side device is periodically recovered based on the established communication connection.

13. The method according to claim 12, characterized in that In each round of iteration, the method includes: Send the corresponding semantic coding model parameters and channel coding model parameters respectively, and update the semantic coding model parameters and channel coding model parameters of each terminal side device based on the transmission loss value after the current iteration, as the initial semantic coding model parameters and initial channel coding model parameters of the terminal side device corresponding to the next iteration round; Sequential learning is performed on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device. After each learning of a terminal side device is completed, the channel decoding model parameters and the semantic decoding model parameters are updated once until this round of iteration is completed. The channel decoding model parameters and the semantic decoding model parameters updated after the last terminal side device learning are used as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server in the next iteration round.

14. The method according to claim 13, characterized in that The update rule for the edge server to update the initial coding model parameters and initial channel coding model parameters of each terminal side device in the next iteration round is: in, is the initial semantic coding model parameter of the next iteration round of the k-th terminal side device; is the initial channel coding model parameter of the next iteration round of the k-th terminal side device; are the initial semantic coding model parameters of the kth terminal-side device in this round; are the initial channel coding model parameters of the kth terminal side device in this round; η is the learning rate; is the gradient of the transmission loss value corresponding to the kth terminal-side device in this round.

15. The method according to claim 13, characterized in that The edge server performs sequential learning on each terminal side device based on the semantic coding model parameters and channel coding model parameters of each terminal side device. After each learning of a terminal side device is completed, the update rule for performing a channel decoding model parameter and a semantic decoding model parameter update is as follows: in, The channel decoding model parameters corresponding to the channel decoding of the k-th terminal side device performed by the edge server; The semantic decoding model parameters corresponding to the semantic decoding of the k-th terminal-side device performed by the edge server; The channel decoding model parameters corresponding to the channel decoding of the k-1th terminal side device performed by the edge server; The semantic decoding model parameters corresponding to the semantic decoding of the k-1th terminal-side device performed by the edge server; η is the learning rate; is the gradient of the transmission loss value corresponding to the k-1th terminal-side device.

16. The method according to claim 13, characterized in that The rule for the edge server to use the channel decoding model parameters and semantic decoding model parameters updated after the last terminal-side device learning as the initial channel decoding model parameters and initial semantic decoding model parameters of the edge server in the next iteration round is: Among them, χ (t+1) The initial channel decoding model parameters of the edge server in the next iteration round; δ (t+1) Initial semantic decoding model parameters for the edge server in the next iteration; Signal decoding model parameters for the last terminal-side device channel decoding performed by the edge server in this round; The semantic decoding model parameters for the last terminal-side device semantic decoding performed by the edge server in this round; η is the learning rate; It is the gradient of the transmission loss value corresponding to the last terminal-side device in this round.

17. An edge-end collaborative semantic communication system for distribution networks, applied to semantic communication between edge servers and terminal devices, wherein the edge servers are communicatively connected with a plurality of terminal devices, characterized in that: The system includes: a terminal-side device for executing the edge-end collaborative semantic communication method for distribution networks as described in any one of claims 1-11, and an edge server for executing the edge-end collaborative semantic communication method for distribution networks as described in any one of claims 12-16.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the edge collaborative semantic communication method for distribution networks as described in any one of claims 1-16.

19. A computer program product comprising a computer program, characterized in that When executed by a processor, the computer program implements the edge collaborative semantic communication method for distribution networks according to any one of claims 1 to 16.

Images