Service transmission method and device for power distribution network and nonvolatile storage medium

Abstract

The invention discloses a service transmission method and device for a power distribution network and a nonvolatile storage medium. The method comprises the following steps: determining target business data in a power distribution network and an initial transmission channel corresponding to the target business data; acquiring the transmission delay of the target service data in the initial transmission channel; under the condition that the time delay exceeds a preset threshold value, a transmission adjustment strategy is determined, and the transmission adjustment strategy comprises adjustment of target service data and adjustment of an initial transmission channel; and transmitting the target service data based on the transmission adjustment strategy. According to the invention, the technical problem that the traditional transmission method cannot dynamically adjust the time delay problem is solved.

Description

Technical Field

[0001] This invention relates to the field of electronic information technology, and more specifically, to a service transmission method, apparatus, and non-volatile storage medium for power distribution networks. Background Technology

[0002] Against the backdrop of the rapid development of smart grids, the demand for communication technologies in distribution networks is increasingly upgrading, with a particular emphasis on real-time performance, reliability, and security. 5G communication technology, with its superior high speed, low latency, and massive connectivity capabilities, has become a leading force in revolutionizing the communication architecture of distribution networks, providing unprecedented possibilities for meeting the stringent requirements of distribution network operations. However, in real-world applications, the deep integration of 5G with distribution networks faces multiple challenges, hindering the full realization of the technology's advantages.

[0003] While 5G networks can theoretically provide stable low-latency services, the unique environment of power distribution networks, including but not limited to severe weather and uncertainties in surrounding electromagnetic interference, often results in unpredictable fluctuations in data transmission latency. This is particularly true in extreme situations such as fault alarms, where spikes in latency severely delay fault response times, posing a significant threat to the stable operation of the power distribution network. Currently, network slicing technology in the integration of 5G and power distribution networks can provide priority communication channels for different services; however, precise resource allocation in current network slicing systems faces challenges, reducing transmission efficiency.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a service transmission method, apparatus, and non-volatile storage medium for power distribution networks, to at least solve the technical problem that traditional transmission methods cannot dynamically adjust for latency issues.

[0006] According to one aspect of the present invention, a service transmission method for a distribution network is provided, comprising: determining target service data in the distribution network and an initial transmission channel corresponding to the target service data; obtaining the transmission delay of the target service data in the initial transmission channel; determining a transmission adjustment strategy when the delay exceeds a preset threshold, wherein the transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel; and transmitting the target service data based on the transmission adjustment strategy.

[0007] Optionally, determining the target service data in the distribution network includes: acquiring the original service data in the distribution network, wherein the original service data includes voltage, current and frequency signals; extracting semantic features from the original service data based on the target neural network model to obtain semantic feature data, wherein the target neural network model is trained based on the initial neural network model; determining the semantic noise corresponding to the semantic feature data; and determining the target service data based on the semantic feature data and the semantic noise.

[0008] Optionally, determining the semantic noise corresponding to the semantic feature data includes: determining the distribution of semantic noise based on adversarial training; determining the intensity of semantic noise based on the state of the initial transmission channel; and determining semantic noise based on the distribution and intensity.

[0009] Optionally, determining the initial transmission channel corresponding to the target service data includes: determining the target channel bandwidth based on the priority of the target service data using network slicing technology; and determining the initial transmission channel based on the target channel bandwidth.

[0010] Optionally, when the transmission adjustment strategy is to adjust the target service data, the target service data is transmitted based on the transmission adjustment strategy, including: determining the target number of bits corresponding to the target service data based on the delay; adjusting the target service data based on the target number of bits to obtain the adjusted target service data; and transmitting the adjusted target service data based on the initial transmission channel.

[0011] Optionally, when the transmission adjustment strategy is to adjust the initial transmission channel, the target service data is transmitted based on the transmission adjustment strategy, including: determining the target channel gain based on the initial channel gain of the initial transmission channel; determining the target transmission channel among multiple backup transmission channels based on the target channel gain; and transmitting the target service data based on the target transmission channel.

[0012] Optionally, the network load rate and security score during the transmission of the target service data are obtained, wherein the security score is determined based on the transmission rate of the target service data; the network load rate and security score are input into a preset Markov chain decision model to obtain the optimal strategy, wherein the optimal strategy includes adjusting the transmission power of the target service data to the optimal transmission power; and the transmission process of the target service data is adjusted based on the optimal strategy.

[0013] Optionally, the network load rate and security score are input into a preset Markov chain decision model to obtain the optimal strategy, including: inputting the network load rate and security score into the Markov chain decision model to obtain an initial strategy, wherein the initial strategy includes adjusting the transmission power of the target service data to an initial transmission power; calculating the reward value corresponding to the initial strategy based on a preset reward function; adjusting the parameters of the Markov chain decision model based on the reward value corresponding to the initial strategy to obtain an optimized Markov chain decision model; repeating the above steps to obtain reward values ​​corresponding to multiple initial strategies; and determining the optimal strategy based on the reward values ​​corresponding to multiple initial strategies.

[0014] According to another aspect of the present invention, a service transmission device for a power distribution network is also provided, comprising: a first determining module, configured to determine target service data in the power distribution network and an initial transmission channel corresponding to the target service data; an acquiring module, configured to acquire the transmission delay of the target service data in the initial transmission channel; a second determining module, configured to determine a transmission adjustment strategy when the delay exceeds a preset threshold, wherein the transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel; and a transmission module, configured to transmit the target service data based on the transmission adjustment strategy.

[0015] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, it controls the device where the non-volatile storage medium is located to execute any of the above-described service transmission methods for power distribution networks.

[0016] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor, the processor being configured to run a program, wherein the program, when running, executes any of the above-described service transmission methods for a power distribution network.

[0017] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the above-described service transmission methods for a power distribution network.

[0018] In this embodiment of the invention, a service transmission method for power distribution networks is adopted. This method involves determining the target service data in the power distribution network and the initial transmission channel corresponding to the target service data; obtaining the transmission delay of the target service data in the initial transmission channel; and determining a transmission adjustment strategy when the delay exceeds a preset threshold. The transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel. Based on the transmission adjustment strategy, the target service data is transmitted, achieving the goal of dynamically adjusting resource allocation and accurately matching service requirements. This improves transmission efficiency and stability, thereby solving the technical problem that traditional transmission methods cannot dynamically adjust for delay issues. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0020] Figure 1 A hardware structure block diagram of a computer terminal for implementing a service transmission method for a power distribution network is shown.

[0021] Figure 2 This is a flowchart illustrating a service transmission method for a power distribution network according to an embodiment of the present invention.

[0022] Figure 3 This is a flowchart of a method for secure transmission of low-latency services in a new power distribution network based on a 5G communication architecture, according to an optional embodiment of the present invention.

[0023] Figure 4 This is a structural block diagram of a service transmission device for a power distribution network provided according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to an embodiment of the present invention, a service transmission method for a power distribution network is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a service transmission method for a power distribution network is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0028] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be implemented wholly or partially as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element in the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the service transmission method for power distribution networks in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the aforementioned service transmission method for power distribution networks. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0030] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0031] Figure 2 This is a flowchart illustrating a service transmission method for a power distribution network according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0032] Step S201: Determine the target service data in the distribution network and the initial transmission channel corresponding to the target service data.

[0033] In this step, the distribution network generates a wide variety of business data, including but not limited to fault alarms, load control, and power quality monitoring. These data have varying timeliness and security requirements. Identifying the target business data means recognizing data types that are extremely sensitive to latency and have high security requirements, and extracting their corresponding semantic features. For example, fault detection data must be transmitted within milliseconds to quickly isolate and repair faults, preventing the escalation of grid accidents; load control signals must be accurately transmitted during peak electricity consumption to regulate the grid's supply and demand balance and prevent overload.

[0034] A semantic encoder using deep neural networks can be employed to extract and encode key semantic features of this business data. A semantic encoder is a powerful tool that delves into the meaning of data rather than merely focusing on its surface appearance. Through training, it learns to identify the inherent patterns in various types of business data, creating unique binary indexes for each data type. This enables the system to quickly identify and process data, laying a solid foundation for subsequent transmission and security strategies.

[0035] Once the target service data is identified, the next task is to allocate the most suitable transmission channels to this data. In the 5G communication architecture, this process primarily relies on network slicing technology. Network slicing allows the creation of multiple virtual networks on the same physical network infrastructure, each with its own specific functions and performance parameters, such as bandwidth, latency, and connection density, to meet the needs of different types of services.

[0036] Step S202: Obtain the transmission delay of the target service data in the initial transmission channel.

[0037] In this step, the system collects real-time transmission status information of service data through sensors and monitoring equipment deployed at key nodes of the distribution network. This information includes, but is not limited to, the data packet transmission time, reception time, path information, and the current network load. For each target service data item, the system uses the received transmission status information to calculate its end-to-end transmission delay in the initial transmission channel. End-to-end transmission delay refers to the total time for data to travel from the sender to the receiver, and it includes the data packet transmission delay, queuing delay, and decoding processing delay in the network.

[0038] Step S203: If the delay exceeds a preset threshold, determine a transmission adjustment strategy, wherein the transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel.

[0039] In this step, the system monitors the end-to-end latency of target service data through the initial transmission channel in real time. The preset threshold can be set based on the real-time requirements of the service data. For example, fault alarm services may require a transmission latency of less than 15 milliseconds to ensure the power grid can respond quickly to faults and prevent the scope of the accident from expanding. When the monitored latency exceeds the preset threshold, the system can automatically identify and initiate a transmission adjustment strategy. This strategy includes adjusting the encoding of the target service data and / or switching the initial transmission channel. This dynamic adjustment mechanism allows the system to flexibly adjust data encoding and transmission strategies according to the real-time monitored network status and service requirements, ensuring that low-latency services in the distribution network can maintain stable and efficient transmission even when the network environment changes or faces external interference. This mechanism breaks through the limitations of traditional static configuration, improves the system's adaptability and overall performance, and is of great significance for ensuring the stable operation of the smart grid, improving power efficiency, and enhancing user experience.

[0040] Step S204: Based on the transmission adjustment strategy, transmit the target service data.

[0041] In this step, the transmission adjustment strategy is a series of optimization measures autonomously determined by the system based on real-time network conditions and service requirements when abnormal transmission latency is detected. Its purpose is to reduce latency and improve the reliability and security of data transmission by dynamically adjusting data encoding methods or switching transmission paths. Through intelligent encoding parameter adjustment and transmission channel optimization, low-latency service data in the distribution network can maintain efficient, reliable, and secure transmission even in complex environments, thus providing a solid technical guarantee for the stable operation and efficient management of the smart grid.

[0042] Through the above steps, the goal of dynamically adjusting resource allocation and accurately matching business needs is achieved, thereby improving transmission efficiency and stability, and solving the technical problem that traditional transmission methods cannot dynamically adjust for latency issues.

[0043] As an optional embodiment, determining the target service data in the distribution network includes: acquiring the original service data in the distribution network, wherein the original service data includes voltage, current and frequency signals; extracting semantic features from the original service data based on a target neural network model to obtain semantic feature data, wherein the target neural network model is trained based on an initial neural network model; determining the semantic noise corresponding to the semantic feature data; and determining the target service data based on the semantic feature data and the semantic noise.

[0044] Optionally, a semantic encoder based on a deep neural network is used to process the original business data, constructing a multimodal codebook with binary indexes. This codebook supports a dynamic update mechanism, and incremental learning algorithms optimize the mapping relationship between codeword indexes and symbols, ensuring that index query efficiency is no less than O(logM), providing a high-efficiency foundation for subsequent processing. In a large amount of complex distribution network business data, this indexing mechanism enables rapid location and processing of specific data. The codebook uses binary indexes, with each codeword index corresponding to a unique sequence of semantic symbols. Mapping rules determine these correspondences, enabling the codebook to accurately reflect the semantic features of the business data. For semantic extraction, mapping rules define the correspondence between key business types and scenarios, making semantic feature extraction more targeted.

[0045] Traditional power distribution network communication equipment has limitations in processing 5G high-frequency signals and lacks the ability to process semantic features specific to power distribution network services, making it difficult to efficiently process service data and achieve fast and accurate data retrieval. Therefore, a transmission infrastructure environment adapted to the 5G architecture is needed. This architecture selects communication equipment supporting 5G high-frequency bands as signal transceivers. The communication equipment integrates high-performance computing modules, including multi-core CPUs and FPGA hardware acceleration units, enabling real-time processing of semantic encoding and decoding tasks for power distribution network service data.

[0046] Specifically, semantic features can be extracted from the raw business data, and mapping rules between key business types and scenarios can be defined, including fault alarms, load control, and power quality monitoring. For example, the fault type "overload" can be mapped to the binary index "1010", and the load level "emergency" can be mapped to the index "1101". Furthermore, semantic transmission is used to process the raw business data through a semantic encoder to extract the important features of the raw business data.

[0047] Among them, the semantic encoder f E This is a model based on a target neural network. Its input is the raw distribution network business data x (including voltage, current, and frequency signals), and its output is semantic feature data d. n The extraction process consists of two layers: the first layer learns the local features of the input data; the second layer combines the local features into a global semantic code. The specific process is as follows:

[0048] d n =f E (x)=ReLU(W2·ReLU(W1x+b1))+x

[0049] Where W1 is the weight matrix from the input layer to the hidden layer in the first transformation, b1 is the bias vector, the second transformation is the weight matrix from the hidden layer to the output layer represented by W2, and the activation function is the modified linear unit ReLU.

[0050] In addition, a multimodal codebook can be constructed based on the extracted semantic feature data. The codebook is a public knowledge base that provides standardized mappings for the semantic features of distribution network business data. It achieves rapid mapping between "semantic features and symbol sequences" through binary indexing. Furthermore, each codeword index... This corresponds to a unique sequence of semantic symbols, which is the target business data. The formula for generating the target business data is:

[0051] c n =f C (f E (x)+Δz n )

[0052] Among them, f E (x) is the semantic encoder, Δz n Learnable, user-perceptible semantic noise is used to confuse the eavesdropper's semantic decoder. Furthermore, the codebook supports a dynamic update mechanism. Based on changes in distribution network business scenarios, it optimizes the mapping relationship between codeword indexes and symbols through incremental learning algorithms, ensuring that index query efficiency is no less than O(logM). The dynamic update mechanism of the codebook employs an online sparse coding algorithm, with the following update rules:

[0053]

[0054] Among them, the new code word c new The old codeword 'c' was extracted from the new business data using Incremental Principal Component Analysis (IPCA). obsolete Elimination is based on access frequency.

[0055] As an optional embodiment, determining the semantic noise corresponding to the semantic feature data includes: determining the distribution of semantic noise based on adversarial training; determining the intensity of semantic noise based on the state of the initial transmission channel; and determining semantic noise based on the distribution and intensity.

[0056] Optionally, semantic noise Δz n The generation process optimizes the noise distribution through adversarial training, ensuring that the eavesdropper's semantic decoding error satisfies:

[0057]

[0058] Where ∈=0.05 is the preset security threshold, and d(·) is the semantic distortion measurement function, which is used to calculate the degree of semantic difference between the eavesdropper's decoding result and the original target data; The eavesdropper's semantic decoder takes the encoded sequence c as input. n The output is the raw data that the eavesdropper inferred, i.e., x.goal The estimated value; x goal is the original target data, i.e., the real semantic data without encoding; ∈ is used to determine whether the eavesdropper's decoding error is large enough. When E[d(·)]>∈, it indicates that the eavesdropper cannot effectively parse the real semantics, and the system's anti-eavesdropping capability meets the standard.

[0059] The noise intensity is dynamically adjusted according to the channel conditions, and the adjustment formula is as follows:

[0060]

[0061] In the formula, α is the learnable coefficient, and h u and h e denoted by , these represent the channel gain for legitimate users and eavesdroppers, respectively. The exponential factor γ ≥ 1 controls the sensitivity of the channel ratio. γ is a presettable and adjustable hyperparameter that can be manually optimized during model deployment based on the actual network environment. In areas with high eavesdropper density, increasing γ enhances sensitivity to channel differences and improves anti-eavesdropping capabilities; in open areas, decreasing γ reduces unnecessary noise injection and improves transmission efficiency. SNRu is the signal-to-noise ratio for legitimate users, and β is a temperature coefficient, also a presettable and adjustable hyperparameter used to adjust the hyperbolic tangent function. The shape of the β curve controls the sensitivity of noise intensity to the signal-to-noise ratio (SNRu). A small β value approaches the saturation region, where small changes in SNRu lead to significant changes in noise intensity, suitable for scenarios sensitive to SNRu. A large β value approaches the linear region, where noise intensity changes slowly with SNRu, suitable for environments with large SNRu fluctuations. Smoothing normalization is achieved using the tanh(·) function, reducing noise injection to avoid communication interruptions when SNRu is low, and allowing for higher noise intensity when SNRu is high. σ(·) is the Sigmoid function, with the threshold τ and slope κ controlling the activation interval. This indicates that the physical layer is sufficiently secure and automatically attenuates noise intensity. This is the physical layer security rate, representing the difference in secure transmission rates between a legitimate user and an eavesdropper. If... This enhances the injection of semantic layer noise. Furthermore, the noise intensity should satisfy ||Δz||. n ||2≤β·||d n ‖2, where β is the safety factor (0.1≤β≤0.3).

[0062] As an optional embodiment, determining the initial transmission channel corresponding to the target service data includes: determining the target channel bandwidth based on the priority of the target service data using network slicing technology; and determining the initial transmission channel based on the target channel bandwidth.

[0063] Optionally, an initial transmission channel can be allocated for the target service data based on 5G network slicing technology, with a channel bandwidth of B.slice Priority satisfies:

[0064] B slice =λ·B total ·η priority

[0065] Where λ∈[0.2,0.5], η priority ∈[0.8,1.2], B total η represents the total 5G bandwidth, λ represents the slice resource ratio coefficient, and η represents the total bandwidth of 5G. priority It is the business priority weight. A large η value indicates a critical business, and a small η value indicates a non-real-time business.

[0066] As an optional embodiment, when the transmission adjustment strategy is to adjust the target service data, the target service data is transmitted based on the transmission adjustment strategy, including: determining the target number of bits corresponding to the target service data based on the delay; adjusting the target service data based on the target number of bits to obtain the adjusted target service data; and transmitting the adjusted target service data based on the initial transmission channel.

[0067] Optionally, if the latency exceeds a preset threshold, a dynamic adjustment mechanism can be triggered to determine the transmission adjustment strategy. When the transmission adjustment strategy involves adjusting the target service data, semantic coding is optimized. Specifically, coding complexity can be reduced by adjusting the number of codebook index bits *b*. High-priority services correspond to a shorter number of index bits, allocating wider slice bandwidth to ensure low-latency transmission; low-priority services use a longer index to save spectrum resources. When the transmission latency exceeds the threshold latency *T*, the transmission delay is reduced. th At that time, by adjusting the number of codebook index bits, the following conditions are met. To ensure that latency recovers to within the threshold. Semantic encoder f e A lightweight convolutional neural network structure is used, and the encoding latency meets the following requirements:

[0068]

[0069] Among them, L data N is the data length. ops For the computational cost per sample, η par F is the parallel efficiency factor. GPU For GPU floating-point computing power, ensure T encode ≤3ms. η∈(0,1] is the parallel efficiency factor, reflecting the multi-core utilization of the GPU. The expression in max represents the memory bandwidth limit, B model M represents the number of model parameters. BW GPU memory bandwidth;

[0070] Optimization of coding parameters can also include adaptive modulation and coding techniques, which adjust the modulation order M and coding rate R according to channel quality. For example, when the signal-to-noise ratio (SNR) is ≥ 20 dB, 64-QAM modulation (M = 6) and LDPC coding (R = 0.9) are used; when 10 dB ≤ SNR < 20 dB, 16-QAM modulation (M = 4) and Turbo coding (R = 0.7) are used.

[0071] As an optional embodiment, when the transmission adjustment strategy is to adjust the initial transmission channel, the target service data is transmitted based on the transmission adjustment strategy, including: determining the target channel gain based on the initial channel gain of the initial transmission channel; determining the target transmission channel among multiple backup transmission channels based on the target channel gain; and transmitting the target service data based on the target transmission channel.

[0072] Optionally, if the latency exceeds a preset threshold, a dynamic adjustment mechanism can be triggered to determine a transmission adjustment strategy. If the transmission adjustment strategy involves adjusting the initial transmission channel, a backup channel can be switched. Specifically, the switching condition from the initial transmission channel to the backup transmission channel is as follows:

[0073]

[0074] in, This refers to the channel gain of the backup transmission channel. The backup transmission channel selection strategy is based on the principle of maximizing channel capacity, and preferably satisfies the following:

[0075]

[0076] Among them, B slice,k Let |h| be the slice bandwidth of the k-th spare channel. u,k f u | 2 The received signal power (energy) of a legitimate user on the k-th channel, where k is the channel index, σ 2 This represents noise power.

[0077] As an optional embodiment, the network load rate and security score are obtained during the transmission of the target service data, wherein the security score is determined based on the transmission rate of the target service data; the network load rate and security score are input into a preset Markov chain decision model to obtain the optimal strategy, wherein the optimal strategy includes adjusting the transmission power of the target service data to the optimal transmission power; and the transmission process of the target service data is adjusted based on the optimal strategy.

[0078] Optionally, a decision-making model based on Markov chains can be designed. Based on Markov chain theory, network states (e.g., network load rate), data characteristics, and security scores are set as state variables. A state transition probability matrix is ​​determined, and a reasonable action space is defined, including operations such as adjusting transmission power. Through a reward function, the model is trained using a large amount of real-world data to accurately adapt to the dynamic changes in distribution network operations.

[0079] Regarding the determination of the security score, traditional security assessment systems only focus on a single security dimension, which cannot comprehensively quantify the security level of the distribution network communication system. Current research also largely lacks comprehensiveness in transmission efficiency assessment, making it difficult to formulate optimization strategies that balance security and efficiency. Therefore, a cross-layer security assessment system can be constructed, defining the security score as a weighted sum of confidentiality, integrity, and the effectiveness of misleading information, and providing calculation methods for each of these aspects.

[0080] Specifically, for constructing a cross-layer security assessment system, the security score S is first defined as the confidentiality score S. conf Integrity S int Validity of misleading information S dec Weighted sum:

[0081] S = w1·S conf +w2·S int +w3·S dec

[0082] The weighting coefficients satisfy w1+w2+w3=1, and w3≥0.4;

[0083] Confidentiality is S conf Physical layer security rate The calculation formula is as follows:

[0084]

[0085] in, It is the physical layer security rate, representing the difference in secure transmission rates between a legitimate user and an eavesdropper; R u It refers to the user transmission rate, that is, the data transmission rate of legitimate users.

[0086] Integrity S int The success rate of hash verification is quantified and defined as follows:

[0087]

[0088] Where, N success This is to verify the number of successfully transmitted data packets.

[0089] Validity of misleading information S decCalculated based on the error rate of the eavesdropper's semantic task:

[0090]

[0091] in, This indicates that the eavesdropper has access to the coded sequence c. n The decoding result is consistent with the original target semantics x goal Average semantic distortion, d max This represents the maximum permissible semantic distortion.

[0092] In addition, data transmission efficiency and spectral efficiency can be calculated simultaneously to obtain the overall transmission efficiency. Then, based on the real-time security score and efficiency score, the injection ratio of semantic noise is adjusted through an adaptive mechanism for the proportion of misleading information. When certain conditions are met, Q-learning-based path optimization is triggered, thereby improving transmission efficiency while ensuring security.

[0093] Specifically, data transmission efficiency can be defined as the ratio of effective data volume to total transmission time:

[0094]

[0095] Among them, L payload T represents the payload length, PER represents the packet error rate, reflecting channel reliability, and T represents the data packet error rate. total End-to-end delay is the sum of transmission delay, propagation delay, and queuing delay. It is calculated based on the modulation and coding scheme (MCS). Among them B slice Given the network slice bandwidth and overall transmission efficiency, the formula is as follows:

[0096] E total =γ·E data +(1-γ)·E spec

[0097] Where γ∈[0.5,0.8] are weighting coefficients. Through an adaptive mechanism for the proportion of misleading information, based on the security score S and efficiency score E... total Adjust semantic noise Δz n Injection ratio α:

[0098]

[0099] Where η is the balance factor η∈[0.8,1.2], ensuring α≤0.3. When E data <E th (E th When the speed is 50 Mbps, Q-learning-based path optimization is triggered. The path optimization includes three core operations: transmission power adjustment, frequency band switching, and noise injection optimization. For transmission power adjustment, increasing the power can improve the signal-to-noise ratio (SNR) of legitimate users.u To reduce the packet error rate (PER), the power adjustment ΔP is used as an action variable, and the delay penalty term (-ζ·T) in the reward function r is applied. delay ) and safety items Optimization. Frequency band switching is performed from the candidate frequency band set {f1, f2, ..., f...} K In this process, the optimal frequency band is selected to avoid interference or eavesdropping risks in the current frequency band. Noise injection optimization involves dynamically modifying the injection intensity α and distribution type of semantic noise. When the channel quality is poor, the SNR... u When the channel quality SNR is low, it switches to higher-order Gaussian noise. u When the condition is good (high), reduce α to decrease transmission overhead. Action selection satisfies:

[0100]

[0101] Where ν is the safety reward weight, and Q(s,a) is the state-action value function. This represents the cross-layer semantic security rate, providing a unified metric for cross-layer security performance by integrating security metrics from the physical layer (including channel encryption and anti-interference) and the application layer (including semantic noise and task reliability). When physical layer security fails... hour, Automatically switching to application-layer security, i.e., semantic noise obfuscation, ensures that the system maintains a basic level of security even in complex environments, as represented by:

[0102]

[0103] in, Semantic security efficiency reflects the ratio of application layer task security to physical layer resource consumption, and it comprehensively evaluates semantic efficiency and physical layer security rate. It is the physical layer security rate, when At this time, security is achieved by utilizing physical layer security redundancy. At this point, physical layer security fails, and the focus shifts to semantic security efficiency.

[0104] As an optional embodiment, network load rate and security score are input into a preset Markov chain decision model to obtain the optimal strategy, including: inputting network load rate and security score into the Markov chain decision model to obtain an initial strategy, wherein the initial strategy includes adjusting the transmission power of the target service data to an initial transmission power; calculating the reward value corresponding to the initial strategy based on a preset reward function; adjusting the parameters of the Markov chain decision model based on the reward value corresponding to the initial strategy to obtain an optimized Markov chain decision model; repeating the above steps to obtain reward values ​​corresponding to multiple initial strategies; and determining the optimal strategy based on the reward values ​​corresponding to multiple initial strategies.

[0105] Optionally, a Markov Decision Process (MDP) model is first constructed, whose state space s is defined as:

[0106] s t =(h u ,h e ,c n ,ρ,S)

[0107] Among them, h u For legitimate user channel gain, h e For the eavesdropping channel gain, c n The target business data is ρ, where ρ is the network load rate and S is the security score. The state transition probability matrix is ​​p. T By using historical data statistical modeling, the following conditions are met:

[0108]

[0109] Among them, the state transitions in each dimension are independent, p i Fitted using a Gaussian Mixture Model (GMM). Action space. It is to adjust the transmission power ΔP to satisfy ||f|| u || 2 ≤ξ, if the current power‖f u || 2 If the power is close to the maximum allowable power ξ, the adjustment magnitude ΔP needs to be optimized by switching frequency bands; switch communication frequency band f K From the candidate set f1, f2, ..., f K Select from the options; and dynamically modify the semantic noise injection method, including the noise intensity α. Reward function r(s) t ,a t )for:

[0110]

[0111] Where κ∈[0.6,0.8] is the security weight, ζ is the delay penalty coefficient ζ≥0.2, and T delay Let be the current transmission delay. The Bellman optimal equation based on the action selection strategy is as follows:

[0112]

[0113] Among them, V * (s) is the optimal state value function, γ = 0.9 is the discount factor, and it is solved using a value iteration algorithm. The model training process includes: first, data collection, gathering 100,000 sets of state-action-transition-reward quadruplets (s) from the actual operation of the distribution network. t ,at ,s t+1 ,r t Then perform offline pre-training, using the Bellman optimal equation to initialize the policy network π. θ (a|s) and reward function r(s) t ,a t Finally, online fine-tuning is performed based on real-time data streams, with a learning rate of η = 10. -4 .

[0114] Furthermore, considering that traditional methods are insufficiently comprehensive and timely in real-time monitoring of distribution network system operation data, failing to quickly acquire information such as network status, data transmission status, and changes in safety indicators, a distributed sensor network can be used to collect system operation data in real time. This data includes network status data, transmission performance data, and safety indicator data, with a data sampling frequency ≥1kHz. The data is then transmitted to edge computing nodes for preprocessing to generate standardized state vectors. These state vectors are then input into a pre-trained deep reinforcement learning policy network of a Markov decision model for real-time inference, outputting actions. Noise distribution type and transmission power are dynamically adjusted based on network load and safety scores, using an online learning framework for iterative optimization. The success rate of dynamic adjustment is defined as a system performance verification indicator, ensuring reliable and secure transmission of low-latency services in the distribution network.

[0115] Specifically, the data sampling frequency is ≥1kHz, and the data is transmitted to the edge computing node for preprocessing to generate a standardized state vector s. t =(h n h s T delay ,ρ, The real-time inference process of a Markov decision model includes: converting the state vector s... t Input pre-trained deep reinforcement learning policy network π θ (a|s), output action:

[0116] a t (ΔP, f) k , α)

[0117] Where ΔP is the transmission power adjustment amount, satisfying ||f|| u +ΔP‖ 2 ≤ξ;f k To switch frequency bands, from the candidate set f1, f2, ..., f K The selected action execution latency is ≤3ms to ensure real-time policy response. The noise distribution type can be dynamically adjusted based on network load ρ and security score S. For example, when ρ>0.8 and S<0.7, high-order Gaussian noise is used. When ρ≤0.8 and S≥0.7, uniform noise is used. Transmission power adaptive adjustment is based on the channel quality index, expressed by the formula:

[0118]

[0119] Where ΔP is the transmission power adjustment amount. ξ-‖f u || 2 This represents the difference between the current power and the maximum allowable power, reflecting the "remaining space" for power adjustment. When the current power approaches the maximum allowable power, the numerator approaches 0, and the power adjustment amplitude decreases. κ is the attenuation coefficient, κ∈[0.5,1.0]. The iterative optimization process uses an online learning framework, processing real-time data quadruples (s... t ,a t ,s t+1 ,r t Store in the playback pool Pool capacity ≥10 6 Mini-batch gradient descent is performed every 100ms, with the objective function being:

[0120]

[0121] in, Let θ be the objective loss function, used to optimize the policy network. Indicates the replay pool The expected value is taken from the sampled quadruple (s,a,r,s'). This is the replay buffer, storing the historical state-action-reward-next state quadruple for model training. Q φ (s,a): State-Action Value Function (Q-function), with parameter φ, used to evaluate the long-term value of performing action a in state s. γ: Discount Factor, with a value of 0.9, used to balance immediate rewards and future rewards. This represents the maximum Q-value of all possible actions a′ in state s′, used to calculate the target value (the guiding target in the Bellman equation). When the strategy volatility... When convergence is achieved, the system is considered to have reached convergence. The success rate of dynamic adjustment can be defined as a system performance verification metric, with the standard being a system state improvement rate ≥ 90% after strategy execution. The calculation formula is:

[0122]

[0123] in, Let T be the indicator function, and T be the total number of adjustments.

[0124] As an optional embodiment, a new method for secure transmission of low-latency services in power distribution networks based on a 5G communication architecture is also provided. Figure 3This is a flowchart of a method for secure transmission of low-latency services in a new power distribution network based on a 5G communication architecture, according to an optional embodiment of the present invention. Figure 3 As shown, this optional embodiment designs a collaborative control system for the entire distribution network business process that integrates semantic communication coding, dynamic isolation of 5G network slicing, multimodal Markov chain decision-making, and trusted security assessment. At the same time, through real-time monitoring and dynamic policy adjustment, the system can adjust transmission parameters and security policies in real time according to network status and business requirements.

[0125] In terms of the transmission infrastructure, equipment adapted to 5G frequency bands and possessing high-performance computing and semantic coding capabilities is selected to construct a dedicated codebook, enabling rapid and accurate data processing and laying a solid foundation for subsequent processes. During transmission, 5G network slicing technology is used to open dedicated channels for low-latency services, and semantic communication coding technology is employed to generate not only compact semantic symbols but also anti-eavesdropping coding sequences through noise injection, ensuring data security and low-latency transmission. Simultaneously, the constructed security assessment system comprehensively considers confidentiality, integrity, and the effectiveness of deceptive information, calculates transmission efficiency, and then formulates optimization strategies to balance security and efficiency. Based on a Markov chain-based decision model, system performance can be dynamically optimized according to factors such as network status and data characteristics. Real-time monitoring and dynamic strategy adjustment mechanisms enable the system to flexibly adapt to network changes, ensuring reliable and secure transmission of low-latency services in the distribution network.

[0126] By introducing semantic communication coding technology into distribution network business data processing, the limitations of traditional communication coding are broken, key information is extracted from the semantic level, greatly improving communication efficiency. Furthermore, learnable semantic noise is used to confuse eavesdroppers, enhancing data confidentiality. Moreover, a decision-making model based on Markov chains is constructed, incorporating multiple factors such as network state and security risks into state variables. A reasonable action space and reward function are designed to achieve dynamic optimization of system performance. This differs from existing technologies with fixed parameter configurations and strategies, enabling the system to adaptively adjust based on real-time data, better coping with the complex and ever-changing 5G network environment and distribution network business needs.

[0127] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0128] Through the above description of the embodiments, those skilled in the art can clearly understand that the service transmission method for power distribution networks according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0129] According to embodiments of the present invention, an apparatus for implementing the above-described service transmission method for a power distribution network is also provided. Figure 4 This is a structural block diagram of a service transmission device for a power distribution network provided according to an embodiment of the present invention, such as... Figure 4 As shown, the device includes: a first determining module 41, an acquiring module 42, a second determining module 43, and a transmitting module 44. The device will be described below.

[0130] The first determining module 41 is used to determine the target service data in the distribution network and the initial transmission channel corresponding to the target service data.

[0131] The acquisition module 42, connected to the first determination module 41, is used to acquire the transmission delay of the target service data in the initial transmission channel.

[0132] The second determining module 43, connected to the obtaining module 42, is used to determine a transmission adjustment strategy when the delay exceeds a preset threshold. The transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel.

[0133] The transmission module 44 is connected to the second determining module 43 and is used to transmit target service data based on the transmission adjustment strategy.

[0134] It should be noted that the first determining module 41, the acquiring module 42, the second determining module 43, and the transmitting module 44 mentioned above correspond to steps S201 to S204 in the embodiments. Multiple modules implement the same instances and application scenarios as their corresponding steps, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can run in the computer terminal 10 provided in the embodiments.

[0135] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0136] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the service transmission method and device for power distribution networks in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned service transmission method for power distribution networks. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0137] The processor can call the information and application program stored in the memory through the transmission device to perform the following steps: determine the target service data in the distribution network and the initial transmission channel corresponding to the target service data; obtain the transmission delay of the target service data in the initial transmission channel; if the delay exceeds a preset threshold, determine the transmission adjustment strategy, wherein the transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel; and transmit the target service data based on the transmission adjustment strategy.

[0138] Optionally, the processor may also execute program code for the following steps: determining target service data in the distribution network, including: acquiring raw service data in the distribution network, wherein the raw service data includes voltage, current and frequency signals; extracting semantic features of the raw service data based on a target neural network model to obtain semantic feature data, wherein the target neural network model is trained based on an initial neural network model; determining semantic noise corresponding to the semantic feature data; and determining the target service data based on the semantic feature data and semantic noise.

[0139] Optionally, the processor may also execute program code for the following steps: determining semantic noise corresponding to semantic feature data, including: determining the distribution of semantic noise based on adversarial training; determining the intensity of semantic noise based on the state of the initial transmission channel; and determining semantic noise based on the distribution and intensity.

[0140] Optionally, the processor may also execute program code for the following steps: determining the initial transmission channel corresponding to the target service data, including: determining the target channel bandwidth based on the priority of the target service data using network slicing technology; and determining the initial transmission channel based on the target channel bandwidth.

[0141] Optionally, the processor may also execute program code for the following steps: when the transmission adjustment strategy is to adjust the target service data, transmit the target service data based on the transmission adjustment strategy, including: determining the target number of bits corresponding to the target service data based on the delay; adjusting the target service data based on the target number of bits to obtain the adjusted target service data; and transmitting the adjusted target service data based on the initial transmission channel.

[0142] Optionally, the processor may also execute program code that performs the following steps: when the transmission adjustment strategy is to adjust the initial transmission channel, transmit target service data based on the transmission adjustment strategy, including: determining the target channel gain based on the initial channel gain of the initial transmission channel; determining the target transmission channel among multiple backup transmission channels based on the target channel gain; and transmitting the target service data based on the target transmission channel.

[0143] Optionally, the processor may also execute program code for the following steps: obtaining network load rate and security score during the transmission of target service data, wherein the security score is determined based on the transmission rate of target service data; inputting the network load rate and security score into a preset Markov chain decision model to obtain the optimal strategy, wherein the optimal strategy includes adjusting the transmission power of target service data to the optimal transmission power; and adjusting the transmission process of target service data based on the optimal strategy.

[0144] Optionally, the processor may also execute program code with the following steps: inputting network load rate and security score into a preset Markov chain decision model to obtain the optimal strategy, including: inputting network load rate and security score into the Markov chain decision model to obtain an initial strategy, wherein the initial strategy includes adjusting the transmission power of the target service data to the initial transmission power; calculating the reward value corresponding to the initial strategy based on a preset reward function; adjusting the parameters of the Markov chain decision model based on the reward value corresponding to the initial strategy to obtain an optimized Markov chain decision model; repeating the above steps to obtain reward values ​​corresponding to multiple initial strategies; and determining the optimal strategy based on the reward values ​​corresponding to multiple initial strategies.

[0145] This invention provides a service transmission method for a distribution network. By determining the target service data in the distribution network and the corresponding initial transmission channel, the transmission delay of the target service data in the initial transmission channel is obtained. If the delay exceeds a preset threshold, a transmission adjustment strategy is determined, which includes adjusting the target service data and adjusting the initial transmission channel. Based on the transmission adjustment strategy, the target service data is transmitted, achieving the goal of dynamically adjusting resource allocation and accurately matching service requirements. This improves transmission efficiency and stability, thus solving the technical problem that traditional transmission methods cannot dynamically adjust for delay issues.

[0146] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0147] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the service transmission method for power distribution networks provided in the above embodiments.

[0148] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0149] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the target service data in the distribution network and the initial transmission channel corresponding to the target service data; obtaining the transmission delay of the target service data in the initial transmission channel; determining a transmission adjustment strategy when the delay exceeds a preset threshold, wherein the transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel; and transmitting the target service data based on the transmission adjustment strategy.

[0150] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining target service data in the distribution network, including: acquiring original service data in the distribution network, wherein the original service data includes voltage, current and frequency signals; extracting semantic features of the original service data based on a target neural network model to obtain semantic feature data, wherein the target neural network model is trained based on an initial neural network model; determining semantic noise corresponding to the semantic feature data; and determining the target service data based on the semantic feature data and the semantic noise.

[0151] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining semantic noise corresponding to semantic feature data, including: determining the distribution of semantic noise based on adversarial training; determining the intensity of semantic noise based on the state of the initial transmission channel; and determining semantic noise based on the distribution and intensity.

[0152] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the initial transmission channel corresponding to the target service data, including: determining the target channel bandwidth based on the priority of the target service data using network slicing technology; and determining the initial transmission channel based on the target channel bandwidth.

[0153] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: when the transmission adjustment strategy is to adjust the target service data, transmitting the target service data based on the transmission adjustment strategy, including: determining the target number of bits corresponding to the target service data based on the latency; adjusting the target service data based on the target number of bits to obtain the adjusted target service data; and transmitting the adjusted target service data based on the initial transmission channel.

[0154] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: when the transmission adjustment strategy is to adjust the initial transmission channel, transmitting target service data based on the transmission adjustment strategy, including: determining a target channel gain based on the initial channel gain of the initial transmission channel; determining a target transmission channel among multiple backup transmission channels based on the target channel gain; and transmitting target service data based on the target transmission channel.

[0155] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: obtaining the network load rate and security score during the transmission of the target service data, wherein the security score is determined based on the transmission rate of the target service data; inputting the network load rate and security score into a preset Markov chain decision model to obtain an optimal strategy, wherein the optimal strategy includes adjusting the transmission power of the target service data to the optimal transmission power; and adjusting the transmission process of the target service data based on the optimal strategy.

[0156] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: inputting network load rate and security score into a preset Markov chain decision model to obtain an optimal strategy, including: inputting network load rate and security score into the Markov chain decision model to obtain an initial strategy, wherein the initial strategy includes adjusting the transmission power of the target service data to an initial transmission power; calculating the reward value corresponding to the initial strategy based on a preset reward function; adjusting the parameters of the Markov chain decision model based on the reward value corresponding to the initial strategy to obtain an optimized Markov chain decision model; repeating the above steps to obtain reward values ​​corresponding to multiple initial strategies; and determining the optimal strategy based on the reward values ​​corresponding to multiple initial strategies.

[0157] Embodiments of the present invention also provide a computer program product, including a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it can: determine the target service data in the distribution network and the initial transmission channel corresponding to the target service data; obtain the transmission delay of the target service data in the initial transmission channel; if the delay exceeds a preset threshold, determine a transmission adjustment strategy, wherein the transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel; and transmit the target service data based on the transmission adjustment strategy.

[0158] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0159] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0160] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0161] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0162] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0163] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0164] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A service transmission method for a power distribution network, characterized in that, include: Determine the target service data in the distribution network and the initial transmission channel corresponding to the target service data; The latency of the target service data being transmitted in the initial transmission channel is obtained; If the latency exceeds a preset threshold, a transmission adjustment strategy is determined, wherein the transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel; Based on the aforementioned transmission adjustment strategy, the target service data is transmitted.

2. The method according to claim 1, characterized in that, The determination of target service data in the distribution network includes: Acquire raw business data from the power distribution network, wherein the raw business data includes voltage, current, and frequency signals; Based on the target neural network model, semantic features of the original business data are extracted to obtain semantic feature data, wherein the target neural network model is trained based on the initial neural network model; Determine the semantic noise corresponding to the semantic feature data; Based on the semantic feature data and the semantic noise, the target business data is determined.

3. The method according to claim 2, characterized in that, Determining the semantic noise corresponding to the semantic feature data includes: The distribution of the semantic noise is determined based on adversarial training; The intensity of the semantic noise is determined based on the state of the initial transmission channel; The semantic noise is determined based on the distribution and the intensity.

4. The method according to claim 1, characterized in that, Determining the initial transmission channel corresponding to the target service data includes: Based on the priority of the target service data, the target channel bandwidth is determined using network slicing technology. The initial transmission channel is determined based on the target channel bandwidth.

5. The method according to claim 1, characterized in that, When the transmission adjustment strategy is to adjust the target service data, transmitting the target service data based on the transmission adjustment strategy includes: Based on the aforementioned latency, determine the target number of bits corresponding to the target service data; Based on the target number of bits, the target service data is adjusted to obtain the adjusted target service data; Based on the initial transmission channel, the adjusted target service data is transmitted.

6. The method according to claim 1, characterized in that, When the transmission adjustment strategy involves adjusting the initial transmission channel, transmitting the target service data based on the transmission adjustment strategy includes: Based on the initial channel gain of the initial transmission channel, determine the target channel gain; Based on the target channel gain, the target transmission channel is determined from multiple backup transmission channels; The target service data is transmitted based on the target transmission channel.

7. The method according to claim 1, characterized in that, Also includes: Obtain the network load rate and security score during the transmission of the target service data, wherein the security score is determined based on the transmission rate of the target service data; The network load rate and the security score are input into a preset Markov chain decision model to obtain the optimal strategy, wherein the optimal strategy includes adjusting the transmission power of the target service data to the optimal transmission power; Based on the optimal strategy, the transmission process of the target service data is adjusted.

8. The method according to claim 7, characterized in that, The step of inputting the network load rate and the security score into a preset Markov chain decision model to obtain the optimal strategy includes: The network load rate and the security score are input into the Markov chain decision model to obtain an initial strategy, wherein the initial strategy includes adjusting the transmission power of the target service data to the initial transmission power; Based on a preset reward function, calculate the reward value corresponding to the initial strategy; Based on the reward value corresponding to the initial strategy, the parameters of the Markov chain decision model are adjusted to obtain the optimized Markov chain decision model. Repeat the above steps to obtain multiple reward values ​​corresponding to the initial strategies; The optimal strategy is determined based on the reward values ​​corresponding to the multiple initial strategies.

9. A service transmission device for a power distribution network, characterized in that, include: The first determining module is used to determine the target service data in the distribution network and the initial transmission channel corresponding to the target service data; The acquisition module is used to acquire the transmission delay of the target service data in the initial transmission channel; The second determining module is used to determine a transmission adjustment strategy when the delay exceeds a preset threshold, wherein the transmission adjustment strategy includes adjusting the target service data and adjusting the initial transmission channel; The transmission module is used to transmit the target service data based on the transmission adjustment strategy.

10. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform the service transmission method for a power distribution network as described in any one of claims 1 to 8.

11. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the service transmission method for a power distribution network as described in any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the service transmission method for a power distribution network as described in any one of claims 1 to 8.

Images