Power distribution network system based on 5G short slice private network and AI and fault diagnosis method

Abstract

The invention relates to a power distribution network system based on a 5G short slice private network and AI and a fault diagnosis method, and belongs to the technical field of power systems, the system comprises a private network module used for providing a data transmission channel through the 5G short slice private network; the edge calculation unit is used for preprocessing the acquired real-time data of the power distribution network to obtain target data; the artificial intelligence module is used for predicting the target data through the trained prediction model to obtain a fault type; and the distribution automation terminal is used for carrying out fault positioning and isolation based on the fault type. According to the power distribution network system based on the 5G short slice private network and the AI, safe operation of the power distribution network can be ensured, the reliability and the stability of the power distribution network system are improved, and a powerful guarantee is provided for safe and stable operation of a power system.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a distribution network system and a fault diagnosis method based on a 5G short-slice private network and AI. Background Art

[0002] With the development of intelligent power grid, higher requirements are placed on the reliability and stability of distribution network systems. Traditional distribution network fault detection and location methods often have problems such as high delay and insufficient accuracy, which makes it difficult to meet the operation and maintenance needs of modern distribution networks.

[0003] Therefore, a new distribution network system that can achieve efficient data transmission and intelligent fault prediction is needed. Summary of the invention

[0004] In view of this, it is necessary to provide a distribution network system and fault diagnosis method based on 5G short-slice private network and AI to solve the problems of low reliability and stability of the existing distribution network system.

[0005] In order to solve the above problems, the present invention provides a distribution network system based on 5G short-slice private network and AI, including: Private network modules, edge computing units, artificial intelligence modules and distribution automation terminals; The private network module is used to provide a data transmission channel through the 5G short-slice private network; The edge computing unit is used to pre-process the acquired real-time data of the distribution network to obtain target data; The artificial intelligence module is used to predict the target data through a trained prediction model to obtain the fault type; The distribution automation terminal is used to locate and isolate the fault based on the fault type.

[0006] In a possible implementation, the edge computing unit is specifically configured to: Acquire real-time data of the distribution network through sensors and IoT devices installed in the distribution network system; The real-time data of the power distribution network is preprocessed, and a data compression algorithm is used to compress the preprocessed data to obtain the target data.

[0007] In a possible implementation, the artificial intelligence module includes: Training unit and prediction unit; The training unit is used to train the convolutional neural network or the long short-term memory network based on the historical data of the distribution network to obtain the prediction model; The prediction unit is used to perform fault prediction on the target data through the prediction model to obtain the fault type.

[0008] In a possible implementation, the artificial intelligence module further includes: An updating unit is used to regularly update the prediction model through an online learning mechanism and the target data.

[0009] In a possible implementation, the artificial intelligence module further includes: The control unit is used to adjust the operating parameters of the distribution network system based on the fault type.

[0010] In a possible implementation, the private network module includes: The resource allocation unit is used to adjust the bandwidth, latency and reliability parameters of different slices according to the needs of the distribution network system.

[0011] In a possible implementation, the method further includes: The human-computer interaction interface is used to display the fault type in real time and receive user input to remotely monitor the distribution network system.

[0012] The present invention also provides a fault diagnosis method, which is applied to the distribution network system based on 5G short-slice private network and AI described in any of the above implementations, including: The acquired real-time data of the distribution network is preprocessed through the edge computing unit to obtain the target data; The target data is sent to the artificial intelligence module through the 5G short-slice private network, so as to predict the target data using the trained prediction model and obtain the fault type; The fault type is sent to the distribution automation terminal through the 5G short-slice private network for fault location and isolation.

[0013] In a possible implementation, the preprocessing includes: Data cleaning and data compression.

[0014] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the fault diagnosis method described in any of the above implementations.

[0015] The beneficial effects of the present invention are as follows: the distribution network system and fault diagnosis method based on 5G short-slice private network and AI provided by the present invention use the 5G short-slice private network through the private network module to provide a high-speed, low-latency data transmission channel, thereby improving data transmission efficiency, pre-processing real-time data through the edge computing unit to enhance data processing capabilities, and using the artificial intelligence module to use the trained prediction model to predict faults for target data, thereby improving the accuracy and efficiency of fault prediction, and locating and isolating faults based on fault types through the distribution automation terminal to ensure the safe operation of the distribution network, thereby improving the reliability and stability of the distribution network system, and providing a strong guarantee for the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A schematic diagram of the structure of an embodiment of a distribution network system based on a 5G short-slice private network and AI provided by the present invention; Figure 2 A method flow chart of an embodiment of a fault diagnosis method provided by the present invention; Figure 3 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0020] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0021] Figure 1 A structural diagram of an embodiment of a distribution network system based on a 5G short-slice private network and AI provided by the present invention is shown in FIG. Figure 1 As shown, the distribution network system 100 based on 5G short-slice private network and AI includes: Private network module 110, edge computing unit 120, artificial intelligence module 130 and distribution automation terminal 140; The private network module 110 is used to provide a data transmission channel through a 5G short-slice private network; The edge computing unit 120 is used to pre-process the acquired real-time data of the distribution network to obtain target data; The artificial intelligence module 130 is used to predict the target data through a trained prediction model to obtain a fault type; The distribution automation terminal 140 is used to locate and isolate the fault based on the fault type.

[0022] It should be noted that the short-slice private network is a private network established on a public wireless base station with the security capabilities of network isolation and physical isolation. It can meet the power industry's requirements for dedicated communication networks and the telecom operators' requirements for the controllable public network frequency resources.

[0023] The private network module can use the slicing technology of the 5G network to provide a dedicated data transmission channel for the distribution network system through the 5G short-slice private network, which can ensure high reliability and low latency of data transmission and meet the strict real-time requirements of the distribution network. During the data transmission process, encryption technology (such as AES-256) can also be used to protect the security of data and prevent unauthorized access and data leakage.

[0024] The edge computing unit is deployed close to the data source, and can use local computing power to process and analyze the real-time data of the distribution network in real time, and send the processed target data to the artificial intelligence module for further analysis through the 5G short-slice private network. The edge computing unit can pre-process and analyze data on the device side, reduce data transmission volume, and reduce network latency. The artificial intelligence module can use these pre-processed data for further analysis and decision-making, improving the overall data processing efficiency.

[0025] The artificial intelligence module can predict the target data through the trained prediction model. The prediction model can be built based on machine learning or deep learning algorithms. It can predict future faults by learning fault characteristics from historical data and obtain the possible fault types (such as short circuit, overload, ground fault, etc.) in the distribution network. The fault type is sent to the distribution automation terminal through the 5G short-slice private network.

[0026] Depending on the fault type, the distribution automation terminal can use built-in fault location algorithms (such as impedance-based fault location methods) to quickly determine the fault location. Once the fault location is determined, the distribution automation terminal will automatically perform fault isolation operations to disconnect the power supply to the faulty area. At the same time, the backup power supply is started or the grid structure is reconfigured to restore normal power supply to non-faulty areas.

[0027] Compared with the prior art, the distribution network system based on 5G short-slice private network and AI provided by the embodiment of the present invention uses the 5G short-slice private network through the private network module to provide a high-speed, low-latency data transmission channel, thereby improving data transmission efficiency. The edge computing unit pre-processes real-time data to enhance data processing capabilities. The artificial intelligence module uses a trained prediction model to predict faults of target data, thereby improving the accuracy and efficiency of fault prediction. The distribution automation terminal locates and isolates faults based on the fault type, thereby ensuring the safe operation of the distribution network, improving the reliability and stability of the distribution network system, and providing a strong guarantee for the safe and stable operation of the power system.

[0028] In some embodiments of the present invention, the edge computing unit is specifically used to: Acquire real-time data of the distribution network through sensors and IoT devices installed in the distribution network system; The real-time data of the power distribution network is preprocessed, and a data compression algorithm is used to compress the preprocessed data to obtain the target data.

[0029] The edge computing unit collects real-time data of the distribution network, such as voltage, current, and power factor, through smart sensors and IoT devices deployed at the distribution network site, and uses local computing power to perform preliminary screening and cleaning of the real-time data of the distribution network to remove noise and outliers.

[0030] In order to reduce the data transmission bandwidth requirements, the edge computing unit uses efficient data compression algorithms (such as LZW and Huffman coding) to compress the pre-processed data to obtain the target data. The target data is then sent to the artificial intelligence module through the 5G short-slice private network for further analysis.

[0031] The edge computing unit ensures the real-time nature of data by optimizing the data processing process, enabling the distribution network system to respond quickly to abnormal situations.

[0032] The distribution network system based on 5G short-slice private network and AI provided by the embodiment of the present invention can process and analyze distribution network data in real time through edge computing units deployed near the data source, reducing the delay in data transmission to the remote server and improving the real-time response capability of the system. Through distributed computing and storage technology, the edge computing unit can share the processing pressure of the central server, improve data processing efficiency and overall system performance. The edge computing unit can support local data processing and analysis of IoT devices, reduce data transmission pressure, and improve the overall efficiency and stability of the IoT system.

[0033] In some embodiments of the present invention, the artificial intelligence module includes: Training unit and prediction unit; The training unit is used to train the convolutional neural network or the long short-term memory network based on the historical data of the distribution network to obtain the prediction model; The prediction unit is used to perform fault prediction on the target data through the prediction model to obtain the fault type.

[0034] The role of the training unit is to train a neural network model based on historical data of the distribution network to generate a prediction model. The neural network model can be a convolutional neural network (CNN) or a long short-term memory network (LSTM).

[0035] The training process can include model training and model validation. Model training is to minimize the loss function through optimization algorithms (such as gradient descent) so that the model gradually learns the rules in the data; model validation is to evaluate the performance of the model through test set data to ensure that the model has good generalization ability.

[0036] The function of the prediction unit is to use the prediction model generated by the training unit to predict faults of the target data, input the target data into the prediction model, calculate the probability distribution of the fault type based on the input data, and determine the final fault type based on the probability distribution.

[0037] In some embodiments of the present invention, the artificial intelligence module further includes: An updating unit is used to regularly update the prediction model through an online learning mechanism and the target data.

[0038] The update unit uses the target data collected each time to regularly update and optimize the prediction model through an online learning mechanism. Online learning is a machine learning method that allows the model to continuously update itself when receiving new data to adapt to changes in the data, thereby improving the model's prediction performance.

[0039] The update unit periodically obtains new target data from the edge computing unit, which reflects the latest status of the distribution network.

[0040] Before updating the model, the update unit can first evaluate the performance of the current prediction model to determine whether it needs to be updated. When it is determined that the model needs to be updated, the update unit will use the new target data to train or fine-tune the prediction model. The updated model needs to be verified to ensure that its performance has not decreased and that it can better adapt to the new data.

[0041] The distribution network system based on 5G short-slice private network and AI provided by the embodiment of the present invention has stronger adaptability and learning ability through the online learning mechanism of the update unit, and can more accurately predict the type of faults in the distribution network, providing more powerful support for the safe and stable operation of the power system.

[0042] In some embodiments of the present invention, the artificial intelligence module further includes: The control unit is used to adjust the operating parameters of the distribution network system based on the fault type.

[0043] The control unit can automatically adjust the operating parameters of the distribution network system based on the type of fault predicted by the artificial intelligence module to prevent or mitigate the impact of the fault. For example, this can include adjusting key parameters such as voltage, current, power factor, and starting or shutting down specific equipment or lines.

[0044] The control unit first receives the fault type information from the prediction unit. Based on the fault type, the control unit will evaluate whether the operating parameters of the current distribution network system are appropriate, such as analysis of voltage stability, current overload, power balance, etc.

[0045] In some embodiments of the present invention, the private network module includes: The resource allocation unit is used to adjust the bandwidth, latency and reliability parameters of different slices according to the needs of the distribution network system.

[0046] The resource allocation unit can dynamically adjust the bandwidth, latency and reliability parameters of different network slices according to the actual needs of the distribution network system to ensure the efficiency and stability of data transmission.

[0047] The resource allocation unit can intelligently allocate and optimize network resources according to the business needs of the distribution network system, including dynamic adjustment of bandwidth, latency and reliability parameters of different network slices (such as power distribution business slices, distribution network operation monitoring business slices, power consumption information business slices, etc.).

[0048] Bandwidth adjustment: According to the bandwidth requirements of various services, the resource allocation unit can flexibly increase or decrease the bandwidth resources of the slice. For example, for distribution network operation monitoring services with high bandwidth requirements, more bandwidth resources can be allocated to ensure real-time data transmission.

[0049] Latency adjustment,Latency is another important performance indicator in the distribution network system. The resource allocation unit can optimize the network path and transmission strategy according to the latency requirements of the service to reduce the latency of the slice. For distribution services with extremely high latency requirements, such as fault warning and rapid response, the latency performance of their transmission channels can be prioritized.

[0050] Reliability adjustment,Reliability parameters reflect the stability and reliability of the network slice during transmission.,The resource allocation unit can adopt redundant transmission,error retransmission and other strategies to improve the reliability of the slice,according to the reliability requirements of the business.,For critical businesses, such as power grid control and protection information,,network slices with high reliability can be allocated to ensure accurate,transmission of data.

[0051] The distribution network system based on 5G short-slice private network and AI provided in the embodiment of the present invention dynamically adjusts the bandwidth, latency and reliability parameters of different network slices according to the actual needs of the distribution network system through a resource allocation unit, thereby ensuring the high efficiency and stability of data transmission and providing strong support for the safe and stable operation of the power system.

[0052] In some embodiments of the present invention, it further includes: The human-computer interaction interface is used to display the fault type in real time and receive user input to remotely monitor the distribution network system.

[0053] The human-computer interaction interface can receive fault type information from the artificial intelligence module in real time and display it on the interface in an intuitive manner (such as charts, alarm information, etc.), which helps operation and maintenance personnel to quickly understand the current status of the distribution network system and promptly discover and handle potential faults.

[0054] Through the human-computer interaction interface, users can remotely monitor the operating status of the distribution network system. The interface usually displays key system parameters (such as voltage, current, power factor, etc.) and the operating status of the equipment (such as online, offline, fault, etc.), providing users with a comprehensive system view to facilitate remote management and decision-making.

[0055] The human-computer interaction interface also supports user input functions, allowing users to interact with the system through devices such as keyboards, mice, or touch screens. Users can adjust the operating parameters of the distribution network system or perform specific operations (such as starting / stopping equipment, switching working modes, etc.) by inputting commands or parameters.

[0056] Figure 2 A method flow chart of an embodiment of the fault diagnosis method provided by the present invention is as follows Figure 2 As shown, the fault diagnosis method includes: S201, preprocessing the acquired real-time data of the distribution network through the edge computing unit to obtain target data; S202. Send the target data to the artificial intelligence module through the 5G short slice private network, so as to predict the target data using the trained prediction model to obtain the fault type; S203. Send the fault type to the distribution automation terminal through the 5G short-slice private network to locate and isolate the fault.

[0057] The executor of the fault diagnosis method provided by the present invention can be the distribution network system based on 5G short-slice private network and AI described in any of the above-mentioned implementation methods.

[0058] In S201, real-time data of the distribution network is collected through various sensors and IoT devices installed in the distribution network system, which may include key parameters such as voltage, current, and power factor.

[0059] The local computing power of the edge computing unit is used to preprocess the real-time data of the distribution network to obtain the target data.

[0060] In S202, the high bandwidth and low latency characteristics of the 5G short-slice private network are utilized to transmit the target data from the edge computing unit to the artificial intelligence module, ensuring the stability and reliability of data transmission.

[0061] The artificial intelligence module stores a trained prediction model, which is built based on algorithms such as deep learning or machine learning. It can predict the possible fault types in the distribution network by analyzing the target data. After processing the target data, the prediction model outputs the predicted fault type (line short circuit, overload, ground fault, etc.).

[0062] In S203, the predicted fault type information is transmitted to the distribution automation terminal using the 5G short-slice private network. The distribution automation terminal is an important device in the distribution network, responsible for monitoring and controlling the operation of the distribution network.

[0063] After receiving the fault type information, the distribution automation terminal combines the topology and real-time data of the distribution network to locate the fault. Fault location refers to determining the specific location or area where the fault occurs. Once the fault is located, the distribution automation terminal will take necessary measures to isolate the fault area to prevent the fault from spreading and protect the normal operation of other equipment. This usually includes steps such as cutting off the power supply to the fault area and starting the backup power supply.

[0064] Compared with the prior art, the fault diagnosis method provided in the embodiment of the present invention realizes rapid data processing and transmission by combining edge computing and 5G short-slice private networks, improves the accuracy and efficiency of diagnosis by using artificial intelligence algorithms for fault prediction, and realizes automatic fault location and isolation by introducing distribution automation terminals, reducing manual intervention. By combining the advantages of edge computing, 5G short-slice private networks and artificial intelligence technologies, it realizes rapid and accurate diagnosis and location of distribution network faults, providing a strong guarantee for the safe and stable operation of the power system.

[0065] In some embodiments of the present invention, the preprocessing comprises: Data cleaning and data compression.

[0066] The edge computing unit can use local computing power to perform preliminary screening and cleaning of real-time data of the distribution network to remove noise and outliers.

[0067] In order to reduce the data transmission bandwidth requirements, the edge computing unit uses efficient data compression algorithms (such as LZW and Huffman coding) to compress the preprocessed data to obtain the target data.

[0068] like Figure 3 As shown, the present invention also provides an electronic device 300. The electronic device 300 includes a processor 301, a memory 302 and a display 303. Figure 3 Only some components of the electronic device 300 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0069] In some embodiments, the processor 301 may be a central processing unit (CPU), a microprocessor or other data processing chip, and is used to run program codes or process data stored in the memory 302, such as the fault diagnosis method of the present invention.

[0070] In some embodiments, the processor 301 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 301 may be local or remote. In some embodiments, the processor 301 may be implemented in a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0071] In some embodiments, the memory 302 may be an internal storage unit of the electronic device 300, such as a hard disk or memory of the electronic device 300. In other embodiments, the memory 302 may also be an external storage device of the electronic device 300, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 300.

[0072] Furthermore, the memory 302 may include both an internal storage unit of the electronic device 300 and an external storage device. The memory 302 is used to store application software installed in the electronic device 300 and various data.

[0073] In some embodiments, the display 303 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an organic light-emitting diode (OLED) touch device, etc. The display 303 is used to display information on the electronic device 300 and to display a visual user interface. The components 301-303 of the electronic device 300 communicate with each other via a system bus.

[0074] In one embodiment, when the processor 301 executes the fault diagnosis program in the memory 302, the following steps may be implemented: The acquired real-time data of the distribution network is preprocessed through the edge computing unit to obtain the target data; The target data is sent to the artificial intelligence module through the 5G short-slice private network, so as to predict the target data using the trained prediction model and obtain the fault type; The fault type is sent to the distribution automation terminal through the 5G short-slice private network for fault location and isolation.

[0075] It should be understood that: when the processor 301 executes the fault diagnosis program in the memory 302, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0076] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 300 mentioned, and the electronic device 300 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 300 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0077] Correspondingly, an embodiment of the present invention also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions in the fault diagnosis method provided by the above-mentioned method embodiments can be implemented.

[0078] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0079] The above is a detailed introduction to the distribution network system and fault diagnosis method based on 5G short-slice private network and AI provided by the present invention. This article uses specific examples to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A distribution network system based on 5G short-slice private network and AI, characterized in that: include: Private network modules, edge computing units, artificial intelligence modules and distribution automation terminals; The private network module is used to provide a data transmission channel through the 5G short-slice private network; The edge computing unit is used to pre-process the acquired real-time data of the distribution network to obtain target data; The artificial intelligence module is used to predict the target data through a trained prediction model to obtain the fault type; The distribution automation terminal is used to locate and isolate the fault based on the fault type.

2. The distribution network system based on 5G short-slice private network and AI according to claim 1, characterized in that: The edge computing unit is specifically used for: Acquire real-time data of the distribution network through sensors and IoT devices installed in the distribution network system; The real-time data of the power distribution network is preprocessed, and a data compression algorithm is used to compress the preprocessed data to obtain the target data.

3. The distribution network system based on 5G short-slice private network and AI according to claim 1, characterized in that: The artificial intelligence module includes: Training unit and prediction unit; The training unit is used to train the convolutional neural network or the long short-term memory network based on the historical data of the distribution network to obtain the prediction model; The prediction unit is used to perform fault prediction on the target data through the prediction model to obtain the fault type.

4. The distribution network system based on 5G short-slice private network and AI according to claim 3 is characterized in that: The artificial intelligence module further includes: An updating unit is used to regularly update the prediction model through an online learning mechanism and the target data.

5. The distribution network system based on 5G short-slice private network and AI according to claim 3 is characterized in that: The artificial intelligence module further includes: The control unit is used to adjust the operating parameters of the distribution network system based on the fault type.

6. The distribution network system based on 5G short-slice private network and AI according to claim 1, characterized in that: The private network module includes: The resource allocation unit is used to adjust the bandwidth, latency and reliability parameters of different slices according to the needs of the distribution network system.

7. The distribution network system based on 5G short-slice private network and AI according to claim 1, characterized in that: Also includes: The human-computer interaction interface is used to display the fault type in real time and receive user input to remotely monitor the distribution network system.

8. A fault diagnosis method, characterized in that: The distribution network system based on 5G short-slice private network and AI as described in any one of claims 1 to 7 comprises: The acquired real-time data of the distribution network is preprocessed through the edge computing unit to obtain the target data; The target data is sent to the artificial intelligence module through the 5G short-slice private network, so as to predict the target data using the trained prediction model and obtain the fault type; The fault type is sent to the distribution automation terminal through the 5G short-slice private network for fault location and isolation.

9. The fault diagnosis method according to claim 8, characterized in that: The pre-processing comprises: Data cleaning and data compression.

10. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the fault diagnosis method as described in claim 8 or 9.

Images