Fault positioning method and system of power communication network and electronic equipment

Abstract

The invention relates to the technical field of electric power communication, in particular to a fault positioning method and system for an electric power communication network and electronic equipment. The method comprises the following steps: training a Bi-GRU neural network model through historical network disturbance alarm data in a power communication network to obtain a trained Bi-GRU neural network model; and when detecting that network disturbance alarm data is generated in the power communication network, applying the trained Bi-GRU neural network model to obtain a fault positioning result corresponding to the network disturbance alarm data. According to the method, the problems that the topological structure of the power communication network is increasingly complicated, the generated alarm data has multiple types and complicated contents, and the operation and maintenance personnel are difficult to accurately position the root alarm fault position in a short time are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power communications, and in particular to a fault locating method, system and electronic equipment for a power communication network. Background Art

[0002] As an important part of energy production, transmission and consumption, the power communication network has become the main platform of the energy Internet with its wide service scope, strong configuration capabilities, high security and reliability, and green and low-carbon characteristics. The power communication network is mainly used to transmit various control signals for power production, and provides a high-reliability, low-latency, and large-bandwidth transmission channel for special networks such as dispatching data networks and data communication networks. It is an indispensable carrier to ensure the safe and stable operation of electricity. Therefore, ensuring the normal operation of the power communication network is of great significance to the entire power system.

[0003] In recent years, due to the continuous development and advancement of the power communication network, the topological structure of the power communication network has become increasingly complex, and the alarm data generated is of many types and complex content. It is difficult for operation and maintenance personnel to accurately locate the root alarm fault location in a short period of time. Summary of the invention

[0004] The present invention provides a fault location method, system and electronic equipment for an electric power communication network, which are used to solve the problem that the topological structure of the electric power communication network is becoming increasingly complex, the alarm data generated is of many types and complicated content, and it is difficult for operation and maintenance personnel to accurately locate the root alarm fault position in a short time.

[0005] The present invention provides a method for locating a fault in a power communication network, comprising: The Bi-GRU neural network model is trained by using the historical network disturbance alarm data in the power communication network to obtain a trained Bi-GRU neural network model; When network disturbance alarm data is detected in the electric power communication network, the trained Bi-GRU neural network model is applied to obtain a fault location result corresponding to the network disturbance alarm data.

[0006] According to a fault location method for a power communication network provided by the present invention, the Bi-GRU neural network model is trained by using historical network disturbance alarm data in the power communication network to obtain a trained Bi-GRU neural network model, including: Acquire historical network disturbance alarm data in the electric power communication network, and process the historical network disturbance alarm data to obtain an alarm data set, wherein the alarm data set is composed of data features of each historical network disturbance alarm data; Acquire frequent item sets in the alarm data set, and obtain an association rule set of the alarm data set according to the frequent item sets of the alarm data set; The association rule set of the alarm data set is input into the Bi-GRU neural network model for training to obtain a trained Bi-GRU neural network model.

[0007] A fault location method for a power communication network provided by the present invention further includes: When the network disturbance alarm data is detected to be generated in the electric power communication network, the trained Bi-GRU neural network model is trained again according to the data features corresponding to the network disturbance alarm data; Obtain the model parameters obtained after retraining to obtain the fluctuation range of each model parameter before and after retraining; According to the model parameters whose fluctuation range is smaller than the preset fluctuation range, the trained Bi-GRU neural network model is updated.

[0008] According to a fault location method for a power communication network provided by the present invention, the Bi-GRU neural network model includes an input layer, a coding layer, a decoding layer and a fully connected layer; The encoding layer of the Bi-GRU neural network model is composed of two layers of bidirectional gated recurrent unit neural networks, and the decoding layer and the encoding layer of the Bi-GRU neural network model have symmetrical structures.

[0009] The present invention also provides a fault location system for a power communication network, comprising: An offline unit is used to train the Bi-GRU neural network model through historical network disturbance alarm data in the electric power communication network to obtain a trained Bi-GRU neural network model; The online unit is used to apply the trained Bi-GRU neural network model to obtain the fault location result corresponding to the network disturbance alarm data when the network disturbance alarm data is detected in the power communication network.

[0010] According to a fault location system of a power communication network provided by the present invention, the offline unit specifically includes: A data processing subunit, used for acquiring historical network disturbance alarm data in the electric power communication network, and processing the historical network disturbance alarm data to obtain an alarm data set, wherein the alarm data set is composed of data features of each historical network disturbance alarm data; A training set acquisition subunit, used to acquire frequent item sets in the alarm data set, and obtain an association rule set of the alarm data set according to the frequent item sets of the alarm data set; The model training subunit is used to input the association rule set of the alarm data set into the Bi-GRU neural network model for training to obtain the trained Bi-GRU neural network model.

[0011] According to a fault location system for an electric power communication network provided by the present invention, the offline unit also includes: a model updating subunit, which is used to re-train the trained Bi-GRU neural network model according to the data features corresponding to the network disturbance alarm data when the network disturbance alarm data is detected to be generated in the electric power communication network; obtain the model parameters obtained after the re-training to obtain the fluctuation range of each model parameter before and after the re-training; and update the trained Bi-GRU neural network model according to the model parameters whose fluctuation range is less than the preset fluctuation range.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a fault location method for a power communication network as described in any one of the above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for locating a fault in a power communication network as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the fault location method of the power communication network as described in any one of the above is implemented.

[0015] The fault location method, system and electronic device of the power communication network provided by the present invention trains the historical network disturbance alarm data in the power communication network by using the Bi-GRU neural network model, automatically learns the complex relationship between the alarm data, and can quickly and accurately locate the fault position when a new network disturbance alarm is detected. The efficiency and accuracy of fault detection are improved, and the time and cost of manual analysis are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 This is one of the flow charts of the fault location method for the power communication network provided by the present invention.

[0018] Figure 2 This is the second flow chart of the fault location method for the power communication network provided by the present invention.

[0019] Figure 3It is a schematic diagram of the principle of a Bi-GRU neural network model provided by the present invention.

[0020] Figure 4 This is the third flow chart of the fault location method for the power communication network provided by the present invention.

[0021] Figure 5 This is one of the schematic diagrams of simulation results of various network models provided by the present invention.

[0022] Figure 6 This is the second schematic diagram of simulation results of various network models provided by the present invention.

[0023] Figure 7 This is the third schematic diagram of simulation results of various network models provided by the present invention.

[0024] Figure 8 It is a structural schematic diagram of a fault location system for a power communication network provided by the present invention.

[0025] Fig. 9 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the descriptions used in this way can be interchanged where appropriate, so that the embodiments can be implemented in a sequence other than that illustrated or described in the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of the steps that appear in the present application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved. The division of modules in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between units can be electrical or other similar forms, which are not limited in this application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical units, or may be distributed in multiple circuit units, and some or all of the units may be selected according to actual needs to achieve the purpose of the present application.

[0028] Combine the following Figure 1-Figure 9 The specific contents of the present invention are described.

[0029] Figure 1 This is one of the flow charts of the fault location method of the power communication network provided by the present invention, such as Figure 1 As shown, the method includes steps S101-S102.

[0030] Step S101, training the Bi-GRU neural network model through historical network disturbance alarm data in the electric power communication network to obtain a trained Bi-GRU neural network model.

[0031] Step S102, when network disturbance alarm data is detected in the electric power communication network, the trained Bi-GRU neural network model is applied to obtain a fault location result corresponding to the network disturbance alarm data.

[0032] In an embodiment of the present invention, the historical network disturbance alarm data in the power communication network includes raw data collected from each gateway device without any data processing, including alarm data of gateway, environment, communication connection, performance and equipment. Since there are a large amount of non-alarm data, invalid data, redundant data, etc. in the original network disturbance alarm data, and the original alarm data is unevenly distributed, in order to ensure the quality of the alarm data and the efficiency of processing and analysis, it is necessary to pre-process the original alarm data in the data management library.

[0033] In an embodiment of the present invention, the "multi-source data aggregation" technology is used to import different types of network disturbance alarm data into the data management library through a unified entrance.

[0034] In a possible implementation, Figure 2 As shown, the Bi-GRU neural network model is trained through historical network disturbance alarm data in the power communication network to obtain a trained Bi-GRU neural network model, including steps S201-S203.

[0035] Step S201, obtaining historical network disturbance alarm data in the electric power communication network, and processing the historical network disturbance alarm data to obtain an alarm data set, wherein the alarm data set is composed of data features of each historical network disturbance alarm data.

[0036] Specifically, the historical network disturbance alarm data in the power communication network is processed to obtain an alarm data set, which specifically includes: Select the alarm information fields related to fault feature extraction in the data management library to obtain historical network disturbance alarm data, perform basic processing such as data cleaning, data deduplication, and data denoising on the historical network disturbance alarm data, and provide basic data support for the location of network disturbance sources. Select the appropriate time window size to synchronize the alarm information at the time of the fault to form an alarm transaction set. Fusion is performed on the network disturbance alarm information in the alarm transaction set after real-time collection and preprocessing. Using data association attachment technology and data association coverage technology, the specified field content is associated and then merged, and the same field is covered through the specified judgment logic to merge into an alarm data set.

[0037] Step S202: acquiring frequent item sets in the alarm data set, and obtaining an association rule set of the alarm data set according to the frequent item sets of the alarm data set.

[0038] Specifically, the data features extracted from the alarm data set are used as input to mine frequent itemsets and association rules based on the weighted association analysis algorithm; Step S203: input the association rule set of the alarm data set into the Bi-GRU neural network model for training to obtain a trained Bi-GRU neural network model.

[0039] Specifically, the frequent item sets and association rules mined by association analysis are sent to the Bi-GRU neural network model as training sample sets for learning and training. The fault source is located from a large number of disturbance alarm features, and the root alarm that can directly reflect the source of the fault in the communication network is mined; the optimization algorithm is used to minimize the loss function to improve the effectiveness and accuracy of fault location association analysis.

[0040] In one possible implementation, the Bi-GRU neural network model includes an input layer, an encoding layer, a decoding layer, and a fully connected layer; the encoding layer of the Bi-GRU neural network model is composed of two layers of bidirectional gated recurrent unit neural networks, and the decoding layer of the Bi-GRU neural network model has a symmetrical structure with the encoding layer.

[0041] Specifically, considering the dynamic and random nature of alarm data, in order to ensure the accuracy of the mapping between alarm data and fault locations, a bidirectional Bi-GRU neural network is used to construct a continuous update of the mapping relationship between new network disturbance alarm data and fault locations.

[0042] For example, Figure 3 As shown in the figure, the entire Bi-GRU neural network model includes an input layer, an encoding layer, a decoding layer, a fully connected layer, and an output layer. The input layer receives the historical data of each alarm information in the alarm system and preprocesses the data, including abnormal data removal and standardization. The encoding layer consists of two layers of bidirectional gated recurrent unit neural networks, which are used to compress and reduce the dimension of data to fully extract the intrinsic information of the time series. The decoding layer is symmetrical with the encoding layer structure, which is used to gradually restore the features after dimensionality reduction and output the reconstructed time series through the fully connected layer. The nonlinear activation function in all network layers uses the hyperbolic tangent (tanh) function.

[0043] In the embodiments of the present invention, a loss function is selected to calculate the difference between the positioning result of the Bi-GRU neural network model and the actual fault point, and the model convergence and the error of fault positioning are minimized by minimizing the loss value, so as to accurately locate the fault position. By calculating the difference between the positioning result and the actual fault point, and returning the error between the two to the network, the parameters are adjusted according to the feedback information, so that the error between its output value and the actual fault is gradually reduced, thereby assisting in rapid fault positioning and preventing misjudgment or misadjustment of communication scheduling.

[0044] During the training process, the softmax function is used as the loss function to evaluate the effect of the model. The softmax function can map each component of a vector to the interval [0,1] to ensure that the sum of all component outputs is 1. Assume that the original neural network output is , then the output after the softmax function is as shown in the formula, which can be regarded as the probability distribution of the predicted category is the i-th category.

[0045]

[0046] In a possible implementation, a fault location method for a power communication network, such as Figure 4 As shown, steps S401-S403 are also included.

[0047] Step S401, when it is detected that network disturbance alarm data is generated in the electric power communication network, the trained Bi-GRU neural network model is trained again according to the data features corresponding to the network disturbance alarm data.

[0048] Step S402, obtaining the model parameters obtained after retraining to obtain the fluctuation range of each model parameter before and after the retraining.

[0049] Step S403, updating the trained Bi-GRU neural network model according to the model parameters whose fluctuation range is smaller than the preset fluctuation range.

[0050] Specifically, the Bi-GRU neural network model is trained through the historical network disturbance alarm data in the power communication network to obtain the trained Bi-GRU neural network model. When a new alarm event occurs, the new alarm event is preprocessed and the associated features are extracted, and then put into the initial neural network model for training to obtain an updated neural network model. Considering that the updated neural network is trained with new alarm events, the parameters of the updated neural network may be more biased towards the new alarm data. In order to prevent the neural network from forgetting the previously learned knowledge, the parameters of the neural network are selectively selected, such as selecting parameters with a variation range less than λ (the preset fluctuation range λ in the embodiment of the present invention is 0-10%) as the parameters of the original neural network model, and parameters with a variation greater than 10% are eliminated.

[0051] The most detailed embodiment of the present invention is given below by way of example.

[0052] In an embodiment of the present invention, the adam gradient descent algorithm is used, the learning rate of the Bi-GRU neural network model is set to 0.005, the maximum number of training times is 1000 times, and the number of forward and backward GRU layers are set to 20. The square absolute error, mean square error and root mean square error results of the training set and the test set can be obtained, as shown in Table 1.

[0053] Table 1

[0054] Among them: MAE stands for mean absolute error, MSE stands for mean square error, and RMSE stands for root mean square error. In the fault location model, the three evaluation indicators of MAE, MSE and RMSE quantify the error between the model prediction value and the actual value, and RMSE gives a higher weight to large errors, which can better reflect the performance of the model in extreme situations.

[0055] The root mean square error (RMSE) is used as the main criterion for evaluating fault location performance. RMSE is defined as the square root of the average of the squared prediction errors and is a common indicator for measuring model prediction accuracy. By comparing the RMSE values ​​of different models on the same data set, the performance of each model in accurately locating system faults is evaluated. The Bi-GRU network model, RNN network model, and LSTM network model are used to train and learn the same data set. The simulation results are shown in Figure 2. Figure 5 As shown in the figure, it can be seen that the RMSE value of the trained Bi-GRU neural network model in the present invention is significantly lower than that of other neural network models, indicating its effectiveness and accuracy in handling complex fault location.

[0056] In order to verify the influence of learning rate on model performance, the root mean square error of fault location of each neural network model is compared by changing the learning rate. The comparison results are as follows: Figure 6 As shown. Figure 6 It can be seen that as the learning rate continues to increase, the RMSE values ​​of the three models are decreasing. This is because as the learning rate continues to increase, the RMSE value continues to decrease, and the accuracy of fault location is getting higher and higher. Compared with the LSTM model and the RNN model, the RMSE of fault location for the alarm data of the power communication network using the Bi-GRU neural network model is lower, indicating that the method proposed in the present invention is superior in the precise positioning process.

[0057] We start by selecting a basic data set and gradually changing the size of the data set to compare the execution time of the training and learning process. The comparison results are as follows: Figure 7As shown in the figure, it can be seen that as the data set increases, the execution time also increases. Compared with the other two neural network models, the execution time of the Bi-GRU neural network model proposed in the present invention is lower, which ensures the real-time performance of the complex network fault location process.

[0058] By adopting the above method, the present invention can achieve at least one of the following beneficial effects: 1. By using the Bi-GRU neural network model to train the historical network disturbance alarm data in the power communication network, the complex relationship between the alarm data can be automatically learned, so that when a new network disturbance alarm is detected, the fault location can be quickly and accurately located. This improves the efficiency and accuracy of troubleshooting and reduces the time and cost of manual analysis.

[0059] 2. When network disturbance alarm data is detected in the power communication network, the trained Bi-GRU neural network model is trained again according to the data features corresponding to the network disturbance alarm data. And the fluctuation range of each model parameter before and after re-training is obtained. The model parameters with a fluctuation range smaller than the preset fluctuation range are used to update the trained Bi-GRU neural network model. This avoids the decrease in model accuracy of the Bi-GRU neural network model due to parameter update.

[0060] The fault location system of the electric power communication network provided by the present invention is described below. The fault location system of the electric power communication network described below and the fault location method of the electric power communication network described above can be referred to each other.

[0061] like Figure 8 As shown, the present invention also provides a fault location system for a power communication network, comprising: An offline unit is used to train the Bi-GRU neural network model through historical network disturbance alarm data in the electric power communication network to obtain a trained Bi-GRU neural network model; The online unit is used to apply the trained Bi-GRU neural network model to obtain the fault location result corresponding to the network disturbance alarm data when the network disturbance alarm data is detected in the power communication network.

[0062] In a possible implementation manner, the offline unit specifically includes: A data processing subunit is used to obtain historical network disturbance alarm data in the power communication network, and process the historical network disturbance alarm data to obtain an alarm data set, wherein the alarm data set is composed of data features of each historical network disturbance alarm data; The training set acquisition subunit is used to acquire frequent item sets in the alarm data set, and obtain the association rule set of the alarm data set according to the frequent item sets of the alarm data set; The model training subunit is used to input the association rule set of the alarm data set into the Bi-GRU neural network model for training to obtain the trained Bi-GRU neural network model.

[0063] In an embodiment of the present invention, the alarm data set is composed of data features of various historical network disturbance alarm data, and the offline unit automatically divides the training set and the test data set according to the alarm data set for training the Bi-GRU neural network model.

[0064] In a possible implementation manner, the offline unit further includes: The model updating subunit is used to retrain the trained Bi-GRU neural network model according to the data features corresponding to the network disturbance alarm data when network disturbance alarm data is detected in the power communication network; obtain the model parameters obtained after the retraining to obtain the fluctuation range of each model parameter before and after the retraining; and update the trained Bi-GRU neural network model according to the model parameters whose fluctuation range is less than the preset fluctuation range.

[0065] In an embodiment of the present invention, the historical normal operation status data includes historical network disturbance alarm data in the power communication network. The offline unit is used to train and update the Bi-GRU neural network model, and load the trained and updated Bi-GRU neural network model into the online unit. In the online unit, when the positioning result does not match the actual fault location, the fault location will be re-performed.

[0066] Fig. 9 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 9 As shown, the electronic device may include: a processor 910, a communications interface 920, a memory 930 and a communication bus 940, wherein the processor 910, the communications interface 920 and the memory 930 communicate with each other through the communication bus 940. The processor 910 may call the logic instructions in the memory 930 to execute a fault location method for a power communication network, the method comprising: The Bi-GRU neural network model is trained by using the historical network disturbance alarm data in the power communication network to obtain a trained Bi-GRU neural network model; When network disturbance alarm data is detected in the power communication network, the trained Bi-GRU neural network model is applied to obtain the fault location result corresponding to the network disturbance alarm data.

[0067] In addition, the logic instructions in the above-mentioned memory 930 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0068] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute a method for locating a fault in a power communication network provided by the above methods, the method comprising: The Bi-GRU neural network model is trained by using the historical network disturbance alarm data in the power communication network to obtain a trained Bi-GRU neural network model; When network disturbance alarm data is detected in the power communication network, the trained Bi-GRU neural network model is applied to obtain the fault location result corresponding to the network disturbance alarm data.

[0069] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, a method for locating a fault in a power communication network provided by the above methods is implemented, the method comprising: The Bi-GRU neural network model is trained by using the historical network disturbance alarm data in the power communication network to obtain a trained Bi-GRU neural network model; When network disturbance alarm data is detected in the power communication network, the trained Bi-GRU neural network model is applied to obtain the fault location result corresponding to the network disturbance alarm data.

[0070] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0071] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for locating a fault in a power communication network, characterized in that: include: The Bi-GRU neural network model is trained by using the historical network disturbance alarm data in the power communication network to obtain a trained Bi-GRU neural network model; When network disturbance alarm data is detected in the electric power communication network, the trained Bi-GRU neural network model is applied to obtain a fault location result corresponding to the network disturbance alarm data.

2. The fault location method of the power communication network according to claim 1, characterized in that: The Bi-GRU neural network model is trained by using the historical network disturbance alarm data in the power communication network to obtain the trained Bi-GRU neural network model, including: Acquire historical network disturbance alarm data in the electric power communication network, and process the historical network disturbance alarm data to obtain an alarm data set, wherein the alarm data set is composed of data features of each historical network disturbance alarm data; Acquire frequent item sets in the alarm data set, and obtain an association rule set of the alarm data set according to the frequent item sets of the alarm data set; The association rule set of the alarm data set is input into the Bi-GRU neural network model for training to obtain a trained Bi-GRU neural network model.

3. The fault location method of the power communication network according to claim 1, characterized in that: Also includes: When the network disturbance alarm data is detected to be generated in the electric power communication network, the trained Bi-GRU neural network model is trained again according to the data features corresponding to the network disturbance alarm data; Obtain the model parameters obtained after retraining to obtain the fluctuation range of each model parameter before and after retraining; According to the model parameters whose fluctuation range is smaller than the preset fluctuation range, the trained Bi-GRU neural network model is updated.

4. The fault location method of the power communication network according to claim 1, characterized in that: The Bi-GRU neural network model includes an input layer, an encoding layer, a decoding layer and a fully connected layer; The encoding layer of the Bi-GRU neural network model is composed of two layers of bidirectional gated recurrent unit neural networks, and the decoding layer and the encoding layer of the Bi-GRU neural network model have symmetrical structures.

5. A fault location system for a power communication network, characterized in that: include: An offline unit is used to train the Bi-GRU neural network model through historical network disturbance alarm data in the electric power communication network to obtain a trained Bi-GRU neural network model; The online unit is used to apply the trained Bi-GRU neural network model to obtain the fault location result corresponding to the network disturbance alarm data when the network disturbance alarm data is detected in the power communication network.

6. The fault location system for the electric power communication network according to claim 5, characterized in that: The offline unit specifically includes: A data processing subunit, used for acquiring historical network disturbance alarm data in the electric power communication network, and processing the historical network disturbance alarm data to obtain an alarm data set, wherein the alarm data set is composed of data features of each historical network disturbance alarm data; A training set acquisition subunit, used to acquire frequent item sets in the alarm data set, and obtain an association rule set of the alarm data set according to the frequent item sets of the alarm data set; The model training subunit is used to input the association rule set of the alarm data set into the Bi-GRU neural network model for training to obtain the trained Bi-GRU neural network model.

7. The fault location system for the electric power communication network according to claim 5, characterized in that: The offline unit further includes: The model updating subunit is used to retrain the trained Bi-GRU neural network model according to the data features corresponding to the network disturbance alarm data when the network disturbance alarm data is detected in the power communication network; obtain the model parameters obtained after the retraining to obtain the fluctuation range of each model parameter before and after the retraining; and update the trained Bi-GRU neural network model according to the model parameters whose fluctuation range is less than the preset fluctuation range.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the fault location method for the power communication network as described in any one of claims 1 to 5 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the fault location method for the power communication network as claimed in any one of claims 1 to 5 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images