Power distribution network monitoring method and device and power distribution network monitoring system

Abstract

The invention provides a power distribution network monitoring method and device and a power distribution network monitoring system. The method comprises the steps that related parameters of the power distribution network are acquired, and the related parameters comprise one or more of current, voltage and temperature; performing first anomaly analysis on the related parameters according to an SVM algorithm to obtain a first analysis result; performing second anomaly analysis on the related parameters according to the sizes of the related parameters to obtain a second analysis result; early warning analysis is carried out according to the first analysis result and the second analysis result, early warning levels are determined, and different early warning levels correspond to different processing strategies. According to the scheme, the problem that effective early warning cannot be achieved due to the fact that the anomaly detection mode of the power distribution network in the prior art is low in efficiency is solved.

Description

Technical Field

[0001] The present application relates to the technical field of distribution network, and in particular to a distribution network monitoring method, device, computer program product and distribution network monitoring system. Background Art

[0002] With the development of smart grids, the complexity and importance of distribution networks have become increasingly prominent. However, the current monitoring of distribution networks mostly relies on static monitoring and regular inspections, lacking dynamic early warning methods. Once a failure occurs, it may cause power outages or even safety accidents. The existing distribution network monitoring technology only relies on prosecutors to judge the real-time parameters of the distribution network, or through the power grid system. Therefore, the current abnormal detection method of the distribution network is inefficient and cannot achieve effective early warning. Summary of the invention

[0003] The main purpose of the present application is to provide a distribution network monitoring method, device, computer program product and distribution network monitoring system, so as to at least solve the problem that the abnormality detection method of the distribution network in the prior art is inefficient and cannot achieve effective early warning.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a monitoring method for a distribution network is provided, comprising: obtaining relevant parameters of the distribution network, wherein the relevant parameters include one or more of current, voltage and temperature; performing a first abnormality analysis on the relevant parameters according to a SVM algorithm to obtain a first analysis result; performing a second abnormality analysis on the relevant parameters according to the size of the relevant parameters to obtain a second analysis result; performing a warning analysis based on the first analysis result and the second analysis result to determine a warning level, wherein different warning levels correspond to different processing strategies.

[0005] Optionally, a first abnormality analysis is performed on the relevant parameters according to an SVM algorithm to obtain a first analysis result, including: constructing a fault analysis model, wherein the fault analysis model is trained by an SVM algorithm using multiple sets of training data, each set of training data in the multiple sets of training data includes historical relevant parameters obtained within a historical time period, and historical first analysis results corresponding to the historical relevant parameters; inputting the relevant parameters into the fault analysis model to obtain the first analysis results corresponding to the relevant parameters.

[0006] Optionally, according to the size of the relevant parameters, a second abnormality analysis is performed on the relevant parameters to obtain a second analysis result, including: obtaining a preset threshold, wherein the preset threshold is a threshold of a standard parameter of the distribution network; when the relevant parameter is less than or equal to the preset threshold, determining that the distribution network has not failed, and obtaining the second analysis result; when the relevant parameter is greater than the preset threshold, determining that the distribution network has failed, and obtaining the second analysis result.

[0007] Optionally, performing a warning analysis based on the first analysis result and the second analysis result to determine the warning level includes: obtaining an evaluation score, wherein the evaluation score is obtained based on the size relationship between the relevant parameters corresponding to the second analysis result and the preset threshold value; performing a warning analysis based on the first analysis result and the evaluation score to determine the warning level.

[0008] Optionally, obtaining an evaluation score includes: when the relevant parameter is less than or equal to a first preset threshold, determining the evaluation score to be a first evaluation score, wherein the first preset threshold is a minimum value of the standard parameter of the distribution network; when the relevant parameter is greater than the first preset threshold and the relevant parameter is less than a second preset threshold, determining the evaluation score to be a second evaluation score, wherein the second preset threshold is a maximum value of the standard parameter of the distribution network, the first preset threshold is less than the second preset threshold, and the first evaluation score is less than the second evaluation score; when the relevant parameter is greater than or equal to the second preset threshold, determining the evaluation score to be a third evaluation score, wherein the second evaluation score is less than the third evaluation score.

[0009] Optionally, performing a warning analysis based on the first analysis result and the evaluation score to determine the warning level includes: when the first analysis result indicates that no fault has occurred and the evaluation score is less than a first score threshold, determining the warning level to be a zero warning level; when the first analysis result indicates that no fault has occurred, and the evaluation score is greater than or equal to the first score threshold, and the evaluation score is less than a second score threshold, determining the warning level to be a first warning level, wherein the first score threshold is less than the second score threshold; when the first analysis result indicates that no fault has occurred and the evaluation score is greater than or equal to the second score threshold, determining the warning level to be a second warning level, wherein the degree of the first warning level is lower than the degree of the second warning level; when the first analysis result indicates that a fault has occurred and the evaluation score is greater than or equal to a third score threshold, determining the warning level to be a third warning level, wherein the first score threshold is greater than the third score threshold, and the degree of the second warning level is lower than the degree of the third warning level.

[0010] Optionally, obtaining relevant parameters of the distribution network includes: obtaining multiple initial relevant parameters, wherein the initial relevant parameters are initial relevant parameters of the distribution network obtained within a target detection period; and calculating an average value of the multiple initial relevant parameters to obtain the relevant parameters.

[0011] According to another aspect of the present application, a monitoring device for a distribution network is provided, including: an acquisition unit, used to acquire relevant parameters of the distribution network, wherein the relevant parameters include one or more of current, voltage and temperature; a first analysis unit, used to perform a first abnormality analysis on the relevant parameters according to a SVM algorithm to obtain a first analysis result; a second analysis unit, used to perform a second abnormality analysis on the relevant parameters according to the size of the relevant parameters to obtain a second analysis result; and an early warning unit, used to perform early warning analysis according to the first analysis result and the second analysis result to determine an early warning level, wherein different early warning levels correspond to different processing strategies.

[0012] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any one of the methods for monitoring a power distribution network are implemented.

[0013] According to another aspect of the present application, a distribution network monitoring system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing any one of the distribution network monitoring methods described.

[0014] By applying the technical solution of the present application, the accuracy of fault identification can be improved based on SVM algorithm detection. By then performing detection through data size, fault identification can be performed directly and simply. This solution does not require manual inspection and judgment. Different abnormality identification results can be obtained through two abnormality analysis methods, thereby improving the efficiency of abnormality detection. Different levels of warnings can also be performed based on the abnormality identification results, thereby achieving effective warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing a method for monitoring a power distribution network provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic diagram of a flow chart of a method for monitoring a distribution network provided according to an embodiment of the present application is shown;

[0018] Figure 3 A schematic flow chart of another method for monitoring a power distribution network is shown;

[0019] Figure 4 A structural block diagram of a monitoring device for a distribution network provided according to an embodiment of the present application is shown;

[0020] Figure 5 A logical schematic diagram of a distribution network monitoring system according to a specific implementation is shown.

[0021] The above drawings include the following reference numerals:

[0022] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0025] It should be noted that 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 sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. 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 comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] The existing early warning systems and early warning judgment methods have the following problems: the monitoring data update is delayed, resulting in a long early warning response time; the fault diagnosis lacks intelligence and cannot effectively predict various fault conditions; there is a lack of comprehensive analysis of the operating status of the distribution network, and various types of data cannot be effectively integrated for early warning.

[0027] As introduced in the background technology, the abnormality detection method of the distribution network in the prior art is inefficient and cannot achieve effective early warning. To solve the above problems, the embodiments of the present application provide a distribution network monitoring method, device, computer program product and distribution network monitoring system.

[0028] 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.

[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for monitoring a distribution network according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] In this embodiment, a method for monitoring a distribution network running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0032] Figure 2 FIG. 1 is a flow chart of a method for monitoring a distribution network according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0033] Step S201, obtaining relevant parameters of the distribution network, wherein the relevant parameters include one or more of current, voltage and temperature;

[0034] Specifically, data collection begins, which is the core starting point of early warning. Relevant parameters include but are not limited to current, voltage and temperature data in the distribution network. These data are usually collected in real time from multiple detection points or sensors in the distribution network, and can be a combination of one or more parameters, so as to comprehensively evaluate the operating status of the distribution network. The purpose of data collection is to provide necessary data support for subsequent analysis and ensure accurate judgment based on the latest operating parameters.

[0035] In the specific implementation process, the detection nodes of the distribution network can be set at the transformer nodes, distribution station nodes, switch equipment nodes (such as circuit breakers, disconnectors), distribution line nodes, etc. of the distribution network. The purpose is to display the comprehensive working conditions of the distribution network area so that the working effect of the early warning system is in the best state.

[0036] Step S202, performing a first abnormality analysis on the above-mentioned related parameters according to the SVM algorithm to obtain a first analysis result;

[0037] Specifically, after the data collection is completed, the pre-trained SVM (Support Vector Machine) algorithm is used to perform in-depth analysis on the collected parameters. The SVM algorithm is a supervised learning method, which is mainly used for classification and regression analysis. It can identify complex patterns in the data and is suitable for processing high-dimensional data. In this step, the SVM algorithm is used to identify abnormal patterns in the distribution network parameters, that is, to detect whether there are parameter values ​​that exceed the normal operating range. The first analysis result is based on the judgment of the relevant parameters by the SVM algorithm, which can indicate whether the operating state of the distribution network deviates from the normal and stable range, thereby predicting whether there is a potential fault.

[0038] Step S203, performing a second abnormality analysis on the above-mentioned related parameters according to the magnitude of the above-mentioned related parameters to obtain a second analysis result;

[0039] Specifically, unlike the abstract model of the machine learning algorithm, the second anomaly analysis is based on intuitive numerical comparison. It compares the collected parameters with the preset thresholds to determine whether the parameters are beyond the acceptable range. For example, if the current or voltage value exceeds the safety threshold, or the temperature exceeds the normal operating temperature, these parameters will be marked as abnormal. This analysis step is based on the traditional threshold judgment method, which provides additional verification for the first analysis results to ensure the comprehensiveness and accuracy of the early warning. The second analysis result directly reflects whether the actual value of the parameter meets the set safety standards.

[0040] Step S204: Perform warning analysis based on the first analysis result and the second analysis result to determine a warning level, wherein different warning levels correspond to different processing strategies.

[0041] Specifically, based on the first two steps, the first analysis result and the second analysis result are combined to determine the warning level through comprehensive analysis. The warning level is determined based on the severity of the first analysis result and the second analysis result, as well as the correlation between them. For example, if the SVM algorithm identifies a potential fault and the parameter value exceeds the threshold, this may indicate a high-risk fault and a higher warning level will be given. Each warning level corresponds to a specific processing strategy. For example, a first-level warning may trigger the system to conduct a detailed inspection, a second-level warning may automatically adjust the load of the distribution network, and a third-level warning may require immediate power supply cutoff and initiation of an emergency response. This hierarchical warning and response mechanism ensures that appropriate actions are taken for events of different risk levels, improving the operational safety and efficiency of the distribution network.

[0042] Through this embodiment, based on the SVM algorithm detection, the accuracy of fault identification can be improved. Then, by detecting through the data size, fault identification can be performed directly and simply. This solution does not require manual inspection and judgment. Different abnormality identification results can be obtained through two abnormality analysis methods, which improves the efficiency of abnormality detection. Different levels of warnings can also be made based on the abnormality identification results, thereby achieving effective warnings.

[0043] Specifically, Figure 3 As shown, it mainly includes the following steps:

[0044] Step A: collecting parameter data of current, voltage and temperature of each detection node on the distribution network within a set detection period;

[0045] Step B, analyzing and processing the collected current, voltage, and temperature data of the detection node to generate current comparison reference data, voltage comparison reference data, and temperature comparison reference data of the corresponding detection node;

[0046] Step C, analyzing and processing the corresponding current parameter data, voltage parameter data, temperature parameter data, current comparison benchmark data, voltage comparison benchmark data and temperature comparison benchmark data to generate a feature vector of the corresponding detection node;

[0047] Step D: input the feature vector of the corresponding detection node into the SVM fault warning model, and output the evaluation parameter A of the corresponding detection node;

[0048] Step E: Compare and calculate the current comparison benchmark data, voltage comparison benchmark data and temperature comparison benchmark data of the corresponding detection node with the corresponding warning threshold value, and output the evaluation parameter B of the corresponding detection node;

[0049] Step F: Compare the evaluation parameters A and B outputted from the data analysis with the set warning standards, and output the corresponding warning level and the warning treatment measures corresponding to the above warning level.

[0050] Specifically, the preset SVM fault warning model and SVM algorithm prediction significantly improve the accuracy of fault identification, integrate multi-dimensional data for all-round monitoring, and can warn of potential risks in advance and reduce the accident rate.

[0051] In the specific implementation process, a first abnormality analysis is performed on the above-mentioned related parameters according to the SVM algorithm to obtain a first analysis result, which can be achieved through the following steps: constructing a fault analysis model, wherein the above-mentioned fault analysis model is obtained by training with the SVM algorithm using multiple sets of training data, and each set of training data in the above-mentioned multiple sets of training data includes historical related parameters obtained within a historical time period and historical first analysis results corresponding to the above-mentioned historical related parameters; the above-mentioned related parameters are input into the above-mentioned fault analysis model to obtain the above-mentioned first analysis result corresponding to the above-mentioned related parameters.

[0052] In this solution, the SVM model can learn and adapt to changes in the operating status of the distribution network based on historical data. With the continuous training and optimization of the model, the intelligence and accuracy of the early warning will continue to improve, reducing the problems of false alarms and missed alarms. Automated fault prediction reduces the reliance on manual regular inspections, which can reduce operating costs while improving response speed and efficiency. The SVM model can comprehensively consider multiple parameters instead of relying on a single parameter, which enables a more comprehensive identification of potential problems in the distribution network and improves the comprehensiveness and reliability of fault identification. Using the SVM algorithm to build a fault analysis model can significantly improve the fault prediction capability of the early warning system, achieve smarter and more comprehensive real-time monitoring and early warning of the distribution network, and help take measures in advance to prevent faults, reduce grid operation risks, and improve the stability and safety of the power system.

[0053] Specifically, a large amount of historical data must first be collected. These data are obtained from the distribution network at different time points in the past, including historical related parameters (such as current, voltage, temperature, etc.) and the results corresponding to these parameters, that is, the historical first analysis results. The "historical first analysis results" here can be the fault state or normal state marked in the past, which is used as the label of the training data to guide the SVM model to learn how to distinguish between normal and abnormal operating states.

[0054] Trained by SVM algorithm: Support vector machine (SVM) is a machine learning algorithm widely used in classification and regression analysis. It can find an optimal decision boundary (hyperplane) to separate data points of different categories (in this case, data points of normal operation and abnormal operation) as much as possible. Through training, the SVM model can learn the complex boundary that distinguishes normal and abnormal states, thus having the ability to predict faults.

[0055] Specifically, the training of the SVM fault warning model (fault analysis model) inputs the work records of the distribution network in the past working time into the Python sklearn library for SVM model training, wherein the work records include feature vector sets and corresponding label sets under normal and fault states, and the SVM fault warning model is obtained after training; when using the SVM fault warning model, as the number of work judgments increases, the SVM fault warning model is dynamically improved to make its judgment more accurate.

[0056] Specifically, the above step D includes:

[0057] D1, detect the feature vector X of the node new Input into the SVM fault warning model, probability = model.decision f unction(X new ), set the prediction threshold threshold = 0.5, where the prediction threshold threshold can be set manually to determine the weight factor of the SVM fault warning model, and output the model prediction result Y pred =(probability>=threshold).astype(int),Y pred =1 or 0; Y pred To evaluate the parameter A.

[0058] Specifically, when Y pred =1, it is judged that the detection node of the distribution network is faulty; when Y pred =0, it is judged that there is no obvious fault in the detection node of the distribution network.

[0059] In some embodiments, according to the sizes of the above-mentioned related parameters, a second abnormality analysis is performed on the above-mentioned related parameters to obtain a second analysis result, which can be specifically achieved through the following steps: obtaining a preset threshold, wherein the above-mentioned preset threshold is a threshold of a standard parameter of the above-mentioned distribution network; when the above-mentioned related parameter is less than or equal to the above-mentioned preset threshold, determining that the above-mentioned distribution network has not failed, and obtaining the above-mentioned second analysis result; when the above-mentioned related parameter is greater than the above-mentioned preset threshold, determining that the above-mentioned distribution network has failed, and obtaining the above-mentioned second analysis result.

[0060] In this solution, by directly comparing real-time parameters with thresholds, anomalies can be immediately identified, which is critical to preventing possible fault escalation. Timely warnings help to take quick measures to avoid possible power outages, equipment damage, or safety accidents. Threshold comparison is a relatively simple and intuitive anomaly detection method that does not require complex calculations or model training. For real-time monitoring systems, this method can achieve rapid response while also reducing the demand for computing resources.

[0061] Specifically, the preset thresholds are safety or warning limits determined based on the normal operating conditions of the distribution network and the performance of the equipment. These thresholds are usually set based on the electrical specifications, design standards, and historical operating data of the distribution network, and represent the maximum or minimum values ​​allowed for various parameters (such as current, voltage, and temperature) in the distribution network. The setting of the preset thresholds is based on professional knowledge and experience of the safe operating conditions of the power grid, and is intended to identify operating parameters that are beyond the normal range, indicating potential safety issues such as equipment overload, short circuit, and excessive heating.

[0062] The parameter data collected in real time is directly compared with the above preset thresholds. If the relevant parameter is less than or equal to the preset threshold, the power grid is considered to be in a safe operating state, no alarm will be issued, and the second analysis result indicates that there is no fault in the distribution network. On the contrary, if the relevant parameter is greater than the preset threshold, this indicates that the operating state of the power grid may have reached or exceeded the safety limit, which may indicate that a fault is about to occur or has occurred, so the second analysis result will indicate the existence of a fault condition.

[0063] For example, current, voltage and temperature data are collected in real time through sensors installed at various key locations of the distribution network, such as transformers, distribution substations, switchgear and distribution lines. For example, the sensors collect data every 5 minutes.

[0064] According to the grid design specifications and historical operation data, the standard threshold of each parameter is determined. For example, for current, the preset threshold may be 150A; for voltage, the preset threshold may be 220V±10%; for temperature, the preset threshold may be 40℃.

[0065] First, the collected current data is compared with a preset current threshold value. If the current values ​​of all detection points are less than or equal to 150A, it is determined that there is no fault in the distribution network in terms of current, and the second analysis result is normal (for example, marked as 0).

[0066] Compare the voltage data with the preset voltage threshold. If the voltage value at the detection point falls within the range of 220V±10%, the voltage analysis result is also normal.

[0067] The temperature data is compared with the preset threshold value of 40°C. If the temperature value is not higher than 40°C, the temperature analysis result is normal.

[0068] In the first case, if the collected current value exceeds 150A, the second abnormality analysis determines that the distribution network has a fault in current, and the second analysis result is abnormal (for example, marked as 1). A current abnormality warning signal is immediately sent.

[0069] For voltage and temperature, similar logic is followed. If the detected voltage value deviates from the range of 220V±10% or the temperature value exceeds 40°C, the second analysis result is abnormal and a corresponding warning signal is also generated.

[0070] In the specific implementation process, early warning analysis is performed based on the above-mentioned first analysis result and the above-mentioned second analysis result to determine the early warning level, which can be achieved through the following steps: obtaining an evaluation score, wherein the above-mentioned evaluation score is obtained based on the size relationship between the above-mentioned relevant parameters corresponding to the above-mentioned second analysis result and the above-mentioned preset threshold value; early warning analysis is performed based on the above-mentioned first analysis result and the above-mentioned evaluation score to determine the above-mentioned early warning level.

[0071] In this solution, by combining the prediction of the machine learning model with the comparison of the threshold of the intuitive numerical value, the real-time status of the distribution network can be evaluated more intelligently and more accurate early warning judgments can be made. The setting of the early warning level enables different levels of response measures to be taken according to the potential severity of the fault, from monitoring notifications to emergency power outages, ensuring the efficiency and pertinence of the early warning response. The introduction of evaluation scores makes the early warning analysis more data-driven, relying not only on the prediction of the model, but also on the degree to which the actual parameters deviate from the normal range, providing decision makers with more comprehensive information and helping to make timely and effective responses.

[0072] Specifically, the evaluation score is obtained based on the results of the second abnormal analysis, that is, the comparison of the real-time parameters with the preset thresholds. After each parameter (such as current, voltage, temperature) is compared with the corresponding threshold, a quantitative indicator indicating the degree of parameter deviation can be obtained. For example, if the current parameter exceeds the threshold, a higher evaluation score can be given by evaluating the degree and frequency of the excess; on the contrary, if the parameter is within the threshold range, the evaluation score may be lower. This evaluation score is set to quantify the results of the second analysis, so that there can be a unified measurement standard for the abnormal status of different parameters, so as to perform effective weighting and integration in the subsequent early warning analysis.

[0073] Early warning analysis is the process of comprehensively considering the first analysis result (prediction based on the SVM algorithm) and the evaluation score of the second analysis result. An algorithm may be used to determine the early warning level based on the positive prediction (potential failure) of the first analysis result and the evaluation score. The early warning level may be divided into multiple levels, such as minor abnormality, moderate risk, severe failure, etc., each level corresponds to a different handling strategy and urgency.

[0074] In some embodiments, obtaining the evaluation score can be specifically achieved through the following steps: when the above-mentioned relevant parameters are less than or equal to the first preset threshold, determining the above-mentioned evaluation score as the first evaluation score, wherein the above-mentioned first preset threshold is the minimum value of the standard parameter of the above-mentioned distribution network; when the above-mentioned relevant parameters are greater than the above-mentioned first preset threshold and the above-mentioned relevant parameters are less than the second preset threshold, determining the above-mentioned evaluation score as the second evaluation score, wherein the above-mentioned second preset threshold is the maximum value of the standard parameter of the above-mentioned distribution network, the above-mentioned first preset threshold is less than the above-mentioned second preset threshold, and the above-mentioned first evaluation score is less than the above-mentioned second evaluation score; when the above-mentioned relevant parameters are greater than or equal to the above-mentioned second preset threshold, determining the above-mentioned evaluation score as the third evaluation score, wherein the above-mentioned second evaluation score is less than the above-mentioned third evaluation score.

[0075] In this solution, by setting three different levels of evaluation scores, the degree of parameter abnormality can be managed in a refined manner, and different warning levels of minor abnormalities, moderate risks and serious failures can be distinguished, which helps to take more accurate and timely measures.

[0076] Specifically, when the relevant parameter (such as current, voltage or temperature) is less than or equal to the first preset threshold (i.e., the minimum value of the standard parameter of the distribution network), the evaluation score is determined to be the first evaluation score. The first preset threshold can be understood as the lower limit of the parameter. Being below this value may mean that the grid is operating below the optimal state or there are potential electrical problems, such as insufficient power or loose electrical connections of equipment. The first evaluation score is used to indicate that the parameter is at or below the lower limit of the normal range, which usually indicates that the grid is operating stably but may need to pay attention to its efficiency or performance.

[0077] When the relevant parameter is greater than the first preset threshold and less than the second preset threshold (i.e., the maximum value of the standard parameter of the distribution network), the evaluation score is determined to be the second evaluation score. The second preset threshold is the upper limit of the parameter, exceeding which may cause equipment overload or grid instability. The second evaluation score is used to quantify the degree of abnormality of the parameter within the normal range, i.e., the state where the parameter is close to the maximum value but has not yet reached the warning level. This indicates that the power grid is operating normally, but the parameters are approaching the safety limit and need to be closely monitored to prevent further deterioration.

[0078] When the relevant parameter is greater than or equal to the second preset threshold, the evaluation score is determined to be the third evaluation score. The third evaluation score is used to indicate that the parameter has exceeded the maximum value of normal operation, which is a clear early warning signal indicating that the power grid may face serious risks, such as equipment overheating, overload or short circuit, and immediate action is required.

[0079] Specifically, the above step E includes:

[0080] E1. Compare the current comparison benchmark data with the set current warning threshold: When I threshold >I avg >kI threshold In this case, I pred =1, where k is the early warning factor, I threshold The fault current value; when I avg ≥I threshold In this case, I pred =2; when I avg ≤kI threshold In this case, I pred =0;

[0081] Specifically, when I pred = 0, the current of the detection node of the distribution network is at a normal value; when I pred =1, the current of the detection node of the distribution network has potential abnormal problems; when I pred =2, the current at the detection node of the distribution network may be overloaded.

[0082] E2. Compare the voltage comparison benchmark data with the set voltage warning threshold: When U threshold >U avg >kU threshold In the case of pred =1, where k is the early warning factor, U threshold Fault voltage value; when U avg ≥U threshold In the case of pred =2; when U avg ≤kU threshold In the case of pred =0;

[0083] Specifically, when U pred =0, the voltage of the detection node of the distribution network is at a normal value; when U pred =1, the voltage of the detection node of the distribution network has potential abnormal problems; when U pred =2, the voltage at the detection node of the distribution network may be too high.

[0084] E3. Compare the temperature comparison benchmark data with the set temperature warning threshold: When T threshold >T avg >kT threshold In the case of T pred =1, where k is the early warning factor, T threshold Fault temperature value; when T avg ≥T threshold In the case of T pred =2; when T avg ≤kT threshold In the case of T pred =0;

[0085] Specifically, when T pred = 0, the temperature of the detection node of the distribution network is at a normal value; when T pred =1, the temperature of the detection node of the distribution network has potential abnormal problems; when T pred =2, the temperature of the detection node of the distribution network may be overheated.

[0086] E4. Data analysis output corresponds to the evaluation parameter B of the detection node = I pred +U pred +T pred .

[0087] In other embodiments, the calculation formula of the evaluation parameter B may add Q1, Q2, Q3 weight factors to different comparison benchmark data, that is, evaluation parameter B = Q1I pred +Q2U pred +Q3T pred To adapt to the actual usage requirements of detection nodes in different distribution networks and increase the practicality of distribution network early warning.

[0088] In a specific implementation process, a warning analysis is performed according to the first analysis result and the evaluation score to determine the warning level, which can be achieved by the following steps: when the first analysis result indicates that no fault has occurred and the evaluation score is less than the first score threshold, the warning level is determined to be a zero warning level; when the first analysis result indicates that no fault has occurred and the evaluation score is greater than or equal to the first score threshold, and the evaluation score is less than the second score threshold, the warning level is determined to be a first warning level, wherein the first score threshold is less than the second score threshold; when the first analysis result indicates that no fault has occurred and the evaluation score is greater than or equal to the second score threshold, the warning level is determined to be a second warning level, wherein the degree of the first warning level is lower than the degree of the second warning level; when the first analysis result indicates that a fault has occurred and the evaluation score is greater than or equal to the third score threshold, the warning level is determined to be a third warning level, wherein the first score threshold is greater than the third score threshold, and the degree of the second warning level is lower than the degree of the third warning level.

[0089] In this solution, by setting different score thresholds and warning levels, a multi-level assessment of the power grid status can be made, distinguishing between minor anomalies, moderate risks and serious faults, which helps to take appropriate response measures to avoid overreaction or underreaction. The multi-level warning mechanism enables the rational allocation of maintenance resources according to the level of warning, giving priority to high-risk issues and improving maintenance efficiency.

[0090] Specifically, when the first analysis result of the SVM algorithm indicates that there is no fault in the power grid and the evaluation score (based on the comparison of the real-time parameters with the preset threshold) is less than the first score threshold, the warning level is determined to be zero warning level, which means that the power grid is operating normally and no special attention or action is required.

[0091] If the first analysis result of the SVM algorithm also shows that no fault has occurred, but the evaluation score is greater than or equal to the first score threshold and less than the second score threshold, it is determined to be the first warning level. The first warning level usually means that the parameter begins to approach or slightly exceed the normal range, and monitoring and preliminary inspection are required, but the situation has not yet reached an emergency state. The setting of the first score threshold and the second score threshold should ensure that potential anomalies can be captured in time to facilitate early intervention.

[0092] If the first analysis result still shows that no fault has occurred, but the evaluation score is greater than or equal to the second score threshold, the warning level is determined to be the second warning level. This usually means that the parameters have significantly deviated from the normal range, there is a high risk, and immediate measures need to be taken for adjustment or maintenance. The second warning level is higher than the first warning level, indicating a more urgent situation.

[0093] When the first analysis result of the SVM algorithm indicates that the power grid has a fault and the evaluation score is greater than or equal to the third score threshold, the warning level will be determined to be the third warning level. This is the highest level of warning, which means that the power grid not only has a fault, but also the parameter abnormality has reached or exceeded the critical point, requiring an emergency response, such as disconnecting the power supply or immediately dispatching maintenance personnel for on-site processing.

[0094] Specifically, the warning levels include level one warning, level two warning and level three warning.

[0095] The warning processing measures for the first-level warning are to issue a warning message and recommend relevant personnel to conduct a close inspection to ensure the normal operation of the distribution network; the warning processing measures for the second-level warning are to automatically adjust the load of the detection node, limit power supply, start the inspection procedure, and dispatch maintenance personnel to conduct on-site evaluation; the warning processing measures for the third-level warning are to immediately cut off the power supply to the fault area where the detection node is located, notify the dispatch center, start the emergency processing plan, and conduct fault investigation and recovery.

[0096] Specifically, the above step F includes:

[0097] F1. When the evaluation parameter A is 1, the warning output is the warning level of "Level 3 warning", and the warning measures are simultaneously output: "Immediately cut off the power supply to the fault area where the detection node is located, notify the dispatch center, start the emergency response plan, and conduct fault troubleshooting and recovery";

[0098] F2. When the evaluation parameter A is 0, if the evaluation parameter B < 2, the warning will not be output;

[0099] F3. When the evaluation parameter A is 0, if the evaluation parameter B ≥ 2 and the evaluation parameter B < 4, the warning output is the warning level of "Level 1 warning", and the warning treatment measures of "issuing a warning message and suggesting that relevant personnel conduct a close inspection to ensure the normal operation of the distribution network" are output simultaneously;

[0100] F4. When the evaluation parameter A is 0, if the evaluation parameter B ≥ 4, the warning output is the warning level of "secondary warning", and the warning processing measures of "automatically adjusting the load of the detection node, limiting power supply, starting the inspection program, and dispatching maintenance personnel for on-site evaluation" are output simultaneously.

[0101] Specifically, since the evaluation parameter A is the result obtained based on the SVM fault warning model, when the evaluation factor B is too large, it proves that the detection node has failed or is about to fail, and the evaluation parameter A will output 1; therefore, the situation where the third-level warning is output by the result of the evaluation parameter B is not considered;

[0102] In actual early warning work, the weight of evaluation parameter A is higher than that of evaluation parameter B.

[0103] In some embodiments, obtaining relevant parameters of the distribution network can be specifically achieved through the following steps: obtaining multiple initial relevant parameters, wherein the above-mentioned initial relevant parameters are the initial relevant parameters of the above-mentioned distribution network obtained within the target detection period; calculating the average value of the multiple above-mentioned initial relevant parameters to obtain the above-mentioned relevant parameters.

[0104] In this scheme, by calculating the average value of the initial parameters, the impact of the randomness of a single measurement or sudden events on the parameter value can be reduced, making the obtained relevant parameters more stable and reliable, providing a solid data foundation for accurate judgment of early warning.

[0105] Specifically, within a set detection cycle, a series of initial parameter data, such as current, voltage, and temperature, are collected from different detection points of the distribution network or multiple time points of the same detection point. These data can be real-time or periodically sampled, but the key is to collect enough samples so that the average value calculated later can more accurately reflect the operating status of the distribution network.

[0106] After collecting multiple initial related parameters, the average value of these parameters is calculated through mathematical operations. The average value calculation method is generally to add all the initial parameters and divide them by the number of samples to obtain a comprehensive and stable related parameter value. This value is used as a representative of the distribution network operation parameters for subsequent analysis and early warning judgment.

[0107] Specifically, step B includes:

[0108] B1. Current comparison benchmark data I avg Calculation: Where N is the total number of samples of current parameter data within the detection period;

[0109] B2. Voltage comparison benchmark data U avg Calculation: Where N is the total number of samples of voltage parameter data within the detection period;

[0110] B3. Temperature comparison benchmark data T avg Calculation: Where N is the total number of samples of temperature parameter data within the detection period.

[0111] The above step C comprises:

[0112] C1, eigenvector X new Calculation of: X new =[I i , U i , T i , I avg , U avg , Tavg ], where I i is the real-time data of current, U i is the real-time voltage data, T i is the real-time temperature data, and the above 1≤i≤N.

[0113] Specifically, i is the real-time data timestamp within the detection period.

[0114] In summary, the solution of the present application improves the response speed of fault warning through real-time data collection and processing; through the preset SVM fault warning model, based on the SVM algorithm prediction, the accuracy of fault identification is significantly improved, and the integration of multi-dimensional data for all-round monitoring can provide early warning of potential risks and reduce the accident rate; at the same time, through the setting of warning levels and the implementation of corresponding measures, the fault handling process is optimized and the overall response efficiency is improved; the distribution network early warning system can help identify high-risk areas of energy consumption and loss, promote the implementation of energy-saving and emission reduction measures, contribute to the realization of sustainable development goals, and promote the use of green electricity and the improvement of energy efficiency; by setting reasonable warning thresholds and multi-level alarm mechanisms, the operation safety of the distribution network can be enhanced, the risk of accidents caused by equipment failures can be reduced, and the safety of staff and equipment can be protected.

[0115] The present application embodiment also provides a monitoring device for a distribution network. It should be noted that the monitoring device for the distribution network of the present application embodiment can be used to execute the monitoring method for the distribution network provided in the present application embodiment. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions thereof will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and contemplated.

[0116] The following is an introduction to the monitoring device for the distribution network provided in an embodiment of the present application.

[0117] Figure 4 1 is a structural block diagram of a monitoring device for a distribution network according to an embodiment of the present application. Figure 4 As shown, the device comprises:

[0118] An acquisition unit 10 is used to acquire relevant parameters of the power distribution network, wherein the relevant parameters include one or more of current, voltage and temperature;

[0119] A first analysis unit 20, configured to perform a first abnormality analysis on the above-mentioned related parameters according to an SVM algorithm to obtain a first analysis result;

[0120] A second analysis unit 30, configured to perform a second abnormality analysis on the above-mentioned related parameters according to the magnitude of the above-mentioned related parameters to obtain a second analysis result;

[0121] The early warning unit 40 is used to perform early warning analysis according to the first analysis result and the second analysis result, and determine the early warning level, wherein different early warning levels correspond to different processing strategies.

[0122] Through this embodiment, based on the SVM algorithm detection, the accuracy of fault identification can be improved. Then, by detecting through the data size, fault identification can be performed directly and simply. This solution does not require manual inspection and judgment. Different abnormality identification results can be obtained through two abnormality analysis methods, which improves the efficiency of abnormality detection. Different levels of warnings can also be made based on the abnormality identification results, thereby achieving effective warnings.

[0123] During the specific implementation process, the first analysis unit includes a construction module and a processing module. The construction module is used to construct a fault analysis model, wherein the above-mentioned fault analysis model is obtained by training through an SVM algorithm using multiple sets of training data, and each set of training data in the above-mentioned multiple sets of training data includes historical relevant parameters obtained within a historical time period and historical first analysis results corresponding to the above-mentioned historical relevant parameters; the processing module is used to input the above-mentioned relevant parameters into the above-mentioned fault analysis model to obtain the above-mentioned first analysis results corresponding to the above-mentioned relevant parameters.

[0124] In this solution, the SVM model can learn and adapt to changes in the operating status of the distribution network based on historical data. With the continuous training and optimization of the model, the intelligence and accuracy of the early warning will continue to improve, reducing the problems of false alarms and missed alarms. Automated fault prediction reduces the reliance on manual regular inspections, which can reduce operating costs while improving response speed and efficiency. The SVM model can comprehensively consider multiple parameters instead of relying on a single parameter, which enables a more comprehensive identification of potential problems in the distribution network and improves the comprehensiveness and reliability of fault identification. Using the SVM algorithm to build a fault analysis model can significantly improve the fault prediction capability of the early warning system, achieve smarter and more comprehensive real-time monitoring and early warning of the distribution network, and help take measures in advance to prevent faults, reduce grid operation risks, and improve the stability and safety of the power system.

[0125] In some embodiments, the second analysis unit includes a first acquisition module, a first determination module and a second determination module, the first acquisition module is used to acquire a preset threshold, wherein the preset threshold is a threshold of a standard parameter of the distribution network; the first determination module is used to determine that the distribution network has not failed when the relevant parameter is less than or equal to the preset threshold, and obtain the second analysis result; the second determination module is used to determine that the distribution network has failed when the relevant parameter is greater than the preset threshold, and obtain the second analysis result.

[0126] In this solution, by directly comparing real-time parameters with thresholds, anomalies can be immediately identified, which is critical to preventing possible fault escalation. Timely warnings help to take quick measures to avoid possible power outages, equipment damage, or safety accidents. Threshold comparison is a relatively simple and intuitive anomaly detection method that does not require complex calculations or model training. For real-time monitoring systems, this method can achieve rapid response while also reducing the demand for computing resources.

[0127] During the specific implementation process, the early warning unit includes a second acquisition module and a third determination module. The second acquisition module is used to obtain an evaluation score, wherein the evaluation score is obtained based on the size relationship between the relevant parameters corresponding to the second analysis result and the preset threshold; the third determination module is used to perform early warning analysis based on the first analysis result and the evaluation score to determine the early warning level.

[0128] In this solution, by combining the prediction of the machine learning model with the comparison of the threshold of the intuitive numerical value, the real-time status of the distribution network can be evaluated more intelligently and more accurate early warning judgments can be made. The setting of the early warning level enables different levels of response measures to be taken according to the potential severity of the fault, from monitoring notifications to emergency power outages, ensuring the efficiency and pertinence of the early warning response. The introduction of evaluation scores makes the early warning analysis more data-driven, relying not only on the prediction of the model, but also on the degree to which the actual parameters deviate from the normal range, providing decision makers with more comprehensive information and helping to make timely and effective responses.

[0129] In some embodiments, the second acquisition module includes a first determination submodule, a second determination submodule and a third determination submodule. The first determination submodule is used to determine that the evaluation score is a first evaluation score when the above-mentioned relevant parameters are less than or equal to a first preset threshold, wherein the first preset threshold is the minimum value of the standard parameter of the above-mentioned distribution network; the second determination submodule is used to determine that the evaluation score is a second evaluation score when the above-mentioned relevant parameters are greater than the above-mentioned first preset threshold and the above-mentioned relevant parameters are less than the second preset threshold, wherein the above-mentioned second preset threshold is the maximum value of the standard parameter of the above-mentioned distribution network, the above-mentioned first preset threshold is less than the above-mentioned second preset threshold, and the above-mentioned first evaluation score is less than the above-mentioned second evaluation score; the third determination submodule is used to determine that the evaluation score is a third evaluation score when the above-mentioned relevant parameters are greater than or equal to the above-mentioned second preset threshold, wherein the above-mentioned second evaluation score is less than the above-mentioned third evaluation score.

[0130] In this solution, by setting three different levels of evaluation scores, the degree of parameter abnormality can be managed in a refined manner, and different warning levels of minor abnormalities, moderate risks and serious failures can be distinguished, which helps to take more accurate and timely measures.

[0131] In the specific implementation process, the third determination module includes a fourth determination submodule, a fifth determination submodule, a sixth determination submodule and a seventh determination submodule. The fourth determination submodule is used to determine that the warning level is a zero warning level when the first analysis result indicates that no fault occurs and the evaluation score is less than the first score threshold; the fifth determination submodule is used to determine that the warning level is a first warning level when the first analysis result indicates that no fault occurs and the evaluation score is greater than or equal to the first score threshold and the evaluation score is less than the second score threshold, wherein the first score threshold is less than the second score threshold; the sixth determination submodule is used to determine that the warning level is a second warning level when the first analysis result indicates that no fault occurs and the evaluation score is greater than or equal to the second score threshold, wherein the degree of the first warning level is lower than the degree of the second warning level; the seventh determination submodule is used to determine that the warning level is a third warning level when the first analysis result indicates that a fault occurs and the evaluation score is greater than or equal to the third score threshold, wherein the first score threshold is greater than the third score threshold and the degree of the second warning level is lower than the degree of the third warning level.

[0132] In this solution, by setting different score thresholds and warning levels, a multi-level assessment of the power grid status can be made, distinguishing between minor anomalies, moderate risks and serious faults, which helps to take appropriate response measures to avoid overreaction or underreaction. The multi-level warning mechanism enables the rational allocation of maintenance resources according to the level of warning, giving priority to high-risk issues and improving maintenance efficiency.

[0133] In some embodiments, the acquisition unit includes a third acquisition module and a calculation module, the third acquisition module is used to acquire multiple initial related parameters, wherein the above-mentioned initial related parameters are the initial related parameters of the above-mentioned distribution network acquired within the target detection period; the calculation module is used to calculate the average value of the multiple above-mentioned initial related parameters to obtain the above-mentioned related parameters.

[0134] In this scheme, by calculating the average value of the initial parameters, the impact of the randomness of a single measurement or sudden events on the parameter value can be reduced, making the obtained relevant parameters more stable and reliable, providing a solid data foundation for accurate judgment of early warning.

[0135] The monitoring device for the distribution network includes a processor and a memory. The acquisition unit, the first analysis unit, the second analysis unit and the early warning unit are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0136] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the problem of low efficiency of abnormal detection of distribution network in the prior art, and thus failure to achieve effective early warning, can be solved by adjusting kernel parameters.

[0137] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0138] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, a device where the computer-readable storage medium is located is controlled to execute the distribution network monitoring method.

[0139] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the program executes the monitoring method of the distribution network when running.

[0140] An embodiment of the present invention provides a device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the steps of the monitoring method of the distribution network are implemented. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0141] A computer program product includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the distribution network monitoring method in each embodiment of the present application are implemented.

[0142] The present application provides a distribution network monitoring system, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any of the above-mentioned distribution network monitoring methods.

[0143] Specifically, the above system is as follows Figure 5 As shown, including:

[0144] The data sampling module is used to collect and transmit parameter data on each detection node on the distribution network within a set detection cycle when the distribution network is in operation; the above parameter data includes operating voltage, operating current and operating temperature;

[0145] The data processing module includes a data processing unit, which is used to process the parameter data transmitted by the above-mentioned data sampling module, and generate and transmit the comparison benchmark data of each detection node accordingly;

[0146] A feature generation unit, used to receive the comparison benchmark data transmitted by the data processing unit, integrate the comparison benchmark data and parameter data to generate a feature vector of each detection node and transmit the feature vector;

[0147] The data analysis module is used to receive the comparison basic data and feature vector transmitted by the above data processing module, input the above feature vector into the SVM fault warning model, and output the evaluation parameter A; compare and calculate the above comparison basic data with the set warning threshold, and output the evaluation parameter B;

[0148] The early warning output module is used to receive the evaluation parameters A and B output by the above-mentioned data analysis module, and output the corresponding early warning level and the early warning processing measures corresponding to the above-mentioned early warning level according to the set early warning standard.

[0149] Visualization module, the above-mentioned visualization interface module includes an intelligent terminal, and the user can view the real-time comparison benchmark data and feature vectors of the above-mentioned data processing module and the warning history records of the above-mentioned data analysis module through the above-mentioned intelligent terminal.

[0150] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0151] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0152] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0153] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0155] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0156] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0157] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0158] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0159] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for monitoring a distribution network, characterized in that: include: Acquire relevant parameters of the power distribution network, wherein the relevant parameters include one or more of current, voltage and temperature; Performing a first abnormality analysis on the relevant parameters according to the SVM algorithm to obtain a first analysis result; According to the magnitude of the relevant parameter, a second abnormality analysis is performed on the relevant parameter to obtain a second analysis result; A warning analysis is performed based on the first analysis result and the second analysis result to determine a warning level, wherein different warning levels correspond to different processing strategies.

2. The method according to claim 1, characterized in that Performing a first abnormality analysis on the relevant parameters according to the SVM algorithm to obtain a first analysis result, including: Constructing a fault analysis model, wherein the fault analysis model is obtained by training with a plurality of sets of training data through an SVM algorithm, wherein each set of training data in the plurality of sets of training data includes historical related parameters obtained within a historical time period and a historical first analysis result corresponding to the historical related parameters; The relevant parameters are input into the fault analysis model to obtain the first analysis results corresponding to the relevant parameters.

3. The method according to claim 1, characterized in that According to the magnitude of the relevant parameter, a second abnormality analysis is performed on the relevant parameter to obtain a second analysis result, including: Obtaining a preset threshold, wherein the preset threshold is a threshold of a standard parameter of the power distribution network; When the relevant parameter is less than or equal to the preset threshold, determining that no fault occurs in the distribution network, and obtaining the second analysis result; When the relevant parameter is greater than the preset threshold, it is determined that a fault occurs in the distribution network, and the second analysis result is obtained.

4. The method according to claim 3, characterized in that Performing early warning analysis according to the first analysis result and the second analysis result to determine the early warning level includes: Obtaining an evaluation score, wherein the evaluation score is obtained according to a magnitude relationship between the relevant parameter corresponding to the second analysis result and the preset threshold; A warning analysis is performed based on the first analysis result and the evaluation score to determine the warning level.

5. The method according to claim 4, characterized in that Get evaluation scores, including: In the case where the relevant parameter is less than or equal to a first preset threshold, determining the evaluation score to be a first evaluation score, wherein the first preset threshold is a minimum value of a standard parameter of the power distribution network; In the case where the relevant parameter is greater than the first preset threshold and the relevant parameter is less than the second preset threshold, determining the evaluation score to be the second evaluation score, wherein the second preset threshold is the maximum value of the standard parameter of the power distribution network, the first preset threshold is less than the second preset threshold, and the first evaluation score is less than the second evaluation score; In a case where the relevant parameter is greater than or equal to the second preset threshold, the evaluation score is determined to be a third evaluation score, wherein the second evaluation score is less than the third evaluation score.

6. The method according to claim 4, characterized in that Performing a warning analysis according to the first analysis result and the evaluation score to determine the warning level includes: When the first analysis result indicates that no fault has occurred and the evaluation score is less than a first score threshold, determining the warning level to be a zero warning level; In a case where the first analysis result indicates that no fault has occurred, and the evaluation score is greater than or equal to the first score threshold, and the evaluation score is less than a second score threshold, determining the warning level to be a first warning level, wherein the first score threshold is less than the second score threshold; In the case where the first analysis result indicates that no fault has occurred and the evaluation score is greater than or equal to the second score threshold, determining the warning level to be a second warning level, wherein the degree of the first warning level is lower than the degree of the second warning level; When the first analysis result indicates that a fault has occurred and the evaluation score is greater than or equal to a third score threshold, the warning level is determined to be the third warning level, wherein the first score threshold is greater than the third score threshold and the degree of the second warning level is lower than the degree of the third warning level.

7. The method according to any one of claims 1 to 6, characterized in that Obtain relevant parameters of the distribution network, including: Acquire a plurality of initial relevant parameters, wherein the initial relevant parameters are initial relevant parameters of the distribution network acquired within a target detection period; The average value of the multiple initial correlation parameters is calculated to obtain the correlation parameter.

8. A monitoring device for a distribution network, characterized in that: include: An acquisition unit, used to acquire relevant parameters of the power distribution network, wherein the relevant parameters include one or more of current, voltage and temperature; A first analysis unit, configured to perform a first abnormality analysis on the relevant parameters according to a SVM algorithm to obtain a first analysis result; A second analysis unit, configured to perform a second abnormality analysis on the relevant parameters according to the magnitude of the relevant parameters to obtain a second analysis result; The early warning unit is used to perform early warning analysis according to the first analysis result and the second analysis result to determine the early warning level, wherein different early warning levels correspond to different processing strategies.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for monitoring a power distribution network as claimed in any one of claims 1 to 7 are implemented.

10. A distribution network monitoring system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the monitoring method of the distribution network described in any one of claims 1 to 7.

Images