Risk early warning method and platform for power distribution network protection area monitoring

Abstract

The invention provides a risk early warning method and platform for power distribution network protection area monitoring, and relates to the technical field of power systems, and the method comprises the steps: traversing the safety demand information of a power distribution network protection area, and carrying out the operation risk recognition; monitoring the protection area of the power distribution network in real time; constructing a risk prediction model, and obtaining a risk prediction data set; introducing a risk rule to carry out risk assessment; and triggering an early warning mechanism according to a risk assessment result, generating early warning feedback information, and performing intelligent early warning on risk monitoring of the power distribution network protection area. The technical problem that potential risks cannot be found in time due to the fact that an existing power distribution network protection area monitoring method lacks real-time performance and comprehensiveness in the prior art can be solved, through real-time monitoring and data flow processing, risk rules are introduced, risk assessment is carried out, intelligent early warning is triggered, potential risk factors are comprehensively recognized, and the safety of the power distribution network protection area is improved. And the risk identification accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a risk warning method and platform for monitoring protection areas of distribution networks. Background Art

[0002] With the continuous development of power systems, the safe operation of distribution networks has become increasingly important. In order to ensure the stability and reliability of distribution networks, monitoring and risk warning of distribution network protection areas have become key links. Existing distribution network protection area monitoring methods mainly rely on manual inspections and fixed sensors to collect data. Traditional manual inspection methods cannot achieve real-time monitoring, and it is difficult to detect and respond to potential risks in a timely manner. Although fixed sensors can collect data, data processing and analysis often have delays, which affects the timeliness and comprehensiveness of monitoring.

[0003] In summary, the prior art has a technical problem that potential risks cannot be discovered in a timely manner due to the lack of real-time and comprehensiveness of the existing monitoring method for the protection area of ​​the distribution network. Summary of the invention

[0004] The purpose of this application is to provide a risk warning method and platform for monitoring the protection area of ​​a distribution network, so as to solve the technical problem in the prior art that the monitoring method of the existing distribution network protection area lacks real-time and comprehensiveness, resulting in the inability to timely detect potential risks.

[0005] In view of the above problems, the present application provides a risk warning method and platform for monitoring the protection area of ​​a distribution network.

[0006] In the first aspect, the present application provides a risk warning method for monitoring a distribution network protection area, and the risk warning method for monitoring a distribution network protection area is implemented by a risk warning platform for monitoring a distribution network protection area, wherein the risk warning method for monitoring a distribution network protection area includes: traversing the security demand information of the distribution network protection area to identify operational risks and determine multiple risk factors; performing real-time monitoring of the distribution network protection area according to the multiple risk factors to obtain a risk factor status data stream; constructing a risk prediction model for the distribution network protection area, synchronizing the risk factor status data stream to the risk prediction model, and obtaining a risk prediction data set; introducing risk rules, performing risk assessment in combination with the risk prediction data set, and generating a risk assessment result; triggering an early warning mechanism according to the risk assessment result, generating early warning feedback information through the early warning mechanism, and performing intelligent early warning on risk monitoring of the distribution network protection area according to the early warning feedback information.

[0007] In the second aspect, the present application also provides a risk warning platform for monitoring the protection area of ​​a distribution network, which is used to execute the risk warning method for monitoring the protection area of ​​a distribution network as described in the first aspect, wherein the risk warning platform for monitoring the protection area of ​​a distribution network includes: a risk identification module, the risk identification module is used to traverse the security demand information of the protection area of ​​the distribution network to identify operational risks and determine multiple risk factors; a real-time monitoring module, the real-time monitoring module is used to perform real-time monitoring of the protection area of ​​the distribution network according to the multiple risk factors, and obtain a risk factor status data stream; a risk prediction model construction module, the risk prediction model construction module is used to construct a risk prediction model for the protection area of ​​the distribution network, synchronize the risk factor status data stream to the risk prediction model, and obtain a risk prediction data set; a risk assessment module, the risk assessment module is used to introduce risk rules, perform risk assessment in combination with the risk prediction data set, and generate a risk assessment result; an early warning mechanism triggering module, the early warning mechanism triggering module is used to trigger the early warning mechanism according to the risk assessment result, generate early warning feedback information through the early warning mechanism, and perform intelligent early warning on the risk monitoring of the protection area of ​​the distribution network according to the early warning feedback information.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By traversing the security demand information of the distribution network protection area, the operation risk is identified and multiple risk factors are determined; the distribution network protection area is monitored in real time according to the multiple risk factors to obtain the risk factor status data stream; a risk prediction model for the distribution network protection area is constructed, and the risk factor status data stream is synchronized to the risk prediction model to obtain a risk prediction data set; risk rules are introduced, and risk assessment is performed in combination with the risk prediction data set to generate risk assessment results; an early warning mechanism is triggered according to the risk assessment results, and early warning feedback information is generated through the early warning mechanism, and intelligent early warning is performed on the risk monitoring of the distribution network protection area according to the early warning feedback information. In other words, through real-time monitoring and data stream processing, risk rules are introduced, risk assessment is performed and intelligent early warning is triggered, potential risk factors are comprehensively identified, and the accuracy of risk identification is improved.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application 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 in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 This is a flow chart of a risk warning method for monitoring a distribution network protection area used in this application; Figure 2 This is a schematic diagram of the structure of the risk warning platform used for distribution network protection area monitoring in this application.

[0012] Explanation of the accompanying drawings: risk identification module 11, real-time monitoring module 12, risk prediction model building module 13, risk assessment module 14, early warning mechanism triggering module 15. DETAILED DESCRIPTION

[0013] This application solves the technical problem in the prior art that the existing monitoring methods for distribution network protection areas lack real-time and comprehensiveness, resulting in the inability to timely detect potential risks, by providing a risk warning method and platform for distribution network protection area monitoring. Through real-time monitoring and data stream processing, risk rules are introduced, risk assessment is performed, and intelligent warnings are triggered, potential risk factors are fully identified, and the accuracy of risk identification is improved.

[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0015] For example, please refer to the attached Figure 1 The present application provides a risk warning method for monitoring a distribution network protection area, wherein the risk warning method for monitoring a distribution network protection area is executed by a risk warning platform for monitoring a distribution network protection area, and the risk warning method for monitoring a distribution network protection area specifically includes the following steps: Step 1: Traverse the security demand information of the distribution network protection area to identify operational risks and determine multiple risk factors.

[0016] Specifically, the distribution network protection area refers to the area in the distribution network that needs special monitoring and protection, such as substations, distribution stations, lines, etc. A comprehensive safety demand analysis is conducted on the distribution network protection area, including detailed review of equipment information (such as the type, capacity, operating status, maintenance history of equipment such as transformers, cables, switches, and protective devices), environmental information (such as geographical location, climate conditions, surrounding environment), and grid structure (such as the topology of the grid, line length, load distribution, and spare capacity) to identify various risks that may be encountered during normal operation and determine the specific factors of these risks. Use mobile ranging technology, which refers to measuring the distance between distribution equipment and mobile objects (such as construction personnel and mobile vehicles) in real time to determine risk factors, including distance risk, dynamic risk, environmental risk, and human risk. Among them, distance risk refers to real-time monitoring of the distance between distribution equipment and mobile objects, analyzing real-time data, identifying whether the distance between the mobile object and the charged object is close to the safety threshold, ensuring that it remains outside the safe distance, and if the distance is less than the safe distance, it is identified as a distance risk. Dynamic risk considers the dynamic movement trajectory of the mobile non-charged object and predicts the risk that it may come into contact with the distribution equipment. For example, construction workers or vehicles may accidentally approach live equipment during operation. Environmental risks require analyzing the impact of environmental factors (such as weather and terrain) on mobile ranging to determine whether the risk is increased. Human risks are to identify the risks that may be caused by operational errors or violations of construction workers or other mobile non-live objects. The collected data is transmitted to the data processing center through a wireless network or a wired network. In the data processing center, the ranging data can be processed and analyzed through filtering, denoising and calibration to identify the position change trend of the moving object, monitor the position change of the moving object, identify the dynamic risk factors approaching the distribution equipment, and monitor the position change of the moving object in real time according to the preset safety distance threshold. Once the moving object approaches the distribution equipment to within the preset safety distance, the system should immediately trigger the early warning mechanism and send out an alarm signal, which can timely identify potential dynamic risk factors, such as accidental collisions, illegal intrusions, etc., and record the time, location and type of the risk event. Risk factors include various specific factors that may lead to distribution network operation risks, such as equipment failure risks (such as equipment aging, overload, operating errors), external infringement risks (such as weather conditions, natural disasters, man-made damage), system stability risks (such as voltage fluctuations, frequency fluctuations, short circuit failures), operating errors, improper maintenance, etc. For example, construction workers accidentally approach high-voltage lines when operating cranes, resulting in insufficient safety distance; bad weather or complex terrain affects the movement trajectory and ranging accuracy of moving objects, causing environmental interference risks; the speed of moving objects is too fast, which may also make it impossible to avoid live objects in time, increasing the risk of accidents. By traversing the safety demand information, the risk factors that affect the operation of the distribution network are fully identified.

[0017] Step 2: Perform real-time monitoring of the distribution network protection area based on the multiple risk factors to obtain a risk factor status data stream.

[0018] Specifically, according to the identified multiple risk factors, various appropriate sensors and monitoring devices are selected and deployed. For example, temperature sensors, current sensors, voltage sensors, mobile distance measuring devices, etc. are installed on key equipment (such as transformers, switches, and lines). Continuous real-time monitoring is carried out on the protection area of ​​the distribution network to collect data on the status of risk factors, such as equipment spacing, temperature, wind speed, inclination, etc. A continuous data stream is formed to obtain the risk factor status data stream, ensuring that all necessary information is included, such as the distance data between devices, the moving speed and direction of the equipment, and other relevant environmental parameters and equipment performance indicators. Monitoring is carried out according to risk factors to ensure that the monitoring activities are targeted, that is, only those risk factors that have been identified as posing a threat to the safe operation of the distribution network are monitored. Through real-time monitoring, equipment overheating, line overload, or abnormal ambient temperature can be immediately discovered, and measures can be taken in time to prevent accidents.

[0019] Step three: construct a risk prediction model for the distribution network protection area, synchronize the risk factor status data stream to the risk prediction model, and obtain a risk prediction data set.

[0020] Specifically, identify the specific risks that the model needs to predict, such as equipment failure, grid overload, voltage fluctuation, equipment displacement, dynamic load, etc. Select appropriate models based on the prediction target, such as time series analysis, regression analysis, machine learning algorithms (random forest, support vector machine, neural network, etc.). Preprocess historical data to remove invalid, erroneous or duplicate data. Select features that are highly relevant to the risk based on the prediction target, such as current, voltage, temperature, humidity, historical failure rate, etc. Use feature selection techniques (such as correlation analysis, principal component analysis) to reduce feature dimensions and improve model efficiency. Use processed historical data to train the model. During the training process, optimize the model's predictive ability by adjusting model parameters. Use a validation set to evaluate the performance of the model, and use techniques such as cross-validation to ensure the generalization ability of the model.

[0021] Divide the data into different time periods according to the time sequence, such as hours, days, weeks, months, etc. Analyze the periodic patterns in the data, such as daily load fluctuations, seasonal changes, etc. Determine the prediction time window, such as predicting the risk in the next 1 hour, 24 hours or longer. Use the preprocessed real-time data as the input of the model, including time series data, in which each time point has a corresponding risk factor status. Perform prediction calculations based on the input real-time data stream and output the prediction results, including the probability or level of a specific risk occurring in a certain period of time in the future. Organize the prediction results of the model into a risk prediction data set, including the prediction time point, risk type, prediction value, etc. By constructing a risk prediction model that takes time into account, risk events that may occur in a specific period of time in the future can be more accurately predicted based on real-time data streams.

[0022] Step 4: Introduce risk rules, perform risk assessment in combination with the risk prediction data set, and generate risk assessment results.

[0023] Specifically, according to the risk assessment dimensions (risk frequency, risk probability, risk impact, and risk controllability), the judgment conditions for different risk levels are clarified. The risk rules are concretized into operational indicators and thresholds. For example, a risk probability of more than 50% and a risk impact score greater than 8 points are considered high risk. The risk prediction data set is risk assessed based on the risk assessment criteria combined with the risk probability and risk frequency. The severity and urgency of each risk event are judged according to the risk rules, and the risk assessment results are generated accordingly. By combining the risk prediction data set with the risk rules, a series of risk assessment results can be generated. Each result will have a corresponding risk level, such as low risk, medium risk, or high risk. For example, according to the risk rules, if a risk event has a frequency of 2 times per month (medium frequency), a probability of 30% (medium probability), an impact range of 20 households (medium impact), and a controllability of 6 hours (medium controllability), then the risk event may be classified as medium risk. By combining the risk assessment criteria, risk probability, and frequency dimensions, the generated risk assessment results help to take preventive measures in advance and reduce the probability of accidents.

[0024] Step 5: triggering an early warning mechanism according to the risk assessment result, generating early warning feedback information through the early warning mechanism, and performing intelligent early warning on risk monitoring of the distribution network protection area according to the early warning feedback information.

[0025] Specifically, trigger conditions are formulated based on multiple risk factors. If the risk assessment results meet the trigger conditions, the early warning mechanism is triggered. If the early warning mechanism is in the running state, the emergency response layer is started to generate the corresponding strategy, and the corresponding strategy is synchronized to the data feedback layer for extraction to generate early warning feedback information. The risk prediction model is optimized according to the early warning feedback information, and the risk factor status data stream is input into the optimized model to obtain the risk prediction optimization data set. The risk prediction optimization data set and the risk prediction data set are compared to determine whether the risk levels are consistent. If not, it means that the model optimization has achieved results. According to the optimized model prediction results, the conditions for triggering the early warning are updated to ensure that the early warning mechanism is more accurate and effective. Risk assessment is performed on the risk prediction optimization data set to obtain the optimized risk assessment results. Similarly, it is determined whether the optimized risk assessment results meet the trigger conditions. If they do, the early warning mechanism is triggered to obtain early warning feedback information.

[0026] According to the early warning feedback information, the distribution network protection area is continuously monitored, and the collected data is recorded in the monitoring data log. According to the preset self-check cycle, the monitoring data log is regularly traversed. The monitoring data log is analyzed, the changing trend of risk factors is tracked, and a risk change trend chart is constructed to intuitively display the change of risk over time. In the risk change trend chart, the extreme points of risk, that is, the highest and lowest values ​​of risk, are identified, and the risk peak identification results are extracted. Combined with the early warning feedback information and the risk peak identification results, the risk is deeply analyzed, and intelligent early warning is carried out according to the analysis results, and relevant personnel or systems are notified in time to take corresponding preventive measures. By triggering the early warning mechanism according to the risk assessment results, it is ensured that the early warning system responds in time in high-risk situations. The generated early warning feedback information helps relevant personnel or systems understand potential risks and take corresponding preventive measures.

[0027] Further, step 4 of this application includes: Based on the security demand information of the distribution network protection area, the risk assessment dimensions are determined, and the risk assessment dimensions include risk frequency dimension, risk probability dimension, risk impact dimension, and risk controllability dimension; risk levels are formulated according to the risk impact dimension and the risk controllability dimension, and risk assessment standards are divided according to the risk levels; the risk rules are formulated based on the risk assessment standards in combination with the risk probability dimension and the risk frequency dimension.

[0028] Specifically, according to the security demand information of the distribution network protection area, the specific dimensions used to assess the risk are determined, including risk frequency, risk probability, risk impact and risk controllability, which together constitute a comprehensive risk assessment framework. Among them, the risk frequency dimension focuses on the frequency or number of risk events within a certain period of time, the risk probability dimension focuses on the possibility or probability of risk events, the risk impact dimension focuses on the degree of impact caused by risk events when they occur, and the risk controllability dimension focuses on the controllability of risk events. According to the risk impact dimension and the risk controllability dimension, the risk level is formulated, such as low risk, medium risk and high risk, considering the degree of impact on the distribution network protection area when the risk occurs and the controllability of the risk. A series of standards or thresholds are defined for each risk level so that risk events can be classified into corresponding levels during the assessment process. For example, the degree of impact is divided into levels such as slight, medium and severe. The control difficulty is divided into levels such as easy, medium and difficult. Risk levels are formulated by combining the risk impact dimension and the risk controllability dimension. Risks with high impact and difficult to control can be classified as "high risk", and risks with low impact and easy to control can be classified as "low risk".

[0029] According to the risk assessment standards that have been divided, considering the frequency and probability of risk, the assessment rules for different levels of risk are determined for the actual risk assessment process. For example, risks that occur frequently and have a high probability require stricter monitoring and early warning. Risk rules are a set of logic or algorithms that are used to evaluate a series of conditions or thresholds for the severity and urgency of risk events, including: triggering an early warning when the frequency and probability of a risk exceed a specific threshold; implementing more frequent monitoring and reporting requirements for risks with large impacts and difficult to control; and taking regular monitoring measures for risks with low impacts and easy to control. Through clear risk assessment dimensions and standards, the risk assessment process is made more standardized and systematic, and the risks in the protection area of ​​the distribution network are accurately assessed and managed.

[0030] Furthermore, step five of this application includes: A weighted calculation is performed based on the multiple risk factors to generate a comprehensive risk index; when the comprehensive risk index is greater than or equal to a preset risk threshold, a trigger condition is formulated; it is determined whether the risk assessment result meets the trigger condition; if the risk assessment result meets the trigger condition, the early warning mechanism is triggered and the state of the early warning mechanism is set to an operating state; if the risk assessment result does not meet the trigger condition, the state of the early warning mechanism is set to a waiting state.

[0031] Specifically, multiple risk factors are weighted and calculated, and a weight is assigned to each factor according to the importance and impact of different risk factors, and then the calculation is performed. By adding the weighted values ​​of each risk factor, a comprehensive risk index can be generated. This index represents the current overall risk level of the distribution network protection area, and can be used to compare the comprehensive risk levels at different time points or in different areas. According to the security requirements and risk management strategies of the distribution network protection area, a risk threshold is pre-set, which represents the minimum comprehensive risk index for triggering the early warning mechanism, and represents the critical point at which the risk early warning system needs to be activated. When the comprehensive risk index is greater than or equal to the preset risk threshold, a trigger condition needs to be formulated. The trigger condition refers to a series of measures or actions that are initiated when the comprehensive risk index reaches or exceeds the preset risk threshold, such as activating the early warning system, automatically adjusting the power load, notifying the operation and maintenance personnel, etc.

[0032] The risk assessment results need to be compared with the previously set trigger conditions. If the risk assessment results meet the trigger conditions, the early warning mechanism needs to be triggered, including issuing an alarm, starting an emergency plan, and automatically adjusting the operating parameters of the power system. The early warning mechanism will be activated and enter the operating state. When the risk assessment results do not meet the trigger conditions, the early warning mechanism state is set to the standby state, and the monitoring is maintained but the early warning is not triggered. In a specific example, assuming that the calculated comprehensive risk index is 6 and the preset risk threshold is 5, because 6 is greater than 5, a trigger condition is formulated: when the risk level in the risk assessment result is "high risk", the early warning is triggered. Assuming that the risk assessment result is "medium risk", because the risk assessment result does not meet the trigger condition of "high risk", the early warning mechanism remains in the standby state. By weighted calculation of the comprehensive risk index, the overall risk level of the distribution network protection area is comprehensively evaluated. When the comprehensive risk index reaches or exceeds the preset risk threshold, the early warning mechanism is triggered, which helps to respond to high-risk situations in a timely manner and ensure the safe operation of the distribution network protection area.

[0033] Furthermore, the present application also includes the following steps: Construct the early warning mechanism, which includes a data input layer, a data processing layer, an emergency response layer, a data feedback layer, and a data output layer; synchronize the risk assessment result to the data processing layer through the data input layer for analysis, and when the early warning mechanism state is the running state, start the emergency response layer, and generate a response strategy based on the emergency response layer and the risk assessment result; synchronize the response strategy to the data feedback layer through the emergency response layer for extraction, determine the early warning feedback information, and synchronize the early warning feedback information to the data output layer; when the early warning mechanism state is the waiting state, start the data feedback layer, generate feedback information, and synchronize the feedback information to the data output layer; the output end of the data processing layer is communicatively connected to the input end of the emergency response layer and the input end of the data feedback layer, the output end of the emergency response layer is communicatively connected to the input end of the data feedback layer, and the output end of the data feedback layer is communicatively connected to the output end of the data output layer.

[0034] Specifically, a multi-level early warning mechanism is constructed, including data input layer, data processing layer, emergency response layer, data feedback layer and data output layer. These layers work together to ensure the effective operation and response of the early warning system. Among them, the data input layer is responsible for receiving the incoming data and synchronizing the input data to the data processing layer; the data processing layer is responsible for preprocessing the input data, backwashing the preprocessed data, and outputting the results; the emergency response layer is the core of the early warning mechanism, responsible for risk assessment and strategy generation based on the results output by the data processing layer, determining whether to trigger the early warning and what response measures to take; the data feedback layer is responsible for collecting and processing feedback information from the emergency response layer, including early warning results, the effects of response measures, etc., for optimizing the early warning mechanism and response strategy; the data output layer is responsible for outputting the feedback results to relevant personnel.

[0035] The data input layer is responsible for receiving data from risk assessment results, including risk level, risk factors, comprehensive risk index, risk trend, etc., and transmitting it to the data processing layer for analysis. The data processing layer analyzes the input data, including data cleaning, feature extraction, model prediction, etc. Determine whether the risk reaches the warning threshold and trigger the warning mechanism. When the warning mechanism is in the operating state, it means that the risk level has reached or exceeded the preset threshold. In this case, the emergency response layer is activated and ready to take action. The emergency response layer formulates specific response strategies based on the current risk assessment results, including adjusting power loads, starting backup equipment, notifying operation and maintenance personnel, etc. The generation of response strategies needs to take into account the specific circumstances, severity and possible consequences of the risks to ensure that the measures taken can effectively reduce or eliminate the risks, including specific response measures, alarm notifications, automated operation instructions, etc.

[0036] The response strategy is synchronized to the data feedback layer for extraction and analysis. The data feedback layer is responsible for receiving and processing strategy information, including data format conversion, storage and extraction, to ensure that the response strategy can be effectively extracted and utilized. The data feedback layer extracts key information from the synchronized response strategy and generates early warning feedback information, such as early warning type, response measures, early warning status, etc. The data output layer is responsible for encrypting, transmitting and displaying the early warning feedback information, and synchronizing it to the external system or interface, including generating early warning reports, sending alarm notifications, triggering automated operation instructions, etc., so that relevant personnel can receive and respond in time, and ensure the accuracy and security of early warning feedback information. When the early warning mechanism is in the waiting state, the data feedback layer is started to generate feedback information about the current risk status, indicating that although the risk exists, it has not yet reached the level of activating the early warning mechanism. At this time, the data feedback layer starts to work, collecting and processing feedback information related to the early warning mechanism, including the operation status of the early warning mechanism, the status of the data processing layer, and the readiness of the emergency response layer. Synchronize this feedback information to the data output layer, encrypt, transmit and display the data, so as to provide the current risk status to relevant personnel or systems, including generating operation reports of early warning mechanisms, sending system status notifications, displaying system readiness, etc.

[0037] The output end of the data processing layer is connected to the input end of the emergency response layer and the input end of the data feedback layer to ensure the smooth flow of data. After the data processing layer completes the processing and analysis of the input data, its output end will generate a series of processed data and analysis results. When the early warning mechanism is in operation, the emergency response layer is started to receive the output information from the data processing layer. The input end is responsible for receiving the data and analysis results from the data processing layer, and performing corresponding processing and application to generate a response strategy. The output end is responsible for synchronizing the response strategy to the data feedback layer. When the early warning mechanism is in the waiting state, a stable communication connection is established between the output end of the data processing layer and the input end of the data feedback layer to ensure that feedback information can be directly generated.

[0038] The output end of the emergency response layer is connected to the input end of the data feedback layer. The data feedback layer can receive and process the response strategy of the emergency response layer to generate feedback information and realize feedback and adjustment of the response strategy. The output end of the data feedback layer is connected to the output end of the data output layer to ensure that the feedback information is smoothly transmitted to the data output layer, so that relevant personnel or systems can understand the operation status and performance of the early warning mechanism. By building an efficient and responsive early warning mechanism, emergency response can be initiated in a timely manner according to the risk assessment results, and adjustments and feedback can be made when necessary.

[0039] Furthermore, the present application also includes the following steps: The risk prediction model is optimized through the early warning feedback information to obtain a risk prediction optimization model; a risk prediction optimization data set is obtained by synchronizing the risk factor status data stream to the risk prediction optimization model; the risk prediction optimization data set is compared with the risk prediction data set to determine whether the risk level of the risk prediction optimization data set is consistent with the risk level of the risk prediction data set; if the risk level of the risk prediction optimization data set is inconsistent with the risk level of the risk prediction data set, the trigger condition is updated.

[0040] Specifically, the key data related to model optimization is screened out from the early warning feedback information to form a feedback incremental information set. The screened data set is standardized to eliminate outliers and deviations in the data to form a standardized data set. The risk prediction model is evaluated using the standardized data set to measure its performance on the current data. According to the evaluation results, the model performs batch incremental learning to learn the patterns and features in the new data, and then optimizes the model according to the learning results. The optimized model is verified to confirm whether its performance meets the requirements. Finally, a risk prediction optimization model is obtained, which can accurately predict risks. The risk factor status data stream is synchronized to the risk prediction optimization model to obtain a risk prediction optimization data set, including prediction time point, risk type, prediction value, etc. The risk levels of the risk prediction data set and the risk prediction optimization data set are compared to determine whether the two are consistent. If the risk level of the risk prediction optimization data set is inconsistent with the risk level of the risk prediction data set, it means that the model optimization has achieved results. Then, according to the prediction results of the optimized model, the conditions for triggering the warning are updated to improve the accuracy of the warning and ensure that the warning system can issue warnings based on the latest risk assessment results. Through the early warning feedback information, the risk prediction model is continuously optimized to improve the accuracy of the prediction.

[0041] Furthermore, the present application also includes the following steps: Based on the early warning feedback information, data screening is performed to obtain a feedback incremental information set; the feedback incremental information set is standardized to determine a feedback incremental standard data set; the risk prediction model is evaluated using the feedback incremental standard data set to generate a model evaluation result; the risk prediction model is batch incrementally learned according to the model evaluation result, and the risk prediction model is optimized according to the incremental learning result to obtain a risk prediction initial optimization model; the risk prediction initial optimization model is verified, and when the verification passes, the risk prediction optimization model is obtained.

[0042] Specifically, key data related to risk prediction are screened out from the early warning feedback information to form a feedback incremental information set. Data screening refers to the process of selecting and retaining useful data from a large amount of data based on specific standards or conditions. The purpose of screening is to extract important information related to the optimization of the risk prediction model and ignore insignificant details. The feedback incremental information set is a data set obtained by screening the early warning feedback information, which contains valuable information for the optimization of the risk prediction model. The feedback incremental information set is standardized to create a standardized data set. The purpose of standardization is to eliminate outliers and deviations in the data, make the data set comparable and consistent, and normalize or standardize the data, such as converting the data into a normal distribution with a mean of 0 and a variance of 1. Standardization involves converting the data into a standard form with the same scale or range, which helps to improve the comparability of the data and the accuracy of the analysis.

[0043] The performance of the risk prediction model is evaluated using a standardized feedback incremental standard data set, the model's prediction results are compared with the actual results, and the model's accuracy, precision, recall and other indicators are calculated. Through the evaluation process, the model evaluation results are generated, which reflect the performance of the model in actual applications, including the advantages and disadvantages of the model. The model evaluation results are used to guide the batch incremental learning process of the risk prediction model. Incremental learning is a machine learning technique that allows the model to learn and improve while continuously acquiring new data. The risk prediction model is optimized according to the results of incremental learning, including adjusting the parameters of the model, improving the algorithm, introducing new features, etc. Through the optimization process, a preliminary optimized risk prediction model is obtained, and its performance is improved compared with the original model. The initial optimized risk prediction model is verified to ensure that the optimized model can accurately predict risks. The verification process includes testing the model with new or existing data sets to check its key indicators such as prediction accuracy, response speed and robustness. If the verification passes, that is, the model performance meets the predetermined standards, the model is considered to be a risk prediction optimization model. By screening and standardizing feedback incremental information and batch incremental learning of the model, the prediction accuracy of the model is improved and the model is continuously optimized to ensure that the risk prediction model constantly adapts to new data and environmental changes, thereby improving the accuracy and reliability of the prediction.

[0044] Furthermore, the present application also includes the following steps: Based on the early warning feedback information, the distribution network protection area is continuously monitored to generate a monitoring data record log; the monitoring data record log is traversed in combination with the self-inspection cycle to track risks and construct a risk change trend chart; based on the risk change trend chart, the distribution network protection area is marked with extreme values, and the risk peak identification result is extracted according to the extreme value identification result; according to the risk peak identification result combined with the early warning feedback information, analysis is performed, and intelligent early warning is performed according to the analysis result.

[0045] Specifically, the distribution network protection area is continuously monitored according to the early warning feedback information, and the data during the monitoring process is recorded to form a log file that records the operation status of the power grid, risk level, early warning events and other information, namely the monitoring data record log. According to the preset self-check cycle, the monitoring data record log is regularly traversed. The monitoring data record log is analyzed to track the changing trend of risk factors. Using chart tools such as line charts or bar charts, a risk change trend chart is constructed to intuitively display the change of risk over time. The extreme value points of risk, that is, the highest and lowest points of risk, are identified in the risk change trend chart. According to the results of extreme value identification, the risk peak identification results are extracted, that is, the time period or area that needs special attention and enhanced monitoring. The extracted risk peak identification results are combined with the early warning feedback information for comprehensive analysis, including analysis of the duration of the risk peak, the frequency of occurrence, the accuracy of the early warning, etc. According to the results of the comprehensive analysis, intelligent early warning is carried out, including adjusting the early warning threshold, optimizing the early warning strategy, improving the early warning method, etc., to improve the accuracy and timeliness of the early warning. Through continuous monitoring and risk tracking, an efficient risk management and early warning system is formed, which can monitor the distribution network protection area in real time, track risk changes, and promptly detect and warn of potential risks.

[0046] In summary, the risk warning method for monitoring the protection area of ​​the distribution network provided by this application has the following technical effects: By traversing the security demand information of the distribution network protection area, the operation risk is identified and multiple risk factors are determined; the distribution network protection area is monitored in real time according to the multiple risk factors to obtain the risk factor status data stream; a risk prediction model for the distribution network protection area is constructed, and the risk factor status data stream is synchronized to the risk prediction model to obtain a risk prediction data set; risk rules are introduced, and risk assessment is performed in combination with the risk prediction data set to generate risk assessment results; an early warning mechanism is triggered according to the risk assessment results, and early warning feedback information is generated through the early warning mechanism, and intelligent early warning is performed on the risk monitoring of the distribution network protection area according to the early warning feedback information. In other words, through real-time monitoring and data stream processing, risk rules are introduced, risk assessment is performed and intelligent early warning is triggered, potential risk factors are comprehensively identified, and the accuracy of risk identification is improved.

[0047] Embodiment 2, based on the same inventive concept as the risk warning method for monitoring the protection area of ​​the distribution network in the aforementioned embodiment 1, the present application also provides a risk warning platform for monitoring the protection area of ​​the distribution network, please refer to the attached Figure 2 , the risk warning platform for monitoring the distribution network protection area includes: The risk identification module 11 is used to traverse the security demand information of the distribution network protection area to identify the operation risks and determine multiple risk factors.

[0048] The real-time monitoring module 12 is used to perform real-time monitoring on the protection area of ​​the distribution network according to the multiple risk factors to obtain a risk factor status data stream.

[0049] The risk prediction model construction module 13 is used to construct a risk prediction model for the distribution network protection area, synchronize the risk factor status data stream to the risk prediction model, and obtain a risk prediction data set.

[0050] The risk assessment module 14 is used to introduce risk rules, perform risk assessment in combination with the risk prediction data set, and generate risk assessment results.

[0051] The early warning mechanism triggering module 15 is used to trigger the early warning mechanism according to the risk assessment result, generate early warning feedback information through the early warning mechanism, and perform intelligent early warning on the risk monitoring of the distribution network protection area according to the early warning feedback information.

[0052] Furthermore, the risk assessment module 14 in the risk warning platform for monitoring the protection area of ​​the distribution network is also used for: Based on the security demand information of the distribution network protection area, the risk assessment dimensions are determined, and the risk assessment dimensions include risk frequency dimension, risk probability dimension, risk impact dimension, and risk controllability dimension; risk levels are formulated according to the risk impact dimension and the risk controllability dimension, and risk assessment standards are divided according to the risk levels; the risk rules are formulated based on the risk assessment standards in combination with the risk probability dimension and the risk frequency dimension.

[0053] Furthermore, the warning mechanism triggering module 15 in the risk warning platform for monitoring the protection area of ​​the distribution network is also used for: A weighted calculation is performed based on the multiple risk factors to generate a comprehensive risk index; when the comprehensive risk index is greater than or equal to a preset risk threshold, a trigger condition is formulated; it is determined whether the risk assessment result meets the trigger condition; if the risk assessment result meets the trigger condition, the early warning mechanism is triggered and the state of the early warning mechanism is set to an operating state; if the risk assessment result does not meet the trigger condition, the state of the early warning mechanism is set to a waiting state.

[0054] Furthermore, the warning mechanism triggering module 15 in the risk warning platform for monitoring the protection area of ​​the distribution network is also used for: Construct the early warning mechanism, which includes a data input layer, a data processing layer, an emergency response layer, a data feedback layer, and a data output layer; synchronize the risk assessment result to the data processing layer through the data input layer for analysis, and when the early warning mechanism state is the running state, start the emergency response layer, and generate a response strategy based on the emergency response layer and the risk assessment result; synchronize the response strategy to the data feedback layer through the emergency response layer for extraction, determine the early warning feedback information, and synchronize the early warning feedback information to the data output layer; when the early warning mechanism state is the waiting state, start the data feedback layer, generate feedback information, and synchronize the feedback information to the data output layer; the output end of the data processing layer is communicatively connected to the input end of the emergency response layer and the input end of the data feedback layer, the output end of the emergency response layer is communicatively connected to the input end of the data feedback layer, and the output end of the data feedback layer is communicatively connected to the output end of the data output layer.

[0055] Furthermore, the warning mechanism triggering module 15 in the risk warning platform for monitoring the protection area of ​​the distribution network is also used for: The risk prediction model is optimized through the early warning feedback information to obtain a risk prediction optimization model; a risk prediction optimization data set is obtained by synchronizing the risk factor status data stream to the risk prediction optimization model; the risk prediction optimization data set is compared with the risk prediction data set to determine whether the risk level of the risk prediction optimization data set is consistent with the risk level of the risk prediction data set; if the risk level of the risk prediction optimization data set is inconsistent with the risk level of the risk prediction data set, the trigger condition is updated.

[0056] Furthermore, the risk warning platform for monitoring the distribution network protection area also includes a prediction model optimization module for: Based on the early warning feedback information, data screening is performed to obtain a feedback incremental information set; the feedback incremental information set is standardized to determine a feedback incremental standard data set; the risk prediction model is evaluated using the feedback incremental standard data set to generate a model evaluation result; the risk prediction model is batch incrementally learned according to the model evaluation result, and the risk prediction model is optimized according to the incremental learning result to obtain a risk prediction initial optimization model; the risk prediction initial optimization model is verified, and when the verification passes, the risk prediction optimization model is obtained.

[0057] Furthermore, the risk warning platform for monitoring the protection area of ​​the distribution network also includes an intelligent warning module for: Based on the early warning feedback information, the distribution network protection area is continuously monitored to generate a monitoring data record log; the monitoring data record log is traversed in combination with the self-inspection cycle to track risks and construct a risk change trend chart; based on the risk change trend chart, the distribution network protection area is marked with extreme values, and the risk peak identification result is extracted according to the extreme value identification result; according to the risk peak identification result combined with the early warning feedback information, analysis is performed, and intelligent early warning is performed according to the analysis result.

[0058] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The risk warning method and specific examples for monitoring the protection area of ​​the distribution network in the first embodiment are also applicable to the risk warning platform for monitoring the protection area of ​​the distribution network in this embodiment. Through the above detailed description of the risk warning method for monitoring the protection area of ​​the distribution network, those skilled in the art can clearly know the risk warning platform for monitoring the protection area of ​​the distribution network in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the platform disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0059] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0060] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A risk warning method for monitoring a distribution network protection area, characterized in that: include: Traverse the security demand information of the distribution network protection area to identify operational risks and determine multiple risk factors; Performing real-time monitoring of the distribution network protection area according to the multiple risk factors to obtain a risk factor status data stream; Constructing a risk prediction model for the distribution network protection area, synchronizing the risk factor status data stream to the risk prediction model, and obtaining a risk prediction data set; Introducing risk rules, performing risk assessment in combination with the risk prediction data set, and generating risk assessment results; An early warning mechanism is triggered according to the risk assessment result, early warning feedback information is generated through the early warning mechanism, and intelligent early warning is performed on risk monitoring of the distribution network protection area according to the early warning feedback information.

2. The risk warning method for monitoring the protection area of ​​a distribution network according to claim 1, characterized in that: Introduce risk rules, combine the risk prediction data set to perform risk assessment, and generate risk assessment results, including: Determine risk assessment dimensions based on the security demand information of the distribution network protection area, wherein the risk assessment dimensions include risk frequency dimension, risk probability dimension, risk impact dimension, and risk controllability dimension; Formulate risk levels according to the risk impact dimension and the risk controllability dimension, and divide risk assessment standards according to the risk levels; The risk rules are formulated based on the risk assessment criteria combined with the risk probability dimension and the risk frequency dimension.

3. The risk warning method for monitoring the protection area of ​​a distribution network according to claim 1, characterized in that: The early warning mechanism is triggered according to the risk assessment results, including: Performing weighted calculation based on the multiple risk factors to generate a comprehensive risk index; When the comprehensive risk index is greater than or equal to a preset risk threshold, a trigger condition is formulated; Determining whether the risk assessment result meets the trigger condition; If the risk assessment result meets the trigger condition, the early warning mechanism is triggered and the state of the early warning mechanism is set to the running state; If the risk assessment result does not meet the trigger condition, the early warning mechanism state is set to a waiting state.

4. The risk warning method for monitoring the protection area of ​​a distribution network according to claim 3, characterized in that: The early warning feedback information is generated by the early warning mechanism, including: Constructing the early warning mechanism, which includes a data input layer, a data processing layer, an emergency response layer, a data feedback layer, and a data output layer; The risk assessment result is synchronized to the data processing layer through the data input layer for analysis, and when the early warning mechanism state is the running state, the emergency response layer is started, and a response strategy is generated according to the emergency response layer combined with the risk assessment result; The response strategy is synchronized to the data feedback layer through the emergency response layer for extraction, the early warning feedback information is determined, and the early warning feedback information is synchronized to the data output layer; When the state of the early warning mechanism is the waiting state, starting the data feedback layer, generating feedback information, and synchronizing the feedback information to the data output layer; The output end of the data processing layer is communicatively connected to the input end of the emergency response layer and the input end of the data feedback layer, the output end of the emergency response layer is communicatively connected to the input end of the data feedback layer, and the output end of the data feedback layer is communicatively connected to the output end of the data output layer.

5. The risk warning method for monitoring the protection area of ​​a distribution network according to claim 3, characterized in that: The early warning mechanism is triggered according to the risk assessment result, and after the early warning feedback information is generated by the early warning mechanism, it includes: Optimizing the risk prediction model through the early warning feedback information to obtain a risk prediction optimization model; By synchronizing the risk factor status data stream to the risk prediction optimization model, a risk prediction optimization data set is obtained; Comparing the risk prediction optimization data set with the risk prediction data set to determine whether the risk level of the risk prediction optimization data set is consistent with the risk level of the risk prediction data set; If the risk level of the risk prediction optimization data set is inconsistent with the risk level of the risk prediction data set, the trigger condition is updated.

6. The risk warning method for monitoring the protection area of ​​a distribution network according to claim 5, characterized in that: The risk prediction model is optimized by using the early warning feedback information to obtain a risk prediction optimization model, including: Performing data screening based on the early warning feedback information to obtain a feedback incremental information set; Standardizing the feedback increment information set to determine a feedback increment standard data set; Using the feedback increment standard data set to evaluate the risk prediction model and generate a model evaluation result; Performing batch incremental learning on the risk prediction model according to the model evaluation results, optimizing the risk prediction model according to the incremental learning results, and obtaining an initial optimized model for risk prediction; The risk prediction initial optimization model is verified, and when the verification passes, the risk prediction optimization model is obtained.

7. The risk warning method for monitoring the protection area of ​​a distribution network according to claim 1, characterized in that: According to the early warning feedback information, intelligent early warning is performed on the risk monitoring of the distribution network protection area, including: Continuously monitor the distribution network protection area based on the early warning feedback information and generate a monitoring data record log; Traversing the monitoring data record log and combining it with the self-check cycle to track risks and build a risk change trend chart; Based on the risk change trend diagram, the protection area of ​​the distribution network is marked with extreme values, and the risk peak value marking result is extracted according to the extreme value marking result; An analysis is performed based on the risk peak identification result and the warning feedback information, and an intelligent warning is performed based on the analysis result.

8. Risk warning platform for distribution network protection area monitoring, characterized in that: Steps for implementing the risk warning method for monitoring the protection area of ​​a distribution network as described in any one of claims 1 to 7, wherein the risk warning platform for monitoring the protection area of ​​a distribution network comprises: A risk identification module, which is used to traverse the security demand information of the distribution network protection area to identify the operation risks and determine multiple risk factors; A real-time monitoring module, the real-time monitoring module is used to perform real-time monitoring on the protection area of ​​the distribution network according to the multiple risk factors to obtain a risk factor status data stream; A risk prediction model construction module, wherein the risk prediction model construction module is used to construct a risk prediction model for a distribution network protection area, synchronize the risk factor status data stream to the risk prediction model, and obtain a risk prediction data set; A risk assessment module, which is used to introduce risk rules, perform risk assessment in combination with the risk prediction data set, and generate risk assessment results; An early warning mechanism triggering module is used to trigger an early warning mechanism according to the risk assessment result, generate early warning feedback information through the early warning mechanism, and perform intelligent early warning on risk monitoring of the distribution network protection area according to the early warning feedback information.

Images