Early warning method, early warning device and early warning equipment for power grid disasters
By analyzing the operating data, geographical location and environmental data of the power grid line, identifying abnormal nodes and combining disaster prediction models to predict the type and degree of damage, the problems of slow response speed and narrow coverage of traditional power grid disaster warning methods are solved, and high Accurate power grid disaster warning.
Patent Information
- Application Number
- CN202411428842.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-14
- Publication Date
- 2025-02-14
AI Technical Summary
Traditional power grid disaster warning methods rely on manual inspection and empirical judgment. The warning effect is limited and the response speed is slow, making it difficult to cover all possible disaster types and scenarios.
By obtaining the operating data, geographical location data and environmental data of the power grid line, the health status indicators of each node are generated based on multi-algorithm analysis, the indicators are integrated to identify abnormal nodes, and combined with the preset disaster prediction model to predict the type of disaster and the degree of damage, generating early warning information and sent to the command center.
Accurate early warning of power grid disasters has been achieved, the accuracy and timeliness of early warnings have been improved, the safety and stability of the power grid have been enhanced, and the impact of disasters on power grid operation has been reduced.
Smart Images
Figure CN119442084A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of electric power technology, and in particular to an early warning method, an early warning device and early warning equipment for power grid disasters. Background Art
[0002] With the continuous expansion and complexity of the power grid, the risk of disasters that may be encountered during the operation of the power grid is also increasing. The occurrence of disasters may not only cause damage to power grid equipment, but also affect the stable operation of the power system and even cause serious losses to social production and life. Therefore, it is particularly important to provide timely warning and effective response to power grid disasters.
[0003] However, traditional power grid disaster early warning methods mainly rely on manual inspections and empirical judgments, with limited early warning effects and slow response speeds. At the same time, due to the diversity and complexity of power grid disasters, a single early warning method often cannot cover all possible disaster types and scenarios. Summary of the invention
[0004] The main purpose of this application is to provide an early warning method, early warning device and early warning equipment for power grid disasters, aiming to achieve accurate early warning and rapid response to power grid disasters.
[0005] To achieve the above purpose, the present application proposes an early warning method for power grid disasters, the early warning method comprising: Obtaining the operation data of the power grid lines in the area to be tested, the geographical location data and the current environmental data of the area to be tested; Based on the first algorithm and the operating data, evaluating the health status of the power grid line and determining a first health status indicator of each node of the power grid line; Analyze the topographical features of each node of the power grid line based on the first algorithm and the geographic location data, and determine the second health status indicator of each node of the power grid line; Based on the first algorithm and the environmental data, predict the environmental change trend of each node of the power grid line in the future period of time, and determine the third health status indicator of each node of the power grid line; The first health status indicator, the second health status indicator and the third health status indicator are integrated to determine abnormal node information during the operation of the power grid line; According to the abnormal node information and the preset disaster prediction model, predict the type of disaster and degree of damage that the power grid line may suffer, so as to generate corresponding prediction results; According to the abnormal node information and the prediction result, corresponding warning information is generated, and the warning information is sent to the command center.
[0006] In one embodiment, the step of fusing the first health status indicator, the second health status indicator, and the third health status indicator to determine abnormal node information during the operation of the power grid line includes: Calculate the comprehensive health index corresponding to each node according to the first health status indicator, the second health status indicator and the third health status indicator of each node; According to the comprehensive health index and the preset health index threshold, determining that the node whose comprehensive health index exceeds the preset health index threshold is an abnormal node; The abnormal information corresponding to the abnormal node is analyzed to generate abnormal node information during the operation of the power grid line.
[0007] In one embodiment, the step of fusing the first health status indicator, the second health status indicator, and the third health status indicator to determine abnormal node information during the operation of the power grid line further includes: Obtain multiple historical operation data, corresponding geographic location data and historical environmental data under normal operation of power grid lines; Training the plurality of the historical operation data, the geographic location data, and the historical environment data based on a second algorithm to construct a mapping relationship model between the corresponding power grid line operation status and the health index; Determining a plurality of historical health index values according to the mapping relationship model; Analyze the distribution of the historical health index values to determine the preset health index threshold.
[0008] In one embodiment, the step of analyzing the distribution of the historical health index values to determine the preset health index threshold value includes: Counting the historical health index values to determine the average value and standard deviation of the historical health index values; According to the mean value and the standard deviation, the mapping relationship model is modified, and the preset health index threshold is generated.
[0009] In one embodiment, the preset disaster prediction model includes a plurality of sub-models, each sub-model corresponding to a possible disaster type; The step of predicting the type of disaster and degree of damage that the power grid line may suffer based on the abnormal node information and the preset disaster prediction model to generate a corresponding prediction result includes: According to the abnormal node information, determine the type of disaster that each abnormal node may suffer, and select a corresponding target sub-model from the multiple sub-models; Based on the target sub-model, abnormal node information and the environmental data, predicting the degree of damage to the power grid line under the corresponding disaster type; The prediction result is generated according to the possible disaster type and the predicted degree of damage.
[0010] In one embodiment, the step of predicting the degree of damage to the power grid line under the corresponding disaster type based on the target sub-model, abnormal node information and the environmental data includes: Based on the target sub-model, analyzing the abnormal type, abnormal location and abnormal degree in the abnormal node information; Determine the potential damaged area of the power grid line under the corresponding disaster type according to the abnormal type, abnormal location and abnormal degree; The degree of damage to the potentially damaged area when a disaster occurs is predicted based on the environmental data.
[0011] In one embodiment, the early warning method further includes: Obtain historical disaster data and historical abnormal operation data of power grid lines; Based on the third algorithm, the historical disaster data and the historical abnormal operation data are trained to generate a plurality of sub-models corresponding to different disaster types; Importing the sub-model into the test set for testing to determine the performance of the sub-model on the test set and generating corresponding sub-model performance parameters; Optimizing the sub-model performance parameters until the performance of the sub-model meets preset requirements; The sub-model whose performance meets the preset requirements is used as the preset disaster prediction model.
[0012] In one embodiment, the step of generating corresponding warning information according to the abnormal node information and the prediction result, and sending the warning information to the command center includes: Determining the emergency response level of the power grid line disaster according to the abnormal node information and the prediction result; Generate corresponding warning information and emergency response measures according to the emergency response level; Send the warning information and emergency response measures to the command center.
[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes an early warning device, which includes: a memory, a processor, and an early warning program for power grid disasters stored in the memory and executable on the processor, wherein the early warning program for power grid disasters is configured to implement the early warning method for power grid disasters as described above.
[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes an early warning device, including the early warning device as described above.
[0015] The embodiment of the present invention obtains the operation data, geographic location data and current health status of the power grid line in the area to be tested, and then analyzes the operation data, geographic location data and environmental data one by one based on the first algorithm to generate a first health status indicator, a second health status indicator and a third health status indicator for each node of the power grid line, respectively, and then integrates the three indicators to determine the abnormal node information during the operation of the power grid line, and imports the abnormal node information into a preset disaster prediction model to predict the type of disaster and the degree of damage that the power grid line may suffer, so as to generate corresponding prediction results, and finally generates corresponding warning information, and sends the warning information to the command center, which can realize accurate warning of power grid disasters, improve the accuracy and timeliness of warnings, enhance the safety and stability of the power grid, and reduce the impact of disasters on the operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0018] Figure 1 A flow chart of an embodiment of a method for early warning of power grid disasters provided in this application; Figure 2 A flow chart of another embodiment of the early warning method for power grid disasters provided in the present application; Figure 3 A flowchart diagram of another embodiment of the early warning method for power grid disasters provided in the present application; Figure 4 A flowchart diagram of another embodiment of the early warning method for power grid disasters provided in the present application; Figure 5 A flowchart diagram of another embodiment of the early warning method for power grid disasters provided in this application; Figure 6 A flow chart of another embodiment of the early warning method for power grid disasters provided in the present application; Figure 7 A flowchart diagram of another embodiment of the early warning method for power grid disasters provided in the present application; Figure 8 A flowchart diagram is provided for another embodiment of the early warning method for power grid disasters of the present application.
[0019] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments, and the well-known modules, units and their connections, links, communications or operations are not shown or described in detail. In addition, the described features, architectures or functions can be combined in any way in one or more embodiments. It should be understood by those skilled in the art that the various embodiments described below are only for illustration and not for limiting the scope of protection of the present invention. It can also be easily understood that the modules or units or processing methods in the various embodiments described herein and shown in the drawings can be combined and designed according to various different configurations. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0021] The limitations of various nouns or methods referred to in the following embodiments, except for those that are logically untenable, are generally based on the broad concepts that can be implemented under the premise of the disclosure in the embodiments. Under such understanding, the various specific subordinate specific limitations of the nouns or methods should be regarded as the inventive content of the present invention, and should not be understood narrowly or interpreted in a biased manner on the grounds that the specification does not disclose the specific limitations. Similarly, under the premise that it can be implemented logically, the order of the steps in the method is flexible and changeable, and the specific subordinate specific limitations in the broad concepts of various nouns or methods all fall within the scope of protection of the present invention.
[0022] With the continuous expansion and complexity of the power grid, the risk of disasters that may be encountered during the operation of the power grid is also increasing. The occurrence of disasters may not only cause damage to power grid equipment, but also affect the stable operation of the power system and even cause serious losses to social production and life. Therefore, it is particularly important to provide timely warning and effective response to power grid disasters.
[0023] In the process of conceiving and implementing this application, the inventors found that there are at least the following problems: the traditional power grid disaster early warning method mainly relies on manual inspection and experience judgment, the early warning effect is limited and the response speed is slow. At the same time, due to the diversity and complexity of power grid disasters, a single early warning method is often difficult to cover all possible disaster types and scenarios.
[0024] To this end, the present invention proposes an early warning method for power grid disasters; it can be understood that an early warning device for storing and executing the following method is provided in the early warning device, and the early warning device can be implemented by a main controller, such as MCU (Microcontroller Unit), DSP (Digital Signal Process), FPGA (Field Programmable Gate Array), SOC (System On Chip), etc.
[0025] Reference Figure 1 , Figure 1 The figure is a flow chart of a method for early warning of power grid disasters according to an embodiment of the present invention. In an embodiment of the present invention, the early warning method includes steps S100-S700, wherein: S100, obtaining operation data of the power grid lines in the area to be tested, geographical location data, and current environmental data of the area to be tested; S200, based on the first algorithm and the operation data, evaluating the health status of the power grid line, and determining the first health status indicator of each node of the power grid line; S300, analyzing the topographical features of each node of the power grid line based on the first algorithm and the geographic location data, and determining a second health status indicator of each node of the power grid line; S400, based on the first algorithm and the environmental data, predicting the environmental change trend of each node of the power grid line in the future period of time, and determining the third health status indicator of each node of the power grid line; S500, integrating the first health status indicator, the second health status indicator and the third health status indicator to determine abnormal node information during the operation of the power grid line; S600, predicting the type of disaster and degree of damage that the power grid line may suffer based on the abnormal node information and a preset disaster prediction model, so as to generate a corresponding prediction result; S700: Generate corresponding warning information according to the abnormal node information and the prediction result, and send the warning information to a command center.
[0026] In this embodiment, the operation data may include electrical parameters such as voltage, current, power of the power grid, and environmental parameters such as temperature and humidity of the line. The above electrical parameters and environmental parameters can be collected and transmitted in real time by sensors installed on the power grid. The geographic location data may include location information such as the longitude and latitude, altitude, slope or terrain undulation of each node of the power grid line in the area to be tested. The environmental data includes the current meteorological conditions and geological conditions of the area to be tested, and the above environmental data can be obtained through external data sources such as meteorological stations and geological monitoring stations.
[0027] In this embodiment, these multi-source data are first obtained, and then the operation data, geographic location data and environmental data are analyzed separately based on the first algorithm, wherein the first algorithm can be a single processing model or a combination of multiple processing models, or a single algorithm or a combination of multiple algorithms, to analyze and evaluate the operation data, geographic location data and environmental data respectively, so as to determine the comprehensive health status of each node of the power grid line. For example, the first algorithm can include but is not limited to machine learning models, statistical analysis algorithms, expert systems, etc. These algorithms can comprehensively consider the operation status of the power grid line, the geographical environment and the trend of environmental changes, so as to provide a more accurate health status assessment.
[0028] The first algorithm may include an algorithm based on machine learning or deep learning, which builds a corresponding operation data model by training and learning a large amount of historical operation data. When the operation data needs to be analyzed, the operation data is imported into the operation data model for operation to achieve an accurate assessment of the health status of the power grid line. By analyzing the operation data, the first health status indicators of each node of the power grid line can be determined, which reflect the health status of the line in terms of electrical and environmental parameters.
[0029] Among them, the first algorithm can analyze multiple geographic location data based on a machine learning algorithm. By embedding the topographic and geomorphic conditions of various places in the model, the topography and geomorphic conditions can be known by importing the geographic location data into the machine learning model for retrieval during the evaluation. For example, by obtaining the longitude and latitude range of the area to be tested and importing the longitude and latitude range into the machine learning model for retrieval, the topographic and geomorphic information within the corresponding longitude and latitude range and the relevant monsoon climate information can be obtained. Therefore, the topographic and geomorphic characteristics of each node of the power grid line can be determined through the analysis of the geographic location data, so as to judge whether the line is susceptible to natural disasters, which is crucial and reflects the potential risks of the line in terms of topography and geomorphology.
[0030] Among them, the first algorithm can analyze environmental data based on a deep learning algorithm. By processing the data provided by meteorological stations and geological monitoring stations through a deep learning model, the environmental change trend in the future can be predicted. By analyzing the environmental data, the environmental change trend of each node of the power grid line in the future can be predicted, including predicting future meteorological conditions, geological conditions, etc., to determine whether these factors will affect the safe operation of the power grid line, thereby reflecting the environmental risks that the line may face in the future. For example, by analyzing historical meteorological data through a deep learning model, specific weather patterns such as typhoons, heavy rains, droughts, etc. can be identified, and the probability of occurrence of these patterns in the future and the areas that may be affected can be predicted. In addition, the deep learning model can also combine geological monitoring data to assess the risks of natural disasters such as earthquakes and landslides, thereby providing a more comprehensive environmental factor consideration for the health status assessment of power grid lines.
[0031] In this embodiment, by integrating the first health status indicator, the second health status indicator and the third health status indicator, the abnormal node information during the operation of the power grid line is determined by comprehensively considering various factors such as electrical, environmental and topographical factors. These abnormal nodes may have a higher disaster risk and require special attention and early warning. According to the abnormal node information and the preset disaster prediction model, the type of disaster and degree of damage that the power grid line may suffer are predicted. The disaster prediction model can be constructed and trained based on historical disaster data and power grid line characteristics to improve the accuracy of the prediction, so that the corresponding prediction results can be generated to provide a decision-making basis for subsequent early warnings.
[0032] Finally, according to the abnormal node information and prediction results, the corresponding warning information is generated and sent to the command center. The warning information can include the location of the abnormal node, the type of disaster, the predicted degree of damage, and the recommended response measures, so that the command center can respond and make decisions in time, realize timely warning and effective response to power grid disasters, improve the safe operation level of the power grid, and reduce the losses and risks caused by disasters.
[0033] This embodiment obtains the operation data, geographic location data and current health status of the power grid line in the area to be tested, and then analyzes the operation data, geographic location data and environmental data one by one based on the first algorithm to generate a first health status indicator, a second health status indicator and a third health status indicator for each node of the power grid line, respectively. The three indicators are then integrated to determine the abnormal node information during the operation of the power grid line, and the abnormal node information is imported into a preset disaster prediction model to predict the type of disaster and the degree of damage that the power grid line may suffer, so as to generate corresponding prediction results, and finally generate corresponding warning information, and send the warning information to the command center, so as to achieve accurate warning of power grid disasters, improve the accuracy and timeliness of warnings, enhance the safety and stability of the power grid, and reduce the impact of disasters on the operation of the power grid.
[0034] Further, see Figure 2 Another embodiment of the present invention provides a method for early warning of power grid disasters. Figure 1 In the embodiment shown, the step of fusing the first health status indicator, the second health status indicator and the third health status indicator to determine abnormal node information during the operation of the power grid line includes S510-S530, wherein: S510, calculating the comprehensive health index corresponding to each node according to the first health status indicator, the second health status indicator and the third health status indicator of each node; S520, according to the comprehensive health index and the preset health index threshold, determining that the node whose comprehensive health index exceeds the preset health index threshold is an abnormal node; S530: Analyze the abnormal information corresponding to the abnormal node, and generate abnormal node information during the operation of the power grid line.
[0035] In this embodiment, the first health status indicator may include indicators of electrical parameters such as the voltage fluctuation range and current stability of the power grid line, which reflect the electrical health of the power grid line. The second health status indicator may include indicators of geographical features such as the slope, altitude, and soil type of the topography, which can reflect the potential impact of the natural geographical environment in which the power grid line is located on its safe operation. The third health status indicator may include meteorological conditions such as rainfall, wind speed, temperature, etc., as well as geological conditions such as indicators of environmental change trends such as seismic activity and soil moisture, which can predict the environmental risks that the power grid line may face in the future.
[0036] In this embodiment, when integrating these indicators, the comprehensive health index corresponding to each node can be calculated according to the first health status indicator, the second health status indicator and the third health status indicator of each node. The calculation of the comprehensive health index can adopt weighted average, linear combination or other suitable mathematical methods to comprehensively consider the influence of different indicators. The specific calculation method and weight distribution can be set and adjusted according to the actual situation.
[0037] In addition, based on the comprehensive health index and the preset health index threshold, the node whose comprehensive health index exceeds the preset health index threshold is determined as an abnormal node. The preset health index threshold can be set based on historical data, expert experience or relevant standards or trained using a machine learning algorithm to distinguish between normal and abnormal states.
[0038] Finally, by analyzing the abnormal information corresponding to the abnormal nodes, the abnormal node information in the operation process of the power grid line is generated. The abnormal information can include the location of the abnormal node, the abnormal type, the degree of abnormality and the possible cause, etc. This information helps the command center understand the risk points and weak links in the operation process of the power grid line so as to take corresponding countermeasures.
[0039] Through the method of this embodiment, the electrical parameters of the power grid, the topographical features, the environmental change trends and other information of the power grid are comprehensively considered to achieve a comprehensive assessment of the health status of the power grid. By calculating the comprehensive health index and comparing it with the preset health index threshold, abnormal nodes can be accurately identified and corresponding abnormal node information can be generated, providing strong support for subsequent disaster warning and response, which can improve the accuracy and timeliness of warning, help enhance the safety and stability of the power grid, and reduce the impact of disasters on the operation of the power grid.
[0040] Further, see Figure 3 Another embodiment of the present invention provides a method for early warning of power grid disasters. Figure 2 In the embodiment shown, the step of fusing the first health status indicator, the second health status indicator and the third health status indicator to determine abnormal node information during the operation of the power grid line also includes S540-S570, wherein: S540, obtaining a plurality of historical operation data, corresponding geographical location data and historical environment data under normal operation of the power grid line; S550, training the plurality of the historical operation data, the geographic location data, and the historical environment data based on a second algorithm to construct a mapping relationship model between the corresponding power grid line operation status and the health index; S560, determining a plurality of historical health index values according to the mapping relationship model; S570: Analyze the distribution of the historical health index values to determine the preset health index threshold.
[0041] In this embodiment, multiple historical operation data, corresponding geographic location data and historical environmental data under normal operation of the power grid are obtained. These historical data can come from the monitoring system of the power grid, historical records or other reliable data sources, and include the operation status information of the power grid at different times and under different conditions, providing a rich data basis for building a mapping relationship model.
[0042] Next, based on the second algorithm (such as a machine learning algorithm, a deep learning algorithm, etc.), multiple historical operating data, geographic location data, and historical environmental data are trained to construct a corresponding mapping relationship model between the operating status of the power grid line and the health index. Through the training process, the model can learn the complex relationship between the operating status of the power grid line and the health index, so that it can predict its health index based on the current operating status of the power grid line. Then, based on the mapping relationship model, multiple historical health index values are determined. These historical health index values represent the health of the power grid line under the historical operating status, and can be used to analyze the distribution of the health index and determine a reasonable health index threshold.
[0043] Finally, the distribution of historical health index values is analyzed to determine the preset health index threshold. By analyzing the distribution of historical health index values, we can understand the difference in health of power grid lines under different states, and set a suitable threshold to distinguish between normal and abnormal states. The preset health index threshold can be flexibly adjusted according to actual conditions to ensure the accuracy and effectiveness of early warning.
[0044] In this embodiment, by using historical data to construct a mapping relationship model between the operation status of power grid lines and the health index, and determining the preset health index threshold accordingly, the accuracy and reliability of early warning can be further improved. At the same time, the method can also make full use of the information in the historical data to provide more comprehensive data support for subsequent abnormal detection and early warning, which helps to improve the safe operation level of the power grid and reduce the losses and risks caused by disasters.
[0045] Further, see Figure 4 Another embodiment of the present invention provides a method for early warning of power grid disasters. Figure 3 In the embodiment shown, the step of analyzing the distribution of the historical health index values and determining the preset health index threshold value includes S571-S572, wherein: S571, counting the historical health index values to determine the average value and standard deviation of the historical health index values; S572. According to the mean value and the standard deviation, the mapping relationship model is modified, and the preset health index threshold is generated.
[0046] In this embodiment, the historical health index value may include a historical normal health index value and a historical abnormal health index value. By counting the historical health index values, the early warning device can calculate the mean and standard deviation of these indexes. These two statistics can reflect the overall distribution and dispersion of the historical health index values. The mean value represents the central trend of the historical health index values, while the standard deviation measures the degree of deviation of the historical health index values from the mean value. The mapping relationship model is then corrected based on the mean value and standard deviation. The purpose of the correction is to fine-tune the model according to the distribution of historical data to improve the accuracy and reliability of the model. By correcting the model, it can better reflect the true relationship between the operating status of the power grid line and the health index.
[0047] In addition, a preset health index threshold is generated based on the revised mapping relationship model. The setting of the preset health index threshold should be based on the distribution of historical data, which should be able to distinguish between normal and abnormal states and avoid false positives and false negatives. The preset health index threshold is set to be less than the standard deviation of the mean minus a preset multiple. This ensures that when the health index of the power grid line is lower than this threshold, it can be identified as an abnormal state and trigger the corresponding early warning mechanism.
[0048] It should be noted that the historical health index value may include the historical normal health index value and the historical abnormal health index value. When determining the preset health index threshold, it is possible to consider excluding the historical abnormal health index value and only perform statistics and analysis based on the historical normal health index value to ensure that the threshold setting is more accurate and reliable. By using the statistical information of the historical health index value to correct the mapping relationship model and determine the preset health index threshold, the accuracy and reliability of the early warning method can be improved. At the same time, the method also makes full use of the information in the historical data, which helps to better understand and evaluate the health status of the power grid line.
[0049] Further, see Figure 5 Another embodiment of the present invention provides a method for early warning of power grid disasters. Figures 1 to 4 In the illustrated embodiment, the preset disaster prediction model includes a plurality of sub-models, each sub-model corresponding to a possible disaster type; The step of predicting the type of disaster and the degree of damage that the power grid line may suffer based on the abnormal node information and the preset disaster prediction model to generate a corresponding prediction result includes S610-S630, wherein: S610, determining the type of disaster that each abnormal node may suffer according to the abnormal node information, and selecting a corresponding target sub-model from the multiple sub-models; S620, predicting the degree of damage to the power grid line under the corresponding disaster type based on the target sub-model, abnormal node information and the environmental data; S630: Generate the prediction result according to the possible disaster type and the predicted degree of damage.
[0050] In this embodiment, the preset disaster prediction model is a comprehensive model, which includes multiple sub-models, each of which models and predicts a possible disaster type. Multiple sub-models can more accurately predict different types of disasters, thereby improving the accuracy and pertinence of early warning.
[0051] In this embodiment, when an abnormal node appears in the power grid line, the early warning device will determine the type of disaster that each abnormal node may suffer based on the abnormal node information. The disaster type may include lightning, typhoon, rainstorm, snow disaster, geological disaster, etc. According to the determined disaster type, the early warning device will select the corresponding target sub-model from multiple sub-models in the preset disaster prediction model. These target sub-models are constructed for specific disaster types and can more accurately predict the impact of this type of disaster on the power grid line.
[0052] This is achieved by analyzing factors such as the geographic location, operating data, and environmental data of abnormal nodes. Once the type of disaster that may occur is determined, the early warning device will select the corresponding target sub-model from multiple sub-models. The target sub-model is trained for a specific disaster type, so it can more accurately predict the impact of the disaster type on the power grid line.
[0053] Subsequently, the early warning device will predict the degree of damage to the power grid under the corresponding disaster type based on the target sub-model, abnormal node information and environmental data. Environmental data includes real-time meteorological data, geological data, etc., which can provide necessary inputs for the prediction model to more accurately assess the impact of disasters on the power grid. By using the target sub-model and comprehensively considering abnormal node information and environmental data, the early warning device can predict the degree of damage to the power grid under specific disaster types, including the possible fault type, impact range and severity.
[0054] Finally, the early warning device will generate the final prediction results based on the types of disasters that each abnormal node may suffer and the predicted degree of damage. The prediction result of the degree of damage can be a specific value, or a level or range, which is used to describe the potential loss of the power grid line under the influence of disasters. The prediction results can include a list of the types of disasters that the power grid line may suffer, an assessment of the degree of damage under each type of disaster, and the corresponding warning level. These prediction results can provide important decision-making basis for power grid management departments, helping them to take timely response measures to reduce the impact of disasters on power grid lines and ensure the safe and stable operation of the power grid.
[0055] It should be noted that the preset disaster prediction model and sub-model in this embodiment can be constructed based on a large amount of historical data and advanced machine learning algorithms. Through continuous learning and optimization, these models can gradually improve the accuracy and reliability of predictions and provide more powerful support for power grid disaster warnings. By using multiple sub-models to predict different types of disasters, and combining abnormal node information and environmental data to accurately predict the degree of damage, more comprehensive and accurate warning information can be provided, which helps to improve the disaster response capabilities of the power grid.
[0056] Further, see Figure 6 Another embodiment of the present invention provides a method for early warning of power grid disasters. Figure 5 In the illustrated embodiment, the step of predicting the degree of damage to the power grid line under the corresponding disaster type based on the target sub-model, abnormal node information and the environmental data includes S621-S623, wherein: S621. Analyze the abnormal type, abnormal location and abnormal degree in the abnormal node information based on the target sub-model; S622, determining a potential damaged area of the power grid line under a corresponding disaster type according to the abnormality type, abnormality location and abnormality degree; S623: Predict the extent of damage to the potentially damaged area when a disaster occurs based on the environmental data.
[0057] In this embodiment, the abnormal type may include a variety of situations, which are usually inconsistent with the normal operation of the power grid line and may indicate potential safety hazards or impending failures. For example, voltage abnormality, the voltage fluctuation in the power grid line exceeds the normal range, which may be manifested as too high or too low voltage, which may be caused by equipment failure, load change or external interference. Current abnormality, the abnormal increase or decrease of the current in the line may be caused by equipment short circuit, overload or open circuit, etc., and the current abnormality may cause risks such as line overheating, equipment damage or fire. Temperature abnormality, the abnormal increase in the temperature of the power grid line or related equipment may indicate problems such as poor contact, insulation aging or overload, and high temperature may accelerate equipment aging and even cause fire. Frequency abnormality, the fluctuation of the power grid frequency exceeds the normal range, which may be caused by unstable operation of the generator set or sudden changes in load, etc., and the frequency abnormality may affect the stability of the power grid and the normal operation of the equipment. Protection device action, when a power grid line fails, the protection device (such as a circuit breaker, relay, etc.) may act to cut off the faulty part or sound an alarm. The action of the protection device is an important manifestation of power grid line abnormality. Other abnormalities, in addition to the common abnormal types mentioned above, may also include other abnormal conditions, such as abnormal equipment vibration, reduced insulation resistance, gas leakage, etc. These abnormal conditions may pose a threat to the safe operation of power grid lines.
[0058] In this embodiment, by analyzing the abnormal type, abnormal location and abnormal degree in the abnormal node information, the type of disaster and potential damaged area that the power grid line may suffer can be preliminarily determined. The abnormal type provides clues about the nature of the fault, while the abnormal location and abnormal degree help determine the scope and severity of the damaged area. Based on the determined abnormal type, abnormal location and abnormal degree, the target sub-model and environmental data are further used to predict the degree of damage to the power grid line under the corresponding disaster type. Environmental data includes real-time meteorological data, geological data, etc. These data can reflect the environmental conditions when the disaster occurs, which is crucial for accurately predicting the degree of damage.
[0059] By comprehensively considering abnormal node information, target sub-models and environmental data, this embodiment can more accurately predict the damage to power grid lines under the influence of disasters, help reduce the impact of disasters on power grid lines, and improve the safety and reliability of the power grid.
[0060] Further, see Figure 7 Another embodiment of the present invention provides a method for early warning of power grid disasters. Figure 6 In the embodiment shown, the early warning method further includes S640-S680, wherein: S640, obtaining historical disaster data and historical abnormal operation data of power grid lines; S650: Based on the third algorithm, train the historical disaster data and the historical abnormal operation data to generate a plurality of sub-models corresponding to different disaster types; S660, importing the sub-model into the test set for testing to determine the performance of the sub-model on the test set, and generating corresponding sub-model performance parameters; S670, optimizing the sub-model performance parameters until the performance of the sub-model meets preset requirements; S680: Use the sub-model whose performance meets the preset requirements as the preset disaster prediction model.
[0061] In this embodiment, the historical disaster data may include records of various disaster events that the power grid has suffered in the past. These data describe in detail the type of disaster, time of occurrence, location, scope of impact, and actual damage to the power grid. By collecting and analyzing these historical disaster data, the characteristics and laws of damage to the power grid under different disaster types can be better determined, providing an important basis for the early warning device to establish a disaster prediction model. At the same time, historical abnormal operation data is also indispensable, which records various abnormal conditions that occur during the normal operation of the power grid, including voltage fluctuations, current anomalies, equipment failures, etc. These abnormal data can reflect the instability and potential risks of the power grid during operation, and are of great value for predicting the impact of disasters on the power grid.
[0062] In this embodiment, the historical disaster data and the historical abnormal operation data are trained by using the third algorithm to generate multiple sub-models corresponding to different disaster types. The third algorithm can be a machine learning algorithm or a deep learning algorithm, which can learn the damage patterns and laws of power grid lines under different disaster types from a large amount of historical data, thereby building a model that can predict the impact of disasters. Through the sub-models obtained by training, we can predict different types of disasters and formulate corresponding early warning strategies based on the prediction results.
[0063] In addition, in order to evaluate the performance of the sub-model, the above sub-model is imported into the test set for testing. The test set contains data samples different from the training set, which is used to verify the generalization ability and prediction accuracy of the model. By comparing the performance of the sub-model on the test set, we can generate the corresponding sub-model performance parameters, such as accuracy, recall, F1 value, etc. These performance parameters can reflect the pros and cons of the sub-model in predicting the impact of disasters. After obtaining the sub-model performance parameters, we perform optimization operations to improve the prediction accuracy and performance of the sub-model. Optimization methods can include adjusting the parameters of the model, improving the algorithm structure, adding feature engineering, etc. Through continuous optimization and iteration, we can make the performance of the sub-model gradually approach the preset requirements, thereby ensuring the accuracy and reliability of the prediction results.
[0064] Finally, we use the sub-models that meet the preset performance requirements as preset disaster prediction models for actual power grid disaster warning work. These preset disaster prediction models can quickly predict the degree of damage to power grid lines under the corresponding disaster type based on real-time data and abnormal node information, and provide timely and accurate warning information to power grid management departments, helping them to effectively respond to disaster risks and ensure the safe and stable operation of the power grid.
[0065] Further, see Figure 8 Another embodiment of the present invention provides a method for early warning of power grid disasters. Figures 1 to 4 In the embodiment shown, the step of generating corresponding warning information according to the abnormal node information and the prediction result, and sending the warning information to the command center includes S710-S730, wherein: S710, determining an emergency response level for a power grid line disaster according to the abnormal node information and the prediction result; S720, generating corresponding warning information and emergency handling measures according to the emergency response level; S730: Send the warning information and emergency response measures to the command center.
[0066] In this embodiment, the abnormal node information may include detailed information such as the location of the abnormal node in the power grid line, the abnormal type, and the degree of abnormality. The above abnormal node information is crucial for judging the severity and impact range of power grid line disasters. The prediction results reflect the degree of damage to the power grid line under the corresponding disaster type, and provide an important basis for determining the emergency response level. By comprehensively analyzing the abnormal node information and the prediction results, the urgency and potential impact of the power grid line disaster can be accurately judged, thereby determining the corresponding emergency response level.
[0067] In this embodiment, the emergency response level is usually divided into different levels, such as level 1, level 2, level 3, etc., and each level corresponds to different disaster severity and response measures. Once the emergency response level is determined, the corresponding warning information and emergency response measures can be generated according to the level. The warning information may include key information such as the type of disaster, location of occurrence, scope of impact, and expected duration, so that the command center can understand the disaster situation in a timely manner and make corresponding decisions. Emergency response measures are a series of response measures for disasters, including personnel evacuation, equipment maintenance, resource allocation, etc., aimed at reducing the impact of disasters on power grid lines and ensuring the stable operation of the power system.
[0068] Finally, the emergency will send the warning information and treatment measures to the command center so that the command center can make decisions and take corresponding countermeasures in a timely manner. This helps to ensure that when a disaster occurs in the power grid line, an emergency response can be carried out quickly and effectively, minimize the impact of the disaster on the power grid system, and ensure the safety and stability of the power system.
[0069] The present invention also proposes a control device, comprising: the control device comprising: a memory, a processor, and an early warning program for power grid disasters stored in the memory and executable on the processor, the early warning program for power grid disasters being configured to implement the early warning method for power grid disasters as described above.
[0070] It is worth noting that since the control device of the present invention is based on the above-mentioned power grid disaster early warning method, the embodiments of the control device of the present invention include all technical solutions of all embodiments of the above-mentioned power grid disaster early warning method, and the technical effects achieved are also exactly the same, which will not be repeated here.
[0071] The present invention also provides an early warning device, which includes the control device as described in the above embodiment.
[0072] It is worth noting that since the early warning device of the present invention is based on the above-mentioned control device, the embodiments of the early warning device of the present invention include all technical solutions of all embodiments of the above-mentioned control device, and the technical effects achieved are also exactly the same, which will not be repeated here.
[0073] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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, article or system. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0074] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0075] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, including a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0076] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A method for early warning of power grid disasters, characterized in that: The early warning method includes: Obtaining the operation data of the power grid lines in the area to be tested, the geographical location data and the current environmental data of the area to be tested; Based on the first algorithm and the operating data, evaluating the health status of the power grid line and determining a first health status indicator of each node of the power grid line; Analyze the topographical features of each node of the power grid line based on the first algorithm and the geographic location data, and determine the second health status indicator of each node of the power grid line; Based on the first algorithm and the environmental data, predict the environmental change trend of each node of the power grid line in the future period of time, and determine the third health status indicator of each node of the power grid line; By integrating the first health status indicator, the second health status indicator and the third health status indicator, abnormal node information during the operation of the power grid line is determined; According to the abnormal node information and the preset disaster prediction model, predict the type of disaster and degree of damage that the power grid line may suffer, so as to generate corresponding prediction results; According to the abnormal node information and the prediction result, corresponding warning information is generated, and the warning information is sent to the command center.
2. The early warning method according to claim 1, characterized in that: The step of fusing the first health status indicator, the second health status indicator and the third health status indicator to determine abnormal node information during the operation of the power grid line includes: Calculate the comprehensive health index corresponding to each node according to the first health status indicator, the second health status indicator and the third health status indicator of each node; According to the comprehensive health index and the preset health index threshold, determining that the node whose comprehensive health index exceeds the preset health index threshold is an abnormal node; The abnormal information corresponding to the abnormal node is analyzed to generate abnormal node information during the operation of the power grid line.
3. The early warning method according to claim 2, characterized in that: The step of fusing the first health status indicator, the second health status indicator and the third health status indicator to determine abnormal node information during the operation of the power grid line also includes: Obtain multiple historical operation data, corresponding geographic location data and historical environmental data under normal operation of power grid lines; Training the plurality of the historical operation data, the geographic location data, and the historical environment data based on a second algorithm to construct a mapping relationship model between the corresponding power grid line operation status and the health index; Determining a plurality of historical health index values according to the mapping relationship model; Analyze the distribution of the historical health index values to determine the preset health index threshold.
4. The early warning method according to claim 3, characterized in that: The step of analyzing the distribution of the historical health index values to determine the preset health index threshold value includes: Counting the historical health index values to determine the average value and standard deviation of the historical health index values; According to the mean value and the standard deviation, the mapping relationship model is modified, and the preset health index threshold is generated.
5. The early warning method according to any one of claims 1 to 4, characterized in that: The preset disaster prediction model includes multiple sub-models, each sub-model corresponds to a possible disaster type; The step of predicting the type of disaster and degree of damage that the power grid line may suffer based on the abnormal node information and the preset disaster prediction model to generate a corresponding prediction result includes: According to the abnormal node information, determine the type of disaster that each abnormal node may suffer, and select a corresponding target sub-model from the multiple sub-models; Based on the target sub-model, abnormal node information and the environmental data, predicting the degree of damage to the power grid line under the corresponding disaster type; The prediction result is generated according to the possible disaster type and the predicted degree of damage.
6. The early warning method according to claim 5, characterized in that: The step of predicting the degree of damage to the power grid line under the corresponding disaster type based on the target sub-model, abnormal node information and the environmental data includes: Based on the target sub-model, analyzing the abnormal type, abnormal location and abnormal degree in the abnormal node information; Determine the potential damaged area of the power grid line under the corresponding disaster type according to the abnormal type, abnormal location and abnormal degree; The degree of damage to the potentially damaged area when a disaster occurs is predicted based on the environmental data.
7. The early warning method according to claim 6, characterized in that: The early warning method also includes: Obtain historical disaster data and historical abnormal operation data of power grid lines; Based on the third algorithm, the historical disaster data and the historical abnormal operation data are trained to generate a plurality of sub-models corresponding to different disaster types; Importing the sub-model into the test set for testing to determine the performance of the sub-model on the test set and generating corresponding sub-model performance parameters; Optimizing the sub-model performance parameters until the performance of the sub-model meets preset requirements; The sub-model whose performance meets the preset requirements is used as the preset disaster prediction model.
8. The early warning method according to any one of claims 1 to 4, characterized in that: The step of generating corresponding warning information according to the abnormal node information and the prediction result, and sending the warning information to the command center includes: Determining the emergency response level of the power grid line disaster according to the abnormal node information and the prediction result; Generate corresponding warning information and emergency response measures according to the emergency response level; Send the warning information and emergency response measures to the command center.
9. An early warning device, characterized in that: The early warning device includes: a memory, a processor, and an early warning program for power grid disasters stored in the memory and executable on the processor, wherein the early warning program for power grid disasters is configured to implement the early warning method for power grid disasters as described in any one of claims 1 to 8.
10. An early warning device, characterized in that: Comprising the early warning device as claimed in claim 9.