Power grid emergency operation visual analysis method, system, equipment and medium

Abstract

The invention relates to the technical field of power grid data visual analysis, and discloses a power grid emergency operation visual analysis method, system and device and a medium, and the method comprises the steps: obtaining and preprocessing a first parameter of a power grid, and training a first identification model; establishing a second visual model based on the second parameter; and fusing the first identification model and the second visualization model, and carrying out emergency operation visualization analysis. And the efficiency and the accuracy of power grid emergency operation are improved. By training the first identification model, the fault type and the fault position in the power grid can be rapidly and accurately identified, and powerful support is provided for emergency operation. Meanwhile, due to the establishment of the second visual model, the emergency operation process of the power grid is more intuitive and visual, and operators can better understand the state of the power grid and make a more reasonable emergency decision.

Description

Technical Field

[0001] The present application relates to the technical field of power grid data visualization analysis, and in particular to a power grid emergency operation visualization analysis method, system, equipment and medium. Background Art

[0002] In recent years, with the continuous expansion and increasing complexity of power grids, the frequency and scope of grid failures have also gradually increased. Traditional grid emergency response methods often rely on manual judgment and simple data analysis tools. This is not only inefficient but also inadequate for complex grid failures. Especially in emergency situations, how to quickly and accurately locate the fault, identify the fault type, and implement effective emergency measures in a timely manner has become a major challenge in current power system operation and maintenance.

[0003] Furthermore, existing grid data processing methods lack the ability to effectively integrate heterogeneous data from multiple sources, making real-time monitoring and dynamic early warning difficult. In particular, the lack of sophisticated analytical tools for key indicators such as voltage fluctuations, current intensity changes, frequency deviations, and load factors leads to insufficient support for grid emergency decision-making and an inability to meet the modern smart grid's demand for efficient, accurate, and real-time data analysis.

[0004] Therefore, there is an urgent need for an emergency operation visualization analysis method that can comprehensively consider multiple parameters of the power grid and their characteristics of change over time and seasons, so as to improve the speed and accuracy of power grid emergency response and ensure the safe and stable operation of the power grid. Summary of the Invention

[0005] In view of the above existing problems, this application is proposed.

[0006] Therefore, the present application provides a method, system, device and medium for visual analysis of power grid emergency operations, which can solve the problems of low efficiency in power grid emergency operation processing, inaccurate fault location and lack of real-time dynamic warning in the existing technology.

[0007] To solve the above technical problems, this application provides the following technical solutions:

[0008] In a first aspect, the present application provides a method for visual analysis of power grid emergency operations, comprising:

[0009] Acquiring a first parameter of a target power grid and performing a first preprocessing on the first parameter;

[0010] Training a first identification model according to the first preprocessed target power grid first parameter;

[0011] The first identification model is used to identify the emergency operation position according to the first preprocessed target power grid first parameter;

[0012] In response to obtaining a second parameter of the target power grid, establishing a second visualization model based on the second parameter;

[0013] fusing the first recognition model with the second visualization model, wherein the output of the first recognition model serves as the input of the second visualization model;

[0014] Perform a target power grid emergency operation visualization analysis based on the output of the second visualization model.

[0015] As a preferred solution of the method for visual analysis of power grid emergency operations described in this application, the first preprocessing includes:

[0016] Presetting key indicators based on the target power grid, the key indicators including voltage fluctuation, current intensity change, frequency deviation and load rate;

[0017] Obtaining derived indicators based on the key indicators;

[0018] Key indicators and derived indicators are extracted from the first parameter.

[0019] As a preferred solution of the method for visual analysis of power grid emergency operations described in this application, the first preprocessing further includes:

[0020] The first parameter after the index extraction is segmented and marked as data blocks, and a label database is established according to the first parameter after the data block segmentation and marking.

[0021] This preferred solution extracts key indicators such as voltage fluctuations, current intensity changes, frequency deviation, and load factor to more accurately identify abnormalities in the power grid, providing more accurate data support for subsequent visual analysis. Furthermore, the first parameter extracted from the indicators is segmented and labeled, and a label database is established, which helps to quickly locate and analyze power grid faults and improve emergency response speed.

[0022] As a preferred solution of the visual analysis method for power grid emergency operations described in the present application, wherein: the training of the first identification model according to the first parameter of the target power grid after the first preprocessing includes:

[0023] Determining a first normal range of the key indicator and the derived indicator;

[0024] Adding a dynamic adjustment factor for the target grid load changing with time and season to the first normal range to determine a second normal range for key indicators and derived indicators under different time and season changes;

[0025] Determine a training set and a validation set for a first identification model according to the second normal range;

[0026] The training set is a first pre-processed target power grid first parameter that does not meet a second normal range;

[0027] The verification set is a first pre-processed target power grid first parameter that meets a second normal range.

[0028] As a preferred solution of the power grid emergency operation visualization analysis method described in the present application, the first identification model is used to obtain the fault type and fault location according to the first preprocessed target power grid first parameter.

[0029] As a preferred solution of the power grid emergency operation visualization analysis method described in this application, the second visualization model includes:

[0030] The second visualization model includes two input terminals, one input terminal is a second parameter of the target power grid, and the other input terminal is an output of the first identification model;

[0031] The second visualization model is used to perform corresponding visualization operations according to a preset threshold.

[0032] As a preferred solution of the power grid emergency operation visualization analysis method described in this application, the performing corresponding visualization operations according to the preset threshold value includes: determining the abnormality level according to the preset threshold value, and performing corresponding visualization operations according to the abnormality level.

[0033] In a second aspect, the present application provides a power grid emergency operation visualization analysis system, comprising:

[0034] a data processing module, configured to obtain a first parameter of a target power grid and perform a first preprocessing on the first parameter;

[0035] an identification model building module, configured to train a first identification model according to the first preprocessed target power grid first parameter;

[0036] The first identification model is used to identify the emergency operation position according to the first preprocessed target power grid first parameter;

[0037] a visualization model establishing module, configured to establish a second visualization model based on the second parameter in response to obtaining the second parameter of the target power grid;

[0038] a fusion module, configured to fuse the first recognition model with the second visualization model, wherein the output of the first recognition model serves as the input of the second visualization model;

[0039] An analysis module is used to perform a visualization analysis of the target power grid emergency operation according to the output of the second visualization model.

[0040] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described above when executing the computer program.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described above when the computer program is executed by a processor.

[0042] Compared with existing technologies, the present application has the following beneficial effects: It proposes a method for visual analysis of power grid emergency operations, which involves obtaining a first parameter of a target power grid and performing a first preprocessing on the first parameter; training a first identification model based on the first preprocessed parameter of the target power grid; establishing a second visualization model based on the second parameter in response to obtaining a second parameter of the target power grid; fusing the first identification model with the second visualization model, with the output of the first identification model serving as the input of the second visualization model; and performing visual analysis of the target power grid emergency operations based on the output of the second visualization model. This method improves the efficiency and accuracy of power grid emergency operations. By training the first identification model, fault types and locations in the power grid can be quickly and accurately identified, providing strong support for emergency operations. Furthermore, the establishment of the second visualization model makes the power grid emergency operation process more intuitive and visual, helping operators better understand the power grid status and make more reasonable emergency decisions. Furthermore, the present application takes into account the temporal and seasonal variations in power grid load and dynamically adjusts key indicators and derivative indicators, further improving the applicability and accuracy of the method.

[0043] Specifically, obtaining the first parameter of the target power grid and performing preprocessing can ensure the accuracy and reliability of the data and provide a basis for subsequent analysis; by training the first identification model, the fault type and location in the power grid can be quickly and accurately identified, providing key information for emergency operations; in response to the acquisition of the second parameter of the target power grid, a second visualization model is established, which can present complex power grid data in an intuitive manner, making it easier for operators to understand and analyze; fusing the first identification model with the second visualization model realizes the organic combination of fault identification and visualization analysis, and improves the efficiency and accuracy of emergency operations; performing visualization analysis of emergency operations of the target power grid based on the output of the second visualization model can provide comprehensive emergency decision-making support for operators, helping to ensure the safe and stable operation of the power grid. In addition, this application also dynamically adjusts key indicators and derivative indicators by considering the characteristics of power grid load changes over time and seasons, further enhancing the practicality and accuracy of the method and providing a more refined analysis method for power grid emergency operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 A flowchart of a method for visual analysis of power grid emergency operations provided in one embodiment of the present application.

[0046] Figure 2 This is a diagram of the internal structure of an electronic device for a method for visual analysis of power grid emergency operations provided in one embodiment of the present application. DETAILED DESCRIPTION

[0047] To make the above-mentioned purposes, features, and advantages of this application more clearly understood, the following detailed description of the specific embodiments of this application is given in conjunction with the accompanying drawings. It is obvious that the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of this application.

[0048] Example 1, reference Figure 1-Figure 2 , which is the first embodiment of the present application, provides a method for visual analysis of power grid emergency operations, including:

[0049] Existing technologies for power grid emergency response suffer from several issues, including low efficiency in handling power grid emergency operations, inaccurate fault location, and a lack of real-time dynamic warnings. These issues severely restrict the speed and accuracy of power grid emergency responses, posing a threat to the safe and stable operation of the grid.

[0050] This application provides a method that can effectively solve the above-mentioned problems. Next, we will describe in detail how to implement the visual analysis method of power grid emergency operations with reference to multiple embodiments.

[0051] Figure 1 A flowchart of a method for visual analysis of power grid emergency operations is shown, including:

[0052] S101, obtaining a first parameter of a target power grid and performing a first preprocessing on the first parameter;

[0053] In an optional embodiment, the target power grid may be a large-scale transmission grid, a city distribution grid, or an industrial power grid. Depending on the type of grid, the first parameter obtained may vary. For example, a large-scale transmission grid may focus more on line transmission capacity, voltage level, and stability indicators, while a city distribution grid may focus more on load distribution, power supply reliability, and power quality.

[0054] In the embodiment of the present application, the target power grid is a large transmission network in Guizhou Province.

[0055] In the embodiments of the present application, the first parameter of the target power grid can be obtained through various sensors, monitoring devices, or data acquisition systems. These devices can monitor various parameters of the power grid in real time, such as voltage, current, frequency, power factor, etc. In addition, some indirect parameters may also be included, such as weather conditions and load forecast data, which may affect the operating status of the power grid.

[0056] In an optional embodiment, the first preprocessing is to perform preliminary processing and cleaning on the acquired first parameter of the target power grid to eliminate noise, fill missing values, and perform data normalization and other operations, thereby improving the accuracy and efficiency of subsequent analysis.

[0057] It should be noted that the specific steps of the first preprocessing can be customized based on the characteristics and requirements of the target power grid to ensure data accuracy and reliability. For example, continuously changing parameters such as voltage and current can be smoothed using methods such as sliding average or filtering. Discrete or categorized parameters can be encoded or categorized to facilitate subsequent analysis and modeling.

[0058] In the embodiment of the present application, the first preprocessing includes:

[0059] Preset key indicators based on the target power grid, including voltage fluctuation, current intensity change, frequency deviation and load rate;

[0060] Obtain derived indicators based on key indicators;

[0061] Extract key indicators and derived indicators from the first parameter.

[0062] In the embodiment of the present application, the first preprocessing further includes:

[0063] The first parameter after the index extraction is segmented and marked as data blocks, and a label database is established according to the first parameter after the data block segmentation and marking.

[0064] For example, the determination of key indicators assumes that the key indicator set of the target power grid is K = {k1, k2, k3, k4}, where k1 represents voltage fluctuation, k2 represents current intensity change, k3 represents frequency deviation, and k4 represents load rate. For each key indicator k i , this application defines its value at time point t as k i (t).

[0065] Furthermore, derived indicators are obtained. Based on the above key indicators, this application calculates a series of derived indicators D = {d1, d2, ..., d n For example, for voltage fluctuation k1, this application can define a derivative indicator d1 as the standard deviation of voltage fluctuation Right now:

[0066]

[0067] in, is the average value of k1 during the observation period, and N is the number of data points during the observation period.

[0068] Similarly, corresponding derived indicators can be defined for other key indicators.

[0069] Furthermore, the key indicators and derived indicators are extracted, and the original first parameter set P = {p1, p2, ..., p m Based on the above key indicator K and derived indicator D, a new parameter set P' is formed by screening and extracting. This process can be expressed as follows:

[0070] P′=Extract(P,K∪D)

[0071] Here, the Extract function represents extracting information related to key indicators and derived indicators from the original parameter set.

[0072] Furthermore, data block segmentation and labeling are performed on the extracted parameter set P′, and the size of each data block is L.

[0073] Assuming there are M data blocks in total, the i-th data block can be expressed as:

[0074] B i ={p′(j)|(i-1)L+1≤j≤iL}

[0075] Where p′(j) is the jth element in the extracted parameter set P′. Subsequently, each data block is labeled to generate a label database T, where each label t i Corresponding to a data block B i, and record the main characteristics or abnormal conditions of the data block.

[0076] Furthermore, a tag database is established by establishing the first parameter according to the above steps.

[0077] It should be noted that obtaining the first parameter of the target power grid and performing a first preprocessing on the first parameter can provide a high-quality data foundation, which is crucial for the subsequent establishment of an accurate identification model and visualization model. By preprocessing the first parameter, the present application ensures the accuracy, completeness and consistency of the data, thereby improving the reliability and efficiency of the entire analysis process. On this basis, the present application can more accurately train the identification model so that it can quickly and accurately identify the type and location of faults in the power grid. At the same time, high-quality data also provides strong support for the establishment of a visualization model, so that the process of power grid emergency operations can be presented in a more intuitive and clear manner, further improving the efficiency and accuracy of emergency operations.

[0078] S102, training a first identification model according to the first preprocessed target power grid first parameter;

[0079] In the embodiment of the present application, the first identification model is used to identify the emergency operation position according to the first preprocessed target power grid first parameter;

[0080] In an optional embodiment, the first identification model can be constructed using a deep learning algorithm, such as a convolutional neural network (CNN) or a recurrent neural network (RNN). These algorithms can extract features from complex data and automatically learn the underlying relationships between the data, thereby accurately identifying the type and location of power grid faults. During the training process, the pre-processed first parameter of the target power grid can be used as input, combined with known fault location and type information as labels, to train the first identification model through supervised learning. As the training progresses, the model can gradually learn the mapping relationship between power grid parameters and faults, thereby achieving accurate prediction of unknown data.

[0081] In an optional embodiment, the first identification model can also be constructed using traditional machine learning algorithms, such as support vector machines (SVM) or decision trees. Although these algorithms may be more complex than deep learning algorithms, they can also perform well when processing specific types of data. During the training process, the pre-processed first parameter of the target power grid can be used as the feature input, combined with the known fault location and type information as the target output, and the model parameters can be adjusted through an iterative optimization algorithm to minimize the error between the model's prediction results and the actual labels. Through reasonable feature selection and model parameter adjustment, traditional machine learning algorithms can also achieve accurate identification of power grid fault types and locations.

[0082] It should be noted that although the above modeling operation can well realize the role of identification model, the samples of the identification model are not particularly sufficient. Therefore, this application designs an expandable sample operation that takes into account the changes of load over time and seasons.

[0083] In an embodiment of the present application, training a first identification model according to the first preprocessed target power grid first parameter includes:

[0084] Determine the first normal range of key indicators and derived indicators;

[0085] Add a dynamic adjustment factor to the target grid load over time and season to the first normal range, and determine the second normal range of key indicators and derived indicators under different time and season changes;

[0086] Determine a training set and a validation set for the first identification model according to the second normal range;

[0087] The training set is the first parameter of the target power grid after the first preprocessing that does not meet the second normal range;

[0088] The validation set is the first parameter of the target power grid after the first preprocessing that meets the second normal range.

[0089] In an embodiment of the present application, the first identification model is used to obtain the fault type and the fault location according to the first preprocessed target power grid first parameter.

[0090] In an embodiment of the present application, a convolutional neural network is used to establish a first identification model. The convolutional neural network model can automatically extract characteristic information from the first parameter of the target power grid through multi-layer convolution and pooling operations, and perform classification and regression through a fully connected layer, and finally output the fault type and fault location.

[0091] It should be noted that training the first identification model based on the first parameter of the target power grid after the first preprocessing can significantly improve the generalization ability and adaptability of the model. In practical applications, the load of the power grid is often affected by a variety of factors, such as weather changes, holidays, economic activity levels, etc., all of which will cause fluctuations in the load of the power grid. By considering the dynamic adjustment factors of the load that change with time and season, the present application can more accurately simulate the actual operating status of the power grid, thereby generating training samples that are closer to reality. This not only helps to improve the accuracy of the model in identifying the type and location of the fault, but also enhances the model's ability to respond to unknown or abnormal situations. In addition, this dynamic adjustment method can also enable the model to maintain stable performance when facing power grid data at different times and seasons, providing more reliable decision support for power grid emergency operations.

[0092] S103, in response to obtaining a second parameter of the target power grid, establishing a second visualization model based on the second parameter;

[0093] In an optional embodiment, the second visualization model is a real-time display model built for visualization analysis. It utilizes advanced technologies such as digital twins, 3D modeling, or virtual reality to graphically and intuitively present the target power grid's operating status, equipment information, and fault conditions. This visualization model not only helps operators quickly understand the overall status of the power grid but also provides detailed equipment information and fault location, significantly improving the speed and accuracy of emergency response.

[0094] In an embodiment of the application, a second visualization model is established using digital twin technology.

[0095] In this embodiment of the present application, the second visualization model includes:

[0096] The second visualization model includes two input terminals, one input terminal is the second parameter of the target power grid, and the other input terminal is the output of the first identification model;

[0097] The second visualization model is used to perform corresponding visualization operations according to a preset threshold.

[0098] In the embodiment of the present application, performing a corresponding visualization operation according to a preset threshold includes: determining an abnormality level according to the preset threshold, and performing a corresponding visualization operation according to the abnormality level.

[0099] The specific steps for establishing the second visualization model may be as follows:

[0100] Step 1: Determine the input terminal

[0101] Input 1: Second parameter of the target power grid. This usually includes real-time monitoring data such as voltage, current, frequency and other key indicators.

[0102] Input 2: Output of the first identification model. This output contains information about the fault type and location.

[0103] Step 2: Data preprocessing and integration

[0104] The data obtained from the two input ends are normalized to ensure that the data from different sources can be compared and analyzed on the same scale.

[0105] The standardized second parameter is associated with the output of the first identification model to form a comprehensive data set D 综合 For example, if the second parameter is {p1,p2,…,p n}, the output of the first identification model is {f1,f2,…,f m}, then D 综合 ={p1,p2,…,p n ,f1,f2,…,f m}.

[0106] Step 3: Build a visualization model

[0107] According to D 综合 Build a second visualization model. This can be achieved through a variety of visualization techniques and algorithms, such as heat maps, scatter plots, and line graphs. The specific choice depends on the characteristics of the data to be displayed and user needs.

[0108] During the construction process, consideration should be given to how to effectively display key information, such as using color coding to show the level of anomaly, using size or shape changes to represent different fault types, etc.

[0109] Step 4: Set the abnormal level and corresponding threshold

[0110] Define several abnormality levels (such as mild, moderate, and severe), and set corresponding thresholds for each level. Assume that this application defines three abnormality levels: Level 1 (mild), Level 2 (moderate), and Level 3 (severe), and set specific threshold ranges T for each key indicator (such as voltage fluctuation, current intensity change, etc.). level .

[0111] Step 5: Apply threshold to determine anomaly level

[0112] For D 综合 Each data point in the set threshold range T is level The voltage fluctuations are compared to determine the abnormality level. For example, if a voltage fluctuation exceeds the threshold of Level 2 but does not reach the threshold of Level 3, it is marked as a Level 2 abnormality.

[0113] Step 6: Perform corresponding visualization operations

[0114] Perform appropriate visualization actions based on the identified anomaly level. This may include but is not limited to:

[0115] Color coding: Use different colors to represent different abnormality levels. For example, green represents normal, yellow represents Level 1, orange represents Level 2, and red represents Level 3.

[0116] Dynamically adjust the display scale: For more serious anomalies, the size of related graphic elements can be increased or their shape can be changed to draw attention.

[0117] Add annotations or warning signs: Directly mark high-risk areas on a map or other visual interface and provide brief instructions or recommended actions.

[0118] It should be noted that, in response to the acquisition of the second parameter of the target power grid, establishing a second visualization model based on the second parameter can achieve real-time monitoring and rapid response to the power grid's emergency operation status. Through the second visualization model, operators can intuitively see the real-time operating status of the power grid, including information such as the fluctuation of various key indicators, fault type and location. This not only improves the speed of emergency response, but also helps operators quickly locate problems and take corresponding measures, thereby effectively reducing the impact of power grid failures on production and life. At the same time, the second visualization model also has the ability to dynamically update and adjust, and can adaptively adjust according to changes in power grid load over time and seasons to ensure the accuracy and reliability of the model. This real-time, intuitive, and accurate monitoring method provides strong decision-making support for power grid emergency operations and further improves the safety and stability of power grid operation.

[0119] S104, fusing the first recognition model with the second visualization model, with the output of the first recognition model serving as the input of the second visualization model;

[0120] In an optional embodiment, when fusing the first recognition model and the second visualization model:

[0121] First, ensure that the first identification model can output fault type and location information;

[0122] Secondly, to ensure data consistency and accuracy, it is necessary to ensure that the output of the first identification model and the second parameter of the target power grid have the same timestamp or time interval. This usually involves time alignment of the data.

[0123] Thirdly, integrating the output of the first identification model with the second parameter of the target power grid and adjusting the output into a format required by the second visualization model;

[0124] Finally, the adjusted fused data is passed as input to the second visualization model. During the transfer process, it is ensured that the fault type and location information are correctly mapped to the visualization elements (such as color coding, icons, etc.).

[0125] In an optional embodiment, preset thresholds can be designed to determine the level of anomalies based on the preset thresholds in the second visualization model, and the display of fault information can be determined accordingly. For example, more severe faults might be displayed with a striking red marker, while less severe faults might be marked with yellow or other colors. As new data continues to flow in, the visualization interface is continuously updated to reflect the latest grid status and any new fault discoveries. This step may require setting a timer or listener to trigger an automatic update mechanism.

[0126] In an optional embodiment, user interaction can be designed to help operators better understand and respond to grid conditions. Interactive features can be added to the visualization interface, such as clicking on a fault point to view detailed information, zooming in and out on the map, etc. A feedback mechanism can be established to allow users to evaluate the visualization results or suggest modifications to further optimize system performance and user experience.

[0127] It should be noted that by integrating the first identification model with the second visualization model and using the output of the first identification model as the input of the second visualization model, comprehensive, real-time, and intuitive management of power grid emergency operations can be achieved. Through the output of the first identification model, the system can quickly locate the type and location of faults in the power grid and provide operators with accurate information. The second visualization model presents this information in a graphical and intuitive manner, allowing operators to understand the overall status and fault conditions of the power grid at a glance. This integrated approach not only improves the speed and accuracy of emergency response, but also provides operators with a more convenient and efficient way of working.

[0128] In practice, operators can quickly determine the grid's operating status based on the information displayed by the second visualization model and take appropriate measures. For example, if an area experiences voltage fluctuations or abnormal changes in current intensity, operators can immediately view detailed information about the area, including device information, fault type, and location, allowing them to quickly locate the problem and take appropriate measures to repair it.

[0129] Furthermore, by integrating the first identification model with the second visualization model, continuous monitoring and optimization of power grid emergency operations can be achieved. As new data continuously flows in, the system continuously updates the visualization interface to reflect the latest grid status and any new faults discovered. Operators can also use the visualization results to evaluate system performance and user experience, or suggest modifications to further optimize system functionality and performance.

[0130] S105 , performing a visual analysis of the target power grid emergency operation according to the output of the second visualization model.

[0131] It should be noted that the output of the second visualization model provides operators with a comprehensive view of grid emergency operations. This view not only includes real-time grid operating status, including key indicators such as voltage, current, and frequency, but also intuitively displays information such as fault type, location, and abnormality level. Operators can quickly identify abnormal conditions in the grid, such as voltage fluctuations, current overloads, or equipment failures, and take immediate emergency measures.

[0132] In practice, operators may need to make a series of decisions based on the information provided by the second visualization model. For example, if a critical device fails, operators can quickly locate the fault and dispatch a maintenance team to the site for repair. Furthermore, based on the type and severity of the fault, operators can also decide whether local or global adjustments to the grid are necessary to ensure stable operation.

[0133] Furthermore, the output of the second visualization model can be stored and analyzed as historical data. By reviewing and analyzing historical data, operators can identify potential problems and trends in grid operations, thereby developing more effective preventive measures and emergency response plans. This not only improves grid reliability and stability but also reduces the cost and risk of emergency response.

[0134] In summary, the present application proposes a method for visual analysis of power grid emergency operations, which includes obtaining a first parameter of a target power grid and performing a first preprocessing on the first parameter; training a first identification model based on the first parameter of the target power grid after the first preprocessing; establishing a second visualization model based on the second parameter in response to obtaining a second parameter of the target power grid; fusing the first identification model with the second visualization model, with the output of the first identification model serving as the input of the second visualization model; and performing visual analysis of the target power grid emergency operations based on the output of the second visualization model. This improves the efficiency and accuracy of power grid emergency operations. By training the first identification model, the fault type and fault location in the power grid can be quickly and accurately identified, providing strong support for emergency operations. At the same time, the establishment of the second visualization model makes the process of power grid emergency operations more intuitive and visual, helping operators to better understand the power grid status and make more reasonable emergency decisions. In addition, the present application also takes into account the characteristics of power grid load changes over time and seasons, and dynamically adjusts key indicators and derivative indicators, further improving the applicability and accuracy of the method.

[0135] Example 2: In a preferred embodiment, the specific operation of training the first identification model according to the first preprocessed target power grid first parameter may be as follows:

[0136] Step 1: Determine the first normal range of key indicators and derived indicators;

[0137] First, according to the key indicators K = {k1, k2, k3, k4} and the derived indicators D = {d1, d2, ..., d n}, this application needs to define a "first normal range" for each indicator. This can be done through historical data analysis. Suppose for each indicator x (x can be k i or d j ), whose value set in historical data is X={x(t)|t∈T hist}, where T hist This application can calculate the statistical distribution of these values ​​(such as the mean μ x and standard deviation σ x ) to determine the first normal range:

[0138] Re1(x)=[μ x -aσ x ,μ x +aσ x ]

[0139] Here, a is a coefficient selected according to the specific application, usually taking a value of 2 or 3.

[0140] Step 2: Add dynamic adjustment factors;

[0141] Taking into account the changes in grid load over time and seasons, this application needs to adjust the above-mentioned first normal range to obtain a second normal range.

[0142] Assume that this application has a function f(t,s) to represent the impact of time t and season s on the grid load. This function can be obtained based on historical data through regression analysis and other methods.

[0143] Then, the second normal range for each indicator x can be expressed as:

[0144] Re2(x,t,s)=[(μ x -aσ x )f(t,s),(μ x +aσ x )f(t,s)]

[0145] Step 3: Determine the training set and validation set of the first identification model;

[0146] Next, use the second normal range Re2 mentioned above to divide the data set into a training set and a validation set:

[0147] Training set: It is composed of data that do not meet the second normal range, that is, for any time t and season s, if a certain indicator x(t) is not within Re2(x,t,s), then the data point is included in the training set.

[0148] Validation set: It consists of data that meet the second normal range, that is, all indicators are within the range of Re2(x, t, s) at a given time and season.

[0149] In this way, the present application effectively utilizes historical grid data and its temporal and seasonal variations to train the first identification model, thereby improving the accuracy and reliability of the model's identification of grid fault types and locations. This process not only considers the basic operating status of the grid but also incorporates the influence of environmental factors, making the model more suitable for practical application scenarios.

[0150] Example 3: This embodiment also provides a power grid emergency operation visualization analysis system, including:

[0151] A data processing module, configured to obtain a first parameter of a target power grid and perform a first preprocessing on the first parameter;

[0152] an identification model building module, configured to train a first identification model according to the first preprocessed target power grid first parameter;

[0153] The first identification model is used to identify the emergency operation position according to the first preprocessed target power grid first parameter;

[0154] a visualization model establishing module, configured to establish a second visualization model based on the second parameter in response to obtaining the second parameter of the target power grid;

[0155] A fusion module, configured to fuse the first recognition model with the second visualization model, wherein the output of the first recognition model serves as the input of the second visualization model;

[0156] The analysis module is used to perform a visualization analysis of the target power grid emergency operation according to the output of the second visualization model.

[0157] The above-mentioned unit modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0158] This embodiment also provides an electronic device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2As shown. The electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for visual analysis of power grid emergency operations is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device can be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse.

[0159] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the following steps are implemented:

[0160] Acquiring a first parameter of the target power grid and performing a first preprocessing on the first parameter;

[0161] training a first identification model according to a first parameter of the target power grid after the first preprocessing;

[0162] The first identification model is used to identify the emergency operation position according to the first preprocessed target power grid first parameter;

[0163] In response to obtaining a second parameter of the target power grid, establishing a second visualization model based on the second parameter;

[0164] fusing the first recognition model with the second visualization model, with the output of the first recognition model serving as the input of the second visualization model;

[0165] Perform a visualization analysis of the target power grid emergency operation based on the output of the second visualization model.

[0166] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application, and all of these should be included in the scope of the claims of the present application.

[0167] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages.

[0168] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0169] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0170] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0171] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0172] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A visual analysis method for power grid emergency operations, characterized in that: include: Acquiring a first parameter of a target power grid and performing a first preprocessing on the first parameter; Training a first identification model according to the first preprocessed target power grid first parameter; The first identification model is used to identify the emergency operation position according to the first preprocessed target power grid first parameter; In response to obtaining a second parameter of the target power grid, establishing a second visualization model based on the second parameter; fusing the first recognition model with the second visualization model, wherein the output of the first recognition model serves as the input of the second visualization model; Perform a target power grid emergency operation visualization analysis based on the output of the second visualization model.

2. A visual analysis method for power grid emergency operations according to claim 1, characterized in that: The first preprocessing includes: Presetting key indicators based on the target power grid, the key indicators including voltage fluctuation, current intensity change, frequency deviation and load rate; Obtaining derived indicators based on the key indicators; Key indicators and derived indicators are extracted from the first parameter.

3. A visual analysis method for power grid emergency operations according to claim 2, characterized in that: The first preprocessing further includes: The first parameter after the index extraction is segmented and marked as data blocks, and a label database is established according to the first parameter after the data block segmentation and marking.

4. A visual analysis method for power grid emergency operations according to claim 3, characterized in that: The training of the first identification model according to the first preprocessed target power grid first parameter includes: Determining a first normal range of the key indicator and the derived indicator; Adding a dynamic adjustment factor for the target grid load changing with time and season to the first normal range to determine a second normal range for key indicators and derived indicators under different time and season changes; Determine a training set and a validation set for a first identification model according to the second normal range; The training set is a first pre-processed target power grid first parameter that does not meet a second normal range; The verification set is a first pre-processed target power grid first parameter that meets a second normal range.

5. A visual analysis method for power grid emergency operations according to claim 4, characterized in that: The first identification model is used to obtain a fault type and a fault location according to the first preprocessed target power grid first parameter.

6. A visual analysis method for power grid emergency operations according to claim 5, characterized in that: The second visualization model includes: The second visualization model includes two input terminals, one input terminal is a second parameter of the target power grid, and the other input terminal is an output of the first identification model; The second visualization model is used to perform corresponding visualization operations according to a preset threshold.

7. A visual analysis method for power grid emergency operations according to claim 6, characterized in that: The performing a corresponding visualization operation according to a preset threshold includes: determining an abnormality level according to the preset threshold, and performing a corresponding visualization operation according to the abnormality level.

8. A visual analysis system for power grid emergency operations, applying the method according to any one of claims 1 to 7, characterized in that: include: a data processing module, configured to obtain a first parameter of a target power grid and perform a first preprocessing on the first parameter; an identification model building module, configured to train a first identification model according to the first preprocessed target power grid first parameter; The first identification model is used to identify the emergency operation position according to the first preprocessed target power grid first parameter; a visualization model establishing module, configured to establish a second visualization model based on the second parameter in response to obtaining the second parameter of the target power grid; a fusion module, configured to fuse the first recognition model with the second visualization model, wherein the output of the first recognition model serves as the input of the second visualization model; An analysis module is used to perform a visualization analysis of the target power grid emergency operation according to the output of the second visualization model.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for visual analysis of power grid emergency operations according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for visual analysis of power grid emergency operations according to any one of claims 1 to 7 are implemented.

Images