Power system monitoring method, device, electronic equipment and storage medium

Abstract

The present application discloses a power system monitoring method, device, electronic device and storage medium. A power system monitoring method includes the following steps: obtaining optimized reference data, the optimized reference data is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system; adjusting the abnormality detection rules and monitoring algorithms according to the optimized reference data; and monitoring the operation of the power system using the adjusted abnormality detection rules and monitoring algorithms. The application of the technical solution provided by the present application is helpful to improve the accuracy of power system monitoring, reduce the occurrence of missed reports and false reports, and ensure the overall stability of the power system.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a power system monitoring method, device, electronic equipment and storage medium. Background Art

[0002] With the continuous progress of the power industry in information and intelligence, the application of power monitoring technology is becoming more and more popular. The core function of this type of technology is to monitor all parts of the power system in real time, so as to quickly identify abnormal conditions and take corresponding measures immediately to ensure the reliability and safety of the overall operation of the power system. As an important part of power system monitoring, the power security monitoring system has the main task of monitoring the safety of equipment in the power system and preventing illegal intrusion, equipment failure or other abnormal situations.

[0003] However, in the relevant power security monitoring system, due to factors such as system design, algorithm selection, data quality, and the setting of anomaly detection rules, false alarms and missed alarms are prone to occur, thus affecting the stability of the power system. For example, the algorithm may misjudge normal maintenance personnel in the station as intruders, or be too sensitive to changes in ambient light (such as shadow changes), resulting in false alarms. In addition, the monitoring system usually needs to set relevant rules to define what constitutes an abnormality. If these rules are set too loosely, it may lead to missed alarms, and if these rules are set too strictly, it may lead to false alarms. Furthermore, failure to detect and deal with potential problems in a timely manner may cause the power system to operate in a faulty or abnormal state, further affecting the overall stability of the power system.

[0004] Therefore, how to improve the accuracy of power system monitoring, reduce the occurrence of missed reports and false reports, and ensure the overall stability of the power system is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] The purpose of this application is to provide a power system monitoring method, device, electronic device and storage medium to improve the accuracy of power system monitoring, reduce the occurrence of missed reports and false alarms, and ensure the overall stability of the power system.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] In a first aspect, a power system monitoring method is provided, which is applied to a monitoring system, and the method comprises:

[0008] Acquire optimization reference data, where the optimization reference data is related to at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system;

[0009] Adjusting anomaly detection rules and monitoring algorithms based on the optimized reference data;

[0010] The operation of the power system is monitored using the adjusted anomaly detection rules and monitoring algorithms.

[0011] Optionally, the adjustment of the anomaly detection rule includes at least one of the following:

[0012] Adjustment of the threshold range in the anomaly detection rule;

[0013] Adjustment of the indicator category in the anomaly detection rule.

[0014] Optionally, the adjustment of the monitoring algorithm includes at least one of the following:

[0015] Adjustments to the type of monitoring algorithm;

[0016] Adjustment of parameters of the monitoring algorithm;

[0017] Adjustment of the indicator categories of the monitoring algorithm;

[0018] Adjustments to the integration method of multiple anomaly detection algorithms included in the monitoring algorithm.

[0019] Optionally, before monitoring the operation of the power system using the adjusted anomaly detection rule and monitoring algorithm, the method further includes at least one of the following:

[0020] Maintaining and calibrating sensor equipment used to monitor said power system;

[0021] Determine the data transmission protocol for real-time monitoring;

[0022] Performing quality control on real-time monitoring data of the power system;

[0023] Determine the storage solution based on the amount of monitoring data and access requirements.

[0024] Optionally, the method further comprises:

[0025] Display monitoring related information through display panels;

[0026] Wherein, the display panel includes at least one display module.

[0027] Optionally, the method further comprises at least one of the following:

[0028] In response to the received module customization instruction, add or delete a display module on the display panel, and in the case of receiving an adjustment instruction for the module size, adjust the size of the corresponding display module on the display panel;

[0029] In response to a received selection instruction for a target abnormal event in a target display module, jump to a target device monitoring screen corresponding to the target abnormal event, and adjust the size or viewing angle of the target device monitoring screen when receiving an adjustment instruction for the target device monitoring screen, wherein the target display module is used to display abnormal event records of the power system;

[0030] In response to the received export instruction for the monitoring report, the monitoring report is displayed on the display panel, and in the case of receiving the export confirmation instruction, the monitoring report file is exported.

[0031] Optionally, an artificial intelligence (AI) voice assistant is provided on the display panel, and the AI ​​voice assistant is used to perform at least one of the following:

[0032] Respond to users' voice query commands in real time;

[0033] Provide operation guidance to users;

[0034] For detected abnormal events, the system analyzes the causes of the abnormalities based on the built-in knowledge base and analysis algorithms, and outputs processing suggestions;

[0035] Learn from user habits and preferences and adjust service methods.

[0036] In a second aspect, a power system monitoring device is provided, which is applied to a monitoring system, and the device includes:

[0037] An acquisition unit, configured to acquire optimization reference data, wherein the optimization reference data is related to at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system;

[0038] An adjustment unit, configured to adjust anomaly detection rules and monitoring algorithms according to the optimized reference data;

[0039] The monitoring unit is used to monitor the operation of the power system using the adjusted abnormality detection rules and monitoring algorithms.

[0040] In a third aspect, an electronic device is provided, including:

[0041] Memory for storing computer programs;

[0042] A processor is used to implement the steps of the power system monitoring method as described in the first aspect when executing the computer program.

[0043] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the power system monitoring method as described in the first aspect are implemented.

[0044] In a fifth aspect, a computer program product is provided, which includes computer instructions, which are stored in a computer-readable storage medium and are suitable for being read and executed by a processor, so that a computer device having the processor performs the steps of the power system monitoring method as described in the first aspect.

[0045] Applying the technical solution provided in the embodiment of the present application, first obtain optimized reference data, which is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system. According to the optimized reference data, adjust the anomaly detection rules and the monitoring algorithm, and use the adjusted anomaly detection rules and the monitoring algorithm to monitor the operation of the power system. The optimized reference data is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system, so that when the anomaly detection rules and the monitoring algorithm are adjusted according to the optimized reference data, the influencing factors of the historical monitoring data, the feedback data for the monitoring system, and the characteristic data of the power system can be taken into account, so that the anomaly detection rules and the monitoring algorithm can better adapt to the changing power system, which helps to improve the accuracy of monitoring the power system, reduce the occurrence of missed reports and false reports, and ensure the overall stability of the power system.

[0046] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. 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 paying creative work.

[0048] Figure 1 This is a flowchart of an implementation method of a power system monitoring method in an embodiment of the present application;

[0049] Figure 2 This is a schematic diagram showing a panel in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of a personalized configuration interface in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of a module selection interface in an embodiment of the present application;

[0052] Figure 5 This is a schematic diagram of the monitoring report export interface in an embodiment of the present application;

[0053] Figure 6 This is a schematic diagram of the structure of a power system monitoring device in an embodiment of the present application;

[0054] Figure 7 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of the present application.

[0056] The terms "first", "second", etc. of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of one type, and the number of objects is not limited, for example, the first object can be one or more. In addition, "or" in the present application represents at least one of the connected objects. For example, the protection scope of "A or B" covers at least three schemes, that is, scheme one: including A and excluding B; scheme two: including B and excluding A; scheme three: including both A and B. In addition, the terms "A and / or B", "at least one of A and B", and "at least one of A or B" also cover at least the above three schemes respectively. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0057] The core of this application is to provide a power system monitoring method, which can be applied to a monitoring system and is suitable for scenarios where the operation of a power system is monitored.

[0058] In related technologies, monitoring systems often rely on fixed anomaly detection rules and monitoring algorithms, and lack consideration of the dynamic characteristics of the power system, which makes it difficult to accurately identify abnormal events when data fluctuates under different loads and working conditions. In addition, traditional monitoring systems often ignore the time correlation of data and fail to make full use of historical monitoring data to improve the accuracy of anomaly detection.

[0059] The embodiment of the present application first obtains optimized reference data, which is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system. According to the optimized reference data, the anomaly detection rules and the monitoring algorithm are adjusted, and the operation of the power system is monitored using the adjusted anomaly detection rules and the monitoring algorithm. The optimized reference data is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system, so that when the anomaly detection rules and the monitoring algorithm are adjusted according to the optimized reference data, the influencing factors of the historical monitoring data, the feedback data for the monitoring system, and the characteristic data of the power system can be taken into account, so that the anomaly detection rules and the monitoring algorithm can better adapt to the changing power system, which helps to improve the accuracy of monitoring the power system, reduce the occurrence of missed reports and false reports, and ensure the overall stability of the power system.

[0060] See also Figure 1 As shown, it is an implementation flow chart of a power system monitoring method provided by an embodiment of the present application. The method can be applied to a monitoring system. The method may include the following steps:

[0061] S110: Acquire optimization reference data.

[0062] The optimized reference data is related to at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system.

[0063] In an embodiment of the present application, the monitoring system is used to monitor the operation of the power system so as to promptly handle abnormal events when they are detected.

[0064] During operation, the monitoring system may acquire optimization reference data, which may be related to at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system.

[0065] It can be understood that the optimization reference data may include at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system.

[0066] Alternatively, it can be understood that the optimization reference data may include data further obtained by analyzing at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system.

[0067] For example, by analyzing historical monitoring data of the power system, we can understand the occurrence patterns and characteristics of real abnormal events, identify common false alarms and missed alarms, and determine the causes of false alarms and missed alarms.

[0068] By analyzing the feedback data from the monitoring system, we can know the operating performance of the monitoring system and get feedback from operators and maintenance personnel.

[0069] By analyzing the characteristic data of the power system, we can know the dynamic characteristics of the power system, such as load fluctuations and the actual operating environment of the power system.

[0070] The data obtained through analysis can be used as reference data for optimization.

[0071] The optimization reference data is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system, which helps to improve the effectiveness of the optimization reference data and provide a data basis for subsequent steps.

[0072] S120: Adjust the anomaly detection rules and monitoring algorithms according to the optimized reference data.

[0073] In the embodiment of the present application, the anomaly detection rules and monitoring algorithms initially used by the monitoring system can be pre-set.

[0074] Initial anomaly detection rules and monitoring algorithms may be simple and crude, such as containing fixed thresholds or single indicators. For example, the current or voltage of the power system is considered abnormal if it exceeds a fixed range. The initial anomaly detection rules do not consider the dynamic characteristics or actual operating conditions of the power system, and may be "if the current of a line in the power system exceeds 500 amps or the voltage is less than 200 volts, trigger an alarm."

[0075] The anomaly detection rules in the embodiments of the present application focus on specific criteria or conditions for defining what constitutes an anomaly, including some thresholds or conditional statements. The monitoring algorithm focuses on mathematical models or computational methods for identifying abnormal events, identifying anomalies by analyzing the characteristics and patterns of data. The monitoring algorithm can be a statistical method, a machine learning method, or an integration of these methods.

[0076] After obtaining the optimized reference data, the anomaly detection rules and monitoring algorithms can be adjusted according to the optimized reference data so that the adjusted anomaly detection rules and monitoring algorithms are better suited to the changing power system. The process of adjusting the anomaly detection rules and monitoring algorithms can also be understood as the process of optimizing the anomaly detection rules and monitoring algorithms.

[0077] The anomaly detection rules are adjusted to make them more intelligent and dynamic, capable of performing anomaly detection based on real-time monitoring data and historical monitoring data, and taking into account the complexity of the power system.

[0078] For example, the anomaly detection rule is adjusted to "if the current of a line in the power system exceeds 500 amperes and the average current value change rate of the line in the past 24 hours exceeds 10%, an alarm is triggered."

[0079] For another example, the anomaly detection rule is adjusted to adjust the current threshold or voltage threshold in the anomaly detection rule to a dynamic threshold based on historical monitoring data. The current threshold can be adjusted according to the load condition, or the voltage threshold can be adjusted according to seasonal changes and equipment characteristics. For example, the current threshold is adjusted to 600 amperes during high load periods and to 450 amperes during low load periods, the voltage threshold is set to 210 volts in winter, and the voltage threshold is set to 190 volts in summer.

[0080] The monitoring algorithm is adjusted so that the adjusted monitoring algorithm can combine multiple indicators and characteristics of the power system to make a comprehensive judgment, and at the same time is more in line with the actual data and operating environment of the power system.

[0081] S130: Monitor the operation of the power system using the adjusted anomaly detection rules and monitoring algorithms.

[0082] In an embodiment of the present application, after obtaining optimized reference data and adjusting the anomaly detection rules and monitoring algorithms based on the optimized reference data, the adjusted anomaly detection rules and monitoring algorithms can be applied to the actual monitoring process, and the operation of the power system can be monitored using the adjusted anomaly detection rules and monitoring algorithms.

[0083] Applying the method provided in the embodiment of the present application, first obtain optimized reference data, which is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system. According to the optimized reference data, the anomaly detection rules and the monitoring algorithm are adjusted, and the operation of the power system is monitored using the adjusted anomaly detection rules and the monitoring algorithm. The optimized reference data is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system, so that when the anomaly detection rules and the monitoring algorithm are adjusted according to the optimized reference data, the influencing factors of the historical monitoring data, the feedback data for the monitoring system, and the characteristic data of the power system can be taken into account, so that the anomaly detection rules and the monitoring algorithm can better adapt to the changing power system, which helps to improve the accuracy of monitoring the power system, reduce the occurrence of missed reports and false reports, and ensure the overall stability of the power system.

[0084] In some embodiments of the present application, the adjustment of the anomaly detection rule may include at least one of the following:

[0085] Adjustment of the threshold range in anomaly detection rules;

[0086] Adjustments to indicator categories in anomaly detection rules.

[0087] In an embodiment of the present application, an abnormality detection rule may be composed of a threshold value for determining an abnormality and an indicator for determining an abnormality. Adjustment of the abnormality detection rule may include at least one of adjustment of the threshold range in the abnormality detection rule and adjustment of the indicator category in the abnormality detection rule. Among them, the indicator may include indicators such as current, voltage, power, and temperature, and accordingly, the threshold may include a current threshold, a voltage threshold, a power threshold, a temperature threshold, and the like.

[0088] The optimized reference data is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system. Using statistical methods, such as mean, standard deviation, coefficient of variation, etc., the distribution characteristics of the historical monitoring data can be analyzed to obtain the optimized reference data, so that the threshold range can be adjusted to a reasonable range, or the indicator category can be adjusted to more categories according to the optimized reference data. The actual operating environment and characteristics of the power system can be known through the characteristic data of the power system, and the optimized reference data can be obtained, so that the threshold range or indicator category can be adjusted according to the optimized parameter data to adapt to the data fluctuations under different loads and working conditions. Through the feedback data for the monitoring system, the operating performance of the monitoring system, such as the accuracy and real-time performance of anomaly detection, can be known, and the feedback opinions of operators and maintenance personnel can also be obtained. Based on the operating performance of the monitoring system and the feedback opinions of operators or maintenance personnel, the optimized reference data can be obtained, so that the threshold range or indicator category can be adjusted according to the optimized reference data to meet the actual usage and needs.

[0089] When adjusting the indicator categories in the anomaly detection rules, multi-factor considerations and cross-validation methods can be introduced, such as introducing multi-indicator comprehensive judgment and cross-validation methods. Multi-indicator comprehensive judgment means not relying solely on a single data indicator, but combining multiple related indicators for comprehensive judgment to reduce the false alarm rate. Multiple indicators can include current, voltage, power, temperature and other indicators.

[0090] For example, the indicator is adjusted from the current indicator to a comprehensive indicator of the current indicator and the temperature indicator. First, the current data of a certain device in the power system under normal operation in the past 6 months is collected. Then, based on the mean and standard deviation, two thresholds are set: the upper threshold: mean + 3 × standard deviation = 50A + 3 × 5A = 65A, and the lower threshold: mean - 3 × standard deviation = 50A - 3 × 5A = 35A. If the temperature of the device exceeds the set safety value, even if the current is slightly lower than 65A but still higher than the normal range, it may need to be marked as abnormal, and the abnormal score is calculated using the weighted scoring method. For example, the score for current exceeding the standard is 2 points, and the score for temperature exceeding the standard is 1 point. When the score exceeds 3 points, an alarm is triggered. Monitor the real-time changes of current data and dynamically adjust the threshold according to the long-term operation of the device. For example, if it is found that the device often approaches the threshold during peak load, consider raising the threshold.

[0091] The adjustment of the anomaly detection rule includes at least one of the adjustment of the threshold range and the adjustment of the indicator category, which helps to improve the monitoring capability of the power system.

[0092] In some embodiments of the present application, the adjustment of the monitoring algorithm may include at least one of the following:

[0093] Adjustments to the type of monitoring algorithms;

[0094] Adjustment of parameters of monitoring algorithms;

[0095] Adjustment of indicator categories of monitoring algorithms;

[0096] Adjustments to the integration method of multiple anomaly detection algorithms included in the monitoring algorithm.

[0097] In an embodiment of the present application, the monitoring algorithm is adjusted according to the optimized reference data. The adjustment of the monitoring algorithm may include the adjustment of the type of the monitoring algorithm. The appropriate type of monitoring algorithm may be selected according to the optimized reference data. The types of monitoring algorithms may include statistical methods and machine learning methods. Statistical methods such as the mean variance method and the Z-score method are suitable for anomaly detection based on data distribution, and are effective for some abnormal events with strong regularity. Machine learning methods include algorithms based on supervised learning and unsupervised learning, such as support vector machines, clustering algorithms, and isolation forests, which can better adapt to the complex characteristics of the power system and reduce the occurrence of false alarms and missed reports.

[0098] Adjustments to the monitoring algorithm may include adjustments to the indicator categories of the monitoring algorithm. That is, when adjusting the monitoring algorithm, multiple indicators and characteristics of the power system can be combined to construct a comprehensive monitoring algorithm, combining multiple indicators such as current, voltage, power, temperature, etc. for joint analysis to distinguish between normal working conditions and abnormal events.

[0099] Adjustment of the monitoring algorithm may include adjustment of the parameters of the monitoring algorithm. The optimization reference data may be related to the characteristic data of the power system. The actual data and operating environment of the power system may be known through the characteristic data of the power system to obtain the optimization reference data. The parameters of the monitoring algorithm may be adjusted according to the optimization reference data, such as threshold, window size, number of cluster centers and other parameters.

[0100] For example, it is known that current data has been collected for the past six months, and it is assumed that there are 10,000 sample data.

[0101] When adjusting the threshold, the threshold range is 38A-62A. Depending on the real-time data feedback and the operating environment, the threshold may need to be adjusted up or down. For example, if actual monitoring finds that the device is close to the threshold during the peak load period, the upper threshold can be adjusted to 65A and the lower threshold can be adjusted to 35A to reduce the occurrence of false alarms;

[0102] When adjusting the sliding window size, the initial window size is set to 1 hour. Assuming that the equipment has large fluctuations during the peak load period, it is considered that adjusting the window size to 2 hours may be more effective. In this case, the window size can be adjusted to 2 hours to capture long-term trends more smoothly and reduce the interference of instantaneous fluctuations.

[0103] When adjusting the number of cluster centers, assuming that the initial setting is 3 centers, the elbow rule is used to determine the optimal number of cluster centers. Through analysis, it is found that 4 centers can more effectively represent normal and abnormal data patterns. Therefore, the number of cluster centers can be adjusted to 4.

[0104] When adjusting the monitoring algorithm, a time series analysis method can be introduced, that is, the time correlation of the data can be considered, and the time series analysis method can be used to perform trend analysis and periodic detection on historical monitoring data, so that the monitoring algorithm can identify potential abnormal events.

[0105] You can first collect and organize the historical monitoring data of the monitoring system, including but not limited to sensor data, event records, alarm records, etc.; clean the data, remove noise and irrelevant data, and ensure the quality of the data; arrange the data in chronological order to form a time series.

[0106] Then use time series analysis methods, such as the Autoregressive Integrated Moving Average Model (ARIMA) and exponential smoothing, to perform trend analysis on historical monitoring data; identify long-term trends, short-term fluctuations, and seasonal patterns in historical monitoring data; analyze the changing trends of historical monitoring data and predict possible future trends;

[0107] Then, the periodic features in the historical monitoring data are detected through spectrum analysis and other methods; the frequency and intensity of periodic events are identified, and their impact on the monitoring system is evaluated;

[0108] Based on the results of the above trend analysis and periodic detection, the monitoring algorithm is adjusted, which can be understood as reflecting the behavior of the monitoring data under normal operating conditions; using statistical methods such as mean, standard deviation, coefficient of variation, etc. to set reasonable thresholds; real-time monitoring of newly collected monitoring data, when the data deviates from the range set by the monitoring algorithm, it is marked as a potential abnormal event;

[0109] Combined with other factors that may affect the monitoring algorithm, such as weather changes, equipment maintenance plans, etc., the possibility of abnormal events is comprehensively judged; the effectiveness of the monitoring algorithm is tested using cross-validation methods to ensure that the monitoring algorithm can accurately identify anomalies under different conditions.

[0110] Implement a dynamic feedback mechanism to adjust the monitoring algorithm according to actual operating conditions and needs; regularly evaluate the performance of the monitoring model and optimize the parameters in the monitoring algorithm based on the evaluation results.

[0111] Adjustments to the monitoring algorithm may include adjustments to the integration method of multiple anomaly detection algorithms included in the monitoring algorithm. The monitoring algorithm may integrate multiple anomaly detection algorithms, and the integration method may be adjusted based on the optimized reference data, such as adjusting the weight of each anomaly detection algorithm. The results of multiple anomaly detection algorithms are integrated using an ensemble learning method, and a comprehensive judgment is made through voting and weighted averaging. It can be understood that the monitoring algorithm integrates multiple classifiers and anomaly detectors, and each anomaly detector corresponds to an anomaly detection algorithm.

[0112] Among them, ensemble learning methods may include: bootstrap aggregation method and stacking method. The bootstrap aggregation method is to train multiple decision trees on random subsets of the data set and average or majority vote on their prediction results to perform classification or regression prediction; the stacking method is to take the prediction results of multiple basic classifiers as input, combine these prediction results through a meta-classifier, and thus generate the final prediction result.

[0113] Timely adjustment of at least one of the type, parameters, indicator category, and integration method of multiple anomaly detection algorithms included in the monitoring algorithm will help improve the monitoring capability of the power system.

[0114] In some embodiments of the present application, before using the adjusted anomaly detection rule and monitoring algorithm to monitor the operation of the power system, the method may further include at least one of the following:

[0115] Maintain and calibrate sensor equipment used to monitor power systems;

[0116] Determine the data transmission protocol for real-time monitoring;

[0117] Perform quality control on real-time monitoring data for power systems;

[0118] Determine the storage solution based on the amount of monitoring data and access requirements.

[0119] In an embodiment of the present application, before using the adjusted anomaly detection rules and monitoring algorithms to monitor the operation of the power system, the quality management of the data may also be improved.

[0120] Optionally, the sensor equipment used to monitor the power system can be maintained and calibrated. Sensor equipment with high accuracy and good stability can be selected, and the sensor equipment can be regularly maintained and calibrated to avoid data loss or errors caused by problems with the collection equipment, so as to improve the reliability and accuracy of monitoring data collection.

[0121] Optionally, a data transmission protocol for real-time monitoring can be determined. That is, the monitoring data collection process is optimized to ensure the stability and reliability of the monitoring data collection process and avoid data loss or errors caused by communication problems. Data transmission protocols and technologies suitable for real-time monitoring are selected to ensure the timeliness and integrity of monitoring data transmission.

[0122] Optionally, quality control can be performed on the real-time monitoring data of the power system. A quality control and monitoring mechanism can be established, data quality control standards and indicators can be formulated and implemented, the accuracy, completeness and consistency of the monitoring data can be monitored, and data quality problems can be discovered and handled in a timely manner through real-time monitoring and feedback mechanisms to reduce the scope of the impact of erroneous data.

[0123] Optionally, you can select a suitable storage solution based on the amount of monitoring data and access requirements to ensure data security and reliability. The storage solution may include interface protocols, backup methods, etc. For example, you can back up data regularly and establish a complete data recovery mechanism to prevent data loss or damage due to unexpected events.

[0124] Improving the quality management of data before using the adjusted anomaly detection rules and monitoring algorithms to monitor the operation of the power system can help improve the effectiveness of the monitoring data, thereby improving the accuracy of abnormal events determined based on the monitoring data.

[0125] It should be noted that the adjustment of anomaly detection rules and monitoring algorithms can be executed according to a set period or when the adjustment conditions are met, continuously monitoring and optimizing the monitoring system performance to ensure the stable operation of the power system.

[0126] In some embodiments of the present application, the method may further include the following steps:

[0127] Display monitoring related information through display panels;

[0128] Wherein, the display panel includes at least one display module.

[0129] In the embodiment of the present application, the monitoring system can display monitoring data through a display panel during operation. The display panel can be understood as a visual cockpit, through which monitoring-related information can be viewed in real time, such as parameter information and status of various devices and power circuits in the power system, as well as abnormal event records.

[0130] The display panel may include at least one display module. Figure 2 As shown, it is a schematic diagram of the display panel, including multiple display modules, such as a display module for displaying the online status of the equipment of the power system, a display module for displaying the distribution of abnormal events of each equipment of the power system, a display module for displaying the abnormal event records of the power system, a display module for displaying the power status of the circuits of each equipment of the power system, a display module for displaying the current trend chart of each equipment of the power system, a display module for displaying the voltage trend chart of each equipment of the power system, and a display module for displaying the power statistics chart of each equipment of the power system.

[0131] For example, the online status of the equipment in the power system displayed may include online, offline, abnormal, etc., which can be expressed as a percentage. The abnormal event distribution of each device displayed can display the proportion of abnormal events of a specific device. In this display module, you can view the distribution of abnormal events of different devices by sliding left and right, or you can choose to view the distribution of abnormal events of a specific device through options. The displayed abnormal event records may include information such as the device name, abnormal event name, abnormal event generation time, and processing status. Abnormal events in an unprocessed state can be displayed at the top of this display module. The power status of each device circuit can be displayed through a distribution system diagram. The current trend chart of each device, the voltage trend chart of each device, and the power statistics chart of each device can be displayed through a line chart.

[0132] Of course, the display panel can also include more display modules, such as a display module for displaying the power factor of the equipment, a display module for displaying the three-phase current of each circuit, a display module for displaying the three-phase voltage of each circuit, etc., which are not listed one by one.

[0133] By displaying monitoring related information on the display panel, users can intuitively view the operation status of the power system and realize real-time monitoring of the dynamic real-time information of the power system.

[0134] In some embodiments of the present application, the method may further include at least one of the following:

[0135] In response to the received module customization instruction, add or delete a display module on the display panel, and in the case of receiving an adjustment instruction for the module size, adjust the size of the corresponding display module on the display panel;

[0136] In response to a received selection instruction for a target abnormal event in a target display module, jump to a target device monitoring screen corresponding to the target abnormal event, and adjust the size or viewing angle of the target device monitoring screen when receiving an adjustment instruction for the target device monitoring screen, the target display module is used to display abnormal event records of the power system;

[0137] In response to the received export instruction for the monitoring report, the monitoring report is displayed on the display panel, and in the case of receiving the export confirmation instruction, the monitoring report file is exported.

[0138] In the embodiment of the present application, the user can personalize the display module in the display panel according to actual needs and issue a module customization instruction. In response to the received module customization instruction, the display module can be added or deleted on the display panel, and the size of the corresponding display module can be adjusted on the display panel when an adjustment instruction for the module size is received.

[0139] For example, after the user clicks the "Module Customization" button in the display panel, the personalized configuration interface can be displayed in the display panel, such as Figure 3 As shown, a delete button, such as a red round button with a minus sign, can be set in the upper right corner of each display module in the display panel. If the user clicks the delete button, the corresponding display module can be deleted. An add button, such as a "+" button, can be set in the personalized configuration interface. If the user clicks the add button, the module selection interface can be displayed to the user, such as Figure 4 As shown, users can check the display modules that need to be displayed in the display panel in the module selection interface according to actual needs. In addition, a "Default Recommendation" button can be set in the module selection interface. If the user clicks the "Default Recommendation" button, several default display modules can be checked with one click to increase the selection speed. After the user selects the display module he wants to display, click the "Finish" button in the module selection interface to return to the personalized configuration interface. In the personalized configuration interface, the borders of each display module can be displayed in dark blue to prompt the user to drag the border to adjust the size of each display module. After the user completes all personalized configurations, click the "Finish" button in the personalized configuration interface to complete the custom configuration of the display module.

[0140] When an abnormality occurs in the power system, the abnormal event record of the power system is displayed in the target display module, and a visual alarm can be issued in the form of color change, flashing, and pop-up windows of the abnormal event record to alert the user. If the abnormal situation is urgent, a sound alarm can also be issued to ensure that the user can respond in time. The target display module is used to display the abnormal event record of the power system.

[0141] The user can view the relevant information of the target abnormal event in the target display module according to actual needs. In response to the received selection instruction for the target abnormal event in the target display module, it is possible to jump to the target device monitoring screen corresponding to the target abnormal event, and when receiving the adjustment instruction for the target device monitoring screen, adjust the size or viewing angle of the target device monitoring screen, such as zooming in or out of the target device monitoring screen, roaming in 360 degrees, etc. This makes it convenient for users to remotely view on-site details, such as viewing the appearance of the equipment, the surrounding environment, etc., and can view the required information by mouse operation as if on-site, which helps to quickly identify the problem and take corresponding measures. The target abnormal event is any abnormal event displayed by the target display module.

[0142] The user can also export the monitoring report according to actual needs. In response to the received export instruction for the monitoring report, the monitoring report can be displayed on the display panel, and the monitoring report file can be exported when the export confirmation instruction is received.

[0143] For example, Figure 5 As shown, the user can click the "One-click Export" button set on the display panel. According to the user's click operation, the monitoring report can be displayed on the display panel for the user to view. If the user further clicks the "Confirm Export" button, the monitoring report file can be exported according to the user's click operation. This is convenient for the user to conduct further analysis based on the monitoring report file.

[0144] The display panel can be used to interact with users, allowing them to view relevant information in a timely manner.

[0145] In some embodiments of the present application, an artificial intelligence (AI) voice assistant is provided on the display panel, and the AI ​​voice assistant is used to perform at least one of the following:

[0146] Respond to users' voice query commands in real time;

[0147] Provide operation guidance to users;

[0148] For detected abnormal events, the system analyzes the causes of the abnormalities based on the built-in knowledge base and analysis algorithms, and outputs processing suggestions;

[0149] Learn from user habits and preferences and adjust service methods.

[0150] In the embodiment of the present application, an AI voice assistant is provided on the display panel, and the AI ​​voice assistant can provide function operation guidance to help users get started with the display panel functions more quickly. The AI ​​voice assistant can be displayed in the form of a floating ball or button.

[0151] The AI ​​voice assistant can respond to the user's voice commands in real time, helping the user to query information such as power system status, equipment parameters, and abnormal event records. The user simply speaks a command, such as "check the status of transformer X", and the AI ​​voice assistant can quickly retrieve relevant information and respond to the user in voice and text form.

[0152] The AI ​​voice assistant can also provide users with operation guidance. For new users who are not familiar with the operation of the monitoring system, the AI ​​assistant can provide operation guidance, including how to configure the display module, export monitoring reports, etc. Through voice and text communication, the AI ​​voice assistant can gradually guide users to complete complex tasks and reduce the difficulty of use.

[0153] The AI ​​voice assistant can also notify users of detected abnormal events, analyze the causes of abnormalities based on the built-in knowledge base and algorithms, and output processing suggestions. For example, when an abnormal current of a device is detected, the AI ​​voice assistant can determine whether the abnormal current is caused by device aging, overload or other external factors, and provide possible solutions or preventive measures.

[0154] AI voice assistants can also provide personalized services and have learning capabilities. They can learn and adjust their service methods based on user habits and preferences. Over time, they will become more understanding of users' specific needs and provide a more personalized service experience.

[0155] In general, the technical solution provided by the embodiments of the present application has the following advantages:

[0156] 1) By optimizing the anomaly detection rules, improving the quality management of data, and timely adjusting the power security monitoring system, it is possible to more reliably identify real abnormal situations, reduce false alarms, ensure the safe operation of the power system, reduce the occurrence of false alarms and missed alarms, improve the precision and accuracy of anomaly detection, and make the monitoring system more flexible and able to adapt to different working conditions and environmental changes.

[0157] 2) The monitoring system selects and optimizes the monitoring algorithm during operation, which can improve the ability and sensitivity of anomaly detection, analyze data, discover anomalies and respond more quickly, which also means that potential problems can be predicted earlier and timely measures can be taken to avoid accidents or reduce power outages, improve the availability and stability of the monitoring system, and effectively process large-scale data and perform complex data analysis and processing in real time; at the same time, by optimizing the performance of the monitoring system, potential bottlenecks and defects can be eliminated, the overall stability and reliability of the monitoring system can be improved, and operating costs can be reduced. It can also improve energy utilization efficiency and the effectiveness of human resource allocation, thereby reducing overall operating costs.

[0158] 3) By providing a visual cockpit for abnormal detection of power security monitoring, the visualization and convenience of real-time monitoring are improved. Among them, the visual cockpit supports custom configuration of the display module and supports one-click default configuration, which improves the user's interactive experience; in addition, the visual cockpit also supports calling remote monitoring. Through the abnormal event record, you can jump to the equipment monitoring screen corresponding to the abnormal event record, so that you can grasp the abnormal on-site situation in real time; the visual cockpit also supports one-click export of information reports corresponding to the display panel, which allows users to capture the corresponding key information, improve reading efficiency, and facilitate decision-making; in addition, the AI ​​voice assistant can make the visual cockpit more intelligent and efficient, improving the user experience.

[0159] Corresponding to the above method embodiment, the embodiment of the present application further provides a power system monitoring device, which is applied to a monitoring system. The power system monitoring device described below and the power system monitoring method described above can be referenced to each other.

[0160] See also Figure 6 As shown, the power system monitoring device 600 may include the following units:

[0161] An acquisition unit 610 is used to acquire optimization reference data, where the optimization reference data is related to at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system;

[0162] An adjustment unit 620, configured to adjust anomaly detection rules and monitoring algorithms according to the optimized reference data;

[0163] The monitoring unit 630 is used to monitor the operation of the power system using the adjusted abnormality detection rules and monitoring algorithms.

[0164] By using the device provided in the embodiment of the present application, the optimized reference data is first obtained, and the optimized reference data is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system. According to the optimized reference data, the abnormality detection rules and the monitoring algorithm are adjusted, and the operation of the power system is monitored using the adjusted abnormality detection rules and the monitoring algorithm. The optimized reference data is related to at least one of the historical monitoring data for the power system, the feedback data for the monitoring system, and the characteristic data of the power system, so that when the abnormality detection rules and the monitoring algorithm are adjusted according to the optimized reference data, the influencing factors of the historical monitoring data, the feedback data for the monitoring system, and the characteristic data of the power system can be taken into account, so that the abnormality detection rules and the monitoring algorithm can better adapt to the changing power system, which helps to improve the accuracy of the monitoring of the power system, reduce the occurrence of missed reports and false reports, and ensure the overall stability of the power system.

[0165] In some embodiments of the present application, the adjustment of the anomaly detection rule includes at least one of the following:

[0166] Adjustment of the threshold range in anomaly detection rules;

[0167] Adjustments to indicator categories in anomaly detection rules.

[0168] In some embodiments of the present application, the adjustment of the monitoring algorithm includes at least one of the following:

[0169] Adjustments to the type of monitoring algorithms;

[0170] Adjustment of parameters of monitoring algorithms;

[0171] Adjustment of indicator categories of monitoring algorithms;

[0172] Adjustments to the integration method of multiple anomaly detection algorithms included in the monitoring algorithm.

[0173] In some embodiments of the present application, the power system monitoring device 600 further includes a first processing unit, which is used to:

[0174] Before monitoring the operation of the power system using the adjusted anomaly detection rule and monitoring algorithm, at least one of the following is performed:

[0175] Maintain and calibrate sensor equipment used to monitor power systems;

[0176] Determine the data transmission protocol for real-time monitoring;

[0177] Perform quality control on real-time monitoring data for power systems;

[0178] Determine the storage solution based on the amount of monitoring data and access requirements.

[0179] In some embodiments of the present application, the power system monitoring device 600 further includes a display unit for:

[0180] Display monitoring related information through display panels;

[0181] Wherein, the display panel includes at least one display module.

[0182] In some embodiments of the present application, the power system monitoring device 600 further includes a second processing unit configured to perform at least one of the following:

[0183] In response to the received module customization instruction, add or delete a display module on the display panel, and in the case of receiving an adjustment instruction for the module size, adjust the size of the corresponding display module on the display panel;

[0184] In response to a received selection instruction for a target abnormal event in a target display module, jump to a target device monitoring screen corresponding to the target abnormal event, and adjust the size or viewing angle of the target device monitoring screen when receiving an adjustment instruction for the target device monitoring screen, the target display module is used to display abnormal event records of the power system;

[0185] In response to the received export instruction for the monitoring report, the monitoring report is displayed on the display panel, and in the case of receiving the export confirmation instruction, the monitoring report file is exported.

[0186] In some embodiments of the present application, an artificial intelligence (AI) voice assistant is provided on the display panel, and the AI ​​voice assistant is used to perform at least one of the following:

[0187] Respond to users' voice query commands in real time;

[0188] Provide operation guidance to users;

[0189] For detected abnormal events, the system analyzes the causes of the abnormalities based on the built-in knowledge base and analysis algorithms, and outputs processing suggestions;

[0190] Learn from user habits and preferences and adjust service methods.

[0191] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0192] Corresponding to the above method embodiment, the present application embodiment further provides an electronic device, including:

[0193] Memory for storing computer programs;

[0194] The processor is used to implement the steps of the above-mentioned power system monitoring method when executing the computer program.

[0195] like Figure 7 , which is a schematic diagram of the composition structure of an electronic device, the electronic device may include: a processor 10, a memory 11, a communication interface 12 and a communication bus 13. The processor 10, the memory 11 and the communication interface 12 all communicate with each other through the communication bus 13.

[0196] In the embodiment of the present application, the processor 10 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic devices, etc.

[0197] The processor 10 may call a program stored in the memory 11 . Specifically, the processor 10 may execute operations in an embodiment of the power system monitoring method.

[0198] The memory 11 is used to store one or more programs, which may include program codes, and the program codes include computer operation instructions. In the embodiment of the present application, the memory 11 at least stores programs for implementing the following functions:

[0199] Acquire optimization reference data, where the optimization reference data is related to at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system;

[0200] Adjust anomaly detection rules and monitoring algorithms based on optimized reference data;

[0201] The operation of the power system is monitored using the adjusted anomaly detection rules and monitoring algorithms.

[0202] In a possible implementation, the memory 11 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function, etc.; the data storage area may store data created during use.

[0203] In addition, the memory 11 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0204] The communication interface 12 may be an interface of a communication module, and is used to connect to other devices or systems.

[0205] Of course, it should be noted that Figure 7The structure shown does not constitute a limitation on the electronic device in the embodiment of the present application. In actual applications, the electronic device may include Figure 7 More or fewer components than shown, or combinations of certain components.

[0206] Corresponding to the above method embodiment, the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned power system monitoring method are implemented.

[0207] In addition, it should be noted that: the embodiment of the present application also provides a computer program product or a computer program, which may include computer instructions, and the computer instructions may be stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor can execute the computer instructions so that the computer device executes the description of the power system monitoring method in the corresponding embodiment of the foregoing text, so it will not be repeated here. In addition, the description of the beneficial effects of using the same method will not be repeated. For technical details not disclosed in the computer program product or computer program embodiment involved in this application, please refer to the description of the method embodiment of this application.

[0208] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0209] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0210] Through the description of the above implementation methods, those skilled in the art can also clearly understand that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0211] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be directly implemented using hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a register, a hard disk, a removable disk, a compact disc read-only memory (CD-ROM), or any other form of storage medium known in the art, including several instructions to execute the methods described in the various embodiments of the present application.

[0212] The embodiments of the present application are described above in conjunction with the accompanying drawings, and the description of the above embodiments is only used to help understand the technical solution and its core idea of ​​the present application. It should be pointed out that the present application is not limited to the above-mentioned specific implementation methods, which are merely illustrative and not restrictive. For ordinary technicians in this field, many forms of implementation methods can be made without departing from the scope of protection of the purpose of the present application and the claims, and the present application can also be improved and modified in a number of ways, and these implementation methods, improvements and modifications are all within the scope of protection of the present application.

Claims

1. A power system monitoring method, characterized in that: Applied to a monitoring system, the method comprises: Acquire optimization reference data, where the optimization reference data is related to at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system; Adjusting anomaly detection rules and monitoring algorithms based on the optimized reference data; The operation of the power system is monitored using the adjusted anomaly detection rules and monitoring algorithms.

2. The method according to claim 1, characterized in that The adjustment of the anomaly detection rule includes at least one of the following: Adjustment of the threshold range in the anomaly detection rule; Adjustment of the indicator category in the anomaly detection rule.

3. The method according to claim 1, characterized in that The adjustment of the monitoring algorithm includes at least one of the following: Adjustments to the type of monitoring algorithm; Adjustment of parameters of the monitoring algorithm; Adjustment of the indicator categories of the monitoring algorithm; Adjustments to the integration method of multiple anomaly detection algorithms included in the monitoring algorithm.

4. The method according to claim 1, characterized in that Before monitoring the operation of the power system using the adjusted anomaly detection rule and monitoring algorithm, the method further includes at least one of the following: Maintaining and calibrating sensor equipment used to monitor said power system; Determine the data transmission protocol for real-time monitoring; Performing quality control on real-time monitoring data of the power system; Determine the storage solution based on the amount of monitoring data and access requirements.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Display monitoring related information through display panels; Wherein, the display panel includes at least one display module.

6. The method according to claim 5, characterized in that The method further comprises at least one of the following: In response to the received module customization instruction, add or delete a display module on the display panel, and in the case of receiving an adjustment instruction for the module size, adjust the size of the corresponding display module on the display panel; In response to a received selection instruction for a target abnormal event in a target display module, jump to a target device monitoring screen corresponding to the target abnormal event, and adjust the size or viewing angle of the target device monitoring screen when receiving an adjustment instruction for the target device monitoring screen, wherein the target display module is used to display abnormal event records of the power system; In response to the received export instruction for the monitoring report, the monitoring report is displayed on the display panel, and in the case of receiving the export confirmation instruction, the monitoring report file is exported.

7. The method according to claim 5, characterized in that The display panel is provided with an artificial intelligence (AI) voice assistant, and the AI ​​voice assistant is used to perform at least one of the following: Respond to users' voice query commands in real time; Provide operation guidance to users; For detected abnormal events, the system analyzes the causes of the abnormalities based on the built-in knowledge base and analysis algorithms, and outputs processing suggestions; Learn from user habits and preferences and adjust service methods.

8. A power system monitoring device, characterized in that: Applied to a monitoring system, the device comprises: An acquisition unit, configured to acquire optimization reference data, wherein the optimization reference data is related to at least one of historical monitoring data for the power system, feedback data for the monitoring system, and characteristic data of the power system; An adjustment unit, configured to adjust anomaly detection rules and monitoring algorithms according to the optimized reference data; The monitoring unit is used to monitor the operation of the power system using the adjusted abnormality detection rules and monitoring algorithms.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the power system monitoring method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the power system monitoring method according to any one of claims 1 to 7 are implemented.

Images