A power data online monitoring system

Abstract

The present invention relates to the field of electric power detection technology, and in particular to an electric power data online monitoring system, comprising: a data acquisition module, a data preprocessing module, an anomaly detection module, a data analysis module, an anomaly degree determination module, an abnormal data verification module, and an early warning module. The present invention ensures that the collected current data is accurate and reliable through cleaning and denoising of the data preprocessing module, accurately determines whether the current value is abnormal by comparing with a preset threshold, improves the detection accuracy of abnormal nodes, accurately determines the degree of abnormality of abnormal current values ​​by calculating the Euclidean distance and using the Z-Score outlier method, distinguishes true anomalies from occasional anomalies, corrects the abnormality degree determination result according to the duration of the anomaly, ensures that the current value determined to be abnormal is true and the duration does not exceed the threshold, and warns of the corrected true anomaly, so that corresponding measures can be taken in advance to prevent potential power problems or failures.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power detection, and in particular to an online monitoring system for electric power data. Background Art

[0002] With the development of power systems and the growth of power demand, the demand for safe, reliable and efficient operation of power systems is becoming increasingly urgent. Traditional offline monitoring methods can no longer meet the needs of real-time monitoring and fault warning of power systems. Therefore, online monitoring of power data has emerged.

[0003] The patent document with publication number CN103457356A discloses an intelligent power grid transmission and transformation equipment online monitoring system, including a transmission and transformation status monitoring data management platform, a monitoring main station, a power information network, a transmission line monitoring system and a substation comprehensive online monitoring system, wherein the transmission line monitoring system includes a transmission line monitoring IED and a transmission line monitoring substation, and the substation comprehensive online monitoring system includes a substation monitoring substation, a substation monitoring IED and a physical isolation device, wherein the transmission and transformation status monitoring data management platform is connected to the monitoring main station, wherein the monitoring main station is connected to the power information network, and wherein the power information network is connected to the transmission line monitoring system and the substation comprehensive online monitoring system. The monitoring system does not have sufficient data quality monitoring and alarm mechanisms, and it is difficult to timely discover and correct data anomalies, errors or distortions, resulting in the collected data being inaccurate for a long time, affecting the reliability and effectiveness of the monitoring system. Summary of the invention

[0004] To this end, the present invention provides an online monitoring system for electric power data, so as to overcome the problem in the prior art that the single data quality monitoring judgment condition leads to poor accuracy of the detected electric power data.

[0005] To achieve the above object, the present invention provides an online power data monitoring system, comprising:

[0006] Data acquisition module, used to collect the current value including time stamp of each node in the power grid in real time;

[0007] A data preprocessing module, connected to the data acquisition module, for preprocessing the current value by cleaning and denoising through median filtering;

[0008] An abnormality detection module, connected to the data preprocessing module, used to compare the preprocessed current value with a preset current threshold to determine whether the node is abnormal;

[0009] A data analysis module, connected to the anomaly detection module, for calculating the Euclidean distance of the current value passing through the abnormal node, and comparing the Euclidean distance with a preset distance threshold to determine whether the current value is abnormal;

[0010] an abnormality degree determination module, connected to the data analysis module, for calculating an outlier using a Z-Score outlier method based on the current value determined to be abnormal and the current value collected by the data collection module within a preset time period, and determining the abnormality degree of the current value by comparing the outlier with a preset outlier threshold, wherein the abnormality degree includes a real abnormality and an occasional abnormality;

[0011] an abnormal data verification module, connected to the abnormal degree determination module and the data analysis module respectively, for correcting the determination result of the abnormal degree determination module according to the abnormal current value determined by the data analysis module and the abnormal duration threshold value calculated by the abnormal duration threshold value, and controlling the abnormal detection module to adjust the outlier threshold value according to the correction result;

[0012] The early warning module is connected to the abnormal data verification module and is used to issue an early warning for the current value whose abnormal degree after correction is a real abnormality.

[0013] Furthermore, the abnormality detection module compares the preprocessed current value with a preset current threshold to determine whether the node is abnormal.

[0014] If the pre-processed current value is greater than the current threshold, determining that the node is abnormal;

[0015] If the preprocessed current value is less than or equal to the current threshold, it is determined that the node is not abnormal.

[0016] Further, the data analysis module obtains the current value of the abnormal node, the current value of the abnormal node is a vector x, selects a preset reference vector y as the current value of the non-abnormal node, performs a subtraction operation (xy) on the current value vector x of the abnormal node and the current value vector y of the reference node to obtain a new vector z, and uses the Euclidean distance formula to calculate the Euclidean distance Q of the vector z. Wherein, a represents the dimension of the vector z, and whether the current value is abnormal is determined based on the calculated Euclidean distance and a preset distance threshold.

[0017] Furthermore, the data analysis module determines whether the current value is abnormal based on the calculated Euclidean distance and a preset distance threshold;

[0018] If the Euclidean distance is greater than the distance threshold, the data analysis module determines that the current value is abnormal;

[0019] If the Euclidean distance is less than or equal to the distance threshold, the data analysis module determines that the current value is not abnormal.

[0020] Furthermore, the abnormality determination module integrates several current values ​​within a preset time period into a current value set D, and performs mean calculation and standard deviation calculation on all current values ​​in the data set D, respectively, to obtain a mean S and a standard deviation W, S=R / n, where R is the sum of all current values ​​in the current value set D, and n is the number of current values ​​in the current value set D, Wherein, X is each current value in the current value set D, and the outlier value Z of each current value in the data set D is calculated by the Z-Score formula, Z=(XS) / W, and the abnormality of the current value is judged according to the preset outlier threshold.

[0021] Furthermore, the abnormality determination module determines the abnormality of the current value according to the preset outlier threshold value.

[0022] If the outlier is greater than the outlier threshold, the abnormality degree determination module determines that the abnormality degree of the current value is the true abnormality;

[0023] If the outlier is less than or equal to the outlier threshold, the abnormality degree determination module determines that the abnormality degree of the current value is the occasional abnormality.

[0024] Furthermore, the abnormal data verification module records the start time when the current value is first determined to be abnormal and the end time when the current value is first determined to be non-abnormal after the start time, calculates the difference between the start time and the end time to obtain the abnormal duration, and compares the abnormal duration with the abnormal duration threshold to determine the actual abnormal degree of the current value.

[0025] Furthermore, the abnormal data verification module compares the abnormal duration with the abnormal duration threshold to determine the actual abnormal degree of the current value.

[0026] If the abnormal duration is greater than the abnormal duration threshold, the abnormal data verification module determines that the actual abnormal degree of the current value is a real abnormality;

[0027] If the abnormality duration is less than or equal to the abnormality duration threshold, the abnormality data verification module determines that the actual abnormality degree of the current value is an occasional abnormality.

[0028] Further, the abnormal data verification module corrects the determination result of the abnormal degree determination module. If the actual abnormal degree of the current value determined as a real abnormality by the abnormal degree determination module is an occasional abnormality, the abnormal data verification module corrects the current value determined as a real abnormality by the abnormal degree determination module to an occasional abnormality, and the abnormal data verification module controls the abnormal degree determination module to reduce the outlier threshold;

[0029] If the actual abnormality degree of the current value determined as an occasional abnormality by the abnormality degree determination module is a real abnormality, the abnormal data verification module corrects the current value determined as an occasional abnormality to a real abnormality, and the abnormal data verification module controls the abnormality degree determination module to increase the outlier threshold.

[0030] Furthermore, the abnormality degree determination module controls the abnormality detection module to adjust the outlier threshold according to the correction result, and the decrease in the outlier threshold is positively correlated with the difference between the current value in the abnormal situation and the average of the current values ​​in a preset time period, and the increase in the outlier threshold is negatively correlated with the difference between the current value in the abnormal situation and the average of the current values ​​in a preset time period.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The data preprocessing module cleans and denoises the collected current data to ensure that it is accurate and reliable. By comparing it with the preset threshold, it accurately determines whether the current value is abnormal, thereby improving the detection accuracy of abnormal nodes. By calculating the Euclidean distance and using the Z-Score outlier method, the abnormal degree of abnormal current values ​​is accurately determined to distinguish real abnormalities from occasional abnormalities. The abnormal data verification module corrects the results of the abnormal degree determination module according to the duration of the abnormality to ensure that the current value determined to be abnormal is real and the duration does not exceed the threshold. The early warning module warns of the corrected real abnormality and can take corresponding measures in advance to prevent potential power problems or failures.

[0033] Furthermore, by comparing the preprocessed current value with the set current threshold, the abnormality detection module can effectively identify the abnormality of the node and provide real-time abnormality determination results.

[0034] Furthermore, by calculating the Euclidean distance, the current value of the abnormal node can be compared with the current value of the reference node, so as to quickly determine the abnormal situation. This can not only provide real-time abnormality determination results, but also help users take timely measures to deal with abnormal situations and prevent further damage and failures.

[0035] Furthermore, by calculating and comparing the Euclidean distance, the current value can be accurately judged as abnormal. This can help users find and solve potential problems in a timely manner and improve the safety and stability of the system. At the same time, the use of the data analysis module can also reduce false positives and false negatives and improve the accuracy and reliability of abnormality detection.

[0036] Furthermore, by calculating the mean and standard deviation and using the Z-Score formula to calculate the outliers, the degree of abnormality of each current value can be accurately assessed. This helps users understand the degree of deviation of the current value and determine its degree of abnormality. By determining the degree of abnormality, users can take timely measures to deal with abnormal situations, prevent equipment damage and failures, and optimize the stability and safety of the power system.

[0037] Furthermore, by judging the relationship between the outlier and the outlier threshold, the degree of abnormality of the current value can be distinguished, which helps users distinguish between real abnormalities and occasional abnormalities. This can provide accurate information on the degree of abnormality, help users to discover real abnormalities in a timely manner, and take appropriate measures to deal with the abnormalities. At the same time, for occasional abnormalities, they can be recorded and monitored so as to further study their causes and take preventive measures.

[0038] Furthermore, by recording the start time, end time and calculating the abnormal duration, the abnormal degree of the current value can be accurately assessed. By comparing with the abnormal duration threshold, it is possible to determine whether the abnormal duration of the current value exceeds the preset threshold, and further correct the result of the abnormal degree determination, which helps to improve the accuracy and reliability of the abnormal determination.

[0039] Furthermore, by comparing the abnormal duration with the abnormal duration threshold, it is possible to distinguish between real abnormalities and occasional abnormalities. This helps to improve the accuracy of abnormality determination and take corresponding measures to deal with abnormal situations. By accurately judging the actual abnormality of the current value, maintenance and repair can be carried out in a timely manner.

[0040] Furthermore, by correcting the actual abnormality level, the abnormality determination result of the current value is ensured to be consistent with the actual situation. This helps to reduce misjudgments and missed judgments and improve the accuracy and reliability of the abnormality monitoring system.

[0041] Furthermore, by calculating the difference between the current value and the current value in the preset time period, the size of the outlier threshold is reduced. In this way, abnormal situations can be judged more accurately and corresponding measures can be taken. At the same time, by adjusting the outlier threshold, the judgment result can be made more accurate, and the reliability of the algorithm is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 Schematic diagram of the structure of the online power data monitoring system of this embodiment;

[0043] Figure 2 This is a logic diagram for determining abnormal nodes in this embodiment;

[0044] Figure 3 This is a logic diagram for determining abnormal current values ​​in this embodiment;

[0045] Figure 4 This is a determination logic diagram for determining the abnormal degree of the abnormal current value in this embodiment. DETAILED DESCRIPTION

[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0048] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0049] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] See also Figure 1 As shown, it is a structural diagram of the power data online monitoring system of this embodiment;

[0051] This embodiment provides a power data online monitoring system, including:

[0052] Data acquisition module, used to collect the current value including time stamp of each node in the power grid in real time;

[0053] A data preprocessing module, connected to the data acquisition module, for preprocessing the current value by cleaning and denoising through median filtering;

[0054] An abnormality detection module, connected to the data preprocessing module, used to compare the preprocessed current value with a preset current threshold to determine whether the node is abnormal;

[0055] A data analysis module, connected to the anomaly detection module, for calculating the Euclidean distance of the current value passing through the abnormal node, and comparing the Euclidean distance with a preset distance threshold to determine whether the current value is abnormal;

[0056] an abnormality degree determination module, connected to the data analysis module, for calculating an outlier using a Z-Score outlier method based on the current value determined to be abnormal and the current value collected by the data collection module within a preset time period, and determining the abnormality degree of the current value by comparing the outlier with a preset outlier threshold, wherein the abnormality degree includes a real abnormality and an occasional abnormality;

[0057] an abnormal data verification module, connected to the abnormal degree determination module and the data analysis module respectively, for correcting the determination result of the abnormal degree determination module according to the abnormal current value determined by the data analysis module and the abnormal duration threshold value calculated by the abnormal duration threshold value, and controlling the abnormal detection module to adjust the outlier threshold value according to the correction result;

[0058] The early warning module is connected to the abnormal data verification module and is used to issue an early warning for the current value whose abnormal degree after correction is a real abnormality.

[0059] The timestamped current value of each node in the power grid is obtained through the data acquisition module, cleaned and denoised through the data preprocessing module, and then the abnormal detection module is used to determine whether the node is abnormal. The Euclidean distance of the current value of the abnormal node is calculated through the data analysis module, and the abnormal degree is calculated through the abnormal degree determination module. The abnormal data verification module corrects the result of the abnormal degree determination module according to the abnormal duration, and finally the early warning module issues an early warning for the corrected real abnormality.

[0060] The data preprocessing module cleans and denoises the collected current data to ensure that it is accurate and reliable. By comparing it with the preset threshold, it accurately determines whether the current value is abnormal, thereby improving the detection accuracy of abnormal nodes. By calculating the Euclidean distance and using the Z-Score outlier method, the abnormal degree of abnormal current values ​​is accurately determined to distinguish real abnormalities from occasional abnormalities. The abnormal data verification module corrects the results of the abnormal degree determination module according to the duration of the abnormality to ensure that the current value determined to be abnormal is real and the duration does not exceed the threshold. The early warning module warns of the corrected real abnormality and can take corresponding measures in advance to prevent potential power problems or failures.

[0061] The current threshold is a threshold for determining whether the current value is abnormal. It can be set to a fixed value or dynamically adjusted based on historical data or expert experience. Generally speaking, the current threshold is determined based on the characteristics of the power grid, the capacity and characteristics of the equipment, and the goals of the system. It is usually 80% or 90% of the rated current value. In this embodiment, the current threshold is set to 80%. Setting a lower current threshold can improve the detection sensitivity of abnormal currents and can detect potential problems or faults earlier. This can avoid abnormal currents exceeding the carrying capacity of the equipment and reduce the risk of damaging the equipment or causing larger problems.

[0062] The distance threshold is a threshold used to determine whether the Euclidean distance of the current value is abnormal. The threshold is used in the data analysis module to determine the abnormality by calculating the distance between the current values. The distance threshold can be set according to the actual situation and can be determined based on historical data, statistical analysis or expert experience. It is generally determined through historical data and statistical analysis and is usually set to a multiple of the standard deviation of the data. The common reference range is 1 to 3 times the standard deviation. In this embodiment, the distance threshold is set to 3 times. Setting a higher distance threshold can improve the accuracy of judging abnormal data. A higher threshold can filter out some fluctuations within a small range, avoid misjudging normal changes as abnormalities, and thus reduce the possibility of false alarms.

[0063] The outlier threshold is the threshold of the Z-Score outlier used to determine the degree of abnormality. The abnormality determination module calculates the Z-Score value of the current value and determines the degree of abnormality based on the threshold. The outlier threshold can be determined by statistical methods. Generally speaking, the common outlier threshold range is between -3 and 3. In this embodiment, the outlier threshold is set to -2. Setting a lower outlier threshold can filter out some smaller abnormal fluctuations or noise, thereby reducing misjudgments and false alarms.

[0064] The abnormal duration threshold is a threshold for judging the duration of the abnormal current value. This threshold is used in the abnormal data verification module to determine whether the abnormal current value is a real abnormality. The abnormal duration threshold can be set according to system requirements, equipment characteristics and empirical knowledge. For instantaneous abnormalities, it is set to a few seconds, and for continuous abnormalities, it is set to a few minutes or hours. In this embodiment, the abnormal duration threshold is set to 5 seconds for detecting abnormal power data of the power grid. By setting the abnormal duration threshold to 5 seconds, faster detection and response to abnormalities can be achieved. A shorter abnormal duration threshold can detect abnormal situations earlier, allowing the system to take necessary measures to deal with abnormalities more promptly.

[0065] Real anomalies refer to real abnormal conditions that actually exist in the system, which are significantly different from the normal state. Through the joint judgment of the anomaly detection module, the data analysis module and the abnormality degree determination module, the real abnormal current value can be identified. These anomalies may be caused by faults, errors, abnormal operations or other abnormal factors, and need to be discovered, alarmed and resolved in a timely manner.

[0066] Occasional anomalies refer to abnormal conditions that occasionally occur in the system, usually due to temporary external or internal factors. These abnormal conditions may be short-lived, non-persistent, and quickly return to normal. In the abnormality determination module, the current value is determined according to the Z-Score outlier method to distinguish the current value of occasional abnormalities. Occasional anomalies may be caused by network interruptions, transient problems of power failures, or short-term errors of sensors, and generally do not cause lasting damage to the overall stability and performance of the system.

[0067] Please continue reading Figure 2 As shown, it is a determination logic diagram for determining abnormal nodes in this embodiment;

[0068] Specifically, the abnormality detection module compares the preprocessed current value with a preset current threshold to determine whether the node is abnormal.

[0069] If the pre-processed current value is greater than the current threshold, determining that the node is abnormal;

[0070] If the preprocessed current value is less than or equal to the current threshold, it is determined that the node is not abnormal.

[0071] The abnormality detection module compares the pre-processed current value with the set current threshold to determine whether the node is abnormal. If the pre-processed current value is greater than the current threshold, it is determined to be an abnormal node; if the pre-processed current value is less than or equal to the current threshold, it is determined to be a non-abnormal node.

[0072] By comparing the preprocessed current value with the set current threshold, the anomaly detection module can effectively identify the abnormal situation of the node and provide real-time anomaly determination results.

[0073] Specifically, the data analysis module obtains the current value of the abnormal node, the current value of the abnormal node is vector x, selects a preset reference vector y as the current value of the non-abnormal node, performs a subtraction operation (xy) on the current value vector x of the abnormal node and the current value vector y of the reference node to obtain a new vector z, and uses the Euclidean distance formula to calculate the Euclidean distance Q of the vector z. Wherein, a represents the dimension of the vector z, and whether the current value is abnormal is determined based on the calculated Euclidean distance and a preset distance threshold.

[0074] The data analysis module obtains the current value of the abnormal node and the current value of the reference node, performs subtraction operations to generate a new vector, and calculates the Euclidean distance of the vector using the Euclidean distance formula. Finally, the calculated Euclidean distance is compared with the preset distance threshold to determine whether the current value is abnormal.

[0075] By calculating the Euclidean distance, the current value of the abnormal node can be compared with the current value of the reference node, so as to quickly determine the abnormal situation. This can not only provide real-time abnormality determination results, but also help users take timely measures to deal with abnormal situations and prevent further damage and failures.

[0076] Please continue reading Figure 3 As shown, it is a determination logic diagram for determining abnormal current value in this embodiment;

[0077] Specifically, the data analysis module determines whether the current value is abnormal based on the calculated Euclidean distance and a preset distance threshold;

[0078] If the Euclidean distance is greater than the distance threshold, the data analysis module determines that the current value is abnormal;

[0079] If the Euclidean distance is less than or equal to the distance threshold, the data analysis module determines that the current value is not abnormal.

[0080] The data analysis module determines whether the current value is abnormal by comparing the calculated Euclidean distance with the preset distance threshold. If the Euclidean distance is greater than the distance threshold, the data analysis module determines that the current value is abnormal. If the Euclidean distance is less than or equal to the distance threshold, the data analysis module determines that the current value is not abnormal.

[0081] By calculating and comparing the Euclidean distance, the current value can be accurately judged as abnormal. This can help users find and solve potential problems in a timely manner and improve the safety and stability of the system. At the same time, the use of the data analysis module can also reduce false positives and false negatives and improve the accuracy and reliability of abnormality detection.

[0082] Specifically, the abnormality determination module integrates several current values ​​within a preset time period into a current value set D, and performs mean calculation and standard deviation calculation on all current values ​​in the data set D to obtain a mean S and a standard deviation W, S=R / n, where R is the sum of all current values ​​in the current value set D, and n is the number of current values ​​in the current value set D. Wherein, X is each current value in the current value set D, and the outlier value Z of each current value in the data set D is calculated by the Z-Score formula, Z=(XS) / W, and the abnormality of the current value is judged according to the preset outlier threshold.

[0083] The abnormality determination module integrates the current values ​​within the preset time period into a data set D, and then calculates the mean and standard deviation of the current values ​​in D to obtain the mean S and standard deviation W. Next, the outlier Z of each current value in the data set D is calculated by the Z-Score formula. Finally, the abnormality of the current value is determined according to the preset outlier threshold.

[0084] By calculating the mean and standard deviation and using the Z-Score formula to calculate outliers, each current value can be accurately evaluated for its abnormality. This helps users understand the degree of deviation of the current value and determine its abnormality. By determining the degree of abnormality, users can take timely measures to deal with abnormal situations, prevent equipment damage and failures, and optimize the stability and safety of the power system.

[0085] The preset time period is generally determined by the frequency of data collection, ranging from a few minutes to a few hours, and needs to be adjusted according to the specific situation. In this embodiment, the preset time period is 15 minutes to ensure real-time monitoring and rapid detection of abnormal conditions, and the selected time period contains sufficient data samples and can reflect abnormal current conditions.

[0086] Please continue reading Figure 4 As shown, it is a determination logic diagram for determining the abnormal degree of abnormal current value in this embodiment;

[0087] Specifically, the abnormality degree determination module determines the abnormality degree of the current value according to the preset outlier threshold value, and if the outlier value is greater than the outlier threshold value, the abnormality degree determination module determines that the abnormality degree of the current value is the real abnormality;

[0088] If the outlier is less than or equal to the outlier threshold, the abnormality degree determination module determines that the abnormality degree of the current value is the occasional abnormality.

[0089] The abnormality determination module determines the current value according to the preset outlier threshold. If the outlier exceeds the outlier threshold, the abnormality of the current value is determined to be a real abnormality. If the outlier is less than or equal to the outlier threshold, the abnormality of the current value is determined to be an occasional abnormality.

[0090] By judging the relationship between the outlier and the outlier threshold, the degree of abnormality of the current value can be distinguished, which helps users distinguish between real abnormalities and occasional abnormalities. This can provide accurate information on the degree of abnormality, help users to promptly discover real abnormalities, and take appropriate measures to deal with the abnormalities. At the same time, for occasional abnormalities, they can be recorded and monitored so that their causes can be further studied and preventive measures can be taken.

[0091] Specifically, the abnormal data verification module records the start time when the current value is first determined to be abnormal and the end time when the current value is first determined to be non-abnormal after the start time, calculates the difference between the start time and the end time to obtain the abnormal duration, and compares the abnormal duration with the abnormal duration threshold to determine the actual abnormal degree of the current value.

[0092] The abnormal data verification module records the start time of the first abnormal current value and the end time of the first non-abnormal current value after the start time. The abnormal duration is obtained by calculating the difference between the start time and the end time. Next, the abnormal duration is compared with the abnormal duration threshold to determine the actual abnormal degree of the current value.

[0093] By recording the start time, end time and calculating the abnormal duration, the abnormal degree of the current value can be accurately assessed. By comparing with the abnormal duration threshold, it is possible to determine whether the abnormal duration of the current value exceeds the preset threshold, and further correct the result of the abnormal degree determination, which helps to improve the accuracy and reliability of the abnormal determination.

[0094] Different types of abnormal situations may have different durations. Some abnormalities may only last for a short time, while others may last for a long time. Therefore, using a unified abnormality duration threshold may not be well adapted to all types of abnormal situations. The method of comparing abnormality duration with abnormality duration threshold is usually used as an auxiliary means to verify and supplement other abnormality judgment methods.

[0095] Specifically, the abnormal data verification module compares the abnormal duration with the abnormal duration threshold to determine the actual abnormal degree of the current value.

[0096] If the abnormal duration is greater than the abnormal duration threshold, the abnormal data verification module determines that the actual abnormal degree of the current value is a real abnormality;

[0097] If the abnormality duration is less than or equal to the abnormality duration threshold, the abnormality data verification module determines that the actual abnormality degree of the current value is an occasional abnormality.

[0098] The abnormal data verification module determines the actual abnormal degree of the current value by comparing the abnormal duration and the abnormal duration threshold. If the abnormal duration exceeds the abnormal duration threshold, the abnormal data verification module determines that the actual abnormal degree of the current value is a real abnormality. If the abnormal duration is less than or equal to the abnormal duration threshold, the abnormal data verification module determines that the actual abnormal degree of the current value is an occasional abnormality.

[0099] By comparing the abnormal duration with the abnormal duration threshold, it is possible to distinguish between real abnormalities and occasional abnormalities. This helps to improve the accuracy of abnormality determination and take appropriate measures to deal with abnormal situations. By accurately judging the actual abnormality of the current value, maintenance and repair can be carried out in a timely manner.

[0100] Specifically, the abnormal data verification module corrects the determination result of the abnormal degree determination module. If the actual abnormal degree of the current value determined as a real abnormality by the abnormal degree determination module is an occasional abnormality, the abnormal data verification module corrects the current value determined as a real abnormality by the abnormal degree determination module to an occasional abnormality.

[0101] If the actual abnormality degree of the current value determined as an occasional abnormality by the abnormality degree determination module is a real abnormality, the abnormal data verification module corrects the current value determined as an occasional abnormality to a real abnormality.

[0102] The abnormal data verification module corrects the determination result of the abnormal degree determination module. If the abnormal degree determination module misjudges the current value that is actually an occasional abnormality as a real abnormality, the abnormal data verification module will correct the current value to an occasional abnormality. If the abnormal degree determination module misjudges the current value that is actually a real abnormality as an occasional abnormality, the abnormal data verification module will correct the current value to a real abnormality.

[0103] By correcting the actual abnormality, the abnormality judgment result of the current value is ensured to be consistent with the actual situation. This helps to reduce misjudgments and missed judgments and improve the accuracy and reliability of the abnormality monitoring system.

[0104] Specifically, the abnormality degree determination module controls the abnormality detection module to adjust the outlier threshold according to the correction result, the decrease in the outlier threshold is positively correlated with the difference between the current value in the abnormal situation and the average of the current values ​​in a preset time period, and the increase in the outlier threshold is negatively correlated with the difference between the current value in the abnormal situation and the average of the current values ​​in a preset time period.

[0105] Calculate the difference between the current value under abnormal conditions and the average current value in a preset time period, and multiply the difference by a preset reduction coefficient to reduce the outlier threshold, V'=V-(XS)×U, where V' is the outlier threshold after reduction adjustment, V is the outlier threshold before adjustment, and U is the preset reduction coefficient;

[0106] The abnormality degree determination module is also used to multiply the difference by a preset reduction coefficient to reduce the outlier threshold, V"=V+(XS)×L, wherein V" is the outlier threshold after increase and adjustment, V is the outlier threshold before adjustment, and L is the preset increase coefficient.

[0107] The abnormality level determination module can calculate the difference between the current value under abnormal conditions and the current value within a preset time period. In order to reduce the outlier threshold, this difference will be multiplied by a preset reduction coefficient and the original outlier threshold will be subtracted. The final V' is the adjusted outlier threshold. In addition, the abnormality level determination module can also multiply the difference by a preset reduction coefficient, and then add the original outlier threshold to obtain an increased and adjusted outlier threshold, namely V".

[0108] By calculating the difference between the current value and the current value in the preset time period, the size of the outlier threshold is reduced. In this way, abnormal situations can be judged more accurately and corresponding measures can be taken. At the same time, by adjusting the outlier threshold, the judgment result can be made more accurate and the reliability of the algorithm can be improved.

[0109] The increase coefficient and the reduction coefficient are calculation coefficients for adjusting the size of the outlier threshold. If the data in the current value set D is relatively stable and there are fewer outliers, a smaller reduction coefficient and increase coefficient can be selected to avoid over-adjusting the outlier threshold. The range of the increase coefficient and the reduction coefficient is usually between 0.1 and 0.5. In this embodiment, the increase coefficient and the reduction coefficient are both set to 0.3. Setting the increase coefficient and the reduction coefficient to the same value (0.3) can maintain the balance of the threshold adjustment to a certain extent. This means that for abnormal situations, the threshold will increase relatively more, and for normal situations, the threshold will decrease relatively less to maintain the sensitivity and accuracy of the judgment.

[0110] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An online power data monitoring system, characterized in that: include: Data acquisition module, used to collect the current value including time stamp of each node in the power grid in real time; A data preprocessing module, connected to the data acquisition module, for preprocessing the current value by cleaning and denoising through median filtering; An abnormality detection module, connected to the data preprocessing module, used to compare the preprocessed current value with a preset current threshold to determine whether the node is abnormal; A data analysis module, connected to the anomaly detection module, for calculating the Euclidean distance of the current value passing through the abnormal node, and comparing the Euclidean distance with a preset distance threshold to determine whether the current value is abnormal; an abnormality degree determination module, connected to the data analysis module, for calculating an outlier using a Z-Score outlier method based on the current value determined to be abnormal and the current value collected by the data collection module within a preset time period, and determining the abnormality degree of the current value by comparing the outlier with a preset outlier threshold, wherein the abnormality degree includes a real abnormality and an occasional abnormality; an abnormal data verification module, connected to the abnormal degree determination module and the data analysis module respectively, for correcting the determination result of the abnormal degree determination module according to the abnormal current value determined by the data analysis module and the abnormal duration threshold value calculated by the abnormal duration threshold value, and controlling the abnormal detection module to adjust the outlier threshold value according to the correction result; The early warning module is connected to the abnormal data verification module and is used to issue an early warning for the current value whose abnormal degree after correction is a real abnormality.

2. The power data online monitoring system according to claim 1, characterized in that: The abnormality detection module compares the preprocessed current value with a preset current threshold to determine whether the node is abnormal, including: if the preprocessed current value is greater than the current threshold, determining that the node is abnormal; If the preprocessed current value is less than or equal to the current threshold, it is determined that the node is not abnormal.

3. The power data online monitoring system according to claim 2, characterized in that: The data analysis module obtains the current value of the abnormal node, the current value of the abnormal node is vector x, selects a preset reference vector y as the current value of the non-abnormal node, performs a subtraction operation (xy) on the current value vector x of the abnormal node and the current value vector y of the reference node to obtain a new vector z, and uses the Euclidean distance formula to calculate the Euclidean distance Q of the vector z. Wherein, a represents the dimension of the vector z, and whether the current value is abnormal is determined based on the calculated Euclidean distance and a preset distance threshold.

4. The power data online monitoring system according to claim 3, characterized in that: The data analysis module determines whether the current value is abnormal according to the calculated Euclidean distance and a preset distance threshold, including: If the Euclidean distance is greater than the distance threshold, the data analysis module determines that the current value is abnormal; If the Euclidean distance is less than or equal to the distance threshold, the data analysis module determines that the current value is not abnormal.

5. The power data online monitoring system according to claim 4, characterized in that: The abnormality degree determination module integrates several current values ​​within a preset time period into a current value set D, and performs mean calculation and standard deviation calculation on all current values ​​in the current value set D, respectively, to obtain a mean S and a standard deviation W, S=R / n, where R is the sum of all current values ​​in the current value set D, and n is the number of current values ​​in the current value set D. Wherein, X is each current value in the current value set D, and the outlier value Z of each current value in the current value set D is calculated by the Z-Score formula, Z=(XS) / W, and the abnormality of the current value is judged according to the preset outlier threshold.

6. The power data online monitoring system according to claim 5, characterized in that: The abnormality determination module determines the abnormality of the current value according to the preset outlier threshold, including: if the outlier is greater than the outlier threshold, the abnormality determination module determines that the abnormality of the current value is the real abnormality; If the outlier is less than or equal to the outlier threshold, the abnormality degree determination module determines that the abnormality degree of the current value is the occasional abnormality.

7. The power data online monitoring system according to claim 6, characterized in that: The abnormal data verification module records the start time when the current value is first determined to be abnormal and the end time when the current value is first determined to be non-abnormal after the start time, calculates the difference between the start time and the end time to obtain the abnormal duration, and compares the abnormal duration with the abnormal duration threshold to determine the actual abnormal degree of the current value.

8. The power data online monitoring system according to claim 7, characterized in that: The abnormal data verification module compares the abnormal duration with the abnormal duration threshold to determine the actual abnormal degree of the current value, including: if the abnormal duration is greater than the abnormal duration threshold, the abnormal data verification module determines that the actual abnormal degree of the current value is a real abnormality; If the abnormality duration is less than or equal to the abnormality duration threshold, the abnormality data verification module determines that the actual abnormality degree of the current value is an occasional abnormality.

9. The power data online monitoring system according to claim 8, characterized in that: The abnormal data verification module amends the determination result of the abnormality degree determination module, including: if the actual abnormality degree of the current value determined as a real abnormality by the abnormality degree determination module is an occasional abnormality, the abnormal data verification module amends the current value determined as a real abnormality by the abnormality degree determination module to an occasional abnormality, and the abnormal data verification module controls the abnormality degree determination module to reduce the outlier threshold; If the actual abnormality degree of the current value determined as an occasional abnormality by the abnormality degree determination module is a real abnormality, the abnormal data verification module corrects the current value determined as an occasional abnormality to a real abnormality, and the abnormal data verification module controls the abnormality degree determination module to increase the outlier threshold.

10. The power data online monitoring system according to claim 9, characterized in that: The abnormality degree determination module controls the abnormality detection module to adjust the outlier threshold according to the correction result, the decrease amount of the outlier threshold is positively correlated with the difference between the current value in the abnormal situation and the average value of the current value in a preset time period, and the increase amount of the outlier threshold is negatively correlated with the difference between the current value in the abnormal situation and the average value of the current value in a preset time period.

Images