Dynamic multi-dimensional data monitoring and early warning method for low-voltage distribution area

Abstract

The invention discloses a dynamic multi-dimensional data monitoring and early warning method for a low-voltage distribution area, and the method comprises the steps: collecting the multi-dimensional data of the low-voltage distribution area in real time, and dynamically transmitting the multi-dimensional data through a data flow frame; and carrying out real-time preprocessing on the transmitted multi-dimensional data, judging an abnormal condition of the multi-dimensional data of the low-voltage distribution area by adopting an abnormal data detection algorithm, setting an early warning strategy and reporting abnormal information. In the invention, the data stream framework is adopted to dynamically transmit the multi-dimensional data, so that the limitation that a traditional monitoring mode is difficult to realize quick response is improved, and the monitoring efficiency is improved; the abnormal condition of the low-voltage distribution area is judged by adopting an abnormal data detection algorithm, and an early warning strategy is set, so that the dynamic real-time monitoring of the abnormal data of the low-voltage distribution area is realized, and the reliability of monitoring and early warning of the low-voltage distribution area is improved.

Description

Technical Field

[0001] The present invention relates to the field of electrical engineering technology, and in particular to a dynamic multi-dimensional data monitoring and early warning method for a low-voltage distribution station area. Background Art

[0002] As an important part of the power system, low-voltage distribution substations are directly facing end users and undertake the key tasks of power supply and distribution. Low-voltage distribution substations are widely present in urban and rural areas, connecting the high-voltage main grid and user electrical equipment. However, due to problems such as load imbalance, equipment aging, and short-circuit failures, low-voltage distribution substations often face challenges in power supply reliability and safety.

[0003] Traditional low-voltage distribution substation monitoring methods mainly rely on regular manual inspections, which makes it difficult to achieve real-time monitoring of equipment status and electrical parameters, and cannot detect potential faults and issue early warnings in a timely manner, which can easily cause power outages or equipment damage. The current intelligent monitoring method usually installs intelligent sensors at key nodes in the distribution substation to achieve data collection and monitoring. However, the amount of data processed in the low-voltage distribution substation is huge, which makes it difficult for the existing low-voltage distribution substation monitoring method to meet the real-time data flow monitoring and rapid response requirements in complex power grid scenarios, thereby reducing the monitoring efficiency and reliability of the low-voltage distribution substation. Summary of the invention

[0004] The present invention provides a dynamic multi-dimensional data monitoring and early warning method for low-voltage distribution station areas, which is used to solve the technical problems of poor monitoring efficiency and reliability of existing low-voltage distribution station area monitoring methods.

[0005] The first aspect of the present invention provides a dynamic multi-dimensional data monitoring and early warning method for a low-voltage distribution station area, comprising:

[0006] Collect multi-dimensional data of low-voltage distribution substations in real time, and dynamically transmit the multi-dimensional data through a data stream framework;

[0007] The transmitted multi-dimensional data is pre-processed in real time, and the abnormal data detection algorithm is used to determine the abnormal situation of the multi-dimensional data in the low-voltage distribution station area, set up early warning strategies and report abnormal information.

[0008] Specifically, the multi-dimensional data of the low-voltage distribution station area specifically includes: environmental parameters and electrical parameters of the low-voltage distribution station area;

[0009] Among them, the environmental parameters of the low-voltage distribution station area include humidity, temperature and air pressure; the electrical parameters of the low-voltage distribution station area include line voltage, current, residual current and power.

[0010] Specifically, in the data stream framework, Kafka is used as the data source, and the Kafka data stream is introduced into Flink and parsed into a Java POJO object.

[0011] Specifically, the step of performing real-time preprocessing on the transmitted multidimensional data specifically includes:

[0012] The missing values ​​of the multidimensional data obtained by transmission are processed by interpolation method;

[0013] The data after missing value processing is processed by Kalman filtering method to remove noise and obtain smooth data;

[0014] The smoothed data is decomposed using a variational mode decomposition algorithm, and the mean, variance, maximum and minimum values ​​of each intrinsic mode function are calculated as characteristic parameters.

[0015] Specifically, the steps of real-time preprocessing of the transmitted multidimensional data, using an abnormal data detection algorithm to determine the abnormal situation of the multidimensional data in the low-voltage distribution station area, setting an early warning strategy and reporting abnormal information specifically include:

[0016] The Scikit-learn library is used to build and train an anomaly detection model based on historical data of low-voltage distribution stations;

[0017] Set up early warning strategies, load the model files of the trained anomaly detection models into Flink, determine the anomalies of the multi-dimensional data in the low-voltage distribution station area, and generate and report anomaly information.

[0018] Specifically, the steps of using the Scikit-learn library to build and train an anomaly detection model based on historical data of low-voltage distribution station areas specifically include:

[0019] The Scikit-learn library is used to build an anomaly detection model based on the historical data of the low-voltage distribution station area, and the random forest algorithm is used to train the anomaly detection model for abnormal situation detection to establish abnormal state decision-making, and a trained anomaly detection model is obtained.

[0020] Specifically, the steps of setting an early warning strategy, loading the model file of the trained anomaly detection model into Flink, judging the abnormal situation of the multi-dimensional data of the low-voltage distribution station area, and generating and reporting abnormal information specifically include:

[0021] Based on the historical electrical data of the low-voltage distribution substation area, a deep learning model is used to establish an early warning model for normal data in the low-voltage distribution substation area;

[0022] The model file of the trained anomaly detection model is loaded into Flink to monitor and identify in real time the abnormal behavior of the early warning mode of the multi-dimensional data of the low-voltage distribution station area that deviates from the normal data, and generate and report the abnormal information.

[0023] The second aspect of the present invention provides a dynamic multi-dimensional data monitoring and early warning system for low-voltage distribution station areas, comprising:

[0024] A multi-dimensional data processing unit, used for collecting multi-dimensional data of the low-voltage distribution station area in real time, and dynamically transmitting the multi-dimensional data through a data stream framework;

[0025] The abnormal information generation unit is used to perform real-time preprocessing on the transmitted multi-dimensional data, use the abnormal data detection algorithm to determine the abnormal situation of the multi-dimensional data in the low-voltage distribution station area, set the early warning strategy and report the abnormal information.

[0026] A third aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any of the dynamic multidimensional data monitoring and early warning methods described above are implemented.

[0027] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any of the dynamic multi-dimensional data monitoring and early warning methods described above are implemented.

[0028] It can be seen from the above technical solutions that the present invention has the following advantages:

[0029] The present invention provides a dynamic multi-dimensional data monitoring and early warning method for low-voltage distribution station areas, comprising: real-time collection of multi-dimensional data of low-voltage distribution station areas, and dynamic transmission of multi-dimensional data through a data flow framework; real-time pre-processing of the transmitted multi-dimensional data, using an abnormal data detection algorithm to determine the abnormal situation of the multi-dimensional data of the low-voltage distribution station area, setting an early warning strategy and reporting abnormal information.

[0030] In the present invention, a data flow framework is used to dynamically transmit multi-dimensional data, which improves the limitation of traditional monitoring methods that are difficult to achieve rapid response and thus improves monitoring efficiency; an abnormal data detection algorithm is used to determine the abnormal conditions of low-voltage distribution substations, and an early warning strategy is set to achieve dynamic real-time monitoring of abnormal data in low-voltage distribution substations, thereby improving the reliability of monitoring and early warning of low-voltage distribution substations, and thereby solving the technical problems of poor monitoring efficiency and reliability of existing low-voltage distribution substation monitoring methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0032] Figure 1 A flowchart of a method for dynamic multi-dimensional data monitoring and early warning of low-voltage distribution station areas provided by an embodiment of the present invention;

[0033] Figure 2 A flowchart of the steps of real-time preprocessing of the transmitted multidimensional data provided by an embodiment of the present invention;

[0034] Figure 3 A structural block diagram of a dynamic multi-dimensional data monitoring and early warning system for low-voltage distribution station areas provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The embodiment of the present invention provides a dynamic multi-dimensional data monitoring and early warning method for a low-voltage distribution station area, which is used to solve the technical problems of poor monitoring efficiency and reliability of the existing low-voltage distribution station area monitoring method.

[0036] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] See also Figure 1 to Figure 2 The first aspect of the present invention provides a dynamic multi-dimensional data monitoring and early warning method for a low-voltage distribution station area, comprising the following steps:

[0038] Step 101, collect multi-dimensional data of low-voltage distribution station area in real time, and dynamically transmit the multi-dimensional data through the data flow framework.

[0039] It should be noted that there is a need for timely data transmission and analysis before and after a fault occurs in a low-voltage distribution substation. Therefore, it is necessary to collect multi-dimensional data of the low-voltage distribution substation in real time, including environmental parameters such as humidity, temperature, air pressure, and electrical parameters such as line voltage, current, residual current, and power in the low-voltage distribution substation.

[0040] In order to improve the monitoring efficiency of the dynamic multi-dimensional data monitoring and early warning method and make the method more responsive, the present invention adopts a data flow framework to dynamically transmit multi-dimensional data. Specifically: the Apache Fink data flow framework is used to dynamically transmit multi-dimensional data. The Apache Fink data flow framework provides the ability to efficiently and accurately process continuous data streams, thereby improving the limitations of traditional multi-dimensional data monitoring methods for low-voltage distribution station areas that are difficult to achieve rapid response.

[0041] In the data stream framework, Kafka is used as the data source, and the Kafka data stream is introduced into Flink and parsed into Java POJO objects. Kafka is a distributed stream platform with high throughput, persistent storage, and multiple copies.

[0042] Step 102, pre-process the transmitted multi-dimensional data in real time, use an abnormal data detection algorithm to determine the abnormal situation of the multi-dimensional data in the low-voltage distribution station area, set an early warning strategy and report the abnormal information.

[0043] See also Figure 2 , the step of performing real-time preprocessing on the transmitted multidimensional data specifically includes the following steps:

[0044] Step 201 , performing missing value processing on the transmitted multidimensional data by using an interpolation method; the interpolation method can effectively process the missing values ​​in the multidimensional data, thereby ensuring the integrity of the multidimensional data.

[0045] Step 202, processing the data after missing value processing by the Kalman filtering method to remove noise and obtain smooth data; the Kalman filtering method can effectively reduce noise interference in data processing and improve the accuracy and stability of data.

[0046] Step 203, using the variational mode decomposition algorithm to decompose the smoothed data, and calculating the mean, variance, maximum and minimum of each intrinsic mode function as characteristic parameters. The intrinsic mode function is the decomposition result obtained by decomposing the smoothed data using the variational mode decomposition algorithm.

[0047] It is understandable that the interpolation method, Kalman filtering method and variational mode decomposition algorithm are used to process the multidimensional data obtained by transmission, so as to improve the processing accuracy and stability of the multidimensional data, and at the same time provide more representative feature parameters for subsequent abnormal situation detection and other operations, optimize data features, and thus improve the reliability of the monitoring and early warning method. Among them, the interpolation method, Kalman filtering method and variational mode decomposition algorithm are all existing technologies and will not be described in detail here.

[0048] Among them, the steps of using an abnormal data detection algorithm to judge the abnormal situation of multi-dimensional data in the low-voltage distribution station area, setting an early warning strategy and reporting abnormal information specifically include the following steps:

[0049] Step 301, using the Scikit-learn library to build and train an anomaly detection model based on historical data of low voltage distribution station areas.

[0050] In this step, the Scikit-learn library is used to build an anomaly detection model based on the historical data of the low-voltage distribution station area, and the random forest algorithm is used to train the anomaly detection model for abnormal situation detection to establish abnormal state decision-making, and obtain a trained anomaly detection model.

[0051] It should be noted that the historical data of the low-voltage distribution substation area needs to be preprocessed to obtain the characteristic parameters of the historical data and convert them into characteristic vectors to build an anomaly detection model. Among them, the historical data of the low-voltage distribution substation area includes historical environmental data and historical electrical data. The anomaly detection model is used to establish a decision boundary to distinguish between normal data and abnormal data in the low-voltage distribution substation area, and improve the accuracy of monitoring and early warning.

[0052] Step 302, set an early warning strategy, load the model file of the trained anomaly detection model into Flink, determine the abnormal situation of the multi-dimensional data of the low-voltage distribution station area, and generate and report abnormal information.

[0053] In this step, based on the historical electrical data of the low-voltage distribution station area, a deep learning model is used to establish an early warning mode for normal data in the low-voltage distribution station area. The model file of the trained anomaly detection model is loaded into Flink to monitor and identify in real time the abnormal behavior of the multi-dimensional data of the low-voltage distribution station area that deviates from the early warning mode of normal data, generate and report abnormal information, and improve the reliability of abnormal situation detection in the low-voltage distribution station area.

[0054] In actual applications, once the multi-dimensional data of the low-voltage distribution station is monitored and identified as abnormal, abnormal information can be sent to remote staff through SMS, email, mobile phone applications and other channels, thereby reminding operation and maintenance personnel to inspect and maintain the low-voltage distribution station.

[0055] In the present invention, the Scikit-learn library is used to build an anomaly detection model based on historical data, and a deep learning model is used to realize dynamic real-time monitoring of abnormal data, thereby improving the monitoring efficiency and reliability of low-voltage distribution station area monitoring and early warning.

[0056] See also Figure 3 The present invention also provides a dynamic multi-dimensional data monitoring and early warning system for low-voltage distribution station areas, the system comprising:

[0057] The multi-dimensional data processing unit 401 is used to collect multi-dimensional data of the low-voltage distribution station area in real time and dynamically transmit the multi-dimensional data through the data flow framework;

[0058] The abnormal information generating unit 402 is used to perform real-time preprocessing on the transmitted multi-dimensional data, use an abnormal data detection algorithm to determine the abnormal situation of the multi-dimensional data of the low-voltage distribution station area, set an early warning strategy and report abnormal information.

[0059] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any of the above dynamic multi-dimensional data monitoring and early warning methods are implemented.

[0060] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above dynamic multi-dimensional data monitoring and early warning methods are implemented.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0062] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0063] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0064] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0065] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0066] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic multi-dimensional data monitoring and early warning method for low-voltage distribution station areas, characterized in that: include: Collect multi-dimensional data of low-voltage distribution substations in real time, and dynamically transmit the multi-dimensional data through a data stream framework; The transmitted multi-dimensional data is pre-processed in real time, and the abnormal data detection algorithm is used to determine the abnormal situation of the multi-dimensional data in the low-voltage distribution station area, set up early warning strategies and report abnormal information.

2. The dynamic multi-dimensional data monitoring and early warning method according to claim 1 is characterized in that: The multi-dimensional data of the low-voltage distribution station area specifically includes: environmental parameters and electrical parameters of the low-voltage distribution station area; Among them, the environmental parameters of the low-voltage distribution station area include humidity, temperature and air pressure; the electrical parameters of the low-voltage distribution station area include line voltage, current, residual current and power.

3. The dynamic multi-dimensional data monitoring and early warning method according to claim 1 is characterized in that: In the data stream framework, Kafka is used as the data source, and the Kafka data stream is introduced into Flink and parsed into Java POJO objects.

4. The dynamic multi-dimensional data monitoring and early warning method according to claim 1 is characterized in that: The step of performing real-time preprocessing on the transmitted multidimensional data specifically includes: The missing values ​​of the multidimensional data obtained by transmission are processed by interpolation method; The data after missing value processing is processed by Kalman filtering method to remove noise and obtain smooth data; The smoothed data is decomposed using a variational mode decomposition algorithm, and the mean, variance, maximum and minimum values ​​of each intrinsic mode function are calculated as characteristic parameters.

5. The dynamic multi-dimensional data monitoring and early warning method according to claim 3 is characterized in that: The steps of real-time preprocessing of the transmitted multidimensional data, using an abnormal data detection algorithm to determine the abnormal situation of the multidimensional data in the low-voltage distribution station area, setting an early warning strategy and reporting abnormal information specifically include: The Scikit-learn library is used to build and train an anomaly detection model based on historical data of low-voltage distribution stations; Set up early warning strategies, load the model files of the trained anomaly detection models into Flink, determine the anomalies of the multi-dimensional data in the low-voltage distribution station area, and generate and report anomaly information.

6. The dynamic multi-dimensional data monitoring and early warning method according to claim 5 is characterized in that: The steps of using the Scikit-learn library to build and train an anomaly detection model based on historical data of low-voltage distribution station areas specifically include: The Scikit-learn library is used to build an anomaly detection model based on the historical data of the low-voltage distribution station area, and the random forest algorithm is used to train the anomaly detection model for abnormal situation detection to establish abnormal state decision-making, and a trained anomaly detection model is obtained.

7. The dynamic multi-dimensional data monitoring and early warning method according to claim 5 is characterized in that: The steps of setting an early warning strategy, loading the model file of the trained anomaly detection model into Flink, judging the abnormal situation of the multi-dimensional data of the low-voltage distribution station area, and generating and reporting abnormal information specifically include: Based on the historical electrical data of the low-voltage distribution substation area, a deep learning model is used to establish an early warning model for normal data in the low-voltage distribution substation area; The model file of the trained anomaly detection model is loaded into Flink to monitor and identify in real time the abnormal behavior of the early warning mode of the multi-dimensional data of the low-voltage distribution station area that deviates from the normal data, and generate and report the abnormal information.

8. A dynamic multi-dimensional data monitoring and early warning system for low-voltage distribution substations, characterized in that: include: A multi-dimensional data processing unit, used for collecting multi-dimensional data of the low-voltage distribution station area in real time, and dynamically transmitting the multi-dimensional data through a data stream framework; The abnormal information generation unit is used to perform real-time preprocessing on the transmitted multi-dimensional data, use the abnormal data detection algorithm to determine the abnormal situation of the multi-dimensional data in the low-voltage distribution station area, set the early warning strategy and report the abnormal information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the dynamic multi-dimensional data monitoring and early warning method as described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the dynamic multi-dimensional data monitoring and early warning method as described in any one of claims 1 to 7 are implemented.

Images