CN118138492A - Digital twinning-based power private network monitoring method, system, equipment and medium - Google Patents

Abstract

A method, a system, equipment and a medium for monitoring a power private network based on digital twinning comprise the steps of determining a communication network quality index to be monitored and collecting corresponding data in real time; the method comprises the steps that a power private network monitoring digital twin body is utilized to carry out physical operation on collected communication network quality data, real-time calculation physical quantity data are obtained, the real-time calculation physical quantity data are compared with a set threshold value, and the digital twin body is corrected in a first time interval; determining and correcting the dynamic error of the power monitoring physical entity in a second time interval according to the corrected digital twin body, and predicting the state of the power monitoring physical entity in a third time interval according to the corrected dynamic error of the digital twin body and the power monitoring physical entity; generating early warning information according to preset early warning rules, displaying the early warning information in a visual mode, and displaying the real-time state and the change trend of the network quality. The early warning effect of the invention can change along with the use time, and the monitoring, analysis and evaluation of the point-surface combination are realized.

Description

Digital twinning-based power private network monitoring method, system, equipment and medium

Technical Field

The invention belongs to the technical field of network communication, and particularly relates to a digital twinning-based power private network monitoring method, a system, equipment and a medium.

Background

The power system uses 230MHz to establish a power private network or a power 5G private network. In the initial stage of the construction of the power private network, in order to ensure the performance and stability of the network constructed by the power private network, network access evaluation applied to the power industry needs to be carried out, and whether the network meets the network access requirement is verified. And (3) carrying out network power simulation test to verify whether the network reaches the power scene application standard. The PC version test software is externally connected with a 5G terminal, so that comprehensive evaluation and test can be performed on the quality, the performance and the like of the power private network.

After the electric power 5G private network is built and used, as the stability and the reliability of a new network cannot be guaranteed, the electric power private network needs to be monitored, analyzed and evaluated in a point-to-surface mode, and meanwhile, the electric power 5G private network has the characteristics of automatic test, data aggregation, data management and data post-processing, the scene network state of each electric power private network and the terminal state of an electric power communication module are monitored in a normalized mode, and the abnormal network performance is found to trigger AI intelligent early warning and abnormal problem data acquisition.

In order to realize the monitoring and early warning of the power private network, the following methods can be adopted:

(1) Data acquisition and transmission: the monitoring system of the power private network is established, network related data such as 5G network parameters, network time delay and speed are collected, and the collected data can be transmitted to a monitoring center in a wired or wireless mode.

(2) Data storage and processing: and a reliable database system is established in the monitoring center and is used for storing the power data from each node, and the collected data is processed, analyzed and stored in real time so as to facilitate subsequent monitoring and early warning analysis.

(3) Monitoring and analysis: and the power data is monitored and analyzed in real time by using a data analysis algorithm and professional monitoring software. By setting proper threshold parameters and rules, the data are compared and analyzed in real time to identify possible abnormal situations or faults.

(4) Early warning and alarming: when the monitoring system detects that an abnormality or a fault occurs in the power system, early warning information or an alarm signal is timely sent out. The early warning information can be sent to related personnel in a short message, mail, app pushing mode and the like, so that the related personnel can take measures in time for processing.

(5) Data visualization and display: and displaying the monitored power data to users and management staff in a visual mode. The information such as the state, parameter change and the like of each node in the power private network can be displayed in real time by utilizing technologies such as an instrument panel, a graph, a Geographic Information System (GIS) and the like, so that comprehensive monitoring and analysis can be performed.

(6) Fault diagnosis and maintenance: and diagnosing and maintaining the equipment or the power line with faults in time. When a fault or abnormality occurs, the relevant algorithm in the monitoring system can help to locate the specific position of the problem, provide a reference to maintenance personnel, and accelerate the fault recovery process.

(7) Periodic maintenance and upgrades: and the power monitoring system is checked and maintained regularly, so that the normal operation of equipment and software is ensured. Meanwhile, according to business requirements and technical development, upgrading and optimizing of the system are carried out, so that accuracy and effect of monitoring and early warning are improved.

The existing method for monitoring and early warning the quality of the communication network of the power private network is difficult to realize accurate monitoring and warning on equipment states, network quality, equipment warning, end-to-end time delay between scenes, remote control and the like in all scenes, the early warning effect is inaccurate along with the use time, and the visualized remote monitoring management of the point-to-surface combination of the power private network is difficult to realize.

Disclosure of Invention

Aiming at the problems in the prior art, the invention provides a digital twin-based power private network monitoring method, a system, equipment and a medium, which enable the early warning effect to be changed along with the use time and to be visually displayed by continuously changing and improving the acquired data and the requirements of users, so as to realize the monitoring, analysis and evaluation of the point-to-surface combination.

In order to achieve the above purpose, the present invention has the following technical scheme:

in a first aspect, a method for monitoring a private power grid based on digital twinning is provided, including:

determining the communication network quality index to be monitored, and collecting data corresponding to the communication network quality index in real time;

Carrying out physical operation on the collected data corresponding to the communication network quality index by utilizing a pre-established power private network monitoring digital twin body to obtain real-time calculated physical quantity data, comparing the real-time calculated physical quantity data with a set threshold value, and correcting the power private network monitoring digital twin body in a first time interval;

Determining and correcting the dynamic error of the power monitoring physical entity in a second time interval according to the corrected power private network monitoring digital twin body, and predicting the state of the power monitoring physical entity in a third time interval according to the corrected power private network monitoring digital twin body and the dynamic error of the power monitoring physical entity;

generating early warning information according to the dynamic error and the predicted state of the power monitoring physical entity and preset early warning rules, displaying in a visual mode, and displaying the real-time state and the change trend of the network quality.

As a preferred scheme, when the communication network quality index to be monitored is determined, and the data corresponding to the communication network quality index is collected in real time, the communication network quality index comprises delay, packet loss rate and bandwidth utilization rate, and the data corresponding to the communication network quality index is collected in real time by arranging monitoring equipment in the power private network.

As a preferable scheme, in the step of correcting the power private network monitoring digital twin body in a first time interval by performing physical operation on the collected data corresponding to the communication network quality index by using the pre-established power private network monitoring digital twin body to obtain real-time calculated physical quantity data and comparing the real-time calculated physical quantity data with a set threshold value, the power private network monitoring digital twin body comprises a physical model and a rule model;

the physical model is used for carrying out physical operation on the collected data corresponding to the communication network quality index to obtain real-time calculated physical quantity data, wherein the real-time calculated physical quantity data comprises an average value, a maximum value and a percentile corresponding to the communication network quality index; the rule model is a model formed by preset quality index data thresholds of all communication networks;

And correcting the power private network monitoring digital twin body in a first time interval by comparing the real-time calculated physical quantity data output by the physical model with a threshold value in the rule model.

As a preferred solution, the step of correcting the power grid monitoring digital twin in the first time interval by comparing the real-time calculated physical quantity data output by the physical model with the threshold value in the rule model includes:

Determining an independent variable sequence Y and an independent variable sequence X of the association analysis according to the requirements according to the following formula:

Y＝[y(1),y(2)…,y(n)]；

Wherein l represents the number of samples; n is the number of features;

the data x _i k in each dependent variable sequence is averaged according to the following formula to obtain

Where x _i (k) represents the kth eigenvalue of the ith sample of the dependent variable sequence; Is the mean of the ith sample;

solving the independent variable y (k) and the independent variable after the averaging process according to the following formula Correlation coefficient value μ _i between:

In the method, in the process of the invention, Η is the resolution coefficient;

The relevance value r _i of all the relevance coefficients of each dependent variable sequence is calculated according to the following formula:

and judging the tightness degree of the connection by calculating the similarity degree between the independent variables and the dependent variables, and determining the influence factors.

As a preferred solution, in the step of generating early warning information according to the dynamic error and the predicted state of the electric power monitoring physical entity and according to the preset early warning rule, displaying the early warning information in a visual manner, and displaying the real-time state and the variation trend of the network quality, the early warning information is notified in a manner of pushing a short message, a mail or an App, and the visual manner includes displaying a dashboard, a chart or a report.

As a preferable scheme, the method also comprises the steps of positioning the fault position according to the early warning information and the real-time state and the change trend of the network quality when the network fault or the communication interruption occurs, and diagnosing and repairing the fault.

As a preferred solution, the method further includes using a pre-established digital machine learning model to monitor the power private network, where the establishing process of the digital machine learning model includes:

carrying out parameter estimation and optimization on the digital machine learning model, and adjusting the parameters of the model through fitting with real data;

Verifying and calibrating the established digital machine learning model by using historical data or test data;

Connecting real-time data of a physical entity with a digital machine learning model, and transmitting and updating the real-time data;

Establishing a user interaction interface, and displaying the result and analysis of the digital machine learning model to a user;

real-time monitoring and optimizing the physical entity through a digital machine learning model;

The digital machine learning model is improved and updated.

In a second aspect, a digital twinning-based power grid monitoring system is provided, comprising:

The data acquisition module is used for determining the communication network quality index to be monitored and acquiring data corresponding to the communication network quality index in real time;

The digital twin body correction module is used for carrying out physical operation on the collected data corresponding to the communication network quality index by utilizing the pre-established power private network monitoring digital twin body to obtain real-time calculated physical quantity data, comparing the real-time calculated physical quantity data with a set threshold value, and correcting the power private network monitoring digital twin body in a first time interval;

The physical entity state prediction module is used for determining and correcting the dynamic error of the power monitoring physical entity in a second time interval according to the corrected power private network monitoring digital twin body, and predicting the state of the power monitoring physical entity in a third time interval according to the corrected power private network monitoring digital twin body and the dynamic error of the power monitoring physical entity;

And the early warning module is used for generating early warning information according to the dynamic error of the power monitoring physical entity and the predicted state and preset early warning rules, displaying the early warning information in a visual mode and displaying the real-time state and the change trend of the network quality.

As a preferable scheme, the digital twin body modification module pre-established power private network monitoring digital twin body comprises a physical model and a rule model;

the physical model is used for carrying out physical operation on the collected data corresponding to the communication network quality index to obtain real-time calculated physical quantity data, wherein the real-time calculated physical quantity data comprises an average value, a maximum value and a percentile corresponding to the communication network quality index; the rule model is a model formed by preset quality index data thresholds of all communication networks;

And correcting the power private network monitoring digital twin body in a first time interval by comparing the real-time calculated physical quantity data output by the physical model with a threshold value in the rule model.

As a preferable scheme, the digital twin modification module pre-establishes a power private network monitoring digital twin to determine an independent variable sequence Y and an independent variable sequence X of the correlation analysis according to the requirement according to the following formula:

Y＝[y(1),y(2)…,y(n)]；

Wherein l represents the number of samples; n is the number of features;

the data x _i k in each dependent variable sequence is averaged according to the following formula to obtain

Where x _i (k) represents the kth eigenvalue of the ith sample of the dependent variable sequence; Is the mean of the ith sample;

solving the independent variable y (k) and the independent variable after the averaging process according to the following formula Correlation coefficient value μ _i between:

In the method, in the process of the invention, Η is the resolution coefficient;

The relevance value r _i of all the relevance coefficients of each dependent variable sequence is calculated according to the following formula:

and judging the tightness degree of the connection by calculating the similarity degree between the independent variables and the dependent variables, and determining the influence factors.

The system also comprises a fault processing module, which is used for diagnosing and repairing the fault when the network fault or communication interruption occurs according to the early warning information, the real-time state of the network quality and the change trend to position the fault.

As a preferred solution, the system further includes a digital machine learning model training module, configured to perform power private network monitoring by using a pre-established digital machine learning model, where the process of establishing the digital machine learning model includes:

carrying out parameter estimation and optimization on the digital machine learning model, and adjusting the parameters of the model through fitting with real data;

Verifying and calibrating the established digital machine learning model by using historical data or test data;

Connecting real-time data of a physical entity with a digital machine learning model, and transmitting and updating the real-time data;

Establishing a user interaction interface, and displaying the result and analysis of the digital machine learning model to a user;

real-time monitoring and optimizing the physical entity through a digital machine learning model;

The digital machine learning model is improved and updated.

In a third aspect, an electronic device is provided, comprising a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement the digital twinning-based power grid monitoring method.

In a fourth aspect, a computer readable storage medium is provided, the computer readable storage medium storing at least one instruction that when executed by a processor implements the digital twinning-based power grid monitoring method.

Compared with the prior art, the first aspect of the invention has at least the following beneficial effects:

Digital twinning is a technique for representing physical objects by a software model, which can be used to model and analyze the physical object's behavior and performance in the real world. According to the method, the power private network monitoring digital twin body is established to perform physical operation on the collected data corresponding to the communication network quality index, real-time calculated physical quantity data are obtained, the calculated physical quantity data are compared with a set threshold value, and the power private network monitoring digital twin body is corrected in a first time interval. And then determining and correcting the dynamic errors of the power monitoring physical entity in a second time interval according to the corrected power private network monitoring digital twin body, and predicting the state of the power monitoring physical entity in a third time interval according to the corrected power private network monitoring digital twin body and the dynamic errors of the power monitoring physical entity. And finally, generating early warning information according to the dynamic error and the predicted state of the power monitoring physical entity and preset early warning rules, displaying in a visual mode, and displaying the real-time state and the change trend of the network quality. The invention carries out visual display by continuously changing and improving the acquired data and the demands of users, and because the purpose of visual display is to carry out more convenient remote monitoring and management on a power system, the specific monitoring and management objects comprise equipment states, network quality, equipment alarms, end-to-end time delay between scenes and remote control for accurate monitoring and alarm under each scene, therefore, the invention carries out point-to-surface combined monitoring, analysis and evaluation on the basis of the framework of the whole digital twin visual model, carries out statistics of detection results into the next monitoring, changes the initial data model of the monitoring, enables the early warning effect to be changed along with the use time, ensures the accuracy and realizes the visual remote monitoring management of the point-to-surface combination of the power private network.

It will be appreciated that the advantages of the second to fourth aspects may be found in the relevant description of the first aspect and are not repeated here.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flow chart of a method for monitoring a private power network based on digital twinning in the embodiment of the invention.

Fig. 2 is a block diagram of a power private network monitoring system based on digital twinning in the embodiment of the invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

The power private network communication network quality monitoring and early warning is quite important in the construction and later maintenance of the power private network, and is specifically embodied in the following aspects:

(1) Ensuring the safe and stable operation of the power system: the power private network is an infrastructure for the operation of a power system and bears the functions of power information transmission, control, protection and the like. Good communication network quality is critical to ensuring safe and stable operation of the power system. By monitoring the quality of the communication network, the problems of communication faults, delay or packet loss and the like can be found in time, corresponding measures are taken for repairing, and the influence of communication interruption and faults on a power system is reduced.

(2) Support remote monitoring and management: the power private network communication network quality monitoring and early warning can support the remote monitoring and management of power equipment, circuits and stations. By acquiring real-time communication network quality data, it is possible to judge whether data transmission is normal or not, and the feasibility of remote operation and maintenance of the apparatus. This helps to improve the operation and maintenance efficiency of the power system, reduce labor costs, and timely respond to abnormal conditions.

(3) And (3) improving the response speed of the power system: the quality monitoring and early warning of the communication network of the power private network can help to find problems such as communication interruption and packet loss as soon as possible, reduce communication delay and improve the response speed of the power system. During operation of the power system, some operations require real-time response, such as fault detection, input and output loads, and the like. Through timely early warning, the interference to the system operation can be reduced, and the fault positioning and repairing time can be shortened.

(4) Improving the maintenance mode of the power equipment: the power private network communication network quality monitoring and early warning can provide real-time monitoring for the running state of the power equipment, and the working condition and the health condition of the equipment are known. Through monitoring data analysis, a more scientific and reasonable equipment maintenance plan can be formulated, and the maintenance efficiency and the equipment utilization rate are improved. Unnecessary maintenance work is avoided, and operation and maintenance cost is reduced.

In summary, the quality monitoring and early warning of the communication network of the power private network has important significance for guaranteeing the stable operation of the power system, supporting remote monitoring and management, improving response speed and improving equipment maintenance mode. By timely monitoring and early warning, communication faults can be found and processed early, the influence on a power system is reduced to the greatest extent, and the reliability and safety of the system are improved.

In the related art, for example, chinese patent CN112910730a discloses a method for detecting network speed, a network problem searching method, a method for assigning workers to repair problems, a method for transmitting information in a backup unit to a storage module by an administrator, and a communication network real-time early warning monitoring method, which are limited by technology, the method proposed in the document is "disposable" for early warning of quality monitoring of a communication network of a power grid, which is not different for different areas where the power grid is located, and is not used for monitoring, analyzing and evaluating point-to-surface combination of the power grid, and is not used for carrying out statistics of detection results into the next monitoring, and is not overlapped with the initial data model of the monitoring, so that early warning effect is inaccurate with time of use.

Currently, networks have become a very important part of people's life and work. The detection of the network quality is an important basis for judging the network optimization effect and improving the user satisfaction.

With the development of smart grids, the requirements of each power information system on the quality of the power network are higher and higher, and the requirements on fault positioning means and solving time are higher and higher. The existing power information communication network management system has the following defects:

1. the network configuration is complicated, and time and labor are wasted; 2. lack of monitoring methods for network performance and quality; 3. the lack of monitoring means for network traffic cannot give accurate prognosis to the state of the overall network.

For another example, a method proposed in chinese patent application CN108011757a, an intelligent network management method and apparatus for power industry, includes obtaining network operation data, and generating a network operation data model; the network operation data model converts network data into equipment identification data and transmits the equipment identification data to specific network equipment; monitoring the running state of each network communication link in real time and uploading the running state to the network running data model; the network operation data model determines an interrupted communication link according to the network operation condition and resumes the interrupted communication link according to the network topology condition; the network operation data model converts the network data into equipment identification data and transmits the equipment identification data to the specific network equipment, and the network operation data model converts the network data into the equipment identification data and transmits the equipment identification data to the specific network equipment through a specified IP address.

The existing method for monitoring the quality of the communication network of the power private network is difficult to realize accurate monitoring and alarming of equipment states, network quality, equipment alarming, end-to-end time delay between scenes, remote control and the like in each scene, and is further difficult to present the condition of monitoring each scene in real time, so that the visualized remote monitoring management of the point-to-surface combination of the power private network is difficult to realize.

Referring to fig. 1, the method for monitoring a private power grid based on digital twinning in an embodiment of the invention includes the following steps:

S1, determining and collecting monitoring indexes: determining communication network quality indexes such as delay (time delay), packet loss rate, bandwidth utilization rate and the like which need to be monitored, wherein the indexes can be selected according to specific requirements and service requirements, and then arranging monitoring equipment at a proper position in an electric private network, wherein the equipment can acquire communication network quality data in real time, and then acquiring the communication network quality data by using the monitoring equipment and storing the communication network quality data in a reliable database system;

S2, constructing a digital twin body for monitoring the power private network: the digital twin body comprises a physical model and a rule model, wherein the physical model is used for carrying out physical operation on collected real-time data to obtain real-time calculated physical quantity data, specifically calculating statistics such as average value, maximum value and percentile of each index, the rule model is a model formed by preset physical quantity thresholds in a power monitoring system, when the power monitoring system carries out data processing, the real-time data of the physical model and the thresholds set by the rule model are compared, and the digital twin body is corrected in a first time interval;

s3, monitoring error analysis of multiple time periods: determining and correcting the dynamic error of the power monitoring physical entity in a second time interval according to the error between the real-time output signals of the power monitoring physical entity and the digital twin body, and predicting the state of the power monitoring physical entity in a third time interval according to the dynamic error of the digital twin body and the physical entity of the power transformer;

S4, early warning processing: setting corresponding early warning rules according to the prediction results and the service demands, triggering an early warning mechanism to generate early warning information when the monitored data exceeds a threshold value or abnormal conditions occur, and timely sending the early warning information to related personnel in a notification mode of short messages, mails and App pushing, so that the monitored data abnormality can be rapidly perceived by the related personnel and corresponding measures can be taken;

S5, visual display: displaying the monitoring result of the communication network quality to users and management staff in a visual mode such as a dashboard, a chart or a report, and displaying the real-time state and the change trend of the communication network quality;

S6, fault processing: when network faults or communication interruption occurs, timely fault diagnosis and maintenance are carried out according to early warning information, the specific position of the problem is positioned by means of monitoring data and analysis results, the fault recovery process is accelerated, and the quality monitoring system of the power private network communication network is regularly maintained and optimized, so that the normal operation of equipment and the accuracy of data are ensured. For example, updating the firmware of the monitoring device, closely focusing on system performance, etc.

S7, creating a digital machine learning model for training: the digital machine learning model is built by utilizing a mathematical modeling technology based on collected data by collecting data such as full network test data, ping delay test, remote control delay, uplink and downlink rates, wireless coverage quality and the like.

In one possible embodiment, the monitoring device deployed at a suitable location in the private power network in step S1 is a network traffic analyzer, a network monitoring tool or sensor, or the like.

In one possible implementation, the data collection in step S1 may be implemented by technologies such as network packet capturing, traffic monitoring, and the like.

In one possible implementation, step S2 uses association analysis to screen the power monitoring influencing factors in the data processing process, and the basic idea of the association analysis is to determine the tightness of the association by calculating the similarity between the independent variable and the dependent variable, including the following steps:

a1, determining an independent variable sequence Y and an independent variable sequence X of the association analysis according to requirements, wherein the independent variable sequence Y and the independent variable sequence X are respectively shown in the following formulas:

Y＝[y(1),y(2)…,y(n)]

Wherein: l represents the number of samples; n is the number of features;

a2, carrying out averaging treatment on the data x _i k in each dependent variable sequence to obtain The following formula is shown:

Wherein: x _i (k) represents the ith sample, the kth eigenvalue, of the dependent variable sequence; Is the mean of the ith sample;

a3, solving the independent variable y (k) and the independent variable after the averaging process The correlation coefficient value mu _i between the two is shown as the following formula:

Wherein, Η is the resolution factor, typically 0.5;

a4, calculating the average value of all the association coefficients of each dependent variable sequence, namely the association degree r _i, wherein the specific calculation formula is as follows:

In one possible implementation, when the digital machine learning model is created for training in step S7, the digital machine learning model is created by using a convolutional neural network algorithm, specifically: the method is characterized in that a basic three-dimensional child node matrix is input, a plurality of nodes (unit node matrix) of a convolution layer are obtained through continuous cyclic weighting, the function of the convolution layer is to conduct deep analysis on each small node, so that higher characteristics of a picture are extracted, the picture enters a pooling layer, the depth of the three-dimensional matrix cannot be changed by the pooling layer, the function of the pooling layer is to reduce the matrix, so that parameters of a network are reduced, and then the picture enters a full-connection layer: finally, the probability distribution of the current sample belonging to different types is obtained through a Softmax layer and classification is completed as the function of the fully connected neural network.

Furthermore, a digital machine learning model is established by utilizing a mathematical modeling technology based on the collected data by collecting data such as full network test data, ping delay test, remote control delay, uplink and downlink rates, wireless coverage quality and the like.

Model parameter estimation and optimization: and carrying out parameter estimation and optimization on the model, and adjusting the parameters of the model through fitting with real data. This may be implemented in conjunction with parameter estimation algorithms, parameter optimization algorithms, etc.

Model verification and calibration: and verifying and calibrating the established digital model by using historical data or test data, and evaluating the accuracy and reliability of the model. Modifications and adjustments to the model may be made if desired.

Integrating real-time data: and connecting the real-time data of the physical entity with the digital model to realize real-time data transmission and updating. Real-time data may be input into the digital model using sensors, data acquisition systems, and the like.

Establishing an interactive interface: and establishing a user interaction interface, and displaying the result and analysis of the digital twin model to a user through a graphical interface or other forms.

Real-time monitoring and optimizing: and real-time monitoring and optimizing the physical entity through the digital twin model. And according to the model result and the early warning mechanism, the problems are identified in time and corresponding measures are taken, so that the stability and the efficiency of the system are improved.

Continuous improvement and update: the digital twin model is continually improved and updated, and based on feedback data and user demand, the model is revised or new functions and features are added.

According to the embodiment of the invention, the data such as full network test data, ping delay test, remote control delay, uplink and downlink speed, wireless coverage quality and the like are collected, a digital machine learning model is established by utilizing a mathematical modeling technology based on the collected data, and parameters of the model are estimated and optimized, and are adjusted by fitting with real data. The method can be realized by matching with a parameter estimation algorithm, a parameter optimization algorithm and the like, and meanwhile, historical data or test data are used for verifying and calibrating the established digital model, so that the accuracy and reliability of the model are evaluated. If necessary, the model can be modified and adjusted, and the real-time data of the physical entity can be connected with the digital model to realize real-time data transmission and updating. Real-time data can be input into the digital model by using devices such as a sensor, a data acquisition system and the like, so that real-time monitoring of the data is realized.

In the embodiment of the invention, the power monitoring influence factors are screened by adopting the association analysis in the data processing process, and the basic idea of the association analysis is to judge the tightness degree of the association by calculating the similarity degree between the independent variable and the dependent variable, so that the whole power monitoring data processing is more fit with the actual processing, and the monitoring and predicting results have more reference significance.

The embodiment of the invention greatly reduces the dynamic error of actual power detection by adopting different monitoring processes of multiple time periods.

Referring to fig. 2, an embodiment of the present invention is a digital twin-based power private network monitoring system, including:

The data acquisition module is used for determining the communication network quality index to be monitored and acquiring data corresponding to the communication network quality index in real time;

The digital twin body correction module is used for carrying out physical operation on the collected data corresponding to the communication network quality index by utilizing the pre-established power private network monitoring digital twin body to obtain real-time calculated physical quantity data, comparing the real-time calculated physical quantity data with a set threshold value, and correcting the power private network monitoring digital twin body in a first time interval;

The physical entity state prediction module is used for determining and correcting the dynamic error of the power monitoring physical entity in a second time interval according to the corrected power private network monitoring digital twin body, and predicting the state of the power monitoring physical entity in a third time interval according to the corrected power private network monitoring digital twin body and the dynamic error of the power monitoring physical entity;

And the early warning module is used for generating early warning information according to the dynamic error of the power monitoring physical entity and the predicted state and preset early warning rules, displaying the early warning information in a visual mode and displaying the real-time state and the change trend of the network quality.

In one possible implementation, the power private network monitoring digital twin established in advance by the digital twin modification module comprises a physical model and a rule model; the physical model is used for carrying out physical operation on the collected data corresponding to the communication network quality index to obtain real-time calculated physical quantity data, wherein the real-time calculated physical quantity data comprises an average value, a maximum value and a percentile corresponding to the communication network quality index; the rule model is a model formed by preset quality index data thresholds of all communication networks; and correcting the power private network monitoring digital twin body in a first time interval by comparing the real-time calculated physical quantity data output by the physical model with a threshold value in the rule model.

In one possible implementation, the digital twin modification module pre-established power private network monitoring digital twin determines the independent variable sequence Y and the dependent variable sequence X of the correlation analysis according to the requirements according to the following formula:

Y＝[y(1),y(2)…,y(n)]；

Wherein l represents the number of samples; n is the number of features;

the data x _i k in each dependent variable sequence is averaged according to the following formula to obtain

Where x _i (k) represents the kth eigenvalue of the ith sample of the dependent variable sequence; Is the mean of the ith sample;

solving the independent variable y (k) and the independent variable after the averaging process according to the following formula Correlation coefficient value μ _i between:

In the method, in the process of the invention, Η is the resolution coefficient;

The relevance value r _i of all the relevance coefficients of each dependent variable sequence is calculated according to the following formula:

and judging the tightness degree of the connection by calculating the similarity degree between the independent variables and the dependent variables, and determining the influence factors.

In one possible implementation manner, the system further comprises a fault processing module, which is used for diagnosing and repairing the fault when the network fault or the communication interruption occurs, and positioning the fault position according to the early warning information and the real-time state and the change trend of the network quality.

In one possible implementation manner, the system further comprises a digital machine learning model training module, configured to perform power private network monitoring by using a pre-established digital machine learning model, wherein the process of establishing the digital machine learning model includes:

carrying out parameter estimation and optimization on the digital machine learning model, and adjusting the parameters of the model through fitting with real data;

Verifying and calibrating the established digital machine learning model by using historical data or test data;

Connecting real-time data of a physical entity with a digital machine learning model, and transmitting and updating the real-time data;

Establishing a user interaction interface, and displaying the result and analysis of the digital machine learning model to a user;

real-time monitoring and optimizing the physical entity through a digital machine learning model;

The digital machine learning model is improved and updated.

The embodiment of the invention also provides electronic equipment, which comprises a processor and a memory, wherein the processor is used for executing a computer program stored in the memory to realize the digital twinning-based power private network monitoring method.

The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores at least one instruction, and the at least one instruction realizes the power private network monitoring method based on digital twinning when being executed by a processor.

The computer program comprises computer program code which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable storage medium may include: any entity or device, medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier wave signals, telecommunications signals, software distribution media, and the like capable of carrying the computer program code. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals. For convenience of description, the foregoing disclosure shows only those parts relevant to the embodiments of the present invention, and specific technical details are not disclosed, but reference is made to the method parts of the embodiments of the present invention. The computer readable storage medium is non-transitory and can be stored in a storage device formed by various electronic devices, and can implement the execution procedure described in the method according to the embodiment of the present invention.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flowchart and/or block of the flowchart illustrations and/or block diagrams, and combinations of flowcharts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.

Claims (14)

1. The power private network monitoring method based on digital twinning is characterized by comprising the following steps of:

determining the communication network quality index to be monitored, and collecting data corresponding to the communication network quality index in real time;

Carrying out physical operation on the collected data corresponding to the communication network quality index by utilizing a pre-established power private network monitoring digital twin body to obtain real-time calculated physical quantity data, comparing the real-time calculated physical quantity data with a set threshold value, and correcting the power private network monitoring digital twin body in a first time interval;

Determining and correcting the dynamic error of the power monitoring physical entity in a second time interval according to the corrected power private network monitoring digital twin body, and predicting the state of the power monitoring physical entity in a third time interval according to the corrected power private network monitoring digital twin body and the dynamic error of the power monitoring physical entity;

generating early warning information according to the dynamic error and the predicted state of the power monitoring physical entity and preset early warning rules, displaying in a visual mode, and displaying the real-time state and the change trend of the network quality.

2. The method for monitoring a private power network based on digital twinning according to claim 1, wherein when the communication network quality index to be monitored is determined, the data corresponding to the communication network quality index is collected in real time, the communication network quality index includes delay, packet loss rate and bandwidth utilization rate, and the data corresponding to the communication network quality index is collected in real time by deploying monitoring equipment in the private power network.

3. The method for monitoring a power private network based on digital twinning according to claim 1, wherein in the step of physically calculating the collected data corresponding to the quality index of the communication network by using the pre-established power private network monitoring digital twinning body to obtain real-time calculated physical quantity data, comparing the calculated physical quantity data with a set threshold value, and correcting the power private network monitoring digital twinning body in a first time interval, the power private network monitoring digital twinning body comprises a physical model and a rule model;

the physical model is used for carrying out physical operation on the collected data corresponding to the communication network quality index to obtain real-time calculated physical quantity data, wherein the real-time calculated physical quantity data comprises an average value, a maximum value and a percentile corresponding to the communication network quality index; the rule model is a model formed by preset quality index data thresholds of all communication networks;

And correcting the power private network monitoring digital twin body in a first time interval by comparing the real-time calculated physical quantity data output by the physical model with a threshold value in the rule model.

4. A method of monitoring a power grid based on digital twinning as set forth in claim 3, wherein the step of modifying the power grid monitoring digital twinning during the first time interval by comparing the real-time calculated physical quantity data output by the physical model with a threshold value in the rule model comprises:

Determining an independent variable sequence Y and an independent variable sequence X of the association analysis according to the requirements according to the following formula:

Y＝[y(1),y(2)…,y(n)]；

Wherein l represents the number of samples; n is the number of features;

the data x _i k in each dependent variable sequence is averaged according to the following formula to obtain

Where x _i (k) represents the kth eigenvalue of the ith sample of the dependent variable sequence; Is the mean of the ith sample;

solving the independent variable y (k) and the independent variable after the averaging process according to the following formula Correlation coefficient value μ _i between:

In the method, in the process of the invention, Η is the resolution coefficient;

The relevance value r _i of all the relevance coefficients of each dependent variable sequence is calculated according to the following formula:

and judging the tightness degree of the connection by calculating the similarity degree between the independent variables and the dependent variables, and determining the influence factors.

5. The method for monitoring the private power grid based on the digital twin system according to claim 1, wherein in the step of generating early warning information according to the dynamic error and the predicted state of the physical power monitoring entity and according to preset early warning rules, displaying the early warning information in a visual manner and displaying the real-time state and the change trend of the network quality, the early warning information is notified in a short message, mail or App push manner, and the visual manner comprises displaying in a dashboard, a chart or a report.

6. The digital twinning-based power private network monitoring method according to claim 1, further comprising the steps of diagnosing and repairing faults by locating fault positions according to early warning information and real-time states and change trends of network quality when network faults or communication interruption occurs.

7. The digital twinning-based power grid monitoring method of claim 1, further comprising performing power grid monitoring using a pre-established digital machine learning model, the process of establishing the digital machine learning model comprising:

carrying out parameter estimation and optimization on the digital machine learning model, and adjusting the parameters of the model through fitting with real data;

Verifying and calibrating the established digital machine learning model by using historical data or test data;

Connecting real-time data of a physical entity with a digital machine learning model, and transmitting and updating the real-time data;

Establishing a user interaction interface, and displaying the result and analysis of the digital machine learning model to a user;

real-time monitoring and optimizing the physical entity through a digital machine learning model;

The digital machine learning model is improved and updated.

8. A digital twinning-based power grid monitoring system, comprising:

The data acquisition module is used for determining the communication network quality index to be monitored and acquiring data corresponding to the communication network quality index in real time;

The digital twin body correction module is used for carrying out physical operation on the collected data corresponding to the communication network quality index by utilizing the pre-established power private network monitoring digital twin body to obtain real-time calculated physical quantity data, comparing the real-time calculated physical quantity data with a set threshold value, and correcting the power private network monitoring digital twin body in a first time interval;

The physical entity state prediction module is used for determining and correcting the dynamic error of the power monitoring physical entity in a second time interval according to the corrected power private network monitoring digital twin body, and predicting the state of the power monitoring physical entity in a third time interval according to the corrected power private network monitoring digital twin body and the dynamic error of the power monitoring physical entity;

And the early warning module is used for generating early warning information according to the dynamic error of the power monitoring physical entity and the predicted state and preset early warning rules, displaying the early warning information in a visual mode and displaying the real-time state and the change trend of the network quality.

9. The digital twinning-based power grid monitoring system of claim 8, wherein the digital twinning modification module pre-established power grid monitoring digital twinning comprises a physical model and a rule model;

the physical model is used for carrying out physical operation on the collected data corresponding to the communication network quality index to obtain real-time calculated physical quantity data, wherein the real-time calculated physical quantity data comprises an average value, a maximum value and a percentile corresponding to the communication network quality index; the rule model is a model formed by preset quality index data thresholds of all communication networks;

And correcting the power private network monitoring digital twin body in a first time interval by comparing the real-time calculated physical quantity data output by the physical model with a threshold value in the rule model.

10. The digital twinning-based power grid monitoring system of claim 9, wherein the digital twinning correction module pre-establishes the power grid monitoring digital twinning to determine the correlation analysis independent variable sequence Y and dependent variable sequence X according to the following formula:

Y＝[y(1),y(2)…,y(n)]；

Wherein l represents the number of samples; n is the number of features;

the data x _i k in each dependent variable sequence is averaged according to the following formula to obtain

Where x _i (k) represents the kth eigenvalue of the ith sample of the dependent variable sequence; Is the mean of the ith sample;

solving the independent variable y (k) and the independent variable after the averaging process according to the following formula Correlation coefficient value μ _i between:

In the method, in the process of the invention, Η is the resolution coefficient;

The relevance value r _i of all the relevance coefficients of each dependent variable sequence is calculated according to the following formula:

and judging the tightness degree of the connection by calculating the similarity degree between the independent variables and the dependent variables, and determining the influence factors.

11. The digital twinning-based power grid monitoring system according to claim 8, further comprising a fault handling module for diagnosing and repairing faults by locating fault positions according to real-time status and trend of change of early warning information and network quality when network faults or communication interruption occurs.

12. The digital twinning-based power grid monitoring system of claim 8, further comprising a digital machine learning model training module for power grid monitoring using a pre-established digital machine learning model, the process of establishing the digital machine learning model comprising:

carrying out parameter estimation and optimization on the digital machine learning model, and adjusting the parameters of the model through fitting with real data;

Verifying and calibrating the established digital machine learning model by using historical data or test data;

Connecting real-time data of a physical entity with a digital machine learning model, and transmitting and updating the real-time data;

Establishing a user interaction interface, and displaying the result and analysis of the digital machine learning model to a user;

real-time monitoring and optimizing the physical entity through a digital machine learning model;

The digital machine learning model is improved and updated.

13. An electronic device comprising a processor and a memory, the processor configured to execute a computer program stored in the memory to implement the digital twinning-based power grid monitoring method of any one of claims 1 to 7.

14. A computer readable storage medium storing at least one instruction that when executed by a processor implements a digital twinning-based power grid monitoring method according to any one of claims 1 to 7.