Intelligent inspection method and system for power grid regulation and control based on digital twinning

Abstract

The invention provides a power grid regulation and control intelligent inspection method and system based on digital twinning. The method comprises the following steps: step 1, constructing a full-node multi-granularity digital twinning model; 2, establishing a mapping relation between the physical entity of the power grid regulation and control system and the digital twinborn model; step 3, realizing connection between the inspection system and different nodes by integrating SSH protocols of all series versions, and further obtaining node data information; 4, calculating the time difference between the clock source node and other nodes according to the obtained node data information, judging whether the time difference exceeds a set threshold value or not, and if the time difference exceeds the threshold value, adjusting the inspection period; and 5, according to the obtained node data information, constructing a periodic wavelet-like function used for predicting the CPU utilization rate and a linear and exponential composite growth model used for predicting the storage space occupancy rate, and optimizing resource allocation according to a prediction result. The method has the advantages of high operation efficiency, high reliability and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment digitization and intelligence, and specifically to a power grid control intelligent inspection method and system based on digital twins. Background Art

[0002] With the continuous expansion of the scale of power systems and the increasing complexity of technology, the operating efficiency and stability of power grid control systems are facing unprecedented challenges. Traditional power grid control methods mainly rely on manual remote inspections, which is not only time-consuming and labor-intensive, but also has obvious limitations. For example, the power supply company's intelligent dispatching control system (D5000 including standby dispatch) has 60 nodes, and each inspection takes 2 to 4 hours, which not only leads to untimely data collection, but also may affect the safe operation of the power grid due to the delay in the discovery of hidden faults. In addition, due to the lack of an effective unified monitoring window, when a node or NTP service goes offline, time deviations are difficult to be quickly discovered, which in turn affects the accurate push of power grid data and the rapid judgment of tripping events.

[0003] In terms of data management and processing, a large number of logs, temporary data, and abnormal analysis files are generated during the operation of the power grid control system. If these data cannot be effectively managed and cleaned up, they will occupy a large amount of system resources, causing the system response speed to decrease, and even freeze, which seriously interferes with the work efficiency and accident handling ability of the on-duty personnel. Therefore, improving the inspection efficiency and data processing capabilities of the power grid control system has become an urgent problem to be solved.

[0004] In recent years, digital twin technology, as an emerging information technology means, has attracted widespread attention because it can achieve a deep integration of the physical world and the digital world. In particular, the application of digital twin technology to the power grid control system can achieve real-time monitoring and accurate simulation of the power grid operation status, and provide strong technical support for fault detection, fault diagnosis, scheduling optimization, state evaluation and other aspects. For example, in the Chinese patent application "Intelligent Prediction and Management Platform Based on the Combination of Digital Twins and Large Models" with application number CN 118536835 A, the platform uses digital twin technology to accurately model and efficiently simulate complex systems, thereby improving the intelligence level of the system.

[0005] However, the existing digital twin technology still has some shortcomings when applied to power grid control systems. First, most studies focus on modeling and simulation at the macro level, lacking refined modeling for specific application scenarios, especially the lack of research on multi-granular digital twin models that can be inspected for applications (services). Secondly, in terms of clock synchronization, although some studies have proposed solutions based on NTP services, they have not given specific methods for calculating clock deviations, which to a certain extent limits the application effect of digital twin technology in the field of power grid control. Finally, for the large amount of data generated by the power grid control system, the existing technical solutions still have a lot of room for improvement in data processing efficiency and resource occupancy optimization. Summary of the invention

[0006] The technical problem to be solved by the present invention is as follows: In view of the above-mentioned problems in the prior art, an intelligent inspection method and system for power grid control based on digital twins with high operating efficiency and reliability is provided, which can monitor key indicators such as the CPU load rate and memory occupancy of the computer room equipment in real time, and can also optimize the overall resource allocation through in-depth analysis of the data, discover and warn of possible fault points in advance, thereby effectively improving the operating efficiency and safety of the computer room.

[0007] In order to solve the above technical problems, the technical solution adopted by the present invention is: A digital twin-based intelligent inspection method for power grid control includes the following steps: Step 1: Build a full-node multi-granularity digital twin model; Divide the physical entities of the power grid control system into multiple levels of granularity, create digital twin model components corresponding to each level of granularity, and load the components to build a digital twin model; Step 2: Establish a mapping relationship between the physical entity of the power grid control system and the digital twin model; The information of all nodes of the physical entity of the power grid control system is stored in a configuration file in a hierarchical manner, and the information in the configuration file is associated with the component information of the digital twin model through the node name to achieve mapping of different granularities; Step 3: Obtaining node data; By integrating the full range of versions of SSH protocol, the inspection system can be connected to different nodes to obtain node data information; Step 4: Clock deviation detection and early warning; Calculate the time difference between the clock source node and other nodes based on the acquired node data information, and determine whether the time difference exceeds the set threshold. If the time difference exceeds the threshold, adjust the inspection cycle. Step 5: Resource prediction and optimization; According to the acquired node data information, a periodic wavelet-like function for predicting CPU usage and a linear and exponential compound growth model for predicting storage space occupancy are constructed, and resource allocation is optimized according to the prediction results.

[0008] As a further improvement of the method of the present invention: in step 2, the method for implementing mapping of different granularities includes: Step 201: Organize the information of all nodes of the physical entity of the power grid control system in a hierarchical manner according to the region, work location, computer room, and cabinet to which the node belongs, and store the collected information in a configuration file; Step 202: Name the component file using the node name so that the component file name of each node is consistent with its name in the configuration file; Step 203: Read and parse the node information in the configuration file, read the corresponding component file according to the node name, parse the parameters in the component file, and associate the information in the configuration file with the information in the component file through the node name; Step 204: Load the component files in the corresponding folder through the access interface to achieve the mapping between the regional level physical entity and the digital twin model; Step 205: Associating the information in the configuration file with the information in the component file through the node name to achieve mapping of the node-level physical entity and the digital twin model.

[0009] As a further improvement of the method of the present invention: the step 2 also includes node status mapping, and the node status mapping is to set different component colors for different node-level components and regional-level components to display the status of the entire node; the node-level component color setting is to set the color of the node-level component according to the inspection results of the application, clock, CPU, memory, and hard disk; the regional-level component color setting is to set the color of the regional-level component after performing Boolean operations based on the inspection results and the node ownership relationships stored in the configuration file.

[0010] As a further improvement of the method of the present invention: in step 3, the method for realizing the connection between the inspection system and different nodes includes: Step 301: using a socket to establish a Transmission Control Protocol (TCP) connection between the inspection system and the node through the IP address and port number of the node, wherein the socket is a network communication method; Step 302: Send a request to the node to inquire about the supported SSH protocol version number through the established transmission control protocol TCP connection; Step 303: After finding the SSH protocol with the same version number, load the protocol and establish an SSH connection.

[0011] As a further improvement of the method of the present invention: in step 4, the method for calculating the clock deviation includes: Step 401: The inspection system sends a request to the clock source node to inquire about the current time, and records the current time as a first timestamp; Step 402: The current time when the clock source sends back the information is used as the second timestamp, and the current time when the inspection system receives the information sent back by the clock source is used as the third timestamp; Step 403: the inspection system sends a request to other nodes to inquire about the current time, and records the current time as a fourth timestamp; Step 404: the current time when the other node sends back the information is used as the fifth timestamp, and the current time when the inspection system receives the information sent back by the other node is used as the sixth timestamp; Step 405: Calculate the time deviation between the clock source and the node according to the first timestamp, the second timestamp, the third timestamp, the fourth timestamp, the fifth timestamp and the sixth timestamp.

[0012] As a further improvement of the method of the present invention: the function expression of the time deviation is: , Among them, t 11 Indicates the current time when the inspection system sends a time request to clock source node 1, t 21 Indicates the current time sent back by clock source node 1, t 31 Indicates the current time when the inspection system receives the time response sent back by clock source node 1, t 1i It represents the current time when the inspection system sends a time request to other nodes i, t 2i Indicates the current time sent back by other node i, t 3i Indicates the current time when the inspection system receives the time response sent back by other node i.

[0013] As a further improvement of the method of the present invention: in step 5, the step of constructing a periodic wavelet-like function for predicting CPU usage includes: Step 501: Define a periodic wavelet-like function to describe the variation pattern of CPU usage: Step 502: estimating the value range of the periodic wavelet-like function parameters according to the operation characteristics of the power grid control system; Step 503: Determine the parameter calculation step length in combination with the accuracy requirement of the prediction result and the computing capability of the inspection system; Step 504: fitting the actual CPU usage history data through a combination of multiple periodic wavelet-like functions, and obtaining the optimal parameters of the periodic wavelet-like functions by minimizing the sum of square errors; Step 505: Use the sum of multiple periodic wavelet-like functions containing optimal parameters to predict the CPU usage rate.

[0014] As a further improvement of the method of the present invention: in step 5, the method of constructing a linear and exponential compound growth model for predicting storage space occupancy rate includes: Step 511: constructing a linear and exponential compound growth model function; Step 512: Obtain historical data of node storage space occupancy, and obtain a data set after processing the historical data; Step 513: fitting the data set using the linear and exponential compound growth model function to obtain parameter values ​​of the linear and exponential compound growth model function; Step 514: Use the constructed linear and exponential compound growth model function to predict the node storage space occupancy rate at a certain moment in the future. When the prediction result exceeds the threshold, shorten the inspection cycle and recommend a corresponding disposal plan.

[0015] The present invention also provides a power grid control intelligent inspection system based on digital twin, comprising A digital twin model construction and management module is used to divide the physical entities of the power grid control system into multiple levels of granularity, create digital twin model components corresponding to each level of granularity, and load the components to build a digital twin model; Data communication and protocol adaptation module, used to obtain node data using a full range of versions of secure communication protocols; Clock deviation monitoring and early warning module, used to calculate clock deviation based on dual-node multi-time stamp; The node resource prediction and analysis module is used to classify and predict node resources based on periodic wavelet-like and compound growth models.

[0016] As a further improvement of the method of the present invention: the clock deviation monitoring and early warning module includes: A timestamp recording unit, used to record the timestamp of sending time query requests to the clock source node and other nodes; A clock deviation calculation unit, used to calculate the time difference between the clock source and other nodes based on the timestamp; The threshold comparison and early warning unit is used to compare with the preset threshold, mark the nodes that exceed the threshold and provide disposal suggestions.

[0017] Compared with the prior art, the advantages of the present invention are: 1. The present invention achieves comprehensive coverage of all levels and details of the power grid control system by constructing a full-node multi-granularity digital twin model, ensuring the accuracy and integrity of the model, and realizes real-time synchronization of physical entities and digital twin models by establishing a mapping relationship between physical entities and digital twin models. Combined with extensive node data acquisition capabilities and clock deviation detection and early warning mechanisms, as well as advanced resource prediction and optimization technologies, the inspection efficiency and reliability of the power grid control system are comprehensively improved, ensuring the stability and efficient operation of the system.

[0018] 2. The present invention integrates a full range of versions of SSH protocols, so that the node automatically loads the corresponding protocol according to the supported protocol version and establishes a secure communication connection, effectively solving the problem of data acquisition difficulties caused by protocol incompatibility in the prior art, improving the versatility and adaptability of the inspection system, and ensuring the stability and reliability of data acquisition.

[0019] 3. The present invention adopts a calculation method based on dual-node multi-timestamp to monitor clock deviation. Compared with the traditional single timestamp or simple time synchronization algorithm, it can more accurately calculate the time difference between the clock source and other nodes, promptly discover nodes whose clock deviation exceeds the threshold, and provide corresponding disposal suggestions, which helps to improve the clock synchronization accuracy of the power grid control system and ensure the stable operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of an intelligent inspection method for power grid control based on digital twins according to an embodiment of the present invention.

[0021] Figure 2 It is a schematic diagram of a physical model of a power grid control system according to an embodiment of the present invention.

[0022] Figure 3 Schematic diagram of a digital twin model of a power grid control system according to an embodiment of the present invention.

[0023] Figure 4 Schematic diagram of the basic units of the digital twin model of the power grid control system according to an embodiment of the present invention.

[0024] Figure 5 The figure is a schematic diagram of the principle of calculating clock deviation based on dual-node multi-time stamp according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments 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.

[0026] like Figure 1 As shown, the intelligent inspection method for power grid control based on digital twin in this embodiment includes the following steps: Step 1: Build a full-node multi-granularity digital twin model; The physical entities of the power grid control system are divided into multiple levels of granularity, digital twin model components corresponding to each level of granularity are made, and the components are loaded to build the digital twin model.

[0027] In a specific application embodiment, constructing a multi-granularity digital twin model of applications (services) of all nodes of a power grid control system includes the following steps: Step 101: Divide the physical entities of the power grid control system into multiple levels of granularity; The power grid control system is divided into 1-5 levels of granularity according to region, work location, computer room, cabinet, and node, such as Figure 2 As shown, the 5-level granularity includes all nodes of the power grid control system, and information such as application (service), clock, CPU, memory, hard disk, etc. is included in each node. It is understandable that the granularity level can be further refined or merged according to actual needs. For example, as the complexity of the power grid system increases, the hardware modules inside the node and the wider region can be divided more finely on the basis of the existing 5-level granularity to form 6-level, 7-level and other finer granularities for more accurate monitoring and management; or some low-level granularities can be appropriately merged to enhance the control of the macro level and highlight the display and analysis of key areas or key links.

[0028] Step 102: Create digital twin model components corresponding to multi-level granularity physical entities; According to the regional administrative divisions, make components corresponding to each administrative area, such as Figure 3 (a) As shown; according to the nodes and their locations in the cabinets and computer rooms, make components corresponding to each node, cabinet, and computer room, such as Figure 3 Components are the basic units of the digital twin model of the power grid control system. Each component includes information such as assembly parameters, geometric parameters, size parameters, color parameters, etc. Figure 4 As shown in the figure, each component is saved as a file. The assembly parameters describe the positional relationship between components and can be modified according to actual conditions; the geometric parameters, size parameters and color parameters describe the geometric shape, size and color attributes of the components in turn, and the color parameters can be set according to actual needs.

[0029] Step 103: Load components to build a digital twin model; The components for constructing the digital twin model at the regional level (hereinafter referred to as regional components) are placed in the folder D1, and the components for constructing the digital twin model at the node level (hereinafter referred to as node components) are placed in the folders G1~Gw in units of computer rooms. For the folders D1 and G1~Gw, access interfaces FD1 and FG1~FGw are established respectively. The component files corresponding to each administrative region are loaded through the access interface FD1, and the data in each component file is read. The three-dimensional model is drawn according to the geometric parameters, size parameters, and color parameters. The positional relationship between each three-dimensional model is determined by the assembly parameters to construct the digital twin model of the power grid control system at the regional level. Similarly, the digital twin models of the power grid control system at the node level are constructed respectively through the access interfaces FG1~FGw.

[0030] Step 2: Establish a mapping relationship between the physical entity of the power grid control system and the digital twin model; The information of all nodes of the physical entity of the power grid control system is stored in the configuration file in a hierarchical manner, and the information in the configuration file is associated with the component information of the digital twin model through the node name to achieve mapping of different granularities.

[0031] In this embodiment, the method for implementing mapping of different granularities includes: Step 201: Organize the information of all nodes of the physical entity of the power grid control system in a hierarchical manner according to the region, work location, computer room, and cabinet to which the node belongs, and store the collected information in a configuration file; wherein the information of all nodes of the physical entity of the power grid control system includes node name, IP address, port number, user name, access password, etc.

[0032] Step 202: Use the node name to name the component file, so that the component file name of each node is consistent with its name in the configuration file.

[0033] Step 203: Read and parse the node information in the configuration file, read the corresponding component file according to the node name, parse the parameters in the component file, and associate the information in the configuration file with the information in the component file through the node name; Step 204: Load the component files in the corresponding folder through the access interface to achieve the mapping between the regional level physical entity and the digital twin model; Step 205: Associating the information in the configuration file with the information in the component file through the node name to achieve mapping of the node-level physical entity and the digital twin model.

[0034] Specifically, since the assembly parameters, geometric parameters, size parameters, and color parameters of the components correspond to the spatial position, shape, size, and color of the physical entity when they are manufactured, the mapping of the physical entity and the digital twin model at the regional granularity level can be achieved by loading the component files in the corresponding folder through the access interface. In the same computer room, the node name is unique, so the component file is named using the node, and by reading the data in the configuration file, the component file name, and the information in the component, and then associating this information through the node name, the mapping of the physical entity and the digital twin model at the node granularity level can be achieved.

[0035] This embodiment establishes a precise mapping relationship between the physical entities of the power grid control system and the digital twin model. Through information such as configuration files and node names, various attributes of the physical entities are associated with the component information of the digital twin model, ensuring that the digital twin model can accurately reflect the state changes of the physical entities, thereby providing a more reliable basis for diagnosis and early warning.

[0036] It is understandable that this embodiment can add more dimensional mapping information, such as functional attributes of equipment, business logic relationships, geographic space locations, etc. Through the fusion mapping of multi-dimensional information, the intrinsic connection between physical entities and digital twin models can be more comprehensively reflected, providing a basis for more complex analysis and application scenarios, such as fault propagation analysis based on business logic, resource optimization configuration based on geographic space, etc.

[0037] In this embodiment, node status mapping is also included. Node status mapping is to set different component colors for different node-level components and regional-level components to display the status of the entire node; the node-level component color setting is to set the color of the node-level component according to the inspection results of the application, clock, CPU, memory, and hard disk; the regional-level component color setting is to set the color of the regional-level component after Boolean operation based on the inspection results and the node ownership relationship stored in the configuration file.

[0038] In this embodiment, node status mapping is used to set the color of components according to the inspection results, which can intuitively display the status of all nodes at the regional level and the node level granularity, so that operation and maintenance personnel can understand the operation status of the power grid control system at a glance, quickly locate abnormal nodes, and improve the efficiency of troubleshooting.

[0039] It is understandable that in addition to the above-mentioned mapping method, this embodiment can also use image recognition, pattern recognition and other technologies in artificial intelligence and machine learning to realize automatic recognition and mapping of physical entities and digital twin models. Through automatic recognition of device appearance, identification, location and other features, the system can automatically associate the corresponding digital twin model components, reduce the workload of manual configuration and intervention, and improve the accuracy and timeliness of mapping. Especially in large-scale complex power grid systems, this method can significantly improve mapping efficiency.

[0040] Step 3: Obtaining node data; By integrating the full range of versions of the SSH protocol, the inspection system can be connected to different nodes to obtain node data information.

[0041] In this embodiment, the entire series of SSH protocols are set in the same file S1 to achieve the integration of the entire series of versions of secure communication protocols. The inspection system reads a certain part of S1 as needed to achieve the loading of a certain version of the SSH protocol.

[0042] In this embodiment, the method for connecting the inspection system to different nodes includes: Step 301: Use a socket to establish a Transmission Control Protocol (TCP) connection between the inspection system and the node through the IP address and port number of the node, wherein the socket is a network communication method.

[0043] Step 302: Send a request to the node to inquire about the supported SSH protocol version number through the established Transmission Control Protocol TCP connection.

[0044] Step 303: After finding the SSH protocol with the same version number, load the protocol and establish an SSH connection.

[0045] In this embodiment, the method for obtaining node data through a secure communication protocol includes: Step 311: The inspection system sends an instruction to query the operating system version to the node through the established SSH connection.

[0046] Step 312: Based on the received node operating system version, the inspection system generates and sends an instruction for querying node detailed information.

[0047] Step 313: Extract required data from the node information according to the received node information and its operating system version.

[0048] This embodiment integrates a full range of SSH protocols, can automatically load the corresponding protocol according to the protocol version supported by the node, and establish a secure communication connection, effectively solving the problem of data acquisition difficulties caused by protocol incompatibility in the prior art, improving the versatility and adaptability of the inspection system, and ensuring the stability and reliability of data acquisition.

[0049] Step 4: Clock deviation detection and early warning; The time difference between the clock source node and other nodes is calculated based on the acquired node data information to determine whether the time difference exceeds the set threshold. If the time difference exceeds the threshold, the inspection cycle is adjusted.

[0050] In this embodiment, the method for calculating the clock deviation includes: Step 401: The inspection system sends a request to the clock source node to inquire about the current time, and records the current time as a first timestamp; Step 402: The current time of the information sent back by the clock source is used as the second timestamp, and the current time of the information sent back by the clock source is received by the inspection system as the third timestamp; Step 403: the inspection system sends a request to other nodes to inquire about the current time, and records the current time as a fourth timestamp; Step 404: the current time when the other nodes send back the information is used as the fifth timestamp, and the current time when the inspection system receives the information sent back by the other nodes is used as the sixth timestamp; Step 405: Calculate the time deviation between the clock source and the node according to the first timestamp, the second timestamp, the third timestamp, the fourth timestamp, the fifth timestamp and the sixth timestamp.

[0051] like Figure 5 As shown, in a specific application embodiment, the method for calculating clock deviation based on dual-node multi-time stamps includes: 1) The inspection system sends a request to the clock source node 1 to inquire about the current time. When sending, the inspection system records the current time as the timestamp t 11 .

[0052] 2) When receiving the current time sent back by clock source node 1, the inspection system records the current time as the timestamp t 31 , the current time sent back by clock source node 1 is used as the timestamp t 21 .

[0053] 3) The inspection system sends a request to other nodes i to inquire about the current time. When sending, the inspection system records the current time as the timestamp t 1i .

[0054] 4) When receiving the current time sent back by other node i, the inspection system records the current time as the timestamp t 3i , take the current time sent back by other point i as the timestamp t 2i .

[0055] 5) The function expression for calculating the time difference between the clock source and other nodes i is: , (1) 6) If Δt 1i If the set threshold is exceeded, it is recommended to shorten the inspection cycle and recommend corresponding disposal plans.

[0056] 7) Repeat 1) to 6), where other node 1 becomes other node 2, until the time differences of all online nodes in the power grid control system have been calculated.

[0057] In this embodiment, a calculation method based on dual-node multi-timestamps is used to monitor clock deviation. Compared with the traditional single timestamp or simple time synchronization algorithm, it can more accurately calculate the time difference between the clock source and other nodes, promptly discover nodes whose clock deviation exceeds the threshold, and provide corresponding disposal suggestions, which helps to improve the clock synchronization accuracy of the power grid control system and ensure the stable operation of the system.

[0058] In this embodiment, the historical clock deviation data can also be mined and analyzed in combination with big data analysis and machine learning technology to establish a clock deviation prediction model. By comprehensively considering multi-dimensional data such as the power grid operation status, environmental factors, and equipment performance, the changing trend of the clock deviation can be predicted in advance to implement an adaptive clock adjustment strategy. That is, before the deviation occurs, the system can automatically adjust the clock parameters to avoid system performance degradation or increased failure risk caused by clock deviation, thereby improving the reliability and stability of the power grid.

[0059] Step 5: Resource prediction and optimization; According to the acquired node data information, a periodic wavelet-like function for predicting CPU usage and a linear and exponential compound growth model for predicting storage space occupancy are constructed, and resource allocation is optimized according to the prediction results.

[0060] In this embodiment, the steps of constructing a periodic wavelet-like function for predicting CPU usage include: Step 501: Define a periodic wavelet-like function to describe the variation pattern of CPU usage: Step 502: estimating the value range of the periodic wavelet-like function parameters according to the operation characteristics of the power grid control system; Step 503: Determine the parameter calculation step length in combination with the accuracy requirement of the prediction result and the computing capability of the inspection system; Step 504: fitting the actual CPU usage history data through a combination of multiple periodic wavelet-like functions, and obtaining the optimal parameters of the periodic wavelet-like functions by minimizing the sum of square errors; Step 505: Use the sum of multiple periodic wavelet-like functions containing optimal parameters to predict the CPU usage rate.

[0061] In a specific application embodiment, a method for predicting the CPU usage rate and memory occupancy rate of a node in a power grid control system based on a periodic wavelet-like function includes: 1) For CPU usage, construct a periodic wavelet-like function: (2) in, The percentage of resources used by a single application (service). is the start time of the operation, For the running time, is a repeating cycle.

[0062] 2) According to the operating characteristics of the power grid control system, estimate 、 、 、 The value range is [Amp Min ,Amp Max ]、[t pMin , t pMax ]、[t RMin , t RMax ]、[t TMin , t TMax ]; 3) Combine the accuracy requirements of the prediction results and the computing power of the inspection system to determine 、 、 、 The calculation step length is Amp Step ,t pStep ,t RStep ,t TStep ; 4) Historical CPU usage data Ratio obtained from the power grid control system nodes CPU (t), according to the maximum number of applications (services) running in the power grid control system node, denoted as A Max Use A Max The sum of formula (2) is used to approximate Ratio CPU (t), and use formula (3) to calculate the approximation error ,when At the minimum value, the corresponding Amp, t p 、t R 、t T The value matrix Mat is the optimal parameter to describe the change law of historical data of CPU usage, as shown in formula (5).

[0063] (3) in, 、 are the start time and end time of the historical data used for analysis. As shown in formula (4): (4) in, [Amp Min :Amp Step :Amp Max ], [t pMin :t pStep :t pMax ], [t RMin :t RStep :t RMax ], [t TMin :t TStep :t TMax ] (5) 5) Set a future time t f , substituting into formula (6), we can predict the node CPU usage (6) in, (7) (8) … (9) 6) If the predicted CPU usage exceeds the set threshold, it is recommended to shorten the inspection cycle and recommend corresponding disposal solutions; 7) If the latest CPU usage obtained exceeds the set threshold, an alarm will be issued and the corresponding disposal plan will be recommended.

[0064] In this embodiment, the method for constructing a linear and exponential compound growth model for predicting storage space occupancy includes: Step 511: constructing a linear and exponential compound growth model function; Step 512: Obtain historical data of node storage space occupancy, and obtain a data set after processing the historical data; Step 513: Fitting the data set using the linear and exponential compound growth model function to obtain parameter values ​​of the linear and exponential compound growth model function; Step 514: Use the constructed linear and exponential compound growth model function to predict the node storage space occupancy rate at a certain moment in the future. When the prediction result exceeds the threshold, shorten the inspection cycle and recommend a corresponding disposal plan.

[0065] In a specific application embodiment, a method for predicting the storage space occupancy rate of a node in a power grid control system based on a compound growth model includes: 1) Construct linear and exponential compound growth model functions (10) in, represents linear growth, represents exponential growth, a, b, c, d are unknown coefficients, t is time, Represents the storage space occupancy rate that changes with time t.

[0066] 2) Eliminate the historical data S of node storage space occupancy H The data Sd dropped in the data set S H1 .

[0067] 3) Use formula (10) to calculate the data set S H1 Fitting is performed to obtain the values ​​of a, b, c, and d, which are a ass 、b ass 、c ass ,d ass .

[0068] 4) If the node storage space usage is reduced by manual operation, including removing files or replacing hard disks, the latest storage space usage is set to a ass .

[0069] 5) Set a future time t f , substituting into formula (11), we can get the predicted node storage space occupancy rate (11) 6) If the predicted storage space occupancy rate exceeds the set threshold, it is recommended to shorten the inspection cycle and recommend corresponding disposal solutions. 7) If the latest storage space usage rate obtained exceeds the set threshold, an alarm will be issued and the corresponding disposal plan will be recommended.

[0070] In this embodiment, the periodic wavelet-like function is used to predict the CPU usage and memory occupancy, and the compound growth model is used to predict the storage space occupancy, which can fully explore the inherent laws and trends of the data. Compared with the traditional prediction method, the prediction results are more accurate and scientific. It helps operation and maintenance personnel to plan resource allocation in advance, optimize the performance of the power grid control system, and avoid system failures caused by insufficient resources.

[0071] It is understandable that this embodiment can integrate deep learning and reinforcement learning technologies on the basis of existing periodic wavelet-like and compound growth models to further improve the accuracy and intelligence level of resource prediction. Deep learning can automatically mine complex features and nonlinear relationships in data, and reinforcement learning can dynamically adjust and optimize according to prediction results and actual feedback, so that the prediction model can better adapt to the dynamic changes and uncertainties of resource use in the power grid control system. For example, when dealing with sudden load growth or equipment failure, it can more accurately predict resource demand and take corresponding measures in advance.

[0072] In this embodiment, in addition to the operation data of the power grid control system itself, more external data can be integrated for resource forecasting, such as economic development data, social activity data, climate change data, etc. There is a potential correlation between these data and power grid load and resource use. Through the fusion analysis of multi-source data, we can more comprehensively understand the changing trend of resource demand and improve the accuracy and reliability of prediction. For example, based on the information of large-scale events held in the city, the increase in power grid load can be predicted in advance, and power generation and transmission resources can be reasonably arranged.

[0073] This embodiment also provides a power grid control intelligent inspection system based on digital twins, including: The digital twin model construction and management module is used to divide the physical entities of the power grid control system into multiple levels of granularity, create digital twin model components corresponding to each level of granularity, and load the components to build the digital twin model; Data communication and protocol adaptation module, used to obtain node data using a full range of versions of secure communication protocols; Clock deviation monitoring and early warning module, used to calculate clock deviation based on dual-node multi-time stamp; The node resource prediction and analysis module is used to classify and predict node resources based on periodic wavelet-like and compound growth models.

[0074] In this embodiment, the digital twin model construction and management module includes: The component library management submodule is used to store and manage a large number of digital twin model components, including regional components and node components made based on physical entities of various granularities. The component library has a classification indexing function, and stores component files according to multi-dimensional labels such as administrative regions, computer room names, and node names to ensure that component files can be quickly retrieved and called. At the same time, a component update mechanism is set up. When the power grid control system has equipment upgrades, new additions, or layout adjustments, the assembly parameters, geometric parameters, size parameters, and color parameters of the corresponding components are updated in a timely manner based on new physical entity parameters, geometric dimensions, and other information to ensure the consistency of the digital twin model with the real entity.

[0075] The model assembly and rendering engine is used to construct efficient three-dimensional models by reading component data from the corresponding folder based on the access interface with the help of graphics processing and modeling algorithms. On the one hand, the component outline is accurately outlined based on geometric parameters and size parameters, and the color parameters are used to give a realistic appearance display effect; on the other hand, the relative spatial position of each component is accurately located based on the assembly parameters, and the scattered regional components and node components are assembled into a complete and hierarchical digital twin model of the power grid control system. The engine supports real-time rendering, dynamically displays model status changes as data is updated, and provides an intuitive visual interface for power grid control system staff.

[0076] In this embodiment, the data communication and protocol adaptation module has a built-in secure communication protocol library with a full range of versions, which centrally manages and stores files of multiple SSH protocol versions. The secure communication protocol library is continuously updated and maintained to ensure that it covers old and new protocol types that may be used by each node in the power grid control system. When the inspection system establishes communication with the node, it quickly locates the adaptation protocol in the secure communication protocol library and loads and switches it according to the protocol version number fed back by the node, seamlessly connecting the communication link to ensure smooth and stable data interaction.

[0077] In this embodiment, by centrally managing and storing the full range of versions of the secure communication protocol library, and quickly adapting and loading the corresponding protocol according to the protocol version number fed back by the node, it is possible to effectively ensure smooth and stable communication between the inspection system and each node of the power grid control system. This mechanism not only improves the compatibility of the system, but also enhances the reliability and security of the system.

[0078] In this embodiment, the clock deviation monitoring and early warning module includes: A timestamp recording unit, used to record the timestamp of sending time query requests to the clock source node and other nodes; A clock deviation calculation unit, used to calculate the time difference between the clock source and other nodes based on the timestamp; The threshold comparison and early warning unit is used to compare with the preset threshold, mark the nodes that exceed the threshold and provide disposal suggestions.

[0079] In this embodiment, the clock deviation monitoring and early warning module automatically and periodically sends time query requests to the clock source node and other online nodes according to the clock deviation calculation method based on dual-node multi-timestamp, accurately records the series of timestamps and calculates the time difference. By comparing with the preset clock deviation threshold, the nodes exceeding the threshold are marked, and the results are fed back to the visual operation and maintenance interface in real time to alert the power grid control system staff, so that the staff can adjust the node clock according to the deviation.

[0080] In this embodiment, the node resource prediction and analysis module includes: Periodic wavelet analysis engine unit The periodic wavelet analysis engine unit is used to deeply explore the inherent periodic fluctuation characteristics of CPU usage and memory occupancy data using the constructed periodic wavelet function. The historical monitoring data is imported into the engine in time series, and the frequency components and amplitude information associated with the operation cycles of different applications (services) are extracted through complex mathematical transformation and parameter fitting, and the usage trend of future time periods is predicted, and the tension of node computing resources is evaluated in advance, providing a quantitative basis for load balancing deployment.

[0081] The compound growth model operation unit is used to predict the node storage space occupancy rate. It uses linear and exponential compound growth model functions, combined with the node storage historical growth data, to fit the optimal model parameters. Considering that data growth is affected by multiple factors such as the explosive growth of business data volume and the accumulation of log files, the model dynamically adjusts the linear and exponential growth weights, accurately estimates the time node when storage space is exhausted, and reminds the power grid control system staff to clean up redundant data and expand storage capacity in a timely manner, ensuring the safe and stable data storage of the power grid control system.

[0082] In this embodiment, the digital twin-based power grid control intelligent inspection system also includes a human-computer interaction interface module. The human-computer interaction interface includes a working condition switching viewing area, a function bar, a company location display area, a storage space usage area, a node display area, a digital twin model display area, a CPU usage area, a memory usage area, and an alarm area, and has good human-computer interaction performance.

[0083] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A digital twin-based intelligent inspection method for power grid control, characterized in that: The following steps are involved: Step 1: Build a full-node multi-granularity digital twin model; Divide the physical entities of the power grid control system into multiple levels of granularity, create digital twin model components corresponding to each level of granularity, and load the components to build a digital twin model; Step 2: Establish a mapping relationship between the physical entity of the power grid control system and the digital twin model; The information of all nodes of the physical entity of the power grid control system is stored in a configuration file in a hierarchical manner, and the information in the configuration file is associated with the component information of the digital twin model through the node name to achieve mapping of different granularities; Step 3: Obtaining node data; By integrating the full range of SSH protocols, the inspection system can be connected to different nodes to obtain node data information. Step 4: Clock deviation detection and early warning; Calculate the time difference between the clock source node and other nodes based on the acquired node data information, and determine whether the time difference exceeds the set threshold. If the time difference exceeds the threshold, adjust the inspection cycle. Step 5: Resource prediction and optimization; According to the acquired node data information, a periodic wavelet-like function for predicting CPU usage and a linear and exponential compound growth model for predicting storage space occupancy are constructed, and resource allocation is optimized according to the prediction results.

2. The intelligent inspection method for power grid control based on digital twin according to claim 1 is characterized in that: In step 2, the method for implementing mapping of different granularities includes: Step 201: Organize the information of all nodes of the physical entity of the power grid control system in a hierarchical manner according to the region, work location, computer room, and cabinet to which the node belongs, and store the collected information in a configuration file; Step 202: Name the component file using the node name so that the component file name of each node is consistent with its name in the configuration file; Step 203: Read and parse the node information in the configuration file, read the corresponding component file according to the node name, parse the parameters in the component file, and associate the information in the configuration file with the information in the component file through the node name; Step 204: Load the component files in the corresponding folder through the access interface to achieve the mapping between the regional level physical entity and the digital twin model; Step 205: Associating the information in the configuration file with the information in the component file through the node name to achieve mapping of the node-level physical entity and the digital twin model.

3. The intelligent inspection method for power grid control based on digital twin according to claim 1 is characterized in that: The step 2 also includes node status mapping, wherein the node status mapping is to set different component colors for different node-level components and regional-level components to display the status of the entire node; the node-level component color setting is to set the color of the node-level component according to the inspection results of the application, clock, CPU, memory, and hard disk; the regional-level component color setting is to set the color of the regional-level component after performing Boolean operations based on the inspection results and the node ownership relationships stored in the configuration file.

4. The intelligent inspection method for power grid control based on digital twin according to claim 1 is characterized in that: In step 3, the method for realizing the connection between the inspection system and different nodes includes: Step 301: using a socket to establish a Transmission Control Protocol (TCP) connection between the inspection system and the node through the IP address and port number of the node, wherein the socket is a network communication method; Step 302: Send a request to the node to inquire about the supported SSH protocol version number through the established transmission control protocol TCP connection; Step 303: After finding the SSH protocol with the same version number, load the protocol and establish an SSH connection.

5. The intelligent inspection method for power grid control based on digital twin according to claim 1 is characterized in that: In step 4, the method for calculating the clock deviation includes: Step 401: The inspection system sends a request to the clock source node to inquire about the current time, and records the current time as a first timestamp; Step 402: The current time when the clock source sends back the information is used as the second timestamp, and the current time when the inspection system receives the information sent back by the clock source is used as the third timestamp; Step 403: the inspection system sends a request to other nodes to inquire about the current time, and records the current time as a fourth timestamp; Step 404: the current time when the other node sends back the information is used as the fifth timestamp, and the current time when the inspection system receives the information sent back by the other node is used as the sixth timestamp; Step 405: Calculate the time deviation between the clock source and the node according to the first timestamp, the second timestamp, the third timestamp, the fourth timestamp, the fifth timestamp and the sixth timestamp.

6. The digital twin-based intelligent inspection method for power grid control according to claim 5 is characterized in that: The time deviation The function expression is: ， Among them, t 11 Indicates the current time when the inspection system sends a time request to clock source node 1, t 21 Indicates the current time sent back by clock source node 1, t 31 Indicates the current time when the inspection system receives the time response sent back by clock source node 1, t 1i It represents the current time when the inspection system sends a time request to other nodes i, t 2i Indicates the current time sent back by other node i, t 3i Indicates the current time when the inspection system receives the time response sent back by other node i.

7. The intelligent inspection method for power grid control based on digital twin according to claim 1 is characterized in that: In step 5, the step of constructing a periodic wavelet-like function for predicting CPU usage includes: Step 501: Define a periodic wavelet-like function to describe the variation pattern of CPU usage: Step 502: estimating the value range of the periodic wavelet-like function parameters according to the operation characteristics of the power grid control system; Step 503: Determine the parameter calculation step length in combination with the accuracy requirement of the prediction result and the computing capability of the inspection system; Step 504: fitting the actual CPU usage history data through a combination of multiple periodic wavelet-like functions, and obtaining the optimal parameters of the periodic wavelet-like functions by minimizing the sum of square errors; Step 505: Use the sum of multiple periodic wavelet-like functions containing optimal parameters to predict the CPU usage rate.

8. The intelligent inspection method for power grid control based on digital twin according to claim 1 is characterized in that: In step 5, the method for constructing a linear and exponential compound growth model for predicting storage space occupancy rate includes: Step 511: constructing a linear and exponential compound growth model function; Step 512: Obtain historical data of node storage space occupancy, and obtain a data set after processing the historical data; Step 513: fitting the data set using the linear and exponential compound growth model function to obtain parameter values ​​of the linear and exponential compound growth model function; Step 514: Use the constructed linear and exponential compound growth model function to predict the node storage space occupancy rate at a certain moment in the future. When the prediction result exceeds the threshold, shorten the inspection cycle and recommend a corresponding disposal plan.

9. A digital twin-based power grid control intelligent inspection system, characterized in that: include A digital twin model construction and management module is used to divide the physical entities of the power grid control system into multiple levels of granularity, create digital twin model components corresponding to each level of granularity, and load the components to build a digital twin model; Data communication and protocol adaptation module, used to obtain node data using a full range of versions of secure communication protocols; Clock deviation monitoring and early warning module, used to calculate clock deviation based on dual-node multi-time stamp; The node resource prediction and analysis module is used to classify and predict node resources based on periodic wavelet-like and compound growth models.

10. The digital twin-based intelligent inspection system for power grid control according to claim 9 is characterized in that: The clock deviation monitoring and early warning module includes: A timestamp recording unit, used to record the timestamp of sending time query requests to the clock source node and other nodes; A clock deviation calculation unit, used to calculate the time difference between the clock source and other nodes based on the timestamp; The threshold comparison and early warning unit is used to compare with the preset threshold, mark the nodes that exceed the threshold and provide disposal suggestions.

Images