Power grid comprehensive monitoring system multi-source information fusion method and device based on data driving and storage medium

Abstract

The invention discloses a power grid comprehensive monitoring system multi-source information fusion method and device based on data driving and a storage medium, and belongs to the field of power grid secondary systems. The method comprises the following steps: analyzing internal correlation between a power network and a communication network based on a complex system theory, constructing an information physical topology model, describing a service transmission path by utilizing a node incidence matrix, defining information physical nodes comprising power elements, sensing elements and the like and branch parameters comprising physical and information transmission media, and constructing a network model; the information flow mode is detected through the processes of state sudden change monitoring, sensing measurement, decision control and the like. The method provides theoretical support for rapid state perception and risk analysis of the power grid, and is suitable for multi-source information fusion processing of a power grid comprehensive monitoring system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power equipment safety detection, and particularly relates to a multi-source information fusion method, device and storage medium of a power grid comprehensive monitoring system based on data driving. BACKGROUND

[0002] With the rapid development of smart grids, the operation scale of power systems is continuously expanding, and the communication network and data sources are increasingly complex. Traditional power grid monitoring systems are difficult to efficiently integrate multi-source data from different devices and different protocols, resulting in low data processing efficiency and low information utilization. Existing power information physical system modeling methods are mostly based on experience or simplified models, and the complex relationship between physical layer devices and information layer data interaction is not well described, which cannot accurately reflect the real state of power grid operation, and the modeling accuracy is difficult to meet the actual demand. In actual operation, the information layer and the physical layer of the power system interact with each other, however, the traditional method lacks effective means to analyze the interaction between the two, and it is difficult to quickly identify the change of information flow path and the influence on the physical system when a fault occurs, which greatly reduces the timeliness and accuracy of power grid fault diagnosis and recovery. Therefore, there is an urgent need for a method that can adapt to complex data sources, improve the modeling accuracy of information physical systems, and effectively analyze the interaction between the information layer and the physical layer, to realize the efficient fusion of multi-source information of the power grid comprehensive monitoring system and ensure the safe and stable operation of the power grid. SUMMARY

[0003] The present application aims to provide a multi-source information fusion method of a power grid comprehensive monitoring system based on data driving. In view of the complex problem of existing power communication and data sources, the present application uses information physical fusion modeling technology to build a CPS (Cyber-Physical Systems) model based on data driving, which solves the technical problems of complex data sources in existing power communication systems, insufficient modeling accuracy of power information physical systems, and difficulty in effectively analyzing the interaction between the information layer and the physical layer. It should be noted that the CPS model is an information physical system model, and the CPS model based on data driving is constructed by deep mining and analyzing historical operation data and real-time monitoring data through machine learning and deep learning algorithms, to build a digital model that can accurately reflect the dynamic interaction relationship between the physical system and the information system, for realizing real-time monitoring, prediction and intelligent decision-making of complex systems.

[0004] The present invention provides a multi-source information fusion method for a data-driven integrated power grid monitoring system, the working steps of which include: constructing a dynamically updated power grid information-physical topology model based on historical operation data and real-time monitoring data, defining information-physical nodes covering physical equipment nodes and information processing nodes in the model and a multidimensional parameter system including operation status parameters and data interaction parameters; defining information-physical branches involving electrical connection branches and data transmission links in the model and their transmission characteristic parameters, protocol adaptation parameters and other associated parameters, using multi-dimensional feature analysis and timing correlation detection methods to systematically detect information flow paths and transmission modes under normal operating conditions and fault scenarios in the information-physical topology model; and detecting normal and fault information flow modes in the information-physical topology model.

[0005] Specifically, the construction of the cyber-physical topology model includes: analyzing the intrinsic correlation between the power network and the power communication network based on complex system theory, constructing a unified primary and secondary power model, and using a node association matrix to describe the service transmission path.

[0006] Specifically, the diagonal elements of the node association matrix are CPS nodes, and the off-diagonal elements are CPS transmission lines.

[0007] Specifically, the information-physical node is defined as a combination of power elements, sensing elements, execution elements, decision links and communication links, wherein: the power elements are used to characterize the physical state, including element identification, control parameters and element rules; the sensing elements are used to characterize the sensing objects, including element identification, sensing objects and sensing rules; the execution elements are used to characterize the control objects, including element identification, control objects and execution rules; the decision link is used to characterize input and output variables, including link identification, input and output variables and decision rules; the communication link is used to characterize transmission properties, including link identification, transmission properties and communication rules.

[0008] Specifically, the control parameters include maximum control parameters and minimum control parameters, the perception rules include sampling frequency and sampling data reliability, the execution rules include control signal delay threshold and control reliability, the decision rules include logical rules or mathematical calculation rules, and the transmission properties include transmission objects, transmission target elements and channel status.

[0009] Specifically, the information-physical branch is defined as a combination of a physical transmission medium and an information transmission medium, wherein: the physical transmission medium is used to characterize power transmission properties, including branch identification, power transmission properties and power transmission rules; the information transmission medium is used to characterize information transmission properties, including branch identification, information transmission properties and information transmission rules.

[0010] Specifically, the power transmission attribute includes first and last end points, impedance, reactance and power constraint, and the power transmission rule includes a power transmission model; the information transmission attribute includes first and last end points, delay and load rate, and the information transmission rule includes a communication link allocation rule.

[0011] Specifically, the detection of the information flow mode includes: monitoring a state mutation of the physical node or the branch; measuring the state mutation by the sensing element and transmitting to the sensing element to correct the state thereof; the sensing element transmits the state to the decision element through the communication link, the decision element generates an output variable according to a decision rule and transmits the output variable to the execution element through the communication link; and the execution element controls the state of the physical element.

[0012] Specifically, the state mutation includes a running state mutation of the physical node or a transmission state mutation of the branch.

[0013] In a second aspect, the present application further provides a multi-source information fusion method and device of a data-driven power grid comprehensive monitoring system, comprising: one or more processors; a memory storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the multi-source information fusion method of the data-driven power grid comprehensive monitoring system, and the information and power interaction mode between multiple devices and subsystems are coupled and analyzed.

[0014] In a third aspect, the present application provides a storage medium containing computer executable instructions, when the computer executable instructions are executed by a computer processor, the computer executable instructions are used to execute the multi-source information fusion method of the data-driven power grid comprehensive monitoring system.

[0015] Advantages

[0016] The data-driven power grid comprehensive monitoring system multi-source information fusion technology of the application fuses and analyzes massive power big data in the power information physics, abstracts the power CPS as a directed network, models the information and physical properties of the nodes and branches, and can simultaneously show the influence of information flow and energy flow on the implementation of device-level, network-level and system-level business. Through this information-physical fusion method, key inherent and related influence elements in the power CPS can be analyzed, and the interaction influence sensitivity of the information layer and the physical layer can be captured. When the parameters in the information communication system change, the influence on the physical layer power flow stability can be accurately quantified and evaluated, thereby providing a theoretical basis for timely correcting the control grid state. The method overcomes the problem of insufficient processing of complex power communication and data sources in the prior art, improves the accuracy and reliability of the power grid comprehensive monitoring through accurate modeling and fusion analysis, and provides strong support for the safe and stable operation of the power grid. The model constructed has good compatibility and scalability, can adapt to the continuous development and change of the power grid system, meets the power grid monitoring needs in different scenarios, and has important application value in power system state monitoring, fault detection and risk analysis. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the drawings shown.

[0018] Figure 1 The data-driven power grid comprehensive monitoring system multi-source information fusion method workflow provided by the embodiment of the present application is shown in the figure.

[0019] Figure 2 The data-driven power grid comprehensive monitoring system multi-source information fusion device structure schematic diagram provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] It should be noted that if the embodiments of the present application involve directionality indication (such as up, down, left, right, front, back, etc.), the directionality indication is only used to explain the relative position relationship, motion condition, etc. between components in a certain posture, and if the certain posture changes, the directionality indication also changes accordingly.

[0022] In addition, if the embodiments of the present application involve descriptions such as "first", "second", etc., the descriptions of "first", "second", etc. are only for description purposes, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, "and / or" or "and / or" appearing throughout the text means that the three parallel schemes are included, for example, "A and / or B" includes A scheme, or B scheme, or A and B simultaneously satisfy the scheme. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or cannot be realized, it should be considered that the combination of technical solutions does not exist, nor within the scope of protection claimed by the present application.

[0023] With the rapid development of big data information technology, information fusion technology is widely used in the field of power communication, and has important theoretical research significance and application value for the reliability of control function, state monitoring and fault detection of power system. For the high-order nonlinear and high-complexity wide-area power system, the complex mechanism contained in the multi-dimensional data needs further research. Many information fusion model algorithms and methods have been proposed in current research. Mainly based on model identification, parameter analysis and knowledge graph algorithm. The present application firstly analyzes the internal correlation between power network and power communication network based on complex system theory, constructs a unified modeling method of power primary and secondary, uses the method of power grid-information correlation matrix modeling to describe the business transmission path, and studies the influence range of communication infrastructure failure or information transmission link abnormal event based on the correlation, thereby providing theoretical support for power grid fast state perception and risk analysis.

[0024] The application aims to provide a multi-source information fusion method of a data-driven power grid comprehensive monitoring system, and the method utilizes information physical fusion modeling technology to build a CPS model based on data driving, and solves the technical problems of complex data sources in the existing power communication system, insufficient modeling precision of the power information physical system, and difficulty in effectively analyzing the interaction between the information layer and the physical layer.

[0025] In one of the embodiments, the construction of the information physical topology model comprises: analyzing the internal correlation between the power network and the power communication network based on the complex system theory, constructing a unified power primary and secondary model, and using a node correlation matrix to describe the business transmission path. The diagonal elements of the node correlation matrix are CPS nodes, and the non-diagonal elements are CPS transmission lines. The information physical node is defined as a combination of power elements, sensing elements, execution elements, decision-making links and communication links, wherein: the power element is used to represent the physical state, including element identification, control parameters and element rules; the sensing element is used to represent the sensing object, including element identification, sensing object and sensing rule; the execution element is used to represent the control object, including element identification, control object and execution rule; the decision-making link is used to represent the input and output variables, including link identification, input and output variables and decision-making rules; and the communication link is used to represent the transmission attribute, including link identification, transmission attribute and communication rule.

[0026] The control parameters include maximum control parameters and minimum control parameters, the perception rules include sampling frequency and sampling data reliability, the execution rules include control signal delay threshold and control reliability, the decision rules include logic rules or mathematical calculation rules, and the transmission attributes include transmission objects, transmission target elements and channel states. The information physical branch is defined as a combination of physical transmission media and information transmission media, wherein: the physical transmission media are used to characterize power transmission attributes, including branch identification, power transmission attributes and power transmission rules; and the information transmission media are used to characterize information transmission attributes, including branch identification, information transmission attributes and information transmission rules. The power transmission attributes include first and last end points, impedance and power constraints, and the power transmission rules include power transmission models; the information transmission attributes include first and last end points, delay and load rate, and the information transmission rules include communication link allocation rules. The detection of the information flow mode includes: monitoring state mutations of physical nodes or branches; measuring the state mutations by perception elements and transmitting them to the perception elements to correct their states; the perception elements transmit the states to the decision elements through the communication links, the decision elements generate output variables according to the decision rules and transmit them to the execution elements through the communication links; and the execution elements control the states of the physical elements. The state mutations include operating state mutations of physical nodes or transmission state mutations of branches.

[0027] In some embodiments, the above process is specifically illustrated by an equivalent system example of an ultra-high voltage converter station. First, an original topology model of the ultra-high voltage converter station is constructed, and then it is simplified into an equivalent model, in which the sampling, transmission and analysis control links of the system are simplified, wherein Sf is a sensor (such as a PMU or other power collection device), A is an execution link (a response-based stability control device), and C is a simplified decision link (which can be a separate control center node or a calculation link attached to the execution link). In this example, the traditional power node B1 and the sensor Sf can be combined as a CPS node according to actual conditions (when the influence of the connecting medium between the sensor and the power node can be ignored), or they can be regarded as independent nodes and connected through an interface (when the medium influence cannot be ignored).

[0028] Figure 2Fig. 1 is a structural schematic diagram of a multi-source information fusion device of a data-driven power grid comprehensive monitoring system provided by an embodiment of the present application. The multi-source information fusion device of the data-driven power grid comprehensive monitoring system comprises a processor 31, a memory 32, a communication device 33, an input device 34, and an output device 35. The number of the processor 31 in the multi-source information fusion device of the data-driven power grid comprehensive monitoring system can be one or more, and the number of the memory 32 in the multi-source information fusion device of the data-driven power grid comprehensive monitoring system can be one or more. The processor 31, the memory 32, the communication device 33, the input device 34, and the output device 35 of the multi-source information fusion device of the data-driven power grid comprehensive monitoring system can be connected through a bus or other means.

[0029] The memory 32 is a computer-readable storage medium, which can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules of the multi-source information fusion method of the data-driven power grid comprehensive monitoring system according to any embodiment of the present application. The memory 32 can mainly include a program storage area and a data storage area. The program storage area can store an operating system and application programs required by at least one function, and the data storage area can store data created according to the use of the device, etc. In addition, the memory 32 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the device through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0030] The communication device 33 is used for data transmission.

[0031] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 32, that is, implements the multi-source information fusion method of the data-driven power grid comprehensive monitoring system described above.

[0032] The input device 34 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. The output device 35 can include a display device such as a display screen.

[0033] The multi-source information fusion device of the data-driven power grid comprehensive monitoring system provided above can be used to execute the multi-source information fusion method of the data-driven power grid comprehensive monitoring system provided by the above embodiments, and has corresponding functions and beneficial effects.

[0034] The embodiment of the present application also provides a storage medium containing computer executable instructions, which are used to execute the data-driven power grid comprehensive monitoring system multi-source information fusion method when executed by a computer processor, and specifically include the following steps: constructing a dynamically updated power grid information-physical topology model based on historical operation data and real-time monitoring data, defining information-physical nodes in the model which cover physical device nodes and information processing nodes and a multi-dimensional parameter system including operation state parameters and data interaction parameters; defining information-physical branches in the model which involve electrical connection branches and data transmission links and associated parameters such as transmission characteristic parameters and protocol adaptation parameters, and using a multi-dimensional feature analysis and time sequence correlation detection method to systematically detect information flow paths and transmission modes in the information-physical topology model under normal conditions and fault scenarios; and detecting normal and fault information flow modes in the information-physical topology model.

[0035] Storage medium - any of various types of memory devices or storage devices. The term "storage medium" is intended to include an installation medium, e.g., a CD-ROM, floppy disks, or tape device; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; or a non-volatile memory such as a magnetic medium (e.g., a hard disk or optical storage); registers, or other similar types of memory elements, etc. The storage medium can also include other types of storage medium or combinations thereof. In addition, the storage medium can be located in a first computer system in which the program is executed, or it can be located in a second different computer system which connects to the first computer system over a network such as the Internet. The second computer system can provide program instructions to the first computer for execution. The term "storage medium" can include two or more storage mediums that reside in different locations, e.g., in different computer systems that are connected over a network. The storage medium can store program instructions (e.g., as an installed program) that can be executed by one or more processors.

[0036] Of course, the storage medium containing computer executable instructions provided by the embodiment of the present application is not limited to the data-driven power grid comprehensive monitoring system multi-source information fusion method as above, and can also execute the related operations in the data-driven power grid comprehensive monitoring system multi-source information fusion method provided by any embodiment of the present application.

[0037] The multi-source information fusion method of the data-driven power grid comprehensive monitoring system provided in the above embodiments can execute the multi-source information fusion method of the data-driven power grid comprehensive monitoring system provided in any of the embodiments of the present application, and technical details not described in detail in the above embodiments can be referred to the multi-source information fusion method of the data-driven power grid comprehensive monitoring system provided in any of the embodiments of the present application.

[0038] In the prior art, for a high-order nonlinear and high-complexity wide-area power system, the complex mechanism contained in the multi-dimensional data lacks in-depth research, and traditional information fusion model algorithms (such as model identification, parameter analysis, and knowledge graph) are difficult to accurately process multi-source heterogeneous information and complex primary and secondary fusion equipment in the power CPS. At the same time, it is difficult to effectively quantify the influence of information communication system parameter changes on the physical layer power flow stability, and it is difficult to realize the rapid state perception and risk analysis of the power grid.

[0039] The multi-source information fusion technology of the data-driven power grid comprehensive monitoring system of the present application is based on the fusion analysis of massive power big data in the power information physics, and the core advantage is to build an information physics fusion model with compatibility and scalability. The model abstracts the power CPS as a directed network, and through standardized modeling of the information attributes and physical attributes of nodes and branches, it can simultaneously present the interaction influence mechanism of information flow and energy flow in device-level, network-level and system-level business, breaking through the limitation of traditional models that can only describe the system state in a single dimension. Through the information physics fusion modeling means, this technology can accurately capture the interaction influence sensitivity of the inherent elements and associated elements in the power CPS. When the transmission delay, link load rate and other parameters in the information communication system change, it can quantitatively evaluate the chain influence of communication abnormalities on the physical layer power flow distribution and device operating state based on the node correlation matrix and parameter definition system, providing quantitative basis for the dynamic adjustment of power grid control strategy, and changing the limitation of traditional methods relying on experience. In the power grid operation monitoring scene, this method realizes the unified expression and fusion processing of multi-source heterogeneous information through standardized node and branch parameter definition, effectively solving the problems of non-uniform data format and semantic ambiguity between the primary system and the secondary system of the power system, improving the data integration efficiency and analysis accuracy. At the same time, based on the information flow detection mechanism, the information transmission path after the state mutation of the physical node can be tracked in real time, providing a systematic analysis framework for fault rapid positioning and early warning, shortening the response time of power grid abnormal events. In addition, the model system built by this technology provides a foundation support for the digital transformation of the power grid. Through accurate modeling of the power CPS system, complete information physics interaction data can be provided for the intelligent decision system, supporting data-driven power grid operation optimization and risk prevention and control, promoting the transformation of the power system from traditional experience-driven to data-driven intelligent operation mode, and enhancing the stability and reliability of the power grid in complex operating environment.

[0040] The above merely provides the preferred embodiments of the present application, and is not intended to limit the patent scope of the present application. Any equivalent structure variations made according to the present application description and the attached drawings, or direct / indirect application in other related technical fields, shall be included in the patent protection scope of the present application.

Claims

1. A data-driven multi-source information fusion method for a power grid integrated monitoring system, characterized in that: The working steps include: Build a dynamically updated cyber-physical topology model of the power grid based on historical operating data and real-time monitoring data, define cyber-physical nodes in the model, including physical device nodes and information processing nodes, and their multi-dimensional parameter system including operating status parameters and data interaction parameters; Defining the cyber-physical branches involving electrical connection branches and data transmission links in the model, as well as their transmission characteristic parameters, protocol adaptation parameters, and other associated parameters, and systematically detecting the information flow paths and transmission modes under normal operating conditions and fault scenarios within the cyber-physical topology model using multi-dimensional feature analysis and timing correlation detection methods; Normal and faulty information flow patterns within the cyber-physical topology model are detected.

2. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 1 is characterized in that: The construction of the information-physical topology model includes: analyzing the inherent correlation between the power network and the power communication network based on complex system theory, constructing a unified primary and secondary power model, and using a node association matrix to describe the service transmission path.

3. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 2 is characterized in that: The diagonal elements of the node association matrix are CPS nodes, and the off-diagonal elements are CPS transmission lines.

4. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 1 is characterized in that: The cyber-physical node is defined as a combination of power elements, sensing elements, execution elements, decision-making links, and communication links, wherein: The power element is used to characterize the physical state, including element identification, control parameters and element rules; The perception element is used to represent the perception object, including the element identification, the perception object and the perception rule; The execution element is used to represent the control object, including the element identification, the control object and the execution rule; The decision link is used to characterize input and output variables, including link identification, input and output variables and decision rules; The communication link is used to characterize transmission attributes, including link identification, transmission attributes and communication rules.

5. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 4 is characterized in that: The control parameters include maximum control parameters and minimum control parameters, the perception rules include sampling frequency and sampling data reliability, the execution rules include control signal delay threshold and control reliability, the decision rules include logical rules or mathematical calculation rules, and the transmission properties include transmission objects, transmission target elements and channel status.

6. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 1 is characterized in that: The cyber-physical branch is defined as a combination of a physical transmission medium and an information transmission medium, wherein: The physical transmission medium is used to characterize power transmission properties, including branch identification, power transmission properties and power transmission rules; The information transmission medium is used to characterize information transmission attributes, including branch identifiers, information transmission attributes, and information transmission rules.

7. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 6 is characterized in that: The power transmission attributes include the starting and ending points, impedance and capacitance, and power constraints, and the power transmission rules include a power transmission model; the information transmission attributes include the starting and ending points, delay, and load rate, and the information transmission rules include communication link allocation rules.

8. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 1 is characterized in that: The detecting of the information flow mode includes: Monitor the state mutation of physical nodes or branches; The state mutation is measured by the sensing element and transmitted to the sensing element to correct its state; The perception component transmits the state to the decision-making component through the communication link. The decision-making component generates output variables according to the decision rules and sends them to the execution component through the communication link. The actuator controls the state of the physical element.

9. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 8, characterized in that: The state mutation includes an operation state mutation of a physical node or a transmission state mutation of a branch.

10. The multi-source information fusion method for a data-driven integrated power grid monitoring system according to claim 1, characterized in that: The method further includes: performing a coupling analysis on information and power interaction modes between multiple devices and subsystems based on a node association matrix of the cyber-physical topology model.

11. A multi-source information fusion device for a data-driven integrated power grid monitoring system, characterized in that: include: one or more processors; A memory storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the data-driven multi-source information fusion method of the power grid integrated monitoring system as described in any one of claims 1-10.

12. A storage medium containing computer-executable instructions, characterized in that: When executed by a computer processor, the computer executable instructions are used to execute the data-driven multi-source information fusion method for a power grid integrated monitoring system according to any one of claims 1 to 10.

Images