A method and system for constructing a digital space twin cloud range based on cloud computing
By constructing a cloud-based digital twin cloud test range, simulating attack tests and detecting the status of power terminals, the problem of low digitalization in the power system was solved, and the security and reliability of the power system were improved.
Patent Information
- Application Number
- CN202411225145.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-03
AI Technical Summary
The power system is not highly digitalized, and the synchronization and accuracy of twin digital technology are insufficient, making it difficult to effectively cope with the uncertainties and security challenges brought about by the grid connection of new energy sources.
A cloud-based digital space twin cloud test range is constructed. By simulating security attack tests, power terminal response data is obtained, status features are extracted, mapped to virtual nodes, and anomaly detection and early warning are provided.
It improves the safety and reliability of the power system, enabling it to better cope with the uncertainties brought about by the grid connection of new energy sources, and enhances the operational efficiency and safety of the power system.
Smart Images

Figure CN118764316B_ABST
Abstract
Description
Technical Field
[0001] The present invention proposes a method and system for constructing a digital space twin cloud range based on cloud computing, and relates to the technical field of power system information security. Background Art
[0002] As an important source of carbon emissions, the power system needs to support the construction of a new power system with new energy as the main body through digital transformation to achieve deep emission reduction and develop renewable energy. Power digital technology helps promote the transformation of the energy structure to low carbon, electrification, networking, and intelligence, and supports the development of green and low-carbon industries. Power digitalization is the core technical support. Through the deep integration of digital technology and power technology, the power system can be digitalized, informationized, and intelligentized, and the efficiency and energy efficiency of the power system can be improved. By building a digital space twin cloud target range, the power system can better adapt to the transformation of the energy structure, improve operational efficiency, and ensure power supply security.
[0003] With the increase in the proportion of new energy sources connected to the grid, the power system is transforming into a new power system and facing many new problems, especially the uncertainty brought by the connection of new energy sources to the grid, which brings challenges to the modeling of the power system. Digital twin technology has advantages in coping with these changes and is an important means to solve and develop new power systems. Through digital twin technology, the power system can create a digital mirror in the virtual space to achieve comprehensive, accurate and real-time reflection and management of the operation process and status of power equipment assets. Improve the safety of the power system: Digital twin technology can be used for monitoring, intelligent analysis and digital autonomy of the power system to improve the safety and reliability of the power system. However, in terms of the digitization of the power system, the integration of power electronics technology and digital technology is not enough, and the synchronization and accuracy of twin digital technology are not high. Summary of the invention
[0004] In order to solve the above technical problems, the present invention proposes a method for constructing a digital space twin cloud range based on cloud computing, comprising the following steps:
[0005] S1. Conduct a simulated security attack test on the power Internet of Things to obtain the response data of each power terminal under the simulated security attack test;
[0006] S2, extracting state characteristics at a fixed frequency from the response data of each power terminal to obtain state characteristic data;
[0007] S3. According to the connection relationship of each power terminal in the power Internet of Things, the topological relationship of the virtual nodes of the twin cloud target range is constructed, and the state feature data of the power terminal is mapped to the digital space of the virtual node in the twin cloud target range to obtain the virtual feature data;
[0008] S4. Check the virtual feature data in the digital space of the virtual node to determine whether the state of the virtual node corresponding to the virtual feature data is abnormal. If the state is abnormal, provide early warning feedback to the power terminal corresponding to the virtual node.
[0009] Furthermore, in step S2, the reaction data of the power terminal are collected at N sampling moments within the sampling period t, and the frequency domain signal of the reaction data is obtained by applying the fast Fourier transform, and the state characteristic data D of the power terminal at the fixed frequency f is extracted by using the frequency domain signal:
[0010]
[0011] Where Z is the normalization constant, is the attenuation coefficient, x n (f) is the frequency domain signal at a fixed frequency f at the nth sampling moment.
[0012] Furthermore, in step S3, the mapping availability A of the virtual feature data is calculated:
[0013]
[0014] In the formula, m represents the number of power terminals in the power Internet of Things, which is also the number of virtual nodes in the twin cloud target range; D i represents the state characteristic data of the i-th power terminal in the power Internet of Things, S i represents the mapping value of the state characteristic data of the i-th power terminal in the power Internet of Things in the twin cloud target range, and the normalization function F converts D i Normalized to the interval [0,1];
[0015] When the mapping availability A is below the threshold, the mapping value S i It can serve as virtual feature data of a virtual node corresponding to the i-th power terminal and be synchronized in the digital space of the corresponding virtual node.
[0016] Furthermore, in step S4, during the security attack test cycle Get the virtual feature data of virtual node j in the tth sampling period , , the period is obtained by the following formula The state deviation value W of each virtual node j in j ;
[0017]
[0018]
[0019] in, The standard state data of virtual node j in sampling period t is , m is the number of virtual nodes, as well as is the proportionality coefficient;
[0020] When the state deviation value W j Exceeding the deviation threshold W th , then the virtual feature data of the virtual node j is abnormal, and the state of the power terminal corresponding to the virtual node j has a safety hazard.
[0021] Furthermore, in step S3, a power terminal partition data stream collection mode is adopted between the twin cloud target range and the power Internet of Things, and data streams of multiple power terminals in different areas are collected and mapped in the power Internet of Things, and data streams are synchronized with multiple virtual nodes in the corresponding virtual intervals in the twin cloud target range.
[0022] The present invention also proposes a digital space twin cloud range construction system based on cloud computing, which is implemented by the above-mentioned digital space twin cloud range construction method based on cloud computing. The digital space twin cloud range construction system includes: a security attack test unit, a reaction data acquisition unit, a state feature extraction unit, a digital twin construction unit and a verification unit;
[0023] The security attack testing unit is responsible for simulating security attack testing on the power Internet of Things;
[0024] The reaction data acquisition unit obtains reaction data of each power terminal under the simulated security attack test;
[0025] The state feature extraction unit extracts state features at a fixed frequency from the response data of each power terminal to obtain state feature data;
[0026] The digital twin construction unit is used to construct the topological relationship of the virtual nodes of the twin cloud range according to the connection relationship of each power terminal in the power Internet of Things, map the state feature data of the power terminal to the digital space of the virtual node in the twin cloud range, and obtain virtual feature data;
[0027] The inspection unit is used to inspect the virtual feature data in the digital space of the virtual node to determine whether the state of the virtual node corresponding to the virtual feature data is abnormal. If the state is abnormal, an early warning feedback is sent to the power terminal corresponding to the virtual node.
[0028] Furthermore, the digital twin construction unit simulates the physical properties of the virtual nodes for the power terminals that can be directly mapped in the power Internet of Things. For the power terminals that cannot be directly mapped, the management end and the business end of the power terminal are dynamically connected to the ports of the virtual nodes corresponding to the twin cloud target range, and the physical properties are simulated in combination with the historical data of the virtual nodes.
[0029] Compared with the prior art, the present invention has the following beneficial technical effects:
[0030] Conduct simulated security attack tests on the power Internet of Things to identify potential power terminals with risks. Through simulated attacks, we can better understand the performance and response capabilities of power terminals in the power system when facing real attacks; obtain the response data of each power terminal under the simulated security attack test, which is conducive to representing the operating status of the power terminal under the simulated security attack test; extract the state features of the response data of each power terminal at a fixed frequency to obtain state feature data, which is helpful for subsequent in-depth analysis of the power Internet of Things; according to the connection relationship of each power terminal in the power Internet of Things, construct the topological relationship of the virtual nodes of the twin cloud target range, map the state feature data of the power terminal to the digital space of the virtual node in the twin cloud target range, and obtain virtual feature data for simulating and testing the state of the power terminal under different attack simulations; check the virtual feature data in the digital space of the virtual node to determine whether the state of the virtual node corresponding to the virtual feature data is abnormal. If the state is abnormal, provide early warning feedback to the power terminal corresponding to the virtual node. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0032] Figure 1 It is a flow chart of the method for constructing a digital space twin cloud range based on cloud computing of the present invention;
[0033] Figure 2 It is a schematic diagram of the relationship between the twin cloud target range and the power Internet of Things of the present invention;
[0034] Figure 3 This is a schematic diagram of the system structure for building a digital space twin cloud range based on cloud computing of the present invention. DETAILED DESCRIPTION
[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0036] In the drawings of the specific embodiments of the present invention, in order to better and more clearly describe the working principles of the various components in the system, the connection relationship of the various parts in the device is shown, which only clearly distinguishes the relative position relationship between the various components, and cannot constitute a limitation on the signal transmission direction, connection sequence and structural size, size and shape of each part within the component or structure.
[0037] Example 1
[0038] like Figure 1 The figure shows a flow chart of a method for constructing a digital space twin cloud range based on cloud computing of the present invention, which includes the following steps:
[0039] S1. Conduct simulated security attack tests on the power Internet of Things and obtain the response data of each power terminal under the simulated security attack test.
[0040] The entire network is tested for security attacks, and the state data sensed by the sensors of the power terminals are collected to obtain a state data set of multiple sensing terminals. In this embodiment, the state data mainly refers to the operation state data, such as whether the equipment is operating abnormally at a certain moment.
[0041] The security attack test of the entire network is to conduct an attack experiment on the target power terminal (power collection terminal, electric vehicle charging pile, on-site safety supervision and control terminal, etc.) through a certain attack method (abnormal operation). The security test conducts a comprehensive security test on the target object to verify the security of the target object.
[0042] S2. Extract state characteristics at a fixed frequency from the response data of each power terminal to obtain state characteristic data.
[0043] The state feature extraction at a fixed frequency is performed on the reaction data of each power terminal. The state feature data can reflect the real operating state of the power terminal under the simulated security attack test. Fast Fourier transform is applied to the time domain signal of the reaction data to convert it into the frequency domain signal of the reaction data. Within the sampling period t, the frequency domain signal at a fixed frequency f at N moments is collected. The state feature data D of the power terminal at the fixed frequency f is calculated using the frequency domain signal and is expressed as:
[0044]
[0045] Where Z is the normalization constant, is the attenuation coefficient, x n (f) is the frequency domain signal at the fixed frequency f at the nth sampling moment, N is the total number of sampling moments, is the attenuation coefficient; exp represents the exponential function with e (approximately equal to 2.71828) as the base.
[0046] S3. According to the connection relationship between each power terminal in the power Internet of Things, the topological relationship of the virtual nodes of the twin cloud target range is constructed, and the state characteristic data of the power terminal is mapped to the digital space of the virtual node in the twin cloud target range to obtain the virtual characteristic data.
[0047] First, according to the connection relationship of each power terminal in the power Internet of Things, the topological relationship of the virtual nodes of the twin cloud target range is constructed, and the physical properties of the virtual nodes of the power terminals that can be directly mapped in the power Internet of Things are simulated. For the power terminals that cannot be directly mapped, the virtual network simulation capability is used to dynamically connect the management end and business end of the power terminals that cannot be directly mapped to the ports of the virtual nodes corresponding to the digital space twin cloud target range, and the physical properties are simulated in combination with the historical data of the virtual nodes.
[0048] The digital space twin cloud target range and the real power Internet of Things adopt a power terminal partition data stream collection mode. In the power Internet of Things, the data streams of multiple power terminals in different areas are collected and mapped in a targeted manner, and a data stream partition synchronization strategy is formulated. The data streams of multiple power terminals in these areas are synchronized in multiple virtual nodes in the virtual interval corresponding to the digital space twin cloud target range, thereby improving the synchronization effect.
[0049] As an information-physical system, the power Internet of Things is vulnerable to false data injection attacks, which may interfere with the device state estimation and cause abnormal virtual node state. In order to improve the security of data, an object-relational mapping framework is adopted to simplify data operations by abstracting data operations into mapping object operations, while preventing false data injection attacks.
[0050] In a preferred embodiment, S i Represents the state characteristic data D of the i-th power terminal in the power Internet of Things i The mapping value in the twin cloud range, the mapping relationship between the two is as follows:
[0051]
[0052] The mod() function represents the modulus operation, that is, finding the remainder after dividing two numbers. i Represents the equipment identification code of the i-th power terminal.
[0053] The state characteristic data of the power terminal is mapped to the digital space of the virtual node in the twin cloud range to obtain virtual characteristic data. The state characteristic data stream of the power Internet of Things is transmitted to the digital space of multiple virtual nodes in the twin cloud range through the above method to construct a virtual characteristic data stream. These virtual characteristic data streams are virtual mappings of the state characteristic data streams of the actual power Internet of Things, which are used to simulate and optimize the operating status of multiple power terminals of the power Internet of Things.
[0054] The mapping availability of the virtual feature data of the created digital space is calculated, and the mapping availability A is as follows:
[0055]
[0056] In the formula, m represents the number of power terminals in the power Internet of Things, which is also the number of virtual nodes in the twin cloud target range; D i represents the state characteristic data of the i-th power terminal in the power Internet of Things, S i Represents the state characteristic data D of the i-th power terminal in the power Internet of Things i The mapping value in the twin cloud range, F is the normalization function, D i Normalized to the interval [0,1]; when the mapping availability A is below the threshold, the mapping value S i It can serve as virtual feature data of the virtual node corresponding to the i-th power terminal and be synchronized in the digital space of the virtual node.
[0057] S4. Check the virtual feature data in the digital space of the virtual node to determine whether the state of the virtual node corresponding to the virtual feature data is abnormal. If the state is abnormal, provide early warning feedback to the power terminal corresponding to the virtual node.
[0058] In the security attack test cycle Get the virtual feature data of virtual node j in the tth sampling period , , the period is obtained by the following formula The state deviation value W of each virtual node j in j ;
[0059]
[0060]
[0061] in, The standard state data of virtual node j in sampling period t is , m is the number of virtual nodes, as well as is the proportionality coefficient.
[0062] The state deviation value W j Exceeding the deviation threshold W th , it is considered that the virtual feature data of the virtual node j is abnormal, which proves that the state of the power terminal corresponding to the virtual node j has safety hazards, such as the rapid change of the corresponding power terminal load or power generation resources affecting the stability of the power system; the corresponding power terminal is short-circuited or disconnected, which may affect the current and voltage levels.
[0063] Example 2
[0064] The present invention also proposes a digital space twin cloud range construction system based on cloud computing, such as Figure 2 As shown, the digital space twin cloud range construction system is executed by the central processing unit in the figure. The central processing unit obtains the reaction data of the power terminal of the power Internet of Things. The reaction data is stored in the memory of each power terminal, and a virtual node corresponding to each power terminal is constructed in the twin cloud range according to each power terminal in the power Internet of Things.
[0065] The present invention also proposes a digital space twin cloud range construction system based on cloud computing, which involves the collaborative work of multiple units to ensure the security and stability of the power Internet of Things. Figure 3 As shown, the digital space twin cloud range construction system includes: a security attack testing unit, a reaction data acquisition unit, a state feature extraction unit, a digital twin construction unit and a verification unit.
[0066] The security attack test unit is responsible for simulating security attack tests on the power Internet of Things to identify potential power terminals with risks. The number of power terminals in the power Internet of Things is huge and growing explosively. The connected power terminals are of various types, scattered distribution, and different communication methods. The existing security threats are complex and complicated. The security of power terminals is an important foundation for ensuring the healthy development of the power Internet of Things. By simulating attacks, we can better understand the performance and response capabilities of the system's power terminals when facing real attacks.
[0067] The reaction data acquisition unit obtains the reaction data of each power terminal under the simulated security attack test. The reaction data is crucial for monitoring the operating status of the power terminal under the simulated security attack test and judging possible risks.
[0068] The state feature extraction unit extracts the state features of the response data of each power terminal at a fixed frequency to obtain state feature data; the state feature data helps to conduct a deeper analysis and understanding of the power Internet of Things.
[0069] The digital twin construction unit is used for the security attack test unit, the reaction data acquisition unit, the state feature extraction unit, the digital twin construction unit and the inspection unit;
[0070] The security attack testing unit is responsible for simulating security attack testing on the power Internet of Things;
[0071] The reaction data acquisition unit obtains reaction data of each power terminal under the simulated security attack test;
[0072] The state feature extraction unit extracts state features at a fixed frequency from the response data of each power terminal to obtain state feature data;
[0073] The digital twin construction unit is used to construct the topological relationship of the virtual nodes of the twin cloud target range according to the connection relationship between each power terminal in the power Internet of Things, and map the state characteristic data of the power terminal to the digital space of the virtual node in the twin cloud target range to obtain virtual characteristic data; the twin cloud target range is a virtual digital model corresponding to the actual power Internet of Things, which is used to simulate and test the risks of power terminals under different attack simulations.
[0074] In a preferred embodiment, the scale parameters of the preset twin cloud range are used to support the simulation and operation of multiple preset application scenarios. Based on the constructed twin cloud range, the virtual network configuration is adjusted, the resource allocation of virtual nodes is optimized, and a digital space in operation is constructed. The digital space in operation can simulate the actual power Internet of Things data flow and data interaction process.
[0075] The inspection unit is used to inspect the virtual feature data in the digital space of the virtual node to determine whether the state of the virtual node corresponding to the virtual feature data is abnormal. If the state is abnormal, an early warning feedback is sent to the power terminal corresponding to the virtual node.
[0076] Once an abnormal state is detected, the digital space twin cloud target range will evaluate the possible impact of the abnormal state on the operation of the power Internet of Things and trigger the early warning mechanism; the early warning feedback can directly act on the power terminal through the intelligent control terminal to achieve reverse intervention and control of the physical equipment.
[0077] Preferably, after detecting an anomaly and issuing an early warning, dynamic scheduling optimization of the power terminal is also required to adapt to emergencies in the operation of the power system. The digital space twin cloud range needs to be continuously iterated and updated based on new data and feedback to maintain its accuracy and reliability.
[0078] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.
[0079] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A method for constructing a digital space twin cloud range based on cloud computing, characterized in that: The steps include: S1. Conduct a simulated security attack test on the power Internet of Things to obtain the response data of each power terminal under the simulated security attack test; S2. Extract the state characteristics of the reaction data of each power terminal at a fixed frequency to obtain the state characteristic data; collect the reaction data of the power terminal at N sampling moments within the sampling period t, apply fast Fourier transform to obtain the frequency domain signal of the reaction data, and use the frequency domain signal to extract the state characteristic data D of the power terminal at the fixed frequency f: ; Where Z is the normalization constant, is the attenuation coefficient, x n (f) is the frequency domain signal at a fixed frequency f at the nth sampling moment; S3. According to the connection relationship of each power terminal in the power Internet of Things, the topological relationship of the virtual nodes of the twin cloud target range is constructed, and the state feature data of the power terminal is mapped to the digital space of the virtual node in the twin cloud target range to obtain the virtual feature data; Calculate the mapping availability A of the virtual feature data: ; In the formula, m represents the number of power terminals in the power Internet of Things, which is also the number of virtual nodes in the twin cloud target range; D i represents the state characteristic data of the i-th power terminal in the power Internet of Things, S i represents the mapping value of the state characteristic data of the i-th power terminal in the power Internet of Things in the twin cloud target range, and the normalization function F converts D i Normalized to the interval [0,1]; When the mapping availability A is below the threshold, the mapping value S i can be used as virtual feature data of a virtual node corresponding to the i-th power terminal and synchronized in the digital space of the corresponding virtual node; S4, checking the virtual feature data in the digital space of the virtual node to determine whether the state of the virtual node corresponding to the virtual feature data is abnormal, and if the state is abnormal, providing early warning feedback to the power terminal corresponding to the virtual node; In the security attack test cycle Get the virtual feature data of virtual node j in the tth sampling period , , the period is calculated by the following formula The state deviation value W of each virtual node j in j ; ; ; in, is the standard state data of virtual node j in sampling period t, m is the number of virtual nodes, as well as is the proportionality coefficient; When the state deviation value W j Exceeding the deviation threshold W th , then the virtual feature data of the virtual node j is abnormal, and the state of the power terminal corresponding to the virtual node j has a safety hazard.
2. According to the method for constructing a digital space twin cloud range based on cloud computing as described in claim 1, it is characterized in that: In step S3, a power terminal partition data stream collection mode is adopted between the twin cloud target range and the power Internet of Things, and data streams of multiple power terminals in different areas are collected and mapped in the power Internet of Things, and data streams are synchronized with multiple virtual nodes in the corresponding virtual intervals in the twin cloud target range.
3. A digital space twin cloud range construction system based on cloud computing, characterized in that: The method for constructing a digital space twin cloud range based on cloud computing as described in any one of claims 1 to 2 is adopted, and the digital space twin cloud range construction system includes: a security attack test unit, a reaction data acquisition unit, a state feature extraction unit, a digital twin construction unit and a verification unit; The security attack testing unit is responsible for simulating security attack testing on the power Internet of Things; The reaction data acquisition unit obtains reaction data of each power terminal under the simulated security attack test; The state feature extraction unit extracts state features at a fixed frequency from the response data of each power terminal to obtain state feature data; The digital twin construction unit is used to construct the topological relationship of the virtual nodes of the twin cloud range according to the connection relationship of each power terminal in the power Internet of Things, map the state feature data of the power terminal to the digital space of the virtual node in the twin cloud range, and obtain virtual feature data; The inspection unit is used to inspect the virtual feature data in the digital space of the virtual node to determine whether the state of the virtual node corresponding to the virtual feature data is abnormal. If the state is abnormal, an early warning feedback is sent to the power terminal corresponding to the virtual node.
4. According to the cloud computing-based digital space twin cloud range construction system described in claim 3, it is characterized in that: The digital twin construction unit simulates the physical properties of virtual nodes for power terminals that can be directly mapped in the power Internet of Things. For power terminals that cannot be directly mapped, the management end and business end of the power terminal are dynamically connected to the ports of the virtual nodes corresponding to the twin cloud target range, and physical property simulation is performed in combination with the historical data of the virtual nodes.
