System stability analysis method based on neural differential equation and energy function

Abstract

The invention discloses a system stability analysis method based on a neural differential equation and an energy function, and the method comprises the steps: building the neural differential equation of a power system, and simulating a dynamic trajectory of the power system; when the power system is subjected to large disturbance, determining an initial balance point of the power system; determining a dominant unstable balance point of the power system based on the dynamic trajectory and the initial balance point; determining a critical energy value of the power system by using the dominant unstable equilibrium point; selecting a to-be-measured point, calculating an energy function value of the to-be-measured point, and calculating an energy function value of an initial balance point; and according to the energy function value of the initial balance point, the energy function value of the to-be-measured point and the critical energy value, determining the stability of the power system after large disturbance. According to the scheme, the accurate dynamic trajectory of the power system can be obtained, the stable state of the power system after large disturbance is comprehensively analyzed by utilizing the energy function values of the to-be-measured point and the initial balance point and the critical energy value, and the analysis accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of system stability analysis, and specifically to a system stability analysis method based on neural differential equations and energy functions. Background Art

[0002] In today's society that is highly dependent on electricity, the stable operation of the power system is of vital importance. With the rapid development of the economy and the continuous advancement of science and technology, the demand for electricity continues to grow, and the scale and complexity of the power system are also increasing. During the operation of the power system, it is inevitable that it will face the impact of various large disturbances. The impact of large disturbances may directly damage the infrastructure of the power system and cause the power system to lose stability. Therefore, the stability analysis of the power system after a large disturbance is a key issue to ensure the safe operation of the power system.

[0003] Traditional stability analysis methods include time domain simulation and direct methods, which can provide partial information on the dynamic behavior of the power system. However, after the power system is subjected to a large disturbance, the situation becomes complicated and there will be multiple equilibrium points. Traditional methods cannot accurately combine multiple equilibrium points for stability analysis, resulting in a low accuracy rate of the analysis results. Summary of the invention

[0004] In view of this, the present application provides a system stability analysis method based on neural differential equations and energy functions, which is used to solve the problem that after the power system is subjected to a large disturbance, the situation is complicated and there will be multiple equilibrium points. The traditional method cannot accurately combine multiple equilibrium points for stability analysis, resulting in a low accuracy rate of the analysis results.

[0005] To achieve the above objectives, the proposed solution is as follows:

[0006] In the first aspect, a system stability analysis method based on neural differential equations and energy functions includes:

[0007] Establishing a neural differential equation for a power system, and simulating a dynamic trajectory of the power system using the neural differential equation;

[0008] When the power system is subjected to a large disturbance, determining an initial equilibrium point of the power system;

[0009] Determining a dominant unstable equilibrium point of the power system based on the dynamic trajectory and the initial equilibrium point;

[0010] Determining a critical energy value of the power system using the dominant unstable equilibrium point;

[0011] Selecting a point to be measured, and calculating the energy function value of the point to be measured, and calculating the energy function value of the initial equilibrium point at the same time;

[0012] The stability of the power system after being subjected to a large disturbance is determined according to the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value.

[0013] Preferably, determining the dominant unstable balance point of the power system based on the dynamic trajectory and the initial balance point includes:

[0014] Starting from the initial balance point, integrating the dynamic trajectory in the time domain to determine the dynamic region of the power system;

[0015] determining an intersection point between the dynamic region and the dynamic trajectory;

[0016] Taking the intersection point as a starting point, integrating the gradient equation of the power system along the dynamic trajectory to determine the minimum gradient point of the power system;

[0017] Based on the minimum gradient point, a power deviation equation of the power system is calculated to obtain a dominant unstable equilibrium point.

[0018] Preferably, the determining the critical energy value of the power system by using the dominant unstable equilibrium point includes:

[0019] constructing an energy function according to the neural differential equation;

[0020] The function value of the energy function at the dominant unstable equilibrium point is calculated, and the function value is used as the critical energy value of the power system.

[0021] Preferably, constructing an energy function according to the neural differential equation comprises:

[0022] Defining state quantity parameters of the power system;

[0023] Constructing a nonlinear differential equation based on the state quantity parameters;

[0024] Solving the nonlinear differential equation using the neural differential equation to obtain network parameters in the nonlinear differential equation;

[0025] An energy function is constructed based on the network parameters.

[0026] Preferably, determining the stability of the power system after a large disturbance according to the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value comprises:

[0027] Calculating the stability margin of the power system according to the energy function value of the initial balance point, the energy function value of the point to be measured and the critical energy value;

[0028] If the stability margin is not less than a preset first threshold, determining that the power system is in a stable state after being subjected to a large disturbance;

[0029] If the stability margin is smaller than the first threshold, it is determined that the power system is in an unstable state after being subjected to a large disturbance.

[0030] Preferably, the calculation formula of the stability margin of the power system is:

[0031] ;

[0032] in, represents the stability margin, Represents the energy function value of the point to be tested, represents the energy function value of the initial equilibrium point, Represents the critical energy value.

[0033] Preferably, the state trajectory equation of the dynamic trajectory is:

[0034] ;

[0035] in, and All are time points, Indicates the power system at time point status, is the initial state of the power system at the initial equilibrium point, is the time point corresponding to the initial equilibrium point, is a nonlinear differential equation, is the network parameter in the nonlinear differential equation, The power system at any point in time status.

[0036] In a second aspect, a system stability analysis device based on neural differential equations and energy functions comprises:

[0037] A dynamic trajectory simulation module, used to establish a neural differential equation of the power system and simulate the dynamic trajectory of the power system using the neural differential equation;

[0038] A balance point determination module, used to determine the initial balance point of the power system when the power system is subjected to a large disturbance;

[0039] A dominant unstable balance point determination module, used to determine the dominant unstable balance point of the power system based on the dynamic trajectory and the initial balance point;

[0040] A critical energy value determination module, used to determine the critical energy value of the power system by using the dominant unstable equilibrium point;

[0041] An energy function value calculation module is used to select a point to be measured, calculate the energy function value of the point to be measured, and calculate the energy function value of the initial equilibrium point at the same time;

[0042] The stability analysis module is used to determine the stability of the power system after a large disturbance based on the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value.

[0043] In a third aspect, a system stability analysis device based on neural differential equations and energy functions includes a memory and a processor;

[0044] The memory is used to store programs;

[0045] The processor is used to execute the program to implement the various steps of the system stability analysis method based on neural differential equations and energy functions as described in any one of the first aspects.

[0046] In a fourth aspect, a storage medium stores a computer program thereon, wherein when the computer program is executed by a processor, the steps of the system stability analysis method based on neural differential equations and energy functions as described in any one of the first aspects are implemented.

[0047] It can be seen from the above technical scheme that the present application establishes a neural differential equation of the power system, and uses the neural differential equation to simulate the dynamic trajectory of the power system; when the power system is subjected to a large disturbance, determines the initial balance point of the power system; based on the dynamic trajectory and the initial balance point, determines the dominant unstable balance point of the power system; uses the dominant unstable balance point to determine the critical energy value of the power system; selects a point to be tested, and calculates the energy function value of the point to be tested, and at the same time calculates the energy function value of the initial balance point; determines the stability of the power system after a large disturbance based on the energy function value of the initial balance point, the energy function value of the point to be tested, and the critical energy value. This scheme uses neural differential equations for simulation, which can obtain the accurate dynamic trajectory of the power system. When the power system is subjected to a large disturbance, the initial balance point of the power system is first determined. This balance point shows the initial balance information of the power system and can provide a basis for subsequent comparison. In addition, the dominant unstable balance point needs to be determined. This point is a balance point where the power system tends to be unstable after a large disturbance, so as to determine the critical energy value of the point, and then select a test point. The energy function value at the test point, the critical energy value and the energy function value of the initial balance point are used to comprehensively analyze the stable state of the power system after a large disturbance. This can not only improve the accuracy of the analysis, but also clarify the stability boundary and critical energy of the power system, effectively improving the stability analysis and evaluation capabilities of the power system under large disturbances, which is beneficial to the subsequent operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0049] Figure 1 An optional flow chart of a system stability analysis method based on neural differential equations and energy functions provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of the structure of a system stability analysis device based on neural differential equations and energy functions provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of the structure of a system stability analysis device based on neural differential equations and energy functions provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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.

[0053] The present invention can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, distributed computing environments including any of the above devices or devices, etc.

[0054] The embodiment of the present invention provides a system stability analysis method based on neural differential equations and energy functions. The method can be applied to various computer terminals or intelligent terminals. The execution subject can be a processor or server of the computer terminal or intelligent terminal. The method flow chart of the method is as follows: Figure 1 As shown, specifically including:

[0055] S1: Establish a neural differential equation for the power system, and use the neural differential equation to simulate the dynamic trajectory of the power system.

[0056] The present application utilizes the dynamic trajectory of the power system to analyze the stability after a large disturbance. The dynamic trajectory can intuitively and vividly display the dynamic behavior or fault response of the power system.

[0057] The neural differential equation is the neural ordinary differential equation NODE, which is a model that combines neural networks and ordinary differential equations. It is based on neural differential equations and can represent continuous dynamic changes in time. Therefore, this application uses neural differential equations to simulate the dynamic trajectory of the power system. It should be noted that the simulation process is always ongoing, especially after a large disturbance, the dynamic trajectory of the power system after the large disturbance is still being simulated. The dynamic trajectory after a large disturbance can also be regarded as a fault trajectory.

[0058] Neural differential equations can provide high-capacity function approximation and fitting capabilities, can flexibly learn and represent complex power system dynamic characteristics, and can be trained to capture these complex relationships, thereby more accurately simulating the dynamic trajectory of the power system.

[0059] S2: When the power system is subjected to a large disturbance, an initial balance point of the power system is determined.

[0060] Large disturbances can be regarded as external shocks with greater impacts, including but not limited to natural disasters, equipment tripping, external force attacks, voltage changes, etc. Under normal circumstances, the power system operates normally and is stable, but after being subjected to these large disturbances, its stability will change. Therefore, an initial balance point / stable point should be determined first, which can be used as a basis for subsequent comparisons and used as the initial balance point.

[0061] S3: Based on the dynamic trajectory and the initial balance point, determine the dominant unstable balance point of the power system.

[0062] After a power system is subjected to a large disturbance, its dynamic trajectory will change. The dominant unstable equilibrium point is an unstable equilibrium point to which the system's dynamic trajectory tends. It is the key point that indicates that the power system has lost stability. A simple analysis shows that if the power system can stay away from the dominant unstable equilibrium point after a large disturbance, then the power system may remain stable. If it tends to the dominant unstable equilibrium point, then the power system may lose stability.

[0063] In order to more accurately determine the stability of the power system, this application does not analyze the dominant unstable equilibrium point in combination with other points.

[0064] S4: Determine a critical energy value of the power system using the dominant unstable equilibrium point.

[0065] The critical energy value refers to the energy function value at the dominant unstable equilibrium point. The energy function can map the state of the power system to a real number, representing the energy value of the state, which can reflect the stability of the power system. Therefore, this step solves the energy function value at the dominant unstable equilibrium point as the critical energy value of the power system, which is also the reference value of the energy boundary of the power system. The method of analyzing the stability of the power system using the dominant unstable equilibrium point can be regarded as the BCU (Boundary Controlling Unstable Equilibrium Point) method.

[0066] S5: Select a point to be measured, and calculate the energy function value of the point to be measured, and simultaneously calculate the energy function value of the initial equilibrium point.

[0067] The point to be tested refers to any point on the power system after it is subjected to a large disturbance. Any point selected can indicate the stability of the power system at that point.

[0068] Similarly, the energy function value at the point to be tested is calculated. In order to make the analysis more comprehensive, the energy function value at the initial equilibrium point also needs to be calculated.

[0069] S6: Determine the stability of the power system after a large disturbance according to the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value.

[0070] By comprehensively analyzing the energy function values ​​at the three points, the stability of the power system after a large disturbance can be accurately analyzed.

[0071] It can be seen from the above technical scheme that the present application establishes a neural differential equation of the power system, and uses the neural differential equation to simulate the dynamic trajectory of the power system; when the power system is subjected to a large disturbance, determines the initial balance point of the power system; based on the dynamic trajectory and the initial balance point, determines the dominant unstable balance point of the power system; uses the dominant unstable balance point to determine the critical energy value of the power system; selects a point to be tested, and calculates the energy function value of the point to be tested, and at the same time calculates the energy function value of the initial balance point; determines the stability of the power system after a large disturbance based on the energy function value of the initial balance point, the energy function value of the point to be tested, and the critical energy value. This scheme uses neural differential equations for simulation, which can obtain the accurate dynamic trajectory of the power system. When the power system is subjected to a large disturbance, the initial balance point of the power system is first determined. This balance point shows the initial balance information of the power system and can provide a basis for subsequent comparison. In addition, the dominant unstable balance point needs to be determined. This point is a balance point where the power system tends to be unstable after a large disturbance, so as to determine the critical energy value of the point, and then select a test point. The energy function value at the test point, the critical energy value and the energy function value of the initial balance point are used to comprehensively analyze the stable state of the power system after a large disturbance. This can not only improve the accuracy of the analysis, but also clarify the stability boundary and critical energy of the power system, effectively improving the stability analysis and evaluation capabilities of the power system under large disturbances, which is beneficial to the subsequent operation of the power system.

[0072] In the method provided in the embodiment of the present invention, the process of determining the dominant unstable balance point of the power system based on the dynamic trajectory and the initial balance point is specifically described as follows:

[0073] Starting from the initial balance point, integrating the dynamic trajectory in the time domain to determine the dynamic region of the power system;

[0074] determining an intersection point between the dynamic region and the dynamic trajectory;

[0075] Taking the intersection point as a starting point, integrating the gradient equation of the power system along the dynamic trajectory to determine the minimum gradient point of the power system;

[0076] Based on the minimum gradient point, a power deviation equation of the power system is calculated to obtain a dominant unstable equilibrium point.

[0077] Specifically, starting from the initial equilibrium point, time domain integration is performed along the dynamic trajectory to determine the dynamic area of ​​the power system. At the same time, the simulation process is still going on, and the future trajectory can be predicted. By gradually integrating the dynamic trajectory, the exit point (EP) of the dynamic trajectory can be detected. The exit point refers to the intersection between the dynamic area and the contraction boundary of the dynamic trajectory. The appearance of this intersection means that the power system begins to leave the stable area, that is, it leaves the stable area from this intersection and approaches the unstable area.

[0078] Next, take the intersection point as the starting point and continue to integrate the gradient equation of the power system along the dynamic trajectory to find the minimum gradient point MGP (Minimum Gradient Point). The minimum gradient point is the point with the smallest gradient value, which can represent the state of the power system with the smallest energy change near the stable boundary. The minimum gradient point can be determined by the following gradient equation:

[0079] ;

[0080] in, It can describe the total energy in the power system state. Represents the gradient of the energy function. The minimum gradient point is also a point close to an unstable state but with the smallest energy change.

[0081] Taking the minimum gradient point as the initial condition, the power deviation equation of the power system is further solved to obtain the controlling unstable equilibrium point CUEP (Controlling Unstable Equilibrium Point), which is as follows:

[0082] ;

[0083] in, As the dominant unstable equilibrium point, is the Lagrange multiplier, which is used to adjust the power deviation. By solving this formula, the dominant unstable equilibrium point of the power system is located, and the dominant unstable equilibrium point determines the stability boundary of the power system.

[0084] The following embodiment illustrates the process of determining the critical energy value of the power system by utilizing the dominant unstable equilibrium point in the present application.

[0085] constructing an energy function according to the neural differential equation;

[0086] The function value of the energy function at the dominant unstable equilibrium point is calculated, and the function value is used as the critical energy value of the power system.

[0087] Specifically, the critical energy value of the power system refers to the function value of the energy function at the dominant unstable equilibrium point. The energy function is expressed as , which depends on the network parameters , then the critical energy value for:

[0088] ;

[0089] The critical energy value represents the energy boundary of the power system from stability to instability.

[0090] Furthermore, the energy function can be constructed based on the neural differential equation. First, the state parameters of the power system are defined to establish a nonlinear differential equation, which can also be regarded as a derivative function:

[0091] ;

[0092] in, is the state of the power system, such as generator phase angle, speed and other dynamic variables, is the input vector, which represents the control input of the system or the external large disturbance. The neural differential equation is used to solve the nonlinear differential equation and adjust the network parameters. , and use the adjusted network parameters to construct the energy function .

[0093] Next, the steps of determining the stability of the power system after a large disturbance based on the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value in the present application are described in detail.

[0094] Calculating the stability margin of the power system according to the energy function value of the initial balance point, the energy function value of the point to be measured and the critical energy value;

[0095] If the stability margin is not less than a preset first threshold, determining that the power system is in a stable state after being subjected to a large disturbance;

[0096] If the stability margin is smaller than the first threshold, it is determined that the power system is in an unstable state after being subjected to a large disturbance.

[0097] Specifically, the calculation formula of the stability margin of the power system is:

[0098] ;

[0099] in, It represents the stability margin, which refers to the relative safety level of the current state of the power system relative to the critical unstable state. Indicates the point to be tested ( The energy function value at time , represents the initial equilibrium point (time point ), Represents the critical energy value.

[0100] The first threshold can be set to a value close to 0 and greater than 0, such as 0.1. If the stability margin is not less than 0.1, it indicates that the power system can still remain stable after a large disturbance. If the stability margin is less than 0.1, for example, it is greater than 0 but infinitely close to 0, or less than 0, it indicates that the power system may be close to an unstable state.

[0101] ;

[0102] .

[0103] Furthermore, the state trajectory equation of the dynamic trajectory is:

[0104] ;

[0105] in, and All are time points, Indicates the power system at time point status, It can also be regarded as a time point corresponding to a point to be tested. is the initial state of the power system at the initial equilibrium point, that is, at the initial equilibrium point (time point ) status, is the time point corresponding to the initial equilibrium point, is a nonlinear differential equation, which refers to the state quantity of the power system. is the network parameter in the nonlinear differential equation, The power system at any point in time status.

[0106] and Figure 1 Corresponding to the method described above, the embodiment of the present invention also provides a system stability analysis device based on neural differential equations and energy functions, which is used to analyze the system stability of the system. Figure 1 The specific implementation of the method in the embodiment of the present invention is that the system stability analysis device based on neural differential equations and energy functions can be used in a computer terminal or various mobile devices, combined with Figure 2 , the system stability analysis device based on neural differential equations and energy functions is introduced, such as Figure 2 As shown, the device may include:

[0107] A dynamic trajectory simulation module 10, used to establish a neural differential equation of the power system and simulate the dynamic trajectory of the power system using the neural differential equation;

[0108] A balance point determination module 20, used to determine the initial balance point of the power system when the power system is subjected to a large disturbance;

[0109] A dominant unstable balance point determination module 30, for determining a dominant unstable balance point of the power system based on the dynamic trajectory and the initial balance point;

[0110] A critical energy value determination module 40, configured to determine a critical energy value of the power system using the dominant unstable equilibrium point;

[0111] An energy function value calculation module 50 is used to select a point to be measured, and calculate the energy function value of the point to be measured, and simultaneously calculate the energy function value of the initial equilibrium point;

[0112] The stability analysis module 60 is used to determine the stability of the power system after a large disturbance according to the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value.

[0113] It can be seen from the above technical scheme that the present application establishes a neural differential equation of the power system, and uses the neural differential equation to simulate the dynamic trajectory of the power system; when the power system is subjected to a large disturbance, determines the initial balance point of the power system; based on the dynamic trajectory and the initial balance point, determines the dominant unstable balance point of the power system; uses the dominant unstable balance point to determine the critical energy value of the power system; selects a point to be tested, and calculates the energy function value of the point to be tested, and at the same time calculates the energy function value of the initial balance point; determines the stability of the power system after a large disturbance based on the energy function value of the initial balance point, the energy function value of the point to be tested, and the critical energy value. This scheme uses neural differential equations for simulation, which can obtain the accurate dynamic trajectory of the power system. When the power system is subjected to a large disturbance, the initial balance point of the power system is first determined. This balance point shows the initial balance information of the power system and can provide a basis for subsequent comparison. In addition, the dominant unstable balance point needs to be determined. This point is a balance point where the power system tends to be unstable after a large disturbance, so as to determine the critical energy value of the point, and then select a test point. The energy function value at the test point, the critical energy value and the energy function value of the initial balance point are used to comprehensively analyze the stable state of the power system after a large disturbance. This can not only improve the accuracy of the analysis, but also clarify the stability boundary and critical energy of the power system, effectively improving the stability analysis and evaluation capabilities of the power system under large disturbances, which is beneficial to the subsequent operation of the power system.

[0114] Furthermore, the embodiment of the present application provides a system stability analysis device based on neural differential equations and energy functions. Optionally, Figure 3 The hardware structure block diagram of the system stability analysis device based on neural differential equations and energy functions is shown. Figure 3 The hardware structure of the system stability analysis device based on neural differential equations and energy functions may include: at least one processor 01, at least one communication interface 02, at least one memory 03 and at least one communication bus 04.

[0115] In the embodiment of the present application, the number of the processor 01 , the communication interface 02 , the memory 03 , and the communication bus 04 is at least one, and the processor 01 , the communication interface 02 , and the memory 03 communicate with each other through the communication bus 04 .

[0116] The processor 01 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0117] The memory 03 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory.

[0118] The memory stores a program, and the processor can call the program stored in the memory, and the program is used to execute the following system stability analysis method based on neural differential equations and energy functions, including:

[0119] Establishing a neural differential equation for a power system, and simulating a dynamic trajectory of the power system using the neural differential equation;

[0120] When the power system is subjected to a large disturbance, determining an initial equilibrium point of the power system;

[0121] Determining a dominant unstable equilibrium point of the power system based on the dynamic trajectory and the initial equilibrium point;

[0122] Determining a critical energy value of the power system using the dominant unstable equilibrium point;

[0123] Selecting a point to be measured, and calculating the energy function value of the point to be measured, and calculating the energy function value of the initial equilibrium point at the same time;

[0124] The stability of the power system after being subjected to a large disturbance is determined according to the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value.

[0125] Optionally, the detailed functions and extended functions of the program may refer to the description of the system stability analysis method based on neural differential equations and energy functions in the method embodiment.

[0126] The embodiment of the present application further provides a storage medium, which may store a program suitable for execution by a processor, and when the program is running, controls the device where the storage medium is located to execute the following system stability analysis method based on neural differential equations and energy functions, including:

[0127] Establishing a neural differential equation for a power system, and simulating a dynamic trajectory of the power system using the neural differential equation;

[0128] When the power system is subjected to a large disturbance, determining an initial equilibrium point of the power system;

[0129] Determining a dominant unstable equilibrium point of the power system based on the dynamic trajectory and the initial equilibrium point;

[0130] Determining a critical energy value of the power system using the dominant unstable equilibrium point;

[0131] Selecting a point to be measured, and calculating the energy function value of the point to be measured, and calculating the energy function value of the initial equilibrium point at the same time;

[0132] The stability of the power system after being subjected to a large disturbance is determined according to the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value.

[0133] Specifically, the storage medium may be a computer-readable storage medium, and the computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk or a ROM.

[0134] Optionally, the detailed functions and extended functions of the program may refer to the description of the system stability analysis method based on neural differential equations and energy functions in the method embodiment.

[0135] In addition, the functional modules in the various embodiments of the present disclosure can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a live broadcast device, or a network device, etc.) to perform all or part of the steps of the methods of the various embodiments of the present disclosure.

[0136] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0137] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0138] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A system stability analysis method based on neural differential equations and energy functions, characterized in that: include: Establishing a neural differential equation for a power system, and simulating a dynamic trajectory of the power system using the neural differential equation; When the power system is subjected to a large disturbance, determining an initial equilibrium point of the power system; Determining a dominant unstable equilibrium point of the power system based on the dynamic trajectory and the initial equilibrium point; Determining a critical energy value of the power system using the dominant unstable equilibrium point; Selecting a point to be measured, and calculating the energy function value of the point to be measured, and calculating the energy function value of the initial equilibrium point at the same time; The stability of the power system after being subjected to a large disturbance is determined according to the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value.

2. The method according to claim 1, characterized in that The determining the dominant unstable balance point of the power system based on the dynamic trajectory and the initial balance point comprises: Starting from the initial balance point, integrating the dynamic trajectory in the time domain to determine the dynamic region of the power system; determining an intersection point between the dynamic region and the dynamic trajectory; Taking the intersection point as a starting point, integrating the gradient equation of the power system along the dynamic trajectory to determine the minimum gradient point of the power system; Based on the minimum gradient point, a power deviation equation of the power system is calculated to obtain a dominant unstable equilibrium point.

3. The method according to claim 1, characterized in that: The method of using the dominant unstable equilibrium point to determine the critical energy value of the power system includes: constructing an energy function according to the neural differential equation; The function value of the energy function at the dominant unstable equilibrium point is calculated, and the function value is used as the critical energy value of the power system.

4. The method according to claim 3, characterized in that The step of constructing an energy function according to the neural differential equation comprises: Defining state quantity parameters of the power system; Constructing a nonlinear differential equation based on the state quantity parameters; Solving the nonlinear differential equation using the neural differential equation to obtain network parameters in the nonlinear differential equation; An energy function is constructed based on the network parameters.

5. The method according to claim 1, characterized in that The step of determining the stability of the power system after being subjected to a large disturbance according to the energy function value of the initial equilibrium point, the energy function value of the point to be measured, and the critical energy value comprises: Calculating the stability margin of the power system according to the energy function value of the initial balance point, the energy function value of the point to be measured and the critical energy value; If the stability margin is not less than a preset first threshold, determining that the power system is in a stable state after being subjected to a large disturbance; If the stability margin is smaller than the first threshold, it is determined that the power system is in an unstable state after being subjected to a large disturbance.

6. The method according to claim 5, characterized in that The calculation formula of the stability margin of the power system is: ； in, represents the stability margin, Represents the energy function value of the point to be tested, represents the energy function value of the initial equilibrium point, Represents the critical energy value.

7. The method according to claim 1, characterized in that The state trajectory equation of the dynamic trajectory is: ； in, and All are time points, Indicates the power system at time point status, is the initial state of the power system at the initial equilibrium point, is the time point corresponding to the initial equilibrium point, is a nonlinear differential equation, is the network parameter in the nonlinear differential equation, The power system at any point in time status.

8. A system stability analysis device based on neural differential equations and energy functions, characterized in that: include: A dynamic trajectory simulation module, used to establish a neural differential equation of the power system and simulate the dynamic trajectory of the power system using the neural differential equation; A balance point determination module, used to determine the initial balance point of the power system when the power system is subjected to a large disturbance; A dominant unstable balance point determination module, used to determine the dominant unstable balance point of the power system based on the dynamic trajectory and the initial balance point; A critical energy value determination module, used to determine the critical energy value of the power system by using the dominant unstable equilibrium point; An energy function value calculation module is used to select a point to be measured, calculate the energy function value of the point to be measured, and calculate the energy function value of the initial equilibrium point at the same time; The stability analysis module is used to determine the stability of the power system after a large disturbance based on the energy function value of the initial equilibrium point, the energy function value of the point to be measured and the critical energy value.

9. A system stability analysis device based on neural differential equations and energy functions, characterized in that: including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement the various steps of the system stability analysis method based on neural differential equations and energy functions as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the system stability analysis method based on neural differential equations and energy functions as described in any one of claims 1 to 7 is implemented.

Images