Method and device for determining power grid fault splitting threshold value and storage medium

Abstract

The application discloses a kind of power grid fault splitting constant value determination method, device and storage medium.The method comprises: in the case where new energy is accessed to power grid, and the working state of power grid is in fault state, the initial fault splitting constant value of power grid is obtained, wherein the initial fault splitting constant value is the parameter value of at least one component in power grid when fault occurs;Based on initial fault splitting constant value, determine the initial fault scene information of power grid, wherein the initial fault scene information is used to represent the scene state of the corresponding power system of power grid in the case of fault;Based on initial fault splitting constant value and initial fault scene information, the fault splitting constant value model of power grid is constrained, and the target fault splitting constant value of power grid is obtained, wherein the target fault splitting constant value is used to make the power system in normal operating state in the case where new energy is accessed to power grid.The application solves the technical problem that the splitting constant value of power grid fault cannot be effectively determined.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid fault, in particular to a method and device for determining power grid fault splitting setting value and a storage medium. BACKGROUND

[0002] With the continuous optimization and transformation of global energy structure, the proportion of new energy in the power system is increasing, especially wind energy and solar energy. Although the high proportion of new energy access helps to reduce carbon emissions and cope with climate change, it brings great challenges to the safe and stable operation of the power grid. Due to the volatility and uncertainty of new energy, in the process of splitting of power grid fault, the traditional power grid protection and control strategy has been difficult to adapt to the new operating conditions, thereby resulting in the technical problem that the splitting setting value of the power grid fault cannot be effectively determined.

[0003] In view of the above technical problem that the splitting setting value of the power grid fault cannot be effectively determined, no effective solution has been proposed so far. SUMMARY

[0004] The embodiments of the present application provide a method and device for determining the splitting setting value of the power grid fault and a storage medium, which at least solve the technical problem that the splitting setting value of the power grid fault cannot be effectively determined.

[0005] According to one aspect of the embodiments of the present application, a method for determining the splitting setting value of the power grid fault is provided. The method can include: acquiring an initial fault splitting setting value of the power grid when the power grid accesses new energy and the working state of the power grid is in a fault state, wherein the initial fault splitting setting value is a parameter value of at least one component in the power grid when a fault occurs; determining initial fault scene information of the power grid based on the initial fault splitting setting value, wherein the initial fault scene information is used to represent the scene state of the corresponding power system of the power grid when a fault occurs; and constraining a fault splitting setting value model of the power grid based on the initial fault splitting setting value and the initial fault scene information, to obtain a target fault splitting setting value of the power grid, wherein the target fault splitting setting value is used to make the power system in a normal operating state when the power grid accesses new energy.

[0006] Optionally, the fault splitting setting value model comprises a generation model and an evaluation model, and the fault splitting setting value model of the power grid is constrained based on the initial fault splitting setting value and the initial fault scene information to obtain a target fault splitting setting value of the power grid, including: inputting the initial fault splitting setting value and the initial fault scene information into the generation model to generate target fault scene information of the power grid; using the evaluation model to evaluate the target fault scene information to obtain an evaluation result of the target fault scene information, wherein the evaluation result is used to represent whether the target fault scene information meets the fault scene preset condition; in response to the evaluation result being that the target fault scene information meets the fault scene preset condition, determining the target fault splitting setting value based on the target fault scene information.

[0007] Optionally, the method further comprises: in response to the evaluation result being that the target fault scene information does not meet the fault scene preset condition, and in the case that the working state of the power grid is in a fault state, re-acquiring the initial fault splitting setting value of the power grid.

[0008] Optionally, inputting the initial fault splitting setting value and the initial fault scene information into the generation model to generate the target fault scene information of the power grid comprises: acquiring an initial sensitivity coefficient and an initial offset coefficient of the generation model, wherein the initial sensitivity coefficient is used to represent the influence degree of different power grid parameters on the target fault scene information generated by the generation model, and the initial offset coefficient is used to represent the offset degree between the target fault scene information and the fault scene preset condition; inputting the initial fault splitting setting value and the initial fault scene information into the generation model to obtain a target sensitivity coefficient and a target offset coefficient of the generation model based on a target dynamic factor of the generation model, wherein the target sensitivity coefficient is less than the initial sensitivity coefficient, and the target offset coefficient is less than the initial offset coefficient; determining the target fault scene information based on the target sensitivity coefficient, the target offset coefficient and the generation model.

[0009] Optionally, determining the target fault scene information based on the target sensitivity coefficient, the target offset coefficient and the generation model comprises: determining a reward function of the generation model based on the target sensitivity coefficient and the target offset coefficient; using the reward function to call the generation model to obtain the target fault scene information.

[0010] Optionally, the initial fault scene information comprises at least one of the following: wind power information, photovoltaic power information, load power information, node voltage information and branch current information, wherein the wind power information is used to represent the power generation capacity of the wind farm of the power grid, the photovoltaic power information is used to represent the power generation capacity of the photovoltaic power station of the power grid, and the load power information is used to represent the power demand of the power grid.

[0011] Optionally, the initial fault splitting setting value comprises an initial splitting threshold and an initial fault splitting delay time, and the target fault splitting setting value comprises a target splitting threshold and a target fault splitting delay time.

[0012] According to an aspect of the embodiments of the present application, a device for determining a power grid fault splitting setting value is provided. The device can comprise: a first obtaining unit configured to obtain an initial fault splitting setting value of a power grid when the power grid is connected to a new energy source and an operating state of the power grid is in a fault state, wherein the initial fault splitting setting value is a parameter value of at least one component in the power grid when the component is in a fault state; a determining unit configured to determine initial fault scenario information of the power grid based on the initial fault splitting setting value, wherein the initial fault scenario information is used to represent a scenario state of a power system corresponding to the power grid when the power system is in a fault state; and a second obtaining unit configured to constrain a fault splitting setting value model of the power grid based on the initial fault splitting setting value and the initial fault scenario information, to obtain a target fault splitting setting value of the power grid, wherein the target fault splitting setting value is used to enable the power system to be in a normal operating state when the power grid is connected to a target proportion of the new energy source.

[0013] According to another aspect of the embodiments of the present application, a computer readable storage medium is provided, which includes a stored program, wherein the program, when executed by a processor, controls a device where the storage medium is located to perform the method in the embodiments of the present application.

[0014] According to another aspect of the embodiments of the present application, a processor is provided, which is used to execute a program, wherein the program, when executed, performs the method in the embodiments of the present application.

[0015] According to another aspect of the embodiments of the present application, a computer program product is provided, which includes a computer program, and the computer program, when executed by a processor, implements the method in the embodiments of the present application.

[0016] According to another aspect of the embodiments of the present application, an electronic device is provided, which includes a processor and a memory for storing processor executable instructions. The processor is configured to execute the instructions to implement the method in the embodiments of the present application.

[0017] In the embodiment of the present application, in the case that the power grid accesses new energy and the working state of the power grid is in a fault state, an initial fault splitting setting value of the power grid is acquired, wherein the initial fault splitting setting value is a parameter value of at least one component in the power grid when a fault occurs; based on the initial fault splitting setting value, initial fault scene information of the power grid is determined, wherein the initial fault scene information is used to represent the scene state of the corresponding power system of the power grid in the case of a fault; based on the initial fault splitting setting value and the initial fault scene information, a fault splitting setting value model of the power grid is constrained to obtain a target fault splitting setting value of the power grid, wherein the target fault splitting setting value is used to make the power system in a normal operating state in the case that the power grid accesses new energy. That is, in the case that the power grid accesses new energy and the working state of the power grid is in a fault state, the initial fault splitting setting value of the power grid is acquired first, and then according to the initial fault splitting setting value obtained above, the initial fault scene information of the power grid can be determined, and finally according to the initial fault splitting setting value and the initial fault scene information, the fault splitting setting value model of the power grid is constrained to achieve the purpose of obtaining the target fault splitting setting value of the power grid. Since the fault splitting setting value model can be called after the initial fault splitting setting value and the initial fault scene information are obtained, so as to obtain the target fault splitting setting value used to represent that the power system is in a normal operating state in the case that the power grid accesses new energy, so as to solve the technical problem that the splitting setting value of the power grid fault cannot be effectively determined, and the technical effect that the splitting setting value of the power grid fault can be effectively determined is realized. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0019] Figure 1 is a flow chart of a method for determining a power grid fault splitting setting value according to an embodiment of the present application;

[0020] Figure 2 is a schematic diagram of the parameter optimization effect of an adaptive artificial bee colony algorithm according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a device for determining a power grid fault splitting setting value according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort should fall within the protection scope of the present application.

[0023] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device including a series of steps or units does not necessarily have to include only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product, or device.

[0024] According to an embodiment of the present application, a method for determining a power grid fault splitting setting value is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0025] The method for determining a power grid fault splitting setting value according to an embodiment of the present application will be described below.

[0026] Figure 1 A flowchart of a method for determining a power grid fault splitting setting value according to an embodiment of the present application is shown in FIG. 1, which can include the following steps: Figure 1

[0027] In step S101, in the case that a new energy is connected to a power grid and the working state of the power grid is in a fault state, an initial fault splitting setting value of the power grid is obtained.

[0028] In the technical solution provided in step S101 of the present application, in the case that a target proportion of new energy is connected to a power grid and the working state of the power grid is in a fault state, an initial fault splitting setting value of the power grid can be obtained, wherein the initial fault splitting setting value is a parameter value of at least one component in the power grid when a fault occurs.

[0029] ​Optionally, the target proportion can be a preset proportion, or the new energy proportion in the power grid can be divided into a high proportion or a low proportion according to the target proportion. It should be noted that the initial fault splitting setting value obtained here is in the case that the power grid accesses a high proportion of new energy and the working state of the power grid is in a fault state.

[0030] Optionally, the initial fault splitting setting value can include an initial splitting threshold and an initial fault splitting delay time, wherein the initial splitting threshold and the initial fault splitting delay time are two important parameters of the fault splitting protection action. The initial splitting threshold can be referred to as an initial fault splitting threshold, or simply as a fault splitting threshold. The initial fault splitting delay time can be referred to as a fault splitting delay time. For example, the initial splitting threshold can include an initial current threshold, an initial voltage threshold, an initial frequency threshold, and an initial temperature threshold, etc. The initial fault splitting delay time can include an initial millisecond delay time, an initial second delay time, an initial adjustable delay time, and an initial cascade splitting time, etc.

[0031] It can be understood that this is only one preferred embodiment of obtaining the initial fault splitting setting value of the power grid, and the process and method of obtaining the initial fault splitting setting value of the power grid in the case that the power grid accesses new energy and the working state of the power grid is in a fault state are not specifically limited.

[0032] Step S102, determining initial fault scene information of the power grid based on the initial fault splitting setting value.

[0033] In the technical solution provided in the above step S102 of the present application, after obtaining the initial fault splitting setting value, the initial fault scene information of the power grid can be determined, wherein the initial fault scene information is used to represent the scene state of the power grid corresponding to the power system in the case of a fault.

[0034] Optionally, the initial fault scene information can be represented by the established power grid fault splitting operation scene data set in the case that a high proportion of new energy accesses the power grid, or by the obtained power grid fault splitting operation scene data set in the case that white noise is superimposed on the high proportion of new energy and accesses the power grid.

[0035] It should be noted that this is only one preferred embodiment of determining the initial fault scene information of the power grid, and the process and method of determining the initial fault scene information of the power grid are not specifically limited. As long as the process and method of determining the initial fault scene information of the power grid according to the initial fault splitting setting value are within the protection scope of the present application, they will not be listed here.

[0036] In step S103, based on the initial fault splitting setting value and the initial fault scene information, the fault splitting setting value model of the power grid is constrained to obtain the target fault splitting setting value of the power grid.

[0037] In the technical solution provided in the above step S103 of the present application, the initial fault splitting setting value and the initial fault scene information obtained in the above steps are used to constrain the fault splitting setting value model of the power grid, so as to obtain the target fault splitting setting value of the power grid, which is used to keep the power system in a normal operating state when the power grid accesses new energy.

[0038] Optionally, the fault splitting setting value model is a model established by a generative adversarial network algorithm, which can also be referred to as a fault splitting setting value setting model, or a power grid fault splitting setting value setting model based on a generative adversarial network algorithm. The generative adversarial network algorithm is a kind of machine learning algorithm, which consists of two neural networks: generator and discriminator. The goal of the generator is to generate as realistic data samples as possible, while the goal of the discriminator is to distinguish the samples generated by the generator from the real samples. The two networks compete with each other in the training process, thus promoting each other's learning.

[0039] For example, based on the obtained initial fault splitting setting value and the obtained power grid fault splitting operating scene data set in the case of high proportion of new energy accessing the power grid, the fault splitting setting value model based on the generative adversarial network algorithm can be called to obtain the target fault splitting setting value for representing the power system in a normal operating state when the power grid accesses new energy.

[0040] The above steps S101 to S103 of the present application can be used to obtain the initial fault splitting setting value of the power grid when the power grid accesses new energy and the working state of the power grid is in a fault state. Then, based on the obtained initial fault splitting setting value, the initial fault scene information of the power grid can be determined. Finally, based on the initial fault splitting setting value and the initial fault scene information, the fault splitting setting value model of the power grid is constrained to obtain the target fault splitting setting value of the power grid. Since the initial fault splitting setting value and the initial fault scene information are obtained, the fault splitting setting value model can be called to obtain the target fault splitting setting value for representing the power system in a normal operating state when the power grid accesses new energy, so as to solve the technical problem of being unable to effectively determine the fault splitting setting value of the power grid, and achieve the technical effect of being able to effectively determine the fault splitting setting value of the power grid.

[0041] The above method of the embodiment will be further introduced as follows.

[0042] As an optional embodiment, the fault splitting setting value model comprises a generation model and an evaluation model, and the fault splitting setting value model of the power grid is constrained based on the initial fault splitting setting value and the initial fault scene information to obtain a target fault splitting setting value of the power grid, comprising: inputting the initial fault splitting setting value and the initial fault scene information into the generation model to generate target fault scene information of the power grid; using the evaluation model to evaluate the target fault scene information to obtain an evaluation result of the target fault scene information, wherein the evaluation result is used to represent whether the target fault scene information meets the preset fault scene condition; in response to the evaluation result that the target fault scene information meets the preset fault scene condition, determining the target fault splitting setting value based on the target fault scene information.

[0043] In this embodiment, the fault splitting setting value model comprises a generation model and an evaluation model, and after obtaining the initial fault splitting setting value and the initial fault scene information, the initial fault splitting setting value and the initial fault scene information can be input into the generation model to generate target fault scene information of the power grid, and then the evaluation model is used to evaluate the target fault scene information to obtain an evaluation result of the target fault scene information. If the evaluation result is that the target fault scene information meets the preset fault scene condition, the target fault splitting setting value can be determined according to the target fault scene information and the target constraint condition of the fault splitting setting value model.

[0044] Optionally, the generation model can be referred to as a fault splitting operation scene generation model of a power grid with a high proportion of new energy access. The evaluation model can be referred to as a fault splitting setting value setting effect evaluation model of a power grid with a high proportion of new energy access. The target fault scene information of the power grid can be obtained through the power grid operation scene information under the current fault splitting condition. The preset fault scene condition can be a condition that the target fault scene information needs to meet, such as a condition that guarantees the safety and stability requirements of the power grid. It should be noted that only the preset fault scene condition is exemplified here, and the content of the preset fault scene condition is not specifically limited.

[0045] Optionally, the target constraint condition can be a preset condition for constraining the fault splitting setting value model, such as an optimization objective condition of a power grid fault splitting setting value setting model based on a generative adversarial network algorithm. The optimization objective condition can be represented by the following formula:

[0046]

[0047] Wherein, V is an optimization objective of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm. G can be used to represent a fault splitting operation scene generation model of the high-proportion new energy access power grid; D can be used to represent a fault splitting setting value setting effect evaluation model of the micro high-proportion new energy access power grid; x can represent input data of the fault splitting operation scene generation model of the high-proportion new energy access power grid; z is used to represent white noise; p z () is used to represent a white noise probability distribution function; E() is a function of taking the mathematical expectation of the operation result.

[0048] For example, the input of the fault splitting operation scene generation model of the high-proportion new energy access power grid includes a fault splitting operation scene data set of the high-proportion new energy access power grid, and a fault splitting threshold and a fault splitting delay time, and the output of the fault splitting operation scene generation model of the high-proportion new energy access power grid is power grid operation scene information under the current fault splitting condition; the fault splitting setting value setting effect evaluation model of the high-proportion new energy access power grid is used to evaluate the output of the fault splitting operation scene generation model of the high-proportion new energy access power grid, that is, whether the power grid operation scene under the current fault splitting condition meets the condition of the power grid safety and stability requirement, if yes, the target fault splitting setting value can be determined according to the fault scene information.

[0049] It should be noted that this is only one preferred embodiment of determining the target fault splitting setting value of the power grid, and the process and method of determining the target fault splitting setting value of the power grid are not specifically limited, as long as the purpose of determining the target fault splitting setting value of the power grid is achieved according to the initial fault splitting setting value and the initial fault scene information, which is not listed here.

[0050] As an optional embodiment, the method further comprises: in response to the evaluation result being that the target fault scene information does not meet the fault scene preset condition and the working state of the power grid being in a fault state, reacquiring the initial fault splitting setting value of the power grid.

[0051] In this embodiment, after obtaining the evaluation result, if the evaluation result at this time is that the target fault scene information does not meet the fault scene preset condition and the working state of the power grid needs to be in a fault state, the initial fault splitting setting value of the power grid is reacquired, and then the above steps are followed until the target fault scene information obtained meets the fault scene preset condition, so as to re-determine the target fault splitting setting value.

[0052] For example, white noise is input into the fault splitting operation scene generation model of the high-proportion new energy access power grid, so as to simulate the uncertainty of the operation of the high-proportion new energy access power grid. The evaluation result of the fault splitting setting value evaluation model of the high-proportion new energy access power grid can be fed back to the fault splitting operation scene generation model of the high-proportion new energy access power grid, and the generated fault splitting threshold and fault splitting delay time are iteratively updated.

[0053] As an optional embodiment, the initial fault splitting setting value and the initial fault scene information are input into the generation model to generate target fault scene information of the power grid, including: obtaining an initial sensitivity coefficient and an initial offset coefficient of the generation model, wherein the initial sensitivity coefficient is used to represent the influence degree of different power grid parameters on the target fault scene information generated by the generation model, and the initial offset coefficient is used to represent the offset degree between the target fault scene information and the preset condition of the fault scene; the initial fault splitting setting value and the initial fault scene information are input into the generation model, and the target dynamic factor of the generation model is used to obtain the target sensitivity coefficient and the target offset coefficient of the generation model, wherein the target sensitivity coefficient is less than the initial sensitivity coefficient, and the target offset coefficient is less than the initial offset coefficient; the target fault scene information is determined based on the target sensitivity coefficient, the target offset coefficient and the generation model.

[0054] In this embodiment, the initial sensitivity coefficient and the initial offset coefficient of the generation model can be obtained first, and then the initial fault splitting setting value and the initial fault scene information are input into the generation model. According to the target dynamic factor of the generation model and by using the adaptive artificial bee colony algorithm, the target sensitivity coefficient and the target offset coefficient of the generation model can be obtained. Finally, according to the target sensitivity coefficient, the target offset coefficient and the generation model, the target fault scene information can be determined. The target dynamic factor can be referred to as a dynamic learning factor, which can be represented by an optimization factor adjustment parameter.

[0055] Optionally, the initial sensitivity coefficient can be referred to as the sensitivity coefficient of the fault splitting operation scene generation model of the high-proportion new energy access power grid. The initial offset coefficient can be referred to as the offset coefficient of the fault splitting operation scene generation model of the high-proportion new energy access power grid. The target sensitivity coefficient can be the sensitivity coefficient of the current fault splitting operation scene generation model of the high-proportion new energy access power grid after the initial sensitivity coefficient is processed. The target offset coefficient can be the offset coefficient of the current fault splitting operation scene generation model of the high-proportion new energy access power grid after the initial offset coefficient is processed.

[0056] Optionally, the calculation step of the adaptive artificial bee colony algorithm is initializing adaptive artificial bee colony algorithm parameters. The adaptive artificial bee colony algorithm parameters include: the number of bees of the adaptive artificial bee colony algorithm, and the initial position of the bees of the adaptive artificial bee colony algorithm (i.e., the sensitivity coefficients of the current high-proportion new-energy-accessed power grid fault isolation operation scenario generation model and the offset coefficients of the high-proportion new-energy-accessed power grid fault isolation operation scenario generation model).

[0057] Optionally, after initializing the adaptive artificial bee colony algorithm parameters, a parameter optimization model of a power grid fault isolation setting model based on a dynamic learning factor-based generative adversarial network algorithm is designed. That is:

[0058]

[0059] In the above formula, may be the potential power grid fault isolation setting model parameters found; u(t) may be a dynamic optimization factor adjustment parameter of the adaptive artificial bee colony algorithm; k and j may be power grid fault isolation setting model parameters different from i; may be the parameters of the current power grid fault isolation setting model; are respectively two arbitrary power grid fault isolation setting model parameters; T i g is the optimal power grid fault isolation setting model parameter in the current round. β is an optimization factor adjustment parameter.

[0060] Optionally, after the optimization model, the power grid fault isolation setting model parameters obtained based on the adaptive artificial bee colony algorithm are sorted according to the effects. The power grid fault isolation setting model parameter sequence is obtained wherein, may be the position of the bee of the adaptive artificial bee colony algorithm; {x1, x2,..., x n correspond to the positions of the bees with the honey content from large to small. If more than half of the power grid fault isolation setting model parameters obtained by the adaptive artificial bee colony algorithm are better than the sensitivity coefficients of the initial high-proportion new-energy-accessed power grid fault isolation operation scenario generation model and the offset coefficients of the high-proportion new-energy-accessed power grid fault isolation operation scenario generation model, the dynamic optimization factor is kept unchanged at this time, otherwise, the dynamic optimization factor adjustment parameter u(t) of the adaptive artificial bee colony algorithm is adjusted to

[0061]

[0062] wherein, M max may be the maximum optimization number of the adaptive artificial bee colony algorithm; m it may be the current optimization number of the adaptive artificial bee colony algorithm.

[0063] Further, when the maximum number of optimization of the adaptive artificial bee colony algorithm is reached, the sensitivity coefficient of the current fault splitting operation scenario generation model of the high-proportion new energy access power grid and the offset coefficient of the fault splitting operation scenario generation model of the high-proportion new energy access power grid are output.

[0064] As an optional embodiment, based on the target sensitivity coefficient, the target offset coefficient and the generation model, the target fault scenario information is determined, including: based on the target sensitivity coefficient and the target offset coefficient, the reward function of the generation model is determined; the reward function is used to call the generation model to obtain the target fault scenario information.

[0065] In this embodiment, after the target sensitivity coefficient and the target offset coefficient are obtained, the reward function of the generation model can be determined, and then the reward function can be used to call the generation model to obtain the target fault scenario information.

[0066] Optionally, the reward function can also be a function of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm, which can be represented by the following formula:

[0067]

[0068] Wherein, R(λ) can be a reward function of a power grid fault splitting setting value setting model based on a generative adversarial network algorithm; n can be a fault splitting operation scenario generation model of a high-proportion new energy access power grid, the nth generated fault splitting operation scenario; ω can be a sensitivity coefficient of the fault splitting operation scenario generation model of the high-proportion new energy access power grid. b can be an offset coefficient of the fault splitting operation scenario generation model of the high-proportion new energy access power grid; i can be a fault splitting operation scenario generation model of a high-proportion new energy access power grid, the ith generated fault splitting operation scenario.

[0069] As an optional embodiment, the initial fault scenario information includes at least one of the following: wind power information, photovoltaic power information, load power information, node voltage information and branch current information, wherein the wind power information is used to represent the power generation capacity of the wind farm of the power grid, the photovoltaic power information is used to represent the power generation capacity of the photovoltaic power station of the power grid, and the load power information is used to represent the power demand of the power grid.

[0070] In this embodiment, the initial fault scenario information can include: wind power information, photovoltaic power information, load power information, node voltage information and branch current information. Wherein, the node voltage information can be referred to as the node voltage information of the power grid. The branch current information can be referred to as the branch current information of the power grid.

[0071] For example, the fault-isolation operation scenario data set of the power grid with a high proportion of new energy access includes wind power information, photovoltaic power information, load power information, power grid node voltage information, and power grid branch current information of the power grid with a high proportion of new energy access.

[0072] Optionally, the wind power information of the power grid with a high proportion of new energy access can be represented as:

[0073]

[0074] wherein Y W is the wind power information of the power grid with a high proportion of new energy access; is the wind power information at the 1st, 2nd, …, n th moment, respectively.

[0075] Optionally, the photovoltaic power information of the power grid with a high proportion of new energy access can be represented as:

[0076]

[0077] wherein Y PV is the photovoltaic power information of the power grid with a high proportion of new energy access; is the photovoltaic power information at the 1st, 2nd, …, n th moment, respectively.

[0078] Optionally, the load power information of the power grid with a high proportion of new energy access can be represented as:

[0079]

[0080] wherein Y LOAD is the load power information of the power grid with a high proportion of new energy access; is the load power information of the power grid with a high proportion of new energy access at the 1st, 2nd, …, n th moment, respectively.

[0081] Optionally, the power grid node voltage information of the power grid with a high proportion of new energy access can be represented as:

[0082]

[0083] wherein, is the power grid node voltage information of the power grid with a high proportion of new energy access at the t th moment; is the voltage information of the 1st, 2nd, …, n th power grid node of the power grid with a high proportion of new energy access at the t th moment, respectively.

[0084] Optionally, the power grid branch current information of the power grid with a high proportion of new energy access can be represented as:

[0085]

[0086] wherein, The grid branch current information of the high-proportion new energy access grid at the t-th moment; The grid branch current information of the high-proportion new energy access grid at the t-th moment;

[0087] As an optional embodiment, the initial fault splitting setting value includes an initial splitting threshold and an initial fault splitting delay time, and the target fault splitting setting value includes a target splitting threshold and a target fault splitting delay time.

[0088] In this embodiment, the initial fault splitting setting value can include an initial splitting threshold and an initial fault splitting delay time, and the target fault splitting setting value includes a target splitting threshold and a target fault splitting delay time. The target splitting threshold can be referred to as a target fault splitting threshold. For example, the target splitting threshold can include a target current threshold, a target voltage threshold, a target frequency threshold, and a target temperature threshold, and the target fault splitting delay time can include a target millisecond delay time, a target second delay time, a target adjustable delay time, and a target cascading splitting time.

[0089] In this embodiment, when the grid accesses new energy and the operating state of the grid is in a fault state, the initial fault splitting setting value of the grid is first obtained, and then according to the obtained initial fault splitting setting value, the initial fault scene information of the grid can be determined, and finally the fault splitting setting value model of the grid is constrained according to the initial fault splitting setting value and the initial fault scene information, so as to achieve the purpose of obtaining the target fault splitting setting value of the grid. Since the fault splitting setting value model can be called after obtaining the initial fault splitting setting value and the initial fault scene information, the target fault splitting setting value for representing that the power system is in a normal operating state when the grid accesses new energy can be obtained, so as to solve the technical problem that the splitting setting value of the grid fault cannot be effectively determined, and achieve the technical effect that the splitting setting value of the grid fault can be effectively determined.

[0090] The technical solutions of the embodiments of the application will be illustrated below in conjunction with preferred embodiments.

[0091] With the continuous optimization and transformation of global energy structure, the proportion of new energy in the power system is increasing, especially wind energy and solar energy. Although the access of high-proportion new energy helps to reduce carbon emissions and cope with climate change, it brings great challenges to the safe and stable operation of the grid. Due to the volatility and uncertainty of new energy, in the splitting process of grid fault, the traditional grid protection and control strategy has been difficult to adapt to the new operating conditions.

[0092] In recent years, some progress has been made in the setting of power grid fault splitting values, but the existing methods are mainly based on traditional static models and empirical rules, and do not fully consider the dynamic changes and complex effects brought by the access of new energy. These methods usually rely on pre-set fixed parameters and lack the ability to effectively respond to the volatility and uncertainty characteristics of new energy. In addition, with the expansion of the scale and the increase of the complexity of the power grid, the existing methods show low efficiency and insufficient accuracy in dealing with large-scale, multi-scenario fault splitting problems, which leads to the technical problem of being unable to effectively determine the splitting value of the power grid fault.

[0093] In an implementable embodiment, a single-phase ground fault detection value adaptive setting method is proposed. The method collects data related to the single-phase ground fault of the distribution network, cleans the data, calculates key system parameters, and then uses the calculation results to build a fault type recognition model. Real-time acquisition of network recording data is performed, and the data is input into the fault type recognition model for fault type recognition. After finding the typical fault characteristics, single-phase ground fault detection value adaptive setting and on-site switch device control are performed.

[0094] In another implementable embodiment, a feeder automation value setting and management method is proposed. The method includes collecting feeder information, analyzing the feeder information through line topology to obtain line value setting output results, generating a value sheet based on the output results, auditing the value sheet, writing the audited value sheet into a file and transmitting it to a value sending area when the audit is completed, and issuing the value through the value sending area. The value after issuance is analyzed for line fault, the device fault tripping information and corresponding tripping current value are searched in a timely manner, the value information of the timing search device is obtained, the tripping current value and the value information are compared, and the evaluation result of the value is obtained.

[0095] Therefore, in order to solve the above problems, the present application proposes a power grid fault splitting value intelligent setting calculation method under the condition of high proportion of new energy access. The method combines the generative adversarial network algorithm and the adaptive artificial bee colony algorithm. The generative adversarial network algorithm simulates diversified fault scenarios to generate representative training data and enhance the response ability to different fault modes. At the same time, the adaptive artificial bee colony algorithm improves the performance of global exploration and local mining by introducing a dynamic learning factor and a secondary optimization mechanism, thereby ensuring that the fault splitting value can be optimally set in a complex and variable power grid environment, significantly improving the accuracy and reliability of power grid fault splitting, reducing the risk of misoperation, and ultimately ensuring the safe and stable operation of the power grid under the condition of high proportion of new energy access. The technical problem of being unable to effectively determine the splitting value of the power grid fault is solved, and the technical effect of being able to effectively determine the splitting value of the power grid fault is achieved.

[0096] In this embodiment, under the condition of high proportion of new energy access, the method for intelligent setting calculation of power grid fault splitting setting value includes the following steps: establishing a power grid fault splitting operation scene data set with high proportion of new energy access; after obtaining the power grid fault splitting operation scene data set with high proportion of new energy access, designing a power grid fault splitting setting value setting model based on a generative adversarial network algorithm; based on the obtained power grid fault splitting setting value setting model, using an adaptive artificial bee colony algorithm to optimize the parameters of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm.

[0097] In this embodiment, the power grid fault splitting operation scene data set with high proportion of new energy access includes wind power information, photovoltaic power information, load power information, power grid node voltage information and power grid branch current information of the power grid with high proportion of new energy access.

[0098] Optionally, the wind power information of the power grid with high proportion of new energy access can be represented as:

[0099]

[0100] wherein Y W is the wind power information of the power grid with high proportion of new energy access; is the wind power information at the 1st, 2nd, …, n th moment respectively.

[0101] Optionally, the photovoltaic power information of the power grid with high proportion of new energy access can be represented as:

[0102]

[0103] wherein Y PV is the photovoltaic power information of the power grid with high proportion of new energy access; is the photovoltaic power information at the 1st, 2nd, …, n th moment respectively.

[0104] Optionally, the load power information of the power grid with high proportion of new energy access can be represented as:

[0105]

[0106] wherein Y LOAD is the load power information of the power grid with high proportion of new energy access; is the load power information of the power grid with high proportion of new energy access at the 1st, 2nd, …, n th moment respectively.

[0107] Optionally, the power grid node voltage information of the power grid with high proportion of new energy access can be represented as:

[0108]

[0109] wherein Y the voltage information of the high-proportion new-energy-accessed power grid node at the tth moment; the voltage information of the high-proportion new-energy-accessed power grid node at the tth moment;

[0110] Optionally, the power grid branch current information of the high-proportion new-energy-accessed power grid can be expressed as:

[0111]

[0112] wherein, the power grid branch current information of the high-proportion new-energy-accessed power grid at the tth moment; the current information of the first, second, and nth power grid branch of the high-proportion new-energy-accessed power grid at the tth moment.

[0113] In this embodiment, after obtaining the high-proportion new-energy-accessed power grid fault splitting operation scenario dataset, the main steps of designing the power grid fault splitting setting value setting model based on the generative adversarial network algorithm are as follows: the power grid fault splitting setting value setting model based on the generative adversarial network algorithm can include a high-proportion new-energy-accessed power grid fault splitting operation scenario generation model and a high-proportion new-energy-accessed power grid fault splitting setting value setting effect evaluation model.

[0114] Optionally, the input of the high-proportion new-energy-accessed power grid fault splitting operation scenario generation model includes the high-proportion new-energy-accessed power grid fault splitting operation scenario dataset, the fault splitting threshold, and the fault splitting delay time, and the output of the high-proportion new-energy-accessed power grid fault splitting operation scenario generation model is the power grid operation scenario information under the current fault splitting condition; the high-proportion new-energy-accessed power grid fault splitting setting value setting effect evaluation model is used to evaluate the output of the high-proportion new-energy-accessed power grid fault splitting operation scenario generation model, that is, whether the power grid operation scenario under the current fault splitting condition meets the conditions required by the power grid safety and stability, if it does, the target fault splitting setting value can be determined according to the fault scenario information.

[0115] Optionally, white noise is input to the high-proportion new-energy-accessed power grid fault splitting operation scenario generation model, so as to simulate the uncertainty of the high-proportion new-energy-accessed power grid operation, and the evaluation result of the high-proportion new-energy-accessed power grid fault splitting setting value setting effect evaluation model can be fed back to the high-proportion new-energy-accessed power grid fault splitting operation scenario generation model for iterative updating of the fault splitting threshold and the fault splitting delay time generated by the high-proportion new-energy-accessed power grid fault splitting operation scenario generation model.

[0116] Optionally, the optimization objective condition of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm can be represented by the following formula:

[0117]

[0118] Wherein, V is the optimization objective of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm. G can be used to represent the fault splitting operation scene generation model of the high-proportion new energy access power grid; D can be used to represent the fault splitting setting value setting effect evaluation model of the micro high-proportion new energy access power grid; x can represent the input data of the fault splitting operation scene generation model of the high-proportion new energy access power grid; z is used to represent white noise; p z () is used to represent the white noise probability distribution function; E() is a function of taking the mathematical expectation of the operation result.

[0119] Optionally, the reward function of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm can be represented as:

[0120]

[0121] Wherein, R(λ) can be the reward function of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm; n can be the fault splitting operation scene generation model of the high-proportion new energy access power grid, the nth generated fault splitting operation scene; ωω can be the sensitivity coefficient of the fault splitting operation scene generation model of the high-proportion new energy access power grid. b can be the offset coefficient of the fault splitting operation scene generation model of the high-proportion new energy access power grid; i can be the fault splitting operation scene generation model of the high-proportion new energy access power grid, the ith generated fault splitting operation scene.

[0122] In this embodiment, based on the obtained power grid fault splitting setting value setting model, the parameters of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm are optimized by using the adaptive artificial bee colony algorithm. The content of the above process mainly includes: the parameters of the power grid fault splitting setting value setting model based on the generative adversarial network algorithm include the sensitivity coefficient of the fault splitting operation scene generation model of the high-proportion new energy access power grid, and the offset coefficient of the fault splitting operation scene generation model of the high-proportion new energy access power grid.

[0123] Optionally, the calculation steps of the adaptive artificial bee colony algorithm are: initializing the adaptive artificial bee colony algorithm parameters. Wherein, the adaptive artificial bee colony algorithm parameters include: the number of bees of the adaptive artificial bee colony algorithm, the initial position of the bee of the adaptive artificial bee colony algorithm (i.e. the current sensitivity coefficient of the fault splitting operation scene generation model of the high-proportion new energy access power grid, and the offset coefficient of the fault splitting operation scene generation model of the high-proportion new energy access power grid).

[0124] Optionally, after initializing the adaptive artificial bee colony algorithm parameters, a parameter optimization model of the power grid fault splitting setting value setting model based on the dynamic learning factor-based generative adversarial network algorithm is designed. That is:

[0125]

[0126] In the above formula, may be the potential power grid fault splitting setting value setting model parameter found; u(t) may be the dynamic optimization factor adjustment parameter of the adaptive artificial bee colony algorithm; k and j may be power grid fault splitting setting value setting model parameters different from i; may be the parameter of the current power grid fault splitting setting value setting model; are respectively two arbitrary power grid fault splitting setting value setting model parameters; T i g is the optimal power grid fault splitting setting value setting model parameter under the current round. β is the optimization factor adjustment parameter.

[0127] Optionally, after the optimization model, the power grid fault splitting setting value setting model parameters obtained based on the adaptive artificial bee colony algorithm are sorted according to the effect. The power grid fault splitting setting value setting model parameter sequence is obtained wherein, may be the bee position of the adaptive artificial bee colony algorithm; {x1, x2,..., x n} corresponds to the bee position with the honey content from large to small. If more than half of the power grid fault splitting setting value setting model parameters obtained by the adaptive artificial bee colony algorithm are better than the sensitivity coefficient of the initial high-proportion new-energy-accessed power grid fault splitting operation scene generation model and the offset coefficient of the high-proportion new-energy-accessed power grid fault splitting operation scene generation model, the dynamic optimization factor is kept unchanged at this time, otherwise, the dynamic optimization factor adjustment parameter u(t) of the adaptive artificial bee colony algorithm is adjusted as:

[0128]

[0129] wherein, M max may be the maximum optimization number of the adaptive artificial bee colony algorithm; m it may be the current optimization number of the adaptive artificial bee colony algorithm.

[0130] Further, when the maximum optimization number of the adaptive artificial bee colony algorithm is reached, the sensitivity coefficient of the current high-proportion new-energy-accessed power grid fault splitting operation scene generation model and the offset coefficient of the high-proportion new-energy-accessed power grid fault splitting operation scene generation model are output.

[0131] In the embodiments of the present application,Figure 2 is a schematic diagram of parameter optimization effect of an adaptive artificial bee colony algorithm according to an embodiment of the present application, as shown in Figure 2 A certain regional power grid is selected for case analysis, and the specific parameters are: the number of nodes is 33, the number of transformers is 18, the number of loads is 32, the number of bees of the adaptive artificial bee colony algorithm is 200, and the maximum number of iterations is 500.

[0132] Alternatively, in order to verify the superiority of the method proposed in the present application, two different fault splitting setting methods, M1 and M2, are compared. M1 is the method proposed in the present application; M2 is a fault splitting setting method based on prior knowledge. The comparison results are shown in Figure 2 . The abscissa is the sequence number of the high-proportion new energy operation scenario, and the ordinate is the fault splitting effect. It can be seen that the fault splitting setting based on the method proposed in the present application has better effect in more high-proportion new energy operation scenarios.

[0133] In this embodiment, when the power grid accesses new energy and the working state of the power grid is in a fault state, the initial fault splitting setting value of the power grid is first obtained, and then according to the initial fault splitting setting value obtained above, the initial fault scene information of the power grid can be determined, and finally the fault splitting setting value model of the power grid is constrained according to the initial fault splitting setting value and the initial fault scene information, so as to achieve the purpose of obtaining the target fault splitting setting value of the power grid. Since the fault splitting setting value model can be called after the initial fault splitting setting value and the initial fault scene information are obtained, the target fault splitting setting value for representing that the power system is in a normal operating state when the power grid accesses new energy can be obtained, so as to solve the technical problem that the fault splitting setting value of the power grid cannot be effectively determined, and achieve the technical effect that the fault splitting setting value of the power grid can be effectively determined.

[0134] According to an embodiment of the present application, a power grid fault splitting setting value determination device is provided. It should be noted that the power grid fault splitting setting value determination device can be used to execute the power grid fault splitting setting value determination method in embodiment 1.

[0135] Figure 3 is a schematic diagram of a power grid fault splitting setting value determination device according to an embodiment of the present application. As shown in Figure 3 , a power grid fault splitting setting value determination device 300 can include a first acquisition unit 301, a determination unit 302, and a second acquisition unit 303.

[0136] The first acquisition unit 301 is configured to, when the power grid accesses new energy and the working state of the power grid is in a fault state, acquire an initial fault splitting setting value of the power grid, wherein the initial fault splitting setting value is a parameter value of at least one component in the power grid when a fault occurs.

[0137] The determining unit 302 is configured to determine initial fault clearing setting information of the power grid based on the initial fault clearing setting value, wherein the initial fault clearing setting information is used to represent a scenario state of a corresponding power system of the power grid in a fault occurrence state.

[0138] The second obtaining unit 303 is configured to constrain a fault clearing setting value model of the power grid based on the initial fault clearing setting value and the initial fault clearing setting information, to obtain a target fault clearing setting value of the power grid, wherein the target fault clearing setting value is used to enable the power system to be in a normal operation state in a case where the power grid accesses a target proportion of new energy.

[0139] Optionally, the fault clearing setting value model comprises a generation model and an evaluation model, and the second obtaining unit 403 further comprises a generation module, an evaluation module, and a determination module.

[0140] Optionally, the apparatus is further configured to, in response to the evaluation result being that the target fault clearing setting information does not meet the fault scenario preset condition and in a case where an operating state of the power grid is in a fault state, re-obtain the initial fault clearing setting value of the power grid.

[0141] Optionally, the generation module further comprises an obtaining submodule, an input submodule, and a determination submodule.

[0142] Optionally, the determination submodule is configured to determine a reward function of the generation model based on the target sensitivity coefficient and the target offset coefficient, and further configured to call the generation model by using the reward function to obtain the target fault clearing setting information.

[0143] Optionally, the initial fault scenario information comprises at least one of wind power information, photovoltaic power information, load power information, node voltage information and branch current information, wherein the wind power information is used to represent the power generation capacity of a wind farm of the power grid, the photovoltaic power information is used to represent the power generation capacity of a photovoltaic power station of the power grid, and the load power information is used to represent the power demand of the power grid.

[0144] Optionally, the initial fault splitting setting value comprises an initial splitting threshold and an initial fault splitting delay time, and the target fault splitting setting value comprises a target splitting threshold and a target fault splitting delay time.

[0145] In this embodiment, the first acquisition unit acquires an initial fault splitting setting value of the power grid when the power grid accesses new energy and the working state of the power grid is in a fault state, wherein the initial fault splitting setting value is a parameter value of at least one component of the power grid when a fault occurs; the determination unit determines initial fault scenario information of the power grid based on the initial fault splitting setting value, wherein the initial fault scenario information is used to represent the scenario state of the corresponding power system of the power grid in the case of a fault; and the second acquisition unit constrains a fault splitting setting value model of the power grid based on the initial fault splitting setting value and the initial fault scenario information to obtain a target fault splitting setting value of the power grid, wherein the target fault splitting setting value is used to enable the power system to be in a normal operating state in the case that the power grid accesses a target proportion of new energy, thereby solving the technical problem that the splitting setting value of the fault of the power grid cannot be effectively determined and achieving the technical effect that the splitting setting value of the fault of the power grid can be effectively determined.

[0146] According to the embodiments of the present application, a computer readable storage medium is also provided, which comprises a stored program, wherein the program, when executed by a processor, controls the device where the readable storage medium is located to perform the determination method of the splitting setting value of the fault of the power grid in the embodiments.

[0147] According to the embodiments of the present application, a processor is also provided, which is used to execute a program, wherein the program, when executed, performs the determination method of the splitting setting value of the fault of the power grid in the embodiments.

[0148] According to the embodiments of the present application, a computer program product is also provided, which comprises a computer program, and the computer program, when executed by a processor, implements the determination method of the splitting setting value of the fault of the power grid in the embodiments of the present application.

[0149] According to the embodiments of the present application, an electronic device is also provided, which comprises a processor and a memory for storing processor executable instructions. The processor is configured to execute the instructions to implement the determination method of the splitting setting value of the fault of the power grid in the embodiments of the present application.

[0150] The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0151] In the above-mentioned embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0152] In the several embodiments of the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit embodiment described above is only schematic. For example, the division of the units can be a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between the units can be indirect coupling or communication connection through some interface, and can be electrical or other forms.

[0153] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0154] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0155] If the integrated unit is realized in the form of software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Ranndom Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0156] The above merely is the preferred embodiment of the present application, it should be pointed out that, for ordinary skilled in the art, without departing from the principles of the present application, can also make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for determining a power grid fault disconnection setting value, characterized in that: include: When a new energy source is connected to a power grid and the working state of the power grid is in a fault state, obtaining an initial fault disconnection setting value of the power grid, wherein the initial fault disconnection setting value is a parameter value of at least one component in the power grid when the fault occurs; Determining initial fault scenario information of the power grid based on the initial fault decoupling setting, wherein the initial fault scenario information is used to characterize a scenario state of the power system corresponding to the power grid when a fault occurs; Based on the initial fault disconnection constant and the initial fault scenario information, the fault disconnection constant model of the power grid is constrained to obtain the target fault disconnection constant of the power grid, wherein the target fault disconnection constant is used to enable the power system to be in normal operating state when the power grid is connected to the new energy.

2. The method according to claim 1, characterized in that in, The fault disconnection setting model includes: a generation model and an evaluation model. Based on the initial fault disconnection setting and the initial fault scenario information, the fault disconnection setting model of the power grid is constrained to obtain a target fault disconnection setting of the power grid, including: Inputting the initial fault separation setting value and the initial fault scenario information into the generation model to generate target fault scenario information of the power grid; Using the evaluation model to evaluate the target fault scenario information, obtaining an evaluation result of the target fault scenario information, wherein the evaluation result is used to indicate whether the target fault scenario information meets a preset fault scenario condition; In response to the evaluation result that the target fault scenario information meets the fault scenario preset condition, the target fault delisting value is determined based on the target fault scenario information.

3. The method according to claim 2, characterized in that The method further comprises: In response to the evaluation result that the target fault scenario information does not meet the preset condition of the fault scenario, and when the working state of the power grid is in a fault state, the initial fault clearance setting value of the power grid is re-acquired.

4. The method according to claim 2, characterized in that Inputting the initial fault decoupling setting and the initial fault scenario information into the generation model to generate target fault scenario information of the power grid includes: Obtaining an initial sensitivity coefficient and an initial offset coefficient of the generation model, wherein the initial sensitivity coefficient is used to characterize the degree of influence of different power grid parameters on the target fault scenario information generated by the generation model, and the initial offset coefficient is used to characterize the degree of offset between the target fault scenario information and the preset condition of the fault scenario; Inputting the initial fault solution setting value and the initial fault scenario information into the generation model, and obtaining a target sensitivity coefficient and a target offset coefficient of the generation model based on a target dynamic factor of the generation model, wherein the target sensitivity coefficient is smaller than the initial sensitivity coefficient, and the target offset coefficient is smaller than the initial offset coefficient; The target fault scenario information is determined based on the target sensitivity coefficient, the target offset coefficient and the generation model.

5. The method according to claim 4, characterized in that Determining the target fault scenario information based on the target sensitivity coefficient, the target offset coefficient, and the generation model includes: determining a reward function of the generative model based on the target sensitivity coefficient and the target offset coefficient; The reward function is used to call the generation model to obtain the target fault scenario information.

6. The method according to claim 1, characterized in that The initial fault scenario information includes at least one of the following: wind power information, photovoltaic power information, load power information, node voltage information and branch current information, wherein the wind power information is used to characterize the power generation capacity of the wind farm of the power grid, the photovoltaic power information is used to characterize the power generation capacity of the photovoltaic power station of the power grid, and the load power information is used to characterize the power demand of the power grid.

7. The method according to claim 1, characterized in that The initial fault disconnection setting value includes: an initial disconnection threshold value and an initial fault disconnection delay time, and the target fault disconnection setting value includes: a target disconnection threshold value and a target fault disconnection delay time.

8. A device for determining a grid fault disconnection setting value, characterized in that: include: a first acquiring unit, configured to acquire, when a new energy source is connected to a power grid and the working state of the power grid is in a fault state, an initial fault disconnection setting value of the power grid, wherein the initial fault disconnection setting value is a parameter value of at least one component in the power grid when the fault occurs; a determining unit, configured to determine initial fault scenario information of the power grid based on the initial fault decoupling setting, wherein the initial fault scenario information is used to characterize a scenario state of a power system corresponding to the power grid when a fault occurs; The second acquisition unit is used to constrain the fault decoupling constant model of the power grid based on the initial fault decoupling constant and the initial fault scenario information, and obtain the target fault decoupling constant of the power grid, wherein the target fault decoupling constant is used to enable the power system to be in normal operating state when the power grid is connected to the new energy.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: a memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 7 when running.

Images