Fault current calculation method, system, electronic device and readable storage medium

Abstract

The present disclosure relates to the field of new energy technology, and discloses a fault current calculation method, system, electronic device and readable storage medium; the method includes: performing fault calculation on a pre-constructed target power grid model according to acquired fault condition data to obtain initial electrical quantity data of each position in the target power grid; for any target nonlinear unit in the target power grid, generating parameter value data of target characteristic parameters based on the initial electrical quantity data of each position; inputting the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value; performing iterative calculation based on a preset node voltage equation and each of the initial fault current prediction values ​​to obtain the final fault current of each nonlinear unit in the target power grid. The present disclosure can predict a more accurate initial fault current prediction value, thereby reducing the number of iterative calculations and improving the calculation efficiency of the fault current of the new power system.

Description

Technical Field

[0001] The present disclosure relates to the field of new energy technology, and in particular to a fault current calculation method, system, electronic device and readable storage medium. Background Art

[0002] With the transformation of the global energy structure and the urgent situation of environmental protection, the construction of new power systems is gradually becoming an important direction for global energy development. In this context, the proportion of new energy power supplies, flexible direct current and other power electronic equipment in the power system continues to increase, making the calculation of fault currents in large-scale, high-proportion new energy power grids more and more difficult. In the field of relay protection, one of the foundations for realizing relay protection setting calculation is to realize large-scale power grid fault current calculation. Therefore, quickly and accurately completing the batch fault current calculation of large-scale power grids is crucial to ensuring the efficiency of relay protection setting calculation.

[0003] When calculating the fault current of a power grid containing new energy and flexible DC transmission lines, unlike synchronous generators, the fault current of new energy power sources and flexible direct current lines presents a nonlinear relationship with the grid connection point voltage, so it usually takes multiple iterations to calculate the accurate fault current. Specifically, the grid connection point voltage of the nonlinear power source can be calculated after the grid fails when each nonlinear power source exits, and then the fault current of each nonlinear power source under this fault voltage is obtained, and then the grid connection point voltage of the nonlinear power source after the fault is recalculated, and it is continuously iterated until the iterative difference of each grid connection point voltage is within the threshold.

[0004] As the number of devices with nonlinear fault characteristics such as new energy and flexible DC transmission lines in the power grid increases, the convergence and convergence speed of fault calculation iteration will continue to decrease, especially when performing fault calculation in large-scale and complex topological power grids, due to the huge order of its mathematical matrix model, the iterative calculation efficiency is even lower. Therefore, it is urgent to solve this technical problem. Summary of the invention

[0005] In view of the above situation, the embodiments of the present disclosure provide a fault current calculation method, system, electronic device and readable storage medium, aiming to solve the above problem or at least partially solve the above problem.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for calculating a fault current, the method comprising:

[0007] According to the acquired fault condition data, the pre-built target power grid model is subjected to fault calculation to obtain the initial electrical quantity data of each location in the target power grid;

[0008] For any target nonlinear unit in the target power grid, based on the initial electrical quantity data of each position, parameter value data of a target characteristic parameter is generated, wherein the target characteristic parameter includes at least one of the following: a first parameter for describing the electrical relationship between the grid connection point and the fault point of the target nonlinear unit, a second parameter for reflecting the operation mode of the target power grid, and a third parameter for describing the electrical state of other nonlinear units;

[0009] Determine a target initial fault current prediction model according to the fault type in the fault condition data, and input the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value;

[0010] Based on the preset node voltage equation and each of the initial fault current prediction values, an iterative calculation is performed to obtain the final fault current of each nonlinear unit in the target power grid.

[0011] In a second aspect, an embodiment of the present disclosure further provides a fault current calculation device, the device comprising:

[0012] An acquisition module is used to perform fault calculation on a pre-built target power grid model according to the acquired fault condition data, and obtain initial electrical quantity data of each location in the target power grid;

[0013] A feature generation module, for generating parameter value data of a target feature parameter based on the initial electrical quantity data of each position for any target nonlinear unit in the target power grid, wherein the target feature parameter includes at least one of the following: a first parameter for describing the electrical relationship between the grid connection point and the fault point of the target nonlinear unit, a second parameter for reflecting the operation mode of the target power grid, and a third parameter for describing the electrical state of other nonlinear units;

[0014] The prediction module is used to determine a target initial fault current prediction model according to the fault type in the fault condition data, and input the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value;

[0015] The calculation module is used to perform iterative calculation based on a preset node voltage equation and each of the initial fault current prediction values ​​to obtain a final fault current of each nonlinear unit in the target power grid.

[0016] In a third aspect, an embodiment of the present disclosure further provides a fault current calculation system, the system comprising: a terminal and a server; the terminal is used to send fault condition data to the server and receive a final fault current; the server is used to execute the steps of the above-mentioned fault current calculation method.

[0017] In a fourth aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the steps of the above-mentioned fault current calculation method.

[0018] In a fifth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the steps of the above-mentioned fault current calculation method.

[0019] By means of the above technical scheme, the fault current calculation method, system, electronic device and readable storage medium provided by the embodiment of the present disclosure can be performed on the pre-built target power grid model according to the acquired fault condition data to obtain the initial electrical quantity data of each position in the target power grid; for any target nonlinear unit in the target power grid, based on the initial electrical quantity data of each position, the parameter value data of the target characteristic parameter is generated, wherein the target characteristic parameter includes at least one of the following: a first parameter for describing the electrical relationship between the target nonlinear unit grid connection point and the fault point, a second parameter for reflecting the operation mode of the target power grid, and a third parameter for describing the electrical state of other nonlinear units; according to the fault type in the fault condition data, the target initial fault current prediction model is determined, and the parameter value data is input into the target initial fault current prediction model to obtain the initial fault current prediction value. It can be seen that the above steps can predict a more reasonable and accurate initial fault current prediction value through the target initial fault current prediction model, so that when iterative calculation is performed based on each initial fault current prediction value and combined with the preset node voltage equation, the number of iterative calculations can be effectively reduced, the convergence of iterative calculations can be improved, and the calculation speed can be improved, thereby greatly improving the calculation efficiency of the fault current of the new power system.

[0020] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0022] Figure 1 A schematic diagram showing a hardware environment of a fault current calculation method provided by an embodiment of the present disclosure;

[0023] Figure 2A schematic diagram showing a flow chart of a fault current calculation method provided by another embodiment of the present disclosure is shown;

[0024] Figure 3 A schematic diagram of passive linear power grid connection provided by an embodiment of the present disclosure is shown;

[0025] Figure 4 Another passive linear power grid wiring schematic diagram provided by an embodiment of the present disclosure is shown;

[0026] Figure 5 Another passive linear power grid wiring schematic diagram provided by an embodiment of the present disclosure is shown;

[0027] Figure 6 A schematic diagram of the structure of a fault current calculation device provided by an embodiment of the present disclosure is shown;

[0028] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions of the present disclosure will be clearly and completely described below in combination with the specific embodiments of the present disclosure and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0030] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such usage is interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to".

[0032] As described above, when calculating the fault current of a power grid containing new energy and flexible direct current transmission lines, unlike synchronous generators, the fault current of new energy power sources and flexible straight lines presents a nonlinear relationship with the grid connection point voltage, so it usually takes multiple iterations to calculate the accurate fault current. Specifically, the grid connection point voltage of the nonlinear power source can be calculated after the grid fails when each nonlinear power source exits, and then the fault current of each nonlinear power source under this fault voltage is obtained, and then the grid connection point voltage of the nonlinear power source after the fault is recalculated, and the iteration difference of each grid connection point voltage is continuously iterated until the iterative difference of each grid connection point voltage is within the threshold. However, as the number of devices with nonlinear fault characteristics such as new energy and flexible direct current transmission lines in the power grid increases, the convergence and convergence speed of the fault calculation iteration will continue to decrease, especially when performing fault calculation in a large-scale and complex topological power grid, due to the huge order of its mathematical matrix model, the iterative calculation efficiency is lower. Based on this, the present invention proposes a fault current calculation method, system, electronic device and readable storage medium, and the present disclosure is described in detail below through specific embodiments.

[0033] First, the professional terms involved in each embodiment of the present disclosure are explained as follows:

[0034] Nonlinear fault characteristics: When calculating the fault current of a traditional synchronous generator, the relationship between the fault current and the fault voltage can be simplified to I = (EU) / X, where I is the current, E is the generator electromotive force, U is the fault voltage, and X is the generator impedance. The IU characteristic diagram drawn with I and U as the horizontal axis and vertical axis is a straight line, that is, the relationship between the fault current and fault voltage of a traditional synchronous generator is linear. However, the IU characteristic diagram of power electronic equipment such as new energy power supplies and flexible direct current is a broken line, indicating that the current and voltage of these power electronic equipment are nonlinear under fault conditions, that is, nonlinear fault characteristics refer to the nonlinear behavior or characteristics exhibited by the equipment under fault conditions.

[0035] Initial value of fault current: When calculating the fault current of renewable energy power sources, first calculate the voltage at the grid connection point of the renewable energy power generation system when each renewable energy source is withdrawn and after a grid failure occurs, and then calculate the fault current of each renewable energy power source under this fault voltage. The fault current calculated for the first time is the initial value of the fault current of this renewable energy power source.

[0036] Basic mode: represents the operation of the power grid under full load or high load conditions.

[0037] Basic small mode: represents the operation of the power grid under low load or specific load distribution.

[0038] N-2 maintenance: refers to the maintenance and testing of the power grid under the condition of simulating the simultaneous failure of two components (such as lines or equipment) to evaluate the stability and reliability of the power grid.

[0039] To facilitate understanding of this embodiment, a fault current calculation method disclosed in the embodiment of the present disclosure is first described in detail. The fault current calculation method provided in the embodiment of the present disclosure can be applied to the following examples: Figure 1 In the hardware environment composed of the terminal 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104.

[0040] The network may include but is not limited to at least one of the following: a wired network, a wireless network. The wired network may include but is not limited to at least one of the following: a wide area network, a metropolitan area network, a local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal 102 may not be limited to a PC, a mobile phone, a tablet computer, etc.

[0041] The fault current calculation method of the embodiment of the present disclosure can be executed by the server 104, or by the terminal 102, or by the server 104 and the terminal 102. The fault current calculation method of the embodiment of the present disclosure can also be executed by the client installed on the terminal 102. The embodiment of the present disclosure provides a fault current calculation system, which includes: a terminal and a server; the terminal is used to send fault condition data to the server and receive the final fault current; the server is used to execute the fault current calculation method.

[0042] Figure 2 The schematic diagram of the flow chart of the fault current calculation method provided by the embodiment of the present disclosure is shown. Figure 2 It can be seen that the embodiment of the present disclosure at least includes steps S201 to S204:

[0043] Step S201: According to the acquired fault condition data, a fault calculation is performed on a pre-built target power grid model to obtain initial electrical quantity data of each location in the target power grid.

[0044] In this step, the fault condition data includes, for example, fault type, fault point location, line parameters, operating status of each power source, voltage of each power source point, power grid topology, etc., which are not limited in the embodiments of the present disclosure. During implementation, simulation software, such as power grid setting calculation software, can be used to set the fault according to the received fault condition data, and then perform fault simulation calculation, first setting the initial fault current of each nonlinear unit to 0, and obtaining the initial electrical quantity data of each position of the power grid when there is only a linear unit, that is, a conventional power supply, such as voltage, current, etc.

[0045] Step S202: for any target nonlinear unit in the target power grid, based on the initial electrical quantity data of each position, parameter value data of a target characteristic parameter is generated, wherein the target characteristic parameter includes at least one of the following: a first parameter for describing the electrical relationship between the grid connection point and the fault point of the target nonlinear unit, a second parameter for reflecting the operating mode of the target power grid, and a third parameter for describing the electrical status of other nonlinear units.

[0046] The target nonlinear unit is a power network element with a nonlinear relationship between output voltage and output current, such as new energy equipment such as wind power generation system, solar power generation system, flexible DC transmission line, etc. The embodiments of the present disclosure are not limited to this.

[0047] It has been found through research that in the disclosed embodiment, when calculating the fault current of a power grid containing nonlinear units, the parameters of the lines, generators, transformers and other equipment in the power grid will not change, and the topological connection of the equipment in the power grid will not change. The factors that affect the fault current of each nonlinear unit mainly include the fault condition, the operation mode of the power grid, other nonlinear units, etc.

[0048] Step S203: determining a target initial fault current prediction model according to the fault type in the fault condition data, and inputting the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value.

[0049] It has been found through research that for different fault types, such as single-phase ground fault, two-phase ground fault, two-phase phase-to-phase fault, three-phase phase-to-phase fault, etc., even if these faults occur at the same location, the fault current of the nonlinear unit will be different due to the different fault types. Therefore, in this embodiment, different models are selected for prediction for different fault types. When training, each model will only use the characteristic parameters under the same fault type for training. Therefore, in this step, the target initial fault current prediction model that matches the fault type can be selected first according to the fault type, and then the parameter value data can be input into the target initial fault current prediction model to obtain the initial fault current prediction value.

[0050] Step S204: performing iterative calculation based on the preset node voltage equation and each of the initial fault current prediction values ​​to obtain a final fault current of each nonlinear unit in the target power grid.

[0051] from Figure 1It can be seen from the method shown that the embodiment of the present disclosure performs fault calculation on the pre-constructed target power grid model according to the acquired fault condition data to obtain the initial electrical quantity data of each position in the target power grid; for any target nonlinear unit in the target power grid, based on the initial electrical quantity data of each position, the parameter value data of the target characteristic parameter is generated, wherein the target characteristic parameter includes at least one of the following: a first parameter for describing the electrical relationship between the target nonlinear unit grid connection point and the fault point, a second parameter for reflecting the operation mode of the target power grid, and a third parameter for describing the electrical state of other nonlinear units; according to the fault type in the fault condition data, the target initial fault current prediction model is determined, and the parameter value data is input into the target initial fault current prediction model to obtain the initial fault current prediction value. It can be seen that the above steps can predict a more reasonable and accurate initial fault current prediction value through the target initial fault current prediction model, so that when iterative calculation is performed based on each initial fault current prediction value and combined with the preset node voltage equation, the number of iterative calculations can be effectively reduced, the convergence of iterative calculations and the calculation speed can be improved, thereby greatly improving the calculation efficiency of the fault current of the new power system.

[0052] Further, in order to better illustrate the process of the above fault current calculation method, as a refinement and extension of the above embodiment, the embodiment of the present invention provides several optional embodiments, but is not limited thereto, which are specifically as follows:

[0053] In a possible implementation manner, if the target characteristic parameter includes the first parameter; the first parameter includes the transfer impedance between the target nonlinear unit grid connection point and the fault point; if the target characteristic parameter includes the second parameter; the second parameter includes at least one of the following: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the target nonlinear unit grid connection point; if the target characteristic parameter includes the third parameter; the third parameter includes at least one of the following: the transfer admittance between other nonlinear unit grid connection points and the target nonlinear unit grid connection point, and the voltage per unit value of other nonlinear unit grid connection points.

[0054] According to research, regarding the fault location, when the fault occurs at the nonlinear unit grid connection point, the fault current generated may be much greater than the fault current generated by the nonlinear unit when the fault occurs at the other end of the grid. The difference may be dozens or even hundreds of times. Therefore, the influence of the fault location on the fault current of the nonlinear unit cannot be ignored. Therefore, the characteristic parameter Z is defined as f , represents the transfer impedance between the target nonlinear unit grid connection point and the fault point. Figure 3 FIG. 1 shows a schematic diagram of a passive linear power grid connection provided by an embodiment of the present disclosure. Figure 3 The calculation method of transfer impedance is given. Figure 3 In , E1, Ei, and En represent the voltages of the first, i-th, and n-th linear unit grid connection points, respectively. During implementation, the node impedance matrix can be generated based on the target grid's line, transformer, and other equipment parameter data and the target grid topology data; then, the initial voltage at the target nonlinear unit grid connection point is obtained from the initial electrical quantity data at each location of the grid. Then, the node impedance matrix can be used to calculate the transfer current at the fault point. Since the fault current of each nonlinear unit is initially 0, the equipment parameters and topology in the grid are fixed, which is equivalent to a passive linear network. Therefore, the given voltage is linearly related to the transfer current, that is, the transfer impedance can be calculated according to the following formula:

[0055]

[0056] Among them, E f is the initial voltage of the grid connection point of the given target nonlinear unit, I f is the transfer current at the fault point.

[0057] The study found that there are two reasons why the grid operation mode affects the fault current of nonlinear units.

[0058] First, the commissioning and withdrawal of linear units other than non-linear units in the target power grid will affect the fault voltage at the grid connection point of the target nonlinear unit, thereby affecting the fault current of the target nonlinear unit. Therefore, the characteristic parameter G can be defined as i , represents the switching status of the linear unit in the target power grid. Among them, i is the serial number of the linear unit, that is, when there are n linear units in the target power grid, there are n characteristic parameters G1~Gn. During implementation, the parameter value of the parameter can be obtained from the fault condition data.

[0059] Second, the input and output of non-power equipment such as lines and transformers in the target power grid, that is, the change in the operation mode of the equipment, will also affect the degree of electrical connection between each linear unit and the target nonlinear unit grid connection point, thereby affecting the fault current of the target nonlinear unit. Therefore, the characteristic parameter M can be defined as i , represents the transfer voltage ratio between each linear unit in the power grid and the target nonlinear unit grid connection point. When there are n nonlinear units in the power grid, there are M1~M n , n characteristic parameters. Figure 4 Another passive linear power grid wiring diagram provided by the embodiment of the present disclosure is shown. Figure 4A calculation method for the transfer voltage ratio is given. When implemented, the node impedance matrix can be generated first according to the device parameter data and the grid topology data of the target grid; then, for any target linear unit, the initial voltage at the grid connection point of the target linear unit is obtained from the initial electrical quantity data of each position of the grid, and the node impedance matrix can be used to calculate the transfer voltage at the grid connection point of the target nonlinear unit. Since the fault current of each nonlinear unit is initially 0, the device parameters and topology structure in the grid are fixed, which is equivalent to a passive linear network. Therefore, the given voltage is linearly related to the transfer voltage, that is, the transfer voltage ratio between the target linear unit and the target nonlinear unit can be calculated according to the following formula:

[0060]

[0061] Through research, it is found that for the factor of other nonlinear units, since there is an electrical connection between the nodes in the power grid, the fault current injected into other nonlinear units of the power grid will affect the voltage of the current target nonlinear unit grid connection point, thereby affecting the fault current of the current target nonlinear unit. Therefore, the characteristic parameter Y can be defined as i , represents the transfer admittance between other nonlinear units in the power grid and the target nonlinear unit grid connection point, where i is the serial number of each other nonlinear unit. When there are n nonlinear units in the power grid, there are characteristic parameter values ​​Y1~Y n-1 . Figure 5 FIG. 2 shows another passive linear power grid wiring schematic diagram provided by an embodiment of the present disclosure. Figure 5 A calculation method for transfer admittance is given. When implemented, the node impedance matrix can be generated first according to the device parameter data and the topological structure data of the target power grid; then, for any target other nonlinear unit, the initial current of the target other nonlinear unit is obtained from the initial electrical quantity data of each position of the power grid, and the node impedance matrix can be used to calculate the transfer voltage at the grid connection point of the target nonlinear unit. Since the fault current of each nonlinear unit is initially 0, the device parameters and topological structure in the power grid are fixed, which is equivalent to a passive linear network. Therefore, the initial current and the transfer voltage are linearly related, that is, the transfer admittance can be calculated according to the following formula.

[0062]

[0063] Among them, I i is the initial current of the other nonlinear units of the target.

[0064] You can also define the characteristic parameter U i , which means that when the target power grid fails, all nonlinear units are disconnected, and the calculated voltage per unit value of each nonlinear unit grid connection point is obtained. i is the serial number of each nonlinear unit. When there are n nonlinear units in the power grid, there are a total of U1~Un During implementation, the initial voltage at each nonlinear unit grid connection point can be obtained from the initial electrical quantity data at each location of the power grid, and then, based on each initial voltage and a preset reference voltage, the per unit voltage value at each nonlinear unit grid connection point can be calculated.

[0065] Exemplarily, the target characteristic parameters include the transfer impedance between the target nonlinear unit grid connection point and the fault point, the switching state of each linear unit in the target power grid, the transfer voltage ratio between each linear unit and the target nonlinear unit grid connection point, the transfer admittance between other nonlinear unit grid connection points and the target nonlinear unit grid connection point, and the voltage per unit value of other nonlinear unit grid connection points. Then the parameter value data X fault =

[0066] [Z f ,G1,..G i ,M1,..M i ,Y1,..Y i ,U1,..U i ], where X fault Parameter value data representing target characteristic parameters. It should be noted that the examples given here are only illustrative and do not limit the embodiments of the present disclosure.

[0067] In a possible implementation manner, before the step of inputting the parameter value data into the target initial fault current prediction model to obtain the initial fault current prediction value, the method further includes:

[0068] Step A1: obtaining a training sample set, wherein the training samples in the training sample set include parameter value data of sample characteristic parameters of sample nonlinear units under the fault type in the target power grid, and a fault current as a label; the sample characteristic parameters include at least one of the following: a fourth parameter for describing the electrical relationship between the grid connection point and the fault point of the sample nonlinear unit, a fifth parameter for reflecting the operation mode of the target power grid, and a sixth parameter for describing the electrical state of other nonlinear units;

[0069] Step A2: Using the training sample set, the initial fault current prediction model to be trained is trained to obtain the target initial fault current prediction model.

[0070] In this embodiment, in a possible implementation manner, if the sample characteristic parameters include the fourth parameter; the fourth parameter includes the transfer impedance between the sample nonlinear unit grid connection point and the fault point; if the sample characteristic parameters include the fifth parameter; the fifth parameter includes at least one of the following: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the sample nonlinear unit grid connection point; if the sample characteristic parameters include the sixth parameter; the sixth parameter includes at least one of the following: the transfer admittance between other nonlinear unit grid connection points and the sample nonlinear unit grid connection points, and the voltage per unit value of other nonlinear unit grid connection points.

[0071] During implementation, different fault conditions under the same fault type can be set, and fault calculation can be performed on the pre-built target power grid model to obtain the initial electrical quantity data of each location in the target power grid, and the initial electrical quantity data can be used to calculate the characteristic parameter Z according to the above calculation method. f , G i 、M i , Y i , U i The parameter value data of the sample characteristic parameter of a training sample is calculated by the method. Then, the fault current iterative calculation method is used to calculate the final grid-connected fault current of the sample nonlinear unit as the label data of the training sample.

[0072] In actual application scenarios, when the scale of the power grid is large and there are many nonlinear unit nodes, due to the presence of a large number of power supply nodes, the number of characteristic parameters of the target nonlinear unit will also increase proportionally, thereby greatly increasing the model calculation cost. Based on this, in a possible implementation of the present disclosure, the parameter value data of the sample characteristic parameters of the sample nonlinear unit are screened according to the following method 1 and / or method 2:

[0073] Method 1: construct an electrical network diagram of the target power grid; use a preset shortest path algorithm to calculate the shortest electrical paths from each linear unit node and each nonlinear unit node in the target power grid to the fault point node; based on the shortest electrical path corresponding to the sample nonlinear unit node, screen each linear unit and other nonlinear units except the sample nonlinear unit to obtain at least one power supply to be deleted; delete the parameter value associated with the at least one power supply to be deleted in the parameter value data of the sample nonlinear unit.

[0074] Method 2: Process the data in the training sample set using a preset feature correlation analysis method to obtain at least one feature parameter to be deleted; delete the parameter value corresponding to the at least one feature parameter to be deleted in the parameter value data of the sample nonlinear unit.

[0075] For power supply nodes that are far apart in the power grid, their impact on the fault current of the sample nonlinear unit will decrease rapidly as the scale of the power grid increases. Therefore, in this embodiment, in one implementation, the parameter value data of the sample characteristic parameters of the sample nonlinear unit can be screened using a method. During implementation, the electrical network diagram of the target power grid can be constructed first. Specifically, each linear unit and nonlinear unit can be used as a node of the graph, and the lines and transformers in the electrical network can be represented as edges in the graph. It is also possible to assign a weight to each edge according to actual conditions, and this weight usually represents the impedance of the line or transformer. Then, the preset shortest path algorithm is used to calculate the shortest electrical path from each linear unit node and each nonlinear unit node in the target power grid to the fault point node (the weights / impedances of all edges on the shortest path can be added to obtain the total impedance, that is, the shortest electrical path). Here, the preset shortest path algorithm can be, for example, the Dijkstra algorithm, the Floyd-Warshall algorithm, etc., which is not limited to the embodiments of the present disclosure. Next, the shortest electrical path corresponding to the sample nonlinear unit node can be used as a reference to screen each linear unit and other nonlinear units except the sample nonlinear unit to obtain at least one power source to be deleted. For example, each shortest electrical path can be sorted, and the power grid power source corresponding to the shortest electrical path greater than or equal to the reference shortest electrical path is determined as the power source to be deleted. Finally, the parameter value data of the sample nonlinear unit involving each power source to be deleted is deleted, thereby completing the screening of the parameter value data of the sample characteristic parameters of the sample nonlinear unit.

[0076] In another embodiment, the parameter value data of the sample characteristic parameters of the sample nonlinear unit can be screened using the second method. During implementation, the data in the training sample set can be processed using a preset feature correlation analysis method to obtain at least one feature parameter to be deleted; for the parameter value data of the sample nonlinear unit, delete the parameter value corresponding to at least one feature parameter to be deleted. Here, the preset feature correlation analysis method can be, for example, a Pearson correlation coefficient method, a Spearman rank correlation coefficient method, a distance correlation coefficient method, a model-based feature selection method (such as a parcel feature selection method), a mutual information method, a variance selection method, etc. Exemplarily, the Pearson correlation coefficient between each feature parameter can be calculated by processing the data in the training sample set, and then the preset correlation threshold is used to screen each Pearson correlation coefficient to obtain a feature parameter with a smaller Pearson correlation coefficient as the feature parameter to be deleted. Finally, for the parameter value data of the sample nonlinear unit, delete the parameter values ​​corresponding to one or more feature parameters to be deleted.

[0077] In another embodiment, the parameter value data of the sample characteristic parameter of the sample nonlinear unit can be screened using the first method and the second method. Specifically, for example, the parameter value data of the sample characteristic parameter of the sample nonlinear unit can be screened using the first method to obtain the intermediate parameter value data corresponding to the sample nonlinear unit, and then the intermediate parameter value data can be deleted using the second method to obtain the final sample characteristic parameter value data of the sample nonlinear unit.

[0078] On the one hand, this embodiment can screen out power supply nodes that have little impact on the sample nonlinear unit due to their long distance, and eliminate the parameter values ​​of related power supplies in the sample characteristic value data; on the other hand, it can delete features with weak correlation with the fault current, thereby greatly reducing the dimension of the characteristic parameter data, improving the accuracy of the model and reducing the calculation cost.

[0079] After obtaining the training sample set, the training sample set can be used to train the initial fault current prediction model to be trained to obtain the target initial fault current prediction model. Here, the initial fault current prediction model to be trained can be, for example, a random forest model, a decision tree, or other algorithms. Specifically, in a possible implementation, the use of the training sample set to train the initial fault current prediction model to be trained to obtain the target initial fault current prediction model includes: dividing the training sample set into a training set and a test set; using the training set to train the initial fault current prediction model to be trained to generate a trained initial fault current prediction model; using the trained initial fault current prediction model to process the test set to obtain a prediction result; if the prediction result meets a preset condition, the trained initial fault current prediction model is used as the target initial fault current prediction model.

[0080] In specific implementation, the training sample set can be divided into a training set and a test set. Specifically, for example, a stratified sampling method can be used. For multiple data under the same fault condition, different operation modes, and maintenance conditions, a portion of the data, such as 20% of the data, can be randomly selected as the test set data according to a certain ratio, thereby ensuring that the sampling error in the data used for training and testing is less affected.

[0081] Then, the training set is used to train the initial fault current prediction model to be trained to generate a trained initial fault current prediction model. During implementation, in order to improve the stability and generalization ability of the model, a hyperparameter search algorithm, such as a grid search method, can be used to find the optimal hyperparameter combination of the model. Then, the initial fault current prediction model to be trained is initialized using the optimal hyperparameter combination, and the training set is used for training to obtain a trained initial fault current prediction model.

[0082] Next, the trained initial fault current prediction model is used to process the samples in the test set to obtain the prediction results. If the prediction results meet the preset conditions, the trained initial fault current prediction model is directly used as the target initial fault current prediction model. Among them, the preset conditions can be set according to actual needs, and the embodiments of the present disclosure are not limited to this. For example, the preset condition is that the change in the average value of the percentage deviation of the prediction result is less than the preset threshold. If the prediction result does not meet the preset conditions, the parameter value data of the sample characteristic parameters can be deleted or added according to the aforementioned method one and / or method two, and the initial fault current prediction model to be trained is retrained until a trained initial fault current prediction model that meets the preset conditions is obtained.

[0083] In a possible implementation manner, the iterative calculation is performed based on the preset node voltage equation and each of the initial fault current prediction values ​​to obtain the final fault current of each nonlinear unit in the target power grid, including: substituting each of the initial fault current prediction values ​​into the preset node voltage equation to obtain the corresponding initial fault voltage; for any target initial fault voltage, determining the target fault current according to a preset target voltage-current characteristic curve, using the target fault current as the initial fault current prediction value, and returning to the step of substituting each of the initial fault current prediction values ​​into the preset node voltage equation to obtain the corresponding initial fault voltage, until the change of each of the target initial fault voltages satisfies the preset convergence condition, and the final fault current of each nonlinear unit in the target power grid is obtained.

[0084] In this embodiment, the preset node voltage equations of each sequence network can be established according to the structure and component parameters of the target power grid as follows:

[0085]

[0086] Among them, U k is the voltage of each bus node in the target power grid, I k The target is the injected current of each bus node in the power grid, Z kk For example, if the kth and k+1th nodes are nonlinear unit grid connection points, the initial fault current prediction values ​​corresponding to the nonlinear units can be used as the injection current I of the kth and k+1th nodes when calculating the voltage of each node of the grid for the first time. k1 ,I (k+1)1 , the injected current I k1 ,I (k+1)1 Substituting into the above node voltage equation, we can get the initial fault voltage U of node k obtained by the first iteration calculation: k1 、k+1 node initial fault voltage U (k+1)1 Next, for any target initial fault voltage, such as Uk1 , according to the preset voltage-current characteristic curve of the k-node nonlinear unit, determine the target fault current I k2 , and then for U (k+1)1 , according to the preset voltage-current characteristic curve of the k+1 node nonlinear unit, determine the target fault current I (k+1)2 Then the target fault current I k2 ,I (k+1)2 Substituting into the above node voltage equation, we can get the initial fault voltage U of node k obtained by the second iteration calculation: k2 、k+1 node initial fault voltage U (k+1)2 . And so on, the iterative calculation is performed continuously as follows:

[0087] ΔI k =I k2 -I k1

[0088] ΔY k =ZΔI k

[0089] U k(n+1) =U k(n) +ΔU k

[0090] The voltage of the nonlinear unit grid connection point k after the n+1th iteration is U k(n+1) , the voltage of the nonlinear unit grid connection point k+1 after the n+1th iteration is U (k+1)(n+1) The preset convergence condition can be set according to actual needs. For example, the preset convergence condition can be: when ΔU k , ΔU k+1 When both are less than the preset threshold, the convergence condition is met and the iterative calculation is stopped. kn ,I (k+1)n are the calculated final fault currents at the kth and k+1th nodes / nonlinear unit grid connection points respectively.

[0091] The present disclosure also provides a method for calculating a fault current, comprising the following steps:

[0092] Step S1: According to the acquired fault condition data, a fault calculation is performed on the pre-built target power grid model to obtain the initial electrical quantity data of each location in the target power grid.

[0093] Step S2: for any target nonlinear unit in the target power grid, based on the initial electrical quantity data of each position, generate parameter value data of the target characteristic parameter, wherein the target characteristic parameter includes at least one of the following: a first parameter for describing the electrical relationship between the grid connection point and the fault point of the target nonlinear unit, a second parameter for reflecting the operating mode of the target power grid, and a third parameter for describing the electrical state of other nonlinear units.

[0094] During implementation, the first parameter includes the transfer impedance between the target nonlinear unit grid connection point and the fault point; the second parameter includes: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the target nonlinear unit grid connection point; the third parameter includes: the transfer admittance between the grid connection points of other nonlinear units and the grid connection points of the target nonlinear unit, and the voltage per unit value of the grid connection points of other nonlinear units.

[0095] Step S3: Determine a target initial fault current prediction model according to the fault type in the fault condition data, and input the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value.

[0096] In specific implementation, the target initial fault current prediction model can be trained according to the following method:

[0097] A training sample set is obtained, wherein the training samples in the training sample set include parameter value data of sample characteristic parameters of sample nonlinear units in the target power grid and under the fault type, and the fault current as a label; the sample characteristic parameters include at least one of the following: a fourth parameter for describing the electrical relationship between the grid connection point of the sample nonlinear unit and the fault point, a fifth parameter for reflecting the operation mode of the target power grid, and a sixth parameter for describing the electrical state of other nonlinear units. Among them, the fourth parameter includes the transfer impedance between the grid connection point of the sample nonlinear unit and the fault point; the fifth parameter includes: the throw-in and throw-out state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the grid connection point of the sample nonlinear unit; the sixth parameter includes: the transfer admittance between the grid connection point of other nonlinear units and the grid connection point of the sample nonlinear unit, and the voltage per unit value of the grid connection point of other nonlinear units.

[0098] For example, in a regional power grid model, there are 459 nodes in the entire network. A certain setting project is selected, which has 20 nodes, 32 lines, and 3 nonlinear unit grid-connected nodes. Fault conditions are set in the setting system. On the basis of large and small basic modes, the lines in the project are set for N-2 maintenance, and the voltage of each node of the power grid and the initial value of the voltage of the grid-connected point of the new energy power source and the fault current are calculated when the non-maintenance line fails under all maintenance conditions, and a training sample set of 63,540 items is generated.

[0099] Next, the training sample set is divided into a training set and a test set; the training set is used to train the initial fault current prediction model to be trained to generate a trained initial fault current prediction model; the trained initial fault current prediction model is used to process the test set to obtain a prediction result; if the prediction result meets the preset conditions, the trained initial fault current prediction model is used as the target initial fault current prediction model. The following Table 1 shows the prediction results of the test set:

[0100] Table 1

[0101]

[0102] The constructed target initial fault current prediction model is applied to the three nonlinear unit grid connection points. In the setting system, the prediction model is used and not used to calculate the grid fault. The number of iterations, time consumption and average deviation of multiple fault calculations are statistically analyzed and the results are shown in Table 2.

[0103] Table 2

[0104]

[0105] From Table 2, it can be seen that after the predicted initial fault current prediction value is applied to the iterative calculation using the prediction model, the calculation time is 3.1s, which is 3.2s faster than the prior art, and the error is no more than 0.64%. It can be seen that compared with the prior art, the fault calculation scheme proposed in the present disclosure can greatly reduce the number of iterative calculations, improve the calculation efficiency, and reduce the calculation time while ensuring the correctness of the calculation.

[0106] During implementation, the feature data in the training sample set can also be reduced in dimension, specifically: construct an electrical network diagram of the target power grid; use a preset shortest path algorithm to calculate the shortest electrical paths from each linear unit node and each nonlinear unit node in the target power grid to the fault point node; based on the shortest electrical path corresponding to the sample nonlinear unit node, screen each linear unit and other nonlinear units except the sample nonlinear unit to obtain at least one power supply to be deleted; delete the parameter value associated with at least one power supply to be deleted in the parameter value data of the sample nonlinear unit; and / or, use a preset feature correlation analysis method to process the data in the training sample set to obtain at least one feature parameter to be deleted; delete the parameter value corresponding to at least one feature parameter to be deleted in the parameter value data of the sample nonlinear unit.

[0107] Step S4: Substitute each initial fault current prediction value into a preset node voltage equation to obtain a corresponding initial fault voltage.

[0108] Step S5: For any target initial fault voltage, determine the target fault current according to the preset target voltage-current characteristic curve, use the target fault current as the initial fault current prediction value, and return to the step of substituting each initial fault current prediction value into the preset node voltage equation to obtain the corresponding initial fault voltage, until the change of each target initial fault voltage meets the preset convergence condition, and the final fault current of each nonlinear unit in the target power grid is obtained.

[0109] Those skilled in the art will appreciate that, in the above method of the specific implementation manner, the writing order of the steps does not mean a strict execution order, but does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0110] It should be noted that, in practical applications, all possible implementations described above can be combined in any manner to form possible embodiments of the present disclosure, which will not be described one by one here.

[0111] Based on the same concept, the embodiment of the present disclosure also provides a fault current calculation device, Figure 6 FIG. 1 shows a schematic diagram of the structure of the fault current calculation device provided by the embodiment of the present disclosure, see FIG. Figure 6 As shown, the fault current calculation device 600 provided in the embodiment of the present disclosure includes:

[0112] The acquisition module 601 is used to perform fault calculation on the pre-built target power grid model according to the acquired fault condition data, and obtain the initial electrical quantity data of each position in the target power grid;

[0113] A feature generation module 602 is used to generate parameter value data of a target feature parameter for any target nonlinear unit in the target power grid based on the initial electrical quantity data of each position, wherein the target feature parameter includes at least one of the following: a first parameter for describing the electrical relationship between the grid connection point and the fault point of the target nonlinear unit, a second parameter for reflecting the operation mode of the target power grid, and a third parameter for describing the electrical state of other nonlinear units;

[0114] The prediction module is used for 603, determining a target initial fault current prediction model according to the fault type in the fault condition data, and inputting the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value;

[0115] The calculation module 604 is used to perform iterative calculation based on the preset node voltage equation and each of the initial fault current prediction values ​​to obtain the final fault current of each nonlinear unit in the target power grid.

[0116] In a possible implementation manner, in the above-mentioned device, if the target characteristic parameter includes the first parameter; the first parameter includes the transfer impedance between the target nonlinear unit grid connection point and the fault point; if the target characteristic parameter includes the second parameter; the second parameter includes at least one of the following: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the target nonlinear unit grid connection point; if the target characteristic parameter includes the third parameter; the third parameter includes at least one of the following: the transfer admittance between other nonlinear unit grid connection points and the target nonlinear unit grid connection point, and the voltage per unit value of other nonlinear unit grid connection points.

[0117] In a possible implementation manner, the device further includes a training module, which is used to: obtain a training sample set, wherein the training samples in the training sample set include parameter value data of sample characteristic parameters of sample nonlinear units in the target power grid and under the fault type, and a fault current as a label; the sample characteristic parameters include at least one of the following: a fourth parameter for describing the electrical relationship between the grid connection point and the fault point of the sample nonlinear unit, a fifth parameter for reflecting the operating mode of the target power grid, and a sixth parameter for describing the electrical state of other nonlinear units; and use the training sample set to train the initial fault current prediction model to obtain the target initial fault current prediction model.

[0118] In a possible implementation manner, in the above-mentioned device, if the sample characteristic parameters include the fourth parameter; the fourth parameter includes the transfer impedance between the sample nonlinear unit grid connection point and the fault point; if the sample characteristic parameters include the fifth parameter; the fifth parameter includes at least one of the following: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the sample nonlinear unit grid connection point; if the sample characteristic parameters include the sixth parameter; the sixth parameter includes at least one of the following: the transfer admittance between other nonlinear unit grid connection points and the sample nonlinear unit grid connection points, and the voltage per unit value of other nonlinear unit grid connection points.

[0119] In a possible implementation manner, the device further includes a screening module, which is used to: construct an electrical network diagram of the target power grid; use a preset shortest path algorithm to calculate the shortest electrical paths from each linear unit node and each nonlinear unit node in the target power grid to the fault point node; based on the shortest electrical path corresponding to the sample nonlinear unit node, screen each linear unit and other nonlinear units except the sample nonlinear unit to obtain at least one power supply to be deleted; delete the parameter value associated with the at least one power supply to be deleted in the parameter value data of the sample nonlinear unit; and / or use a preset feature correlation analysis method to process the data in the training sample set to obtain at least one feature parameter to be deleted; delete the parameter value corresponding to the at least one feature parameter to be deleted in the parameter value data of the sample nonlinear unit.

[0120] In a possible implementation, in the above-mentioned device, the training module is used to: divide the training sample set into a training set and a test set; use the training set to train the initial fault current prediction model to be trained to generate a trained initial fault current prediction model; use the trained initial fault current prediction model to process the test set to obtain a prediction result; if the prediction result meets a preset condition, use the trained initial fault current prediction model as the target initial fault current prediction model.

[0121] In a possible implementation, in the above-mentioned device, the calculation module 604 is used to: substitute each of the initial fault current prediction values ​​into the preset node voltage equation to obtain the corresponding initial fault voltage; for any target initial fault voltage, determine the target fault current according to a preset target voltage-current characteristic curve, use the target fault current as the initial fault current prediction value, and return to the step of substituting each of the initial fault current prediction values ​​into the preset node voltage equation to obtain the corresponding initial fault voltage, until the change of each of the target initial fault voltages meets the preset convergence condition, and obtains the final fault current of each nonlinear unit in the target power grid.

[0122] It should be noted that any of the above-mentioned fault current calculation devices can implement the above-mentioned fault current calculation method in a one-to-one correspondence, which will not be repeated here.

[0123] Figure 7 FIG. 1 shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 7As shown, at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.

[0124] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0125] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0126] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a fault current calculation device at the logical level. The processor executes the program stored in the memory and is specifically used to execute the above method.

[0127] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0128] The electronic device can execute the fault current calculation method provided by the multiple embodiments of the present disclosure, and realize the fault current calculation device in Figure 6 The functions of the illustrated embodiments will not be described in detail in the embodiments of the present disclosure.

[0129] The embodiments of the present disclosure also provide a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute the fault current calculation method provided by multiple embodiments of the present disclosure.

[0130] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0135] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0136] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0137] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity or device including the element.

[0138] It will be appreciated by those skilled in the art that the embodiments of the present disclosure may be provided as methods, systems or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0139] The above are only embodiments of the present disclosure and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the scope of the claims of the present disclosure.

Claims

1. A fault current calculation method, characterized in that: The method comprises: According to the acquired fault condition data, the pre-built target power grid model is subjected to fault calculation to obtain the initial electrical quantity data of each location in the target power grid; For any target nonlinear unit in the target power grid, based on the initial electrical quantity data of each position, parameter value data of a target characteristic parameter is generated, wherein the target characteristic parameter includes at least one of the following: a first parameter for describing the electrical relationship between the grid connection point and the fault point of the target nonlinear unit, a second parameter for reflecting the operation mode of the target power grid, and a third parameter for describing the electrical state of other nonlinear units; Determine a target initial fault current prediction model according to the fault type in the fault condition data, and input the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value; Based on the preset node voltage equation and each of the initial fault current prediction values, iterative calculation is performed to obtain the final fault current of each nonlinear unit in the target power grid; The first parameter includes the transfer impedance between the target nonlinear unit grid connection point and the fault point; The second parameter includes at least one of the following: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the target nonlinear unit grid connection point; The third parameter includes at least one of the following: transfer admittance between other nonlinear unit grid connection points and the target nonlinear unit grid connection point, and voltage per unit value of other nonlinear unit grid connection points; Before the step of inputting the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value, the method further includes: Acquire a training sample set, wherein the training samples in the training sample set include parameter value data of sample characteristic parameters of sample nonlinear units in the target power grid and under the fault type, and a fault current as a label; the sample characteristic parameters include at least one of the following: a fourth parameter for describing the electrical relationship between the grid connection point and the fault point of the sample nonlinear unit, a fifth parameter for reflecting the operation mode of the target power grid, and a sixth parameter for describing the electrical state of other nonlinear units; Using the training sample set, training the initial fault current prediction model to be trained to obtain the target initial fault current prediction model; The using the training sample set to train the initial fault current prediction model to be trained to obtain the target initial fault current prediction model includes: Dividing the training sample set into a training set and a test set; Using the training set to train the initial fault current prediction model to be trained, to generate a trained initial fault current prediction model; Using the trained initial fault current prediction model, the test set is processed to obtain a prediction result; If the prediction result meets the preset conditions, the trained initial fault current prediction model is used as the target initial fault current prediction model; The fourth parameter includes the transfer impedance between the grid connection point and the fault point of the sample nonlinear unit; The fifth parameter includes at least one of the following: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the grid connection point of the sample nonlinear unit; The sixth parameter includes at least one of the following: a transfer admittance between other nonlinear unit grid connection points and the sample nonlinear unit grid connection points, and a voltage per unit value of other nonlinear unit grid connection points.

2. The method according to claim 1, characterized in that The method further comprises: Constructing an electrical network diagram of the target power grid; Using a preset shortest path algorithm, the shortest electrical paths from each linear unit node and each nonlinear unit node in the target power grid to the fault point node are calculated; Taking the shortest electrical path corresponding to the sample nonlinear unit node as a reference, screening each linear unit and other nonlinear units except the sample nonlinear unit to obtain at least one power supply to be deleted; Deleting the parameter value associated with the at least one power source to be deleted from the parameter value data of the sample nonlinear unit; and / or, The data in the training sample set is processed using a preset feature correlation analysis method to obtain at least one feature parameter to be deleted; and the parameter value corresponding to the at least one feature parameter to be deleted in the parameter value data of the sample nonlinear unit is deleted.

3. The method according to any one of claims 1-2, characterized in that: The iterative calculation based on the preset node voltage equation and each of the initial fault current prediction values ​​is performed to obtain the final fault current of each nonlinear unit in the target power grid, including: Substituting each of the initial fault current prediction values ​​into the preset node voltage equation to obtain a corresponding initial fault voltage; For any target initial fault voltage, a target fault current is determined according to a preset target voltage-current characteristic curve, and the target fault current is used as the initial fault current prediction value. The process returns to the step of substituting each of the initial fault current prediction values ​​into the preset node voltage equation to obtain the corresponding initial fault voltage, until the change of each of the target initial fault voltages meets the preset convergence condition, thereby obtaining the final fault current of each nonlinear unit in the target power grid.

4. A fault current calculation device, characterized in that: The device comprises: An acquisition module is used to perform fault calculation on a pre-built target power grid model according to the acquired fault condition data, and obtain initial electrical quantity data of each location in the target power grid; A feature generation module, for generating parameter value data of a target feature parameter based on the initial electrical quantity data of each position for any target nonlinear unit in the target power grid, wherein the target feature parameter includes at least one of the following: a first parameter for describing the electrical relationship between the grid connection point and the fault point of the target nonlinear unit, a second parameter for reflecting the operation mode of the target power grid, and a third parameter for describing the electrical state of other nonlinear units; The prediction module is used to determine a target initial fault current prediction model according to the fault type in the fault condition data, and input the parameter value data into the target initial fault current prediction model to obtain an initial fault current prediction value; A calculation module, used for performing iterative calculation based on a preset node voltage equation and each of the initial fault current prediction values ​​to obtain a final fault current of each nonlinear unit in the target power grid; The first parameter includes the transfer impedance between the target nonlinear unit grid connection point and the fault point; the second parameter includes at least one of the following: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the target nonlinear unit grid connection point; the third parameter includes at least one of the following: the transfer admittance between other nonlinear unit grid connection points and the target nonlinear unit grid connection point, and the voltage per unit value of other nonlinear unit grid connection points; The device also includes a training module, which is used to: obtain a training sample set, wherein the training samples in the training sample set include parameter value data of sample characteristic parameters of sample nonlinear units in the target power grid and under the fault type, and a fault current as a label; the sample characteristic parameters include at least one of the following: a fourth parameter for describing the electrical relationship between the grid connection point and the fault point of the sample nonlinear unit, a fifth parameter for reflecting the operation mode of the target power grid, and a sixth parameter for describing the electrical state of other nonlinear units; using the training sample set, training the initial fault current prediction model to be trained to obtain the target initial fault current prediction model; The training module is specifically used to: divide the training sample set into a training set and a test set; use the training set to train the initial fault current prediction model to be trained to generate a trained initial fault current prediction model; use the trained initial fault current prediction model to process the test set to obtain a prediction result; if the prediction result meets a preset condition, use the trained initial fault current prediction model as the target initial fault current prediction model; The fourth parameter includes the transfer impedance between the sample nonlinear unit grid connection point and the fault point; the fifth parameter includes at least one of the following: the switching state of each linear unit in the target power grid, and the transfer voltage ratio between each linear unit and the sample nonlinear unit grid connection point; the sixth parameter includes at least one of the following: the transfer admittance between other nonlinear unit grid connection points and the sample nonlinear unit grid connection point, and the voltage per unit value of other nonlinear unit grid connection points.

5. A fault current calculation system, characterized in that: The system comprises: a terminal and a server; the terminal is used to send fault condition data to the server and receive the final fault current; the server is used to execute the steps of any method as claimed in claims 1-3.

6. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor is caused to perform the steps of the method according to any one of claims 1 to 3.

7. A computer-readable storage medium storing one or more programs, characterized in that: When the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device executes the steps of the method as claimed in any one of claims 1 to 3.

Images