Simulation intelligent network division method, system and device based on decoupling element and medium

Abstract

The embodiment of the invention relates to the technical field of computer networks, and discloses a simulation intelligent network division method, system and device based on a decoupling element and a medium. According to the invention, the circuit of the power system is subjected to alternating current and direct current separation and network division operation through the decoupling element, so that the circuit in the power system is certainly decoupled and the power system is not influenced; moreover, the simulation time is calculated for different network division modes, and the network division mode with the shortest time is selected for intelligent network division, so that the optimal network division mode can be selected according to the predicted time of simulation after different network division methods are provided for circuit network division, and the precision and efficiency of network division calculation are improved. And the simulation time is shortened to the maximum extent.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer network technology, and in particular to a simulation intelligent networking method, system, device and medium based on decoupling elements. Background Art

[0002] In large-scale power systems, due to the continuous growth of power demand and the widespread access to renewable energy, traditional power system simulation faces severe challenges in computing speed and data processing capabilities. As the complexity of power systems increases, real-time monitoring and rapid decision-making become increasingly important. Therefore, intelligent grid-splitting technology has gradually become a key tool to improve the speed of power system simulation.

[0003] However, the inventors found that there are at least the following problems in the related technology: the current network parallel calculation mainly uses the long transmission line decoupling network parallel algorithm, which converts the wave process of the distributed parameter line into a concentrated parameter circuit containing only resistance and current source, but the long transmission line decoupling network parallel algorithm is a natural decoupling method, and the decoupling conditions involve the simulation step size, transmission line capacitance value, inductance value and transmission line length. The decoupling conditions are relatively high and the calculation requirements are relatively strict. It is only applicable to some power systems and cannot adapt to all power systems. Therefore, a simulation intelligent network method, system, device and medium based on decoupling elements are needed to improve the accuracy of network parallel calculation and improve the versatility of network parallel calculation. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a simulation intelligent network partitioning method, system, device and medium based on decoupling elements, so that the circuits of the power system can be decoupled through the decoupling elements, and intelligent network partitioning can be performed based on the decoupling elements to improve the accuracy and efficiency of network partitioning calculations.

[0005] To solve the above technical problems, an embodiment of the present invention provides a simulation intelligent networking method based on decoupling elements, which is applied to the power system, including: separating the DC circuit and the AC circuit in the power system circuit based on the first decoupling element; performing admittance matrix networking and component networking on the AC circuit based on the second decoupling element; calculating the simulation time of the admittance matrix networking and the simulation time of the component networking; and selecting the networking method corresponding to the shortest simulation time for intelligent networking.

[0006] An embodiment of the present invention also provides an intelligent network partitioning system based on decoupling elements, comprising: an AC / DC separation module, used to separate the DC circuit and the AC circuit in the power system circuit based on a first decoupling element; a network partitioning module, used to perform admittance matrix network partitioning and component network partitioning on the AC circuit based on a second decoupling element; a simulation module, used to calculate the simulation time of the admittance matrix network partitioning and the simulation time of the component network partitioning; and an intelligent network partitioning module, used to select the network partitioning method corresponding to the shortest simulation time for intelligent network partitioning.

[0007] An embodiment of the present invention also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned simulated intelligent networking method based on decoupling elements.

[0008] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned simulation intelligent networking method based on decoupling elements.

[0009] In the embodiment of the present invention, the circuits of the power system are separated into AC and DC and divided into grids by decoupling elements, thereby ensuring that the circuits in the power system are decoupled and have no impact on the power system; and, because the simulation time is calculated for different grid division methods and the grid division method with the shortest time is selected for intelligent grid division, the present application can propose different grid division methods for circuit grid division and select the optimal grid division method based on the predicted time of the simulation, thereby improving the accuracy and efficiency of the grid division calculation and maximizing the shortening of the simulation time.

[0010] In addition, the admittance matrix network division specifically includes: after starting a single-step simulation, dividing the admittance matrix into the admittance matrices and injected currents of multiple sub-networks; calculating the node voltages of the multiple sub-networks according to the admittance matrices and injected currents of the multiple sub-networks; calculating component data according to the admittance matrices, injected currents and node voltages of the sub-networks to complete the single-step simulation.

[0011] In addition, the component sub-network specifically includes: after starting the single-step simulation, separating the components in the power system circuit into multiple sub-networks; starting the single-step simulation of the multiple sub-networks in parallel; after starting the single-step simulation, all sub-networks parallelly calculate the admittance matrix, injection current, and node voltage of each sub-network; all sub-networks calculate component data to complete the single-step simulation parallel calculation of each sub-network.

[0012] In addition, the calculation of the simulation time of the admittance matrix networking and the selection of the networking method corresponding to the shortest simulation time for intelligent networking and the simulation time of component networking include: predicting the simulation time through a partition time evaluation artificial intelligence model, and selecting an intelligent networking strategy based on the prediction results of the partition time evaluation artificial intelligence model.

[0013] In addition, the intelligent network partitioning strategy is selected according to the prediction results of the partition time evaluation artificial intelligence model, including: determining the maximum number of network partitions according to the hardware configuration of the power system circuit, traversing each network partition in order from large to small according to the simulation time, and selecting the network partitioning method in which the partition time of each network partition is close and the merging time is not greater than the preset time.

[0014] In addition, the decoupling element includes a decoupling transmission line and / or a decoupling line.

[0015] In addition, the decoupling circuit includes a first equivalent circuit and a second equivalent circuit; wherein the first equivalent circuit is close to the voltage side of the power system circuit, and the second equivalent circuit is close to the ground side of the power system circuit; wireless data transmission is performed between the first equivalent circuit and the second equivalent circuit. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0017] Figure 1 It is a flow chart of a simulation intelligent networking method based on decoupling elements provided in one embodiment of the present application;

[0018] Figure 2 A decoupling circuit is provided in a power system provided in an embodiment of the present application Figure 1 ;

[0019] Figure 3 A decoupling line circuit is provided in a power system provided by an embodiment of the present application Figure 2 ;

[0020] Figure 4 It is a schematic diagram of the electromagnetic transient simulation operation steps when the network is not divided provided by an embodiment of the present application;

[0021] Figure 5 It is a comparative schematic diagram of the admittance matrix before and after network division provided by an embodiment of the present application;

[0022] Figure 6 It is a schematic diagram of the admittance matrix networking steps provided in one embodiment of the present application;

[0023] Figure 7 It is a schematic diagram of the steps of component networking provided by an embodiment of the present application;

[0024] Figure 8 It is a schematic diagram of the structure of a simulation intelligent network partitioning system based on decoupling elements provided in one embodiment of the present application;

[0025] Fig. 9 It is a schematic diagram of the internal structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] Since the current network parallel calculation mainly uses the long transmission line decoupling network parallel algorithm, it converts the wave process of the distributed parameter line into a concentrated parameter circuit containing only resistance and current source. However, the long transmission line decoupling network parallel algorithm is a natural decoupling method. The decoupling conditions involve the simulation step size, transmission line capacitance value, inductance value and transmission line length. The decoupling conditions have high requirements and the calculation requirements are relatively strict. It is only applicable to some power systems and cannot adapt to all power systems. Therefore, a simulation intelligent network method, system, equipment and medium based on decoupling elements are needed to decouple the circuits of the power system through decoupling elements, and perform intelligent network division based on the decoupling elements to improve the accuracy and efficiency of network calculation.

[0027] To make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the embodiments of the present invention, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can be implemented. The division of the following embodiments is for the convenience of description, and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined and referenced with each other without contradiction.

[0028] One embodiment of the present invention relates to a simulation intelligent network division method based on decoupling elements, which can be applied to large-scale power systems. The simulation intelligent network division method based on decoupling elements includes: separating the DC circuit and AC circuit in the power system circuit based on a first decoupling element; performing admittance matrix network division and element network division on the AC circuit based on a second decoupling element; calculating the simulation time of the admittance matrix network division and the simulation time of the element network division; selecting the network division method corresponding to the shortest simulation time for intelligent network division. The circuit of the power system is separated from the AC and DC by the decoupling element and the network division operation is performed, which ensures that the circuit in the power system is definitely decoupled and does not affect the power system; and, because the simulation simulation time is calculated for different network division methods, and the network division method with the shortest time is selected for intelligent network division, the present application can propose different network division methods for circuit network division and select the optimal network division method according to the predicted time of simulation simulation, thereby improving the accuracy and efficiency of network division calculation and maximizing the shortening of simulation time. The following is a specific description of the implementation details of the simulated intelligent networking method based on decoupling elements according to an embodiment of the present invention. The following content is only provided for easy understanding of the implementation details and is not necessary for implementing the present solution.

[0029] like Figure 1 As shown, in step 101, a DC circuit and an AC circuit in a power system circuit are separated based on a first decoupling element.

[0030] In step 102, the AC circuit is subjected to admittance matrix and element networking based on a second decoupling element.

[0031] Specifically, in the embodiment of the present application, the difference between the first decoupling element and the second decoupling element is that the function of the first decoupling element is to separate the DC circuit and the AC circuit in the power system circuit; and the function of the second decoupling element is to divide the AC circuit in the power system. That is, in the description of the embodiment of the present application, the "first decoupling element" and the "second decoupling element" are distinguished and described to distinguish the functions of the decoupling elements. Those skilled in the art can understand that the actual specific structure or type of the decoupling element is not affected by the name of the decoupling element. The first decoupling element and the second decoupling element can be the same decoupling element or different decoupling elements.

[0032] In some embodiments of the present application, the circuit of the power system can be detected and the decoupling point in the circuit can be detected, and a decoupling element can be added at the position of the decoupling point. The decoupling point can be flexibly set according to the actual application requirements, so as to realize the network operation of the circuit without natural decoupling transmission line. The decoupling element includes a decoupling transmission line and / or a decoupling circuit. The decoupling circuit can decouple any circuit, and the decoupling circuit can make the transmission line no longer have high requirements for decoupling conditions. When using a decoupling circuit for decoupling, decoupling is performed through the decoupling circuit provided in the embodiment of the present application. Figure 2 As shown, the decoupling circuit is set in a circuit with a voltage source S, a resistor R and a ground wire Grd, and the decoupling circuit is connected in series through a bus. The decoupling circuit includes a first equivalent circuit and a second equivalent circuit; wherein the first equivalent circuit is close to the voltage side of the power system circuit, and the second equivalent circuit is close to the ground side of the power system circuit; wireless data transmission is performed between the first equivalent circuit and the second equivalent circuit.

[0033] Specifically, Figure 3 As shown, both the left equivalent circuit and the right equivalent circuit can be regarded as a circuit composed of an ammeter AM, a voltmeter VM, a resistor R and a controlled current source S. The first ammeter AM1 in the left equivalent circuit is connected in series with a parallel circuit composed of a first equivalent resistor R1, a first controlled current source S1 and a first voltmeter VM1 and then grounded; the second ammeter AM2 in the right equivalent circuit is connected in series with a parallel circuit composed of a second equivalent resistor R2, a second controlled current source S2 and a second voltmeter VM2 and then grounded. The left equivalent circuit transmits the inflow current IAM1 and the voltage to ground UVM1 to the right equivalent circuit through a dedicated interface; the right equivalent circuit transmits the inflow current IAM2 and the voltage to ground UVM2 to the left equivalent circuit through a dedicated interface, and uses data transmission instead of circuit simulation to realize the circuit's network division function.

[0034] Specifically, the resistance values ​​of the first equivalent resistor R1 and the second equivalent resistor R2 are calculated according to the resistance value R, the inductance value L, and the sampling frequency Ts of the decoupling circuit.

[0035] The current Is1 output by the first controlled current source and the current Is2 output by the second controlled current source can be calculated based on the first current IAM1 of the first ammeter AM1 and the first voltage UVM1 of the first voltmeter VM1 in the left equivalent circuit and the second current IAM2 of the second ammeter AM2 and the second voltage UVM2 of the second voltmeter VM2 in the right equivalent circuit.

[0036] The decoupling lines in the embodiments of the present application can cope with the situation where the transmission lines cannot be naturally decoupled under large step-size simulation, thereby achieving more flexible network division operations.

[0037] The decoupling lines in the embodiments of the present application can cope with the situation where the transmission lines cannot be naturally decoupled under large step-size simulation, thereby achieving more flexible network division operations.

[0038] In some embodiments of the present application, during the operation of electromagnetic transient simulation without network division, after the element calculates the admittance matrix and the injected current, the admittance matrix and the injected current are subjected to LU decomposition to calculate the node voltage, and the calculated node voltage is used to calculate the internal data of the current step element to complete the single-step simulation, such as Figure 4 As shown. LU decomposition is a method of decomposing a matrix into the product of two matrices, and is often used to simplify the solution of a system of linear equations. In power system analysis, LU decomposition is often used to solve node voltages. When calculating node voltages, a system of linear equations is usually established to represent the relationship between current, voltage, and impedance (for example, based on Kirchhoff's current law and Ohm's law). By performing LU decomposition on the matrix of this system of linear equations, the node voltage can be effectively solved. Compared with directly solving a system of linear equations, LU decomposition is more efficient, especially when repeatedly solving similar systems, the LU decomposition process can be reused.

[0039] In some embodiments of the present application, the admittance matrix is ​​divided into networks, specifically including: after starting a single-step simulation, dividing the admittance matrix into multiple network admittance matrices and injected currents; calculating the node voltages of the multiple network according to the admittance matrices and injected currents of the multiple network; calculating the component data according to the admittance matrix, injected current and node voltage of the network, and completing the single-step simulation. Specifically, Figure 5 and Figure 6 As shown in the figure, the AC circuit is divided into multiple small matrices through decoupling elements, and the injected current result is also divided into multiple injected current arrays according to the sub-network information. The divided admittance matrix and injected current are decomposed into LU to calculate the sub-network node voltage using parallel computing, so as to realize the parallel computing of node voltage. The size of the matrix to be solved is reduced by sub-networking the admittance matrix, thereby reducing the computational complexity.

[0040] Assume that the network is divided into m sub-networks through the admittance matrix, and the sub-network sizes are n1, n2, n3...n m , then the main network size is Before network division, the time complexity of solution is After the network is divided, the time complexity of the solution is In a specific embodiment of the present application, the admittance matrix is ​​divided into three sub-networks, and the sizes of the sub-networks are 10, 15, and 14 respectively. The time complexity of the un-networked solution can be calculated as: (10+15+14) 3 =59319; and the time complexity of solving after network division is 10 3 +15 3 +143 =7119, it can be seen that the computational complexity is significantly reduced after network division.

[0041] In some embodiments of the present application, the component sub-network specifically includes: after starting a single-step simulation, separating the components in the power system circuit into multiple sub-networks; starting a single-step simulation in parallel for the multiple sub-networks; after starting a single-step simulation, all sub-networks parallelly calculate the admittance matrix, injection current, and node voltage of each sub-network; all sub-networks calculate component data to complete the single-step simulation parallel calculation of each sub-network. Specifically, Figure 7 As shown, the component subnet also separates the circuit components into multiple subnets, and uses parallel computing to run multiple subnet algorithms simultaneously, that is, different subnets perform single-step simulation steps simultaneously, in parallel, and independently of each other. The embodiment of the present application can provide different subnetting methods for different situations, so as to perform flexible subnetting and facilitate further maximizing the reduction of simulation time.

[0042] In step 103, the simulation time of the admittance matrix network and the simulation time of the component network are calculated, and the network mode corresponding to the shortest simulation time is selected to perform intelligent network division.

[0043] In some embodiments of the present application, the simulation time of calculating the admittance matrix network and the network mode corresponding to the selection of the shortest simulation time are used for intelligent network division, and the simulation time of the component network division includes: predicting the simulation time through the partition time evaluation artificial intelligence model, and selecting the intelligent network division strategy according to the prediction result of the partition time evaluation artificial intelligence model. Specifically, the input of the partition time evaluation artificial intelligence model is the number of electrical nodes, the data transmission volume of the decoupling element, and the number of each component. A deep neural network is used as the hidden layer, and the simulation time is finally used as the output content. It should be noted that the selection of artificial intelligence models may not be limited to deep neural networks. Those skilled in the art can understand that the model can be flexibly adjusted according to actual production needs, such as support vector machine model, hidden Markov model, generative adversarial network, Q learning model, etc.; and the selection of models is not limited to one model, and a combination of multiple models can be selected to improve the authenticity and accuracy of the simulation time simulation, and this application is not limited here.

[0044] In some embodiments of the present application, the intelligent network partitioning strategy is selected according to the prediction results of the partition time evaluation artificial intelligence model, including: determining the maximum number of network partitions according to the hardware configuration of the power system circuit, traversing each network partition in order from large to small according to the simulation time, and selecting the network partitioning method in which the partition time of each network partition is close and the merging time is not greater than the preset time. Specifically, the preset time is the maximum estimated time, and the simulation time output by the partition time evaluation artificial intelligence model is sorted in order from large to small, and all the network partitions are traversed in turn, and the simulation time is paired to ensure that the merged operation time is not greater than the maximum estimated time, and to ensure that the time of each partition is close, that is, the mean square error of the single-step simulation time of the network partition is minimized, thereby achieving maximum parallel computing.

[0045] Specifically, for the host computer, according to the CPU resources of the host computer as the basis of the automatic allocation mechanism, according to the thread priority of the host computer CPU, in the form of queues, the idle cores are allocated one by one for calculation. Therefore, the maximum number of sub-networks of the host computer is the maximum number of CPU threads in the host computer; and for the lower computer, the CPU core can be bound to the algorithm, and the sub-network algorithm can be bound to the CPU core to realize the exclusive operation of the kernel, so as to realize the maximum number of sub-networks of the lower computer according to the number of CPU cores. If the number of sub-networks is greater than the maximum number of sub-networks, the simulation time of all sub-networks is added and divided by the maximum number of sub-networks, the theoretical parallel partition time is calculated, and the partitions are merged according to the theoretical parallel partition time, so as to ensure that the time of the merged partitions is close, that is, the mean square error of the merged partition time is minimized, and the parallel calculation is optimized according to the hardware configuration to realize dynamic sub-networks for different hardware configurations. When the hardware configuration does not match the number of sub-networks, the sub-networks are reorganized to average the simulation time, maximize the use of hardware performance, improve the parallel computing efficiency of large-scale power system circuit sub-networks, and improve the efficiency of power grid simulation experiment construction.

[0046] In an embodiment of the present invention, the circuits of the power system are separated into AC and DC and divided into grids by decoupling elements, thereby ensuring that the circuits in the power system are decoupled and have no impact on the power system; and, because the simulation time is calculated for different grid division methods and the grid division method with the shortest time is selected for intelligent grid division, the present application can propose different grid division methods for circuit grid division and select the optimal grid division method based on the predicted time of the simulation, thereby improving the accuracy and efficiency of the grid division calculation and maximizing the shortening of the simulation time.

[0047] The steps of the above method are divided only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0048] In addition, the examples mentioned in the above embodiments can be freely combined, and any combination can be understood as an embodiment. The "embodiment" or "example" appearing in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It can be understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0049] In summary, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results.

[0050] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0051] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists, A and B exist at the same time, and B exists. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0052] Another embodiment of the present invention relates to an intelligent network distribution system based on decoupling elements, such as Figure 8 As shown, including:

[0053] An AC / DC separation module, used to separate a DC circuit and an AC circuit in a power system circuit based on a first decoupling element;

[0054] A network division module, used for performing admittance matrix network division and element network division on the AC circuit based on the second decoupling element;

[0055] The simulation module is used to calculate the simulation time of the admittance matrix network and the simulation time of the component network, and select the network mode corresponding to the shortest simulation time for intelligent network division.

[0056] In an embodiment of the present invention, the circuits of the power system are separated into AC and DC and divided into grids by decoupling elements, thereby ensuring that the circuits in the power system are decoupled and have no impact on the power system; and, because the simulation time is calculated for different grid division methods and the grid division method with the shortest time is selected for intelligent grid division, the present application can propose different grid division methods for circuit grid division and select the optimal grid division method based on the predicted time of the simulation, thereby improving the accuracy and efficiency of the grid division calculation and maximizing the shortening of the simulation time.

[0057] It is not difficult to find that this embodiment is a device embodiment corresponding to the above method embodiment, and this embodiment can be implemented in conjunction with the above method embodiment. The relevant technical details mentioned in the above method embodiment are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above method embodiment.

[0058] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.

[0059] Another embodiment of the present invention relates to an electronic device, such as Fig. 9 As shown, it includes at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned simulation intelligent networking method based on decoupling elements.

[0060] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0061] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0062] Another embodiment of the present invention relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0063] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0064] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present invention, and that in actual applications, various changes may be made in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A simulation intelligent network partitioning method based on decoupling elements, characterized in that: Applied to power systems, including: Separating a DC circuit and an AC circuit in the power system circuit based on a first decoupling element; Performing admittance matrix and component networking on the AC circuit based on a second decoupling element; The simulation time of the admittance matrix network and the simulation time of the component network are calculated, and the network mode corresponding to the shortest simulation time is selected for intelligent network division.

2. The simulation intelligent network partitioning method based on decoupling elements according to claim 1 is characterized in that: The admittance matrix sub-network specifically includes: After starting the single-step simulation, the admittance matrix is ​​divided into multiple sub-network admittance matrices and injected currents; Calculating node voltages of the plurality of sub-networks according to the admittance matrices of the plurality of sub-networks and the injected currents; The component data is calculated based on the admittance matrix, injected current and node voltage of the sub-network to complete the single-step simulation.

3. The simulation intelligent network partitioning method based on decoupling elements according to claim 1 is characterized in that: The component sub-network specifically includes: After starting the single-step simulation, separating the components in the power system circuit into a plurality of sub-networks; The multiple sub-networks start single-step simulation in parallel; After starting the single-step simulation, all sub-networks calculate the admittance matrix, injection current, and node voltage of each sub-network in parallel; All sub-network calculation component data are completed, and single-step simulation and parallel calculation of each sub-network are completed.

4. The method for simulating intelligent networking based on decoupling elements according to claim 1, characterized in that: The calculation of the simulation time of the admittance matrix network segmentation and the selection of the network segmentation method corresponding to the shortest simulation time for intelligent network segmentation and the simulation time of the component network segmentation include: The simulation time is predicted by using a partition time evaluation artificial intelligence model, and an intelligent network partitioning strategy is selected according to the prediction results of the partition time evaluation artificial intelligence model.

5. The method for simulating intelligent networking based on decoupling elements according to claim 4, characterized in that: The selecting of the intelligent network partitioning strategy according to the prediction result of the artificial intelligence model for partitioning time evaluation includes: The maximum number of sub-networks is determined according to the hardware configuration of the power system circuit, and each sub-network is traversed in descending order according to the simulation time, and a sub-network division method in which the sub-network division time is close and the merging time is not greater than the preset time is selected for network division.

6. The simulation intelligent network partitioning method based on decoupling elements according to claim 1 is characterized in that: The decoupling element includes a decoupling transmission line and / or a decoupling line.

7. The method for simulating intelligent networking based on decoupling elements according to claim 6, characterized in that: The decoupling circuit includes a first equivalent circuit and a second equivalent circuit; Wherein, the first equivalent circuit is close to the voltage side of the power system circuit, and the second equivalent circuit is close to the ground side of the power system circuit; Wireless data transmission is performed between the first equivalent circuit and the second equivalent circuit.

8. An intelligent network distribution system based on decoupling elements, characterized in that: include: An AC / DC separation module, used to separate a DC circuit and an AC circuit in a power system circuit based on a first decoupling element; A network division module, used for performing admittance matrix network division and element network division on the AC circuit based on the second decoupling element; The simulation module is used to calculate the simulation time of the admittance matrix network and the simulation time of the component network, and select the network mode corresponding to the shortest simulation time for intelligent network division.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the simulated intelligent networking method based on decoupling elements as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the simulation intelligent networking method based on decoupling elements according to any one of claims 1 to 7 is implemented.

Images