Method and apparatus for simulating real-time electromagnetic transient of power system

Abstract

The application provides a simulation method and simulation device for real-time electromagnetic transient of a power system, the method comprising: obtaining first historical data and second historical data; obtaining real-time input data and inputting the real-time input data into a neural network model to obtain real-time output data; and determining the real-time output data as a simulation result of real-time electromagnetic transient of the power system. By introducing a neural network model, the first historical data and the second historical data of the original complex electromagnetic transient simulation model under different conditions are trained, so that the simplified neural network model can still accurately describe the key characteristics of the power system, without complicated parameter input and model debugging, and efficient prediction of real-time electromagnetic transient of the power system is realized. The problem of low simulation process efficiency of electromagnetic transient in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of power system simulation, and more specifically, to a method, simulation device, computer-readable storage medium, and electronic device for simulating real-time electromagnetic transients of a power system. Background Technology

[0002] During power system faults or operations, various changes occur in the internal operating parameters, and the operating state transitions from one state to another. Since these changes are not instantaneous, this transition is called the power system's transient process. Power system transient processes include electromagnetic transients and electromechanical transients. Electromagnetic transients are common in power systems, referring to changes in the electric and magnetic fields, as well as the corresponding voltage and current, within the system's components. These changes can occur due to lightning strikes, switching operations, short-circuit faults, etc.

[0003] Electromagnetic transient analysis is of great significance for the operation and design of power systems. Currently, the construction of electromagnetic transient simulation models mainly relies on specialized software such as EMTP and PSCAD. However, existing software requires cumbersome parameter input and model debugging when building real-time simulation models, resulting in a time-consuming and inefficient construction process.

[0004] Therefore, there is an urgent need for a method to solve the problem of low efficiency in the electromagnetic transient simulation process of power systems in existing technologies. Summary of the Invention

[0005] The main objective of this application is to provide a method, simulation device, computer-readable storage medium, and electronic device for simulating real-time electromagnetic transients of power systems, so as to at least solve the problem of low efficiency in the simulation process of electromagnetic transients of power systems in the prior art.

[0006] According to one aspect of this application, a method for simulating real-time electromagnetic transients of a power system is provided. The power system includes electrical equipment and electrical appliances. The method includes: acquiring first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical appliances at the historical time, wherein the historical time is a time prior to the current time; acquiring real-time input data and inputting the real-time input data into a neural network model to obtain real-time output data, wherein the neural network model is trained using the first historical data and the second historical data through machine learning, the real-time input data includes connection relationship data of the electrical equipment at the current time, electrical parameters of the electrical equipment at the current time, and operating status data of the electrical equipment at the current time, and the real-time output data is the electrical parameters of the electrical appliances at the current time; and determining the real-time output data as the simulation result of the real-time electromagnetic transients of the power system.

[0007] Optionally, when the power system is a new energy system, the electrical equipment includes generators, transformers, power lines, and circuit breakers. Acquiring first historical data includes: acquiring electrical parameters of the generators, transformers, power lines, and circuit breakers under different operating conditions at a historical time, wherein the operating conditions include the location of the new energy system, the ambient wind speed of the new energy system, and the electrical power generated by the new energy system, and the electrical parameters include at least the voltage signal, current signal, and frequency signal of the electrical equipment; acquiring operating status data of the generators, transformers, power lines, and circuit breakers under different operating conditions at a historical time, wherein the operating status data includes fault status data and working status data, the fault status data being data characterizing the electrical equipment in a fault state, and the working status data being data characterizing the electrical equipment in a working state; acquiring the connection relationships between the generators, transformers, power lines, and circuit breakers at a historical time, and generating the topology of the power system based on the connection relationships between the generators, transformers, power lines, and circuit breakers; and determining the topology of the power system as the connection relationship data of the electrical equipment at the historical time.

[0008] Optionally, the electrical equipment includes an interface transformer, and acquiring second historical data includes: acquiring voltage and current signals of the interface transformer under different operating conditions at the historical moment.

[0009] Optionally, after acquiring the first historical data and the second historical data, and before inputting the real-time input data into the neural network model, the method further includes at least one of the following: a first processing step, performing data cleaning processing on the first historical data and the second historical data to obtain the first historical data and the second historical data after data cleaning processing; a second processing step, performing unit conversion processing on the first historical data and the second historical data to obtain the first historical data and the second historical data after unit conversion processing; a third processing step, performing data format standardization processing on the first historical data and the second historical data to obtain the first historical data and the second historical data after standardization processing, wherein, when at least two of the first processing step, the second processing step, and the third processing step are included, the data processed in the next processing step is the data obtained after processing in the previous step.

[0010] Optionally, after acquiring the real-time input data and before inputting the real-time input data into the neural network model, the method further includes at least one of the following: during the training of the neural network model, using the OpenCL parallel computing framework to perform calculations on the neural network model; during the training of the neural network model, using a field-programmable gate array to accelerate the calculations on the neural network model.

[0011] Optionally, after acquiring the real-time input data and before inputting the real-time input data into the neural network model, the method further includes: adjusting the iteration step size of the neural network model until a predetermined condition is met, wherein the iteration step size is the magnitude of the iteration of the neural network model, and the predetermined condition includes at least one of the following: the number of iterations of the neural network model reaches a predetermined number and the accuracy of the neural network model reaches a predetermined accuracy.

[0012] Optionally, adjusting the iteration step size of the neural network model includes: increasing the iteration step size of the neural network model to improve the computation speed of the neural network model when the dispersion value of the first historical data is less than or equal to a predetermined value, wherein the dispersion value is used to characterize the dispersion of the first historical data; and decreasing the iteration step size of the neural network model to accelerate the convergence speed of the neural network model when the dispersion value of the first historical data is greater than the predetermined value.

[0013] Optionally, after determining that the real-time output data is the simulation result of the real-time electromagnetic transient of the power system, the method further includes: displaying the simulation result through at least one of charts, waveforms, and animations.

[0014] Optionally, after determining that the real-time output data is the simulation result of the real-time electromagnetic transient of the power system, the method further includes: in the event of a fault in the power system, adjusting the power system according to the simulation result of the real-time electromagnetic transient of the power system to eliminate the fault in the power system.

[0015] According to another aspect of this application, a simulation device for real-time electromagnetic transients of a power system is provided. The power system includes electrical equipment and electrical appliances. The device includes: an acquisition unit for acquiring first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical appliances at the historical time, wherein the historical time is a time prior to the current time; a processing unit for acquiring real-time input data and inputting the real-time input data into a neural network model to obtain real-time output data, wherein the neural network model is trained using the first historical data and the second historical data through machine learning, the real-time input data includes connection relationship data of the electrical equipment at the current time, electrical parameters of the electrical equipment at the current time, and operating status data of the electrical equipment at the current time, and the real-time output data is the electrical parameters of the electrical appliances at the current time; and a determination unit for determining the real-time output data as the simulation result of the real-time electromagnetic transients of the power system.

[0016] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0017] According to another aspect of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to perform any of the methods described by the computer program.

[0018] Applying the technical solution of this application, firstly, first historical data and second historical data are acquired; then, real-time input data is acquired and input into a neural network model to obtain real-time output data; finally, the real-time output data is determined as the simulation result of the real-time electromagnetic transients of the power system. By introducing a neural network model and training the original complex electromagnetic transient simulation model with first and second historical data under different conditions, the simplified neural network model can still accurately describe the key characteristics of the power system without the need for cumbersome parameter input and model debugging, thus achieving efficient prediction of the real-time electromagnetic transients of the power system. This solves the problem of low efficiency in the simulation process of electromagnetic transients of power systems in the prior art. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 A hardware block diagram of a mobile terminal for performing a simulation method for real-time electromagnetic transients of a power system, according to an embodiment of this application, is shown.

[0021] Figure 2 A flowchart illustrating a simulation method for real-time electromagnetic transients of a power system according to an embodiment of this application is shown.

[0022] Figure 3 A schematic flowchart of a real-time electromagnetic transient simulation method for a power system according to an embodiment of this application is shown.

[0023] Figure 4 A structural block diagram of a simulation device for real-time electromagnetic transients of a power system provided according to an embodiment of this application is shown.

[0024] The above figures include the following reference numerals:

[0025] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0027] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] As described in the background section, the simulation process of electromagnetic transients in power systems in the prior art is inefficient. To solve the above problems, embodiments of this application provide a method, simulation device, computer-readable storage medium, and electronic device for simulating real-time electromagnetic transients in power systems.

[0030] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0031] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a real-time electromagnetic transient simulation method for a power system according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0032] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the real-time electromagnetic transient simulation method of the power system in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] This embodiment provides a method for simulating the real-time electromagnetic transients of a power system running on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] Figure 2 This is a flowchart of a simulation method for real-time electromagnetic transients of a power system according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0035] Step S201: Obtain first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical equipment at the historical time, and the historical time is the time before the current time.

[0036] Specifically, the aforementioned first and second historical data can be obtained from the power system monitoring system or the power system data platform. The aforementioned connection relationship data can be the topology of the power system, the aforementioned electrical parameters can be the specific component parameters of each electrical device, the aforementioned operating status data can be data characterizing the electrical device in normal operating condition and data characterizing the electrical device in normal operating condition, and the aforementioned electrical equipment can be the interface transformer at the interface between the converter and the AC grid.

[0037] Step S202: Obtain real-time input data and input the real-time input data into the neural network model to obtain real-time output data. The neural network model is obtained by machine learning training using the first historical data and the second historical data. The real-time input data includes the connection relationship data of the electrical equipment at the current time, the electrical parameters of the electrical equipment at the current time, and the operating status data of the electrical equipment at the current time. The real-time output data is the electrical parameters of the electrical equipment at the current time.

[0038] Specifically, the real-time input data can be of the same type as the first historical data at a different time point. Therefore, after the neural network model learns the relationship between the first and second historical data, it can predict the corresponding real-time output data based on the real-time input data.

[0039] Step S203: Determine that the above real-time output data is the simulation result of the real-time electromagnetic transient of the above power system.

[0040] Specifically, the key information in the aforementioned real-time output data can serve as simulation results of the real-time electromagnetic transients of the power system. This helps users understand the evolution of the real-time electromagnetic transients of the power system, further providing strong support for the operation and design of the power system.

[0041] This embodiment first acquires first and second historical data; then, it acquires real-time input data and inputs it into a neural network model to obtain real-time output data; finally, it determines the real-time output data as the simulation result of the real-time electromagnetic transients of the power system. By introducing a neural network model and training the original complex electromagnetic transient simulation model with first and second historical data under different conditions, the simplified neural network model can still accurately describe the key characteristics of the power system without the need for cumbersome parameter input and model debugging, thus achieving efficient prediction of the real-time electromagnetic transients of the power system. This solves the problem of low efficiency in the simulation process of electromagnetic transients of power systems in existing technologies.

[0042] In specific implementation, step S201 can be achieved through the following steps: Step S2011, obtaining the electrical parameters of the generator, transformer, power line, and circuit breaker under different operating conditions at the historical time, wherein the operating conditions include the location of the new energy system, the ambient wind speed of the new energy system, and the electrical power generated by the new energy system, and the electrical parameters include at least the voltage signal, current signal, and frequency signal of the electrical equipment; Step S2012, obtaining the operating status data of the generator, transformer, power line, and circuit breaker under different operating conditions at the historical time, wherein... The aforementioned operational status data includes fault status data and operating status data. The fault status data represents the electrical equipment in a fault state, and the operating status data represents the electrical equipment in a working state. Step S2013 involves obtaining the connection relationships between the generator, transformer, power line, and circuit breaker at the aforementioned historical moment, and generating the topology of the power system based on these connections. Step S2014 involves determining the topology of the power system as the connection relationship data of the electrical equipment at the aforementioned historical moment. This method automatically extracts topology, component parameters, and operational status data from power system data, reducing the tedious work of manual input and model debugging, and further improving the efficiency of model construction.

[0043] Specifically, because the new power system has more flexible adaptive and regulatory capabilities, its structure is more complex, making it more suitable for the prediction process of the aforementioned neural network model. By inputting data from different operating conditions of the new power system into the neural network model for training, it can more accurately describe the key characteristics of the power system. These different operating conditions can include wind speed, regional location, power output, and fault conditions of the new energy system.

[0044] To further expedite the acquisition of the aforementioned second historical data, step S201 of this application can also be implemented through the following step: Step S2015, acquiring the voltage and current signals of the interface transformer under different operating conditions at the aforementioned historical moment. This method, by acquiring the current and voltage signals of the interface transformer under different operating conditions, can further prevent overfitting of the aforementioned neural network model.

[0045] Specifically, interface transformers are mainly used to connect power grids of different voltage levels. They effectively match voltages between different grids, enabling energy exchange between the two grids. Based on practical applications, they can be categorized as follows: Main transformer station interface transformers: connect the main transformer station and the auxiliary distribution network, used for the separation of transmission and distribution functions. High-voltage backbone network and medium-voltage distribution network interface transformers: connect high-voltage backbone networks above 35kV and medium- and low-voltage distribution networks below 10kV. Medium-voltage distribution network interface transformers: connect two different medium-voltage (e.g., 10kV and 20kV) distribution networks. Distribution network and user-side interface transformers: connect medium- and low-voltage distribution networks to user equipment, such as distributed generation.

[0046] The present application includes at least one of the following steps after step S201 and before step S202: step S301, a first processing step, performing data cleaning on the first historical data and the second historical data to obtain the first historical data and the second historical data after data cleaning; step S302, a second processing step, performing unit conversion on the first historical data and the second historical data to obtain the first historical data and the second historical data after unit conversion; step S303, a third processing step, performing data format standardization on the first historical data and the second historical data to obtain the first historical data and the second historical data after standardization, wherein, when at least two of the first, second, and third processing steps are included, the data processed in the next processing step is the data obtained after the previous step. This method can further improve the training speed and stability of the model.

[0047] Specifically, the purpose of the above data cleaning process is to remove irrelevant data. Due to the different acquisition devices of various equipment in the power system, the purpose of the above unit conversion process is to unify various physical quantities in the power system into the International System of Units (SI). The purpose of the above format standardization process is to convert the data into the standard format required by electromagnetic transient simulation software.

[0048] In specific implementation, step S202 can be achieved through at least one of the following steps: Step S2021, during the training of the neural network model, the OpenCL parallel computing framework is used to perform the computation of the neural network model; Step S2022, during the training of the neural network model, a field-programmable gate array (FPGA) is used to accelerate the computation of the neural network model. This method optimizes the model in software using OpenCL and in hardware using FPGA, further ensuring the accuracy and practicality of the real-time simulation results.

[0049] Specifically, traditional simulation models contain control loops, nonlinear loops, and delay loops, and the various parts of the model are coupled with each other, making it difficult to optimize the model's computation process. OpenCL (Open Computing Language) is an open standard for parallel programming that can run on various hardware devices such as CPUs, GPUs, and FPGAs. It can execute on different operating systems and hardware platforms and provides two parallel programming methods: queue model and work item model. Moreover, OpenCL emphasizes high optimization to improve the performance of computationally intensive applications. The above method, by adopting the OpenCL parallel computing framework, effectively distributes simulation tasks across various multi-core processors, playing a significant role in task partitioning, load balancing, and communication optimization. For example, OpenCL supports asynchronous execution and task scheduling, allowing the CPU to perform other tasks, such as model data preparation and simulation result collection, while the GPU is executing computational tasks, thereby improving the overall efficiency of the system. In addition to using general-purpose processors, we can also utilize dedicated hardware accelerators, such as FPGAs, to accelerate simulation. Field Programmable Gate Arrays (FPGAs) are a type of programmable semiconductor chip that can implement user-defined digital logic circuits. FPGAs possess characteristics such as programmability, reprogrammability, high performance, low power consumption, high parallelism, ease of customization, and ease of deployment. An FPGA mainly consists of programmable logic blocks that implement basic logic functions, input / output blocks that interact with the external world, embedded memory blocks that store configuration data and intermediate results, interconnects that connect different blocks, and a configuration memory for storing configuration bitstream data. Therefore, in general, FPGAs, through reprogrammability, enable the implementation of customized digital circuits and systems. For example, the above method can utilize a large number of FPGAs for the simulation of new energy power electronic devices.

[0050] Step 202 above can also be implemented through the following steps: Step S2023, adjust the iteration step size of the neural network model until a predetermined condition is met, wherein the iteration step size is the magnitude of the iteration of the neural network model, and the predetermined condition includes at least one of the following: the number of iterations of the neural network model reaches a predetermined number and the accuracy of the neural network model reaches a predetermined accuracy. This method, by adjusting the iteration step size, further and more quickly obtains the optimal simulation results.

[0051] Specifically, adjusting the iteration step size can accelerate or slow down the model's convergence speed, avoid oscillations or jumping out of the optimal solution region, and improve the model's accuracy and performance. If the iteration step size is large, the learning speed may be fast, but it may ignore the effective solution space and eventually fail to converge. If the iteration step size is too small, the learning speed is slow, but it can find the optimal solution more accurately. A reasonable update step size can find a balance between the two, allowing the model to converge to a higher accuracy faster. Methods for adjusting the iteration step size include: fixed rate decreasing method, which refers to multiplying the iteration step size by a coefficient less than 1 after each iteration, so that the iteration step size gradually decreases; exponential decreasing method, which refers to the iteration step size decreasing exponentially with the number of iterations; dynamic adjustment method, which refers to dynamically adjusting the step size according to the changes in the model's loss function; and batch training with initial value method, which refers to initializing the iteration step size to a large value in batch training and gradually decreasing it with supervised training.

[0052] In some embodiments, step S2023 can be implemented through the following steps: Step S20231, when the dispersion value of the first historical data is less than or equal to a predetermined value, increasing the iteration step size of the neural network model to improve the computation speed of the neural network model, wherein the dispersion value is used to characterize the dispersion of the first historical data; Step S20232, when the dispersion value of the first historical data is greater than the predetermined value, decreasing the iteration step size of the neural network model to accelerate the convergence speed of the neural network model. This method further ensures the accuracy and practicality of real-time simulation results by optimizing the model.

[0053] Specifically, increasing the iteration step size can accelerate model convergence. During model training, the weight parameters need to be continuously updated to improve model performance. This requires many iterations. In each iteration, the model updates with a certain step size based on the direction of gradient descent. Increasing the iteration step size provides maximum update space within permissible limits, allowing the model to approach ideal parameters as quickly as possible and saving time costs in later iterations. For example, in a simulated power grid model, when the generator output variation is small, the model can be optimized by increasing the simulation step size, thereby accelerating the simulation. On the other hand, decreasing the iteration step size can improve accuracy. Smaller changes to weights improve final accuracy, prevent model divergence, accelerate convergence, and improve stability. For example, in a simulated power grid model, when the generator output variation is too large, the model can be optimized by decreasing the simulation step size, thereby improving model accuracy.

[0054] In some embodiments, step S204 is included after step S203, displaying the simulation results through at least one of graphs, waveforms, and animations. This method analyzes real-time simulation results, extracts key information, and presents it to the user in the form of graphs, waveforms, or animations. This helps users understand more intuitively the occurrence, evolution, and impact of electromagnetic transient phenomena, further providing strong support for the operation and design of power systems.

[0055] Specifically, based on the above methods, a user-friendly graphical interface can be developed to facilitate the rapid and accurate construction of real-time electromagnetic transient simulation models of power systems. Users can intuitively input basic information, topology, and equipment parameters of the power system. This graphical interface supports drag-and-drop operations, allowing users to easily organize and adjust various elements of the power system. Furthermore, the graphical interface can provide a pre-set library of component models for users to directly select and use. The graphical interface integrates simulation result visualization capabilities, allowing users to view simulation results at different angles and scales through interactive operations (such as zooming, panning, and rotating), gaining a deeper understanding of the details of electromagnetic transient phenomena. Additionally, through the graphical interface, users can easily import existing real-time electromagnetic transient simulation models of power systems for modification, optimization, and simulation. Simultaneously, users can export the constructed simulation models to common formats (such as CIM and PSCAD) for interaction with other simulation software or tools.

[0056] In some embodiments, step S205 is included after step S203, in which, in the event of a power system failure, the power system is adjusted based on the simulation results of the real-time electromagnetic transients to eliminate the power system failure. This method can further provide effective technical support for the design, optimization, and operation and maintenance of power systems.

[0057] Specifically, a digital twin system can be used to create a digital copy of the power system, obtaining more data results than reality, providing efficient decision support, and enabling online real-time monitoring of actual data, allowing for adjustments when deviations occur. Adjusting the power system based on electromagnetic transient simulation results mainly includes the following aspects: First, based on voltage and current analysis results, determine whether the load distribution is reasonable and balanced, and adjust the load distribution accordingly. If some lines are heavily loaded, the load distribution can be optimized; for example, load dispatching can be prioritized for users near high-load lines to reduce peak loads, the load curves of certain users can be optimized to reduce peak-period loads, and some load can be added to key lines. Second, if simulation results show that the voltage of some lines is low or the current is too high, consider improving the line topology, adding branch lines and distribution transformers to alleviate the main line load, or adding new lines to divert some load. Third, based on the transformer input and output currents and load conditions, determine whether the capacity is sufficient and adjust the transformer capacity accordingly. If the load is close to saturation, new transformers can be added to share some load, or smaller capacity transformers can be replaced. Fourth, if simulation results show that the voltage and current of some switches exceed the limits, the connection sequence of the switches can be optimized to improve circulation. Fifth, optimize the system's lightning protection, instantaneous overvoltage protection, and lightning protection based on voltage transient fluctuations and over-limit conditions.

[0058] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the real-time electromagnetic transient simulation method for power systems of this application will be described in detail below with reference to specific embodiments.

[0059] This embodiment relates to a specific simulation method for real-time electromagnetic transients in a power system, such as... Figure 3 As shown, it includes the following steps:

[0060] Step S1: Analyze the power system to be simulated and obtain historical data of the power system;

[0061] Step S2: Create the basic topology of the power system and obtain the topology of the power system;

[0062] Step S3: Configure detailed parameters for the device;

[0063] Step S4: Integrate a custom device model and operate it automatically using computer and artificial intelligence methods;

[0064] Step S5: Add control strategies and protection settings. Pre-set control and protection strategies for potential problems in the power system.

[0065] Step S6: Set electromagnetic transient simulation parameters. Based on user needs or the actual operation of the system, set real-time simulation parameters such as simulation time step, simulation duration, and output variables.

[0066] Step S7: Run real-time simulation. Use the constructed and optimized electromagnetic transient model to perform real-time simulation calculations to simulate electromagnetic transient phenomena in the power system.

[0067] Step S8: Visual analysis of simulation results. Analyze the real-time simulation results, extract key information, and present it to the user in the form of charts, waveforms, or animations.

[0068] This application also provides a simulation device for real-time electromagnetic transients of a power system. It should be noted that this simulation device can be used to execute the simulation method for real-time electromagnetic transients of a power system provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0069] The following describes the simulation device for real-time electromagnetic transients of a power system provided in the embodiments of this application.

[0070] Figure 4 This is a schematic diagram of a simulation device for real-time electromagnetic transients of a power system according to an embodiment of this application. Figure 4 As shown, the device includes:

[0071] The acquisition unit 10 is used to acquire first historical data and second historical data. The first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time. The second historical data includes electrical parameters of the electrical equipment at the historical time. The historical time is the time before the current time.

[0072] Specifically, the aforementioned first and second historical data can be obtained from the power system monitoring system or the power system data platform. The aforementioned connection relationship data can be the topology of the power system, the aforementioned electrical parameters can be the specific component parameters of each electrical device, the aforementioned operating status data can be data characterizing the electrical device in normal operating condition and data characterizing the electrical device in normal operating condition, and the aforementioned electrical equipment can be the interface transformer at the interface between the converter and the AC grid.

[0073] The processing unit 20 is used to acquire real-time input data and input the real-time input data into a neural network model to obtain real-time output data. The neural network model is obtained by machine learning training using the first historical data and the second historical data. The real-time input data includes the connection relationship data of the electrical equipment at the current time, the electrical parameters of the electrical equipment at the current time, and the operating status data of the electrical equipment at the current time. The real-time output data is the electrical parameters of the electrical equipment at the current time.

[0074] Specifically, the real-time input data can be of the same type as the first historical data at a different time point. Therefore, after the neural network model learns the relationship between the first and second historical data, it can predict the corresponding real-time output data based on the real-time input data.

[0075] The determination unit 30 is used to determine that the above real-time output data is the simulation result of the real-time electromagnetic transient of the above power system.

[0076] Specifically, the key information in the aforementioned real-time output data can serve as simulation results of the real-time electromagnetic transients of the power system. This helps users understand the evolution of the real-time electromagnetic transients of the power system, further providing strong support for the operation and design of the power system.

[0077] In this embodiment, the acquisition unit acquires first and second historical data; the processing unit acquires real-time input data and inputs it into the neural network model to obtain real-time output data; the determination unit determines the real-time output data as the simulation result of the real-time electromagnetic transients of the power system. By introducing a neural network model and training the original complex electromagnetic transient simulation model with first and second historical data under different conditions, the simplified neural network model can still accurately describe the key characteristics of the power system without the need for cumbersome parameter input and model debugging, thus achieving efficient prediction of the real-time electromagnetic transients of the power system. This solves the problem of low efficiency in the simulation process of electromagnetic transients of power systems in the prior art.

[0078] In specific implementation, the aforementioned acquisition unit includes a first acquisition module, a second acquisition module, a third acquisition module, and a first determination module. The first acquisition module acquires the electrical parameters of the generator, transformer, power line, and circuit breaker under different operating conditions at the aforementioned historical time. These operating conditions include the location of the renewable energy system, the ambient wind speed of the renewable energy system, and the electrical power generated by the renewable energy system. The electrical parameters include at least the voltage signal, current signal, and frequency signal of the electrical equipment. The second acquisition module acquires the different operating conditions of the generator, transformer, power line, and circuit breaker at the aforementioned historical time. The device extracts operational status data, including fault status data and operating status data. The fault status data represents the electrical equipment in a fault state, and the operating status data represents the electrical equipment in a working state. A third acquisition module acquires the connection relationships between the generator, transformer, power line, and circuit breaker at a historical moment, and generates the power system topology based on these connections. A first determination module determines the power system topology as the connection relationship data of the electrical equipment at the historical moment. This device automatically extracts topology, component parameters, and operational status data from power system data, reducing the tedious work of manual input and model debugging, and further improving the efficiency of model building.

[0079] Specifically, because the new power system has more flexible adaptive and regulatory capabilities, its structure is more complex, making it more suitable for the prediction process of the aforementioned neural network model. By inputting data from different operating conditions of the new power system into the neural network model for training, it can more accurately describe the key characteristics of the power system. These different operating conditions can include wind speed, regional location, power output, and fault conditions of the new energy system.

[0080] To further expedite the acquisition of the aforementioned second historical data, the acquisition unit of this application further includes a fourth acquisition unit, used to acquire the voltage and current signals of the interface transformer under different operating conditions at the aforementioned historical time. By acquiring the current and voltage signals of the interface transformer under different operating conditions, this device can further prevent the aforementioned neural network model from overfitting.

[0081] Specifically, interface transformers are mainly used to connect power grids of different voltage levels. They effectively match voltages between different grids, enabling energy exchange between the two grids. Based on practical applications, they can be categorized as follows: Main transformer station interface transformers: connect the main transformer station and the auxiliary distribution network, used for the separation of transmission and distribution functions. High-voltage backbone network and medium-voltage distribution network interface transformers: connect high-voltage backbone networks above 35kV and medium- and low-voltage distribution networks below 10kV. Medium-voltage distribution network interface transformers: connect two different medium-voltage (e.g., 10kV and 20kV) distribution networks. Distribution network and user-side interface transformers: connect medium- and low-voltage distribution networks to user equipment, such as distributed generation.

[0082] This application also includes a first processing unit, a second processing unit, and a third processing unit. The first processing unit performs a first processing step, cleaning the first historical data and the second historical data to obtain cleaned first historical data and cleaned second historical data. The second processing unit performs a second processing step, converting the first historical data and the second historical data to obtain converted first historical data and converted second historical data. The third processing unit performs a third processing step, standardizing the first historical data and the second historical data to obtain standardized first historical data and standardized second historical data. Where at least two of the first, second, and third processing steps are included, the data processed in the next processing step is the data obtained in the previous step. This device can further improve the training speed and stability of the model.

[0083] Specifically, the purpose of the above data cleaning process is to remove irrelevant data. Due to the different acquisition devices of various equipment in the power system, the purpose of the above unit conversion process is to unify various physical quantities in the power system into the International System of Units (SI). The purpose of the above format standardization process is to convert the data into the standard format required by electromagnetic transient simulation software.

[0084] In its specific implementation, the aforementioned processing unit includes at least one of a first processing module and a second processing module: the first processing module is used to perform computations on the neural network model using the OpenCL parallel computing framework during the training process; the second processing module is used to accelerate the computations of the neural network model using a field-programmable gate array (FPGA) during the training process. This device optimizes the model in software using OpenCL and in hardware using an FPGA, further ensuring the accuracy and practicality of the real-time simulation results.

[0085] Specifically, traditional simulation models contain control loops, nonlinear loops, and delay loops, and the various parts of the model are coupled with each other, making it difficult to optimize the model's computation process. OpenCL (Open Computing Language) is an open standard for parallel programming that can run on various hardware devices such as CPUs, GPUs, and FPGAs. It can execute on different operating systems and hardware platforms and provides two parallel programming methods: queue model and work item model. Moreover, OpenCL emphasizes high optimization to improve the performance of computationally intensive applications. The aforementioned device, by adopting the OpenCL parallel computing framework, effectively distributes simulation tasks across various multi-core processors, playing a significant role in task partitioning, load balancing, and communication optimization. For example, OpenCL supports asynchronous execution and task scheduling, allowing the CPU to perform other tasks, such as model data preparation and simulation result collection, while the GPU is executing computational tasks, thereby improving the overall efficiency of the system. In addition to using general-purpose processors, we can also utilize dedicated hardware accelerators, such as FPGAs, to accelerate simulation. Field Programmable Gate Arrays (FPGAs) are a type of programmable semiconductor chip that can implement user-defined digital logic circuits. FPGAs possess characteristics such as programmability, reprogrammability, high performance, low power consumption, high parallelism, ease of customization, and ease of deployment. An FPGA mainly consists of programmable logic blocks that implement basic logic functions, input / output blocks that interact with the external world, embedded memory blocks that store configuration data and intermediate results, interconnects that connect different blocks, and configuration memory for storing configuration bitstream data. Therefore, in general, FPGAs, through reprogrammability, enable the creation of customized digital circuits and systems. For example, in the aforementioned device, a large number of FPGAs can be used for the simulation of new energy power electronic devices.

[0086] The processing unit further includes an adjustment module for adjusting the iteration step size of the neural network model until a predetermined condition is met. The iteration step size is the magnitude of iterations performed by the neural network model, and the predetermined condition includes at least one of the following: the number of iterations of the neural network model reaches a predetermined number, and the accuracy of the neural network model reaches a predetermined accuracy. By adjusting the iteration step size, this device can further and more quickly obtain optimal simulation results.

[0087] Specifically, adjusting the iteration step size can accelerate or slow down the model's convergence speed, avoid oscillations or jumping out of the optimal solution region, and improve the model's accuracy and performance. If the iteration step size is large, the learning speed may be fast, but it may ignore the effective solution space and eventually fail to converge. If the iteration step size is too small, the learning speed is slow, but it can find the optimal solution more accurately. A reasonable update step size can find a balance between the two, allowing the model to converge to a higher accuracy faster. Methods for adjusting the iteration step size include: fixed-rate decreasing method, which refers to multiplying the iteration step size by a coefficient less than 1 after each iteration, causing the iteration step size to gradually decrease; exponential decreasing method, which refers to the iteration step size decreasing exponentially with the number of iterations; dynamic adjustment method, which refers to dynamically adjusting the step size based on changes in the model's loss function; and batch training with initial value method, which refers to initializing the iteration step size to a large value during batch training and gradually decreasing it during supervised training.

[0088] In some embodiments, the adjustment module includes an addition submodule and a reduction submodule. The adjustment submodule increases the iteration step size of the neural network model when the dispersion value of the first historical data is less than or equal to a predetermined value, thereby improving the computational speed of the neural network model. The dispersion value characterizes the dispersion of the first historical data. The reduction submodule decreases the iteration step size of the neural network model when the dispersion value of the first historical data is greater than the predetermined value, thereby accelerating the convergence speed of the neural network model. This device further ensures the accuracy and practicality of real-time simulation results by optimizing the model.

[0089] Specifically, increasing the iteration step size can accelerate model convergence. During model training, the weight parameters need to be continuously updated to improve model performance. This requires many iterations. In each iteration, the model updates with a certain step size based on the direction of gradient descent. Increasing the iteration step size provides maximum update space within permissible limits, allowing the model to approach ideal parameters as quickly as possible and saving time costs in later iterations. For example, in a simulated power grid model, when the generator output variation is small, the model can be optimized by increasing the simulation step size, thereby accelerating the simulation. On the other hand, decreasing the iteration step size can improve accuracy. Smaller changes to weights improve final accuracy, prevent model divergence, accelerate convergence, and improve stability. For example, in a simulated power grid model, when the generator output variation is too large, the model can be optimized by decreasing the simulation step size, thereby improving model accuracy.

[0090] In some embodiments, the device further includes a display unit for displaying the simulation results through at least one of graphs, waveforms, and animations. The device analyzes real-time simulation results, extracts key information, and presents it to the user in the form of graphs, waveforms, or animations. This helps users understand more intuitively the occurrence, evolution, and impact of electromagnetic transient phenomena, further providing strong support for the operation and design of power systems.

[0091] Specifically, based on the aforementioned device, a user-friendly graphical interface can be developed to facilitate the rapid and accurate construction of real-time electromagnetic transient simulation models of power systems. Users can intuitively input basic information, topology, and equipment parameters of the power system. This graphical interface supports drag-and-drop operations, allowing users to easily organize and adjust various elements of the power system. Furthermore, the graphical interface can provide a pre-set library of component models for direct selection and use. The graphical interface integrates simulation result visualization, allowing users to view simulation results at different angles and scales through interactive operations (such as zooming, panning, and rotating), gaining a deeper understanding of the details of electromagnetic transient phenomena. Additionally, through the graphical interface, users can easily import existing real-time electromagnetic transient simulation models of power systems for modification, optimization, and simulation. Simultaneously, users can export the constructed simulation models to common formats (such as CIM and PSCAD) for interaction with other simulation software or tools.

[0092] In some embodiments, the device further includes an adjustment unit for adjusting the power system based on the simulation results of the real-time electromagnetic transients of the power system in the event of a power system failure, thereby eliminating the power system failure. This device can further provide effective technical support for the design, optimization, and operation and maintenance of power systems.

[0093] Specifically, a digital twin system can be used to create a digital copy of the power system, obtaining more data results than reality, providing efficient decision support, and enabling online real-time monitoring of actual data, allowing for adjustments when deviations occur. Adjusting the power system based on electromagnetic transient simulation results mainly includes the following aspects: First, based on voltage and current analysis results, determine whether the load distribution is reasonable and balanced, and adjust the load distribution accordingly. If some lines are heavily loaded, the load distribution can be optimized; for example, load dispatching can be prioritized for users near high-load lines to reduce peak loads, the load curves of certain users can be optimized to reduce peak-period loads, and some load can be added to key lines. Second, if simulation results show that the voltage of some lines is low or the current is too high, consider improving the line topology, adding branch lines and distribution transformers to alleviate the main line load, or adding new lines to divert some load. Third, based on the transformer input and output currents and load conditions, determine whether the capacity is sufficient and adjust the transformer capacity accordingly. If the load is close to saturation, new transformers can be added to share some load, or smaller capacity transformers can be replaced. Fourth, if simulation results show that the voltage and current of some switches exceed the limits, the connection sequence of the switches can be optimized to improve circulation. Fifth, optimize the system's lightning protection, instantaneous overvoltage protection, and lightning protection based on voltage transient fluctuations and over-limit conditions.

[0094] The aforementioned simulation device for real-time electromagnetic transients of the power system includes a processor and a memory. The acquisition unit, processing unit, and determination unit are all stored as program units in the memory, and the processor executes these program units to achieve the corresponding functions. All of the above modules reside in the same processor; alternatively, the modules may be located in different processors in any combination.

[0095] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and real-time electromagnetic transient simulation of power systems can be performed by adjusting kernel parameters.

[0096] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0097] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform a simulation method for real-time electromagnetic transients of the power system.

[0098] Specifically, simulation methods for real-time electromagnetic transients in power systems include:

[0099] Step S201: Obtain first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical equipment at the historical time, and the historical time is the time before the current time.

[0100] Specifically, the aforementioned first and second historical data can be obtained from the power system monitoring system or the power system data platform. The aforementioned connection relationship data can be the topology of the power system, the aforementioned electrical parameters can be the specific component parameters of each electrical device, the aforementioned operating status data can be data characterizing the electrical device in normal operating condition and data characterizing the electrical device in normal operating condition, and the aforementioned electrical equipment can be the interface transformer at the interface between the converter and the AC grid.

[0101] Step S202: Obtain real-time input data and input the real-time input data into the neural network model to obtain real-time output data. The neural network model is obtained by machine learning training using the first historical data and the second historical data. The real-time input data includes the connection relationship data of the electrical equipment at the current time, the electrical parameters of the electrical equipment at the current time, and the operating status data of the electrical equipment at the current time. The real-time output data is the electrical parameters of the electrical equipment at the current time.

[0102] Specifically, the real-time input data can be of the same type as the first historical data at a different time point. Therefore, after the neural network model learns the relationship between the first and second historical data, it can predict the corresponding real-time output data based on the real-time input data.

[0103] Step S203: Determine that the above real-time output data is the simulation result of the real-time electromagnetic transient of the above power system.

[0104] Specifically, the key information in the aforementioned real-time output data can serve as simulation results of the real-time electromagnetic transients of the power system. This helps users understand the evolution of the real-time electromagnetic transients of the power system, further providing strong support for the operation and design of the power system.

[0105] This invention provides a processor for running a program, wherein the program executes a simulation method for real-time electromagnetic transients of a power system.

[0106] Specifically, simulation methods for real-time electromagnetic transients in power systems include:

[0107] Step S201: Obtain first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical equipment at the historical time, and the historical time is the time before the current time.

[0108] Specifically, the aforementioned first and second historical data can be obtained from the power system monitoring system or the power system data platform. The aforementioned connection relationship data can be the topology of the power system, the aforementioned electrical parameters can be the specific component parameters of each electrical device, the aforementioned operating status data can be data characterizing the electrical device in normal operating condition and data characterizing the electrical device in normal operating condition, and the aforementioned electrical equipment can be the interface transformer at the interface between the converter and the AC grid.

[0109] Step S202: Obtain real-time input data and input the real-time input data into the neural network model to obtain real-time output data. The neural network model is obtained by machine learning training using the first historical data and the second historical data. The real-time input data includes the connection relationship data of the electrical equipment at the current time, the electrical parameters of the electrical equipment at the current time, and the operating status data of the electrical equipment at the current time. The real-time output data is the electrical parameters of the electrical equipment at the current time.

[0110] Specifically, the real-time input data can be of the same type as the first historical data at a different time point. Therefore, after the neural network model learns the relationship between the first and second historical data, it can predict the corresponding real-time output data based on the real-time input data.

[0111] Step S203: Determine that the above real-time output data is the simulation result of the real-time electromagnetic transient of the above power system.

[0112] Specifically, the key information in the aforementioned real-time output data can serve as simulation results of the real-time electromagnetic transients of the power system. This helps users understand the evolution of the real-time electromagnetic transients of the power system, further providing strong support for the operation and design of the power system.

[0113] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0114] Step S201: Obtain first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical equipment at the historical time, and the historical time is the time before the current time.

[0115] Step S202: Obtain real-time input data and input the real-time input data into the neural network model to obtain real-time output data. The neural network model is obtained by machine learning training using the first historical data and the second historical data. The real-time input data includes the connection relationship data of the electrical equipment at the current time, the electrical parameters of the electrical equipment at the current time, and the operating status data of the electrical equipment at the current time. The real-time output data is the electrical parameters of the electrical equipment at the current time.

[0116] Step S203: Determine that the above real-time output data is the simulation result of the real-time electromagnetic transient of the above power system.

[0117] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0118] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0119] Step S201: Obtain first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical equipment at the historical time, and the historical time is the time before the current time.

[0120] Step S202: Obtain real-time input data and input the real-time input data into the neural network model to obtain real-time output data. The neural network model is obtained by machine learning training using the first historical data and the second historical data. The real-time input data includes the connection relationship data of the electrical equipment at the current time, the electrical parameters of the electrical equipment at the current time, and the operating status data of the electrical equipment at the current time. The real-time output data is the electrical parameters of the electrical equipment at the current time.

[0121] Step S203: Determine that the above real-time output data is the simulation result of the real-time electromagnetic transient of the above power system.

[0122] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0123] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0124] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0125] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0126] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0127] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0128] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0129] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0130] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0131] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0132] 1) The real-time electromagnetic transient simulation method for power systems disclosed in this application first acquires first and second historical data; then, it acquires real-time input data and inputs it into a neural network model to obtain real-time output data; finally, it determines the real-time output data as the simulation result of the real-time electromagnetic transients of the power system. By introducing a neural network model and training the original complex electromagnetic transient simulation model with first and second historical data under different conditions, the simplified neural network model can still accurately describe the key characteristics of the power system without the need for cumbersome parameter input and model debugging, thus achieving efficient prediction of real-time electromagnetic transients of the power system. This solves the problem of low efficiency in the simulation process of electromagnetic transients of power systems in existing technologies.

[0133] 2) The real-time electromagnetic transient simulation device for power systems disclosed in this application comprises: an acquisition unit acquiring first and second historical data; a processing unit acquiring real-time input data and inputting it into a neural network model to obtain real-time output data; and a determination unit determining the real-time output data as the simulation result of the real-time electromagnetic transients of the power system. By introducing a neural network model and training the original complex electromagnetic transient simulation model with first and second historical data under different conditions, the simplified neural network model can still accurately describe the key characteristics of the power system without the need for cumbersome parameter input and model debugging, thus achieving efficient prediction of real-time electromagnetic transients of the power system. This solves the problem of low efficiency in the simulation process of electromagnetic transients of power systems in the prior art.

[0134] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for simulating real-time electromagnetic transients in a power system, characterized in that, The power system includes electrical equipment and electrical appliances, wherein the method includes: Acquire first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical equipment at the historical time, wherein the historical time is a time before the current time; Real-time input data is acquired and input into a neural network model to obtain real-time output data. The neural network model is trained using the first historical data and the second historical data through machine learning. The real-time input data includes the connection relationship data of the electrical equipment at the current time, the electrical parameters of the electrical equipment at the current time, and the operating status data of the electrical equipment at the current time. The real-time output data is the electrical parameters of the electrical equipment at the current time. The real-time output data is determined to be the simulation result of the real-time electromagnetic transients of the power system; When the power system is a new energy system, the electrical equipment includes generators, transformers, power lines, and circuit breakers. Acquiring first historical data includes: acquiring electrical parameters of the generators, transformers, power lines, and circuit breakers under different operating conditions at a historical time, wherein the operating conditions include the location of the new energy system, the ambient wind speed of the new energy system, and the electrical power generated by the new energy system, and the electrical parameters include at least the voltage signal, current signal, and frequency signal of the electrical equipment; acquiring operating status data of the generators, transformers, power lines, and circuit breakers under different operating conditions at a historical time, wherein the operating status data includes fault status data and working status data, the fault status data being data characterizing the electrical equipment in a fault state, and the working status data being data characterizing the electrical equipment in a working state; acquiring the connection relationships between the generators, transformers, power lines, and circuit breakers at a historical time, and generating the topology of the power system based on the connection relationships between the generators, transformers, power lines, and circuit breakers; and determining the topology of the power system as the connection relationship data of the electrical equipment at the historical time.

2. The method according to claim 1, characterized in that, The electrical equipment includes an interface transformer, and the acquisition of second historical data includes: The voltage and current signals of the interface transformer under different operating conditions at the historical moment are obtained.

3. The method according to claim 1, characterized in that, After acquiring the first historical data and the second historical data, and before inputting the real-time input data into the neural network model, the method further includes at least one of the following: The first processing step involves cleaning the first historical data and the second historical data to obtain the first historical data and the second historical data after data cleaning. The second processing step is to perform unit conversion processing on the first historical data and the second historical data to obtain the first historical data and the second historical data after unit conversion processing. The third processing step involves standardizing the data format of the first historical data and the second historical data to obtain standardized first historical data and standardized second historical data. In cases where at least two of the first, second, and third processing steps are included, the data processed in the next processing step is the data obtained after the previous step.

4. The method according to claim 1, characterized in that, After acquiring the real-time input data and before inputting the real-time input data into the neural network model, the method further includes at least one of the following: During the training of the neural network model, the OpenCL parallel computing framework is used to perform calculations on the neural network model. During the training of the neural network model, a field-programmable gate array (FPGA) is used to accelerate the computation of the neural network model.

5. The method according to claim 1, characterized in that, After acquiring the real-time input data and before inputting the real-time input data into the neural network model, the method further includes: The iteration step size of the neural network model is adjusted until a predetermined condition is met, wherein the iteration step size is the magnitude of the iteration of the neural network model, and the predetermined condition includes at least one of the following: the number of iterations of the neural network model reaches a predetermined number and the accuracy of the neural network model reaches a predetermined accuracy.

6. The method according to claim 5, characterized in that, Adjusting the iteration step size of the neural network model includes: If the dispersion value of the first historical data is less than or equal to a predetermined value, the iteration step size of the neural network model is increased to improve the computation speed of the neural network model, wherein the dispersion value is used to characterize the dispersion of the first historical data. If the dispersion value of the first historical data is greater than the predetermined value, the iteration step size of the neural network model is reduced to accelerate the convergence speed of the neural network model.

7. The method according to claim 1, characterized in that, After determining that the real-time output data is the simulation result of the real-time electromagnetic transients of the power system, the method further includes: The simulation results are displayed using at least one of the following: charts, waveforms, and animations.

8. The method according to claim 1, characterized in that, After determining that the real-time output data is the simulation result of the real-time electromagnetic transients of the power system, the method further includes: In the event of a power system failure, the power system is adjusted based on the simulation results of the real-time electromagnetic transients to eliminate the failure.

9. A simulation device for real-time electromagnetic transients of a power system, characterized in that, The power system includes electrical equipment and electrical appliances, wherein the device includes: The acquisition unit is used to acquire first historical data and second historical data, wherein the first historical data includes connection relationship data of the electrical equipment at a historical time, electrical parameters of the electrical equipment at the historical time, and operating status data of the electrical equipment at the historical time, and the second historical data includes electrical parameters of the electrical equipment at the historical time, wherein the historical time is a time before the current time; A processing unit is configured to acquire real-time input data and input the real-time input data into a neural network model to obtain real-time output data. The neural network model is trained using the first historical data and the second historical data through machine learning. The real-time input data includes the connection relationship data of the electrical equipment at the current time, the electrical parameters of the electrical equipment at the current time, and the operating status data of the electrical equipment at the current time. The real-time output data is the electrical parameters of the electrical equipment at the current time. A determining unit is used to determine that the real-time output data is the simulation result of the real-time electromagnetic transients of the power system; In the case where the power system is a new energy system, the electrical equipment includes generators, transformers, power lines, and circuit breakers. The acquisition unit includes a first acquisition module, a second acquisition module, a third acquisition module, and a first determination module. The first acquisition module is used to acquire the electrical parameters of the generator, the transformer, the power line, and the circuit breaker under different operating conditions at a historical time. The operating conditions include the location of the new energy system, the ambient wind speed of the new energy system, and the electrical power generated by the new energy system. The electrical parameters include at least the voltage signal, current signal, and frequency signal of the electrical equipment. The second acquisition module is used to acquire the electrical parameters of the generator, the transformer, the power line, and the circuit breaker under different operating conditions at a historical time. The circuit breaker's operating status data under different operating conditions at a historical time includes fault status data and working status data. The fault status data represents the electrical equipment in a fault state, and the working status data represents the electrical equipment in a working state. The third acquisition module is used to acquire the connection relationship between the generator, the transformer, the power line, and the circuit breaker at a historical time, and generate the topology of the power system based on the connection relationship between the generator, the transformer, the power line, and the circuit breaker. The first determination module is used to determine the topology of the power system as the connection relationship data of the electrical equipment at a historical time.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 8.

11. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 8 through the computer program.

Images