Frequency modulation damping cooperative control circuit, method, device and medium for power distribution network

Abstract

This invention relates to a frequency regulation damping coordinated control circuit, method, device, and medium for distribution networks, belonging to the field of smart grid technology. The circuit includes: an improved state observation module integrating a neural network for acquiring information related to the distribution network system state and total disturbance; an adaptive compensation module connected to the improved state observation module for adjusting the output results of disturbance-related information; a state feedback control module connected to the improved state observation module for generating control signals based on system state information; and a smart terminal interface module connected to a smart energy meter, a smart fusion terminal, the state feedback control module, and the improved state observation module. The control circuit achieves seamless compatibility with smart energy meters and smart fusion terminals without requiring additional hardware modifications. The improved state observation module integrating a neural network improves the accuracy of distribution network system state perception and disturbance estimation.

Description

Technical Field

[0001] This invention relates to the field of smart grid technology, and in particular to a frequency regulation damping coordinated control circuit, method, device, and medium for distribution networks. Background Technology

[0002] As the penetration rate of distributed energy sources such as photovoltaics and wind power in the distribution network continues to increase, the large-scale access of power electronic equipment and the enhanced load volatility lead to the deterioration of the damping characteristics of the distribution network, the decline in frequency regulation capability, and the superposition and spread of low-frequency oscillation and frequency fluctuation problems, which can easily cause problems such as power swing, voltage collapse, frequency over-limit or protection malfunction. Summary of the Invention

[0003] This invention provides a frequency regulation and damping coordinated control method for distribution networks to solve the problems that existing distribution network control methods are difficult to adapt to scenarios with a high proportion of distributed energy access, and that conventional control technologies suffer from slow response, poor adaptability, and inaccurate disturbance estimation under the resource constraints of smart terminals.

[0004] In a first aspect, the present invention provides a frequency regulation damping coordinated control circuit for a power distribution network, comprising:

[0005] An improved state observation module, integrating a neural network, is used to acquire information related to the state and total disturbance of the distribution network system;

[0006] An adaptive compensation module, connected to the improved state observation module, is used to adjust the output results of disturbance-related information;

[0007] A state feedback control module, connected to the improved state observation module, is used to generate control signals based on system state information;

[0008] The intelligent terminal interface module connects to the smart energy meter, the smart fusion terminal, the status feedback control module, and the improved status observation module, respectively.

[0009] Secondly, the present invention provides a frequency regulation damping coordinated control method for a power distribution network, the method comprising:

[0010] S1, the system status information and total disturbance information are obtained by processing the operating data through an improved state observation module integrating a neural network, and the total disturbance information is processed by an adaptive compensation module; the operating data is obtained by collecting data from the distribution network by smart energy meters or smart fusion terminals;

[0011] S2, Based on the system status information and the processed total disturbance information, a control command is generated and transmitted to the intelligent fusion terminal for execution.

[0012] Thirdly, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0013] Memory, used to store computer programs;

[0014] When a processor executes a program stored in a memory, it implements the steps of the frequency regulation damping coordinated control method for a power distribution network as described in any embodiment of the first aspect.

[0015] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the frequency regulation damping coordinated control method for a distribution network as described in any embodiment of the first aspect.

[0016] The technical solutions provided in the embodiments of the present invention have the following advantages compared with the prior art:

[0017] By integrating an improved state observation module with a neural network and an adaptive compensation module, the accuracy of state perception and disturbance estimation in the distribution network system is significantly improved. The seamless compatibility of the control circuit with smart meters and smart fusion terminals achieves a "plug-and-play" deployment effect without the need for additional hardware modifications.

[0018] With a concise core process and periodic execution mechanism, it balances real-time control with resource efficiency, achieving a control cycle of 10-20ms and enabling rapid response to frequency fluctuations and low-frequency oscillations. Compared to traditional control technologies, it shortens voltage recovery time and improves power fluctuation suppression rate, effectively solving the stability control problem of distribution networks with a high proportion of distributed energy resources. At the same time, it reduces the computing resource consumption and deployment cost of smart terminals, demonstrating significant engineering practical value. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A structural block diagram of a frequency modulation damping coordinated control device for a power distribution network provided in an embodiment of the present invention;

[0022] Figure 2A flowchart illustrating a frequency regulation damping coordinated control method for a power distribution network provided in an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of a sub-process of a frequency regulation damping coordinated control method for a power distribution network provided in an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] Example

[0027] In this embodiment, the implementation of the distribution network on "smart electricity meters" and "smart converged terminals" is embodied in an edge-end collaborative architecture of "layered sensing, centralized decision-making, and collaborative execution":

[0028] In smart meters: a fixed, lightweight algorithm module is responsible for high-precision acquisition of electrical quantities and real-time calculation of characteristic quantities, such as voltage deviation, frequency deviation, and active power change rate. These characteristic quantities are reported through a high-speed communication interface (such as HPLC), which greatly reduces the amount of uplink data and enables "precise perception" and "preliminary preprocessing" of the local state of the distribution network.

[0029] In the intelligent converged terminal: as the core of regional control, it receives characteristic data streams from one or more energy meters. Its fully implemented RBF-P-LADRC algorithm uses these characteristic quantities as observer inputs y(k) to perform complete calculations of the discretized state update equations, achieving accurate observation of the system-level state and high-order estimation of the total regional disturbance. It also generates coordinated control commands for controllable devices (such as photovoltaic inverters and energy storage converters) for execution.

[0030] This collaborative mechanism concentrates computationally intensive tasks (RBF network, state estimation) on the relatively resource-rich fusion terminal, while decomposing the widely distributed data acquisition and feature extraction tasks to each electricity meter, thus achieving an optimal balance between control accuracy and system feasibility.

[0031] See Figure 1This invention provides a frequency regulation damping coordinated control circuit for a power distribution network. The circuit includes an improved state observation module, integrating a neural network, for acquiring information related to the power distribution network system state and total disturbance; an adaptive compensation module, connected to the improved state observation module, for adjusting the output of disturbance-related information; a state feedback control module, connected to the improved state observation module, for generating control signals based on system state information; and a smart terminal interface module, connected to a smart energy meter, a smart fusion terminal, the state feedback control module, and the improved state observation module.

[0032] In this embodiment, the improved state observation module integrates the core sensing unit of the neural network to collect and process distribution network operation data, outputting system state information (such as voltage and frequency-related states) and total disturbance information (such as disturbances caused by load fluctuations and changes in distributed energy output). The adaptive compensation module, linked to the improved state observation module, is a parameter optimization unit used to dynamically adjust disturbance-related information and improve the accuracy of disturbance estimation. The state feedback control module is a decision-making unit that generates control signals based on system state information and is the core execution logic carrier for achieving stable control of the distribution network. The intelligent terminal interface module is the connection unit that enables data interaction between various functional modules and smart meters and intelligent converged terminals, ensuring smooth data transmission and command issuance.

[0033] In a specific embodiment, in a power distribution network, the control circuit is integrated into a smart fusion terminal. One end of the smart terminal interface module is connected to the metering data output terminal of the smart energy meter to acquire real-time data such as voltage and current. The other end of the smart terminal interface module is connected to the control port of the distributed photovoltaic inverter. The improved state observation module integrates a lightweight radial basis function neural network with 4 neurons to process the data transmitted by the energy meter in real time. The adaptive compensation module dynamically corrects the disturbance estimation results. The state feedback control module generates voltage regulation commands based on the corrected information and sends them to the inverter through the interface module to realize dynamic adjustment of photovoltaic output.

[0034] The modular design achieves a clear division of functions. The integration of the neural network and the observation module improves the accuracy of state and disturbance perception. The interface module ensures seamless compatibility with existing smart terminals and can be deployed without additional hardware modifications. This solves the problems of traditional control circuits, such as lack of frequency modulation targeting, poor compatibility, and insufficient perception accuracy.

[0035] Figure 2 This is a flowchart illustrating a frequency regulation damping coordinated control method for a distribution network provided in an embodiment of the present invention. The present invention proposes a frequency regulation damping coordinated control method for a distribution network; specifically, see [link to documentation]. Figure 2 The frequency regulation and damping coordinated control method of this power distribution network includes the following steps S1-S2.

[0036] S1, the system status information and total disturbance information are obtained by processing the operating data through an improved state observation module integrating a neural network, and the total disturbance information is processed by an adaptive compensation module; the operating data is obtained by collecting data from the distribution network by smart energy meters or smart fusion terminals.

[0037] S2, Based on the system status information and the processed total disturbance information, a control command is generated and transmitted to the intelligent fusion terminal for execution.

[0038] In specific implementation, in a power distribution network, smart meters collect voltage, current, power, and frequency data every 15ms and transmit them to the control module; in step S1, the improved state observation module analyzes the collected data to obtain the power distribution network voltage offset state and photovoltaic power output fluctuation disturbance information, and the adaptive compensation module corrects the disturbance estimation deviation; in step S2, the state feedback control module generates a photovoltaic inverter active power adjustment command based on the voltage offset state and the corrected disturbance information, transmits it to the smart fusion terminal and executes it to suppress voltage fluctuations.

[0039] Steps S1-S2 constitute the frequency regulation and damping coordinated control process between the energy meter and the fusion terminal, which improves the coordinated efficiency of frequency response and oscillation suppression, and avoids the problems of cumbersome process and lagging frequency response in traditional control methods.

[0040] In one embodiment, the operating data includes the effective voltage value data, effective current value data, instantaneous active power value data, instantaneous reactive power value data, and instantaneous frequency value data of the distribution network. Step S1 above includes steps S21-S23:

[0041] S21, calculate voltage deviation and frequency deviation based on the effective voltage value data and instantaneous frequency value data.

[0042] S22, calculate the power change rate based on the instantaneous active power data and the instantaneous reactive power data.

[0043] S23, using voltage deviation, frequency deviation, and power change rate as inputs to the neural network, and combining them with pre-configured parameters to obtain system state information and total disturbance information; the pre-configured parameters include the gain parameters of the improved state observation module, the preset center value of the neural network, and the preset output weights.

[0044] In this embodiment, operational data are key parameters reflecting the operating status of the distribution network. By calculating the difference and rate of change of the operational data, characteristic parameters that can be recognized by neural networks, such as voltage deviation, frequency deviation, and power change rate, are obtained. Pre-configured parameters refer to the basic parameters that ensure the initial operation of the module.

[0045] In a specific embodiment, the smart energy meter collects the effective value of the distribution network voltage (220V), the instantaneous frequency value (50.2Hz), the instantaneous active power value (80kW), and the instantaneous reactive power value (20kVar). In step S1, the voltage deviation (220V-230V=-10V) and the frequency deviation (50.2Hz-50Hz=0.2Hz) are calculated first, and then the active power change rate (80kW-75kW) / 15ms≈333kW / s is calculated. The above three characteristic parameters are input into the neural network, and combined with the pre-configured observation module gain parameters and the initial center value and weight of the neural network, the system voltage instability state and load surge disturbance information are obtained.

[0046] In one embodiment, step S1 above includes the step of: using preset compensation parameters obtained from cloud pre-training as a basis, and combining the deviation between the total disturbance information and the system state information acquired in real time, adjusting the output parameters of the adaptive compensation module to correct the total disturbance information.

[0047] In this embodiment, the preset compensation parameters are initial compensation benchmark parameters obtained through training with historical data in the cloud, ensuring the initial performance of the compensation module. The deviation between the total disturbance information and the system state information serves as the basis for adjusting the compensation parameters. The adaptive compensation module improves the accuracy of the disturbance information by dynamically correcting the output parameters.

[0048] In a specific embodiment, the cloud-based system trains preset compensation parameters based on one year of historical disturbance data of the distribution network (including scenarios such as load fluctuations and changes in photovoltaic output). In actual operation, when the total disturbance information output by the improved state observation module is "load surge of 5kW", and the system state information shows that the actual voltage deviation differs from the theoretical deviation corresponding to the disturbance by 15%, the adaptive compensation module adjusts the output parameters online based on this deviation using the recursive least squares method, correcting the disturbance information to "load surge of 5.7kW", thereby improving the disturbance estimation accuracy.

[0049] In one embodiment, the step of generating control instructions includes:

[0050] The target control quantity is calculated based on the voltage deviation and frequency deviation in the system status information; the total disturbance information after being processed by the adaptive compensation module is introduced to correct the target control quantity, resulting in a control command that includes voltage regulation command and distributed energy control command.

[0051] In this embodiment, the target control quantity is a control reference quantity initially calculated based on the core deviation parameters (voltage deviation, frequency deviation) in the system state information, and it forms the basis of the control commands. Correction refers to introducing compensated and precise disturbance information to optimize and adjust the target control quantity, ensuring the relevance of the control commands. Voltage regulation commands and distributed energy control commands are specific execution command types adapted to the stability control requirements of the distribution network.

[0052] In a specific embodiment, when the system status information shows a voltage deviation of -8V and a frequency deviation of 0.1Hz, the target control quantity is first calculated as "increase the active power output of the distributed power source by 3kW". Combined with the disturbance information of "photovoltaic power output drops by 2kW" corrected by the adaptive compensation module, the target control quantity is corrected to generate a control instruction of "increase the active power output of the distributed power source by 5kW", along with a voltage regulation instruction of "adjust the transformer tap position by 1 level", which is transmitted to the intelligent fusion terminal for execution.

[0053] In one embodiment, the method further includes periodically executing step S1, which specifically includes:

[0054] The time interval between two executions of step S1 is set to 10ms-20ms, and before each execution of step S1, the latest operating data collected by the smart energy meter or smart converged terminal is updated through the smart terminal interface module.

[0055] In this embodiment, periodically executing step S1 means repeatedly executing step S1 at fixed time intervals. The 10ms-20ms time interval is a reasonable sampling period to adapt to the dynamic changes of the distribution network, balancing control real-time performance and intelligent terminal resource consumption. The step is updated through the intelligent terminal interface module to synchronize the latest operating data before each cycle, ensuring that control commands are generated based on the current actual operating state.

[0056] In a specific embodiment, the execution interval of the control method is set to 12ms. The smart terminal executes step S1 once every 12ms. Before execution, the latest voltage, current and other data collected by the smart energy meter are obtained through the smart terminal interface module. For the scenario of rapid fluctuation of photovoltaic output in the distribution network, the periodic data update and processing enable the control command to keep up with the fluctuation changes in real time. The output control parameters of the photovoltaic inverter are adjusted once every 12ms, which effectively suppresses power swing.

[0057] In one embodiment, the preset center value of the neural network is obtained by clustering historical operating data of the power distribution network using an improved K-means algorithm.

[0058] In this embodiment, the improved K-means algorithm is an optimized clustering algorithm that enhances the rationality and effectiveness of clustering results by optimizing the selection of cluster centers. Historical operating data of the distribution network typically refers to samples of distribution network operating data covering different operating conditions and time periods, serving as the fundamental data source for cluster analysis. The preset center values ​​are the center parameters of the hidden layer neurons in the neural network obtained through the clustering algorithm, providing an effective input mapping benchmark for the initial operation of the neural network.

[0059] In a specific embodiment, the cloud collects 365 days of historical operation data of the power distribution network and extracts 100,000 samples of voltage deviation, frequency deviation, and power change rate. An improved K-means algorithm is used to cluster the samples, and the number of cluster centers is set to 5 (matching 5 neurons in the hidden layer of the neural network). The 5 cluster centers are obtained through iterative optimization and used as the preset center values ​​of the neural network, which are then sent to the control module of the smart terminal.

[0060] In one embodiment, the step of processing operational data by the improved state observation module integrating a neural network includes:

[0061] Using a preset time interval as the sampling period, the system state information and total disturbance information for the current period are calculated through a discretized state update equation based on the system state information of the previous period and the operating data of the current period.

[0062] In this embodiment, the preset time interval sampling period is consistent with the periodic execution interval of the control method, ensuring the synchronization of data acquisition and processing. The previous cycle state information is the system state and disturbance data obtained from the previous round of processing, providing a historical reference for the current cycle calculation. The discretized state update equation refers to a simplified calculation method adapted to the computing resources of the intelligent terminal, reducing computational complexity through discretization.

[0063] In a specific embodiment, a preset time interval of 15ms is set. The improved state observation module takes the voltage stability information of the previous cycle and the voltage and power data collected in the current cycle as input, and uses a discretized state update equation to calculate the system state information and total disturbance information of the current cycle. The calculation process is completed on the ARM Cortex-M processor of the intelligent fusion terminal. Let the system sampling and control cycle be T (typically T=15ms). At the k-th sampling time, the discrete state update equation of the improved LESO is as follows:

[0064] ;

[0065] ;

[0066] ;

[0067] Where e(k)=y(k)-z1(k) is the observation error; Δe(k)=e(k)-e(k-1) is the error change; φ(e(k),Δe(k)) is the nonlinear dynamic compensation term of the output of the lightweight RBF neural network; η is the adjustable compensation strength coefficient; β1, β2, and β3 are the gain parameters of the improved state observation module; z1 is the estimated value of the key output of the distribution network, which corresponds to the actual operating value of the voltage or frequency; z2 is the estimated value of the rate of change of the key output of the distribution network, i.e., the rate of change of voltage or frequency, reflecting the dynamic change speed of the system; z3 is the estimated value of the total disturbance of the distribution network, which covers all comprehensive disturbances affecting the stability of the system, such as load fluctuations and distributed energy output fluctuations; b0 is the system control gain parameter, which reflects the influence of the control quantity on the output of the distribution network (such as voltage and frequency).

[0068] Discretization reduces the computational complexity of the observation module, making better use of the limited computing resources of the smart terminal. At the same time, combining historical state information improves the accuracy of the current period's calculation results, solving the problems of computational complexity and high resource consumption in traditional observation modules, and ensuring the efficient operation of the control method on the smart terminal.

[0069] The embodiments of the present invention can achieve the following advantages:

[0070] By integrating an improved state observation module with a neural network and an adaptive compensation module, the accuracy of state perception and disturbance estimation in the distribution network system is significantly improved. The seamless compatibility of the control circuit with smart meters and smart fusion terminals achieves a "plug-and-play" deployment effect without the need for additional hardware modifications.

[0071] With a concise core process and periodic execution mechanism, it balances real-time control with resource efficiency, achieving a control cycle of 10-20ms and enabling rapid response to frequency fluctuations and low-frequency oscillations. Compared to traditional control technologies, it shortens voltage recovery time and improves power fluctuation suppression rate, effectively solving the stability control problem of distribution networks with a high proportion of distributed energy resources. At the same time, it reduces the computing resource consumption and deployment cost of smart terminals, demonstrating significant engineering practical value.

[0072] like Figure 4 As shown, Figure 4 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0073] The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0074] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it causes the processor 502 to execute a frequency regulation damping coordinated control method for a power distribution network.

[0075] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0076] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a frequency regulation damping coordinated control method for a power distribution network.

[0077] The network interface 505 is used for network communication with other devices. Those skilled in the art will understand that the above structure is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. A specific computer device 500 may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements.

[0078] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0079] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0080] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program.

[0081] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk, or any other physical storage medium capable of storing program code. The computer-readable storage medium can be non-volatile or volatile.

[0082] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0083] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0084] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0085] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0086] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0087] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0088] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A frequency regulation damping coordinated control method for a power distribution network, characterized in that, Includes the following steps: S1, the system status information and total disturbance information are obtained by processing the operating data through an improved state observation module integrating a neural network, and the total disturbance information is processed by an adaptive compensation module; the operating data is obtained by collecting data from the distribution network by smart energy meters or smart fusion terminals; S2, Based on the system status information and the processed total disturbance information, a control command is generated and transmitted to the intelligent fusion terminal for execution; The operating data includes the effective voltage value data, effective current value data, instantaneous active power value data, instantaneous reactive power value data, and instantaneous frequency value data of the distribution network. Step S1 includes: Calculate voltage deviation and frequency deviation based on the effective voltage value data and the instantaneous frequency value data; Calculate the power change rate based on the instantaneous active power data and the instantaneous reactive power data; Voltage deviation, frequency deviation, and power change rate are used as inputs to a neural network, and system state information and total disturbance information are obtained by combining them with pre-configured parameters. The pre-configured parameters include the gain parameters of the improved state observation module, the preset center value of the neural network, and the preset output weights. The system state information includes system voltage instability state information, and the total disturbance information includes load surge disturbance information. The step of processing the total disturbance information through the adaptive compensation module includes: Based on the preset compensation parameters obtained from cloud pre-training, and combined with the deviation between the total disturbance information and the system state information acquired in real time, the output parameters of the adaptive compensation module are adjusted online using the recursive least squares method to correct the total disturbance information. The step of generating control commands includes: Calculate the target control quantity based on the voltage deviation and frequency deviation in the system status information; The total disturbance information processed by the adaptive compensation module is used to correct the target control quantity, resulting in a control command that includes voltage regulation command and distributed energy control command.

2. The method according to claim 1, characterized in that, It also includes the periodic execution of step S1, which specifically includes: The time interval between two executions of step S1 is set to 10ms-20ms, and before each execution of step S1, the latest operating data collected by the smart energy meter or smart converged terminal is updated through the smart terminal interface module.

3. The method according to claim 1, characterized in that, The preset center value of the neural network is obtained by clustering historical operating data of the power distribution network using an improved K-means algorithm.

4. The method according to claim 1, characterized in that, The steps of processing operational data using the improved state observation module with integrated neural network include: Using a preset time interval as the sampling period, the system state information and total disturbance information for the current period are calculated through a discretized state update equation based on the system state information of the previous period and the operating data of the current period.

5. A computer device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method according to any one of claims 1-4.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-4.

Images