Power supply control method and system based on microgrid

Abstract

The application discloses a power supply control method and system based on a micro-grid and belongs to the technical field of micro-grids. The application obtains real-time operation data of the micro-grid, determines a target controlled mode and a collaborative adjustment subject according to the real-time operation data, the collaborative adjustment subject comprising wind energy equipment, light energy equipment and energy storage equipment, constructs a multi-target collaborative optimization model according to the target controlled mode and the collaborative adjustment subject, determines a dynamic power modulation strategy of each collaborative adjustment subject according to the multi-target collaborative optimization model, generates a control instruction according to the dynamic power modulation strategy, and suppresses power oscillation of the micro-grid according to the control instruction, so that the power oscillation is reduced, and the beneficial effect of guaranteeing safe operation of the power grid is achieved.

Description

Technical Field

[0001] This invention relates to the field of microgrid technology, and in particular to a power supply control method and system based on microgrids. Background Technology

[0002] Microgrids, as a type of distributed energy system, typically integrate renewable energy sources such as wind and solar power, along with energy storage devices. They generally achieve power supply stability through autonomous control. However, the power output of wind and solar power is often affected by weather conditions, leading to imbalances and instability. Traditional power oscillation suppression methods, typically based on damping control—a passive response approach—are effective in traditional large power grids, primarily by increasing system damping to attenuate low-frequency oscillations. However, these methods are less effective in microgrids, resulting in excessive power oscillations and ultimately impacting the safe operation of the power grid.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a power supply control method and system based on a microgrid, aiming to ensure the safe operation of the power grid by reducing power oscillations. To achieve the above objective, this invention provides a power supply control method based on a microgrid, which includes the following steps: The system acquires real-time operating data of the microgrid and determines the target controlled mode and the coordinating control subject based on the real-time operating data. The coordinating control subject includes: wind power equipment, solar power equipment, and energy storage equipment. A multi-objective collaborative optimization model is constructed based on the target controlled mode and the collaborative adjustment agent; The dynamic power modulation strategy for each of the cooperative adjustment subjects is determined based on the multi-objective cooperative optimization model; Control commands are generated according to the dynamic power modulation strategy, and power oscillations of the microgrid are suppressed according to the control commands.

[0005] Optionally, the real-time operating data includes: synchronous phasor measurement data, equipment status data, and park load characteristic data. The park load characteristic data includes: charging pile load data or server power consumption data. The step of determining the target controlled mode and the coordinated adjustment subject based on the real-time operating data includes: The oscillation frequency, damping ratio, and participation factor are extracted based on the identification algorithm and the synchronous phasor measurement data. The target controlled mode is determined based on the oscillation frequency, the damping ratio, and the participation factor; The adjustable power margin of the coordinated regulation subject is determined based on the equipment status data and the park load characteristic data; The coordinated adjustment subject is determined based on the adjustable power margin.

[0006] Optionally, the step of constructing a multi-objective cooperative optimization model based on the target controlled mode and the cooperative adjustment agent includes: The oscillation attenuation objective function is determined based on the target controlled mode, and the action cost objective function is determined based on the cooperative adjustment subject; The multi-objective collaborative optimization model is constructed based on the oscillation attenuation objective function and the action cost objective function, wherein the oscillation attenuation objective function is positively correlated with the amplitude increase rate of the target controlled mode, and the action cost objective function is positively correlated with the active power adjustment deviation of the collaborative adjustment subject.

[0007] Optionally, the step of determining the dynamic power modulation strategy for each of the cooperative adjustment agents based on the multi-objective cooperative optimization model includes: The reward function of the reinforcement learning environment is determined based on the multi-objective collaborative optimization model. The action space of each of the cooperative regulatory agents is determined based on the reinforcement learning environment; The active power modulation gain and reactive power modulation gain of each of the cooperative adjustment subjects are determined by optimizing the reward function, the action space, and the deep reinforcement learning algorithm in the reinforcement learning environment, and used as the dynamic power modulation strategy.

[0008] Optionally, before the step of optimizing the solution in the reinforcement learning environment using a deep reinforcement learning algorithm, the method further includes: The current system operating mode is determined based on the proportion of new energy output of the microgrid and the load fluctuation characteristics of the park; The network parameters of the deep reinforcement learning algorithm are adaptively adjusted based on the current system operating mode.

[0009] Optionally, the step of adaptively adjusting the network parameters of the deep reinforcement learning algorithm according to the current system operating mode includes: The current mode feature fingerprint is determined based on the current system operating mode. The current mode feature fingerprint includes: system topology, distributed power supply penetration rate, and load spatiotemporal distribution characteristics. Based on the current modality feature fingerprint, retrieve the parameter set of similar historical modalities from the preset parameter library; The parameter migration gain is determined based on the parameter set of the similar historical modes and the feature fingerprint of the current mode; The network parameters of the deep reinforcement learning algorithm are smoothly updated based on the parameter transfer gain.

[0010] Optionally, after the step of suppressing power oscillations in the microgrid according to the control command, the method further includes: Monitor the residual oscillation energy of the microgrid after executing the control command; The model update step size is determined based on the residual oscillation energy, and the weight parameters of the multi-objective collaborative optimization model are fine-tuned online based on the model update step size. The model update step size is positively correlated with the residual oscillation energy.

[0011] Furthermore, to achieve the above objectives, the present invention also provides a microgrid-based power supply control system, the microgrid-based power supply control system comprising: The monitoring module is used to acquire real-time operating data of the microgrid and determine the target controlled mode and the coordinating adjustment subject based on the real-time operating data. The coordinating adjustment subject includes: wind power equipment, solar power equipment and energy storage equipment. The modeling module is used to construct a multi-objective collaborative optimization model based on the target controlled mode and the collaborative adjustment agent; The analysis module is used to determine the dynamic power modulation strategy of each of the cooperative adjustment subjects based on the multi-objective cooperative optimization model; The control module is used to generate control commands according to the dynamic power modulation strategy and suppress power oscillations of the microgrid according to the control commands.

[0012] Furthermore, to achieve the above objectives, the present invention also provides a microgrid-based power supply control device, the device comprising: a memory, a processor, and a microgrid-based power supply control program stored in the memory and executable on the processor, the microgrid-based power supply control program being configured to implement the steps of the microgrid-based power supply control method described in any of the above claims.

[0013] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a microgrid-based power supply control program, wherein when the microgrid-based power supply control program is executed by a processor, it implements the steps of the microgrid-based power supply control method described in any of the above claims.

[0014] This invention proposes a power supply control method based on a microgrid. This method acquires real-time operating data of the microgrid and determines the target controlled mode and the coordinating regulator based on this data, enabling each power supply device in the system to participate in grid regulation. A multi-objective cooperative optimization model is constructed based on the target controlled mode and the coordinating regulator. A dynamic power modulation strategy for each coordinating regulator is determined based on the multi-objective cooperative optimization model, and control commands are generated based on the dynamic power modulation strategies. These control commands are then used to suppress power oscillations in the microgrid. Therefore, compared to traditional power oscillation suppression methods, this method achieves power oscillation suppression by coordinating the various power supply devices. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of a microgrid-based power supply control device for the hardware operating environment involved in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the first embodiment of the power supply control method based on a microgrid according to the present invention. Figure 3 This is a flowchart illustrating a second embodiment of the power supply control method based on a microgrid according to the present invention. Figure 4 This is a flowchart illustrating the third embodiment of the power supply control method based on a microgrid according to the present invention.

[0016] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0018] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a microgrid-based power supply control device for the hardware operating environment involved in the embodiments of the present invention.

[0019] like Figure 1As shown, the microgrid-based power supply control device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The interactive device 1003 may include a display screen or an input unit such as a keyboard. Optionally, the interactive device 1003 may also be connected to the communication bus via standard wired or wireless interfaces. The network interface 1004 may optionally include standard wired or wireless interfaces (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0020] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on microgrid-based power supply control equipment, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0021] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a power supply control program based on a microgrid.

[0022] exist Figure 1 In the microgrid-based power supply control device shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with users; the processor 1001 and memory 1005 in the microgrid-based power supply control device of the present invention can be set in the microgrid-based power supply control device, and the microgrid-based power supply control device calls the microgrid-based power supply control program stored in the memory 1005 through the processor 1001 and executes the microgrid-based power supply control method provided in the embodiment of the present invention.

[0023] This invention provides a power supply control method based on a microgrid, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a power supply control method based on a microgrid according to the present invention.

[0024] In this embodiment, the power supply control method based on microgrid includes: Step S1: Obtain the real-time operation data of the microgrid, and determine the target controlled mode and the coordinating regulation subject based on the real-time operation data. The coordinating regulation subject includes: wind power equipment, solar power equipment and energy storage equipment. In this embodiment, the data collected during the real-time operation of the microgrid at the current moment may include: power generation output data, load data, and system operating status, which can typically be obtained through sensors. This data can be used to analyze the current behavior of the microgrid. The target controlled mode here refers to a specific oscillation mode in the microgrid that needs to be specifically suppressed, such as a low-frequency oscillation mode. Optionally, the low-frequency oscillation mode here can have a frequency of 0.5Hz and a damping ratio of 0.05. The coordinated regulation subject here refers to the devices and units participating in the regulation. These coordinated regulation subjects can communicate with each other through a preset network, thereby enabling coordinated operation of multiple devices.

[0025] Step S2: Construct a multi-objective collaborative optimization model based on the target controlled mode and the collaborative adjustment agent; In this embodiment, the multi-objective collaborative optimization model is a mathematical model, including multiple constraints and multiple optimization objectives. The optimization objectives may include minimizing cost, maximizing damping, and reducing carbon emissions. The constraints include the power output limits of each collaborative regulating entity. Optionally, the optimization objectives may include a damping ratio in the range of [0.1, 0.2] and minimum economic cost. The constraints may include the output power of the energy storage device and its current energy storage state.

[0026] Step S3: Determine the dynamic power modulation strategy for each of the cooperative adjustment subjects based on the multi-objective cooperative optimization model; Based on the real-time changes in the system state, the power output / input strategy of each regulating entity is dynamically adjusted, including active and reactive power modulation. Specifically, it is necessary to output the changes in the operation of each device under various conditions. For example, when the frequency deviation is >0.1Hz, the wind power equipment increases its output by 5%, the solar power equipment injects 10kVar of reactive power, and the energy storage equipment releases 20kW. This is because wind power equipment generally has power reserves, while the injection of reactive power by solar power equipment is one of the common functions of photovoltaic systems, which is suitable for oscillation suppression.

[0027] Step S4: Generate control commands according to the dynamic power modulation strategy, and suppress power oscillations of the microgrid according to the control commands.

[0028] Specifically, the dynamic power modulation strategy is converted into control commands that each device can recognize, and the control commands are sent to the controller. The controller controls the operation of the coordinated adjustment subject through the control commands, thereby suppressing the power oscillation of the microgrid.

[0029] In this embodiment, by acquiring real-time operating data of the microgrid and determining the target controlled mode and the coordinating entity based on the real-time operating data, each power supply device in the system can participate in the regulation of the power grid. A multi-objective cooperative optimization model is constructed based on the target controlled mode and the coordinating entity. The dynamic power modulation strategy of each coordinating entity is determined based on the multi-objective cooperative optimization model. Control commands are generated based on the dynamic power modulation strategy, and power oscillations of the microgrid are suppressed based on the control commands. Thus, compared with traditional power oscillation suppression methods, power oscillations are suppressed by coordinating each power supply device.

[0030] Furthermore, based on the first embodiment, a second embodiment of the power supply control method based on a microgrid of the present invention is proposed. In this embodiment, reference is made to... Figure 3 The real-time operating data includes: synchronous phasor measurement data, equipment status data, and park load characteristic data. The park load characteristic data includes: charging pile load data or server power consumption data. The step of determining the target controlled mode and the coordinated adjustment subject based on the real-time operating data includes: Step S11: Extract the oscillation frequency, damping ratio, and participation factor based on the identification algorithm and the synchronous phasor measurement data; The waveform is decoupled into several potential oscillation components by an identification algorithm, and the oscillation frequency, damping ratio and participation factor that can reflect the dynamic stability of the power grid are extracted. The above physical quantities can be used for subsequent mode screening. In this embodiment, the control decision does not rely on empirical thresholds, but identifies abnormal changes in the microgrid based on real-time perception of oscillation characteristics.

[0031] Step S12: Determine the target controlled mode based on the oscillation frequency, the damping ratio, and the participation factor; Modes whose oscillation frequency falls within the sensitive range and whose participation factors are prominent are selected as target controlled modes. In this step, the frequency domain characteristics are transformed into specific control objects, so that subsequent adjustment resources can be used to suppress the dominant oscillations that are most likely to cause instability. This avoids the redundant control of the broad-based approach in traditional methods, thereby improving control efficiency and reducing interference with normal power transmission, achieving a balance between grid stability and economy.

[0032] Step S13: Determine the adjustable power margin of the coordinated adjustment subject based on the equipment status data and the park load characteristic data; The real-time output, state of charge, energy storage status, and health indicators of the equipment status data are combined with the charging pile power curves or server power consumption fluctuations in the park load characteristic data to calculate the adjustable power margin of each controllable unit in the next time period. It should be noted that the margin here needs to take into account the physical limits of the equipment.

[0033] Step S14: Determine the coordinated adjustment subject based on the adjustable power margin.

[0034] Optionally, units with sufficient margin and fast response speed are prioritized as the main body of coordinated regulation; the selected main body undertakes the tasks of damping compensation and power balance in the subsequent closed-loop control, and its remaining capacity provides elastic space for oscillation suppression.

[0035] In this embodiment, the oscillation frequency, damping ratio, and participation factor are extracted by the identification algorithm and the synchronous phasor measurement data. The target controlled mode is determined based on the oscillation frequency, the damping ratio, and the participation factor. The adjustable power margin of the coordinated regulation subject is determined based on the equipment status data and the park load characteristic data. The coordinated regulation subject is determined based on the adjustable power margin, thereby effectively screening out the coordinated regulation subject.

[0036] Furthermore, based on the first or second embodiment, a third embodiment of the power supply control method based on a microgrid of the present invention is proposed. In this embodiment, reference is made to... Figure 3 The step of constructing a multi-objective collaborative optimization model based on the target controlled mode and the collaborative adjustment agent includes: Step S21: Determine the oscillation attenuation objective function based on the target controlled mode, and determine the action cost objective function based on the cooperative adjustment subject; Optionally, the amplitude increase rate can be used as the main variable in the oscillation attenuation objective function, causing the function value to monotonically increase as the oscillation intensifies, thus transforming the stabilization of the power grid into a mathematical solution that minimizes this function value. It should be noted that the coordinated regulation entity generally needs to calculate the corresponding adjustment cost during the regulation process to avoid excessively high costs. Optionally, for the selected coordinated regulation entity, the active power regulation deviation can be used as the action cost objective function; a larger deviation means a greater adjustment in equipment output.

[0037] Step S22: Construct the multi-objective collaborative optimization model based on the oscillation decay objective function and the action cost objective function; The oscillation attenuation objective function is positively correlated with the amplitude increase rate of the target controlled mode, and the action cost objective function is positively correlated with the active power adjustment deviation of the coordinated adjustment subject.

[0038] Preferably, the oscillation attenuation objective function and the action cost objective function are solved jointly. Furthermore, it should be noted that other constraints need to be converted into corresponding constraint-type functional relationships. During the solution process, these constraint-type functional relationships need to be solved jointly with the aforementioned oscillation attenuation objective function and action cost objective function. Optionally, through weight normalization and Pareto sorting, the multi-objective collaborative optimization model can output control commands that balance stability margin and economy in a single solution, avoiding the drawbacks of traditional single-objective schemes that neglect one aspect for another. The final generated control strategy not only quickly weakens the dominant oscillation but also distributes the adjustment amount to devices with large adjustability margins and low costs, achieving high resilience and low-loss operation of the park microgrid under disturbances.

[0039] In this embodiment, the oscillation attenuation objective function is determined by the target controlled mode, and the action cost objective function is determined by the cooperative adjustment subject. The multi-objective cooperative optimization model is constructed based on the oscillation attenuation objective function and the action cost objective function, thereby improving the accuracy of the multi-objective cooperative optimization model.

[0040] Furthermore, based on any of the above embodiments, a fourth embodiment of the power supply control method based on a microgrid is proposed. In this embodiment, the step of determining the dynamic power modulation strategy of each of the cooperative adjustment subjects according to the multi-objective cooperative optimization model includes: The reward function of the reinforcement learning environment is determined based on the multi-objective collaborative optimization model. The action space of each of the cooperative regulatory agents is determined based on the reinforcement learning environment; The active power modulation gain and reactive power modulation gain of each of the cooperative adjustment subjects are determined by optimizing the reward function, the action space, and the deep reinforcement learning algorithm in the reinforcement learning environment, and used as the dynamic power modulation strategy.

[0041] In this embodiment, specifically, the combined value of oscillation decay and action cost output by the multi-objective collaborative optimization model is directly mapped to the time step reward of the reinforcement learning environment, so that the impact on grid stability and economy can be immediately perceived every time a power adjustment is performed; the action space can be a continuous interval of active and reactive power modulation gain for each collaborative adjustment subject, thus preserving both the physical constraints of the equipment and sufficient control flexibility.

[0042] Furthermore, prior to the step of optimizing the solution in the reinforcement learning environment using a deep reinforcement learning algorithm, the method further includes: The current system operating mode is determined based on the proportion of new energy output of the microgrid and the load fluctuation characteristics of the park; The network parameters of the deep reinforcement learning algorithm are adaptively adjusted based on the current system operating mode.

[0043] In this embodiment, multiple judgment conditions can be set. When the observed proportion of new energy output increases, it is recorded as the "high-temperature mode." When there is a concentrated start-up and shutdown of charging piles in the park, it is recorded as the "impact mode." When both labels appear simultaneously, they are combined to form the current system operating mode. When similar historical records are retrieved from the parameter library, the corresponding network weights are read. After calculating the transfer gain, the existing network is smoothly updated. When the update is complete, the agent's initial policy is close to the new mode. When deep reinforcement learning is started, the convergence speed is improved and the exploration risk is reduced.

[0044] The step of adaptively adjusting the network parameters of the deep reinforcement learning algorithm according to the current system operating mode includes: The current mode feature fingerprint is determined based on the current system operating mode. The current mode feature fingerprint includes: system topology, distributed power supply penetration rate, and load spatiotemporal distribution characteristics. Based on the current modality feature fingerprint, retrieve the parameter set of similar historical modalities from the preset parameter library; The parameter migration gain is determined based on the parameter set of the similar historical modes and the feature fingerprint of the current mode; The network parameters of the deep reinforcement learning algorithm are smoothly updated based on the parameter transfer gain.

[0045] In this embodiment, optionally, the system topology, distributed power supply penetration rate and load spatiotemporal distribution are encoded to form a high-dimensional vector. The most similar historical operating scenario is then retrieved from a preset parameter library. The parameter set of similar historical modes is used as prior knowledge, and the parameter transfer gain is calculated by combining fingerprint differences. This is then injected into a deep reinforcement learning network in a smooth update manner, thereby preserving historical experience.

[0046] Furthermore, based on any of the above embodiments, a fifth embodiment of the power supply control method based on a microgrid is proposed. In this embodiment, after the step of suppressing the power oscillation of the microgrid according to the control command, the method further includes: Monitor the residual oscillation energy of the microgrid after executing the control command; The model update step size is determined based on the residual oscillation energy, and the weight parameters of the multi-objective collaborative optimization model are fine-tuned online based on the model update step size. The model update step size is positively correlated with the residual oscillation energy.

[0047] Furthermore, this invention also proposes a microgrid-based power supply control system, which includes: The monitoring module is used to acquire real-time operating data of the microgrid and determine the target controlled mode and the coordinating adjustment subject based on the real-time operating data. The coordinating adjustment subject includes: wind power equipment, solar power equipment and energy storage equipment. The modeling module is used to construct a multi-objective collaborative optimization model based on the target controlled mode and the collaborative adjustment agent; The analysis module is used to determine the dynamic power modulation strategy of each of the cooperative adjustment subjects based on the multi-objective cooperative optimization model; The control module is used to generate control commands according to the dynamic power modulation strategy and suppress power oscillations of the microgrid according to the control commands.

[0048] Furthermore, embodiments of the present invention also propose a microgrid-based power supply control device, the device comprising: a memory, a processor, and a microgrid-based power supply control program stored in the memory and executable on the processor, the microgrid-based power supply control program being configured to implement the steps of the microgrid-based power supply control method described above.

[0049] Furthermore, embodiments of the present invention also propose a storage medium storing a microgrid-based power supply control program, wherein when the microgrid-based power supply control program is executed by a processor, it implements the steps of the microgrid-based power supply control method described above.

[0050] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. 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 system that includes that element.

[0051] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0052] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0053] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A power supply control method based on a microgrid, characterized in that, The microgrid-based power supply control method includes the following steps: The system acquires real-time operating data of the microgrid and determines the target controlled mode and the coordinating control subject based on the real-time operating data. The coordinating control subject includes: wind power equipment, solar power equipment, and energy storage equipment. A multi-objective collaborative optimization model is constructed based on the target controlled mode and the collaborative adjustment agent; The dynamic power modulation strategy for each of the cooperative adjustment subjects is determined based on the multi-objective cooperative optimization model; Control commands are generated according to the dynamic power modulation strategy, and power oscillations of the microgrid are suppressed according to the control commands.

2. The power supply control method based on a microgrid as described in claim 1, characterized in that, The real-time operational data includes: synchronous phasor measurement data, equipment status data, and park load characteristic data. The park load characteristic data includes: charging pile load data or server power consumption data. The step of determining the target controlled mode and the collaborative adjustment subject based on the real-time operational data includes: The oscillation frequency, damping ratio, and participation factor are extracted based on the identification algorithm and the synchronous phasor measurement data. The target controlled mode is determined based on the oscillation frequency, the damping ratio, and the participation factor; The adjustable power margin of the coordinated regulation subject is determined based on the equipment status data and the park load characteristic data; The coordinated adjustment subject is determined based on the adjustable power margin.

3. The power supply control method based on a microgrid as described in claim 1, characterized in that, The step of constructing a multi-objective collaborative optimization model based on the target controlled mode and the collaborative adjustment agent includes: The oscillation attenuation objective function is determined based on the target controlled mode, and the action cost objective function is determined based on the cooperative adjustment subject; The multi-objective collaborative optimization model is constructed based on the oscillation attenuation objective function and the action cost objective function, wherein the oscillation attenuation objective function is positively correlated with the amplitude increase rate of the target controlled mode, and the action cost objective function is positively correlated with the active power adjustment deviation of the collaborative adjustment subject.

4. The power supply control method based on a microgrid as described in claim 1, characterized in that, The step of determining the dynamic power modulation strategy for each of the cooperative adjustment agents based on the multi-objective cooperative optimization model includes: The reward function of the reinforcement learning environment is determined based on the multi-objective collaborative optimization model. The action space of each of the cooperative regulatory agents is determined based on the reinforcement learning environment; The active power modulation gain and reactive power modulation gain of each of the cooperative adjustment subjects are determined by optimizing the reward function, the action space, and the deep reinforcement learning algorithm in the reinforcement learning environment, and used as the dynamic power modulation strategy.

5. The power supply control method based on a microgrid as described in claim 4, characterized in that, Before the step of optimizing the solution in the reinforcement learning environment using a deep reinforcement learning algorithm, the method further includes: The current system operating mode is determined based on the proportion of new energy output of the microgrid and the load fluctuation characteristics of the park; The network parameters of the deep reinforcement learning algorithm are adaptively adjusted based on the current system operating mode.

6. The power supply control method based on a microgrid as described in claim 5, characterized in that, The step of adaptively adjusting the network parameters of the deep reinforcement learning algorithm according to the current system operating mode includes: The current mode feature fingerprint is determined based on the current system operating mode. The current mode feature fingerprint includes: system topology, distributed power supply penetration rate, and load spatiotemporal distribution characteristics. Based on the current modality feature fingerprint, retrieve the parameter set of similar historical modalities from the preset parameter library; The parameter migration gain is determined based on the parameter set of the similar historical modes and the feature fingerprint of the current mode; The network parameters of the deep reinforcement learning algorithm are smoothly updated based on the parameter transfer gain.

7. The power supply control method based on a microgrid as described in claim 1, characterized in that, After the step of suppressing power oscillations in the microgrid according to the control command, the method further includes: Monitor the residual oscillation energy of the microgrid after executing the control command; The model update step size is determined based on the residual oscillation energy, and the weight parameters of the multi-objective collaborative optimization model are fine-tuned online based on the model update step size. The model update step size is positively correlated with the residual oscillation energy.

8. A power supply control system based on a microgrid, characterized in that, The microgrid-based power supply control system includes: The monitoring module is used to acquire real-time operating data of the microgrid and determine the target controlled mode and the coordinating adjustment subject based on the real-time operating data. The coordinating adjustment subject includes: wind power equipment, solar power equipment and energy storage equipment. The modeling module is used to construct a multi-objective collaborative optimization model based on the target controlled mode and the collaborative adjustment agent; The analysis module is used to determine the dynamic power modulation strategy of each of the cooperative adjustment subjects based on the multi-objective cooperative optimization model; The control module is used to generate control commands according to the dynamic power modulation strategy and suppress power oscillations of the microgrid according to the control commands.

9. A power supply control device based on a microgrid, characterized in that, The device includes: a memory, a processor, and a microgrid-based power supply control program stored in the memory and executable on the processor, the microgrid-based power supply control program being configured to implement the steps of the microgrid-based power supply control method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a microgrid-based power supply control program, which, when executed by a processor, implements the steps of the microgrid-based power supply control method as described in any one of claims 1 to 7.

Images