Source load storage cooperative active support control method and system in station area planned off-network mode

Abstract

The invention belongs to the technical field of power system control, and provides a source-load-storage cooperative active support control method and system in a station area planned off-grid mode, and the method comprises the steps: obtaining the grid-connected data information of an optical storage charging power station; predicting the off-grid risk of the optical storage power station of the obtained data information based on a gradient boosting tree model; when the obtained off-grid risk prediction value exceeds a risk threshold value, calculating the charge state of energy storage based on a particle swarm optimization algorithm, predicting the photovoltaic power based on support vector regression, and performing off-grid switching; according to the energy storage charge state and the photovoltaic power prediction value, an energy storage charge state-frequency control model is constructed, the voltage-frequency of the charging station is dynamically adjusted, and off-grid operation is carried out; optimal scheduling of the charging station is carried out by predicting the charging load until the power is balanced, and a grid-connected recovery stage is entered; smooth switching control of off-grid operation and grid-connected operation is carried out based on a second-order low-pass filtering smooth switching method, and source-load-storage cooperative active support control is completed.

Description

Technical Field

[0001] This invention belongs to the field of power system control technology, specifically relating to a source-load-storage collaborative active support control method and system under the planned off-grid mode of distribution area. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Photovoltaic-storage charging stations, as a new type of integrated energy utilization facility, play an important role in improving energy efficiency and alleviating grid pressure. In situations such as grid maintenance, faults, or power supply disruptions in remote areas, distribution transformers need to enter planned off-grid operation. Ensuring the stable operation of photovoltaic-storage charging stations and achieving coordinated control of energy sources, loads, and storage has become an urgent problem to be solved.

[0004] Traditional grid-connected energy storage control methods focus solely on maintaining voltage and frequency stability when off-grid, completely neglecting the battery's charge level. This makes energy storage devices highly susceptible to overcharging or over-discharging during actual operation. Overcharging intensifies internal chemical reactions, generating significant heat that can shorten battery life and even lead to safety accidents. Over-discharging damages the battery's electrode materials, similarly drastically reducing performance and lifespan. However, this control approach, which ignores battery charge level, severely impacts the long-term stable operation of the energy storage device and limits the overall system's reliability and economic efficiency.

[0005] Electric vehicle charging is highly unpredictable. The randomness of vehicle owners' arrival times makes it difficult for charging stations to accurately plan power supply in advance, and charging time varies depending on factors such as vehicle model and remaining battery power. This poses a significant challenge to power dispatching in off-grid conditions. If these uncertainties cannot be effectively addressed, the power fluctuations generated during electric vehicle charging can severely impact off-grid photovoltaic-storage-charging stations, seriously affecting system stability.

[0006] Meanwhile, the operation plans for photovoltaic-storage-charging stations are often designed separately in grid-connected and off-grid states. Failure to fully anticipate potential off-grid situations during grid-connected operation can prevent energy storage and photovoltaic equipment from preparing in advance. When suddenly switching to off-grid mode, the equipment cannot quickly adapt to the new operating mode, which can easily lead to problems such as power surges and voltage fluctuations, seriously affecting the stability and reliability of the off-grid switching process. Summary of the Invention

[0007] To address the aforementioned issues, this invention proposes a source-load-storage coordinated active support control method and system under the planned off-grid mode of a distribution area. This effectively overcomes the problems of overcharging and over-discharging of energy storage, uncertainty of electric vehicle charging load, and disconnection between grid-connected and off-grid operation in traditional off-grid control, and achieves coordinated and optimized control of photovoltaic, energy storage, and charging loads.

[0008] According to some embodiments, the first aspect of the present invention provides a source-load-storage coordinated active support control method under the planned off-grid mode of transformer substations, which adopts the following technical solution: A source-load-storage coordinated active support control method under the off-grid mode of transformer area planning includes: Obtain grid connection data information for photovoltaic, energy storage, and charging stations; Off-grid risk of photovoltaic energy storage charging stations based on data information obtained from gradient boosting tree model prediction; When the obtained off-grid risk prediction value exceeds the risk threshold, the state of charge of energy storage is calculated based on particle swarm optimization algorithm, and photovoltaic power is predicted based on support vector regression, and off-grid switching is performed. During off-grid switching, an energy storage state of charge-frequency control model is constructed based on the energy storage state of charge and photovoltaic power prediction values ​​to dynamically adjust the voltage-frequency of the charging station and enter off-grid operation. When operating off-grid, the charging station is optimized and scheduled by predicting the charging load until power balance is achieved and the grid connection recovery phase begins. During the grid connection recovery phase, a smooth switching control between off-grid and grid-connected operation is performed based on the second-order low-pass filter smooth switching method until grid-connected operation is achieved, thus completing the source-load-storage coordinated active support control.

[0009] As a further technical limitation, in the process of predicting the off-grid risk of photovoltaic-storage-charging stations based on the acquired data information obtained from the gradient boosting tree model, the acquired grid-connected data information of the photovoltaic-storage-charging stations includes at least the grid voltage. U t ,frequency f t Active power flow P t Reactive power flow Q t Meteorological data W t and maintenance plan M t Construct feature vectors based on the acquired grid connection data. X t ,Right now The probability of churn risk is predicted by using a gradient boosting tree model and feature vectors; that is, the probability of churn risk. for .

[0010] As a further technical limitation, at the instant of off-grid operation, the energy storage converter enters an active grid-connection mode, setting the bus frequency based on the state of charge of the energy storage; that is, the bus set frequency. for ;in, k For adjustment coefficients, SOC ref This is a reference value for the state of charge of energy storage. In the state of energy storage charge, f rated This is the reference frequency.

[0011] As a further technical limitation, in the process of optimizing the scheduling of charging stations, mixed integer linear programming is used to optimize the charging scheduling. The objective function is to minimize the difference between the maximum and minimum values ​​of the predicted charging load, thereby obtaining the total charging load.

[0012] As a further technical constraint, a priority load limiting strategy is adopted to ensure power balance, namely... ;in, H For removable load sets, P j cut For load j The resection power, Δ P deficit For power deficits, the priority of load shedding is determined by sorting non-critical loads in ascending order of load importance coefficient.

[0013] As a further technical limitation, the second-order low-pass filter for ;in, Indicates the cutoff frequency. This indicates the damping ratio.

[0014] According to some embodiments, the second aspect of the present invention provides a source-load-storage collaborative active support control system under the planned off-grid mode of transformer substations, which adopts the following technical solution: A source-load-storage collaborative active support control system under a planned off-grid mode for transformer substations includes: The grid-connected operation module is configured to acquire grid-connected data information of the photovoltaic-storage-charging station; predict the off-grid risk of the acquired photovoltaic-storage-charging station based on the gradient boosting tree model; and when the obtained off-grid risk prediction value exceeds the risk threshold, calculate the state of charge of the energy storage based on the particle swarm optimization algorithm, predict the photovoltaic power based on support vector regression, and perform off-grid switching. The off-grid switching module is configured to construct an energy storage state of charge-frequency control model based on the energy storage state of charge and photovoltaic power prediction values, dynamically adjust the voltage-frequency of the charging station, and enter off-grid operation. The off-grid operation module is configured to optimize the scheduling of charging stations by predicting the charging load until power balance is achieved and the grid-connected recovery phase begins. The grid-connected recovery module is configured to perform smooth switching control between off-grid and grid-connected operation based on a second-order low-pass filter smooth switching method until grid-connected operation is achieved, thus completing the source-load-storage coordinated active support control.

[0015] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium, employing the following technical solution: A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the source-load-storage coordinated active support control method under the off-grid mode of the transformer area planning as described in the first aspect of the present invention.

[0016] According to some embodiments, the fourth aspect of the present invention provides an electronic device, which adopts the following technical solution: An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the source-load-storage coordinated active support control method under the off-grid mode of the transformer area plan as described in the first aspect of the present invention.

[0017] According to some embodiments, the fifth aspect of the present invention provides a computer program product, which adopts the following technical solution: A computer program product includes software code, wherein the program in the software code performs the steps in the source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan as described in the first aspect of the present invention.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention effectively overcomes problems such as overcharging and over-discharging of energy storage, uncertainty of electric vehicle charging load, and disconnect between grid-connected and off-grid operation in traditional off-grid control, achieving coordinated and optimized control of photovoltaic, energy storage, and charging loads. Its application scenarios cover planned off-grid distribution areas, microgrids, isolated power supply areas, and distribution network environments with a high proportion of renewable energy. While improving power supply continuity and reliability, it also considers extending equipment lifespan and improving renewable energy utilization efficiency, which is of great significance for smart grid construction and the optimization of electric vehicle charging infrastructure. Attached Figure Description

[0019] The accompanying drawings, which form part of this embodiment, are used to provide a further understanding of this embodiment. The illustrative embodiments and their descriptions are used to explain this embodiment and do not constitute an improper limitation of this embodiment.

[0020] Figure 1This is a flowchart of the source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan in Embodiment 1 of the present invention; Figure 2 This is a detailed schematic diagram illustrating the steps of the source-load-storage coordinated active support control method under the off-grid mode of the transformer area plan in Embodiment 1 of the present invention; Figure 3 This is a structural block diagram of the source-load-storage collaborative active support control system under the off-grid mode of the transformer area plan in Embodiment 2 of the present invention. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0023] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0024] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.

[0025] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0026] Example 1 Embodiment 1 of the present invention introduces a source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan.

[0027] like Figure 1 The method for source-load-storage collaborative active support control under the off-grid mode of transformer area planning, as shown, includes: Obtain grid connection data information for photovoltaic, energy storage, and charging stations; Off-grid risk of photovoltaic energy storage charging stations based on data information obtained from gradient boosting tree model prediction; When the obtained off-grid risk prediction value exceeds the risk threshold, the state of charge of energy storage is calculated based on particle swarm optimization algorithm, and photovoltaic power is predicted based on support vector regression, and off-grid switching is performed. During off-grid switching, an energy storage state of charge-frequency control model is constructed based on the energy storage state of charge and photovoltaic power prediction values ​​to dynamically adjust the voltage-frequency of the charging station and enter off-grid operation. When operating off-grid, the charging station is optimized and scheduled by predicting the charging load until power balance is achieved and the grid connection recovery phase begins. During the grid connection recovery phase, a smooth switching control between off-grid and grid-connected operation is performed based on the second-order low-pass filter smooth switching method until grid-connected operation is achieved, thus completing the source-load-storage coordinated active support control.

[0028] The specific steps of the source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan in this embodiment are as follows: Figure 2 As shown, during the grid connection phase, off-grid risk prediction is performed using grid operation data, meteorological information, and maintenance plans. A heuristic algorithm is used to determine the optimal State of Charge (SOC) of the energy storage system within the range of 70% to 90%, while adjusting photovoltaic power and module angle based on solar irradiance prediction. Secondly, during off-grid switching, a dynamic voltage and frequency adjustment is achieved by constructing a SOC-frequency control model for the energy storage converter. Subsequently, during off-grid operation, the charging load for the next hour is predicted on a rolling basis, and charging scheduling is optimized using linear programming. Finally, in operation monitoring and grid connection recovery, a combination of heuristic and smooth switching algorithms is used to keep voltage and frequency fluctuations within a reasonable range, ultimately achieving proactive support control through source-load-storage collaboration.

[0029] In off-grid risk prediction, grid voltage is collected. U t ,frequency f t Active power flow P t Reactive power flow Q t Meteorological data W t and maintenance plan M t Construct feature vectors X t ;Right now .

[0030] The gradient boosting tree (GBDT) model is used to predict the probability of churn risk; that is... ;in, P (Offline) represents the probability of the risk of being offline. P When (offline) > δ, enter the offline preparation mode, where δ is the threshold, usually taken as 0.7.

[0031] Based on the estimated off-grid duration T off and meet the needs L t The PSO algorithm is used to solve the SOC objective, i.e. ;in, E SOC For the available energy storage capacity, the constraints are as follows: .

[0032] This embodiment uses the SVR model to predict light intensity. I t Receive photovoltaic power P PV ( t ),Right now ;in, η PV For conversion efficiency, A The photovoltaic area is determined; then, the tilt angle and power limit of the photovoltaic modules are adjusted according to the forecast results to avoid sudden power changes during switching.

[0033] At the moment of disconnection from the grid, the energy storage converter enters active grid-connection mode, and the bus frequency setpoint is determined by the State of Charge (SOC). ;in, k For adjustment coefficients, SOC ref For reference only, we take 50%-70% here. f rated The reference frequency is 50Hz.

[0034] The energy storage converter employs fuzzy adaptive PID control, where the PID parameters are dynamically adjusted by a BP neural network based on operating data to achieve adaptive optimization. ;in, e ( t )= f ref - f ( t ).

[0035] Charging load forecasting utilizes a Long Short-Term Memory (LSTM) network model, predicting the charging load for the next hour every 15 minutes. ;in, X hist Input features include historical load, travel data, and weather data.

[0036] In the scheduling optimization process, charging scheduling is optimized using mixed-integer linear programming (MILP), with the objective function being: Total load is The constraints are: ;in, x k,t Indicates electric vehicles k exist t Charging status during a given time period: 1 for charging, 0 for not charging. P k Indicates the charging power of a single electric vehicle. E k req This indicates the electricity demand of a single electric vehicle.

[0037] This embodiment employs a priority load-limiting strategy to ensure power balance, prioritizing the cutting off of non-critical loads. The power balance equation in the priority load-limiting strategy is as follows: ;in, H For removable load sets, P j cut For load j The resection power, Δ P deficit For power deficits, the priority of load cut-off is sorted in ascending order of load importance coefficient.

[0038] This embodiment uses a second-order low-pass filter for smooth switching control, ensuring voltage fluctuations during switching are ≤2%, thus smoothing out grid connection impacts. The formula for the second-order low-pass filter is as follows: ;in, ω n =10πrad / s, representing the cutoff frequency. ζ =0.707, which represents the damping ratio.

[0039] Discretization is performed using a second-order low-pass filter, i.e. ;in, x n For grid connection instructions, x n ∈{0,1}, where 1 represents a grid connection command and 0 represents a non-grid connection command. y n This is the smoothed switching signal.

[0040] In this embodiment, the model is trained with the latest incremental data every 24 hours, and the prediction model parameters are updated online. The update mechanism is as follows: ;in, D window For rolling time window data, η Represents the learning rate in LSTM. η= 0.001.

[0041] During off-grid operation, key operating parameters are continuously monitored. If an overload risk is detected, a heuristic load-limiting strategy incorporating priority constraints is activated to ensure voltage fluctuations do not exceed ±5% and frequency fluctuations do not exceed ±0.2Hz, maintaining system stability. When reconnection to the grid is required, a second-order low-pass filter smoothing switching algorithm is employed to achieve seamless, shock-free synchronization and connection between the microgrid and the main grid, ensuring a smooth transition. Furthermore, incremental data generated during system operation is automatically used to update predictive models and control parameters, continuously improving the system's adaptability to future operating conditions and control accuracy.

[0042] This embodiment effectively overcomes problems such as overcharging and over-discharging of energy storage, uncertainty of electric vehicle charging load, and disconnect between grid-connected and off-grid operation in traditional off-grid control, achieving coordinated and optimized control of photovoltaic, energy storage, and charging loads. Its application scenarios cover planned off-grid distribution areas, microgrids, islanded power supply areas, and distribution network environments with a high proportion of renewable energy. While improving power supply continuity and reliability, it also considers extending equipment lifespan and improving renewable energy utilization efficiency, which is of great significance for smart grid construction and the optimization of electric vehicle charging infrastructure.

[0043] Example 2 Embodiment 2 of the present invention introduces a source-load-storage collaborative active support control system under the off-grid mode of the transformer area plan.

[0044] like Figure 3 The source-load-storage collaborative active support control system shown in the diagram, under the off-grid mode of the transformer area plan, includes: The grid-connected operation module is configured to acquire grid-connected data information of the photovoltaic-storage-charging station; predict the off-grid risk of the acquired photovoltaic-storage-charging station based on the gradient boosting tree model; and when the obtained off-grid risk prediction value exceeds the risk threshold, calculate the state of charge of the energy storage based on the particle swarm optimization algorithm, predict the photovoltaic power based on support vector regression, and perform off-grid switching. The off-grid switching module is configured to construct an energy storage state of charge-frequency control model based on the energy storage state of charge and photovoltaic power prediction values, dynamically adjust the voltage-frequency of the charging station, and enter off-grid operation. The off-grid operation module is configured to optimize the scheduling of charging stations by predicting the charging load until power balance is achieved and the grid-connected recovery phase begins. The grid-connected recovery module is configured to perform smooth switching control between off-grid and grid-connected operation based on a second-order low-pass filter smooth switching method until grid-connected operation is achieved, thus completing the source-load-storage coordinated active support control.

[0045] The detailed steps are the same as those of the source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan provided in Example 1, and will not be repeated here.

[0046] Example 3 Embodiment 3 of the present invention provides a computer-readable storage medium.

[0047] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the source-load-storage coordinated active support control method under the off-grid mode of the transformer area plan as described in Embodiment 1 of the present invention.

[0048] The detailed steps are the same as those of the source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan provided in Example 1, and will not be repeated here.

[0049] Example 4 Embodiment 4 of the present invention provides an electronic device.

[0050] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the source-load-storage coordinated active support control method under the off-grid mode of the transformer area plan as described in Embodiment 1 of the present invention.

[0051] The detailed steps are the same as those of the source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan provided in Example 1, and will not be repeated here.

[0052] Example 5 Embodiment 5 of the present invention provides a computer program product.

[0053] A computer program product includes software code, wherein the program in the software code performs the steps of the source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan as described in Embodiment 1 of the present invention.

[0054] The detailed steps are the same as those of the source-load-storage collaborative active support control method under the off-grid mode of the transformer area plan provided in Example 1, and will not be repeated here.

[0055] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0056] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0057] 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.

[0058] 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.

[0059] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0060] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0061] The above description is merely a preferred embodiment of this practice and is not intended to limit the scope of this practice. Various modifications and variations can be made to this practice by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this practice should be included within the protection scope of this practice.

Claims

1. A source-load-storage collaborative active support control method in a planning off-grid mode of a transformer area, characterized in that, The method comprises the following steps: acquiring grid-connected data information of the photovoltaic energy storage charging station; predicting off-grid risk of the photovoltaic energy storage charging station based on a gradient boosting tree model according to the acquired data information; when the obtained off-grid risk prediction value exceeds a risk threshold, calculating a state of charge of the energy storage based on a particle swarm optimization algorithm, predicting photovoltaic power based on a support vector regression, and performing off-grid switching; when the off-grid switching is performed, constructing an energy storage state of charge-frequency control model according to the state of charge of the energy storage and the prediction value of the photovoltaic power, dynamically adjusting voltage-frequency of the charging station, and entering off-grid operation; when the off-grid operation is performed, performing optimal scheduling of the charging station by predicting charging load until power balance is achieved, and entering a grid-connected recovery stage; when the grid-connected recovery stage is entered, performing smooth switching control between off-grid operation and grid-connected operation based on a second-order low-pass filter smooth switching method until grid-connected operation is achieved, and completing source-load-storage collaborative active support control.

2. The source-load-storage collaborative active support control method in the off-grid mode of a transformer area planning according to claim 1, characterized in that, In the process of predicting the off-grid risk of the obtained data information of the photovoltaic storage and charging station based on the gradient boosting tree model, by obtaining grid-connected data information of the photovoltaic storage and charging station, the obtained grid-connected data information at least includes grid voltage U t , frequency f t , active power flow P t , reactive power flow Q t , weather data W t and maintenance plan M t ; according to the obtained grid-connected data information, a feature vector is constructed X t , that is ; by the gradient boosting tree model and the feature vector, the probability prediction of the off-grid risk is carried out; that is, the off-grid risk probability is .

3. The source-load-storage collaborative active support control method in the off-grid mode of a transformer area planning according to claim 1, characterized in that, At the moment of off-grid operation, the energy storage converter enters the active grid forming mode, and the bus frequency is set based on the state of charge of the energy storage; that is, the bus set frequency For ; wherein, k is the adjustment coefficient, SOC ref is the energy storage state of charge reference value, is the energy storage state of charge, f rated is the reference frequency.

4. The source-load storage collaborative active support control method in the off-grid mode of a transformer area planning according to claim 1, characterized in that, In the process of optimal scheduling of the charging station, optimal charging scheduling is performed by a mixed integer linear programming, and a difference between a maximum value and a minimum value of the prediction value of the charging load is taken as an objective function for optimal charging scheduling, so as to obtain total charging load.

5. The source-load storage collaborative active support control method in the off-grid mode of a transformer area planning according to claim 1, characterized in that, The priority load limiting strategy is adopted to guarantee power balance, that is ; wherein, H is a set of removable loads, P j cut is the removal power of the load j , Δ P deficit is a power shortage, and the removal priority is sorted in ascending order of the load importance coefficient to preferentially remove non-critical loads.

6. The source-load storage collaborative active support control method in the off-grid mode of a transformer area planning according to claim 1, characterized in that, The second order low pass filter To ; wherein, denotes the cutoff frequency, denotes the damping ratio.

7. A source-load-storage collaborative active support control system in a planning off-grid mode of a transformer area, characterized in that, The method comprises the following steps: a grid-connected operation module configured to acquire grid-connected data information of the photovoltaic energy storage charging station; predicting off-grid risk of the photovoltaic energy storage charging station based on a gradient boosting tree model according to the acquired data information; when the obtained off-grid risk prediction value exceeds a risk threshold, calculating a state of charge of the energy storage based on a particle swarm optimization algorithm, predicting photovoltaic power based on a support vector regression, and performing off-grid switching; an off-grid switching module configured to construct an energy storage state of charge-frequency control model according to the state of charge of the energy storage and the prediction value of the photovoltaic power, dynamically adjust voltage-frequency of the charging station, and enter off-grid operation; an off-grid operation module configured to perform optimal scheduling of the charging station by predicting charging load until power balance is achieved, and enter a grid-connected recovery stage; a grid-connected recovery module configured to perform smooth switching control between off-grid operation and grid-connected operation based on a second-order low-pass filter smooth switching method until grid-connected operation is achieved, and complete source-load-storage collaborative active support control.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the steps of the source-load-storage collaborative active support control method in the off-grid mode of the transformer area as claimed in any one of claims 1-6.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, The processor executes the program to realize the steps of the source-load-storage collaborative active support control method in the off-grid mode of the transformer area as claimed in any one of claims 1-6.

10. A computer program product comprising software code, characterized in that, The program in the software code executes the steps of the source-load-storage collaborative active support control method in the off-grid mode of the transformer area as claimed in any one of claims 1-6.

Images