Method and device for operating a distributed energy generation system

Abstract

The application provides an operation control method and device of a distributed energy power generation system, and belongs to the technical field of energy power generation. The method comprises the following steps: acquiring environmental parameters, first electrical parameters of a distributed energy power generation system and second electrical parameters of a load device within a preset time; inputting the above parameters into a three-dimensional dynamic digital twin, obtaining an influence source of voltage fluctuation, a sensitive node of voltage fluctuation and an influence level corresponding to the sensitive node according to a simulation result; adjusting duty cycles of each port of a multi-port solid-state transformer based on the influence source of voltage fluctuation, the sensitive node of voltage fluctuation and the influence level corresponding to the sensitive node; and regulating the operation state of the distributed energy power generation system based on the duty cycles of each port of the multi-port solid-state transformer. The application can quickly adjust the duty cycles of each port when voltage fluctuation occurs, maintain voltage stability and ensure the power safety of the load.

Description

Technical Field

[0001] This application belongs to the field of energy power generation technology, and more specifically, relates to an operation control method and device for a distributed energy power generation system. Background Technology

[0002] With the acceleration of the global energy transition, distributed energy generation systems have become a core component of smart grids and microgrids due to their advantages such as cleanliness, flexibility, and local consumption. However, the complementary nature of distributed energy sources (such as the intermittent power supply of wind and solar power) and their multi-node interconnection structure make the system susceptible to environmental parameters and load equipment, leading to abnormal voltage fluctuations that seriously affect power quality and equipment safety. Summary of the Invention

[0003] To address the aforementioned issues, this application provides an operation control method and apparatus for a distributed energy generation system, which can rapidly reduce voltage fluctuations and ensure stable system operation by adjusting the duty cycle of each port of a solid-state transformer.

[0004] A first aspect of this application provides an operation control method for a distributed energy generation system, applied to a distributed energy generation system, the system including a multi-port solid-state transformer and multiple energy modules of different energy types; each input port of the multi-port solid-state transformer is connected to an energy module; the method includes:

[0005] The system acquires environmental parameters, first electrical parameters of the distributed energy generation system, and second electrical parameters of the load equipment within a preset time period. The first electrical parameters include the electrical parameters corresponding to each of the energy modules of different energy types.

[0006] Environmental parameters, first electrical parameters, and second electrical parameters are input into a three-dimensional dynamic digital twin. Based on the simulation results of the three-dimensional dynamic digital twin, the sources of voltage fluctuation, sensitive nodes of voltage fluctuation, and the corresponding impact levels of sensitive nodes are obtained.

[0007] Based on the sources of voltage fluctuations, the sensitive nodes of voltage fluctuations, and the impact levels corresponding to the sensitive nodes, the operating strategy for the distributed energy generation system is determined to be adjusting the duty cycle of each port of the multi-port solid-state transformer.

[0008] The operating status of distributed energy generation systems is regulated based on the operating strategy of the distributed energy generation system.

[0009] A second aspect of this application provides an operation control device for a distributed energy generation system, applied to a distributed energy generation system, the system including a multi-port solid-state transformer and multiple energy modules of different energy types; each input port of the multi-port solid-state transformer is connected to an energy module; the device includes:

[0010] The data acquisition unit is used to acquire environmental parameters, first electrical parameters of the distributed energy generation system, and second electrical parameters of the load equipment within a preset time period; the first electrical parameters include the electrical parameters corresponding to each of multiple energy modules of different energy types.

[0011] The first data processing unit is used to input environmental parameters, first electrical parameters, and second electrical parameters into the three-dimensional dynamic digital twin, and obtain the source of voltage fluctuation, the sensitive node of voltage fluctuation, and the influence level corresponding to the sensitive node based on the simulation results of the three-dimensional dynamic digital twin.

[0012] The second data processing unit is used to determine the operation strategy of the distributed energy generation system based on the source of voltage fluctuation, the sensitive node of voltage fluctuation, and the impact level of the sensitive node, which is to adjust the duty cycle of each port of the multi-port solid-state transformer.

[0013] The control unit is used to control the operating status of the distributed energy generation system based on the operating strategy of the distributed energy generation system.

[0014] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described operation control method for a distributed energy generation system.

[0015] In a fourth aspect of this application, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described operation control method for a distributed energy generation system.

[0016] The beneficial effects of the operation control method and apparatus for distributed energy generation systems provided in this application are as follows:

[0017] This application embodiment reproduces the operating state of a distributed energy system using a three-dimensional dynamic digital twin. Based on input multi-source data, it effectively predicts the voltage fluctuation amplitude, duration, and propagation path within a first time period, thereby quickly locating the influencing source and sensitive nodes, and assessing the impact level of the sensitive nodes. Based on the influencing source, the sensitive node experiencing voltage fluctuations, and the impact level of that sensitive node, the duty cycle of each port of the multi-port solid-state transformer is dynamically adjusted to achieve balanced power distribution, stabilize the load-side voltage, and reduce the impact of voltage fluctuations on the load-side electrical equipment. This application embodiment can significantly improve the power supply quality of the distributed energy system, maintain stable system operation and anti-interference capabilities, and optimize energy utilization efficiency. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the structure of a distributed energy generation system provided in an embodiment of this application;

[0020] Figure 2 A flowchart illustrating the operation control method of a distributed energy generation system provided in an embodiment of this application;

[0021] Figure 3 A structural block diagram of an operation control device for a distributed energy generation system provided in an embodiment of this application;

[0022] Figure 4 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0023] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0025] Figure 1 This is a schematic diagram of a distributed energy generation system 100 provided in one embodiment of this application. The distributed energy generation system 100 is used to supply power to load devices 200. Load devices 200 can be electrical devices within the power grid or single electrical devices existing independently of the power grid. The electricity demand of these devices fluctuates and is not constant. For example, the load of residential power grids has obvious seasonal and periodic characteristics; electricity consumption during the day in summer is significantly greater than that during the night in winter, exhibiting a clear peak-and-trough effect. Similarly, a single electrical device may exist in various states such as startup, stable operation, and standby, and the electricity load will differ in different states. Therefore, the aforementioned load devices 200 are fluctuating loads, requiring the distributed energy generation system 100 to meet these fluctuations while minimizing costs.

[0026] Therefore, refer to Figure 1This application provides a distributed energy generation system 100, which includes a multi-port solid-state transformer 110, a control module 120, and multiple energy modules of different energy types. These multiple energy modules of different energy types include, but are not limited to, at least two of the following: a photovoltaic power generation module 130, a wind power generation module 140, a gas-fired power generation module 150, an oil-fired power generation module 160, or an energy storage module 170. Figure 1 The system shown includes five different energy modules: a photovoltaic power generation module 130, a wind power generation module 140, a gas power generation module 150, an oil power generation module 160, and an energy storage module 170. Each input port of the multi-port solid-state transformer 110 is connected to an energy module; that is, the multiple input ports of the multi-port solid-state transformer 110 are respectively connected to the photovoltaic power generation module 130, the wind power generation module 140, the gas power generation module 150, the oil power generation module 160, and the energy storage module 170. The control port of the multi-port solid-state transformer 110 is connected to the control module 120, and the output port is connected to the load device 200. The control module 120 is also connected to multiple data acquisition devices (…). Figure 1 (Not shown in the diagram) A network of multiple data acquisition devices is used to collect environmental data, first electrical parameters of the distributed energy generation system 100, and second electrical parameters of the load device 200. The first electrical parameters include the electrical parameters corresponding to each of the multiple energy modules of different energy types. The aforementioned distributed energy generation system 100 can stably supply power to the load device 200 with the electrical energy output from the energy modules.

[0027] The aforementioned photovoltaic power generation module 130 is used to convert solar energy into electrical energy using the photovoltaic effect. Photovoltaic power generation employs solar panels composed of multiple solar cells containing photovoltaic materials. Multiple photovoltaic modules containing solar panels are connected in series and parallel, together with a supporting structure and an inverter, to form a photovoltaic array.

[0028] The wind power generation module 140 converts wind energy into mechanical energy through aerodynamic principles, and then into electrical energy through a generator. It mainly consists of a wind turbine unit, a transmission unit, a generator, and a control unit.

[0029] The gas-fired power generation module 150 uses combustible gases such as natural gas and biogas as fuel, and generates electricity by driving a generator through an internal combustion engine or gas turbine. It features fast start-up and low pollution. The gas-fired power generation module 150 mainly consists of a gas supply unit, a combustion unit, a generator, and a waste heat recovery unit.

[0030] The fuel-fired power generation module 160 uses fuel (such as diesel, gasoline, heavy oil, etc.) as fuel. It converts the chemical energy of the fuel into mechanical energy through power devices such as internal combustion engines and gas turbines, and then converts the mechanical energy into electrical energy through a generator. This module features rapid start-up, a small footprint, and relatively convenient fuel access, and is widely used in emergency power supply scenarios.

[0031] The energy storage module 170 is connected to the power grid for storing electrical energy. The energy storage module 170 may consist of one or more of the following: a lithium-ion battery; a lead-acid battery; or a supercapacitor.

[0032] A distributed energy generation system corresponding to the above embodiment, Figure 2 This is a flowchart illustrating an operation control method for a distributed energy generation system according to an embodiment of this application. (Refer to...) Figure 2 The operation control method may include S101~S104.

[0033] S101: Obtain environmental parameters, the first electrical parameters of the distributed energy generation system, and the second electrical parameters of the load equipment within a preset time period.

[0034] In this embodiment, the preset time refers to a time interval pre-set before the data acquisition operation is performed. This time interval defines the time range for the environmental parameters, the first electrical parameter, and the second electrical parameter to be acquired, ensuring the timeliness and relevance of the data to the current operating status. For example, it can be set to "within the past 10 minutes," and the specific duration can be set according to seasonal characteristics, the periodic characteristics of the electricity load, or other conditions. The parameter data in this embodiment can be collected by multiple data acquisition devices, including temperature and humidity sensors, light intensity sensors, and anemometers that can collect environmental data; voltage sensors, current sensors, and temperature sensors that can collect the first electrical parameter of the distributed energy system; and power monitoring instruments that can collect the second electrical parameter of the load equipment.

[0035] In this embodiment, the environmental parameters refer to external conditions affecting the operation of the distributed energy system, including but not limited to light intensity, wind speed, temperature, humidity, and pressure. The first electrical parameter reflects the operating status of the energy modules within the system, including but not limited to the output voltage and output power of each energy module. The second electrical parameter describes the power demand and power quality on the load side, including but not limited to harmonic components of voltage / current, active power, reactive power, and power factor. Load devices on the load side include industrial loads, commercial loads, residential loads, and special loads (such as hospitals, communication base stations, etc.).

[0036] S102: Input the environmental parameters, the first electrical parameter, and the second electrical parameter into the three-dimensional dynamic digital twin. Based on the simulation results of the three-dimensional dynamic digital twin, obtain the source of voltage fluctuation, the sensitive node of voltage fluctuation, and the influence level corresponding to the sensitive node.

[0037] In this embodiment, the three-dimensional dynamic digital twin is a virtual mirror of the physical distributed energy generation system. By integrating multi-source data (environmental parameters, first electrical parameters, and second electrical parameters), physical mechanism models (such as electromagnetic transient simulation models), and data-driven models, real-time simulation and prediction of the system's operating state are achieved. The electromagnetic transient simulation model is a mathematical model that simulates short-timescale (microsecond to millisecond) electromagnetic phenomena in the power generation system, used to reproduce the dynamic behavior of power equipment during transient processes (e.g., voltage surges / dips). The data-driven model is used to obtain predicted data within a first time period based on the aforementioned multi-source data, and based on the predicted data, to determine the sources of voltage fluctuations, sensitive nodes of voltage fluctuations, and the corresponding impact levels of sensitive nodes.

[0038] In other words, after inputting environmental parameters, the first electrical parameter, and the second electrical parameter into a three-dimensional dynamic digital twin, the digital twin reproduces the voltage fluctuation phenomenon of the distributed energy generation system through virtual simulation. Based on multi-source data, it predicts the voltage fluctuation amplitude, duration, and propagation path within a first time period. Finally, based on the above predicted data, the source of voltage fluctuation and the sensitive nodes can be obtained. According to the equipment characteristics corresponding to the sensitive nodes and the voltage fluctuation amplitude, the impact level corresponding to the sensitive nodes can be obtained. These parameters help the system adjust its control strategy in a timely manner, reduce the impact of voltage fluctuations on load equipment, and significantly improve the power supply quality and operational stability of the system.

[0039] S103: Based on the sources of voltage fluctuation, the sensitive nodes of voltage fluctuation, and the impact level of the sensitive nodes, the operating strategy of the distributed energy generation system is determined to be adjusting the duty cycle of each port of the multi-port solid-state transformer.

[0040] In this embodiment, the source of voltage fluctuation can be an internal source or an external source. The internal source can be the switching operation of the energy module or the multi-port solid-state transformer, while the external source can be sudden changes in environmental parameters, the addition of load devices, etc.

[0041] For example, if the source of voltage fluctuations is the photovoltaic (PV) power module (its power output is affected when sunlight is blocked by clouds), then the output power of other energy modules can be increased or other energy modules can be used to power the load. The same principle applies if the source of voltage fluctuations is the wind power module. Voltage fluctuations can also be caused by the load equipment itself; when a high-power device is suddenly connected to the load equipment within a certain period, the required voltage on the load side increases.

[0042] Voltage fluctuation sensitive nodes are the locations in the system that respond most significantly to voltage fluctuations, typically exhibiting large voltage deviation amplitudes, high fluctuation frequencies, or long durations. Voltage fluctuation sensitive nodes can be port nodes of multi-port solid-state transformers, critical load bus nodes, edge load nodes, or energy storage module interface nodes, etc. By identifying voltage fluctuation sensitive nodes, the corresponding equipment can be accurately identified, and the impact level of the node can be calculated based on the importance coefficient of the equipment at that node and the corresponding voltage fluctuation amplitude. After determining the source of voltage fluctuations, sensitive nodes, and their corresponding impact levels, a mapping relationship of "duty cycle - port power - node voltage" can be established using electromagnetic transient models or historical data fitting methods. This allows for timely adjustment of the output power of each energy module and the duty cycle of each port connected to the multi-port solid-state transformer, ensuring stable voltage on the load side.

[0043] S104: Regulate the operating status of distributed energy generation systems based on the operating strategies of distributed energy generation systems.

[0044] In this embodiment, after determining the operating strategy of the distributed energy generation system, the control module sends instructions to the multi-port solid-state transformer to dynamically adjust the on-time ratio (i.e., duty cycle) of the switching devices at each port, thereby changing the power distribution at each port. For example, when the photovoltaic power generation module experiences a sudden drop in light intensity, resulting in a low voltage on the primary load bus (sensitive node, high impact level), it is necessary to reduce the duty cycle of the photovoltaic port of the multi-port solid-state transformer, or set the duty cycle of that port to zero, stopping the photovoltaic power generation module from supplying power to the load equipment and reducing voltage fluctuations; at the same time, the duty cycle of the gas-fired power generation port is increased to make up for the power gap. When the wind power generation module experiences DC bus overvoltage due to increased wind force, the duty cycle of the wind power generation port is reduced to limit the input, and the charging duty cycle of the energy storage port is increased to absorb excess power.

[0045] As can be seen from the above, the embodiments of this application reproduce the operating state of the distributed energy system through a three-dimensional dynamic digital twin, and effectively predict the voltage fluctuation amplitude, duration, and propagation path within a first time period based on the input multi-source data, thereby quickly locating the influencing source and sensitive nodes, and assessing the impact level of the sensitive nodes. Based on the influencing source, the sensitive node of voltage fluctuation, and the impact level of the sensitive node, the duty cycle of each port of the multi-port solid-state transformer is dynamically adjusted to achieve balanced power distribution, stabilize the load-side voltage, and reduce the impact of voltage fluctuations on the load-side electrical equipment. The embodiments of this application can significantly improve the power supply quality of the distributed energy system, maintain the stable operation and anti-interference capability of the system, and optimize energy utilization efficiency.

[0046] In one embodiment of this application, regulating the operating state of a distributed energy generation system based on its operating strategy includes:

[0047] The sources of voltage fluctuation, the sensitive nodes of voltage fluctuation, and the influence levels of the sensitive nodes are input into the reinforcement learning model to obtain the power distribution of each port of the multi-port solid-state transformer.

[0048] The target optimization strategy is obtained by adjusting the operation strategy of the distributed energy generation system based on the power allocation;

[0049] The operation status of distributed energy generation systems is regulated based on target optimization strategies.

[0050] In this embodiment, the initial operating strategy of the distributed energy generation system may prioritize addressing voltage fluctuations, but may neglect other issues. For example, to reduce losses in multi-port solid-state transformers, the initial strategy may limit the duty cycle adjustment range, but this may not completely suppress voltage fluctuations. Therefore, it is necessary to find a globally optimal solution among multiple objectives such as voltage quality, equipment lifespan, and system efficiency through optimization.

[0051] In this embodiment, the sources of voltage fluctuation, the sensitive nodes of voltage fluctuation, and the influence levels corresponding to the sensitive nodes are input into the reinforcement learning model to obtain the power allocation of each port of the multi-port solid-state transformer, including:

[0052] The sources of voltage fluctuation, the sensitive nodes of voltage fluctuation, and the influence levels corresponding to the sensitive nodes are input into the global coordinator of the reinforcement learning model to calculate the evaluation value of the objective function. The combination of weight coefficients that minimizes the evaluation value is determined as the target weight coefficient combination.

[0053] The priority of each port of a multi-port solid-state transformer is determined based on the combination of target weight coefficients;

[0054] The priority and real-time status information of each port of the multi-port solid-state transformer are input into the local controller of the reinforcement learning model to obtain the power allocation of each port of the multi-port solid-state transformer; the real-time status information of each port includes the electrical parameters of each energy module.

[0055] In this embodiment, the reinforcement learning model is a machine learning model that achieves dynamic optimization through "state awareness-action decision-reward feedback." Its core is to gradually adjust the strategy to maximize long-term cumulative rewards through interactive learning between the agent and the environment. In this embodiment, the reinforcement learning model is a two-layer reinforcement learning structure (global coordinator + local controller) used to solve the dynamic optimization problem of distributed energy generation systems among multiple objectives such as "voltage quality," "equipment lifespan," and "system efficiency." The model learns the mapping relationship between "influence source-sensitive node-influence level" and "power allocation," ultimately generating the optimal duty cycle adjustment strategy for multi-port solid-state transformers.

[0056] The global coordinator takes the sources of voltage fluctuations, sensitive nodes of voltage fluctuations, and the corresponding impact levels of sensitive nodes as inputs from the 3D dynamic digital twin. It uses total power balance constraints and equipment safety constraints as global constraints to output the priority of each port of the multi-port solid-state transformer. The total power balance constraint indicates that the sum of the output power / voltage of multiple energy modules in the system equals the total power / voltage demand of the load equipment. The equipment safety constraint indicates that each energy module is within a safe range; for example, the safe range of the State of Charge (SOC) of the energy storage module is [SOC1, SOC2] (e.g., [20%, 80%]), and the minimum operating power of the gas-fired power generation module is greater than a preset percentage of its rated power (e.g., 10%).

[0057] The optimization objective of the global coordinator is to minimize the evaluation value of the objective function, which is expressed as:

[0058]

[0059] in, Let be the objective function. The weighting factor is for voltage stability. The total number of sensitive nodes. The actual voltage deviation of the i-th sensitive node. The maximum voltage deviation of the i-th sensitive node. These are the weighting factors for power balance. Total number of ports The actual charge / discharge power of the j-th port. Let be the rated power of the j-th port.

[0060] When the evaluation value of the objective function is minimized, we can obtain... and The value is based on and The value of can determine the contribution of each port to the objective function evaluation value, and the priority of each port of the multi-port solid-state transformer is determined according to the ranking of contribution values. For example, a multi-port solid-state transformer includes a photovoltaic power generation port, an energy storage port, and a gas-fired power generation port, and the contribution values ​​of the above ports to the objective function evaluation value are a1, a2, and a3, respectively, where a2 > a1 > a3. Then the priority of the energy storage port is > the priority of the photovoltaic power generation port > the priority of the gas-fired power generation port.

[0061] The local controller takes the priority and real-time status information of each port of the multi-port solid-state transformer as input, encodes the multi-dimensional real-time status information of each port into feature vectors, and outputs the power allocation of each port through a deep reinforcement learning policy network (such as DDPG, PPO). For example, when the weight coefficient of voltage stability is greater than the weight coefficient of power balance, the local controller prioritizes adjusting the duty cycle of the photovoltaic power generation port to suppress voltage fluctuations, while the energy storage port adjusts the charging / discharging power according to the SOC; at the same time, it corrects the action through hard constraints (such as duty cycle range limit, which cannot exceed the range [0,1]) to ensure compliance with the physical limitations of the equipment; finally, it outputs the power allocation of each port (i.e., the correction action).

[0062] This embodiment obtains the power allocation of each port based on the global coordinator and the local controller, and adjusts the duty cycle of each port to obtain the target optimization strategy based on the power allocation of each port. The operation state of the distributed energy generation system is regulated based on the target optimization strategy, which can provide a clear direction for the dynamic and adaptive control of multi-port solid-state transformers in complex power grid environments and improve the stability of the system.

[0063] In one embodiment of this application, the operation control method further includes:

[0064] If the power allocation output by the local controller does not meet the constraints, the power allocation is corrected using the gradient descent method to obtain the corrected power allocation.

[0065] In this embodiment, gradient descent is a local optimization algorithm used to correct power allocation. Constraints refer to the physical operating limits or safety thresholds of the multi-port solid-state transformer and each energy module. Constraints include, but are not limited to, the duty cycle range of each port and the power threshold of each energy module. The duty cycle range of each port refers to the duty cycle of each port of the multi-port solid-state transformer being limited to the [0,1] interval (determined by hardware circuit characteristics; exceeding this range will cause equipment damage); the power limit refers to the charging / discharging power of each energy module (such as a photovoltaic power generation module or an energy storage module) not exceeding its rated power.

[0066] If the power distribution output of the local controller ( When the constraints are not met, the power allocation output of the local controller is first checked port by port to determine whether the constraints are violated. For power allocations that violate the constraints, a loss function is constructed for the "deviation between the power allocation and the constraint boundary". For example, if the constraint is the power threshold of each energy module, then the loss function is... for:

[0067]

[0068] Let L be the maximum power threshold of the j-th port, and let L be the sum of the loss functions of all ports.

[0069] The steps for gradient calculation and iterative correction are as follows:

[0070] Step 1: Calculate the gradient of the total loss function L with respect to the power allocation P. :

[0071]

[0072] Step 2: Adjust the power allocation along the opposite direction of the gradient:

[0073]

[0074] in The learning rate (controls the adjustment step size to avoid over-correction).

[0075] Step 3: Repeat steps 1 and 2 until the corrected power allocation is achieved. All constraints are satisfied, meaning L is 0.

[0076] Will satisfy the constraints As the final power allocation.

[0077] In this embodiment, when the power allocation output by the local controller violates the constraints, the power allocation is gradually adjusted along the opposite direction of the gradient by calculating the gradient of the loss function formed by the deviation between the power allocation and the constraint boundary, so that the corrected power allocation meets the constraints and the system operates stably.

[0078] In one embodiment of this application, the method for identifying voltage fluctuation sensitive nodes includes:

[0079] Calculate the sensitivity coefficient of each node voltage to the power of each port of the multi-port solid-state transformer, and determine the absolute value of the voltage deviation amplitude and the duration of the fluctuation under the disturbance scenario based on the source of voltage fluctuation.

[0080] The sensitivity coefficient, the absolute value of the voltage deviation amplitude, and the duration of the fluctuation are input into the node evaluation formula to obtain the evaluation score of each node.

[0081] The evaluation score of each node is compared with the first preset threshold, and the sensitive node of voltage fluctuation is determined based on the comparison result.

[0082] In this embodiment, the sensitivity coefficient is a parameter that quantifies the sensitivity of a node voltage to changes in the power at each port of a multi-port solid-state transformer. It reflects the rate of change of the node voltage when the port power fluctuates; a larger coefficient indicates that the node voltage is more significantly affected by the power at the corresponding port. The node evaluation formula is a mathematical expression used to comprehensively quantify the node's sensitivity to voltage fluctuations, which can be expressed as:

[0083]

[0084] This represents the evaluation score of the i-th node. , and These represent the sensitivity coefficient, the absolute value of the voltage deviation amplitude, and the duration of the fluctuation corresponding to the i-th node, respectively. , and Normalized values, dimensionless. , and They are respectively , and The corresponding weighting coefficients.

[0085] In this embodiment, if there is a node whose evaluation score is greater than the first preset threshold, then all nodes with scores greater than the first preset threshold are considered as sensitive nodes for voltage fluctuations.

[0086] As can be seen from the above, by comprehensively considering the sensitivity coefficient, voltage deviation amplitude, and duration, a quantitative assessment of sensitive nodes can be achieved, avoiding misjudgments caused by a single indicator, ensuring that the identified nodes are truly key locations that respond significantly to voltage fluctuations, and providing an important basis for subsequent regulation.

[0087] In one embodiment of this application, the method for determining the impact level corresponding to a sensitive node includes:

[0088] The absolute value of the voltage deviation amplitude is determined based on a preset standard to determine its level.

[0089] The level of sensitivity of nodes is determined based on their importance.

[0090] The influence level of the sensitive node is obtained by multiplying the level of the absolute value of the voltage deviation amplitude.

[0091] In this embodiment, firstly, a voltage deviation amplitude range can be preset, for example, 0-5V is level 1, 5-10V is level 2, etc. Based on this standard, the level of the absolute value of the voltage deviation amplitude can be determined, quantifying the intensity of voltage fluctuations. Secondly, based on the importance of sensitive nodes (such as whether they are critical load nodes like hospitals or data centers), their own levels are preset (e.g., ordinary nodes are level 1, important nodes are level 2, and core nodes are level 3). Finally, the level of the sensitive node is multiplied by the level of the absolute value of the voltage deviation amplitude, and the result is the impact level corresponding to that sensitive node, thus comprehensively reflecting the degree of influence under the combined effect of node importance and voltage fluctuation intensity.

[0092] As can be seen from the above, this embodiment achieves a precise assessment of the impact of sensitive nodes by quantifying the voltage deviation amplitude and node importance in a hierarchical manner, thus avoiding the limitations of single-dimensional judgment.

[0093] In one embodiment of this application, the operation control method further includes:

[0094] The importance of each sensitive node is determined based on the load type connected to each sensitive node and its position in the topology of the 3D dynamic digital twin.

[0095] In this embodiment, different loads have significantly different requirements for power supply stability: for example, life support equipment in hospitals and core equipment rooms of communication base stations are classified as primary loads, with extremely low tolerance to voltage fluctuations, making the nodes they connect to highly important; while ordinary residential lighting loads are less sensitive to fluctuations, and the corresponding nodes are less important. From the topological relationship of the three-dimensional dynamic digital twin, the location of a sensitive node in the system determines its range of influence: when a sensitive node is a node between an energy module and a major load hub, a voltage fluctuation could lead to serious damage to the load, thus its importance is high; while the fluctuation impact range of end branch nodes is limited, and their importance is relatively low.

[0096] This embodiment can objectively quantify the importance of each sensitive node by combining the above two dimensions.

[0097] Corresponding to the operation control method of the distributed energy generation system in the above embodiment, Figure 3 This is a structural block diagram of an operation control device for a distributed energy generation system according to an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 3The operation control device 20 of the distributed energy generation system is applied to the distributed energy generation system, which includes a multi-port solid-state transformer and multiple energy modules of different energy types; each input port of the multi-port solid-state transformer is connected to an energy module. The device 20 includes: a data acquisition unit 21, a first data processing unit 22, a second data processing unit 23, and a control unit 24.

[0098] The data acquisition unit 21 is used to acquire environmental parameters, first electrical parameters of the distributed energy generation system, and second electrical parameters of the load equipment within a preset time period; the first electrical parameters include electrical parameters corresponding to each of multiple energy modules of different energy types.

[0099] The first data processing unit 22 is used to input environmental parameters, first electrical parameters and second electrical parameters into the three-dimensional dynamic digital twin, and obtain the source of voltage fluctuation, sensitive node of voltage fluctuation and the influence level corresponding to the sensitive node based on the simulation results of the three-dimensional dynamic digital twin.

[0100] The second data processing unit 23 is used to determine the operation strategy of the distributed energy generation system based on the source of voltage fluctuation, the sensitive node of voltage fluctuation and the influence level of the sensitive node, which is to adjust the duty cycle of each port of the multi-port solid-state transformer.

[0101] The control unit 24 is used to control the operating status of the distributed energy generation system based on the operating strategy of the distributed energy generation system.

[0102] In one embodiment of this application, the control unit 24 is specifically used for:

[0103] The sources of voltage fluctuation, the sensitive nodes of voltage fluctuation, and the influence levels of the sensitive nodes are input into the reinforcement learning model to obtain the power distribution of each port of the multi-port solid-state transformer.

[0104] The target optimization strategy is obtained by adjusting the operation strategy of the distributed energy generation system based on the power allocation;

[0105] The operation status of distributed energy generation systems is regulated based on target optimization strategies.

[0106] In one embodiment of this application, the control unit 24 is specifically used for:

[0107] The sources of voltage fluctuation, the sensitive nodes of voltage fluctuation, and the influence levels corresponding to the sensitive nodes are input into the global coordinator of the reinforcement learning model to calculate the evaluation value of the objective function. The combination of weight coefficients that minimizes the evaluation value is determined as the target weight coefficient combination.

[0108] The priority of each port of a multi-port solid-state transformer is determined based on the combination of target weight coefficients;

[0109] The priority and real-time status information of each port of the multi-port solid-state transformer are input into the local controller of the reinforcement learning model to obtain the power allocation of each port of the multi-port solid-state transformer; the real-time status information of each port includes the electrical parameters of each energy module.

[0110] In one embodiment of this application, the second data processing unit 23 is specifically used for:

[0111] Calculate the sensitivity coefficient of each node voltage to the power of each port of the multi-port solid-state transformer, and determine the absolute value of the voltage deviation amplitude and the duration of the fluctuation under the disturbance scenario based on the source of voltage fluctuation.

[0112] The sensitivity coefficient, the absolute value of the voltage deviation amplitude, and the duration of the fluctuation are input into the node evaluation formula to obtain the evaluation score of each node.

[0113] The evaluation score of each node is compared with the first preset threshold, and the sensitive node of voltage fluctuation is determined based on the comparison result.

[0114] In one embodiment of this application, the second data processing unit 23 is specifically used for:

[0115] The absolute value of the voltage deviation amplitude is determined based on a preset standard to determine its level.

[0116] The level of sensitivity of nodes is determined based on their importance.

[0117] The influence level of the sensitive node is obtained by multiplying the level of the absolute value of the voltage deviation amplitude.

[0118] In one embodiment of this application, the second data processing unit 23 is further configured to:

[0119] The importance of each sensitive node is determined based on the load type connected to each sensitive node and its position in the topology of the 3D dynamic digital twin.

[0120] In one embodiment of this application, the expression for the objective function is:

[0121]

[0122] in, Let be the objective function. The weighting factor is for voltage stability. The total number of sensitive nodes. The actual voltage deviation of the i-th sensitive node. The maximum voltage deviation of the i-th sensitive node. These are the weighting factors for power balance. Total number of ports The actual charge / discharge power of the j-th port. Let be the rated power of the j-th port.

[0123] In one embodiment of this application, the control unit 24 is further configured to:

[0124] If the power allocation output by the local controller does not meet the constraints, the power allocation is corrected using the gradient descent method to obtain the corrected power allocation.

[0125] In one embodiment of this application, the energy modules of multiple different energy types include at least two of the following:

[0126] Photovoltaic power generation modules, wind power generation modules, gas-fired power generation modules, oil-fired power generation modules, or energy storage modules.

[0127] See Figure 4 , Figure 4 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 4 The electronic device 300 shown in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. The processors 301 are configured to invoke the program instructions to execute the functions of the units in the above-described device embodiments, such as the functions of the data acquisition unit 21, the first data processing unit 22, the second data processing unit 23, and the control unit 24.

[0128] It should be understood that, in the embodiments of this application, the processor 301 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.

[0129] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0130] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory.

[0131] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the operation control method of the distributed energy power generation system provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0132] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0133] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0134] 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 application.

[0135] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0136] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0137] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0138] Furthermore, the functional units in the various embodiments of this application 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0139] The above are merely specific embodiments of this application, but the scope of protection of this application 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 this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for operating and controlling a distributed energy generation system, characterized in that, This invention is applied to a distributed energy generation system, which includes a multi-port solid-state transformer and multiple energy modules of different energy types; each input port of the multi-port solid-state transformer is connected to one of the energy modules. The method includes: The system acquires environmental parameters, first electrical parameters of the distributed energy generation system, and second electrical parameters of the load devices within a preset time period; the first electrical parameters include the electrical parameters corresponding to each of the multiple energy modules of different energy types. The environmental parameters, the first electrical parameter, and the second electrical parameter are input into a three-dimensional dynamic digital twin. Based on the simulation results of the three-dimensional dynamic digital twin, the sources of voltage fluctuation, the sensitive nodes of voltage fluctuation, and the influence levels corresponding to the sensitive nodes are obtained. Based on the sources of voltage fluctuation, the sensitive nodes of voltage fluctuation, and the impact level corresponding to the sensitive nodes, the operating strategy of the distributed energy generation system is determined to be adjusting the duty cycle of each port of the multi-port solid-state transformer. The operating status of the distributed energy generation system is regulated based on the operating strategy of the distributed energy generation system. The regulation of the operating state of the distributed energy generation system based on the operating strategy of the distributed energy generation system includes: The source of the voltage fluctuation, the sensitive node of the voltage fluctuation, and the influence level corresponding to the sensitive node are input into the reinforcement learning model to obtain the power allocation of each port of the multi-port solid-state transformer. The target optimization strategy is obtained by adjusting the operation strategy of the distributed energy generation system based on the power allocation; The operating status of the distributed energy generation system is regulated based on the target optimization strategy. The step of inputting the source of the voltage fluctuation, the sensitive node of the voltage fluctuation, and the influence level corresponding to the sensitive node into the reinforcement learning model to obtain the power allocation of each port of the multi-port solid-state transformer includes: The source of the voltage fluctuation, the sensitive node of the voltage fluctuation, and the influence level corresponding to the sensitive node are input into the global coordinator of the reinforcement learning model to calculate the evaluation value of the objective function. The combination of weight coefficients that minimizes the evaluation value is determined as the target weight coefficient combination. The priority of each port of the multi-port solid-state transformer is determined based on the target weight coefficient combination. The priority and real-time status information of each port of the multi-port solid-state transformer are input into the local controller of the reinforcement learning model to obtain the power allocation of each port of the multi-port solid-state transformer; the real-time status information of each port includes the electrical parameters of each energy module. The expression for the objective function is: in, Let be the objective function. The weighting factor is for voltage stability. The total number of sensitive nodes. The actual voltage deviation of the i-th sensitive node. The maximum voltage deviation of the i-th sensitive node. These are the weighting factors for power balance. Total number of ports The actual charge / discharge power of the j-th port. Let be the rated power of the j-th port.

2. The method as described in claim 1, characterized in that, The method for identifying sensitive nodes of voltage fluctuations includes: Calculate the sensitivity coefficient of each node voltage to the power of each port of the multi-port solid-state transformer, and determine the absolute value of the voltage deviation amplitude and the duration of the fluctuation under the disturbance scenario based on the source of voltage fluctuation. The sensitivity coefficient, the absolute value of the voltage deviation amplitude, and the duration of the fluctuation are input into the node evaluation formula to obtain the evaluation score of each node; The evaluation score of each node is compared with a first preset threshold, and the sensitive node of voltage fluctuation is determined based on the comparison result.

3. The method as described in claim 2, characterized in that, The methods for determining the impact level of the sensitive nodes include: The absolute value of the voltage deviation amplitude is determined based on a preset standard to determine its level. The level of the sensitive node is determined based on its importance. The influence level of the sensitive node is obtained by multiplying the level of the absolute value of the voltage deviation amplitude.

4. The method as described in claim 3, characterized in that, Also includes: The importance of each sensitive node is determined based on the load type connected to each sensitive node and the position of that sensitive node in the topology of the three-dimensional dynamic digital twin.

5. The method as described in claim 1, characterized in that, Also includes: If the power allocation output by the local controller does not meet the constraints, the power allocation is corrected by the gradient descent method to obtain the corrected power allocation.

6. The method as described in claim 1, characterized in that, The energy modules of the various different energy types include at least two of the following: Photovoltaic power generation modules, wind power generation modules, gas-fired power generation modules, oil-fired power generation modules, or energy storage modules.

7. An operation control device for a distributed energy generation system, characterized in that, This invention is applied to a distributed energy generation system, which includes a multi-port solid-state transformer and multiple energy modules of different energy types; each input port of the multi-port solid-state transformer is connected to one of the energy modules. The device includes: The data acquisition unit is used to acquire environmental parameters, first electrical parameters of the distributed energy generation system, and second electrical parameters of the load equipment within a preset time period; the first electrical parameters include the electrical parameters corresponding to each of the multiple energy modules of different energy types. The first data processing unit is used to input the environmental parameters, the first electrical parameters, and the second electrical parameters into a three-dimensional dynamic digital twin, and obtain the source of voltage fluctuation, the sensitive node of voltage fluctuation, and the influence level corresponding to the sensitive node based on the simulation results of the three-dimensional dynamic digital twin. The second data processing unit is used to determine the operating strategy of the distributed energy generation system as adjusting the duty cycle of each port of the multi-port solid-state transformer based on the source of the voltage fluctuation, the sensitive node of the voltage fluctuation, and the influence level corresponding to the sensitive node. The control unit is used to control the operating status of the distributed energy generation system based on the operating strategy of the distributed energy generation system. The control unit is specifically used for: The source of the voltage fluctuation, the sensitive node of the voltage fluctuation, and the influence level corresponding to the sensitive node are input into the reinforcement learning model to obtain the power allocation of each port of the multi-port solid-state transformer. The target optimization strategy is obtained by adjusting the operation strategy of the distributed energy generation system based on the power allocation; The operating status of the distributed energy generation system is regulated based on the target optimization strategy. The control unit (24) is specifically used for: The source of the voltage fluctuation, the sensitive node of the voltage fluctuation, and the influence level corresponding to the sensitive node are input into the global coordinator of the reinforcement learning model to calculate the evaluation value of the objective function. The combination of weight coefficients that minimizes the evaluation value is determined as the target weight coefficient combination. The priority of each port of the multi-port solid-state transformer is determined based on the target weight coefficient combination. The priority and real-time status information of each port of the multi-port solid-state transformer are input into the local controller of the reinforcement learning model to obtain the power allocation of each port of the multi-port solid-state transformer; the real-time status information of each port includes the electrical parameters of each energy module. The expression for the objective function is: in, Let be the objective function. The weighting factor is for voltage stability. The total number of sensitive nodes. The actual voltage deviation of the i-th sensitive node. The maximum voltage deviation of the i-th sensitive node. These are the weighting factors for power balance. Total number of ports The actual charge / discharge power of the j-th port. Let be the rated power of the j-th port.

Images