Anti-flow control device and method for three-phase four-wire converter

Abstract

The three-phase four-wire converter reverse flow prevention control device and method provided by the embodiment of the application comprises a data acquisition module, a pre-judgment decision module and a phase-by-phase reverse flow prevention control module, the phase-by-phase reverse flow prevention control module is used for determining a phase load power prediction value in a preset time period based on historical load data, real-time load data and scene feature data, determining a three-phase load imbalance coefficient based on the real-time load data, dynamically generating a phase-by-phase power adjustment instruction based on the phase load power prediction value and the three-phase load imbalance coefficient, and controlling a phase-by-phase power output value of the three-phase four-wire converter based on the phase-by-phase power adjustment instruction, so that the three-phase four-wire converter actively adjusts the output power before a load mutation, rather than passively responding to a reverse flow time; and the three-phase load imbalance coefficient is combined to realize differential adjustment of the output power, and the accuracy and adaptability of the phase-by-phase power adjustment are improved.

Description

Technical Field

[0001] This application relates to the field of power electronic converter technology, and in particular to a reverse current control device and method for a three-phase four-wire converter. Background Technology

[0002] In distributed photovoltaic, energy storage, and other new energy systems, three-phase four-wire converters are the core equipment for power conversion and grid-connected / off-grid operation. Converters require anti-reverse current control; the core objective of this control is to prevent the converter's output power from exceeding the local load's power consumption and thus feeding power back to the grid, ensuring stable grid operation.

[0003] In industrial, commercial, and residential microgrid scenarios, the widespread use of single-phase air conditioners, lighting, and precision equipment has led to a prominent problem of three-phase load imbalance, increasing the difficulty of backflow prevention control.

[0004] In related technologies, phase-by-phase anti-reverse current is achieved by setting single-phase power limits or by using a master-slave inverter system with phase-by-phase power regulation schemes. However, the above schemes have response lag and are prone to instantaneous reverse current problems. Summary of the Invention

[0005] This application provides a three-phase four-wire converter anti-reverse current control device and method to reduce the occurrence of instantaneous reverse current while improving response speed.

[0006] In a first aspect, embodiments of this application provide a reverse current prevention control device for a three-phase four-wire converter, wherein each phase of the three-phase four-wire converter is connected to a load, and the device includes:

[0007] The data acquisition module is used to acquire historical load data, real-time load data, and scenario feature data.

[0008] The prediction and decision-making module is used to receive and determine the predicted load power of each phase for a preset time period based on the historical load data, the real-time load data and the scene feature data, according to the load prediction model.

[0009] Based on the real-time load data, the three-phase load imbalance coefficient is determined according to a preset calculation logic.

[0010] And based on the predicted load power values ​​of each phase and the three-phase load imbalance coefficient, dynamically generate phase power adjustment commands;

[0011] The phase-by-phase anti-reverse current control module is used to control the power output value of each phase of the three-phase four-wire converter according to the phase-by-phase power adjustment command.

[0012] In one possible implementation, the prediction decision module includes a load prediction unit, which is used to construct a load prediction model based on the historical load data, the real-time load data, and the scene feature data, using a long short-term memory network combined with an attention mechanism, and output the predicted load power values ​​of each phase within a preset time period.

[0013] In one possible implementation, the prediction and decision module includes an imbalance analysis unit, used to determine the average power of each phase load based on the real-time load data, wherein the real-time load data includes at least the load power of each phase.

[0014] Furthermore, the three-phase load imbalance coefficient is determined based on the load power of each phase and the average power.

[0015] In one possible implementation, the prediction decision module includes a decision output unit, used to determine the upper limit of the output power of the corresponding phase or predict the output power based on the predicted load power values ​​of each phase.

[0016] And based on the three-phase load imbalance coefficient and according to the preset mapping relationship, the adjustment coefficient is determined, wherein the adjustment coefficient represents the adjustment range of the output power of each phase;

[0017] Based on the upper limit of output power or the predicted output power, and the adjustment coefficient, a phase power adjustment command is dynamically generated.

[0018] In one possible implementation, the phase-separated anti-reverse flow control module includes:

[0019] The phase-separated power regulation unit is used to dynamically adjust the reference values ​​of the current in each phase according to the phase-separated power regulation command and the regulation algorithm.

[0020] The converter drive unit is used to generate drive signals based on the adjusted reference values ​​of the current in each phase, wherein the drive signals are used to control the switching devices in the three-phase four-wire converter to turn on or off.

[0021] In one possible implementation, the phase-to-phase anti-reverse flow control module is also used to collect the actual output data of the three-phase four-wire converter in real time and feed it back to the load prediction unit.

[0022] The load prediction unit is also used to adjust the parameters of the load prediction model based on the actual output data and the predicted load power values ​​of each phase.

[0023] In one possible implementation, the data acquisition module includes:

[0024] A voltage and current acquisition unit is located at the output terminal, grid input point, and load terminal of the three-phase four-wire converter, and is used to acquire the voltage and current of each phase in real time.

[0025] The load monitoring unit is used to determine the real-time power of each phase load based on the voltage and current of each phase.

[0026] The scene data acquisition unit is used to acquire scene feature data and historical load data.

[0027] In one possible implementation, the device further includes a collaborative linkage module, the collaborative linkage module comprising:

[0028] The platform interface is used to upload the predicted load power values ​​and anti-reverse current control status of each phase to the external management platform, and to receive instructions issued by the external management platform.

[0029] In one possible implementation, the collaborative linkage module includes a communication unit for electrically connecting to the energy storage system and sending charging or discharging commands to the energy storage system.

[0030] Secondly, embodiments of this application provide a method for preventing reverse current in a three-phase four-wire converter connected to a load. The method includes the following steps:

[0031] Acquire historical load data, real-time load data, and scenario characteristic data;

[0032] Based on the historical load data, the real-time load data, and the scenario feature data, the predicted load power values ​​for each phase over a preset time period are determined using a load prediction model.

[0033] Based on the real-time load data, the three-phase load imbalance coefficient is determined according to a preset calculation logic.

[0034] Based on the predicted load power values ​​of each phase and the three-phase load imbalance coefficient, a phase power adjustment command is dynamically generated.

[0035] According to the phase power adjustment command, the power output value of each phase of the three-phase four-wire converter is controlled.

[0036] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0037] The memory stores computer-executed instructions;

[0038] The processor executes computer execution instructions stored in the memory, causing the processor to perform the second aspect and / or various possible implementations of the second aspect as described above.

[0039] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the second aspect and / or various possible implementations of the second aspect as described above.

[0040] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the second aspect and / or various possible implementations of the second aspect as described above.

[0041] The anti-reverse current control device and method for a three-phase four-wire converter provided in this application embodiment predicts the load power of each phase within a future period based on the fusion analysis of historical load data, real-time load data, and scenario characteristic data. This enables the three-phase four-wire converter to actively adjust its output power before load changes, rather than passively responding to the reverse current time. At the same time, combined with the three-phase load imbalance coefficient, it achieves differentiated adjustment of output power, improving the accuracy and adaptability of phase-by-phase power regulation. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] Figure 1 A schematic diagram of the anti-reverse flow control system for the three-phase four-wire converter provided in this application.

[0044] Figure 2 A schematic diagram of the topology of the anti-reverse flow control system for the three-phase four-wire converter provided in this application.

[0045] Figure 3 Flowchart of the anti-reverse current control method for a three-phase four-wire converter provided in this application Figure 1 .

[0046] Figure 4 Flowchart of the anti-reverse current control method for a three-phase four-wire converter provided in this application Figure 2 .

[0047] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0048] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0049] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0050] In distributed photovoltaic, energy storage and other new energy systems, three-phase four-wire converters are the core equipment for realizing power conversion and grid-connected / off-grid operation.

[0051] Currently, in order to consume and use electricity directly near renewable energy generation sites, rather than transmitting it over long distances, anti-reverse current control has become an essential function of converters. Its core objective is to prevent the converter's output power from exceeding the power consumed by the local load and feeding power back to the grid, thus ensuring the stable operation of the grid.

[0052] In current industrial, commercial, and residential microgrid scenarios, the widespread use of single-phase air conditioners, lighting, and precision equipment has led to a prominent problem of three-phase load imbalance, increasing the difficulty of backflow prevention and control.

[0053] In related technologies, phase-by-phase anti-reverse current is achieved by designing single-phase power limits, or by using a master-slave inverter system with a phase-by-phase power regulation scheme. However, in the above schemes, the control logic relies on real-time monitoring data. When a reverse current problem is detected based on the monitoring data, an adjustment command is issued, but instantaneous reverse current still occurs, and the response of the phase-by-phase power regulation scheme is lagging.

[0054] In view of this, this application provides a three-phase four-wire converter anti-reverse flow control device and method. The device is based on the fusion analysis of historical load data, real-time load data and scenario characteristic data to predict the load power of each phase, so as to adjust the output power before the load changes, thereby reducing the instantaneous reverse flow problem. At the same time, combined with the three-phase load imbalance coefficient, it realizes differentiated adjustment of output power, improving the accuracy and adaptability of phase power regulation.

[0055] The execution subject of the embodiments of this application can be an electronic device with processing capabilities, such as a computer, server, laptop computer, etc., and this application does not limit it.

[0056] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0057] Figure 1The schematic diagram of the anti-reverse current control system for the three-phase four-wire converter provided in this application is as follows: Figure 1 As shown, the system includes a three-phase four-wire converter anti-reverse control device 100 and a three-phase four-wire converter 200.

[0058] The aforementioned three-phase four-wire converter 200 is a power electronic device whose core function is to convert and control electrical energy. The three-phase four-wire converter 200 can be configured as a rectifier, inverter, AC converter, etc.

[0059] The three-phase four-wire converter anti-reverse control device 100 is used to perform anti-reverse control on the three-phase four-wire converter 200, and each phase of the three-phase four-wire converter 200 is connected to a load 300.

[0060] like Figure 1 As shown, the three-phase four-wire converter anti-reverse flow control device 100 includes a data acquisition module 101, a prediction and decision module 102, and a phase-by-phase anti-reverse flow control module 103.

[0061] The data acquisition module 101 collects converter output data, load data, and scenario characteristic data in real time; the prediction and decision-making module 102 predicts the load change trend through the load prediction model and outputs phase power adjustment commands in combination with the unbalance analysis model; the phase anti-reverse flow control module 103 dynamically adjusts the output power of each phase according to the adjustment commands.

[0062] The following provides a detailed description of the data acquisition module 101, the prediction and decision-making module 102, and the phase-separated anti-reverse flow control module 103.

[0063] The aforementioned data acquisition module 101 is used to acquire historical load data, real-time load data, and scenario feature data.

[0064] In some implementations, the data acquisition module 101 includes:

[0065] The voltage and current acquisition unit 1011 is located at the output terminal, grid input point and load terminal of the three-phase four-wire converter 200, and is used to acquire the voltage and current of each phase in real time.

[0066] The load monitoring unit 1012 is used to determine the real-time power of each phase load based on the phase voltage and current.

[0067] The scene data acquisition unit 1013 is used to acquire scene feature data and historical load data.

[0068] The voltage and current acquisition unit 1011 is configured with voltage and current sensors, which are installed at the output terminal, grid connection point, and load terminal of the three-phase four-wire converter 200. It acquires the voltage and current of each phase in real time.

[0069] To ensure the timeliness of sampling, a sampling frequency needs to be set. For example, the sampling frequency should not be lower than 1 kHz.

[0070] It should be noted that those skilled in the art can set the sampling frequency as needed; this is merely an example.

[0071] The load monitoring unit 1012 determines the real-time power of each phase based on the voltage and current data of each phase. It can also be seen that parameters such as impedance can be determined based on the voltage and current data of each phase.

[0072] The aforementioned scenario data acquisition unit 1013 collects user scenario characteristic data (for example, production shifts of industrial and commercial users, electricity consumption periods of household users, meteorological data, etc.) and historical load data (load change curves of the past 1-3 months).

[0073] It should be noted that the time period for historical load data can be set as needed, and this application does not impose any restrictions; this is merely an example.

[0074] This application introduces scenario feature data and combines it with the model's self-learning capability to adapt to the load characteristics of different scenarios such as industrial and commercial, and home environments. It does not require manual adjustment of control parameters and its adaptability is significantly improved compared to general-purpose solutions.

[0075] By integrating historical load data, real-time load data, and scenario feature data, control strategies can be self-learned and adapted to different scenarios.

[0076] In some implementations, a preprocessing unit is set up to preprocess the collected data in order to improve the accuracy of subsequent model training. Specifically, the preprocessing unit performs operations such as outlier removal and standardization on the collected data. The preprocessed data is then transmitted to the prediction and decision module 102.

[0077] It is understood that the preprocessing unit can be set up independently of the above-mentioned units, or the preprocessing unit can be integrated into one of the above-mentioned units to improve the integration of the modules.

[0078] The sensors in the above embodiments can be wired sensors. In some embodiments, wireless sensor networks can be used to replace wired sensors to collect load data, reducing wiring costs and adapting to distributed load scenarios.

[0079] In some implementations, the anti-reverse flow control device 100 for three-phase four-wire converters can incorporate digital twin technology to generate supplementary data through virtual models, thereby improving the training effect of subsequent load prediction models.

[0080] The aforementioned prediction and decision-making module 102 is used to receive and determine the predicted load power of each phase for a preset time period based on historical load data, real-time load data, and scenario characteristic data, using a load prediction model.

[0081] The prediction and decision module 102 is also used to determine the three-phase load imbalance coefficient based on real-time load data and preset calculation logic.

[0082] The prediction and decision module 102 is also used to dynamically generate phase power adjustment commands based on the predicted load power of each phase and the three-phase load imbalance coefficient.

[0083] In the above, by determining the predicted load power of each phase within a preset time period in the future, the load change trend can be predicted in advance within a preset time period, and passive adjustment can be changed to active control. The dynamic adjustment time is less than or equal to 50ms, which is more than 6 times faster than related technologies such as using a master-slave inverter system with a phase-by-phase power regulation scheme (350ms) and setting a single-phase power limit to achieve a phase-by-phase anti-reverse current scheme (300ms+). There is no instantaneous reverse current in the case of sudden load changes.

[0084] In some embodiments, the prediction decision module 102 includes a load prediction unit 1021, which is configured with a load prediction model.

[0085] The load prediction unit 1021 is used to construct a load prediction model based on historical load data, real-time load data and scene feature data, using a long short-term memory network combined with an attention mechanism, and output the predicted load power values ​​of each phase within a preset time period.

[0086] The above is constructed using a Long Short-Term Memory (LSTM) network combined with an attention mechanism. The input data consists of preprocessed historical load data, real-time load data, and scene feature data. The output is the predicted load power of each phase within the next 1-5 minutes.

[0087] Experimental testing showed that the prediction error of this load power prediction was controlled within ±3%. This model continuously learns user load characteristics and optimizes prediction accuracy, enabling early prediction of load fluctuations.

[0088] The load prediction model based on LSTM and attention mechanism in this application can predict the load change trend of each phase in advance and solve the response lag problem from the root, which is the core of realizing active backflow prevention.

[0089] In some embodiments, the load prediction module uses GRU (Gated Recurrent Unit) instead of LSTM to reduce computational complexity and adapt to small converters with limited resources.

[0090] In some embodiments, the prediction and decision-making module 102 includes an imbalance analysis unit 1022, which stores preset calculation logic.

[0091] The imbalance analysis unit 1022 is used to determine the average power of each phase load based on real-time load data, the real-time load data including at least the load power of each phase; and to determine the three-phase load imbalance coefficient based on the load power of each phase and the average power.

[0092] For example, based on real-time load power data for each phase, the three-phase load imbalance coefficient is determined according to preset calculation logic. The formula for the three-phase load imbalance coefficient is as follows:

[0093]

[0094] in, , , These represent the load power of each phase. This represents the average power.

[0095] The future trend of load imbalance can be analyzed based on the three-phase load imbalance coefficient and the load power prediction value output by the load prediction model.

[0096] In some embodiments, the determination of the three-phase load imbalance coefficient can be optimized by combining the random forest algorithm to improve the analysis accuracy in complex scenarios.

[0097] In some embodiments, the prediction decision module 102 includes a decision output unit 1023, which is used to determine the upper limit of the output power of the corresponding phase or predict the output power based on the predicted load power of each phase.

[0098] In the above, based on the predicted load power values ​​for each phase, the upper limit of the output power or the predicted output power for the corresponding phase is determined. Specifically:

[0099] When it is predicted that the load on a certain phase will increase, that is, when the predicted load power is greater than the current load output power, the upper limit of the output power of that phase is increased in advance.

[0100] When it is predicted that the load on a certain phase will decrease and there is a risk of reverse current, that is, the predicted load power is less than the current load output power, the output power of that phase is reduced to the predicted output power in advance to prevent reverse current problems.

[0101] The decision output unit 1023 is used to determine the adjustment coefficient based on the three-phase load imbalance coefficient and a preset mapping relationship, wherein the adjustment coefficient represents the adjustment range of the output power of each phase.

[0102] Based on the upper limit of output power or the predicted output power, and the adjustment coefficient, the phase power adjustment command is dynamically generated.

[0103] The adjustment coefficient is dynamically set based on the three-phase load imbalance coefficient, taking into account both anti-reverse current accuracy and output power, and adapting to different imbalance scenarios.

[0104] Experimental tests have shown that the anti-backflow device described in this application can effectively prevent backflow. In scenarios with an imbalance of ≤50%, the power of each phase feeder is strictly controlled within 0W±1%, and the anti-reverse current accuracy is improved by an order of magnitude compared to related technologies. At the same time, it can maximize the converter output efficiency and avoid energy waste caused by excessive power limiting.

[0105] In the above, different adjustment coefficients are set for different three-phase load imbalance coefficients to ensure adjustment accuracy.

[0106] The value of the three-phase load imbalance coefficient can be divided into several levels, corresponding to different adjustment coefficients, and a linear correspondence can also be set.

[0107] For example, ≤20% is considered mild imbalance, <20% ≤50% is considered moderate imbalance. A balance greater than 50% indicates a severe imbalance, with corresponding adjustment coefficients of 1.0, 1.2, and 1.5, respectively.

[0108] It should be noted that the larger the adjustment coefficient mentioned above, the higher the adjustment sensitivity.

[0109] In some embodiments, to improve output power, an optimization objective is added. The optimization objective is set as follows: the power fed to the grid in each phase is ≤0, and the converter output efficiency is maximized. The optimization objective combines the load power prediction value and the three-phase load imbalance coefficient to dynamically generate power adjustment commands for each phase. Here, the power fed to the grid in each phase ≤0 indicates that no reverse current phenomenon occurs in each phase.

[0110] The aforementioned phase-by-phase anti-reverse flow control module 103 is used to control the power output value of each phase of the three-phase four-wire converter according to the phase-by-phase power adjustment command.

[0111] In some embodiments, the phase-separated anti-reverse current control module 103 includes:

[0112] The phase-separated power regulation unit 1031 is used to dynamically adjust the reference values ​​of the current in each phase according to the phase-separated power regulation command and the regulation algorithm.

[0113] In some implementations, the reference values ​​of the current in each phase are dynamically adjusted by an improved PI control algorithm to achieve independent adjustment of the power of each phase.

[0114] In some embodiments, the model predictive control (MPC) algorithm is used to replace the improved PI algorithm to further enhance the dynamic adjustment accuracy and adapt to precision manufacturing scenarios with ultra-high precision requirements.

[0115] The converter drive unit 1032 is used to generate drive signals based on the adjusted reference values ​​of the phase currents. The drive signals are used to control the switching devices in the three-phase four-wire converter to turn on or off.

[0116] In the above process, based on the adjusted reference values ​​of the current in each phase, a PWM drive signal is generated to control the switching devices (such as IGBTs) inside the converter to turn on and off, thereby precisely adjusting the output power of each phase.

[0117] In some embodiments, the phase-to-phase anti-reverse flow control module 103 is also used to collect the actual output data of the three-phase four-wire converter in real time and feed it back to the load prediction unit 1021.

[0118] The load prediction unit 1021 is also used to adjust the parameters of the load prediction model based on the actual output data and the predicted load power values ​​of each phase.

[0119] By feeding back the actual output data of the three-phase four-wire converter 200 collected in real time to the prediction and decision module 102, a closed-loop control is formed.

[0120] For example, the relevant parameters are adjusted based on the difference between the actual output data and the predicted load power of each phase.

[0121] like Figure 1 As shown, the data acquisition module 101 is connected to the load 300 and the three-phase four-wire converter 200 to collect real-time operating data. The prediction and decision-making module 102 communicates bidirectionally with the data acquisition module 101 and outputs power regulation commands. The phase-by-phase anti-reverse current control module 103 is connected to the three-phase four-wire converter 200 to execute power regulation actions. The three-phase four-wire converter 200 is connected to the power grid 600 and the load 300 via a line.

[0122] The data acquisition module 101, the prediction and decision-making module 102, and the phase-separated anti-backflow control module 103 work together to achieve full-process anti-backflow management of prediction, decision-making, and control.

[0123] In some embodiments, such as Figure 1 As shown, the device also includes a collaborative linkage module 104, which includes a platform interface 1041 for uploading the predicted load power values ​​and anti-reverse current control status of each phase to the external management platform 500, and receiving instructions issued by the external management platform 500.

[0124] In some embodiments, the collaborative linkage module 104 includes a communication unit 1042 for electrically connecting to the energy storage system 400 and sending charging or discharging commands to the energy storage system 400.

[0125] In the above, the collaborative linkage module 104 is connected to the prediction and decision-making module 102, the external management platform 500 and the energy storage system 400 respectively, so as to realize the collaborative control of each part.

[0126] By working together with the data acquisition module 101, the prediction and decision-making module 102, the phase-separated anti-backflow control module 103, and the collaborative linkage module 104, the whole-process anti-backflow management of prediction, decision-making, control, and linkage is realized, thereby optimizing the overall energy utilization efficiency.

[0127] By setting up the collaborative linkage module 104, it is helpful to realize the enterprise's integrated characteristics of new energy grid-load-storage.

[0128] The following explanation uses the external management platform 500 as an example of setting up an AI energy management platform.

[0129] Load forecast data and anti-backflow control status are uploaded to the AI ​​energy management platform through platform interface 1041, and global energy optimization instructions are received from the AI ​​energy management platform.

[0130] The communication unit 1042 is linked with the energy storage system 400. When the predicted load output power drops significantly and the output power of the three-phase four-wire converter 200 is excessive, the energy storage system is instructed to charge in advance to avoid energy waste caused by excessive power limiting of the converter. When the predicted load output power rises significantly, the energy storage system is instructed to discharge to assist in power supply and improve power supply stability.

[0131] By linking the AI ​​energy management platform with the energy storage system, the limitations of a single converter in preventing backflow are overcome. While preventing backflow, energy distribution is optimized, and the overall energy utilization efficiency is improved, which is in line with the strategy of integrating new energy load and storage.

[0132] In some embodiments, in addition to linking the energy storage system 400, the collaborative linkage module 104 can also link the MPPT adjustment module of the photovoltaic inverter to assist in anti-reverse current control by adjusting the photovoltaic output power and improve system redundancy.

[0133] Figure 2 This application provides a schematic diagram of the anti-reverse flow control system for a three-phase four-wire converter.

[0134] The anti-reverse flow control device 100 for the three-phase four-wire converter is integrated into the three-phase four-wire converter 200 in the figure.

[0135] The three-phase four-wire converter 200 is electrically connected to the external management platform 500, the energy storage system 400, and the distributed photovoltaic system 700, respectively.

[0136] The three-phase four-wire converter 200 receives AC power from the distributed photovoltaic system 700 and transmits it to the power grid 600. Simultaneously, excess electrical energy can be stored in the energy storage system 400.

[0137] The three-phase four-wire converter anti-reverse control device 100 can receive instructions from the external management platform 500, which facilitates multi-faceted control of the three-phase four-wire converter anti-reverse control device 100.

[0138] By integrating the core module or all of the three-phase four-wire converter anti-reverse control device 100 into the existing three-phase four-wire converter, without major changes to the hardware structure, and combined with the production capacity of the intelligent controller factory, industrialization can be achieved quickly.

[0139] In some embodiments, a specific implementation is presented using a commercial three-phase four-wire photovoltaic inverter system as an example, detailing the application process of the technical solution of this application. This system is adapted to a 100kW load and suffers from severe single-phase load imbalance.

[0140] 1. System setup.

[0141] Voltage / current sensors are installed at the output of the photovoltaic inverter, the grid connection point, and the A / B / C three-phase load terminals, with the sampling frequency set to 2kHz.

[0142] The scene data acquisition unit 1013 collects the production shifts of the industrial and commercial user (8:00-20:00 is the production period, with large load fluctuations; 20:00-8:00 the next day is the rest period, with only lighting load retained) and historical load data for the past month.

[0143] The prediction and decision-making module 102 is deployed in the local edge computing unit of the inverter, and the collaborative linkage module 104 is connected to the AI ​​energy management platform and the 100kWh energy storage system.

[0144] 2. Model training and initialization.

[0145] Based on the collected one month of historical load data and scenario feature data, the load prediction model is trained, and the model parameters are initialized after training.

[0146] Setting a grading standard for the three-phase load imbalance coefficient: ≤20% is considered mild imbalance, <20% ≤50% is considered moderate imbalance. A balance greater than 50% indicates a severe imbalance, with corresponding adjustment coefficients of 1.0, 1.2, and 1.5. The larger the adjustment coefficient, the higher the adjustment sensitivity.

[0147] 3. Operation control process.

[0148] Data Acquisition: Real-time data acquisition of A-phase load power (30kW), B-phase load power (20kW), and C-phase load power (50kW) was obtained, and the unbalance degree (ε) was determined to be 42%, indicating a moderate unbalance. Simultaneously, the current time was collected at 7:50 (approaching the production period), and the scenario data was "production preparation stage".

[0149] Forecasting and Decision-Making: The load forecasting model outputs the load forecast values ​​for the next 10 minutes (8:00-8:10), with phase A increasing to 50kW, phase B to 30kW, and phase C to 60kW, and the imbalance degree... =38%, which is still considered a moderate imbalance.

[0150] The decision output unit 1023 combines the predicted load power value with the current three-phase load imbalance coefficient to generate phase power adjustment commands. Specifically, the upper limit of the output power of phase A is increased from the current 30kW to 48kW, phase B from 20kW to 28kW, and phase C from 50kW to 58kW, with an adjustment coefficient of 1.2 for all phases.

[0151] Execution and linkage: The phase-by-phase anti-reverse current control module 103 adjusts the reference values ​​of the current in each phase according to the phase-by-phase power adjustment command, and drives the inverter to adjust the output power.

[0152] The collaborative module 104 uploads the predicted data to the AI ​​energy management platform, and the platform instructs the energy storage system to remain in standby mode (because the predicted load is rising, there is no need to charge to absorb the excess power).

[0153] Closed-loop optimization: After production starts at 8:00, the deviation between the actual load data and the predicted value is ≤2%, the power of each phase feeder is 0W, and there is no reverse current phenomenon; the system feeds the actual load data back to the load prediction model to further optimize the prediction accuracy.

[0154] Compared with the Ginlong master-slave anti-reverse current scheme in the above specific embodiments and related technologies, the dynamic adjustment time of this application is shortened to less than 50ms, and there is no instantaneous reverse current when the load changes suddenly; in the moderate imbalance scenario, the converter output efficiency is improved by 2%-3%, and energy waste is reduced.

[0155] Figure 3 Flowchart of the anti-reverse current control method for a three-phase four-wire converter provided in this application Figure 1 ,like Figure 3 As shown, the method includes:

[0156] S301: Obtain historical load data, real-time load data, and scenario feature data.

[0157] In the above, the data acquisition module 101 acquires phase voltage, current, power, scene characteristic data and historical load data in real time at the converter output end, load end and grid connection point. After outlier removal and standardization, the data is transmitted to the prediction and decision module 102.

[0158] S302: Based on historical load data, real-time load data, and scenario characteristic data, determine the predicted load power of each phase for a preset time period using a load prediction model.

[0159] For example, the load forecasting model outputs the predicted load power of each phase for the next 1-5 minutes based on preprocessed data.

[0160] S303: Determine the three-phase load imbalance coefficient based on real-time load data and preset calculation logic.

[0161] In some implementations, the imbalance analysis model determines the real-time three-phase load imbalance coefficient and analyzes the load change trend by combining the predicted load power values ​​of each phase.

[0162] S304: Dynamically generate phase power adjustment commands based on the predicted load power of each phase and the three-phase load imbalance coefficient.

[0163] For example, the decision output unit 1023 aims at "no backflow + high efficiency", combines the predicted load power of each phase with the three-phase load imbalance coefficient, generates power adjustment commands for each phase, and sets differentiated adjustment coefficients for different imbalance degrees.

[0164] S305: Controls the power output value of each phase of the three-phase four-wire converter according to the phase power adjustment command.

[0165] For example, the phase power regulation unit adjusts the current reference value of each phase according to the power regulation command of each phase, and the three-phase four-wire converter drive unit generates a PWM signal to control the output power of the three-phase four-wire converter, so as to achieve precise adjustment of the power of each phase.

[0166] Figure 4 Flowchart of the anti-reverse current control method for a three-phase four-wire converter provided in this application Figure 2 ,like Figure 4 As shown, in this embodiment... Figure 3 Based on the examples, a detailed explanation is provided on how to dynamically generate phase power regulation commands. This method includes:

[0167] S401: Based on historical load data, real-time load data, and scenario feature data, a load prediction model is constructed using a long short-term memory network combined with an attention mechanism, and the predicted load power values ​​for each phase within a preset time period are output.

[0168] S402: Based on real-time load data, determine the average power of each phase load, where the real-time load data includes at least the power of each phase load; based on the power of each phase load and the average power, determine the three-phase load imbalance coefficient.

[0169] S403: Adjust the upper limit of the output power or the output power of the corresponding phase based on the predicted load power of each phase.

[0170] Based on the three-phase load imbalance coefficient and according to the preset mapping relationship, the adjustment coefficient is determined, whereby the adjustment coefficient represents the adjustment range of the output power of each phase.

[0171] In some embodiments, controlling the power output value of each phase of a three-phase four-wire converter according to a phase power regulation command includes the following steps:

[0172] Based on the power regulation commands for each phase, the reference values ​​of the current for each phase are dynamically adjusted using the regulation algorithm.

[0173] Based on the adjusted reference values ​​of each phase current, a drive signal is generated, which is used to control the switching devices in the three-phase four-wire converter to turn on or off.

[0174] In some embodiments, the method further includes a feedback step, specifically comprising:

[0175] The actual output data of the three-phase four-wire converter is collected in real time and fed back to the load prediction unit.

[0176] Adjust the parameters of the load prediction model based on the actual output data and the predicted load power of each phase, and dynamically optimize the model parameters and phase power regulation commands.

[0177] In some embodiments, a detailed description is provided of how to obtain historical load data, real-time load data, and scenario characteristic data, the method including:

[0178] Real-time acquisition of phase voltage and current; determination of real-time load power for each phase based on phase voltage and current; acquisition of scene characteristic data and historical load data.

[0179] In some embodiments, the collaborative linkage module 104 uploads the control status to the external management platform 500, and the energy storage system 400 is linked to optimize energy distribution.

[0180] The anti-reverse flow control method based on a three-phase four-wire converter provided in this embodiment can be applied to the device provided in the above-mentioned device embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0181] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Figure 5As shown, the electronic device 500 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 500 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0182] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0183] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0184] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0185] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0186] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0187] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0188] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0189] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0190] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0191] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components 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 indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0192] 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 this embodiment according to actual needs.

[0193] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0194] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0195] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0196] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A reverse current prevention control device for a three-phase four-wire converter, characterized in that, This device is used for anti-reverse current control of a three-phase four-wire converter, wherein each phase of the three-phase four-wire converter is connected to a load. The device includes: The data acquisition module is used to acquire historical load data, real-time load data, and scenario feature data. The prediction and decision-making module is used to receive and determine the predicted load power of each phase for a preset time period based on the historical load data, the real-time load data and the scene feature data, according to the load prediction model. Based on the real-time load data, the three-phase load imbalance coefficient is determined according to a preset calculation logic. And based on the predicted load power values ​​of each phase and the three-phase load imbalance coefficient, dynamically generate phase power adjustment commands; The phase-by-phase anti-reverse current control module is used to control the power output value of each phase of the three-phase four-wire converter according to the phase-by-phase power adjustment command. The prediction and decision-making module includes a decision output unit, which is used to determine the upper limit of the output power of the corresponding phase or the predicted output power based on the predicted load power values ​​of each phase. Specifically, when it is predicted that the load of a certain phase will increase, that is, the predicted load power value is greater than the current load output power, the upper limit of the output power of that phase is increased in advance; when it is predicted that the load of a certain phase will decrease and there is a risk of reverse current, that is, the predicted load power value is less than the current load output power, the output power of that phase is reduced to the predicted output power in advance. And based on the three-phase load imbalance coefficient and according to the preset mapping relationship, the adjustment coefficient is determined, wherein the adjustment coefficient represents the adjustment range of the output power of each phase; Based on the upper limit of output power or the predicted output power, and the adjustment coefficient, a phase power adjustment command is dynamically generated.

2. The apparatus according to claim 1, characterized in that, The prediction and decision-making module includes a load prediction unit. The load prediction unit is used to construct a load prediction model based on the historical load data, the real-time load data, and the scene feature data, using a long short-term memory network combined with an attention mechanism, and output the predicted load power values ​​of each phase within a preset time period.

3. The apparatus according to claim 1, characterized in that, The prediction and decision-making module includes an imbalance analysis unit, which is used to determine the average power of each phase load based on the real-time load data, wherein the real-time load data includes at least the load power of each phase. Furthermore, the three-phase load imbalance coefficient is determined based on the load power of each phase and the average power.

4. The apparatus according to claim 1, characterized in that, The phase-separation anti-reverse flow control module includes: The phase-separated power regulation unit is used to dynamically adjust the reference values ​​of the current in each phase according to the phase-separated power regulation command and the regulation algorithm. The converter drive unit is used to generate drive signals based on the adjusted reference values ​​of the current in each phase, wherein the drive signals are used to control the switching devices in the three-phase four-wire converter to turn on or off.

5. The apparatus according to claim 2, characterized in that, The phase-to-phase anti-reverse flow control module is also used to collect the actual output data of the three-phase four-wire converter in real time and feed it back to the load prediction unit. The load prediction unit is also used to adjust the parameters of the load prediction model based on the actual output data and the predicted load power values ​​of each phase.

6. The apparatus according to any one of claims 1-5, characterized in that, The data acquisition module includes: A voltage and current acquisition unit is located at the output terminal, grid input point, and load terminal of the three-phase four-wire converter, and is used to acquire the voltage and current of each phase in real time. The load monitoring unit is used to determine the real-time power of each phase load based on the voltage and current of each phase. The scene data acquisition unit is used to acquire scene feature data and historical load data.

7. The apparatus according to claim 1, characterized in that, It also includes a collaborative linkage module, which includes: The platform interface is used to upload the predicted load power values ​​and anti-reverse current control status of each phase to the external management platform, and to receive instructions issued by the external management platform.

8. The apparatus according to claim 7, characterized in that, The collaborative linkage module includes: A communication unit is used to electrically connect to the energy storage system and send charging or discharging commands to the energy storage system.

9. A method for preventing backflow in a three-phase four-wire converter, characterized in that, The method includes the following steps: Acquire historical load data, real-time load data, and scenario characteristic data; Based on the historical load data, the real-time load data, and the scenario feature data, the predicted load power values ​​for each phase over a preset time period are determined using a load prediction model. Based on the real-time load data, the three-phase load imbalance coefficient is determined according to a preset calculation logic. Based on the predicted load power values ​​of each phase, determine the upper limit of the output power or the predicted output power of the corresponding phase; wherein, when it is predicted that the load of a certain phase will increase, that is, the predicted load power value is greater than the current load output power, the upper limit of the output power of that phase is increased in advance; when it is predicted that the load of a certain phase will decrease and there is a risk of reverse current, that is, the predicted load power value is less than the current load output power, the output power of that phase is reduced to the predicted output power in advance. And based on the three-phase load imbalance coefficient and according to the preset mapping relationship, the adjustment coefficient is determined, wherein the adjustment coefficient represents the adjustment range of the output power of each phase; Based on the upper limit of output power or the predicted output power, and the adjustment coefficient, a phase power adjustment command is dynamically generated; According to the phase power adjustment command, the power output value of each phase of the three-phase four-wire converter is controlled.

Images