System control method, device and electronic equipment

Abstract

The present invention discloses a system control method, device, and electronic device, wherein the method is applied to a multi-machine parallel converter, wherein the multi-machine parallel converter includes at least two parallel converters, wherein the method includes: obtaining the current load power of the multi-machine parallel converter; determining the target converter unit corresponding to the current load power according to a pre-configured system efficiency model of the multi-machine parallel converter, wherein at least part of the load power corresponding to the system efficiency curve of the system efficiency model is associated with at least one converter unit; and controlling the multi-machine parallel converter to start the target converter units to operate in parallel. The embodiment of the present invention determines the converter units used under different loads through a reasonably configured system efficiency model, thereby facilitating the improvement of the scientific nature of converter unit control and the improvement of converter working efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of power electronic converters, and in particular to a system control method, device and electronic equipment. Background Art

[0002] Currently, multi-machine parallel converters are widely used in photovoltaic or energy storage systems. Existing converter operation control methods fail to fully tap the potential of these devices. For example, an over-provisioned converter designed to achieve triple overload capacity undergoes operational changes due to factors such as bus voltage, grid voltage, ambient temperature, and operating temperature. This causes the converter's efficiency curve to fluctuate, resulting in variable system efficiency. Conventional converter control methods are unable to achieve precise control of the converter, preventing the system from maintaining optimal operation. This lack of a sound control basis prevents scientific converter control, resulting in poor overall efficiency for the photovoltaic or energy storage system. Summary of the Invention

[0003] The present invention provides a system control method, device and electronic equipment to determine the converter units used under different loads through a reasonably configured system efficiency model, thereby improving the scientific nature of the converter unit control and improving the working efficiency of the converter.

[0004] According to one aspect of the present invention, a system control method is provided, wherein the method is applied to a multi-machine parallel converter, wherein the multi-machine parallel converter includes at least two parallel converter units, and the method includes:

[0005] Obtaining the current load power of the multi-machine parallel converter;

[0006] determining a target converter unit corresponding to the current load power according to a preconfigured system efficiency model of the multi-machine parallel converter, wherein at least a portion of the load power corresponding to a system efficiency curve of the system efficiency model is associated with at least one of the converter units;

[0007] The multi-machine parallel converter is controlled to start the target converter units to operate in parallel.

[0008] According to another aspect of the present invention, a system control device is provided, wherein the system control device is applied to a multi-machine parallel converter, wherein the multi-machine parallel converter includes at least two parallel converter units, and the system control device includes:

[0009] A power acquisition module, configured to acquire the current load power of the multi-machine parallel converter;

[0010] a target determination module, configured to determine a target converter unit corresponding to the current load power according to a preconfigured system efficiency model of the multi-machine parallel converter, wherein at least part of the load power corresponding to the system efficiency curve of the system efficiency model is associated with at least one of the converter units;

[0011] The working control module is used to control the multi-machine parallel converter to start the target converter units to work in parallel.

[0012] According to another aspect of the present invention, an electronic device is provided, comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the system control method according to any embodiment of the present invention.

[0016] The technical solution of the embodiment of the present invention obtains the current load power of the multi-machine parallel converter, determines the target converter unit started by the current load power through the system efficiency model configured for the multi-machine parallel converter, and controls the target converter units in the multi-machine parallel converter to work in parallel. The embodiment of the present invention determines the target converter that reaches the maximum efficiency state based on the system efficiency model, which can provide a scientific basis for converter control, enhance the accuracy of converter control, and make the multi-machine parallel converter continuously in the maximum efficiency state, which can improve the overall working efficiency of the system.

[0017] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 This is a flow chart of a system control method provided according to the first embodiment of the present invention;

[0020] Figure 2is a flow chart of another system control method provided according to the second embodiment of the present invention;

[0021] Figure 3 This is an example diagram of a curve showing changes in system efficiency with load and bus voltage according to the second embodiment of the present invention;

[0022] Figure 4 This is an example diagram of a curve showing changes in system efficiency with load and grid-side voltage according to the second embodiment of the present invention;

[0023] Figure 5 This is an example diagram of a curve showing changes in system efficiency with load and ambient temperature according to the second embodiment of the present invention;

[0024] Figure 6 This is an example diagram of a curve showing changes in system efficiency with load and operating time according to the second embodiment of the present invention;

[0025] Figure 7 is a flow chart of a system control method provided according to embodiment 3 of the present invention;

[0026] Figure 8 This is an example diagram of a system efficiency curve provided according to the fourth embodiment of the present invention;

[0027] Figure 9 This is an example diagram of overload switching of an overload switching subsystem provided according to a fourth embodiment of the present invention;

[0028] Figure 10 1 is a comparison example diagram of a predicted efficiency curve and an actual efficiency curve of a prediction model provided according to the fourth embodiment of the present invention;

[0029] Figure 11 1 is a schematic diagram of a curve showing a change in converter efficiency versus load according to a fourth embodiment of the present invention;

[0030] Figure 12 1 is a schematic diagram of a loss curve when two converters distribute different powers according to a fourth embodiment of the present invention;

[0031] Figure 13 1 is a schematic diagram of two converters switching from a maximum efficiency mode to an overload maximum efficiency mode according to a fourth embodiment of the present invention;

[0032] Figure 14 2 is a schematic diagram of two converters switching from an overload maximum efficiency mode to a maximum efficiency mode according to a fourth embodiment of the present invention;

[0033] Figure 15 This is a structural diagram of a system control device provided according to a fifth embodiment of the present invention;

[0034] Figure 16 It is a structural diagram of an electronic device for implementing the system control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] In an embodiment of the present invention, a multi-machine parallel converter can be a system in which at least two converter units are connected in parallel to jointly supply power to a power grid or load. The parallel converter units in the multi-machine parallel converter can have the same or different specifications, brands, or types. The number of converter units connected in parallel in the multi-machine parallel converter is not limited. For example, the multi-machine parallel converter can include 2, 3, or 5 converter units connected in parallel. The multi-machine parallel converter can be applied to photovoltaic or energy storage systems. The rated power of the multi-machine parallel converter is Pr = P1r + ... + PNr, where N is the number of converter units connected in parallel in the multi-machine parallel converter, Pir is the rated power of each converter unit, and i = 1, 2, 3, ..., N. When a single converter is overloaded, its power POL = M * Pr, where M is the overload multiple. The embodiments of the present invention are intended to control the operation of a multi-machine parallel converter, explore and realize the system efficiency of the multi-machine parallel converter, improve the scientific nature of the regulation, and optimize the overall efficiency of a photovoltaic or energy storage system.

[0038] Example 1

[0039] Figure 1A flowchart of a system control method is provided for the first embodiment of the present invention. This embodiment is applicable to the control and scheduling of a multi-machine parallel converter. The method can be executed by a system control device. The system control device can be implemented in the form of hardware and / or software. The system control device can be configured locally in the multi-machine parallel converter or in the host computer of the multi-machine parallel converter. The multi-machine parallel converter includes at least two parallel converter units. Figure 1 As shown, the method includes:

[0040] Step 110: Obtain the current load power of the multi-machine parallel converter.

[0041] The current load power may be the power provided to the load by the output terminal of the multi-machine parallel converter. The current load power may be determined by direct measurement, simulation analysis, or based on a control strategy.

[0042] In the embodiment of the present invention, the load power of the multi-machine parallel converter can be monitored, and the load power data monitored each time can be used as the current load power of the multi-machine parallel converter.

[0043] Step 120 : Determine a target converter unit corresponding to the current load power according to a preconfigured system efficiency model of the multi-machine parallel converter, wherein at least part of the load power corresponding to the system efficiency curve of the system efficiency model is associated with at least one converter unit.

[0044] The system efficiency model can be a control strategy model for controlling a multi-machine parallel converter to achieve optimal efficiency. The system efficiency model can include a converter unit that enables the multi-machine parallel converter to achieve optimal efficiency under different load powers and a converter unit that enables the multi-machine parallel converter to achieve optimal efficiency. The system efficiency model can exist in the form of a system efficiency curve, which can represent how the system efficiency of the multi-machine parallel converter changes with load under different operating conditions. The system efficiency curve corresponding to the system efficiency model can contain converter units corresponding to partial load powers, that is, starting the associated converter units to work under this partial load power can enable the multi-machine parallel converter to achieve the maximum efficiency in the system efficiency curve.

[0045] In an embodiment of the present invention, a system efficiency model of a multi-machine parallel converter can be obtained. It can be understood that different types of multi-machine parallel converters can have their own corresponding system efficiency models. The corresponding system efficiency model can be found according to the type of the multi-machine parallel converter. The system efficiency model can exist in the form of a configuration file or configuration parameters. The system efficiency model of the multi-machine parallel converter can be configured locally in the multi-machine parallel converter or in the host computer of the multi-machine parallel converter. Further, the system efficiency model can exist in the form of a system efficiency curve. The system efficiency curve can include a mapping relationship between load power and system efficiency. The load power in the system efficiency curve can be associated with one or more converter units of the multi-machine parallel converter. The associated converter unit can enable the multi-machine parallel converter to achieve the optimal system efficiency in the system efficiency curve under the corresponding load power.

[0046] Step 130: Control the multi-machine parallel converter to start the target converter units to operate in parallel.

[0047] Specifically, the multi-machine parallel converter can be controlled to start the determined target converter units, so that the target converter units in the multi-machine parallel converter work in parallel. Furthermore, the multi-machine parallel converter can be controlled to switch other converter units to a non-operating state. It is understandable that when starting the target converter units to work in parallel, each target converter unit can also be allocated a respective output power. The output power can be determined by the performance of each target converter unit. For example, when the target converter units are of the same type, the load power can be evenly divided according to the number of target converter units, and the evenly divided load power can be used as the output power of the target converter unit.

[0048] An embodiment of the present invention obtains the current load power of a multi-machine parallel converter, determines the target converter unit to be started by the current load power through a system efficiency model configured for the multi-machine parallel converter, and controls the target converter units in the multi-machine parallel converter to work in parallel. An embodiment of the present invention determines the target converter unit that reaches the maximum efficiency state based on the system efficiency model, which can provide a scientific basis for converter control, enhance the accuracy of converter control, and enable the multi-machine parallel converter to be continuously in the maximum efficiency state, thereby improving the overall working efficiency of the system.

[0049] Example 2

[0050] Figure 2 This is a flow chart of another system control method provided according to the second embodiment of the present invention. This embodiment of the present invention is a specific embodiment based on the above embodiment. The process of constructing the system efficiency model is described. Figure 2 The method provided in the embodiment of the present invention specifically includes the following steps:

[0051] Step 210: Obtain a model training data set for a multi-machine parallel converter, and train an initial neural network model as a single-machine efficiency prediction model according to the model training data set, wherein the initial neural network model includes at least one of the following: a multi-layer perceptron neural network model, a long short-term memory network model, a convolutional neural network model, and a wavelet neural network model.

[0052] The model training data set may be a data set for training a single-machine efficiency prediction model for a multi-machine parallel converter. The model training data set may include at least one set of data, including historical operating states and historical efficiency values corresponding to the historical operating states. The data may be obtained by testing the multi-machine parallel converter. The single-machine efficiency prediction model may be a neural network model used to predict the system efficiency of each converter connected in parallel within the multi-machine parallel converter. The single-machine efficiency prediction model may be an initial neural network model trained using the model training data set. The input of the single-machine efficiency prediction model may be the operating state data of each converter. For example, the operating state data may include load power, bus-side voltage, grid-side voltage, operating time, and ambient temperature. The initial neural network model may be one or more of a multi-layer perceptron neural network model, a long short-term memory network model, a convolutional neural network model, and a wavelet neural network model.

[0053] In an embodiment of the present invention, a corresponding model training data set is obtained for a multi-machine parallel converter, and the model training data set can be called to train an initial neural network model. The trained initial neural network model can be used as a single-machine efficiency prediction model, and the single-machine efficiency model can be used to predict the system efficiency of each converter connected in parallel in the multi-machine parallel converter. The method of training the initial neural network model as a single-machine efficiency prediction model through the model training data set may include but is not limited to the gradient descent method, the Adam optimization algorithm, the momentum method, etc.

[0054] Step 220 , calling the single-machine efficiency prediction model to determine the single-machine efficiency of each converter unit in the multi-machine parallel converter under different load powers, and generating a single-machine efficiency curve corresponding to each converter unit according to the single-machine efficiency of each converter unit under different load powers.

[0055] Among them, the single-machine efficiency can be the efficiency value corresponding to each converter unit under different load powers, the single-machine efficiency curve can be the corresponding relationship between the load power and efficiency value of each converter unit, and the single-machine efficiency curve can specifically be a function mapping relationship between the load power and the efficiency value.

[0056] In an embodiment of the present invention, a single-unit efficiency prediction model can be used to predict the single-unit efficiency of each parallel converter unit in a multi-unit parallel converter. Operating status data such as load, bus-side voltage, grid-side voltage, operating time, and ambient temperature of each converter unit can be input into the single-unit efficiency prediction model. The single-unit efficiency prediction model can then process the corresponding operating status data to obtain the single-unit efficiency. For each converter unit, a single-unit efficiency curve can be constructed based on the corresponding relationship between single-unit efficiency and load. The single-unit efficiency curve can have load as the horizontal axis and efficiency as the vertical axis.

[0057] Step 230: Determine the parallel efficiency curves when starting different numbers of converter units according to the efficiency curves of the individual units.

[0058] Specifically, after obtaining the single-machine efficiency curve of each converter unit in the multi-machine parallel converter, the parallel efficiency curve of the multiple converter units working in parallel can be determined. The parallel efficiency curve can be determined by the single-machine efficiency curves of the multiple converter units participating in the parallel work. The number of converter units participating in the parallel work can be 2, 3,..., N, where N can be the number of all converter units in the multi-machine parallel converter. That is, the parallel efficiency curve of multiple converters working in parallel can be determined by the single-machine efficiency curve of each converter.

[0059] In an embodiment of the present invention, different numbers of converter units can be selected to determine the parallel efficiency curve, and the single-machine efficiency curve of the selected converter unit can be used to determine the parallel efficiency curve. The determination process can be implemented by numerical fitting methods, optimization objective function methods, modeling and simulation analysis methods, aggregation modeling methods, etc. Taking the data fitting method as an example, according to the efficiency value of each converter unit at each load power, the numerical fitting method is used to obtain the parallel efficiency curve of the parallel converter when the corresponding multiple converter units are started; or, taking the optimization objective function method as an example, the optimization objective function is set by the single-machine efficiency curve of each converter unit, and the optimal efficiency of the parallel converter under each power load can be determined by the optimization objective function, so as to construct the parallel efficiency curve based on the optimal efficiency and the corresponding power load.

[0060] Furthermore, the parallel efficiency curve of the multi-machine parallel converter can determine different parallel efficiency curves according to the number of converter units selected for start-up and the types of converter units. For example, the multi-machine parallel converter may include converter unit A, converter unit B and converter unit C, and there may be three parallel efficiency curves corresponding to the two converter units, for example, including the parallel efficiency curve when converter unit A and converter unit B are started, the parallel efficiency curve when converter unit B and converter unit C are started, and the parallel efficiency curve when converter unit A and converter unit C are started, etc.

[0061] Step 240 : determining each single-machine efficiency curve and a partial efficiency curve with the highest efficiency in each parallel efficiency curve under different load powers, and obtaining a converter identifier of the converter unit to which each partial efficiency curve belongs.

[0062] Among them, the partial efficiency curve can be a part of the efficiency curve in the single-machine efficiency curve or the parallel efficiency curve for the same load power, and the efficiency value is higher than the efficiency value of other efficiency curves. The partial efficiency curve can be a part of the single-machine efficiency curve or a part of the parallel efficiency curve. The other efficiency curves can be the single-machine efficiency curve or the parallel efficiency curve other than the efficiency curve currently having the partial efficiency curve. The converter identifier can indicate the information of the converter unit in the multi-machine parallel converter. Different converter units can have different converter identifiers. The converter identifier can include the number, name or type name of the converter unit.

[0063] In an embodiment of the present invention, the single-machine efficiency curve and the parallel efficiency curve can be aligned according to the load power, the partial efficiency curve with the highest efficiency can be selected from all the single-machine efficiency curves and parallel efficiency curves, the single-machine efficiency curve or parallel efficiency curve to which each partial efficiency curve belongs can be determined, the converter unit corresponding to the above-mentioned single-machine efficiency curve or parallel efficiency curve can be obtained, and the converter identifier of the converter unit can be used as the converter identifier of the partial efficiency curve.

[0064] Step 250: Merge the partial efficiency curves into a system efficiency curve, and associate each converter identifier with a different load power range of the system efficiency curve according to the corresponding partial efficiency curve.

[0065] Specifically, each partial efficiency curve can be sequentially spliced according to its corresponding load power, and the efficiency curve generated after splicing can be used as the system efficiency curve. The system efficiency curve can be an efficiency curve composed of the highest efficiency that can be achieved by a multi-machine parallel converter. For each partial efficiency curve, its corresponding converter identifier can be associated with the corresponding responsible power in the system efficiency curve according to the load power corresponding to the partial efficiency curve. For example, the load power of the partial efficiency curve is 0.1 to 0.25, and the converter identifier of the partial efficiency curve can be associated with the load power range of 0.1 to 0.25 in the system efficiency curve. The association can include a physical association or a logical association. For example, the converter identifier and a load power range of the system efficiency curve can be stored in a configuration file, and the configuration file can be used as the association relationship between the converter identifier and the load power range of the system efficiency curve, or the converter identifier can be directly marked to the corresponding load power range in the system efficiency curve.

[0066] In an embodiment of the present invention, when part of the efficiency curve belongs to a single-machine efficiency curve, a converter identifier corresponding to the single-machine efficiency curve can be associated with the responsible power range corresponding to the system efficiency curve; when part of the efficiency curve belongs to a parallel efficiency curve, multiple converter identifiers corresponding to the parallel efficiency curve can be associated with the responsible power range corresponding to the system efficiency curve.

[0067] Step 260: Save the system efficiency curve and the identifiers of the converters associated with different load power ranges as a system efficiency model.

[0068] In an embodiment of the present invention, the system efficiency curve and the converter identifiers associated with different load power ranges in the system efficiency curve can be saved as a system efficiency model. The saving method may include saving it locally to a multi-machine parallel converter or to a host computer or cloud server of the multi-machine parallel converter.

[0069] Step 270: Obtain the current load power of the multi-machine parallel converter.

[0070] Step 280 : Determine a target converter corresponding to the current load power according to a preconfigured system efficiency model of the multi-machine parallel converter, wherein at least part of the load power corresponding to the system efficiency curve of the system efficiency model is associated with at least one converter.

[0071] Step 290: Control the multi-machine parallel converter to start the target converter to work in parallel.

[0072] In an embodiment of the present invention, a model training data set corresponding to a multi-machine parallel converter is obtained, an initial neural network model is trained as a single-machine efficiency prediction model according to the model training data, the single-machine efficiency model is called to predict the single-machine efficiency of converter units in the multi-machine parallel converter under different load powers, a single-machine efficiency curve is constructed based on the single-machine efficiency of each converter unit, parallel efficiency curves when starting different numbers of converter units are determined based on the single-machine efficiency curves of each converter unit, partial efficiency curves with the highest efficiency under each load power are selected from each single-machine efficiency curve and the parallel efficiency curve, converter identifiers of converter units corresponding to each partial efficiency curve are extracted, the partial efficiency curves are merged into a system efficiency curve, the converter identifier of each partial efficiency curve is associated with a load power range corresponding to the system efficiency curve, and the system efficiency curve is saved as a system efficiency model. Then, a current load power of the multi-machine parallel converter is obtained, a target converter unit corresponding to the current load power is determined using the system efficiency model, and the target converter units of the multi-machine parallel converter are controlled to operate in parallel. The embodiment of the present invention can determine the target converter unit to be controlled based on the system efficiency model corresponding to the maximum efficiency curve, provide a scientific basis for converter unit control, enhance the accuracy of converter control, enable the multi-machine parallel converter to be continuously in the maximum efficiency state, and improve the overall working efficiency of the system.

[0073] Furthermore, based on the above-mentioned embodiment of the invention, a model training data set of a multi-machine parallel converter is obtained, including:

[0074] The historical working status of each converter unit in a multi-machine parallel converter and the historical efficiency values corresponding to the historical working status are collected, where the historical working status includes at least: historical load power, historical bus-side voltage, historical grid-side voltage, historical operating time, and historical ambient temperature; linear interpolation is performed on the historical working status and historical efficiency values to obtain the interpolated working status and the interpolated predicted efficiency value corresponding to the interpolated working status; the historical working status, historical efficiency values, interpolated working status, and interpolated predicted efficiency values are used as the model training data set.

[0075] In an embodiment of the present invention, the historical working status and historical efficiency value of each converter unit in a multi-machine parallel converter can be obtained. The historical working status and historical efficiency value can be obtained through experiments. The historical working status and historical efficiency value can be linearly interpolated to obtain interpolation predicted efficiency values corresponding to other interpolation working states. A model training data set can be constructed based on the historical working status, historical efficiency value, interpolation working status and interpolation predicted efficiency value. Furthermore, the model training data set can also include the converter identification of the converter unit corresponding to the historical working status, historical efficiency value, interpolation working status and interpolation predicted efficiency value.

[0076] For example, since the amount of data measured by the experiment is small and limited, it is difficult to fully and accurately reflect the efficiency changes of the system under different conditions. The present invention first expands the data by linear interpolation. Figure 3 , Figure 4 , Figure 5 , Figure 6 The fitting becomes a function of the corresponding efficiency changing with the load, so a linear superposition method can be used to construct a comprehensive model. Assume that the bus voltage is V bus , the temperature is T, the grid side voltage is V grid , the running time is t. Let y bus is the efficiency function when only the bus voltage changes are considered. Similarly, for changes in grid voltage, temperature, and operating time, the efficiency function y can also be obtained. grid ,y T ,y t By using the linear interpolation method, the efficiency under different bus voltages, grid voltages, ambient temperatures, and operating times can be calculated. The formulas can be expressed as follows:

[0077]

[0078]

[0079]

[0080]

[0081] The comprehensive efficiency y can be approximately expressed as:

[0082]

[0083] Where y0 is the efficiency curve under baseline conditions. These baseline conditions can be conditions suitable for normal operation of the converter unit. These baseline conditions can include the load-efficiency relationship corresponding to a baseline bus voltage, a baseline grid-side voltage, a baseline ambient temperature, and a baseline operating time. This method can generate more representative data points based on the existing small amount of data, greatly enriching the data sample and improving its diversity and integrity.

[0084] Example 3

[0085] Figure 7 This is a flow chart of a system control method provided according to the third embodiment of the present invention. This embodiment of the present invention is a specific embodiment of the present invention. The target converter unit to be controlled in the multi-machine parallel converter is determined by the current load power and the system efficiency model. Figure 7 As shown, the method includes:

[0086] Step 310: Obtain the current load power of the multi-machine parallel converter.

[0087] Step 320: Obtain a system efficiency curve corresponding to a system efficiency model configured for a multi-machine parallel converter.

[0088] In an embodiment of the present invention, a separate system efficiency model can be configured for each type of multi-machine parallel converter. Different types of multi-machine parallel converters can be configured with different system efficiency models. The system efficiency model configured for the corresponding multi-machine parallel converter can be obtained. The system efficiency model can be configured on a host computer or server that manages the multi-machine parallel converter, or it can be configured locally on the multi-machine parallel converter. Taking the system efficiency model saved to the host computer or server as an example, the system efficiency curve stored in association with the type or identification number of the multi-machine parallel converter can be searched in the host computer or server according to the type or identification number of the multi-machine parallel converter.

[0089] Step 330: Determine the target load power range to which the current load power belongs within the system efficiency curve.

[0090] In the embodiment of the present invention, the target load power range to which the current load power value belongs may be determined according to the system efficiency curve, and the target load power range may have an associated converter identifier.

[0091] Step 340: Use the converter unit corresponding to the converter identifier associated with the target load power range in the system efficiency curve as the target converter unit.

[0092] In an embodiment of the present invention, a converter identifier associated with a target load power range of a system efficiency curve can be searched, and a converter unit corresponding to the converter identifier can be used as a target converter unit. Depending on the different association methods between the load power range and the converter identifier in the system efficiency curve, the converter identifier associated with the target load power range can be searched through different search methods. Taking the configuration file in which the load power range and the converter identifier are configured in the system efficiency curve as an example, the converter identifier stored in association with the target load power range can be searched in the configuration file. Taking the load power range marked by the converter identifier in the system efficiency curve as an example, the converter identifier marked in the system efficiency curve according to the target load power can be directly searched.

[0093] Step 350: Search the target output power of each target converter unit in the system efficiency model according to the target load power range of each target converter unit.

[0094] In an embodiment of the present invention, the system efficiency model may also include the output power of the converter unit associated with each load power range. The output power can be determined through simulation analysis, data fitting or actual operation data analysis. When the target converter unit is determined, the target output power corresponding to each target converter unit can also be searched in the system efficiency model.

[0095] Step 360: Control the target converter units in the multi-machine parallel converter to operate in parallel according to their respective target output powers, and switch the other converter units in the multi-machine parallel converter to a low power consumption operation mode.

[0096] In an embodiment of the present invention, the target converter unit in the multi-machine parallel converter can be controlled to switch to the working mode and operate according to the target output power determined by each, while the other converter units in the multi-machine parallel converter can be switched to the low-power operation mode. In the low-power operation mode, some non-critical components inside each converter unit, such as some auxiliary power supply circuits and some non-essential control chips, enter a sleep state, which can greatly reduce the energy consumption of the converter unit while retaining the key wake-up and quick start functions to ensure that it can respond to changes in power demand in a short time.

[0097] The embodiment of the present invention obtains the current load power of the multi-machine parallel converter, extracts the system efficiency curve of the multi-machine parallel converter configuration, searches for the target load power range corresponding to the current load power within the system efficiency curve, determines the converter identifier corresponding to the target load power range within the system efficiency model, uses the converter unit corresponding to the converter identifier as the target converter unit, and controls the target converter units within the multi-machine parallel converter to operate in parallel. The embodiment of the present invention determines the target converter unit that reaches the maximum efficiency state based on the system efficiency model, which can provide a scientific basis for converter control, enhance the accuracy of converter control, and ensure that the multi-machine parallel converter is continuously in the maximum efficiency state, thereby improving the overall working efficiency of the system.

[0098] Furthermore, based on the above embodiments of the invention, at least one of the following may be included:

[0099] When it is detected that the grid voltage of the multi-machine parallel converter rises or drops beyond a voltage threshold, all converter units of the multi-machine parallel converter are controlled to operate in parallel;

[0100] When it is determined that the current load power is greater than the load threshold, all converter units of the multi-machine parallel converter are controlled to operate in parallel.

[0101] The voltage threshold can be a critical value for determining a grid-side voltage jump. When the grid-side voltage increases or decreases by more than the voltage threshold, all converter units in the multi-machine parallel converter can be started. The load threshold can be a critical value for determining when the load exceeds the operating load of some converter units. The load threshold can be configured based on experience.

[0102] In an embodiment of the present invention, the grid voltage and / or current load kilometer of a multi-machine parallel converter can be continuously monitored. If it is determined that the grid voltage rises or drops beyond a voltage threshold, or if it is determined that the current load power is greater than a load threshold, all converter units of the multi-machine parallel converter can be controlled to operate in parallel, and all converter units of the multi-machine parallel converter can be switched to a working mode so that each converter unit can provide output power.

[0103] Furthermore, based on the above-mentioned embodiments of the invention, when it is detected that the grid-side voltage of a multi-machine parallel converter rises or drops beyond a voltage threshold, the overload current value corresponding to the grid-side voltage is determined, and the overload multiple of the multi-machine parallel converter for the overload current value is obtained; each converter unit is controlled to switch to a normal operating mode, and output power according to the overload multiple.

[0104] In an embodiment of the present invention, when the grid-side voltage rises or drops beyond a threshold, it is necessary to perform overload control on the multi-machine parallel converter, because when the grid-side voltage rises or drops, the converter needs to provide more reactive current to support the grid. The grid-side voltage change value of the voltage rise or drop can be determined, and the current change value of all converter units can be determined based on the rated current of each converter unit and the grid-side voltage change value. The current change value can be recorded as the overload current value, and the rated current value of each converter unit can be obtained. The ratio of the overload current value to the sum of the rated current values is used as the overload multiple, and each converter can be controlled to switch to a normal working mode and output power according to the overload multiple.

[0105] In some embodiments of the invention, it also includes: determining that the operating parameters of the first converter unit exceed a threshold, reducing the first output power of the first converter unit, and increasing the second output power of other converter units in the multi-machine parallel converter.

[0106] In an embodiment of the present invention, the converter units controlled by a multi-machine parallel converter can be monitored to determine the operating parameters of each converter unit. The operating parameters may include parameters such as output power, temperature, and current. When it is determined that the operating parameters exceed a threshold value, the converter unit can be marked as a first converter unit, the first output power of the first converter unit can be reduced, and the second output power of other converter units in the multi-machine parallel converter can be increased. It can be understood that the reduction in the first output power can be the same as the sum of the increases in all second output powers.

[0107] Example 4

[0108] An embodiment of the present invention provides a control system that can implement the system control method provided in any embodiment of the present invention. The system may include the following subsystems:

[0109] 1. Converter operating mode diversification subsystem: Three different operating modes are set for each converter unit: normal operating mode, low-power operating mode, and standby mode. In normal operating mode, all components of the converter unit operate at full power to meet the power requirements of the load. In low-power operating mode, some non-critical components within the converter unit, such as some auxiliary power circuits and some non-essential control chips, enter a dormant state, significantly reducing energy consumption while retaining key wake-up and fast startup functions to ensure that changes in power demand can be responded to in a short time. In standby mode, the converter unit only maintains the most basic wake-up and monitoring functions, consuming almost no power, further reducing system energy consumption.

[0110] 2. Intelligent Decision-Making and Control Subsystem: The central control unit incorporates advanced optimization algorithms and a detailed, accurate efficiency model. Generally, the converter efficiency curve rises and then falls as the load power increases. However, system efficiency is not static and can be significantly affected by many factors. To ensure the system consistently makes optimal operating decisions based on the accurate efficiency curve, it is necessary to predict the converter's efficiency under different loads by measuring and recording the ambient temperature, bus voltage, grid-side voltage, and operating time under actual converter operating conditions. Figure 3 The curves of efficiency changing with load and bus voltage are given. Under the same external conditions and the same output power, the converter efficiency decreases with the increase of bus voltage. Figure 4 The curves of efficiency changing with load and grid-side voltage are given. Under the same external conditions and the same output power, the converter efficiency decreases as the grid-side voltage decreases. Figure 5The efficiency curves that vary with load and temperature are given. Under the same external conditions and the same output power, the converter efficiency decreases as the temperature increases. In addition, as the converter runs for a longer time, the components will age and their parameters will change. For example, as the running time increases, the on-resistance and on-time of the controllable semiconductor devices in the converter will increase, and the parasitic resistance of the capacitor will increase, further reducing the efficiency. The efficiency curve is shown in Figure 1. Figure 6 shown.

[0111] Since the amount of data measured by experiments is small and limited, it is difficult to fully and accurately reflect the efficiency changes of the system under different conditions. The present invention first expands the data by linear interpolation. Figure 3 , Figure 4 , Figure 5 , Figure 6 The fitting becomes a function of the corresponding efficiency changing with the load, so a linear superposition method can be used to construct a comprehensive model. Assume that the bus voltage is V bus , the temperature is T, the grid side voltage is V grid , the running time is t. Let y bus is the efficiency function when only the bus voltage changes are considered. Similarly, for changes in grid voltage, temperature, and operating time, the efficiency function y can also be obtained. grid ,y T ,y t By using the linear interpolation method, the efficiency under different bus voltages, grid voltages, ambient temperatures, and operating times can be calculated. The formulas can be expressed as follows:

[0112]

[0113]

[0114]

[0115]

[0116] The comprehensive efficiency y can be approximately expressed as:

[0117]

[0118] Where y0 is the efficiency curve under the baseline conditions. Through the above method, we can generate more representative data points based on the existing small amount of data, greatly enriching the data sample and improving the diversity and integrity of the data.

[0119] After completing the data expansion, the efficiency curve under different conditions is predicted by the neural network method. The known system efficiency changes with bus voltage, temperature, grid voltage, and operating time are collected to form a data set. Each record in the data set can be (V bus ,V grid ,T,t,x,y), where V bus is the bus voltage, V grid is the grid voltage, T is the ambient temperature, t is the operating time, x is the load power, and y is the corresponding efficiency. All data are normalized so that their range is between [0,1]. A multi-layer perceptron neural network is used as the prediction model, and the input layer is set to 5 nodes, corresponding to the normalized bus voltage, grid voltage, temperature, operating time and load power respectively. Its hidden layer is set to 2-3 layers, and the number of neurons in each layer is determined based on experiments and optimization. The output layer is set to 1 node to output the normalized efficiency prediction value. The mean square error is used as the loss function to measure the difference between the model prediction value and the true value. The formula is:

[0120]

[0121] Where n is the number of samples, y i is the true value, .

[0122] The above method yields a curve showing the efficiency of a single converter as it changes with load output power. The overall efficiency first increases and then decreases with load power. Therefore, by selecting the number of converters connected in parallel and distributing the output power of the parallel converters, the overall system can operate at maximum efficiency as the load changes. For example, the system can operate from one converter alone to three converters in parallel. Figure 8 The efficiency curves are shown in Figure 2. Figure 8It can be seen that as the system power increases, there is a maximum efficiency point at a certain specific power for a single converter to three converters. Through in-depth analysis of the efficiency characteristics of a single converter under different power outputs, as well as the mutual influence and synergy mechanism when multiple converters are operated in parallel, it can be understood that the converter in the embodiment of the present application may include an inverter. When the central control unit receives the load power data, it will quickly compare and analyze it with the pre-set key power points P1 (the intersection of the efficiency curve of a single operation and the efficiency curve of two parallel operations), P2 (the intersection of the efficiency curve of two operations and the efficiency curve of three parallel operations), etc., and calculate the optimal converter operation plan under the current load conditions through the optimization algorithm based on the efficiency model. Specifically, when the load power is below point P1, the central control unit precisely selects the best-performing converter from among all converters and sends a command to it to enter normal operating mode, while simultaneously sending commands to the other converters to switch to low-power operating mode. When the load power is between points P1 and P2, the central control unit, after precise calculations, selects two converters to work together and rationally distributes power output between them to ensure optimal system efficiency. When the load power is greater than point P2, the central control unit instructs all three converters to operate simultaneously, and dynamically and precisely adjusts the output power of each converter based on the real-time load characteristics and the actual status of each converter to ensure that the system always operates at the highest efficiency. The same characteristics apply when more than three converters are connected in parallel. The system will appropriately select the number of converters in parallel and distribute the converter output power based on the current power status to maintain maximum system efficiency.

[0123] When different models are connected in parallel, although the efficiency curves of different models are inconsistent, the overall trends are the same. At this time, the system will first conduct a detailed analysis of the efficiency curves of each model and establish a comprehensive efficiency model. After receiving the load power data, the system will accurately calculate the power share that each different model inverter should bear based on the model. For example, when the load power is lower than a certain value, the system will select the inverter with the highest efficiency in this power range from all the different models of inverters and put it into operation, and the remaining inverters will enter low-power mode. When the load power is in different ranges, the system will select an appropriate number of different models of inverters to work together according to the principle of maximizing efficiency, and dynamically and accurately allocate power according to their respective efficiency curves, thereby ensuring that the system can always achieve maximum efficiency when different models are connected in parallel.

[0124] Overload switching subsystem: see Figure 9A dedicated overload detection module is set up in the central control unit. On the one hand, it detects the degree of grid voltage rise or drop. When the grid suddenly experiences low voltage ride-through or high voltage ride-through, the converter switches to an overload state and supports the grid by increasing the output reactive current. On the other hand, the overload threshold is set by real-time analysis of the load power data collected by the power sensor. Once an overload is detected, the central control unit immediately suspends the ongoing efficiency optimization-related calculations and analysis work and quickly sends an "overload" command to all converters in low-power operation mode, standby mode, and normal power output mode. Converters that receive the "overload" command quickly switch from low-power or standby mode to normal operation mode, no longer restricted by the current power allocation plan, and output power at maximum capacity to meet overload requirements. In overload operation mode, the central control unit continuously monitors the operating status of each converter, including parameters such as output power, temperature, and current. If a converter's temperature is too high, approaching a safety threshold, or if excessive current could damage the equipment, the control unit immediately reduces the power of that converter and instructs other converters to increase their output power appropriately to maintain the overall overload capacity and ensure safe and stable system operation under overload conditions. When the high or low voltage ride-through condition ends, or the load power decreases and remains below the overload threshold for a period of time, the central control unit determines that the overload condition has ended and instructs each converter to gradually return to normal, efficiency-optimized operation.

[0125] Furthermore, in an embodiment of the present invention, prediction is carried out by using a curve showing that the efficiency of a single converter varies with load. Figure 10 The predicted efficiency curve and the measured efficiency curve under specific working conditions are respectively shown, where the solid line is the predicted efficiency curve determined by the prediction model provided by the present invention, and the dotted line is the measured efficiency curve. It can be clearly seen that the predicted efficiency curve is extremely close to the actually measured efficiency curve, which strongly verifies the effectiveness of the prediction model provided by the embodiment of the present invention.

[0126] After successfully obtaining the efficiency curve of each converter under this working condition, the number of converters connected in parallel can be flexibly selected according to the current power demand, and the output power of each converter can be precisely controlled, thereby maximizing the system efficiency. Specifically, the rated power of the converter in this embodiment is 200kW, and there are two converters running in parallel. Since the parameters such as the operating time of these two converters are different, according to the efficiency curve prediction method described in the present invention, the predicted efficiency curve is as follows: Figure 11 As shown, assuming that the current power demand is 180kW, the loss of the two converters when they receive different powers can be obtained according to their efficiency curves, as shown in Figure 12As shown, the horizontal axis is the power output of the first converter, in kilowatts. After precise calculation using the method of the present invention, when the output power of one converter is 95.4kW and the output power of the other is 84.6kW, the efficiency of the entire system can reach its maximum value.

[0127] When the converter faces an overload, the system can respond quickly. In this example, two converters with a rated power of 200kW are connected in parallel, but the current power demand increases from 180kW to 380kW. To meet the power demand, both converters are allocated 190kW. The converters quickly switch from a mode that seeks maximum efficiency output to a maximum power output mode, ensuring that the system can still operate stably and meet the actual power demand during the overload condition. After the overload condition ends, the converters automatically return to the maximum efficiency output mode. Figure 13 and Figure 14 The waveforms of the system switching from maximum efficiency mode to maximum power output mode under overload conditions and from overload maximum power output mode to maximum efficiency output mode are shown respectively. Figure 13 and Figure 14 It can be seen that the system can run stably and respond quickly.

[0128] Example 5

[0129] Figure 15 Schematic diagram of a system control device according to the fifth embodiment of the present invention. The device is applied to a multi-machine parallel converter, which includes at least two parallel converter units, such as Figure 15 As shown, the device includes:

[0130] The power acquisition module 410 is used to acquire the current load power of the multi-machine parallel converter.

[0131] The target determination module 420 is used to determine the target converter unit corresponding to the current load power according to the pre-configured system efficiency model of the multi-machine parallel converter, wherein at least part of the load power corresponding to the system efficiency curve of the system efficiency model is associated with at least one converter unit.

[0132] The operation control module 430 is used for the parallel-connected converter to start the target converter units to operate in parallel.

[0133] In an embodiment of the present invention, the current load power of the multi-machine parallel converter is obtained through a power acquisition module, the target determination module determines the target converter unit to be started by the current load power through a system efficiency model configured for the multi-machine parallel converter, and the working control module controls the target converter units in the multi-machine parallel converter to work in parallel. The embodiment of the present invention determines the target converter that reaches the maximum efficiency state based on the system efficiency model, which can provide a scientific basis for converter control, enhance the accuracy of converter control, and enable the multi-machine parallel converter to be continuously in the maximum efficiency state, thereby improving the overall working efficiency of the system.

[0134] Based on the above embodiment of the invention, the invention further includes: a model configuration module, which includes:

[0135] A prediction model unit is used to obtain a model training data set for a multi-machine parallel converter, and train an initial neural network model as a single-machine efficiency prediction model according to the model training data set, wherein the initial neural network model includes at least one of the following: a multi-layer perceptron neural network model, a long short-term memory network model, a convolutional neural network model, and a wavelet neural network model.

[0136] The single-machine efficiency unit is used to call the single-machine efficiency prediction model to determine the single-machine efficiency of each converter unit in the multi-machine parallel converter under different load powers, and generate the corresponding single-machine efficiency curve of each converter unit according to the single-machine efficiency of each converter unit under different load powers.

[0137] The parallel efficiency unit is used to determine the parallel efficiency curve when starting different numbers of converter units according to the efficiency curve of each single machine.

[0138] The curve selection unit is used to determine the efficiency curves of each single machine and the partial efficiency curves with the highest efficiency in each parallel efficiency curve under different load powers, and obtain the converter identification of the converter to which each partial efficiency curve belongs.

[0139] The system efficiency unit is used to merge the partial efficiency curves into a system efficiency curve, associate each converter identifier with different load power ranges of the system efficiency curve according to the corresponding partial efficiency curve; and save the system efficiency curve and each converter identifier associated with different load power ranges as a system efficiency model.

[0140] Based on the above-mentioned embodiment of the invention, the prediction model unit obtains a model training data set of a multi-machine parallel converter, including:

[0141] Collecting the historical operating status of each converter unit in the multi-machine parallel converter and the historical efficiency value corresponding to the historical operating status, wherein the historical operating status includes at least: historical load power, historical bus side voltage, historical grid side voltage, historical operating time and historical ambient temperature;

[0142] Performing linear interpolation on historical working states and historical efficiency values to obtain interpolated working states and interpolated predicted efficiency values corresponding to the interpolated working states;

[0143] The historical working status, historical efficiency values, interpolated working status and interpolated predicted efficiency values are used as the model training data set.

[0144] Based on the above embodiments of the invention, the target determination module 420 includes:

[0145] The curve loading unit is used to obtain a system efficiency curve corresponding to a system efficiency model configured for a multi-machine parallel converter.

[0146] The load range unit is used to determine a target load power range to which the current load power belongs within the system efficiency curve.

[0147] The target search unit is configured to use the converter corresponding to the converter identifier associated with the target load power range in the system efficiency curve as the target converter unit.

[0148] Based on the above-mentioned embodiments of the invention, the system efficiency model also includes the output power of converter units associated with different load power ranges. The working control module 430 is specifically used to: search for the target output power of each target converter unit in the system efficiency model according to the target load power range of each target converter unit; control each target converter unit in the multi-machine parallel converter to operate in parallel according to their respective target output powers, and switch other converter units in the multi-machine parallel converter to a low-power operation mode.

[0149] In some embodiments of the invention, an exception handling module is also included, which is used for at least one of the following: when it is detected that the grid-side voltage of the multi-machine parallel converter rises or drops beyond the voltage threshold, all converter units of the multi-machine parallel converter are controlled to operate in parallel; when it is determined that the current load power is greater than the load threshold, all converter units of the multi-machine parallel converter are controlled to operate in parallel.

[0150] In some embodiments of the invention, controlling all converter units of a multi-machine parallel converter to operate in parallel specifically includes: when detecting that the grid-side voltage of the multi-machine parallel converter rises or drops beyond a voltage threshold, determining the overload current value corresponding to the grid-side voltage, and obtaining the overload multiple of the multi-machine parallel converter for the overload current value; controlling each converter unit to switch to a normal operating mode, and outputting power according to the overload multiple.

[0151] Based on the above-mentioned embodiment of the invention, it also includes a power adjustment module, which is used to determine that the operating parameters of the first converter unit exceed the threshold, thereby reducing the first output power of the first converter unit and increasing the second output power of other converter units in the multi-machine parallel converter.

[0152] The system control device provided in the embodiment of the present invention can execute the system control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0153] Example 6

[0154] Figure 16 is a schematic diagram of the structure of an electronic device that implements the system control method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0155] like Figure 16 As shown, electronic device 10 includes at least one processor 11 and memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by the at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer programs stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. An input / output (I / O) interface 15 is also connected to bus 14.

[0156] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0157] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as the system control method.

[0158] In some embodiments, the system control method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the system control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the system control method in any other suitable manner (e.g., via firmware).

[0159] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0161] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0162] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0163] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0164] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0165] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0166] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A power system control method, characterized in that: Applied to a multi-machine parallel converter, the multi-machine parallel converter includes at least two parallel converter units, and the method includes: Obtain a model training data set for the multi-machine parallel converter, and train an initial neural network model as a single-machine efficiency prediction model according to the model training data set, wherein the initial neural network model includes at least one of the following: a multi-layer perceptron neural network model, a long short-term memory network model, a convolutional neural network model, and a wavelet neural network model. Obtaining the model training data set for the multi-machine parallel converter includes: collecting historical working states of each converter unit in the multi-machine parallel converter and historical efficiency values corresponding to the historical working states, wherein the historical working states include at least historical load power, historical bus-side voltage, historical grid-side voltage, historical operating time, and historical ambient temperature; performing linear interpolation on the historical working states and the historical efficiency values to obtain interpolated working states and interpolated predicted efficiency values corresponding to the interpolated working states; and using the historical working states, the historical efficiency values, the interpolated working states, and the interpolated predicted efficiency values as the model training data set; Calling the single-machine efficiency prediction model to respectively determine the single-machine efficiency of each converter unit in the multi-machine parallel converter under different load powers, and generating a single-machine efficiency curve corresponding to each converter unit according to the single-machine efficiency of each converter unit under different load powers; Determining, according to each of the single-machine efficiency curves, a parallel efficiency curve when starting different numbers of the converter units; determining each of the single-machine efficiency curves and a partial efficiency curve with the highest efficiency in each of the parallel efficiency curves under different load powers, and obtaining a converter identifier of the converter unit to which each of the partial efficiency curves belongs; Combining the partial efficiency curves into a system efficiency curve, and associating the converter identifiers with different load power ranges of the system efficiency curve according to the corresponding partial efficiency curves; saving the system efficiency curve and the identifiers of the converters associated with the different load power ranges as a system efficiency model; Obtaining the current load power of the multi-machine parallel converter; Determine the target converter unit corresponding to the current load power according to the system efficiency model pre-configured for the multi-machine parallel converter, wherein at least part of the load power corresponding to the system efficiency curve of the system efficiency model is associated with at least one of the converter units; determining the target converter unit corresponding to the current load power according to the system efficiency model pre-configured for the multi-machine parallel converter comprises: obtaining the system efficiency curve corresponding to the system efficiency model configured for the multi-machine parallel converter; determining the target load efficiency range to which the current load power belongs within the system efficiency curve; and using the converter corresponding to the converter identifier associated with the target load efficiency range within the system efficiency curve as the target converter unit; The multi-machine parallel converter is controlled to start the target converter units to operate in parallel.

2. The method according to claim 1, characterized in that The system efficiency model further includes output powers of converter units associated with different load power ranges, and controlling the multi-machine parallel converter to start the target converter units to operate in parallel includes: searching for a target output power of each target converter unit in the system efficiency model according to a target load power range of each target converter unit; The target converter units in the multi-machine parallel converter are controlled to operate in parallel according to their respective target output powers, and the other converter units in the multi-machine parallel converter are switched to a low power consumption operation mode.

3. The method according to claim 1, characterized in that Also includes at least one of the following: When detecting that the grid-side voltage of the multi-machine parallel converter rises or drops beyond a voltage threshold, controlling all the converter units of the multi-machine parallel converter to operate in parallel; When it is determined that the current load power is greater than a load threshold, all the converter units of the multi-machine parallel converter are controlled to operate in parallel.

4. The method according to claim 3, characterized in that The controlling all the converter units of the multi-machine parallel converter to operate in parallel includes: When detecting that the grid-side voltage of the multi-machine parallel converter rises or drops beyond a voltage threshold, determining an overload current value corresponding to the grid-side voltage, and obtaining an overload multiple of the multi-machine parallel converter for the overload current value; Control each of the converter units to switch to a normal operating mode and output power according to the overload multiple.

5. The method according to claim 3 or 4, characterized in that: Also includes: If it is determined that the operating parameter of the first converter unit exceeds a threshold, the first output power of the first converter unit is reduced, and the second output power of other converter units in the multi-machine parallel converter is increased.

6. A power system control device, characterized in that: Applicable to a multi-machine parallel converter, the multi-machine parallel converter includes at least two parallel converter units, and the device includes: The model configuration module includes: a prediction model unit, which is used to obtain a model training data set of the multi-machine parallel converter, and train an initial neural network model as a single-machine efficiency prediction model according to the model training data set, wherein the initial neural network model includes at least one of the following: a multi-layer perceptron neural network model, a long short-term memory network model, a convolutional neural network model and a wavelet neural network model, collect the historical working status of each converter unit in the multi-machine parallel converter and the historical efficiency value corresponding to the historical working status, wherein the historical working status at least includes: historical load power, historical bus side voltage, historical grid side voltage, historical operating time and historical ambient temperature; linearly interpolate the historical working status and the historical efficiency value to obtain the interpolated working status and the interpolated predicted efficiency value corresponding to the interpolated working status; use the historical working status, the historical efficiency value, the interpolated working status and the interpolated predicted efficiency value as the model training data set; a single-machine An efficiency unit, used to call the single-machine efficiency prediction model to respectively determine the single-machine efficiency of each converter unit in the multi-machine parallel converter under different load powers, and generate a single-machine efficiency curve corresponding to each converter unit according to the single-machine efficiency of each converter unit under different load powers; a parallel efficiency unit, used to determine the parallel efficiency curve when starting different numbers of converter units according to each single-machine efficiency curve; a curve selection unit, used to determine each single-machine efficiency curve and the partial efficiency curve with the highest efficiency in each parallel efficiency curve under different load powers, and obtain the converter identifier of the converter unit to which each partial efficiency curve belongs; a system efficiency unit, used to merge each partial efficiency curve into a system efficiency curve, and associate each converter identifier with different load power ranges of the system efficiency curve according to the corresponding partial efficiency curve; and save the system efficiency curve and each converter identifier associated with different load power ranges as a system efficiency model; A power acquisition module, configured to acquire the current load power of the multi-machine parallel converter; A target determination module is used to determine the target converter unit corresponding to the current load power according to the system efficiency model pre-configured for the multi-machine parallel converter, wherein at least part of the load power corresponding to the system efficiency curve of the system efficiency model is associated with at least one of the converter units; the determining the target converter unit corresponding to the current load power according to the system efficiency model pre-configured for the multi-machine parallel converter comprises: obtaining the system efficiency curve corresponding to the system efficiency model configured for the multi-machine parallel converter; determining the target load efficiency range to which the current load power belongs within the system efficiency curve; and using the converter corresponding to the converter identifier associated with the target load efficiency range within the system efficiency curve as the target converter unit; The operation control module is used to control the multi-machine parallel converter to start the target converter units to operate in parallel.

7. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the power system control method according to any one of claims 1 to 5.

Images