Converter grid-connected control method and device based on prediction model, equipment and medium

Abstract

The invention relates to a prediction model-based converter grid-connected control method and device, equipment and a medium. According to the method, a load prediction value is obtained through prediction according to a plurality of load sampling values, a load difference value is determined by combining the load prediction value and a load reference value, an energy storage prediction value is obtained through prediction according to the load difference value, an energy storage state value is further obtained, and the load reference value is fed back and adjusted according to the energy storage state value and an energy storage threshold value. Therefore, it is ensured that the energy storage state value corresponding to each target sampling point meets the preset condition, the situation that a battery pack corresponding to the energy storage converter cannot supply the load requirement of the target power grid is avoided, and therefore under the situation that stable operation of the target power grid is ensured, manual setting of a load reference value is not needed, and the efficiency of converter grid-connected control is improved.

Description

Technical Field

[0001] The present invention is applicable to the field of converter control, and in particular relates to a method, device, equipment and medium for converter grid-connected control based on a prediction model. Background Art

[0002] At present, in the power system, the energy storage system can enhance the regulation ability of the power supply, and the two-way conversion between the energy storage system and the power system is usually achieved through the energy storage inverter. The energy storage inverter can control the charging and discharging process of the energy storage system and perform AC / DC conversion. It can invert the DC power of the energy storage system into AC power and transmit it to the power grid or use it for AC loads, and it can also rectify the AC power of the power grid into DC power to charge the energy storage system.

[0003] In the grid-connected mode, usually during the load valley period, the energy storage inverter rectifies the AC power of the grid into DC power to charge the battery pack. During the load peak period, the energy storage inverter inverts the DC power in the battery pack into AC power and sends it back to the grid.

[0004] However, in actual applications, load troughs and peaks are usually determined by manually set load thresholds, which are affected by subjective factors and may cause the battery pack's energy storage to be unable to meet the grid load requirements. Moreover, there are differences in the battery pack status, grid status, and load status in different scenarios. Even if the manually set load threshold in a certain scenario is more reliable, it cannot be reused in other scenarios, which requires a lot of human resources and results in low control efficiency and accuracy of the converter. Therefore, how to improve the control efficiency of the converter has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method, device, equipment and medium for controlling a converter connected to a grid based on a prediction model to solve the problem.

[0006] In a first aspect, a method for controlling a converter connected to a grid based on a prediction model is provided, the method comprising: Obtain the load sampling values ​​corresponding to the M first sampling points of the target power grid, where M is a positive integer; Input the M load sampling values ​​into the trained load forecasting model to obtain the load forecasting values ​​corresponding to the N second sampling points, where N is a positive integer; The M load sampling values ​​and the N load prediction values ​​are used as the load sample values ​​corresponding to the M+N target sampling points respectively; For any load sample value, according to the load sample value and the load reference value obtained by initialization, a load difference value corresponding to the load sample value is obtained; Input the M+N load difference values ​​into the trained energy storage prediction model respectively to obtain M+N energy storage prediction values; According to the M+N energy storage prediction values, M+N energy storage state values ​​are obtained; A first training loss is calculated according to the M+N energy storage state values ​​and a preset energy storage threshold, and the load reference value is updated according to the first training loss to obtain a load target value; According to the load target value and the N load forecast values, grid-connection control is performed on the energy storage converter corresponding to the target power grid at the N second sampling points respectively.

[0007] In a second aspect, a converter grid-connected control device based on a prediction model is provided, the device comprising: A load sampling module is used to obtain the load sampling values ​​corresponding to the M first sampling points of the target power grid, where M is a positive integer; A load prediction module, used for inputting M load sampling values ​​into a trained load prediction model to obtain load prediction values ​​corresponding to N second sampling points, where N is a positive integer; A sample construction module, used to use the M load sampling values ​​and the N load prediction values ​​as load sample values ​​corresponding to M+N target sampling points respectively; A difference calculation module, used for obtaining, for any load sample value, a load difference value corresponding to the load sample value according to the load sample value and an initialized load reference value; The energy storage prediction module is used to input M+N load difference values ​​into the trained energy storage prediction model to obtain M+N energy storage prediction values; A state calculation module, used to obtain M+N energy storage state values ​​according to the M+N energy storage prediction values; A parameter updating module, configured to calculate a first training loss according to the M+N energy storage state values ​​and a preset energy storage threshold, and update the load reference value according to the first training loss to obtain a load target value; A grid-connected control module is used to perform grid-connected control on the energy storage converter corresponding to the target power grid at the N second sampling points according to the load target value and the N load forecast values.

[0008] In a third aspect, an embodiment of the present invention provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, it implements the inverter grid-connected control method as in the first aspect.

[0009] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for controlling the grid-connected converter according to the first aspect is implemented.

[0010] Compared with the prior art, the present invention has the following beneficial effects: A load prediction value is obtained based on a number of load sampling values. The load difference value is determined by combining the load prediction value and the load reference value. Then, an energy storage prediction value is obtained based on the load difference value prediction, and then an energy storage state value is obtained. According to the energy storage state value and the energy storage threshold, the load reference value is adjusted through feedback to ensure that the energy storage state value corresponding to each target sampling point meets the preset conditions, avoiding the situation where the battery group corresponding to the energy storage inverter cannot supply the load demand of the target power grid. Therefore, while ensuring the stable operation of the target power grid, there is no need to manually set the load reference value, thereby improving the efficiency of the inverter grid-connected control. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative labor. Figure 1 1 is a schematic diagram of an application environment of a method for controlling a grid-connected converter based on a prediction model provided in Embodiment 1 of the present invention; Figure 2 It is a flow chart of a method for controlling a grid-connected converter based on a prediction model provided in the first embodiment of the present invention; Figure 3 is a structural schematic diagram of a converter grid-connected control device based on a prediction model provided in Embodiment 2 of the present invention; Figure 4 It is a structural schematic diagram of a computer device corresponding to a method for controlling a grid-connected converter based on a prediction model provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0013] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0014] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0015] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0016] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0017] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0018] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0019] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0020] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0021] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0022] A method for controlling a grid-connected converter based on a prediction model provided by the first embodiment of the present invention can be applied in the following aspects: Figure 1 In an application environment, the client communicates with the energy storage converter. The client includes but is not limited to PDAs, desktop computers, laptops, ultra-mobile personal computers (UMPCs), netbooks, cloud terminal devices, personal digital assistants (PDAs) and other terminal devices. The energy storage converter can be used to rectify the AC power of the target power grid into DC power to charge the battery pack corresponding to the energy storage converter, and can also be used to invert the DC power in the battery pack corresponding to the energy storage converter into AC power and send it back to the target power grid.

[0023] See also Figure 2 , is a flow chart of a method for controlling a current transformer connected to a grid based on a prediction model provided in the first embodiment of the present invention. The method for controlling a current transformer connected to a grid can be applied to Figure 1 In the client, the client obtains M load sampling values ​​from the target power grid and obtains the energy storage threshold from the user side. The client has a storage function and stores the trained load prediction model and the trained energy storage prediction model. Figure 2 As shown, the converter grid-connected control method may include the following steps: Step S201, obtaining load sampling values ​​corresponding to M first sampling points of the target power grid.

[0024] Among them, M is a positive integer, the target power grid corresponds to the energy storage converter and the user side, the power demand on the user side is the power load of the target power grid, and the user side can include various types of power consumers such as industry, commerce, and residents.

[0025] The first sampling point may refer to a moment when the load of the target power grid is actually sampled, and the load sampling value may refer to a result of actually sampling the load of the target power grid at the corresponding first sampling point.

[0026] Specifically, the time interval between the M first sampling points may be a fixed value, for example, the fixed value may be 30 minutes, and the implementer may adjust the fixed value according to actual conditions.

[0027] Step S202: input the M load sampling values ​​into the trained load prediction model to obtain the load prediction values ​​corresponding to the N second sampling points respectively.

[0028] Wherein, N is a positive integer. The trained load prediction model can be used to predict the load value corresponding to the next sampling point based on the load values ​​corresponding to several input sampling points. The sampling points may include a first sampling point and a second sampling point. Accordingly, the load value corresponding to the sampling point may include a load sampling value corresponding to the first sampling point and a load prediction value corresponding to the second sampling point.

[0029] Specifically, the input of the trained load prediction model is a first fixed number of load values, and the output is a second fixed number of load values. In this embodiment, the first fixed number may be M, and the second fixed number may be 1.

[0030] Optionally, the M load sampling values ​​are input into a trained load forecasting model to obtain load forecasting values ​​corresponding to the N second sampling points, including: Input the M load sampling values ​​into the trained load forecasting model to obtain the load forecast value corresponding to the first second sampling point; Initialize n=1, input the load sampling value from the n+1th to the Mth load sampling value, and the load prediction value corresponding to the first second sampling point to the load prediction value corresponding to the nth second sampling point into the trained load prediction model, and obtain the load prediction value corresponding to the n+1th second sampling point; Update n=n+1, return to execute the step of converting the n+1th load sampling value to the Mth load sampling value, and the load prediction value corresponding to the first second sampling point to the load prediction value corresponding to the nth second sampling point, inputting them into the trained load prediction model, and obtaining the load prediction value corresponding to the n+1th second sampling point, until n+1=N, and obtaining the load prediction values ​​corresponding to the N second sampling points respectively.

[0031] Among them, this embodiment takes the first fixed number as M as an example. For the first prediction, M load sampling values ​​are input into the trained load prediction model to obtain the load prediction value corresponding to the first second sampling point. For the second prediction, n=1, and the load sampling values ​​from the second to the Mth load sampling values, and the load prediction value corresponding to the first second sampling point, are input into the trained load prediction model to obtain the load prediction value corresponding to the second second sampling point. For the third prediction, n=2, and the load sampling values ​​from the third to the Mth load sampling values, and the load prediction values ​​corresponding to the first second sampling point to the second second sampling point, are input into the trained load prediction model to obtain the load prediction value corresponding to the third second sampling point, and so on, until the load prediction values ​​corresponding to the N second sampling points are obtained.

[0032] Specifically, in this embodiment, it is assumed that the time interval between the first sampling points is longer than the prediction duration of the load prediction model, so there is no need to consider collecting new load sampling values ​​when the load prediction model is used.

[0033] In this embodiment, long-term load prediction can be achieved through iterative prediction, thereby eliminating the need to frequently collect load information, improving load prediction efficiency, and further improving the efficiency of overall converter control.

[0034] Step S203: Taking the M load sampling values ​​and the N load prediction values ​​as the load sample values ​​corresponding to the M+N target sampling points respectively.

[0035] The target sampling point may include a first sampling point and a second sampling point, and the load sample value may include a load sampling value and a load prediction value.

[0036] Step S204 , for any load sample value, a load difference value corresponding to the load sample value is obtained according to the load sample value and the initialized load reference value.

[0037] The load reference value may be used to determine the working state of the energy storage converter, and the working state of the energy storage converter may include a charging state and a discharging state.

[0038] The load difference value can be used to characterize the difference between the load sample value and the load reference value.

[0039] Specifically, the implementer may multiply the maximum value of all load sample values ​​by a preset coefficient and use the multiplication result as the initialization value of the load reference value. In this embodiment, the preset coefficient may be set to 0.5.

[0040] Optionally, for any load sample value, a load difference value corresponding to the load sample value is obtained according to the load sample value and the load reference value obtained by initialization, including: For any load sample value, subtract the load sample value from the load reference value, and use the subtraction result as the load difference value corresponding to the load sample value; The M+N load sample values ​​are traversed to obtain the load difference values ​​corresponding to the M+N load sample values.

[0041] When the load sample value is less than the load reference value, the load difference value is a negative value, and when the load sample value is greater than the load reference value, the load difference value is a positive value.

[0042] Step S205, inputting the M+N load difference values ​​into the trained energy storage prediction model respectively to obtain M+N energy storage prediction values.

[0043] Among them, the energy storage prediction model can be used to predict the energy storage change value of the battery group corresponding to the energy storage inverter according to the load difference value.

[0044] Optionally, the training process of the energy storage prediction model includes: Obtaining an actual energy storage value of the energy storage converter corresponding to the fourth sampling point, and an actual load value and an actual control value of the target power grid corresponding to the fourth sampling point; According to the actual load value and the actual control value, the actual difference value is obtained; The actual difference value is input into the energy storage prediction model to obtain the target energy storage value; According to the target energy storage value and the actual energy storage value, a second training loss is calculated, and the energy storage prediction model is trained according to the second training loss to obtain a trained energy storage prediction model.

[0045] Among them, the fourth sampling point may refer to a time point in the historical operation of the energy storage inverter, and the actual energy storage value may refer to the energy storage energy change value of the energy storage inverter at the fourth sampling point. When the actual energy storage value is a positive value, it indicates that the energy storage energy of the energy storage inverter at the fourth sampling point increases, and the energy storage inverter is in a charging state. When the actual energy storage value is a negative value, it indicates that the energy storage energy of the energy storage inverter at the fourth sampling point decreases, and the energy storage inverter is in a discharging state.

[0046] The actual load value may refer to the load information corresponding to the target power grid at the fourth sampling point, and the actual control value may refer to the load threshold corresponding to the energy storage converter at the fourth sampling point.

[0047] The target energy storage value may refer to a predicted value obtained by an energy storage prediction model according to the actual difference value.

[0048] Specifically, according to the target energy storage value and the actual energy storage value, a second training loss is calculated by a mean square error loss function. According to the second training loss, the model parameters of the energy storage prediction model are trained using a reverse gradient descent method to obtain a trained energy storage prediction model.

[0049] In one embodiment, since the battery pack capacity corresponding to the energy storage inverter may be different, the input of the energy storage prediction model also includes the battery pack capacity. Accordingly, during training, the actual battery pack capacity corresponding to the energy storage inverter is also obtained, and the actual difference value and the actual battery pack capacity are input into the energy storage prediction model to obtain the target energy storage value.

[0050] Step S206, obtaining M+N energy storage state values ​​according to the M+N energy storage prediction values.

[0051] The energy storage state value may be used to characterize the energy storage capacity of the battery pack corresponding to the energy storage converter at the corresponding target sampling point.

[0052] Optionally, M+N energy storage state values ​​are obtained according to the M+N energy storage prediction values, including: For the j-th energy storage prediction value, calculate the sum of the first energy storage prediction value to the j-th energy storage prediction value, and use the sum as the j-th energy storage state value corresponding to the j-th energy storage prediction value, where j is an integer in the range of [1, M+N]; Traverse M+N energy storage prediction values ​​to obtain M+N energy storage state values.

[0053] Among them, the energy storage prediction value can be used to characterize the energy storage energy change value of the battery group corresponding to the energy storage converter. Therefore, the energy storage state value can be used to characterize the energy storage energy of the battery group corresponding to the energy storage converter.

[0054] In one embodiment, the battery pack energy storage amount corresponding to the first target sampling point is obtained, and accordingly, for the jth energy storage prediction value, the sum of the first energy storage prediction value to the jth energy storage prediction value and the battery pack energy storage amount is calculated, and the sum is used as the jth energy storage state value corresponding to the jth energy storage prediction value.

[0055] Step S207, calculating a first training loss according to the M+N energy storage state values ​​and a preset energy storage threshold, and updating the load reference value according to the first training loss to obtain a load target value.

[0056] The energy storage threshold may be set by the implementer, and the energy storage threshold may be used to ensure that the energy storage capacity of the battery pack is not too low.

[0057] Optionally, the first training loss is calculated according to the M+N energy storage state values ​​and a preset energy storage threshold, including: Subtract the M+N energy storage state values ​​from the energy storage threshold value to obtain M+N energy storage difference values; The M+N energy storage difference values ​​are respectively mapped through a preset mapping function to obtain mapping values ​​corresponding to the energy storage difference values; The sum of all mapped values ​​is used as the first training loss.

[0058] Among them, the energy storage threshold in this embodiment can be 0, and the mapping function can be a negative exponential function. When the energy storage difference is less than 0, it is usually a value greater than 1 after mapping through the negative exponential function. When the energy storage difference is greater than 0, it is usually a value less than 1 after mapping through the negative exponential function. Therefore, when any energy storage difference is less than 0, the first training loss will be large, thereby feedback adjusting the load reference value.

[0059] Specifically, in order to improve the target power grid's ability to withstand load fluctuations, the implementer may set the energy storage threshold to a value greater than 0, so that when the load is greater than expected, the battery pack still has a certain amount of energy storage to maintain the stability of the target power grid.

[0060] Step S208, according to the load target value and the N load forecast values, the energy storage converters corresponding to the target power grid are respectively controlled to be connected to the grid at the N second sampling points.

[0061] Optionally, according to the load target value and the N load forecast values, the energy storage converter corresponding to the target power grid is respectively connected to the grid at the N second sampling points, including: For any second sampling point, when the load prediction value corresponding to the second sampling point is greater than the load target value, the energy storage converter is controlled to discharge to the target power grid; When the load prediction value corresponding to the second sampling point is less than the load target value, the target power grid is controlled to charge the energy storage converter.

[0062] Among them, when the load prediction value corresponding to the second sampling point is greater than the load target value, the energy storage inverter is required to provide additional power. Therefore, the energy storage inverter is controlled to discharge to the target power grid. When the load prediction value corresponding to the second sampling point is less than the load target value, the target power grid has redundant power that can be stored in the energy storage inverter. Therefore, the target power grid is controlled to charge the energy storage inverter.

[0063] This embodiment predicts a load prediction value based on a number of load sampling values, combines the load prediction value and the load reference value to determine the load difference value, and then predicts an energy storage prediction value based on the load difference value, and then obtains the energy storage state value. According to the energy storage state value and the energy storage threshold, the load reference value is feedback-adjusted to ensure that the energy storage state value corresponding to each target sampling point meets the preset conditions, avoiding the situation where the battery group corresponding to the energy storage inverter cannot supply the load demand of the target power grid. Therefore, while ensuring the stable operation of the target power grid, there is no need to manually set the load reference value, thereby improving the efficiency of the inverter grid-connected control.

[0064] Corresponding to the method of the above embodiment 1, Figure 3A schematic diagram of the structure of a converter grid-connected control device based on a prediction model provided in the second embodiment of the present invention is shown. The converter grid-connected control device is applied to a client, and the client obtains M load sampling values ​​from the target power grid and obtains the energy storage threshold from the user side. The client has a storage function, and the client stores a trained load prediction model and a trained energy storage prediction model. For ease of explanation, only the part related to the embodiment of the present invention is shown.

[0065] See also Figure 3 , the converter grid-connected control device comprises: The load sampling module 31 is used to obtain the load sampling values ​​corresponding to the M first sampling points of the target power grid, where M is a positive integer; The load prediction module 32 is used to input the M load sampling values ​​into the trained load prediction model to obtain the load prediction values ​​corresponding to the N second sampling points, where N is a positive integer; A sample construction module 33 is used to use M load sample values ​​and N load prediction values ​​as load sample values ​​corresponding to M+N target sampling points respectively; The difference calculation module 34 is used to obtain, for any load sample value, a load difference value corresponding to the load sample value according to the load sample value and the load reference value obtained by initialization; The energy storage prediction module 35 is used to input the M+N load difference values ​​into the trained energy storage prediction model to obtain M+N energy storage prediction values; A state calculation module 36, used to obtain M+N energy storage state values ​​according to the M+N energy storage prediction values; A parameter updating module 37 is used to calculate a first training loss according to the M+N energy storage state values ​​and a preset energy storage threshold, and to update a load reference value according to the first training loss to obtain a load target value; The grid-connected control module 38 is used to perform grid-connected control on the energy storage converters corresponding to the target power grid at N second sampling points according to the load target value and the N load forecast values.

[0066] Optionally, the load forecasting module 32 includes: A first prediction unit is used to input M load sampling values ​​into a trained load prediction model to obtain a load prediction value corresponding to the nth second sampling point; The second prediction unit is used to initialize n=1, input the load sampling value from the n+1th to the Mth load sampling value, and the load prediction value corresponding to the first second sampling point to the load prediction value corresponding to the nth second sampling point into the trained load prediction model, and obtain the load prediction value corresponding to the n+1th second sampling point; The third prediction unit is used to update n=n+1, and returns to execute the step of inputting the n+1th load sampling value to the Mth load sampling value, and the load prediction value corresponding to the first second sampling point to the load prediction value corresponding to the nth second sampling point into the trained load prediction model to obtain the load prediction value corresponding to the n+1th second sampling point, until n+1=N, and obtains the load prediction values ​​corresponding to the N second sampling points respectively.

[0067] Optionally, the difference calculation module 34 includes: A first subtraction unit is used for subtracting the load sample value from the load reference value for any load sample value, and taking the subtraction result as the load difference value corresponding to the load sample value; The first traversal unit is used to traverse M+N load sample values ​​to obtain load difference values ​​corresponding to the M+N load sample values.

[0068] Optionally, the above-mentioned converter grid-connected control device further includes: A data acquisition module, used to acquire an actual energy storage value of the energy storage converter corresponding to the fourth sampling point, and an actual load value and an actual control value of the target power grid corresponding to the fourth sampling point; A sample difference determination module, used for obtaining an actual difference value according to an actual load value and an actual control value; A sample prediction module is used to input the actual difference value into the energy storage prediction model to obtain the target energy storage value; The model training module is used to calculate a second training loss according to a target energy storage value and an actual energy storage value, and train the energy storage prediction model according to the second training loss to obtain a trained energy storage prediction model.

[0069] Optionally, the state calculation module 36 includes: a summation calculation unit, for calculating the summation result of the first energy storage prediction value to the jth energy storage prediction value for the jth energy storage prediction value, and taking the summation result as the jth energy storage state value corresponding to the jth energy storage prediction value, where j is an integer in the range of [1, M+N]; The second traversal unit is used to traverse M+N energy storage prediction values ​​to obtain M+N energy storage state values.

[0070] Optionally, the parameter updating module 37 includes: A subtraction calculation unit, used for subtracting the M+N energy storage state values ​​from the energy storage threshold value respectively to obtain M+N energy storage difference values; A mapping unit, used to map the M+N energy storage difference values ​​respectively through a preset mapping function to obtain mapping values ​​corresponding to the energy storage difference values; The loss determination unit is used to take the sum of all mapped values ​​as the first training loss.

[0071] Optionally, the above-mentioned grid connection control module 38 includes: A first control unit is used for controlling the energy storage converter to discharge to the target power grid when the load prediction value corresponding to any second sampling point is greater than the load target value; The second control unit is used to control the target power grid to charge the energy storage converter when the load prediction value corresponding to the second sampling point is less than the load target value.

[0072] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules and units are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0073] Figure 4 A schematic diagram of the structure of a computer device corresponding to a method for controlling a grid-connected converter based on a prediction model provided in Embodiment 3 of the present invention. Figure 4 As shown, the computer device of this embodiment includes: at least one processor ( Figure 4 Only one is shown), a memory, and a computer program stored in the memory and executable on at least one processor, wherein when the processor executes the computer program, the steps in any of the above-mentioned embodiments of the method for dynamically sensing material demand for grid-connected converter control are implemented.

[0074] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that Figure 4 This is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.

[0075] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0076] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of a computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments, it may also be an external storage device of the computer device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory may also include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0077] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0078] The present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiment when executing.

[0079] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0080] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0081] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for controlling a converter connected to a grid based on a prediction model, characterized in that: The converter grid-connected control method comprises: Obtain the load sampling values ​​corresponding to the M first sampling points of the target power grid, where M is a positive integer; Input the M load sampling values ​​into the trained load forecasting model to obtain the load forecasting values ​​corresponding to the N second sampling points, where N is a positive integer; The M load sampling values ​​and the N load prediction values ​​are used as the load sample values ​​corresponding to the M+N target sampling points respectively; For any load sample value, according to the load sample value and the load reference value obtained by initialization, a load difference value corresponding to the load sample value is obtained; Input the M+N load difference values ​​into the trained energy storage prediction model respectively to obtain M+N energy storage prediction values; According to the M+N energy storage prediction values, M+N energy storage state values ​​are obtained; A first training loss is calculated according to the M+N energy storage state values ​​and a preset energy storage threshold, and the load reference value is updated according to the first training loss to obtain a load target value; According to the load target value and the N load forecast values, grid-connection control is performed on the energy storage converter corresponding to the target power grid at the N second sampling points respectively.

2. The method for controlling the grid-connected converter according to claim 1, characterized in that: The step of inputting the M load sampling values ​​into the trained load prediction model to obtain the load prediction values ​​corresponding to the N second sampling points respectively includes: Inputting M load sampling values ​​into the trained load forecasting model to obtain the load forecasting value corresponding to the nth second sampling point; Initialize n=1, input the load sampling value from the n+1th to the Mth load sampling value, and the load prediction value corresponding to the first second sampling point to the load prediction value corresponding to the nth second sampling point into the trained load prediction model, and obtain the load prediction value corresponding to the n+1th second sampling point; Update n=n+1, return to execute the step of converting the n+1th load sampling value to the Mth load sampling value, and the load prediction value corresponding to the first second sampling point to the load prediction value corresponding to the nth second sampling point, inputting them into the trained load prediction model, and obtaining the load prediction value corresponding to the n+1th second sampling point, until n+1=N, and obtaining the load prediction values ​​corresponding to the N second sampling points respectively.

3. The method for controlling the grid-connected converter according to claim 1, characterized in that: The step of obtaining, for any load sample value, a load difference value corresponding to the load sample value according to the load sample value and an initialized load reference value includes: For any load sample value, subtract the load sample value from the load reference value, and use the subtraction result as the load difference value corresponding to the load sample value; The M+N load sample values ​​are traversed to obtain the load difference values ​​corresponding to the M+N load sample values.

4. The method for controlling the grid-connected converter according to claim 1, characterized in that: The training process of the energy storage prediction model includes: Acquire an actual energy storage value of the energy storage converter corresponding to a fourth sampling point, and an actual load value and an actual control value of the target power grid corresponding to the fourth sampling point; Obtaining an actual difference value according to the actual load value and the actual control value; Inputting the actual difference value into the energy storage prediction model to obtain a target energy storage value; A second training loss is calculated according to the target energy storage value and the actual energy storage value, and the energy storage prediction model is trained according to the second training loss to obtain the trained energy storage prediction model.

5. The method for controlling the grid-connected converter according to claim 1, characterized in that: The method of obtaining M+N energy storage state values ​​according to the M+N energy storage prediction values ​​includes: For the j-th energy storage prediction value, calculate the sum of the first energy storage prediction value to the j-th energy storage prediction value, and use the sum as the j-th energy storage state value corresponding to the j-th energy storage prediction value, where j is an integer in the range of [1, M+N]; The M+N energy storage prediction values ​​are traversed to obtain the M+N energy storage state values.

6. The method for controlling the grid-connected converter according to claim 1, characterized in that: The step of calculating a first training loss according to the M+N energy storage state values ​​and a preset energy storage threshold comprises: Subtracting the M+N energy storage state values ​​from the energy storage threshold respectively to obtain M+N energy storage difference values; The M+N energy storage difference values ​​are respectively mapped through a preset mapping function to obtain mapping values ​​corresponding to the energy storage difference values; The sum of all mapped values ​​is used as the first training loss.

7. The method for controlling the grid-connected converter according to any one of claims 1 to 6, characterized in that: The grid-connection control of the energy storage converter corresponding to the target power grid is performed at the N second sampling points according to the load target value and the N load prediction values, including: For any second sampling point, when the load prediction value corresponding to the second sampling point is greater than the load target value, controlling the energy storage converter to discharge to the target power grid; When the load prediction value corresponding to the second sampling point is less than the load target value, the target power grid is controlled to charge the energy storage converter.

8. A converter grid-connected control device based on a prediction model, characterized in that: The converter grid-connected control device comprises: A load sampling module is used to obtain the load sampling values ​​corresponding to the M first sampling points of the target power grid, where M is a positive integer; A load prediction module, used for inputting M load sampling values ​​into a trained load prediction model to obtain load prediction values ​​corresponding to N second sampling points, where N is a positive integer; A sample construction module, used to use the M load sampling values ​​and the N load prediction values ​​as load sample values ​​corresponding to M+N target sampling points respectively; A difference calculation module, used for obtaining, for any load sample value, a load difference value corresponding to the load sample value according to the load sample value and an initialized load reference value; The energy storage prediction module is used to input M+N load difference values ​​into the trained energy storage prediction model to obtain M+N energy storage prediction values; A state calculation module, used to obtain M+N energy storage state values ​​according to the M+N energy storage prediction values; A parameter updating module, configured to calculate a first training loss according to the M+N energy storage state values ​​and a preset energy storage threshold, and update the load reference value according to the first training loss to obtain a load target value; A grid-connected control module is used to perform grid-connected control on the energy storage converter corresponding to the target power grid at the N second sampling points according to the load target value and the N load forecast values.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for grid-connected control of the converter according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the converter grid-connected control method according to any one of claims 1 to 7 is implemented.

Images