Deep learning-based photovoltaic water pump inverter control method and system

Abstract

This application relates to the field of photovoltaic inverter control, and discloses a control method and system for a photovoltaic water pump inverter based on deep learning. The method includes: obtaining the sequential light intensity and sequential panel temperature of a photovoltaic solar panel under working conditions, obtaining the sequential output voltage and sequential output current of the inverter, and obtaining the preset sequential output pressure of the water flow output by the water pump; wherein, the electric energy output by the photovoltaic solar panel is converted by the inverter and supplied to the water pump; through a sequential prediction model, according to the sequential light intensity, sequential panel temperature, sequential output voltage, sequential output current and preset sequential output pressure, determining the sequential predicted output voltage and sequential predicted output current of the inverter, and the sequential predicted output voltage and sequential predicted output current are used for maximum power tracking of the inverter. The system of this application can be stabilized near the true maximum power point.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic inverter control, and more specifically, to a control method and system for a photovoltaic water pump inverter based on deep learning. Background Art

[0002] The optimal operating point of a solar panel is called the maximum power point, which mainly depends on the operating temperature of the panel and the current light level. The maximum power point of a solar panel is different under different temperatures and light intensities. To make the solar panel work at the maximum power point as much as possible, it is necessary to use photovoltaic maximum power point tracking (MPPT). The most important thing in MPPT technology is to find a suitable MPPT control algorithm that can effectively track the maximum power point under rapidly changing weather conditions and control the panel to work at the maximum power point as much as possible.

[0003] Patent CN106936362B (application number: CN201710121665.1) provides a method and system for fast MPPT of a photovoltaic water pump inverter. By presetting the voltage close to the maximum power point, within a motor acceleration time, the output frequency of the frequency converter is adjusted by PID, the upper limit of the output frequency is increased, and the maximum power point voltage is gradually adjusted according to the increase or decrease of the output frequency, so that the solar panel can work near the maximum power point as much as possible. In the method of Patent CN106936362B, due to the mismatch between the dynamic response characteristics of PID regulation and the fixed-step adjustment strategy under rapidly changing light conditions, there is a risk of algorithm convergence. For example, when intermittent shadows are caused by cloud movement, the power-voltage (P-V) curve of the solar panel will fluctuate violently and may exhibit multi-peak characteristics. At this time, the frequency regulation of the PID controller based on historical error data (integral term) and change trend (differential term) will produce a lag response, and the fixed-step voltage adjustment mechanism superimposes discretization disturbances. The phase difference between the two causes a positive feedback effect when the system approaches the maximum power point - the inertial regulation of PID will continuously cross the actual maximum power point, and the fixed step exacerbates the voltage crossing amplitude. Especially in the steep region of the P-V curve, the coordinated disorder of this dual regulation will trigger continuous overshoot oscillations, making the system unable to stabilize near the true maximum power point, resulting in poor control effect on the photovoltaic water pump inverter. Summary of the Invention

[0004] The purpose of the present application is to provide a control method and system for a photovoltaic water pump inverter based on deep learning, which solves the technical problem that the system cannot be stable near the true maximum power point and achieves the technical effect that the system is stable near the true maximum power point.

[0005] A photovoltaic water pump inverter control method provided by an embodiment of the present application, the method includes: obtaining the sequential illumination intensity and sequential panel temperature of a photovoltaic solar panel under working conditions, obtaining the sequential output voltage and sequential output current of the inverter, and obtaining the preset sequential output pressure of the water flow output by the water pump; wherein, the electric energy output by the photovoltaic solar panel is supplied to the water pump after being converted by the inverter; through a sequential prediction model, according to the sequential illumination intensity, sequential panel temperature, sequential output voltage, sequential output current and preset sequential output pressure, determine the sequential predicted output voltage and sequential predicted output current of the inverter, and the sequential predicted output voltage and sequential predicted output current are used for maximum power tracking of the inverter.

[0006] In a possible implementation manner, through a sequential prediction model, according to the sequential illumination intensity, sequential panel temperature, sequential output voltage, sequential output current and preset sequential output pressure, determining the sequential predicted output voltage and sequential predicted output current of the inverter includes: determining the sequential illumination intensity weight according to the sequential illumination intensity attention unit, determining the sequential panel temperature weight according to the sequential panel temperature attention unit, determining the sequential output voltage weight according to the sequential output voltage attention unit, determining the sequential output current weight according to the sequential output current attention unit, and determining the preset sequential output pressure weight according to the preset sequential output pressure attention unit; through the sequential prediction model, according to the sequential illumination intensity, sequential illumination intensity weight, sequential panel temperature, sequential panel temperature weight, sequential output voltage, sequential output voltage weight, sequential output current, sequential output current weight, preset sequential output pressure and preset sequential output pressure weight, determine the sequential predicted output voltage and sequential predicted output current of the inverter.

[0007] In another possible implementation, through a timing prediction model, based on the timing light intensity, the timing panel temperature, the timing output voltage, the timing output current, and the preset timing output pressure, the timing prediction output voltage and the timing prediction output current of the inverter are determined. It further includes: through a light intensity fusion processing unit, based on the timing light intensity and the timing light intensity weight, determining a light intensity fusion feature; through a first fusion unit, based on the light intensity fusion feature, the timing panel temperature, and the timing panel temperature weight, determining a first fusion feature; through a second fusion unit, based on the light intensity fusion feature, the timing output voltage, and the timing output voltage weight, determining a second fusion feature; through a third fusion unit, based on the light intensity fusion feature, the timing output current, and the timing output current weight, determining a second fusion feature; through a third fusion unit, based on the light intensity fusion feature, the preset timing output pressure, and the preset timing output pressure weight, determining a third fusion feature; through the timing prediction model, based on the light intensity fusion feature, the first fusion feature, the second fusion feature, and the third fusion feature, determining the timing prediction output voltage and the timing prediction output current of the inverter.

[0008] In another possible implementation, the method further includes: through a weather classification model, based on the timing light intensity, determining weather classification information, obtaining a first time window corresponding to the weather classification information, and obtaining the timing light intensity within the first time window; and obtaining the timing panel temperature, the timing output voltage, the timing output current, and the preset timing output pressure within a second time window; wherein, the length of the second time window is greater than the duration of the first time window, and both the first time window and the second time window are time windows traced back from the current moment; through the light intensity fusion processing unit, based on the timing light intensity within the first time window and the timing light intensity weight, determining a light intensity fusion feature; through the first fusion unit, based on the light intensity fusion feature, the timing panel temperature within the second time window, and the timing panel temperature weight, determining a first fusion feature; through the second fusion unit, based on the light intensity fusion feature, the timing output voltage within the second time window, and the timing output voltage weight, determining a second fusion feature; through the third fusion unit, based on the light intensity fusion feature, the timing output current within the second time window, and the timing output current weight, determining a second fusion feature; through the third fusion unit, based on the light intensity fusion feature, the preset timing output pressure within the second time window, and the preset timing output pressure weight, determining a third fusion feature; through the timing prediction model, based on the light intensity fusion feature, the first fusion feature, the second fusion feature, and the third fusion feature, determining the timing prediction output voltage and the timing prediction output current of the inverter.

[0009] In another possible implementation, the method further includes: respectively obtaining weather state information within a first time window and a third time window, and determining, by a weather state recognition unit, weighted summation weights corresponding to the first time window and the third time window according to the weather state information within the first time window and the third time window; wherein the third time window is a time window before the first time window, and the duration of the third time window is 3 to 5 times the duration of the first time window; summing the sequential light intensities of the first time window and the third time window according to the weighted summation weights corresponding to the first time window and the third time window, and using the result as the sequential light intensity within the first time window.

[0010] In another possible implementation, the method further includes: respectively obtaining the sequential light intensities of a plurality of associated photovoltaic solar panels of a target photovoltaic solar panel within a first time window; respectively determining a plurality of first light intensity variance values of a plurality of first sequential light intensities of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels, and determining the minimum first light intensity variance value among the plurality of first light intensity variance values; wherein the plurality of associated photovoltaic solar panels are a plurality of photovoltaic solar panels with positions close to that of the target photovoltaic solar panel; obtaining the first time window of the photovoltaic solar panel corresponding to the minimum first light intensity variance value as the target first time window; and determining, by a light intensity fusion processing unit, a target light intensity fusion feature according to the sequential light intensity and the sequential light intensity weight within the target first time window, and determining unified sequential prediction output voltages and sequential prediction output currents of inverters of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels according to the target light intensity fusion feature.

[0011] In another possible implementation, the method further includes: respectively obtaining the sequential light intensities of a plurality of associated photovoltaic solar panels of a target photovoltaic solar panel within a third time window; respectively determining a plurality of third light intensity variance values of a plurality of third sequential light intensities of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels, and determining the minimum third light intensity variance value among the plurality of third light intensity variance values; obtaining the third time window of the photovoltaic solar panel corresponding to the minimum third light intensity variance value as the target third time window; determining, by a weather state recognition unit, weighted summation weights corresponding to the target first time window and the target third time window according to the weather state information within the target first time window and the target third time window; summing the sequential light intensities of the target first time window and the target third time window according to the weighted summation weights corresponding to the target first time window and the target third time window, and using the result as the sequential light intensity within the target first time window, and determining unified sequential prediction output voltages and sequential prediction output currents of inverters of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels according to the sequential light intensity within the target first time window.

[0012] In another possible implementation, the method further includes: respectively obtaining the weather classification information of a plurality of associated photovoltaic solar panels of the target photovoltaic solar panel; when the weather classification information of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels is the same, determining the time-sequential average light intensity of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels within the first time window, the time-sequential average panel temperature within the second time window, the time-sequential average output voltage, the time-sequential average output current, and the time-sequential average output pressure; and determining the unified time-sequential predicted output voltage and the time-sequential predicted output current of the inverters of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels according to the time-sequential average light intensity of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels within the first time window, the time-sequential average panel temperature within the second time window, the time-sequential average output voltage, the time-sequential average output current, and the time-sequential average output pressure.

[0013] In another possible implementation, the method further includes: obtaining the plurality of weighted summation weights corresponding to the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels in the first time window and the third time window respectively, and determining the target weighted summation weight with the largest value in the first time window among the plurality of weighted summation weights; summing and averaging the time-sequential light intensities of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels in the first time window and the third time window according to the target weighted summation weights corresponding to the first time window and the third time window, as the time-sequential average light intensity of the target photovoltaic solar panel and the plurality of associated photovoltaic solar panels within the first time window.

[0014] The embodiment of the present application further provides a photovoltaic water pump inverter control system based on deep learning, including a unit for executing the method described in any one of the above.

[0015] The beneficial effects of the embodiment of the present application compared with the prior art are:

[0016] An embodiment of the present application provides a control method for a photovoltaic water pump inverter based on deep learning. The method includes: obtaining the sequential illumination intensity and sequential panel temperature of a photovoltaic solar panel under working conditions, obtaining the sequential output voltage and sequential output current of the inverter, and obtaining the preset sequential output pressure of the water flow output by the water pump; wherein, the electric energy output by the photovoltaic solar panel is supplied to the water pump after being converted by the inverter; through a sequential prediction model, according to the sequential illumination intensity, sequential panel temperature, sequential output voltage, sequential output current, and preset sequential output pressure, determining the sequential predicted output voltage and sequential predicted output current of the inverter, and the sequential predicted output voltage and sequential predicted output current are used for maximum power tracking of the inverter. The embodiment of the present application can control the sequential predicted output voltage and sequential predicted output current of the inverter by combining the sequential illumination intensity, sequential panel temperature, sequential output voltage, sequential output current, and preset sequential output pressure in the sequential characteristics, and can directly combine the sequential characteristics of the photovoltaic solar panel, water pump, and inverter to comprehensively control the working state of the inverter, improving the control effect of the inverter. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a schematic flow chart of the first control method for a photovoltaic water pump inverter based on deep learning provided by the embodiment of the present application;

[0019] Figure 2 It is a schematic working flow chart of the first control method for a photovoltaic water pump inverter based on deep learning provided by the embodiment of the present application;

[0020] Figure 3 It is a schematic flow chart of the second control method for a photovoltaic water pump inverter based on deep learning provided by the embodiment of the present application;

[0021] Figure 4 It is a schematic flow chart of the third control method for a photovoltaic water pump inverter based on deep learning provided by the embodiment of the present application;

[0022] Figure 5 It is a schematic flow chart of the fourth control method for a photovoltaic water pump inverter based on deep learning provided by the embodiment of the present application;

[0023] Figure 6Schematic flowchart of the fifth deep learning-based photovoltaic water pump inverter control method provided by the embodiments of the present application;

[0024] Figure 7 Schematic flowchart of the sixth deep learning-based photovoltaic water pump inverter control method provided by the embodiments of the present application;

[0025] Figure 8 Schematic flowchart of the seventh deep learning-based photovoltaic water pump inverter control method provided by the embodiments of the present application;

[0026] Figure 9 Schematic logical structure diagram of a deep learning-based photovoltaic water pump inverter control system provided by the embodiments of the present application. Detailed implementation manners

[0027] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0028] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" according to the context.

[0030] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0031] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that specific features, structures or characteristics described in connection with that embodiment are included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments" etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0032] In the existing methods for fast MPPT of photovoltaic water pump inverters, the frequency regulation based on the PID controller based on historical error data (integral term) and change trend (differential term) will produce a lag response, and the voltage adjustment mechanism with a fixed step size superimposes discretized perturbations. The phase difference between the two causes a positive feedback effect in the system when approaching the maximum power point - the inertial regulation of the PID will continuously cross the actual maximum power point, and the fixed step size exacerbates the voltage crossing amplitude. Especially in the steep region of the P-V curve, the coordinated disorder of this dual regulation will trigger continuous overshoot oscillations, making the system unable to stabilize near the true maximum power point, resulting in poor control effect on the photovoltaic water pump inverter.

[0033] For the above reasons, the embodiments of this application provide a control method for a photovoltaic water pump inverter based on deep learning. The method includes: obtaining the sequential light intensity and sequential panel temperature of the photovoltaic solar panel under working conditions, obtaining the sequential output voltage and sequential output current of the inverter, and obtaining the preset sequential output pressure of the water flow output by the water pump; wherein, the electric energy output by the photovoltaic solar panel is supplied to the water pump after being converted by the inverter; through a sequential prediction model, according to the sequential light intensity, sequential panel temperature, sequential output voltage, sequential output current and preset sequential output pressure, determining the sequential predicted output voltage and sequential predicted output current of the inverter, and the sequential predicted output voltage and sequential predicted output current are used for maximum power tracking of the inverter. The embodiments of this application can combine the sequential light intensity, sequential panel temperature, sequential output voltage, sequential output current and preset sequential output pressure in the sequential features to control the sequential predicted output voltage and sequential predicted output current of the inverter, and can directly combine the sequential features of the photovoltaic solar panel, water pump and inverter to comprehensively control the working state of the inverter, improving the control effect of the inverter.

[0034] In some scenarios, a control method for a photovoltaic water pump inverter based on deep learning according to an embodiment of the present application can be applied to a control system coupled with a photovoltaic solar panel, a water pump, and an inverter, which can accurately control the working state of the inverter and improve the accuracy of the MPPT of the inverter.

[0035] The following specifically describes a control method for a photovoltaic water pump inverter based on deep learning provided by an embodiment of the present application with specific examples.

[0036] Figure 1 It is a schematic flowchart of the first control method for a photovoltaic water pump inverter based on deep learning provided by an embodiment of the present application. As Figure 1 shown, this method includes S110 to S120, and the following specifically describes S110 to S120.

[0037] S110. Obtain the sequential light intensity and sequential panel temperature of the photovoltaic solar panel under working conditions, obtain the sequential output voltage and sequential output current of the inverter, and obtain the preset sequential output pressure of the water flow output by the water pump. Among them, the electric energy output by the photovoltaic solar panel is supplied to the water pump after being converted by the inverter.

[0038] Figure 2 It is a schematic working flowchart of the first control method for a photovoltaic water pump inverter based on deep learning provided by an embodiment of the present application. As Figure 2 shown, in the embodiment of the present application, the sequential light intensity and sequential panel temperature of the photovoltaic solar panel under working conditions can be obtained. The sequential light intensity is multiple light intensities of the photovoltaic solar panel in chronological order, and the sequential panel temperature is multiple panel temperatures of the photovoltaic solar panel in chronological order. The working state of the photovoltaic inverter can be controlled by combining the sequential light intensity and sequential panel temperature with the working characteristics of the photovoltaic solar panel in chronological order.

[0039] In the embodiment of the present application, the sequential output voltage and sequential output current of the inverter can also be obtained. The sequential output voltage is multiple output voltages of the inverter in chronological order, and the sequential output current is multiple output currents of the inverter in chronological order. The working state of the photovoltaic inverter can be controlled by combining the sequential output voltage and sequential output current of the inverter with the working characteristics of the inverter in chronological order.

[0040] In the embodiments of the present application, it is also possible to obtain the preset sequential output pressure of the water pump output water flow. The preset sequential output pressure is the pressure characteristic of the water pump outputting water flow in chronological order. The preset sequential output pressure is the preset sequential output pressure for the purpose of controlling the working state of the water pump. The preset sequential output pressure is preset. Through the preset sequential output pressure of the water pump, the working state of the photovoltaic inverter can be controlled in combination with the working characteristics of the water pump in chronological order.

[0041] During operation, the preset sequential output pressure during the operation of the water pump corresponds to the water flow pressure state pumped by the output terminal voltage of the frequency converter. Compared with only controlling the working state of the water pump through the output terminal voltage of the frequency converter, the present application can perform accurate feedback control on the working state of the water pump in combination with the pressure of the water flow.

[0042] Exemplarily, the preset sequential output pressure of the water pump can be preset according to irrigation requirements and water usage requirements. The preset sequential output pressure can be derived from the water pressure control curve during the operation of the water pump.

[0043] It should be noted that the electric energy output by the photovoltaic solar panel is supplied to the water pump after being converted by the inverter. The photovoltaic solar panel is used to generate electric energy, the inverter is used to convert the electric energy generated by the photovoltaic solar panel into current and voltage suitable for the operation of the water pump, and the water pump is used to pump and drive the water flow.

[0044] S120. Through the time series prediction model, according to the time series light intensity, time series panel temperature, time series output voltage, time series output current, and preset sequential output pressure, determine the time series predicted output voltage and time series predicted output current of the inverter. The time series predicted output voltage and time series predicted output current are used for maximum power tracking of the inverter.

[0045] As Figure 2 shown, after obtaining the time series light intensity, time series panel temperature, time series output voltage, time series output current, and preset sequential output pressure, the time series predicted output voltage and time series predicted output current of the inverter can be determined through the time series prediction model according to the time series light intensity, time series panel temperature, time series output voltage, time series output current, and preset sequential output pressure, thereby realizing the control of the time series predicted output voltage and time series predicted output current of the inverter. The time series predicted output voltage and time series predicted output current are used for maximum power tracking of the inverter of the photovoltaic water pump.

[0046] Exemplarily, the time series prediction model is trained by the labeled time series light intensity, time series panel temperature, time series output voltage, time series output current, preset time series output pressure, time series predicted output voltage of the inverter, and time series predicted output current. The time series predicted output voltage and time series predicted output current of the labeled inverter are the inverter control parameters corresponding to the labeled time series light intensity, time series panel temperature, time series output voltage, time series output current, and preset time series output pressure. Among them, the preset time series output pressure is the preset time series output pressure preset when controlling the water pump.

[0047] It should be noted that the time series predicted output voltage and time series predicted output current of the labeled inverter are the maximum power tracking points of the photovoltaic water pump inverter. Furthermore, through the time series prediction model, the maximum power tracking of the photovoltaic water pump inverter can be performed, improving the effect of maximum power tracking of the photovoltaic water pump inverter.

[0048] The existing PID-based inertial regulation method will continuously cross the actual maximum power point. Especially in the steep region of the P-V curve, the coordination disorder of this dual regulation will cause continuous overshoot oscillations, making the system unable to stabilize near the true maximum power point, resulting in poor control effect on the photovoltaic water pump inverter.

[0049] In the embodiment of the present application, when the frequency converter of the photovoltaic water pump drives the water pump, as the speed of the water pump increases, the load becomes larger and the output current becomes larger. From the characteristic curve of the solar panel, it can be seen that when the current increases to a certain extent, the voltage will drop rapidly. Or in the event of sudden situations such as clouds blocking the sun, the output voltage of the solar power generation panel is too low. If the adjustment is not timely, it will cause the frequency converter to power off and restart. In the embodiment of the present application, by controlling the output voltage generated by the inverter of the solar power generation panel, it is possible to avoid the power off and restart of the frequency converter caused by the poor control effect of the time series predicted output voltage and time series predicted output current of the inverter.

[0050] The beneficial effect of the above implementation manner is that through the time series prediction model, according to the time series light intensity, time series panel temperature, time series output voltage, time series output current, and preset time series output pressure, the time series predicted output voltage and time series predicted output current of the inverter are determined. The time series prediction model can perform high-power tracking on the photovoltaic water pump inverter, improve the effect of maximum power tracking of the photovoltaic water pump inverter, and avoid the continuous overshoot oscillations caused by the PID-based inertial regulation method.

[0051] In some implementation manners, in the above S120, through the time series prediction model, according to the time series light intensity, time series panel temperature, time series output voltage, time series output current, and preset time series output pressure, the time series predicted output voltage and time series predicted output current of the inverter are determined, and it further includes S121 to 122. The following will specifically describe S121 to 122.

[0052] S121. Determine the time-series light intensity weight according to the time-series light intensity attention unit, determine the time-series solar panel temperature weight according to the time-series solar panel temperature attention unit, determine the time-series output voltage weight according to the time-series output voltage attention unit, determine the time-series output current weight according to the time-series output current attention unit, and determine the preset time-series output pressure weight according to the preset time-series output pressure attention unit.

[0053] In the embodiment of the present application, in order to further improve the effect of maximum power tracking of the photovoltaic water pump inverter, the time-series light intensity weight can be determined according to the time-series light intensity attention unit, and the time-series light intensity weight is used to determine the weights of the light intensities at different moments in the time-series light intensity.

[0054] Determine the time-series solar panel temperature weight according to the time-series solar panel temperature attention unit, where the time-series solar panel temperature weight is used to determine the weights of the solar panel temperatures at different moments in the time-series solar panel temperature, determine the time-series output voltage weight according to the time-series output voltage attention unit, where the time-series output voltage weight is used to determine the weights of the output voltages at different moments in the time-series output voltage, determine the time-series output current weight according to the time-series output current attention unit, where the time-series output current weight is used to determine the weights of the output currents at different moments in the time-series output current, determine the preset time-series output pressure weight according to the preset time-series output pressure attention unit, where the preset time-series output pressure weight is used to determine the weights of the preset output pressures at different moments in the preset time-series output pressure, so as to further improve the accuracy of determining the time-series predicted output voltage and the time-series predicted output current.

[0055] Exemplarily, it is possible to perform normalization processing on the time-series light intensity, solar panel temperature, output voltage, output current, and output pressure data on the side, ensure that the data is on the same scale, and further divide the data into sequences of fixed length to adapt to the processing of the attention mechanism, and design multiple independent attention units for each time-series data (including time-series light intensity, time-series solar panel temperature, time-series output voltage, time-series output current, and preset time-series output pressure), and determine the weights corresponding to each time-series data through the multiple independent attention units.

[0056] S122. Through the time-series prediction model, determine the time-series predicted output voltage and the time-series predicted output current of the inverter according to the time-series light intensity, the time-series light intensity weight, the time-series solar panel temperature, the time-series solar panel temperature weight, the time-series output voltage, the time-series output voltage weight, the time-series output current, the time-series output current weight, the preset time-series output pressure, and the preset time-series output pressure weight.

[0057] When controlling the timing prediction output voltage and the timing prediction output current, through the timing prediction model, according to the timing light intensity, the timing light intensity weight, the timing panel temperature, the timing panel temperature weight, the timing output voltage, the timing output voltage weight, the timing output current, the timing output current weight, the preset timing output pressure, and the preset timing output pressure weight, the timing prediction output voltage and the timing prediction output current of the inverter can be determined, realizing the calculation of the timing prediction output voltage and the timing prediction output current based on the respective weights of the timing light intensity, the timing panel temperature, the timing output voltage, the timing output current, and the preset timing output pressure.

[0058] The beneficial effect of the above implementation method is that by the attention unit, the timing light intensity weight, the timing panel temperature weight, the timing output voltage weight, the timing output current weight, and the preset timing output pressure weight are determined, and the timing prediction output voltage and the timing prediction output current of the inverter can be determined according to the timing light intensity, the timing light intensity weight, the timing panel temperature, the timing panel temperature weight, the timing output voltage, the timing output voltage weight, the timing output current, the timing output current weight, the preset timing output pressure, and the preset timing output pressure weight. When determining the timing prediction output voltage and the timing prediction output current of the inverter, the accuracy of the timing prediction output voltage and the timing prediction output current of the inverter is improved according to the importance of different parameters, and the effect of controlling the timing prediction output voltage and the timing prediction output current of the inverter is improved.

[0059] In some implementation methods, in the above S120, through the timing prediction model, according to the timing light intensity, the timing panel temperature, the timing output voltage, the timing output current, and the preset timing output pressure, the timing prediction output voltage and the timing prediction output current of the inverter are determined, and it further includes S123 to S124. The following will specifically describe S123 to S124.

[0060] S123: Through the light fusion processing unit, according to the timing light intensity and the timing light intensity weight, the light intensity fusion feature is determined. Through the first fusion unit, according to the light intensity fusion feature, the timing panel temperature, and the timing panel temperature weight, the first fusion feature is determined. Through the second fusion unit, according to the light intensity fusion feature, the timing output voltage, and the timing output voltage weight, the second fusion feature is determined. Through the third fusion unit, according to the light intensity fusion feature, the timing output current, and the timing output current weight, the third fusion feature is determined. Through the fourth fusion unit, according to the light intensity fusion feature, the preset timing output pressure, and the preset timing output pressure weight, the fourth fusion feature is determined.

[0061] When controlling the inverter, since the light intensity is of greater importance, in order to improve the control effect of the inverter, in the embodiments of the present application, in order to further optimize the feature extraction of the light intensity, through the light intensity fusion processing unit, according to the sequential light intensity and the sequential light intensity weight, the light intensity fusion feature is determined, and the light intensity fusion feature fuses the sequential light intensity and the sequential light intensity weight information.

[0062] After obtaining the light intensity fusion feature, the first fusion unit can be used to determine the first fusion feature according to the light intensity fusion feature, the sequential panel temperature, and the sequential panel temperature weight. The first fusion feature includes the information of the sequential panel temperature and the sequential panel temperature weight, realizing the shallow fusion of the light intensity fusion feature, the sequential panel temperature, and the sequential panel temperature weight.

[0063] Exemplarily, the first fusion unit can be a deep learning unit based on LSTM, and through the first fusion unit, the light intensity fusion feature, the sequential panel temperature, and the sequential panel temperature weight can be fused.

[0064] After obtaining the light intensity fusion feature, the second fusion unit can be used to determine the second fusion feature according to the light intensity fusion feature, the sequential output voltage, and the sequential output voltage weight. The second fusion feature includes the information of the sequential output voltage and the sequential output voltage weight, realizing the shallow fusion of the light intensity fusion feature, the sequential output voltage, and the sequential output voltage weight.

[0065] After obtaining the light intensity fusion feature, the third fusion unit can be used to determine the third fusion feature according to the light intensity fusion feature, the sequential output current, and the sequential output current weight. The third fusion feature includes the information of the sequential output current and the sequential output current weight, realizing the shallow fusion of the light intensity fusion feature, the sequential output current, and the sequential output current weight.

[0066] After obtaining the light intensity fusion feature, the fourth fusion unit can be used to determine the fourth fusion feature according to the light intensity fusion feature, the preset sequential output pressure, and the preset sequential output pressure weight. The fourth fusion unit includes the information of the preset sequential output pressure and the preset sequential output pressure weight, realizing the shallow fusion of the light intensity fusion feature, the preset sequential output pressure, and the preset sequential output pressure weight.

[0067] S124. Through the sequential prediction model, according to the light intensity fusion feature, the first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature, determine the sequential predicted output voltage and the sequential predicted output current of the inverter.

[0068] After obtaining the light intensity fusion feature, the first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature, the time series prediction model can be further used to determine the time series predicted output voltage and the time series predicted output current of the inverter according to the light intensity fusion feature, the first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature. At this time, the light intensity fusion feature, the first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature are fused again to generate control information for the time series predicted output voltage and the time series predicted output current, realizing the deep fusion of the light intensity fusion feature and the first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature, realizing the two - level feature fusion of the light intensity fusion feature at the shallow and deep levels, improving the utilization effect of the light intensity information corresponding to the light intensity fusion feature, and improving the control effect of the inverter according to the key parameter of light intensity.

[0069] The beneficial effects of the above - mentioned implementation method are as follows: it realizes the shallow - level fusion of the light intensity fusion feature, the time - series panel temperature, and the time - series panel temperature weight; it realizes the shallow - level fusion of the light intensity fusion feature, the time - series output voltage, and the time - series output voltage weight; it realizes the shallow - level fusion of the light intensity fusion feature, the time - series output current, and the time - series output current weight; it realizes the shallow - level fusion of the light intensity fusion feature, the preset time - series output pressure, and the preset time - series output pressure weight; and it realizes the deep - level fusion of the light intensity fusion feature and the first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature, realizing the two - level feature fusion of the light intensity fusion feature at the shallow and deep levels, improving the utilization effect of the light intensity information corresponding to the light intensity fusion feature, and improving the control effect of the inverter according to the key parameter of light intensity.

[0070] Figure 3 The flowchart of the second photovoltaic water pump inverter control method based on deep learning provided by the embodiment of the present application is shown as Figure 3 As shown, the above - mentioned method further includes S210 to S220, and the following further explains S210 to S230.

[0071] S210: Through the weather classification model, determine the weather classification information according to the time - series light intensity, obtain the first time window corresponding to the weather classification information, and obtain the time - series light intensity within the first time window. And obtain the time - series panel temperature, the time - series output voltage, the time - series output current, and the preset time - series output pressure within the second time window. Wherein, the length of the second time window is greater than the duration of the first time window, and both the first time window and the second time window are time windows traced back from the current moment.

[0072] Since the variation characteristics of the light intensity under different weather classifications are different. For example, under the sunny weather classification, the change of the light intensity over time is not obvious. Another example is that under the cloudy weather classification, the change of the light intensity over time will change sharply with the change of the cloud layer.

[0073] In order to further improve the utilization effect of the light intensity information, through a weather classification model, according to the sequential light intensity, the weather classification information is determined. The weather classification information characterizes the change of the light intensity, and then the first time window corresponding to the weather classification information can be obtained, and the sequential light intensity within the first time window is obtained. Among them, the time lengths of different first time windows are different.

[0074] Exemplarily, when the weather classification information is cloudy, the first time window is the time window within 1 hour backtracked from the current moment.

[0075] Exemplarily, when the weather classification information is sunny, the first time window is the time window within 5 hours backtracked from the current moment.

[0076] At the same time, in order to ensure the control effect of the inverter, the sequential battery panel temperature, sequential output voltage, sequential output current and preset sequential output pressure within the second time window can also be obtained. Among them, the length of the second time window is greater than the duration of the first time window. Compared with the first time window, the purpose of improving the control effect of the inverter according to the sequential battery panel temperature, sequential output voltage, sequential output current and preset sequential output pressure within the second time window of a longer time period is achieved.

[0077] It should be noted that both the first time window and the second time window are time windows backtracked from the current moment to ensure the control accuracy of the inverter.

[0078] S220: Through the light intensity fusion processing unit, according to the sequential light intensity and the sequential light intensity weight within the first time window, the light intensity fusion feature is determined. Through the first fusion unit, according to the light intensity fusion feature, the sequential battery panel temperature and the sequential battery panel temperature weight within the second time window, the first fusion feature is determined. Through the second fusion unit, according to the light intensity fusion feature, the sequential output voltage and the sequential output voltage weight within the second time window, the second fusion feature is determined. Through the third fusion unit, according to the light intensity fusion feature, the sequential output current and the sequential output current weight within the second time window, the third fusion feature is determined. Through the fourth fusion unit, according to the light intensity fusion feature, the preset sequential output pressure and the preset sequential output pressure weight within the second time window, the fourth fusion feature is determined.

[0079] After obtaining the sequential light intensity within the first time window, the light intensity fusion processing unit can determine the light intensity fusion feature according to the sequential light intensity and the sequential light intensity weight within the first time window, where the sequential light intensity weight can be determined through step S121.

[0080] After obtaining the light intensity fusion feature, through a method similar to that in 123, the first fusion unit can determine the first fusion feature according to the light intensity fusion feature, the sequential temperature of the solar panel, and the sequential temperature weight of the solar panel within the second time window. The second fusion unit can determine the second fusion feature according to the light intensity fusion feature, the sequential output voltage, and the sequential output voltage weight within the second time window. The third fusion unit can determine the third fusion feature according to the light intensity fusion feature, the sequential output current, and the sequential output current weight within the second time window. The fourth fusion unit can determine the fourth fusion feature according to the light intensity fusion feature, the preset sequential output pressure, and the preset sequential output pressure weight within the second time window. Among them, the first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature all combine the control features within the second time window and the light intensity features within the first time window, achieving the purpose of adjusting the light intensity features according to the weather conditions, and further improving the control effect of the inverter under different weather conditions.

[0081] S230. Through the sequential prediction model, according to the light intensity fusion feature, the first fusion feature, the second fusion feature, and the third fusion feature, determine the sequential predicted output voltage and the sequential predicted output current of the inverter.

[0082] Furthermore, through the sequential prediction model, according to the light intensity fusion feature, the first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature, determine the sequential predicted output voltage and the sequential predicted output current of the inverter, and realize the control of the inverter according to the sequential predicted output voltage and the sequential predicted output current of the inverter.

[0083] The beneficial effect of the above implementation method is that the light intensity features are adjusted according to the weather conditions. The first fusion feature, the second fusion feature, the third fusion feature, and the fourth fusion feature all combine the control features within the second time window and the light intensity features within the first time window, further improving the control effect of the inverter under different weather conditions.

[0084] Figure 4 This is a schematic flowchart of the third photovoltaic water pump inverter control method based on deep learning provided by the embodiment of the present application. As Figure 4 shown, the above method further includes S240 to S250, and the following is a specific description of S240 to S250.

[0085] S240. Obtain the weather condition information within the first time window and the third time window respectively. Through the weather condition recognition unit, determine the weighted summation weights corresponding to the first time window and the third time window respectively according to the weather condition information within the first time window and the third time window. Herein, the third time window is the time window before the first time window, and the duration of the third time window is 3 to 5 times the duration of the first time window.

[0086] When processing the light intensity information by the method in S210 to S230, only truncating the time according to the weather condition to obtain the first time window corresponding to the sequential light intensity may lead to insufficient consideration of the sequential light intensity before the first time window, and further lead to poor effect of controlling the inverter only by the light intensity within the first time window.

[0087] In order to improve the utilization effect of the information of the sequential light intensity before the first time window, the weather condition information within the first time window and the third time window can be obtained respectively. Through the weather condition recognition unit, determine the weighted summation weights corresponding to the first time window and the third time window respectively according to the weather condition information within the first time window and the third time window, so as to realize the fusion of the light intensity within the first time window and the third time window before the first time window, and improve the utilization effect of the information of the sequential light intensity before the first time window.

[0088] Exemplarily, the weather condition information can be the local weather condition information obtained through weather forecast.

[0089] It should be noted that the third time window is the time window before the first time window, and the duration of the third time window is 3 to 5 times the duration of the first time window to ensure the utilization effect of the information of the sequential light intensity before the first time window.

[0090] Exemplarily, the weather condition recognition unit can be an LSTM-based neural network, which can determine the weighted summation weights at each moment corresponding to the first time window and the third time window respectively according to the weather condition information within the first time window and the third time window.

[0091] S250. Sum the sequential light intensities of the first time window and the third time window according to the weighted summation weights corresponding to the first time window and the third time window, and use the sum as the sequential light intensity within the first time window.

[0092] After obtaining the temporal illumination intensities of the first time window and the third time window before the first time window, the temporal illumination intensities of the first time window and the third time window can be summed according to the weighted summation weights corresponding to the first time window and the third time window, and used as the temporal illumination intensity within the first time window, so that the temporal illumination intensity within the first time window represents the illumination intensity effects within the first time window and the third time window, improving the subsequent control effect of the inverter based on the temporal illumination intensity within the first time window.

[0093] Exemplarily, when subsequently controlling the inverter according to the temporal illumination intensity within the first time window, the state of the inverter can be controlled according to the methods in S210 to S230 above.

[0094] The beneficial effect of the above implementation method is that it avoids obtaining the first time window corresponding to the temporal illumination intensity by simply truncating the time according to the weather state, avoiding insufficient consideration of the temporal illumination intensity before the first time window, and optimizing the illumination intensity information of the first time window through the weighted summation weights of the illumination intensity information within the first time window and the third time window corresponding to different weather state information, improving the subsequent control effect of the inverter based on the temporal illumination intensity within the first time window.

[0095] Figure 5 The flow diagram of the fourth photovoltaic water pump inverter control method based on deep learning provided by the embodiments of this application is as Figure 5 shown. The above method further includes S310 to S320, which will be specifically described below.

[0096] S310. Obtain the temporal illumination intensities of multiple associated photovoltaic solar panels of the target photovoltaic solar panel within the first time window respectively. Determine the first illumination intensity variance values of the multiple first temporal illumination intensities of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels respectively, and determine the minimum first illumination intensity variance value among the multiple first illumination intensity variance values. Among them, the multiple associated photovoltaic solar panels are multiple photovoltaic solar panels with positions close to the target photovoltaic solar panel.

[0097] To reduce the computational complexity of the maximum power point tracking of multiple photovoltaic solar panels, the temporal illumination intensities of multiple associated photovoltaic solar panels of the target photovoltaic solar panel within the first time window can be obtained respectively, so as to be able to evaluate the temporal illumination intensities of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels within the first time window.

[0098] When obtaining the target photovoltaic solar panel and the sequential light intensities of multiple associated photovoltaic solar panels within the first time window, the multiple first light intensity variance values of the multiple first sequential light intensities of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels can be determined respectively. The first light intensity variance value characterizes the fluctuation of the first sequential light intensity. At the same time, the minimum first light intensity variance value among the multiple first light intensity variance values can be further determined. The photovoltaic solar panel corresponding to the minimum first light intensity variance value has the smallest fluctuation amplitude of the light intensity.

[0099] It should be noted that the multiple associated photovoltaic solar panels are multiple photovoltaic solar panels with positions close to the target photovoltaic solar panel. Since the multiple associated photovoltaic solar panels have similar light intensities due to their close positions to the target photovoltaic solar panel, the inverters of the multiple associated photovoltaic solar panels and the target photovoltaic solar panel can be centrally controlled according to the light intensity, so as to reduce the computational complexity of controlling the inverters of the multiple associated photovoltaic solar panels and the target photovoltaic solar panel.

[0100] S320. Obtain the first time window of the photovoltaic solar panel corresponding to the minimum first light intensity variance value as the target first time window. Through the light fusion processing unit, according to the sequential light intensity and the sequential light intensity weight within the target first time window, determine the target light intensity fusion feature, and determine the unified sequential predicted output voltage and sequential predicted output current of the inverters of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels according to the target light intensity fusion feature.

[0101] After obtaining the minimum first light intensity variance value, it indicates that the photovoltaic solar panel corresponding to the minimum first light intensity variance value has the smallest detected fluctuation amplitude of the light intensity, and the detected value of the light intensity detected by the photovoltaic solar panel corresponding to the minimum first light intensity variance value may be the most accurate and most in line with the actual local light intensity change situation. The frequency of the photovoltaic solar panel corresponding to the minimum first light intensity variance value being blocked by clouds is the lowest. Furthermore, the first time window of the photovoltaic solar panel corresponding to the minimum first light intensity variance value can be obtained as the target first time window, and the inverters of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels can be controlled according to the target first time window.

[0102] Exemplarily, when obtaining the first time window of the photovoltaic solar panel corresponding to the minimum first light intensity variance value, the first time window of the photovoltaic solar panel corresponding to the minimum first light intensity variance value can be determined according to the method in step S210.

[0103] After obtaining the first time window of the photovoltaic solar panel corresponding to the minimum first light intensity variance value, the light intensity fusion processing unit can determine the target light intensity fusion feature according to the sequential light intensity and the sequential light intensity weight within the target first time window, and determine the unified sequential predicted output voltage and sequential predicted output current of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels according to the target light intensity fusion feature, improving the control effect on the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels according to the most accurate sequential light intensity in the detection result.

[0104] The beneficial effect of the above implementation is that the control effect on the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is improved according to the most accurate sequential light intensity in the detection result, and the calculation amount for controlling the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is reduced.

[0105] The beneficial effect of the above implementation is also that the detected value of the light intensity detected by the photovoltaic solar panel corresponding to the minimum first light intensity variance value may be the most accurate and most in line with the actual local light intensity change situation, and the frequency of the photovoltaic solar panel corresponding to the minimum first light intensity variance value being blocked by clouds is the lowest. Controlling the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels through the target first time window of the photovoltaic solar panel corresponding to the minimum first light intensity variance value improves the stability of controlling the inverters.

[0106] Figure 6 The flowchart of the fifth method for controlling a photovoltaic water pump inverter based on deep learning provided by the embodiments of the present application is shown as Figure 6 As shown, the above method further includes S330 to S340, and the following is a specific description of S330 to S340.

[0107] S330. Respectively obtain the sequential light intensities of multiple associated photovoltaic solar panels of the target photovoltaic solar panel within the third time window. Respectively determine the multiple third light intensity variance values of the multiple third sequential light intensities of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, and determine the minimum third light intensity variance value among the multiple third light intensity variance values.

[0108] To further improve the control effect on the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, the sequential light intensities of multiple associated photovoltaic solar panels of the target photovoltaic solar panel within the third time window can also be respectively obtained, and specifically, the sequential light intensities within the third time window can be obtained through the above step S240.

[0109] After obtaining the temporal light intensity within the third time window, the multiple third light intensity variance values of the target photovoltaic solar panel and multiple associated photovoltaic solar panels can be determined respectively. The multiple third light intensity variance values characterize the fluctuation amplitude of the third light intensity of the target photovoltaic solar panel and multiple associated photovoltaic solar panels. Further, the minimum third light intensity variance value among the multiple third light intensity variance values can be determined. The minimum third light intensity variance value is the third light intensity with the smallest fluctuation amplitude.

[0110] S340. Obtain the third time window of the photovoltaic solar panel corresponding to the minimum third light intensity variance value as the target third time window. Through the weather state recognition unit, determine the weighted summation weights corresponding to the target first time window and the target third time window according to the weather state information within the target first time window and the target third time window. Sum the temporal light intensities of the target first time window and the target third time window according to the weighted summation weights corresponding to the target first time window and the target third time window as the temporal light intensity within the target first time window, and determine the unified temporal prediction output voltage and temporal prediction output current of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels according to the temporal light intensity within the target first time window.

[0111] After obtaining the minimum third light intensity variance value, the third time window of the photovoltaic solar panel corresponding to the minimum third light intensity variance value can be obtained as the target third time window. The detected value of the light intensity within the target third time window may be the most accurate, most in line with the local actual light intensity change situation, and have the lowest frequency of being blocked by clouds. Furthermore, through the weather state recognition unit, determine the weighted summation weights corresponding to the target first time window and the target third time window according to the weather state information within the target first time window and the target third time window, realizing the control of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels based on the target first time window and the target third time window where the detected value of the light intensity may be the most accurate, most in line with the local actual light intensity change situation, and have the lowest frequency of being blocked by clouds.

[0112] When controlling the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, sum the temporal light intensities of the target first time window and the target third time window according to the weighted summation weights corresponding to the target first time window and the target third time window as the temporal light intensity within the target first time window. Specifically, the method in step S250 can be used to determine the temporal light intensity within the target first time window.

[0113] After obtaining the chronological light intensity within the target first time window by the method in step S250, the chronological predicted output voltage and chronological predicted output current of the inverter of the target photovoltaic solar panel and multiple associated photovoltaic solar panels can be determined according to the chronological light intensity within the target first time window. Specifically, the chronological light intensity within the target first time window can be determined according to the above method, realizing the unified control of the inverter of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, and successfully reducing the calculation amount.

[0114] The beneficial effect of the above implementation manner is that, according to the target first time window and the target third time window with the detection value of the light intensity being possibly the most accurate, most in line with the actual local light intensity change situation, and having the lowest frequency of being blocked by clouds, the control of the inverter of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is improved, the unified control of the inverter of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is successfully reduced, and the control effect of the system of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is improved.

[0115] Figure 7 The flowchart of the sixth photovoltaic water pump inverter control method based on deep learning provided by the embodiment of the present application is shown as Figure 7 shown. The above method further includes S410 to S420, and the following is a specific description of S410 to S420.

[0116] S410: Obtain the weather classification information of multiple associated photovoltaic solar panels of the target photovoltaic solar panel respectively. When the weather classification information of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is the same, determine the chronological average light intensity, chronological average panel temperature, chronological average output voltage, chronological average output current, and chronological average output pressure within the first time window of the target photovoltaic solar panel and multiple associated photovoltaic solar panels.

[0117] When controlling the target photovoltaic solar panel and multiple associated photovoltaic solar panels, the weather classification information of multiple associated photovoltaic solar panels of the target photovoltaic solar panel can be obtained respectively. When the weather classification information of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is the same, it indicates that the weather classification information corresponding to the target photovoltaic solar panel and multiple associated photovoltaic solar panels is relatively accurate, and the inverter of the target photovoltaic solar panel and multiple associated photovoltaic solar panels can be centrally controlled.

[0118] When performing centralized control on the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, it is possible to determine the sequential average light intensity within the first time window, the sequential average panel temperature within the second time window, the sequential average output voltage, the sequential average output current, and the sequential average output pressure of the target photovoltaic solar panel and multiple associated photovoltaic solar panels. Furthermore, centralized control can be performed on the target photovoltaic solar panel and multiple associated photovoltaic solar panels based on the mean values of the parameters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels.

[0119] S420. Determine the unified sequential predicted output voltage and sequential predicted output current of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels based on the sequential average light intensity within the first time window, the sequential average panel temperature within the second time window, the sequential average output voltage, the sequential average output current, and the sequential average output pressure of the target photovoltaic solar panel and multiple associated photovoltaic solar panels.

[0120] When performing centralized control on the target photovoltaic solar panel and multiple associated photovoltaic solar panels based on the mean values of the parameters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, it is possible to determine the unified sequential predicted output voltage and sequential predicted output current of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels based on the sequential average light intensity within the first time window, the sequential average panel temperature within the second time window, the sequential average output voltage, the sequential average output current, and the sequential average output pressure of the target photovoltaic solar panel and multiple associated photovoltaic solar panels. Specifically, the inverter can be controlled according to S210 to S230 above, reducing the computational load for controlling the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels.

[0121] The beneficial effect of the above implementation is that when the weather classification information of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is the same, indicating that the weather classification information corresponding to the target photovoltaic solar panel and multiple associated photovoltaic solar panels is relatively accurate, centralized control is performed on the target photovoltaic solar panel and multiple associated photovoltaic solar panels based on the mean values of the parameters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, reducing the computational load for controlling the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, and improving the accuracy and control effect of controlling the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels.

[0122] Figure 8 The flowchart of the seventh photovoltaic water pump inverter control method based on deep learning provided by the embodiment of the present application is shown as Figure 8 shown. The above method further includes S510 to S520, which will be specifically described below.

[0123] S510. Obtain multiple weighted summation weights corresponding to the target photovoltaic solar panel and multiple associated photovoltaic solar panels in the first time window and the third time window respectively, and determine the target weighted summation weight that is the largest in the first time window among the multiple weighted summation weights.

[0124] When centrally controlling the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, it is possible to obtain multiple weighted summation weights corresponding to the target photovoltaic solar panel and multiple associated photovoltaic solar panels in the first time window and the third time window respectively, that is, obtain multiple weighted summation weights corresponding to the target photovoltaic solar panel in the first time window and the third time window respectively, and obtain multiple weighted summation weights corresponding to multiple associated photovoltaic solar panels in the first time window and the third time window respectively. Further, it is possible to determine the target weighted summation weight that is the largest in the first time window among the multiple weighted summation weights. Among the target weighted summation weights that are the largest in the first time window, the weight of the sequential light intensity within the first time window corresponding to the target weighted summation weight is the largest. According to the target weighted summation weight, the sequential light intensity within the first time window can be considered to the greatest extent, and the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels can be centrally controlled by the sequential light intensity within the first time window that is considered to the greatest extent, ensuring the accuracy of the centralized control of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels.

[0125] S520. Sum and average the sequential light intensities of the target photovoltaic solar panel and multiple associated photovoltaic solar panels in the first time window and the third time window according to the target weighted summation weights corresponding to the first time window and the third time window, and use it as the sequential average light intensity of the target photovoltaic solar panel and multiple associated photovoltaic solar panels within the first time window.

[0126] When centrally controlling the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels, sum and average the sequential light intensities of the target photovoltaic solar panel and multiple associated photovoltaic solar panels in the first time window and the third time window according to the target weighted summation weights corresponding to the first time window and the third time window, and use it as the sequential average light intensity of the target photovoltaic solar panel and multiple associated photovoltaic solar panels within the first time window. The inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels can be centrally controlled by the sequential light intensity within the first time window that is considered to the greatest extent, and by summing and averaging the sequential light intensity within the first time window that is considered to the greatest extent and the sequential light intensity within the third time window, the control accuracy of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels is further improved.

[0127] The beneficial effects of the above implementation method are as follows: when centrally controlling the target photovoltaic solar panel and the inverters of multiple associated photovoltaic solar panels, the target photovoltaic solar panel and the inverters of multiple associated photovoltaic solar panels are centrally controlled by taking into account the chronological light intensity within the first time window to the greatest extent, and the chronological light intensity within the first time window and the chronological light intensity within the third time window of the target photovoltaic solar panel and multiple associated photovoltaic solar panels are summed and averaged, thereby improving the control accuracy of the target photovoltaic solar panel and the inverters of multiple associated photovoltaic solar panels.

[0128] The embodiment of the present application further provides a photovoltaic water pump inverter control system based on deep learning, including a unit for executing the method described in any one of the above.

[0129] Figure 9 It is a schematic logical structure diagram of a photovoltaic water pump inverter control system provided by an embodiment of the present application, as Figure 9 shown. The system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be repeated here.

[0130] It should be noted that the information interaction, execution process, etc. between the above devices / units, due to being based on the same concept as the method embodiment of the present application, for their specific functions and the technical effects brought, please refer to the method embodiment part specifically, and will not be repeated here.

[0131] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used for illustration. In actual applications, the above functions can be allocated to different functional units and modules according to needs, 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. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be repeated here.

[0132] When 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 this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0133] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0135] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in an electrical, mechanical, or other form.

[0136] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A photovoltaic water pump inverter control method based on deep learning, characterized in that: The method comprises: Obtain the timed light intensity and timed panel temperature of the photovoltaic solar panel under working conditions, obtain the timed output voltage and timed output current of the inverter, and obtain the preset timed output pressure of the water flow output by the water pump; wherein, the electric energy output by the photovoltaic solar panel is converted by the inverter to supply power to the water pump; Through the timing prediction model, according to the timing light intensity, the timing battery panel temperature, the timing output voltage, the timing output current and the preset timing output pressure, the timing prediction output voltage and the timing prediction output current of the inverter are determined. The timing prediction output voltage and the timing prediction output current are used to perform maximum power tracking on the inverter; Through the timing prediction model, according to the timing light intensity, timing solar panel temperature, timing output voltage, timing output current and preset timing output pressure, the timing prediction output voltage and timing prediction output current of the inverter are determined, including: Determine the sequential light intensity weight according to the sequential light intensity attention unit, determine the sequential battery panel temperature weight according to the sequential battery panel temperature attention unit, determine the sequential output voltage weight according to the sequential output voltage attention unit, determine the sequential output current weight according to the sequential output current attention unit, and determine the preset sequential output pressure weight according to the preset sequential output pressure attention unit; Determine the inverter's predicted output voltage and predicted output current through a timing prediction model according to the timing light intensity, the timing light intensity weight, the timing battery panel temperature, the timing battery panel temperature weight, the timing output voltage, the timing output voltage weight, the timing output current, the timing output current weight, the preset timing output pressure, and the preset timing output pressure weight; Through the timing prediction model, according to the timing light intensity, the timing battery panel temperature, the timing output voltage, the timing output current and the preset timing output pressure, the timing prediction output voltage and the timing prediction output current of the inverter are determined, and also include: Through the illumination fusion processing unit, the illumination intensity fusion feature is determined according to the sequential illumination intensity and the sequential illumination intensity weight; through the first fusion unit, the first fusion feature is determined according to the illumination intensity fusion feature, the sequential battery panel temperature and the sequential battery panel temperature weight; through the second fusion unit, the second fusion feature is determined according to the illumination intensity fusion feature, the sequential output voltage and the sequential output voltage weight; through the third fusion unit, the second fusion feature is determined according to the illumination intensity fusion feature, the sequential output current and the sequential output current weight; through the third fusion unit, the third fusion feature is determined according to the illumination intensity fusion feature, the preset sequential output pressure and the preset sequential output pressure weight; Through the timing prediction model, the timing predicted output voltage and the timing predicted output current of the inverter are determined according to the light intensity fusion feature, the first fusion feature, the second fusion feature and the third fusion feature.

2. The method according to claim 1, characterized in that The method further comprises: Determine weather classification information according to the time-series light intensity through the weather classification model, obtain a first time window corresponding to the weather classification information, and obtain the time-series light intensity within the first time window; and obtain the time-series battery panel temperature, time-series output voltage, time-series output current and preset time-series output pressure within the second time window; wherein the length of the second time window is greater than the length of the first time window, and both the first time window and the second time window are time windows that are traced back from the current moment; The illumination fusion processing unit determines the illumination intensity fusion feature according to the sequential illumination intensity and the sequential illumination intensity weight in the first time window; the first fusion unit determines the first fusion feature according to the illumination intensity fusion feature, the sequential battery panel temperature and the sequential battery panel temperature weight in the second time window; the second fusion feature is determined according to the illumination intensity fusion feature, the sequential output voltage and the sequential output voltage weight in the second time window by the second fusion unit; the second fusion feature is determined according to the illumination intensity fusion feature, the sequential output current and the sequential output current weight in the second time window by the third fusion unit; the third fusion feature is determined according to the illumination intensity fusion feature, the preset sequential output pressure and the preset sequential output pressure weight in the second time window by the third fusion unit; Through the timing prediction model, the timing predicted output voltage and the timing predicted output current of the inverter are determined according to the light intensity fusion feature, the first fusion feature, the second fusion feature and the third fusion feature.

3. The method according to claim 2, characterized in that The method further comprises: Acquire weather status information in the first time window and the third time window respectively, and determine weighted sum weights corresponding to the first time window and the third time window respectively according to the weather status information in the first time window and the third time window through a weather status identification unit; wherein the third time window is a time window before the first time window, and the duration of the third time window is 3 to 5 times the duration of the first time window; According to the weighted summation weights corresponding to the first time window and the third time window, the temporal illumination intensity of the first time window and the third time window are summed up as the temporal illumination intensity within the first time window.

4. The method according to claim 3, characterized in that The method further comprises: Respectively obtain the time-series illumination intensities of multiple associated photovoltaic solar panels of the target photovoltaic solar panel within the first time window; respectively determine multiple first illumination intensity variance values ​​of multiple first time-series illumination intensities of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels, and determine the minimum first illumination intensity variance value among the multiple first illumination intensity variance values; wherein the multiple associated photovoltaic solar panels are multiple photovoltaic solar panels that are located close to the position of the target photovoltaic solar panel; The first time window of the photovoltaic solar panel corresponding to the minimum first light intensity variance value is obtained as the target first time window; the target light intensity fusion feature is determined through the light fusion processing unit according to the temporal light intensity and the temporal light intensity weight in the target first time window, and the unified temporal predicted output voltage and temporal predicted output current of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels are determined according to the target light intensity fusion feature.

5. The method according to claim 4, characterized in that The method further comprises: Respectively obtain the time-series illumination intensities of multiple associated photovoltaic solar panels of the target photovoltaic solar panel within the third time window; respectively determine multiple third illumination intensity variance values ​​of multiple third time-series illumination intensities of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels, and determine the minimum third illumination intensity variance value among the multiple third illumination intensity variance values; The third time window of the photovoltaic solar panel corresponding to the minimum third light intensity variance value is obtained as the target third time window; the weighted sum weights corresponding to the target first time window and the target third time window are determined through the weather state recognition unit according to the weather state information in the target first time window and the target third time window; the time series light intensities of the target first time window and the target third time window are summed according to the weighted sum weights corresponding to the target first time window and the target third time window as the time series light intensity in the target first time window, and the unified time series predicted output voltage and time series predicted output current of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels are determined according to the time series light intensity in the target first time window.

6. The method according to claim 5, characterized in that The method further comprises: Respectively obtain weather classification information of multiple associated photovoltaic solar panels of the target photovoltaic solar panel, and when the weather classification information of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels are the same, determine the time-series average light intensity within a first time window, the time-series average panel temperature within a second time window, the time-series average output voltage, the time-series average output current, and the time-series average output pressure of the target photovoltaic solar panel and the multiple associated photovoltaic solar panels; Based on the sequential average light intensity of the target photovoltaic solar panel and multiple associated photovoltaic solar panels in the first time window, the sequential average panel temperature, the sequential average output voltage, the sequential average output current and the sequential average output pressure in the second time window, the unified sequential predicted output voltage and sequential predicted output current of the inverters of the target photovoltaic solar panel and multiple associated photovoltaic solar panels are determined.

7. The method according to claim 6, characterized in that The method further comprises: Obtain multiple weighted sum weights corresponding to the target photovoltaic solar panel and multiple associated photovoltaic solar panels in the first time window and the third time window respectively, and determine the target weighted sum weight with the largest value in the first time window among the multiple weighted sum weights; According to the target weighted summation weights corresponding to the first time window and the third time window, the time-series light intensities of the target photovoltaic solar panel and multiple associated photovoltaic solar panels in the first time window and the third time window are summed and averaged, which is used as the time-series average light intensity of the target photovoltaic solar panel and multiple associated photovoltaic solar panels in the first time window.

8. A photovoltaic water pump inverter control system based on deep learning, characterized in that: Comprising means for performing the method according to any one of claims 1 to 7.

Images