Intelligent building energy control method and system based on photovoltaic storage and direct flexible

Abstract

The present invention discloses an intelligent building energy control method and system based on photovoltaic, storage, direct current and flexible control, which is applied to smart buildings. The smart buildings are provided with a control module, a photovoltaic module, an energy storage module, a DC distribution module, a plurality of DC power-consuming devices and a plurality of AC power-consuming devices. The control module can determine the photovoltaic power generation prediction data based on the weather forecast data of the day and a first prediction model, and determine the predicted power consumption of the grid access of the day in combination with the daily average total power consumption of the target smart building and the current power parameters of the energy storage module. After inputting it into the second prediction model, a time-segmented photovoltaic power generation prediction data sequence for determining the photovoltaic power generation strategy can be obtained. The photovoltaic power generation process of the smart building is more intelligently controlled by using photovoltaic, storage, direct current and flexible control technology.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic-storage-direct-flexible technology, and in particular to a building energy intelligent control method and system based on photovoltaic-storage-direct-flexible technology. Background Art

[0002] PEDF is the abbreviation of the four technologies of solar photovoltaic, energy storage, direct current and flexibility in the field of construction. At present, some buildings built with green environmental protection concepts, such as industrial buildings and public buildings, have adopted some technologies of PEDF, such as photovoltaic power generation devices and wind power generation devices. However, a large number of distributed energy sources have been abandoned after installation in these green buildings, resulting in low utilization rate of new energy; moreover, there is a lack of analysis on the utilization rate of new energy, the operating status of PEDF equipment, and the power consumption, so the entire PEDF system cannot be used reasonably. Summary of the invention

[0003] The embodiments of the present invention provide a method and system for intelligent building energy control based on photovoltaic storage and direct-flexible, aiming to solve the problem in the prior art that green buildings lack analysis of the utilization rate of new energy, the operating status of photovoltaic storage equipment, electricity consumption, etc., and cannot reasonably use the entire photovoltaic storage and direct-flexible system.

[0004] In the first aspect, an embodiment of the present invention provides a building energy intelligent control method based on photovoltaic storage direct and flexible, which is applied to a smart building, wherein the smart building is provided with a control module, a photovoltaic module, an energy storage module, a DC distribution module, a plurality of DC power devices and a plurality of AC power devices, the photovoltaic module is connected to the energy storage module, the energy storage module is connected to the plurality of DC power devices through the DC distribution module, the energy storage module is also connected to a plurality of AC power devices compatible with AC and DC among the plurality of AC power devices through the DC distribution module, the control module is communicatively connected to the photovoltaic module, the energy storage module and the DC distribution module; the building energy intelligent control method based on photovoltaic storage direct and flexible comprises:

[0005] The control module responds to the energy intelligent control instruction, obtains a target smart building corresponding to the energy intelligent control instruction, and determines a building type corresponding to the target smart building;

[0006] The control module determines the photovoltaic power generation prediction data corresponding to the weather forecast data of the day based on the weather forecast data of the day and the first prediction model trained in advance; wherein the first prediction model is obtained by training the first prediction model to be trained using the historical weather forecast-photovoltaic power generation data set as a training set;

[0007] The control module obtains the daily average total power consumption of the target smart building and the current power parameters of the energy storage module, and determines the predicted power consumption for grid access on that day based on the daily average total power consumption, the current power parameters and the photovoltaic power generation prediction data; wherein the current power parameters of the energy storage module include at least the current remaining power, the maximum storage power and the average charging power;

[0008] The control module acquires a time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data of the day based on the photovoltaic power generation prediction data and a pre-trained second prediction model;

[0009] The control module obtains the target historical date grid access forecast power consumption data from the historical date grid access forecast power consumption data set based on the current day grid access forecast power consumption and the preset screening conditions, and obtains the current day peak time period forecast power consumption and the current day trough time period forecast power consumption corresponding to the current day grid access forecast power consumption from the target historical date grid access forecast power consumption data; wherein each historical date grid access forecast power consumption data in the historical date grid access forecast power consumption data set includes at least the historical date, the actual grid access power consumption on the historical date, the actual power consumption on the peak time period on the historical date, and the actual power consumption on the trough time period on the historical date;

[0010] The control module determines the photovoltaic power generation control strategy for the day based on the time segment photovoltaic power generation prediction data sequence, the power generation working parameters of the photovoltaic module, the predicted power consumption during the peak time period of the day and the predicted power consumption during the trough time period of the day, and sends it to the photovoltaic module;

[0011] The photovoltaic module performs photovoltaic power generation based on the photovoltaic power generation control strategy for the day, and transmits the photovoltaic power generation electric energy to the energy storage module and / or multiple AC power consumption equipment.

[0012] In a second aspect, an embodiment of the present invention further provides a building energy intelligent control system based on photovoltaic storage and direct-flexible, which is applied to a smart building, wherein a control module, a photovoltaic module, an energy storage module, a DC distribution module, a plurality of DC power devices and a plurality of AC power devices are provided in the smart building, wherein the photovoltaic module is connected to the energy storage module, the energy storage module is connected to the plurality of DC power devices through the DC distribution module, the energy storage module is also connected to a plurality of AC power devices compatible with AC and DC among the plurality of AC power devices through the DC distribution module, and the control module is communicatively connected to the photovoltaic module, the energy storage module and the DC distribution module;

[0013] The control module is used to respond to the energy intelligent control instruction, obtain the target smart building corresponding to the energy intelligent control instruction, and determine the building type corresponding to the target smart building;

[0014] The control module is further used to determine the photovoltaic power generation prediction data corresponding to the weather forecast data of the day based on the weather forecast data of the day and the pre-trained first prediction model; wherein the first prediction model is obtained by training the first prediction model to be trained using the historical weather forecast-photovoltaic power generation data set as a training set;

[0015] The control module is further used to obtain the daily average total power consumption of the target smart building and the current power parameters of the energy storage module, and determine the predicted power consumption for grid access on the day based on the daily average total power consumption, the current power parameters and the photovoltaic power generation prediction data; wherein the current power parameters of the energy storage module include at least the current remaining power, the maximum storage power and the average charging power;

[0016] The control module acquires a time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data of the day based on the photovoltaic power generation prediction data and a pre-trained second prediction model;

[0017] The control module is further used to obtain the target historical date power grid access forecast power consumption data from the historical date power grid access forecast power consumption data set based on the current day power grid access forecast power consumption and preset screening conditions, and obtain the current day peak time period forecast power consumption and the current day trough time period forecast power consumption corresponding to the current day power grid access forecast power consumption from the target historical date power grid access forecast power consumption data; wherein each historical date power grid access forecast power consumption data in the historical date power grid access forecast power consumption data set includes at least the historical date, the actual power grid access power consumption of the historical date, the actual power consumption of the peak time period of the historical date, and the actual power consumption of the trough time period of the historical date;

[0018] The control module is further used to determine the photovoltaic power generation control strategy for the day based on the time segment photovoltaic power generation prediction data sequence, the power generation working parameters of the photovoltaic module, the predicted power consumption during the peak time period of the day and the predicted power consumption during the trough time period of the day, and send it to the photovoltaic module;

[0019] The photovoltaic module is used to perform photovoltaic power generation based on the photovoltaic power generation control strategy for the day, and transmit the photovoltaic power generation electric energy to the energy storage module and / or multiple AC power consumption equipment.

[0020] The embodiment of the present invention provides a building energy intelligent control method and system based on photovoltaic storage direct and flexible, which is applied to smart buildings. The smart building is provided with a control module, a photovoltaic module, an energy storage module, a DC distribution module, a plurality of DC power devices and a plurality of AC power devices. The photovoltaic module is connected to the energy storage module, the energy storage module is connected to the plurality of DC power devices through the DC distribution module, the energy storage module is also connected to a plurality of AC power devices compatible with AC and DC among the plurality of AC power devices through the DC distribution module, the control module is connected to the photovoltaic module, the energy storage module and the DC distribution module in communication; the building energy intelligent control method based on photovoltaic storage direct and flexible includes: the control module responds to energy The intelligent control instruction obtains the target smart building corresponding to the energy intelligent control instruction, and determines the building type corresponding to the target smart building; the control module determines the photovoltaic power generation prediction data corresponding to the weather forecast data of the day based on the weather forecast data of the day and the pre-trained first prediction model; wherein the first prediction model is obtained by training the first prediction model to be trained with the historical weather forecast-photovoltaic power generation data set as the training set; the control module obtains the daily average total power consumption of the target smart building and the current power parameters of the energy storage module, and determines the predicted power consumption of the grid access on the day based on the daily average total power consumption, the current power parameters and the photovoltaic power generation prediction data; wherein the storage module The current power parameters of the energy module at least include the current remaining power, the maximum storage power and the average charging power; the control module obtains the time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data of the day based on the photovoltaic power generation prediction data and the pre-trained second prediction model; the control module obtains the target historical date grid access prediction power consumption data from the historical date grid access prediction power consumption data set based on the grid access prediction power consumption of the day and the preset screening conditions, and obtains the peak time period prediction power consumption of the day and the trough time period prediction power consumption of the day corresponding to the grid access prediction power consumption of the day from the grid access prediction power consumption data of the target historical date; wherein Each piece of historical date grid access predicted electricity consumption data in the historical date grid access predicted electricity consumption data set at least includes the historical date, the historical date grid access actual electricity consumption, the historical date peak time period actual electricity consumption and the historical date trough time period actual electricity consumption; the control module determines the photovoltaic power generation control strategy for the day based on the time segment photovoltaic power generation prediction data sequence, the power generation working parameters of the photovoltaic module, the predicted electricity consumption for the peak time period of the day and the predicted electricity consumption for the trough time period of the day, and sends it to the photovoltaic module; the photovoltaic module performs photovoltaic power generation according to the photovoltaic power generation control strategy for the day, and transmits the photovoltaic power generation electric energy to the energy storage module and / or multiple AC power consumption equipment.The embodiment of the present invention can determine photovoltaic power generation prediction data based on the control module in combination with the weather forecast data of the day and the first prediction model, and determine the predicted power consumption of the grid access on the day in combination with the daily average total power consumption of the target smart building and the current power parameters of the energy storage module. After inputting it into the second prediction model, a time-segmented photovoltaic power generation prediction data sequence for determining the photovoltaic power generation strategy can be obtained, and the photovoltaic power generation process of the smart building is more intelligently controlled by the photovoltaic storage direct-flexible technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0022] Figure 1 A schematic block diagram of a building energy intelligent control system based on photovoltaic storage and direct flexible control provided by an embodiment of the present invention;

[0023] Figure 2 A schematic diagram of a flow chart of a building energy intelligent control method based on photovoltaic storage and direct flexible control provided by an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of a sub-process of a building energy intelligent control method based on photovoltaic storage and direct flexible control provided by an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of a sub-process of a building energy intelligent control method based on photovoltaic storage and direct flexible control provided by an embodiment of the present invention;

[0026] Figure 5 A schematic diagram of a sub-process of a building energy intelligent control method based on photovoltaic storage and direct flexible control provided by an embodiment of the present invention;

[0027] Figure 6 A schematic diagram of a sub-process of a building energy intelligent control method based on photovoltaic storage and direct flexible control provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0030] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0031] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0032] Please also refer to Figure 1 and Figure 2 ,in Figure 1 A schematic block diagram of a building energy intelligent control system based on photovoltaic storage and direct flexible power supply provided in an embodiment of the present invention (which can also be regarded as a scenario schematic diagram of a building energy intelligent control method based on photovoltaic storage and direct flexible power supply provided in an embodiment of the present invention), Figure 2 FIG. 1 is a flow chart of a building energy intelligent control method based on photovoltaic storage and direct flexible control provided by an embodiment of the present invention. Figure 1 As shown, the intelligent control method of building energy based on photovoltaic storage and direct flexible provided by the embodiment of the present invention is applied to a smart building, in which a control module 10, a photovoltaic module 20, an energy storage module 30, a DC distribution module 40, a plurality of DC power devices 50 and a plurality of AC power devices 60 are provided. The photovoltaic module 20 is connected to the energy storage module 30, and the energy storage module 30 is connected to the plurality of DC power devices 50 through the DC distribution module 40. The energy storage module 30 is also connected to a plurality of AC power devices compatible with AC and DC among the plurality of AC power devices 60 through the DC distribution module 40. The control module 10 is all connected to the photovoltaic module 20, the energy storage module 30 and the DC distribution module 40. In specific implementation, the photovoltaic module 20 is also connected to the DC distribution module 40.

[0033] like Figure 2 As shown, the method includes the following steps S110-S170.

[0034] S110. The control module responds to the energy intelligent control instruction, obtains a target smart building corresponding to the energy intelligent control instruction, and determines a building type corresponding to the target smart building.

[0035] In this embodiment, the control module can be regarded as the control center of the entire smart building and includes at least one control host, and can perform intelligent control on the daily photovoltaic power generation, energy storage, and specific power consumption of DC power equipment of the smart building. Specifically, taking the control module for the daily energy control process of the smart building as an example to illustrate the technical solution of this application, first, when the control module receives the energy intelligent control instruction generated locally, sent by other smart terminals, or other servers (the generation time of the energy intelligent control instruction can be pre-set to any time point between 00:00-00:30 every day, such as 00:05), in order to more accurately generate the corresponding control strategy, it is necessary to first obtain the target smart building corresponding to the energy intelligent control instruction, and then use the intelligent control of each device in the target smart building (such as photovoltaic module, energy storage module, DC distribution module, multiple DC power equipment and multiple AC power equipment) as the control target. After determining the target smart building, its corresponding building type can also be obtained, such as residential buildings, public buildings, industrial buildings, and agricultural buildings, and the energy control strategy corresponding to the target smart building can be obtained more intelligently in combination with the obtained building type. In addition, the control module can also regularly obtain the photovoltaic power generation control strategy library and energy storage module charging control strategy library corresponding to the building type of the target smart building from the cloud server.

[0036] S120, the control module determines photovoltaic power generation prediction data corresponding to the weather forecast data of the day based on the weather forecast data of the day and a pre-trained first prediction model.

[0037] The first prediction model is obtained by training the first prediction model using the historical weather forecast-photovoltaic power generation data set as a training set.

[0038] In this embodiment, after the control module detects the energy intelligent control instruction, it can first know the instruction generation time of the energy intelligent control instruction and the specific date corresponding to it, and then obtain the weather forecast data for the day from other servers according to the specific date of generation of the energy intelligent control instruction, and can also obtain the light intensity data for the day in the weather forecast data for the day (more specifically, the light intensity-time curve is also known). Then the weather forecast data for the day is input into the first prediction model, mainly to predict the photovoltaic power generation for the day and obtain the photovoltaic power generation prediction data. It can be seen that through the above method, the control module can quickly predict the photovoltaic power generation for the day in combination with the weather forecast data for the day to obtain the photovoltaic power generation prediction data.

[0039] Among them, in the historical weather forecast-photovoltaic power generation data set, it can be composed of the light intensity data in the weather forecast data of each day in the whole year of last year, half of last year (such as the first half of last year or the second half of last year), a quarter (which can be the corresponding quarter of the quarter to which the instruction generation date of the energy intelligent control instruction belongs, calculated one year ago) or a month (which can be the corresponding month of the month to which the instruction generation date of the energy intelligent control instruction belongs, calculated one year ago). The first prediction model can be a feedforward neural network. After model training is performed on the first prediction model to be trained using the historical weather forecast-photovoltaic power generation data set as a training set, the first prediction model can be obtained.

[0040] In one embodiment, if Figure 3 As shown, step S120 includes:

[0041] S121, obtaining the equivalent peak sunshine hours corresponding to the light intensity data in the weather forecast data for the day;

[0042] S122: Input the equivalent peak sunshine hours into the first prediction model to obtain the photovoltaic power generation prediction data.

[0043] In this embodiment, after obtaining the light intensity-time curve graph in the weather forecast data for the day, the equivalent peak sunshine hours can be determined accordingly. The specific process is as follows:

[0044] 11) Divide the 24 hours of the day into 24 time periods according to each hour;

[0045] 12) For each of the 24 time periods, the corresponding average light intensity is obtained and divided by the preset standard light intensity to obtain the equivalent hours for each time period;

[0046] 13) Sum the equivalent hours of the above 24 time periods to obtain the equivalent peak sunshine hours for the day.

[0047] After obtaining the equivalent peak sunshine hours of the day, it is input as input data into the first prediction model to obtain the photovoltaic power generation prediction data. It can be seen that the photovoltaic power generation of the day can be quickly predicted based on the light intensity related data in the weather forecast data in the early morning of the day, and can be used as reference data for subsequent energy intelligent control.

[0048] In one embodiment, after step S122, the method further includes:

[0049] Based on the preset photovoltaic power generation prediction strategy, the maximum illuminated area of ​​the photovoltaic module, the conversion efficiency of the photovoltaic module, the transmission line loss rate of the smart building and the equivalent peak sunshine hours, determine the photovoltaic power generation theoretical prediction data corresponding to the weather forecast data of the day;

[0050] Based on a preset weighted summation strategy, the photovoltaic power generation prediction data and the photovoltaic power generation theoretical prediction data, current photovoltaic power generation adjustment prediction data is determined, and the photovoltaic power generation prediction data is updated with the current photovoltaic power generation adjustment prediction data.

[0051] In this embodiment, in order to improve the reliability of photovoltaic power generation prediction data, the obtained photovoltaic power generation theoretical prediction data can also be predicted from another dimension. Specifically, the maximum illumination area of ​​the photovoltaic module, the conversion efficiency of the photovoltaic module, the transmission line loss rate of the smart building and the equivalent peak sunshine hours are first obtained, and then the above parameters are substituted into the calculation formula corresponding to the photovoltaic power generation prediction strategy to obtain the photovoltaic power generation theoretical prediction data; wherein the calculation formula corresponding to the photovoltaic power generation prediction strategy is E=S*H*A1*(1-A2), S is the maximum illumination area of ​​the photovoltaic module, H is the equivalent peak sunshine hours, A1 represents the conversion efficiency of the photovoltaic module, and A2 represents the conversion efficiency of the photovoltaic module. The conversion efficiency and A2 represent the transmission line loss rate of the smart building; wherein, in the specific implementation, the calculation formula corresponding to the photovoltaic power generation prediction strategy can also be adjusted to multiply by one more photovoltaic module health coefficient A3, and the photovoltaic module health coefficient A3 can be specifically determined by the photovoltaic module filling factor, and the filling factor = the maximum power point power of the photovoltaic module / (the open circuit voltage of the photovoltaic module * the short circuit current of the photovoltaic module), and then the filling factor / 0.7 can be used to obtain the photovoltaic module health coefficient, which has a major impact on the conversion efficiency of the photovoltaic module (generally, the higher the photovoltaic module health coefficient, the higher the photovoltaic module conversion efficiency). Afterwards, the calculation result of the photovoltaic power generation prediction data * the first preset weight value + the photovoltaic power generation theoretical prediction data * the second preset weight value can be used as the current photovoltaic power generation adjustment prediction data based on the preset weighted summation strategy (wherein, the first preset weight value + the second preset weight value = 1). Finally, the photovoltaic power generation prediction data is directly updated with the current photovoltaic power generation adjustment prediction data, thereby obtaining the latest photovoltaic power generation prediction data.

[0052] S130, the control module obtains the daily average total power consumption of the target smart building and the current power parameters of the energy storage module, and determines the predicted power consumption for grid access on that day based on the daily average total power consumption, the current power parameters and the photovoltaic power generation prediction data.

[0053] Among them, the current power parameters of the energy storage module include at least the current remaining power, the maximum storage power and the average charging power.

[0054] In this embodiment, the energy storage module in the smart building can specifically adopt a lithium battery module including a battery management system, and the current power parameters of the energy storage module obtained by the control module at least include the current remaining power, the maximum storage power and the average charging power. The calculation result of the daily average total power consumption - the current remaining power in the current power parameter - the photovoltaic power generation prediction data can be used as the predicted power consumption for grid access on that day.

[0055] S140, the control module obtains a time-segmented photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data for the day based on the photovoltaic power generation prediction data and a pre-trained second prediction model.

[0056] In this embodiment, after the photovoltaic power generation prediction data of the day is obtained in the control module, multiple historical photovoltaic power generation prediction data and the corresponding historical time segment photovoltaic power generation prediction data sequences can be combined as reference data and used together to input into the second prediction model to obtain the time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data of the day. The time segment photovoltaic power generation prediction data sequence obtained in the above manner can be used as a basis for controlling the photovoltaic power generation power of the photovoltaic module in each time period of the day.

[0057] In one embodiment, if Figure 4 As shown, step S140 includes:

[0058] S141, obtaining, from the historical weather forecast data set, target historical weather forecast data that has the maximum similarity value with the area to which the target smart building belongs, the weather forecast data of the day and the month to which it belongs, and a target historical date corresponding to the target historical weather forecast data;

[0059] S142, acquiring a plurality of candidate historical dates whose date intervals from the historical target date do not exceed a preset day interval threshold, and forming a candidate historical date set with the historical target date;

[0060] S143, acquiring historical time segment photovoltaic power generation prediction data sequences corresponding to multiple historical dates in the candidate historical date set from the locally stored historical time segment photovoltaic power generation prediction data sequence set, and forming multiple input photovoltaic power generation prediction data sequences in chronological order;

[0061] S144, inputting the plurality of input photovoltaic power generation prediction data sequences into the second prediction model to obtain a time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data for the day.

[0062] In this embodiment, a historical weather forecast data set corresponding to the target smart building is stored in a memory corresponding to the control module, wherein each historical weather forecast data includes a historical date, and the memory also stores historical date photovoltaic power generation prediction data and historical time segment photovoltaic power generation prediction data sequence corresponding to each historical weather forecast data.

[0063] When determining the time segment photovoltaic power generation prediction data sequence for the day based on the photovoltaic power generation prediction data and the second prediction model, the specific process is to first determine the target historical weather forecast data that has the maximum similarity value with the area to which the target smart building belongs, the weather forecast data for the day and the month to which it belongs. For example, in the historical weather forecast data set, there is a historical weather forecast data that is also the weather forecast data for the same area as the target smart building (wherein the historical weather forecast data and the weather forecast data for the day can both be weather forecast data for a specific area), the corresponding date of the historical weather forecast data belongs to the month and The month to which the weather forecast data for the day belongs is the same month (may not belong to the same year), and the similarity between the light intensity-time curve graph of the historical weather forecast data and the light intensity-time curve graph of the weather forecast data for the day has the maximum similarity (when calculating the similarity of two curves, the Euclidean distance between the two curves can be calculated as the similarity between the curves, and the smaller the Euclidean distance between the two curves, the more similar the two curves are), then the historical weather forecast data can be determined as the target historical weather forecast data, and the target historical date corresponding to the target historical weather forecast data can also be determined at the same time.

[0064] Afterwards, based on the preset day interval threshold (such as 15 days, 30 days, etc.), the historical target date is taken as the starting date, and multiple dates including the historical target date ~ the historical target date + the preset day interval threshold are obtained to form a candidate historical date set.

[0065] Then, the historical time segment photovoltaic power generation prediction data sequences corresponding to the multiple historical dates of the candidate historical date set are obtained from the historical time segment photovoltaic power generation prediction data sequence set locally stored in the memory, and each historical time segment photovoltaic power generation prediction data sequence includes 24 photovoltaic power generation prediction data (corresponding to each hour of the 24 hours of a day). When the above multiple historical time segment photovoltaic power generation prediction data sequences are combined into multiple input photovoltaic power generation prediction data sequences in chronological order, they can be composed of input data input to the second prediction model, and finally the time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data of the day is output through the second prediction model. Among them, the second prediction model can specifically adopt a time series model. The obtained time segment photovoltaic power generation prediction data sequence can be used as reference data for the control module to generate corresponding control strategies.

[0066] S150. The control module obtains the target historical date grid access forecast power consumption data from the historical date grid access forecast power consumption data set based on the grid access forecast power consumption for the day and preset screening conditions, and obtains the peak time period forecast power consumption for the day and the trough time period forecast power consumption for the day corresponding to the grid access forecast power consumption for the day from the target historical date grid access forecast power consumption data.

[0067] Among them, each piece of historical date grid access predicted electricity consumption data in the historical date grid access predicted electricity consumption data set includes at least the historical date, the actual grid access electricity consumption on the historical date, the actual electricity consumption during the peak period of the historical date, and the actual electricity consumption during the trough period of the historical date.

[0068] In this embodiment, the memory corresponding to the control module also stores the predicted power consumption of the grid access on the historical date corresponding to each historical date, and the actual power consumption of the grid access on the historical date corresponding to each historical date, and the actual power consumption of the peak time period of the historical date and the actual power consumption of the trough time period of the historical date are also corresponding to each historical date. After the predicted power consumption of the grid access on the current day is determined, a historical date predicted power consumption of the grid access on the current day that meets the preset screening conditions can be selected from multiple historical date predicted power consumption data of the grid access, and the actual power consumption of the peak time period of the historical date and the actual power consumption of the trough time period of the historical date included in the predicted power consumption data of the grid access on the current day are respectively used as the predicted power consumption of the peak time period of the current day and the predicted power consumption of the trough time period of the current day corresponding to the predicted power consumption of the grid access on the current day.

[0069] In one embodiment, if Figure 5 As shown, step S150 includes:

[0070] S151, obtaining the target historical date power grid access predicted power consumption data that has the maximum similarity value with the building type of the target smart building, the power grid access predicted power consumption on the day and the month to which it belongs from the historical date power grid access predicted power consumption data set;

[0071] S152. Obtain the actual power consumption during the peak period of the target historical date and the actual power consumption during the trough period of the target historical date corresponding to the predicted power consumption data for grid access on the target historical date, and use the actual power consumption during the peak period of the target historical date as the predicted power consumption during the peak period of the day, and use the actual power consumption during the trough period of the historical date.

[0072] In this embodiment, the predicted power consumption of the grid access obtained on the day is only used for the various power-consuming devices in the smart building that need to be directly connected to the grid from the grid on the day (such as AC power-consuming devices, etc.), but because the price of the grid electricity is different in different time periods, more specifically, the grid electricity-powered power-consuming devices can be connected to the grid power supply and the energy storage module can be charged first during the electricity trough period when the grid electricity price is lower, and the electricity generated by the photovoltaic module and the electricity stored by the energy storage module can be used first during the electricity peak period when the grid electricity price is higher. For example, based on the month to which the day belongs (because the peak time period and the trough time period are different in spring and autumn and summer and winter), the peak time period of the day (generally in the two time periods of 7:00~11:00 and 13:00~23:00, which lasts for 14 hours) and the trough time period (other time periods except the peak time period, which lasts for 10 hours) can be known.

[0073] After determining the target historical date power grid access predicted power consumption data that has the maximum similarity value with the building type of the target smart building, the predicted power consumption of the power grid access on the day and the month to which it belongs, for example, there is a historical date power grid access predicted power consumption data in the historical date power grid access predicted power consumption data that is also for the same building type of the target smart building, the corresponding month of the historical date power grid access predicted power consumption data and the month to which the predicted power grid access on the day belongs are the same month (may not belong to the same year), and the difference between the historical date power grid access predicted power consumption data and the predicted power grid access on the day is the smallest in absolute value (for example, the absolute value of the difference between the two can be 0 at the minimum), it is determined that the preset screening conditions are met, and the historical date power grid access predicted power consumption data can be determined as the target historical date power grid access predicted power consumption data. Afterwards, the actual power consumption during the peak time period of the target historical date and the actual power consumption during the trough time period of the target historical date corresponding to the predicted power grid access power consumption data of the target historical date are specifically obtained, and the actual power consumption during the peak time period of the target historical date is used as the predicted power consumption during the peak time period of the day, and the actual power consumption during the trough time period of the historical date is used. It can be seen that the above method can quickly determine the daily peak time period predicted power consumption and the daily trough time period predicted power consumption corresponding to the daily grid access predicted power consumption, and use them as reference data for generating the daily power consumption control strategy.

[0074] S160, the control module determines the photovoltaic power generation control strategy for the day based on the time-segmented photovoltaic power generation prediction data sequence, the power generation operating parameters of the photovoltaic module, the predicted power consumption during the peak time period of the day and the predicted power consumption during the trough time period of the day, and sends it to the photovoltaic module.

[0075] In this embodiment, the photovoltaic power generation control strategy for the day can be determined in the control module in combination with the time-segmented photovoltaic power generation prediction data sequence, the power generation working parameters of the photovoltaic module, the predicted power consumption during the peak time period of the day, and the predicted power consumption during the valley time period of the day. Specifically, the photovoltaic power generation prediction data belonging to the peak time period of the day in the time-segmented photovoltaic power generation prediction data sequence can be summed to obtain the predicted photovoltaic power generation during the peak time period of the day; the photovoltaic power generation prediction data belonging to the valley time period of the day in the time-segmented photovoltaic power generation prediction data sequence can also be summed to obtain the predicted photovoltaic power generation during the valley time period of the day. Afterwards, the corresponding target photovoltaic power generation control strategy is obtained from the preset photovoltaic power generation control strategy library in combination with the relationship between the predicted photovoltaic power generation during the valley time period of the day and the predicted power consumption during the valley time period of the day, and the relationship between the predicted photovoltaic power generation during the peak time period of the day and the predicted power consumption during the peak time period of the day.

[0076] In one embodiment, if Figure 6 As shown, step S160 includes:

[0077] S161. If it is determined that the photovoltaic power generation predicted during the valley period of the day is greater than the power consumption predicted during the valley period of the day, and the photovoltaic power generation predicted during the peak period of the day is less than the power consumption predicted during the peak period of the day, then the first target preset photovoltaic power generation control strategy is obtained from the preset photovoltaic power generation control strategy library and used as the photovoltaic power generation control strategy for the day, and sent to the photovoltaic module; wherein the first target preset photovoltaic power generation control strategy is used to control the photovoltaic module to generate electricity at the maximum photovoltaic power generation power during the valley period of the day and store the electric energy generated by the photovoltaic power generation in the energy storage module, and is used to control the photovoltaic module to generate electricity at the maximum photovoltaic power generation power during the peak period of the day and supply the electric energy generated by the photovoltaic power generation to multiple AC power consumption equipment, or supply power to a DC distribution module to supply power to multiple DC power consumption equipment;

[0078] S162. If it is determined that the predicted photovoltaic power generation during the valley period of the day is less than the predicted electricity consumption during the valley period of the day, and the predicted photovoltaic power generation during the peak period of the day is less than the predicted electricity consumption during the peak period of the day, then obtain the second target preset photovoltaic power generation control strategy from the photovoltaic power generation control strategy library and use it as the photovoltaic power generation control strategy for the day, and send it to the photovoltaic module; wherein the second target preset photovoltaic power generation control strategy is used to control the photovoltaic module to generate electricity at the maximum photovoltaic power during the valley period of the day and the peak period of the day and to supply the electric energy generated by photovoltaic power generation to multiple AC power users, or to supply electricity to a DC distribution module to power multiple DC power users.

[0079] In this embodiment, when it is determined that the predicted photovoltaic power generation during the trough period of the day is greater than the predicted electricity consumption during the trough period of the day, and the predicted photovoltaic power generation during the peak period of the day is less than the predicted electricity consumption during the peak period of the day, it means that the photovoltaic module generates a large amount of electricity based on photovoltaic module power generation during the trough period of the day (such as one of the time periods from 11:00 to 13:00 when the weather is clear and the sunshine intensity is strong). Considering that the cost of connecting various electrical equipment in the smart building to the mains electricity is relatively low during the trough period of the day, the first target preset photovoltaic power generation control strategy can be obtained from the photovoltaic power generation control strategy library including multiple photovoltaic power generation control strategies and used as the photovoltaic power generation control strategy for the day. The photovoltaic power generation control strategy preset by the first target enables the photovoltaic module to generate electricity at the maximum photovoltaic power during the trough period of the day and store the electricity generated by photovoltaic power generation in the energy storage module (also to facilitate the discharge of the energy storage module to supply power to various electrical equipment in the smart building during the peak period of the day, where DC electrical equipment has a higher priority than AC electrical equipment in the energy storage module), and also enables the photovoltaic module to generate electricity at the maximum photovoltaic power during the peak period of the day and supply the electricity generated by photovoltaic power generation to multiple AC electrical equipment, or to the DC distribution module to supply power to multiple DC electrical equipment. At the same time, the energy storage module is the second priority for power supply during the peak period of the day, and then when the photovoltaic module and the energy storage module are not sufficient to complete the power supply work, the rest is connected to the mains as a supplement.

[0080] When it is determined that the photovoltaic power generation predicted in the valley time period of the day is less than the power consumption predicted in the valley time period of the day, and the photovoltaic power generation predicted in the peak time period of the day is less than the power consumption predicted in the peak time period of the day, it means that the photovoltaic module generates electricity based on the photovoltaic module during the valley time period of the day. Considering that the cost of connecting the various electrical equipment in the smart building to the mains during the valley time period of the day is low, and the cost of directly using the mains to charge the energy storage module is also low, the second target preset photovoltaic power generation control strategy can be obtained from the photovoltaic power generation control strategy library including multiple photovoltaic power generation control strategies and used as the photovoltaic power generation control strategy of the day. The second target preset photovoltaic power generation control strategy enables the photovoltaic module to generate electricity at the maximum photovoltaic power generation power during the valley time period of the day and the peak time period of the day, and the electricity generated by the photovoltaic power generation is supplied to multiple AC power equipment for use, or supplied to the DC distribution module for multiple DC power equipment. At the same time, the energy storage module is the second priority for power supply during the peak time period of the day. When the photovoltaic module and the energy storage module are not enough to complete the power supply work, the remaining access to the mains is supplemented.

[0081] S170: The photovoltaic module performs photovoltaic power generation based on the photovoltaic power generation control strategy for the day, and transmits the photovoltaic power generation electric energy to the energy storage module and / or multiple AC power consumption devices.

[0082] In this embodiment, when the photovoltaic module receives the photovoltaic power generation control strategy for the day, it specifically executes the photovoltaic power generation control strategy for the day to perform photovoltaic power generation, and transmits the photovoltaic power generation electric energy to the energy storage module and / or multiple AC power-consuming equipment. Of course, the photovoltaic power generation electric energy can also be transmitted to the DC distribution module so that it can convert the AC power generated by the photovoltaic power generation into DC power through the DC distribution module and then supply power to the DC power-consuming equipment for use.

[0083] It can be seen that the implementation example of the method can determine the photovoltaic power generation forecast data based on the control module in combination with the weather forecast data of the day and the first forecast model, and determine the daily grid access forecast power consumption in combination with the daily average total power consumption of the target smart building and the current power parameters of the energy storage module. After inputting it into the second forecast model, a time-segmented photovoltaic power generation forecast data sequence for determining the photovoltaic power generation strategy can be obtained, and the photovoltaic power generation process of the smart building is more intelligently controlled by the photovoltaic storage direct-flexible technology.

[0084] Figure 1 Schematic diagram of a building energy intelligent control system based on photovoltaic storage and direct flexible control provided by an embodiment of the present invention. Figure 1 As shown, corresponding to the above-mentioned intelligent control method for building energy based on photovoltaic storage and direct and flexible, the present invention also provides an intelligent control system for building energy based on photovoltaic storage and direct and flexible, which is applied to smart buildings, in which a control module 10, a photovoltaic module 20, an energy storage module 30, a DC distribution module 40, a plurality of DC power devices 50 and a plurality of AC power devices 60 are provided, the photovoltaic module 20 is connected to the energy storage module 30, the energy storage module 30 is connected to the plurality of DC power devices 50 through the DC distribution module 40, the energy storage module 30 is also connected to a plurality of AC power devices compatible with AC and DC among the plurality of AC power devices 60 through the DC distribution module 40, and the control module 10 is all connected in communication with the photovoltaic module 20, the energy storage module 30 and the DC distribution module 40. In specific implementation, the photovoltaic module 20 is also connected to the DC distribution module 40.

[0085] The control module 10 is used to respond to the energy intelligent control instruction, obtain the target smart building corresponding to the energy intelligent control instruction, and determine the building type corresponding to the target smart building;

[0086] The control module 10 is further used to determine the photovoltaic power generation prediction data corresponding to the weather forecast data of the day based on the weather forecast data of the day and the first prediction model trained in advance; wherein the first prediction model is obtained by training the first prediction model to be trained using the historical weather forecast-photovoltaic power generation data set as a training set;

[0087] The control module 10 is further used to obtain the daily average total power consumption of the target smart building and the current power parameters of the energy storage module, and determine the predicted power consumption of the grid access on the day based on the daily average total power consumption, the current power parameters and the photovoltaic power generation prediction data; wherein the current power parameters of the energy storage module at least include the current remaining power, the maximum storage power and the average charging power;

[0088] The control module 10 is further used to obtain a time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data of the day based on the photovoltaic power generation prediction data and a pre-trained second prediction model;

[0089] The control module 10 is further used to obtain the target historical date grid access forecast power consumption data from the historical date grid access forecast power consumption data set based on the current day grid access forecast power consumption and preset screening conditions, and obtain the current day peak time period forecast power consumption and the current day trough time period forecast power consumption corresponding to the current day grid access forecast power consumption from the target historical date grid access forecast power consumption data; wherein each historical date grid access forecast power consumption data in the historical date grid access forecast power consumption data set includes at least the historical date, the actual grid access power consumption on the historical date, the actual power consumption on the peak time period on the historical date, and the actual power consumption on the trough time period on the historical date;

[0090] The control module 10 is further used to determine the photovoltaic power generation control strategy for the day based on the time segment photovoltaic power generation prediction data sequence, the power generation working parameters of the photovoltaic module, the predicted power consumption during the peak time period of the day and the predicted power consumption during the trough time period of the day, and send it to the photovoltaic module;

[0091] The photovoltaic module 20 is used to perform photovoltaic power generation based on the photovoltaic power generation control strategy of the day, and transmit the photovoltaic power generation electric energy to the energy storage module and / or multiple AC power consumption equipment.

[0092] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned building energy intelligent control system based on photovoltaic storage and direct flexible and each module or device can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0093] It can be seen that the implementation example of the device can determine the photovoltaic power generation forecast data based on the control module in combination with the weather forecast data of the day and the first forecast model, and determine the grid access forecast power consumption of the day in combination with the daily average total power consumption of the target smart building and the current power parameters of the energy storage module. After inputting it into the second forecast model, a time-segmented photovoltaic power generation forecast data sequence for determining the photovoltaic power generation strategy can be obtained, and the photovoltaic power generation process of the smart building is more intelligently controlled by the photovoltaic storage direct-flexible technology.

[0094] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0095] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0096] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0097] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A building energy intelligent control method based on solar storage and direct flexible, applied to smart buildings, characterized in that: The smart building is provided with a control module, a photovoltaic module, an energy storage module, a DC distribution module, a plurality of DC power devices and a plurality of AC power devices. The photovoltaic module is connected to the energy storage module, and the energy storage module is connected to the plurality of DC power devices through the DC distribution module. The energy storage module is also connected to a number of AC power devices compatible with AC and DC among the plurality of AC power devices through the DC distribution module. The control module is communicatively connected to the photovoltaic module, the energy storage module and the DC distribution module. The intelligent building energy control method based on photovoltaic storage and direct current flexibility includes: The control module responds to the energy intelligent control instruction, obtains a target smart building corresponding to the energy intelligent control instruction, and determines a building type corresponding to the target smart building; The control module determines photovoltaic power generation prediction data corresponding to the weather forecast data of the day based on the weather forecast data of the day and the pre-trained first prediction model; wherein the first prediction model is obtained by training the first prediction model to be trained using the historical weather forecast-photovoltaic power generation data set as a training set; The control module obtains the daily average total power consumption of the target smart building and the current power parameters of the energy storage module, and determines the predicted power consumption for grid access on that day based on the daily average total power consumption, the current power parameters and the photovoltaic power generation prediction data; wherein the current power parameters of the energy storage module include at least the current remaining power, the maximum storage power and the average charging power; The control module acquires a time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data based on the photovoltaic power generation prediction data and a pre-trained second prediction model; The control module obtains the target historical date grid access forecast power consumption data from the historical date grid access forecast power consumption data set based on the current day grid access forecast power consumption and the preset screening conditions, and obtains the current day peak time period forecast power consumption and the current day trough time period forecast power consumption corresponding to the current day grid access forecast power consumption from the target historical date grid access forecast power consumption data; wherein each historical date grid access forecast power consumption data in the historical date grid access forecast power consumption data set includes at least the historical date, the actual grid access power consumption on the historical date, the actual power consumption on the peak time period on the historical date, and the actual power consumption on the trough time period on the historical date; The control module determines the photovoltaic power generation control strategy for the day based on the time-segmented photovoltaic power generation prediction data sequence, the power generation working parameters of the photovoltaic module, the predicted power consumption in the peak time period of the day, and the predicted power consumption in the valley time period of the day, and sends it to the photovoltaic module; wherein the photovoltaic power generation prediction data belonging to the peak time period of the day in the time-segmented photovoltaic power generation prediction data sequence are summed to obtain the predicted photovoltaic power generation in the peak time period of the day; the photovoltaic power generation prediction data belonging to the valley time period of the day in the time-segmented photovoltaic power generation prediction data sequence are summed to obtain the predicted photovoltaic power generation in the valley time period of the day; The photovoltaic module performs photovoltaic power generation based on the photovoltaic power generation control strategy for the day, and transmits the photovoltaic power generation electric energy to the energy storage module and / or multiple AC power consumption equipment.

2. The method according to claim 1, characterized in that The step of determining photovoltaic power generation prediction data corresponding to the weather forecast data for the day based on the weather forecast data for the day and the pre-trained first prediction model includes: Obtaining the equivalent peak sunshine hours corresponding to the light intensity data in the weather forecast data for the day; The equivalent peak sunshine hours are input into the first prediction model to obtain the photovoltaic power generation prediction data.

3. The method according to claim 2, characterized in that After the step of inputting the equivalent peak sunshine hours into the first prediction model to obtain the photovoltaic power generation prediction data, the method further includes: Based on the preset photovoltaic power generation prediction strategy, the maximum illuminated area of ​​the photovoltaic module, the conversion efficiency of the photovoltaic module, the transmission line loss rate of the smart building and the equivalent peak sunshine hours, determine the photovoltaic power generation theoretical prediction data corresponding to the weather forecast data of the day; Based on a preset weighted summation strategy, the photovoltaic power generation prediction data and the photovoltaic power generation theoretical prediction data, current photovoltaic power generation adjustment prediction data is determined, and the photovoltaic power generation prediction data is updated with the current photovoltaic power generation adjustment prediction data.

4. The method according to claim 1, characterized in that: The step of obtaining a time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data based on the photovoltaic power generation prediction data and a pre-trained second prediction model includes: Obtaining, from the historical weather forecast data set, target historical weather forecast data that has the maximum similarity value with the area to which the target smart building belongs, the weather forecast data of the day and the month to which it belongs, and a target historical date corresponding to the target historical weather forecast data; Acquire multiple candidate historical dates whose date days interval with the target historical date does not exceed a preset day interval threshold, and form a candidate historical date set with the target historical date; Acquire historical time segment photovoltaic power generation prediction data sequences corresponding to multiple historical dates in the candidate historical date set from the locally stored historical time segment photovoltaic power generation prediction data sequence set, and form multiple input photovoltaic power generation prediction data sequences in chronological order; The multiple input photovoltaic power generation prediction data sequences are input into the second prediction model to obtain time segment photovoltaic power generation prediction data sequences corresponding to the photovoltaic power generation prediction data.

5. The method according to claim 1, characterized in that The method of acquiring the target historical date power grid access forecast power consumption data from the historical date power grid access forecast power consumption data set based on the current day power grid access forecast power consumption and the preset screening conditions, and acquiring the current day peak time period forecast power consumption and the current day trough time period forecast power consumption corresponding to the current day power grid access forecast power consumption from the target historical date power grid access forecast power consumption data, includes: Obtaining the target historical date power grid access predicted power consumption data that has the maximum similarity value with the building type of the target smart building, the predicted power grid access power consumption on the day, and the corresponding month from the historical date power grid access predicted power consumption data set; Obtain the actual electricity consumption during the peak time period of the target historical date and the actual electricity consumption during the trough time period of the target historical date corresponding to the predicted electricity consumption data for grid access on the target historical date, and use the actual electricity consumption during the peak time period of the target historical date as the predicted electricity consumption during the peak time period of the day, and use the actual electricity consumption during the trough time period of the historical date.

6. The method according to claim 1, characterized in that The photovoltaic power generation control strategy for the day is determined based on the time segment photovoltaic power generation prediction data sequence, the power generation working parameters of the photovoltaic module, the predicted power consumption during the peak time period of the day, and the predicted power consumption during the trough time period of the day, and is sent to the photovoltaic module, including: If it is determined that the photovoltaic power generation predicted during the trough period of the day is greater than the power consumption predicted during the trough period of the day, and the photovoltaic power generation predicted during the peak period of the day is less than the power consumption predicted during the peak period of the day, then the first target preset photovoltaic power generation control strategy is obtained from the preset photovoltaic power generation control strategy library and used as the photovoltaic power generation control strategy for the day, and sent to the photovoltaic module; wherein the first target preset photovoltaic power generation control strategy is used to control the photovoltaic module to generate electricity at the maximum photovoltaic power generation power during the trough period of the day and store the electric energy generated by the photovoltaic power generation in the energy storage module, and is used to control the photovoltaic module to generate electricity at the maximum photovoltaic power generation power during the peak period of the day and supply the electric energy generated by the photovoltaic power generation to multiple AC power users, or to supply power to a DC distribution module to supply power to multiple DC power users; If it is determined that the predicted photovoltaic power generation during the trough period of the day is less than the predicted power consumption during the trough period of the day, and the predicted photovoltaic power generation during the peak period of the day is less than the predicted power consumption during the peak period of the day, then the second target preset photovoltaic power generation control strategy is obtained from the photovoltaic power generation control strategy library and used as the photovoltaic power generation control strategy for the day, and sent to the photovoltaic module; wherein the second target preset photovoltaic power generation control strategy is used to control the photovoltaic module to generate electricity at the maximum photovoltaic power generation power during the trough period of the day and the peak period of the day and to supply the electric energy generated by photovoltaic power generation to multiple AC power users, or to supply power to a DC distribution module to power multiple DC power users.

7. An intelligent building energy control system based on solar storage and direct flexible, applied to smart buildings, characterized in that: The smart building is provided with a control module, a photovoltaic module, an energy storage module, a DC distribution module, a plurality of DC power devices and a plurality of AC power devices. The photovoltaic module is connected to the energy storage module, and the energy storage module is connected to the plurality of DC power devices through the DC distribution module. The energy storage module is also connected to a plurality of AC power devices compatible with AC and DC among the plurality of AC power devices through the DC distribution module. The control module is communicatively connected to the photovoltaic module, the energy storage module and the DC distribution module. The control module is used to respond to the energy intelligent control instruction, obtain the target smart building corresponding to the energy intelligent control instruction, and determine the building type corresponding to the target smart building; The control module is further used to determine the photovoltaic power generation prediction data corresponding to the weather forecast data of the day based on the weather forecast data of the day and the pre-trained first prediction model; wherein the first prediction model is obtained by training the first prediction model to be trained using the historical weather forecast-photovoltaic power generation data set as a training set; The control module is further used to obtain the daily average total power consumption of the target smart building and the current power parameters of the energy storage module, and determine the predicted power consumption for grid access on the day based on the daily average total power consumption, the current power parameters and the photovoltaic power generation prediction data; wherein the current power parameters of the energy storage module include at least the current remaining power, the maximum storage power and the average charging power; The control module acquires a time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data based on the photovoltaic power generation prediction data and a pre-trained second prediction model; The control module is further used to obtain the target historical date power grid access forecast power consumption data from the historical date power grid access forecast power consumption data set based on the current day power grid access forecast power consumption and preset screening conditions, and obtain the current day peak time period forecast power consumption and the current day trough time period forecast power consumption corresponding to the current day power grid access forecast power consumption from the target historical date power grid access forecast power consumption data; wherein each historical date power grid access forecast power consumption data in the historical date power grid access forecast power consumption data set includes at least the historical date, the actual power grid access power consumption of the historical date, the actual power consumption of the peak time period of the historical date, and the actual power consumption of the trough time period of the historical date; The control module is further used to determine the photovoltaic power generation control strategy for the day based on the time-segmented photovoltaic power generation prediction data sequence, the power generation working parameters of the photovoltaic module, the predicted power consumption in the peak time period of the day and the predicted power consumption in the valley time period of the day, and send it to the photovoltaic module; wherein the photovoltaic power generation prediction data belonging to the peak time period of the day in the time-segmented photovoltaic power generation prediction data sequence are summed to obtain the predicted photovoltaic power generation in the peak time period of the day; the photovoltaic power generation prediction data belonging to the valley time period of the day in the time-segmented photovoltaic power generation prediction data sequence are summed to obtain the predicted photovoltaic power generation in the valley time period of the day; The photovoltaic module is used to perform photovoltaic power generation based on the photovoltaic power generation control strategy for the day, and transmit the photovoltaic power generation electric energy to the energy storage module and / or multiple AC power consumption equipment.

8. The building energy intelligent control system based on solar energy storage and direct flexible according to claim 7 is characterized in that: The step of determining photovoltaic power generation prediction data corresponding to the weather forecast data for the day based on the weather forecast data for the day and the pre-trained first prediction model includes: Obtaining the equivalent peak sunshine hours corresponding to the light intensity data in the weather forecast data for the day; The equivalent peak sunshine hours are input into the first prediction model to obtain the photovoltaic power generation prediction data.

9. The building energy intelligent control system based on solar energy storage and direct flexible according to claim 7 is characterized in that: The step of obtaining a time segment photovoltaic power generation prediction data sequence corresponding to the photovoltaic power generation prediction data based on the photovoltaic power generation prediction data and a pre-trained second prediction model includes: Obtaining, from the historical weather forecast data set, target historical weather forecast data that has the maximum similarity value with the area to which the target smart building belongs, the weather forecast data of the day and the month to which it belongs, and a target historical date corresponding to the target historical weather forecast data; Acquire multiple candidate historical dates whose date days interval with the target historical date does not exceed a preset day interval threshold, and form a candidate historical date set with the target historical date; Acquire historical time segment photovoltaic power generation prediction data sequences corresponding to multiple historical dates in the candidate historical date set from the locally stored historical time segment photovoltaic power generation prediction data sequence set, and form multiple input photovoltaic power generation prediction data sequences in chronological order; The multiple input photovoltaic power generation prediction data sequences are input into the second prediction model to obtain time segment photovoltaic power generation prediction data sequences corresponding to the photovoltaic power generation prediction data.

10. The building energy intelligent control system based on photovoltaic storage and direct flexible according to claim 7 is characterized in that: The method of acquiring the target historical date power grid access forecast power consumption data from the historical date power grid access forecast power consumption data set based on the current day power grid access forecast power consumption and the preset screening conditions, and acquiring the current day peak time period forecast power consumption and the current day trough time period forecast power consumption corresponding to the current day power grid access forecast power consumption from the target historical date power grid access forecast power consumption data, includes: Obtaining the target historical date power grid access predicted power consumption data that has the maximum similarity value with the building type of the target smart building, the predicted power grid access power consumption on the day, and the corresponding month from the historical date power grid access predicted power consumption data set; Obtain the actual electricity consumption during the peak time period of the target historical date and the actual electricity consumption during the trough time period of the target historical date corresponding to the predicted electricity consumption data for grid access on the target historical date, and use the actual electricity consumption during the peak time period of the target historical date as the predicted electricity consumption during the peak time period of the day, and use the actual electricity consumption during the trough time period of the historical date.

Images