Construction method and device of photovoltaic power prediction data set, equipment and medium

Abstract

The invention discloses a photovoltaic power prediction data set construction method and device, equipment and a medium, and relates to the technical field of new energy, and the method comprises the steps: obtaining historical meteorological data, historical power data and historical satellite data of a target photovoltaic station as an original data set; dividing the original data set according to a preset extreme temperature division rule to obtain an original extreme temperature event data set; matching meteorological satellite observation data of the target photovoltaic station in the historical satellite data based on the first position information of the target photovoltaic station and the time information corresponding to each extreme temperature event contained in the extreme temperature event data set; training a satellite power forecasting model based on the satellite remote sensing surface temperature data value, the satellite remote sensing surface irradiance data value and the historical power data; the extreme temperature event data set is expanded based on the historical satellite data and the satellite power prediction model, the target photovoltaic power prediction data set is obtained, and the sample data availability under the extreme temperature condition is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy, and particularly to a method, device, equipment and medium for constructing a photovoltaic power prediction data set. Background Art

[0002] New energy power generation systems are extremely sensitive to extreme weather, which may lead to large-scale equipment outages and significant reductions in power generation. In extreme cases, it may even pose a threat to the safe and stable operation of the power grid. Extreme weather generally refers to those disastrous weather conditions where meteorological elements deviate significantly from normal levels and cause serious consequences. From the perspective of photovoltaic power generation, any meteorological factors that cause fluctuations in photovoltaic power generation, such as irradiance, temperature, etc., and weather phenomena that change violently in a short period of time can be defined as extreme weather. With the intensification of global warming and the increasing frequency of extreme weather, as well as the continuous improvement of the photovoltaic power generation penetration rate, the impact of extreme weather on power grid operation has become increasingly significant. Therefore, accurately predicting and warning the photovoltaic output under complex extreme weather and enhancing the resilience of the power system are the key research directions in the future.

[0003] However, current mainstream power prediction technologies mainly rely on statistical models such as machine learning and deep learning that require a large amount of data. Since extreme weather is a small-probability event and the sample data is scarce, the new energy power prediction model based on small samples of complex extreme weather is prone to overfitting during training, seriously affecting the accuracy and reliability of power prediction. On the other hand, under complex extreme weather conditions, the drastic dynamic changes in meteorological element data greatly increase the difficulty of data processing and sample extraction; at the same time, the causes of the drastic changes in photovoltaic power generation under abnormal weather are complex, and it is difficult to effectively capture the internal connection between meteorological fluctuations and power fluctuations, resulting in great difficulty in accurately predicting the photovoltaic power generation under complex extreme weather.

[0004] Therefore, how to construct an accurate photovoltaic power prediction data set for extreme weather, which is a small-probability event, has become an urgent problem to be solved. Summary of the Invention

[0005] The present invention provides the following technical solution: A method for constructing a photovoltaic power prediction data set, which includes the following steps,

[0006] Obtain the historical data of the target photovoltaic power station as the original data set;

[0007] Divide the original data set according to a preset extreme temperature division rule to obtain an original extreme temperature event data set;

[0008] Match the meteorological satellite observation data of the target photovoltaic power station in the historical satellite data based on the first position information of the target photovoltaic power station and the time information corresponding to each extreme temperature event included in the extreme temperature event data set;

[0009] Train a satellite power prediction model based on meteorological satellite observation data and the original dataset;

[0010] Augment the extreme temperature event dataset based on the original dataset and the satellite power prediction model to obtain the target photovoltaic power prediction dataset.

[0011] As a preferred embodiment of the method for constructing the photovoltaic power prediction dataset according to the present invention, wherein: the augmenting the extreme temperature event dataset based on the original dataset and the satellite power prediction model to obtain the target photovoltaic power prediction dataset includes,

[0012] Match the historical satellite data based on the spatio-temporal characteristics or meteorological characteristics of the target photovoltaic power station to obtain the matched satellite data;

[0013] Input the matched satellite data into the pre-trained satellite power prediction model to obtain power prediction data;

[0014] Divide the matched satellite data and the power prediction data according to the preset extreme temperature division rule to obtain the augmented extreme temperature event dataset;

[0015] Merge the augmented extreme temperature event dataset and the extreme temperature event dataset to obtain the target photovoltaic power prediction dataset;

[0016] The historical data includes historical meteorological data, historical power data, and historical satellite data;

[0017] The meteorological satellite observation data includes satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data.

[0018] As a preferred embodiment of the method for constructing the photovoltaic power prediction dataset according to the present invention, wherein: the matching the historical satellite data based on the spatio-temporal characteristics of the target photovoltaic power station includes:

[0019] Within a preset area, obtain the second position information of at least one target position whose position matching degree with the first position information is greater than the preset degree;

[0020] Match the historical satellite data based on the second position information and the time information to obtain the matched satellite data.

[0021] As a preferred embodiment of the method for constructing the photovoltaic power prediction dataset according to the present invention, wherein: the obtaining, within a preset area, the second position information of at least one target position whose position matching degree with the first position information is greater than the preset degree includes:

[0022] Within a preset area, obtain a first sub-target position whose straight-line distance from the target photovoltaic power station is less than a preset distance as the second position information.

[0023] As a preferred solution of the method for constructing a photovoltaic power prediction data set according to the present invention, wherein: the obtaining, within a preset area, of second position information of at least one target position whose position matching degree with the first position information is greater than a preset degree further includes:

[0024] Within a preset area, obtain a second sub-target position of other photovoltaic power stations as the second position information.

[0025] As a preferred solution of the method for constructing a photovoltaic power prediction data set according to the present invention, wherein: the matching of historical satellite data based on the meteorological characteristics of the target photovoltaic power station includes:

[0026] Perform similarity matching on historical satellite data based on meteorological satellite observation data to obtain a matching result;

[0027] Based on the matching result, select target satellite data with a matching degree greater than a preset degree from the historical satellite data as matching satellite data.

[0028] As a preferred solution of the method for constructing a photovoltaic power prediction data set according to the present invention, wherein: the preset extreme temperature division rule includes a preset extreme high temperature division rule and a preset extreme low temperature division rule, and the historical meteorological data includes historical ambient temperature and historical photovoltaic module temperature;

[0029] Divide the original data set according to the preset extreme temperature division rule to obtain an original extreme temperature event data set, including:

[0030] Extract first sub-historical meteorological data with the historical ambient temperature greater than a first preset temperature, the historical photovoltaic module temperature greater than a second preset temperature, and a continuous duration greater than a first preset duration, and first sub-historical power data corresponding to the time series of the first sub-historical meteorological data as an original extreme high temperature event;

[0031] The first preset temperature is less than the second preset temperature;

[0032] Extract second sub-historical meteorological data with the historical ambient temperature less than a third preset temperature and a continuous duration greater than a second preset duration, and second sub-historical power data corresponding to the time series of the second sub-historical meteorological data as an original extreme low temperature event;

[0033] The second preset duration is greater than the first preset duration;

[0034] Merge the original extreme high temperature events and the original extreme low temperature events to obtain the original extreme temperature event data set.

[0035] To solve the above technical problems, the present invention provides the following technical solutions: a method and device for constructing a photovoltaic power prediction data set, including: an acquisition module, configured to acquire historical meteorological data, historical power data, and historical satellite data of a target photovoltaic power station as an original data set;

[0036] a division module, configured to divide the original data set according to a preset extreme temperature division rule to obtain an original extreme temperature event data set;

[0037] a matching module, configured to match meteorological satellite observation data of the target photovoltaic power station in the historical satellite data based on the first position information of the target photovoltaic power station and the time information corresponding to each extreme temperature event included in the extreme temperature event data set; wherein, the meteorological satellite observation data includes satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data;

[0038] a power prediction module, configured to train a satellite power prediction model based on the satellite remote sensing surface temperature data value, the satellite remote sensing surface irradiance data value, and the historical power data;

[0039] an expansion module, configured to expand the extreme temperature event data set based on the historical satellite data and the satellite power prediction model to obtain a target photovoltaic power prediction data set.

[0040] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for constructing a photovoltaic power prediction data set are implemented.

[0041] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for constructing a photovoltaic power prediction data set are implemented.

[0042] The beneficial effects of the present invention: By constructing a coupling relationship model between meteorological satellite data and historical power data, the present invention generates a series of virtual power data of other regions in the same period, which together with the satellite remote sensing surface temperature data and surface irradiance data form a constructed virtual data set, thereby achieving the purpose of expanding small samples and improving the availability of sample data under extreme temperature conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 This is the overall flowchart of the construction method of the photovoltaic power prediction data set provided by the first embodiment of the present invention.

[0045] Figure 2 This is the structural block diagram of the construction device of the photovoltaic power prediction data set provided by the second embodiment of the present invention.

[0046] Figure 3 This is the schematic diagram of the hardware structure of the computer device in the construction method of the photovoltaic power prediction data set provided by the second embodiment of the present invention. Detailed implementation manners

[0047] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the detailed implementation manners of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] Embodiment 1, referring to Figure 1 One embodiment of the present invention provides a method for constructing a photovoltaic power prediction data set, including:

[0049] Step S101, obtaining historical data of the target photovoltaic power station as the original data set.

[0050] The historical data includes historical meteorological data, historical power data, and historical satellite data.

[0051] In this embodiment, the historical meteorological data and historical power data of the target photovoltaic power station can be obtained by acquiring the recorded data of the target photovoltaic power station.

[0052] Exemplarily, the historical meteorological data can be obtained by acquiring historical numerical weather forecast data.

[0053] Exemplarily, the historical meteorological data can be obtained by acquiring the meteorological data acquisition device set in the target photovoltaic power station.

[0054] Exemplarily, the historical meteorological data may include historical forecast irradiance data and historical photovoltaic module temperature data; the historical irradiance forecast data is obtained through historical numerical weather forecasts, and the historical photovoltaic module temperature data is obtained through the meteorological data acquisition device.

[0055] Exemplarily, the historical satellite data can be collected by the target remote sensing satellite; the historical satellite data includes at least the remote sensing surface temperature data value and the satellite remote sensing surface irradiance data.

[0056] Exemplarily, after obtaining historical meteorological data and historical power data, preliminary cleaning and reconstruction are performed on the outliers in the historical data; specifically, for the meteorological data and historical power data in the original dataset, the abnormal data where the meteorological data is equal to zero and the photovoltaic power generation is not equal to zero is deleted.

[0057] Step S102: Divide the original dataset according to a preset extreme temperature division rule to obtain an original extreme temperature event dataset.

[0058] For a photovoltaic power station, common extreme weather events usually include extreme high temperature events and extreme low temperature events; under extreme high temperature conditions, the temperature of the photovoltaic modules will increase significantly, resulting in a decrease in the photoelectric conversion efficiency due to the "temperature effect"; while under extreme low temperature conditions, the physical properties of the photovoltaic modules and the operating states of electronic components are affected. Therefore, the preset extreme temperature division rule may include an extreme high temperature event division rule and an extreme low temperature event division rule.

[0059] In one embodiment, considering the ambient temperature where the photovoltaic modules are located, extreme high temperature events and extreme low temperature events are divided. The historical data corresponding to the timestamps where the ambient temperature is greater than a preset temperature value and the duration is greater than a first preset duration is used as extreme high temperature events.

[0060] Specifically, the first sub-historical meteorological data where the historical ambient temperature is greater than the first preset temperature and the duration is greater than the first preset duration, and the first sub-historical power data corresponding to the time sequence of the first sub-historical meteorological data are extracted as the original extreme high temperature events; where the first preset temperature is less than the second preset temperature.

[0061] The second sub-historical meteorological data where the historical ambient temperature is less than a third preset temperature and the duration is greater than a second preset duration, and the second sub-historical power data corresponding to the time sequence of the second sub-historical meteorological data are extracted as the original extreme low temperature events; where the second preset duration is greater than the first preset duration.

[0062] In one embodiment, only considering the temperature of the photovoltaic modules to divide extreme high temperature events, the historical data corresponding to the timestamps where the temperature of the photovoltaic modules is greater than a preset temperature value and the duration is greater than a first preset duration is used as extreme high temperature events.

[0063] Specifically, the first sub-historical meteorological data where the historical ambient temperature is greater than the second preset temperature and the duration is greater than the first preset duration, and the first sub-historical power data corresponding to the time sequence of the first sub-historical meteorological data are extracted as the original extreme high temperature events; where the second preset temperature is greater than the first preset temperature.

[0064] In one embodiment, extreme high temperature events are classified by considering both the ambient temperature and the photovoltaic panel temperature of the photovoltaic module. Historical data corresponding to timestamps with the ambient temperature greater than a first preset temperature value, the photovoltaic panel temperature greater than a second preset temperature value, and the duration being greater than a first preset duration is used as extreme high temperature events.

[0065] Specifically, first sub-historical meteorological data with the historical ambient temperature greater than the first preset temperature, the historical photovoltaic module temperature greater than the second preset temperature, and the duration being greater than the first preset duration, and first sub-historical power data corresponding to the time series of the first sub-historical meteorological data are extracted as the original extreme high temperature events; where the first preset temperature is less than the second preset temperature.

[0066] After obtaining the original extreme temperature event dataset, since extreme weather is a small-probability event and sample data is scarce, it is easy for the new energy power prediction model based on small samples of complex extreme weather to overfit during training, seriously affecting the accuracy and reliability of power prediction. To solve this problem, in the present invention, the extreme event dataset is augmented with satellite data. Specifically, a satellite power prediction model is trained with historical power data and historical satellite data, so as to obtain predicted power data by predicting power with satellite data, and further augment the extreme temperature event dataset according to the predicted power data and satellite data.

[0067] Step S103, match the meteorological satellite observation data of the target photovoltaic power station in the historical satellite data based on the first position information of the target photovoltaic power station and the time information corresponding to each extreme temperature event included in the extreme temperature event dataset; where the meteorological satellite observation data includes satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data.

[0068] In this embodiment, first, the meteorological satellite observation data of the target photovoltaic power station is matched in the historical satellite data based on the first position information of the target photovoltaic power station and the time information corresponding to each extreme temperature event included in the extreme temperature event dataset; where the meteorological satellite observation data includes remote sensing surface temperature data values and satellite remote sensing surface irradiance data.

[0069] Among them, the first position information is the geographical longitude and latitude information of the target photovoltaic power station.

[0070] As a possible implementation, after obtaining the historical satellite data, preprocessing such as data cleaning, data standardization, and data interpolation is performed on the historical satellite data; where data cleaning aims to remove abnormal or missing values caused by sensor failures, cloud occlusion, or other environmental factors; data standardization aims to ensure that data from different sources and dimensions can be compared and analyzed in the same framework; data interpolation is used to fill data gaps caused by satellite observation intervals or orbital limitations.

[0071] Further, based on the preprocessed data, satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data are obtained according to the location information of the target photovoltaic power station and the time information of the extreme temperature time.

[0072] Step S104: Train a satellite power prediction model based on the satellite remote sensing surface temperature data value, the satellite remote sensing surface irradiance data value, and the historical power data.

[0073] Exemplarily, the satellite power prediction model is used to capture the relationship between the satellite remote sensing surface temperature data value, the satellite remote sensing surface irradiance data value, and the historical power data.

[0074] Specifically, during the model training process, the satellite remote sensing surface temperature data value and the satellite remote sensing surface irradiance data value are input into a pre-constructed preset power prediction model for model training, and the model parameters of the preset power prediction model are continuously adjusted until the model converges.

[0075] In this embodiment, the satellite power prediction model can be a Support Vector Machine (SVM) model.

[0076] Step S105: Expand the extreme temperature event data set based on the historical satellite data and the satellite power prediction model to obtain a target photovoltaic power prediction data set.

[0077] In the present invention, the extreme temperature event data set is expanded by the historical satellite data and the satellite power prediction model to solve the problem of inaccurate data set construction for extreme weather of small probability events in the related art.

[0078] In one embodiment, when expanding the extreme temperature event data set based on the historical satellite data and the satellite power prediction model, the historical satellite data can be first screened according to a preset temperature division rule to obtain extreme meteorological satellite data. Further, the extreme meteorological satellite data is input into the satellite power prediction model to obtain power prediction data. Finally, the extreme temperature event data set is expanded based on the extreme meteorological satellite data and the power prediction data to obtain a target photovoltaic power prediction data set.

[0079] In one embodiment, when augmenting the extreme temperature event dataset based on historical satellite data and the satellite power prediction model, the historical satellite data may be matched based on the spatio-temporal characteristics and / or meteorological characteristics of the target photovoltaic power station to obtain matched satellite data. Further, the matched satellite data is input into the satellite power prediction model to obtain power prediction data. Finally, the extreme temperature event dataset is augmented based on the matched meteorological satellite data and the power prediction data to obtain the target photovoltaic power prediction dataset.

[0080] For the above method of the present invention, historical meteorological data, historical power data, and historical satellite data of the target photovoltaic power station are obtained as the original dataset; the original dataset is divided according to a preset extreme temperature division rule to obtain the original extreme temperature event dataset; the meteorological satellite observation data of the target photovoltaic power station is matched in the historical satellite data based on the first position information of the target photovoltaic power station and the time information corresponding to each extreme temperature event included in the extreme temperature event dataset; wherein, the meteorological satellite observation data includes satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data; a satellite power prediction model is trained based on the satellite remote sensing surface temperature data value, the satellite remote sensing surface irradiance data value, and the historical power data; the extreme temperature event dataset is augmented based on the historical satellite data and the satellite power prediction model to obtain the target photovoltaic power prediction dataset; for the above method, by constructing a coupling relationship model between meteorological satellite data and historical power data, a series of virtual power data of other regions in the same period is generated, which together with the satellite remote sensing surface temperature data and surface irradiance data constitutes the constructed virtual dataset, thereby achieving the purpose of augmenting small samples and improving the availability of sample data under extreme temperature conditions.

[0081] As an exemplary embodiment, augmenting the extreme temperature event dataset based on the historical satellite data and the satellite power prediction model to obtain the target photovoltaic power prediction dataset includes: matching the historical satellite data based on the spatio-temporal characteristics and / or meteorological characteristics of the target photovoltaic power station to obtain matched satellite data; inputting the matched satellite data into the pre-trained satellite power prediction model to obtain power prediction data; dividing the matched satellite data and the power prediction data according to a preset extreme temperature division rule to obtain an augmented extreme temperature event dataset; and combining the augmented extreme temperature event dataset and the extreme temperature event dataset to obtain the target photovoltaic power prediction dataset.

[0082] In this embodiment, first, matching satellite data corresponding to locations or meteorology similar to the target photovoltaic power station is determined. Further, power prediction is performed based on the matching satellite data to obtain power forecast data. Finally, the extreme temperature event dataset is expanded based on the matching satellite data and the power forecast data to solve the problem in the related art that the dataset constructed for extreme weather of small-probability events is inaccurate.

[0083] In one embodiment, the historical satellite data can be matched separately according to the spatio-temporal characteristics of the target photovoltaic power station to obtain the matching satellite data. Specifically, a preset area can be determined first according to the longitude and latitude where the target photovoltaic power station is located. Using the satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data within the preset area, power forecast data representing the power output of other areas at the same time point except the target photovoltaic power station is generated. Further, it is jointly constructed with the satellite remote sensing surface temperature data and surface irradiance data to form a virtual dataset. And the virtual dataset is screened again using the preset extreme temperature division rule to remove data that does not belong to extreme high temperature and low temperature weather. Finally, it is merged with the initially screened original extreme temperature event dataset to form a target photovoltaic power prediction dataset under extreme temperature for photovoltaic power prediction under extreme temperature conditions. Among them, as a possible implementation, the preset area is not larger than the actual area corresponding to the historical satellite data.

[0084] In one embodiment, the historical satellite data can be matched separately according to the meteorological characteristics of the target photovoltaic power station. Specifically, clustering is performed on the historical satellite data based on the satellite remote sensing surface temperature data value and the satellite remote sensing surface irradiance data value of the target photovoltaic power station, and sub-historical satellite data similar to the target photovoltaic power station is selected. Further, power forecast data is generated using the sub-historical satellite data. Further, it is jointly constructed with the sub-historical satellite data to form a virtual dataset. And the virtual dataset is screened again using the preset extreme temperature division rule to remove data that does not belong to extreme high temperature and low temperature weather. Finally, it is merged with the initially screened original extreme temperature event dataset to form a target photovoltaic power prediction dataset under extreme temperature for photovoltaic power prediction under extreme temperature conditions.

[0085] Based on this, as an exemplary embodiment, the matching of the historical satellite data based on the meteorological characteristics of the target photovoltaic power station includes: performing similarity matching on the historical satellite data based on the meteorological satellite observation data to obtain a matching result; selecting target satellite data with a matching degree greater than a preset degree in the historical satellite data based on the matching result as the matching satellite data.

[0086] In one embodiment, when selecting target satellite data with a matching degree greater than a preset degree from the historical satellite data based on the matching result as the matching satellite data, historical satellite data with a similarity degree greater than a preset value can be used as the matching satellite data.

[0087] Among them, as a possible implementation, the preset value can take any value within [0.8, 0.95].

[0088] As an exemplary embodiment, the matching of the historical satellite data based on the spatio-temporal characteristics of the target photovoltaic power station includes: obtaining, within a preset area, second position information of at least one target position with a position matching degree greater than a preset degree with the first position information; and matching the historical satellite data based on the second position information and the time information to obtain the matching satellite data.

[0089] For the method where all satellite data within the above target area participate in dataset expansion, the target area may cover a relatively large spatial range, and it is necessary to further screen the historical satellite data based on the position information of the target photovoltaic power station.

[0090] Therefore, in this embodiment, the historical satellite data is matched through the second position information and the time information to obtain the matching satellite data.

[0091] Exemplarily, the position matching degree between the second position information and the first position information is greater than a preset degree.

[0092] In one embodiment, a first sub-target position with a straight-line distance less than a preset distance from the target photovoltaic power station can be used as the second position information to eliminate the problem that extreme temperature events vary with different latitudes and longitudes in a relatively large spatial range.

[0093] Based on this, as an exemplary embodiment, the obtaining, within a preset area, second position information of at least one target position with a position matching degree greater than a preset degree with the first position information includes: obtaining, within a preset area, a first sub-target position with a straight-line distance less than a preset distance from the target photovoltaic power station as the second position information.

[0094] In one embodiment, the positions of other photovoltaic power stations within the target area can be used as the second position information to eliminate the problem that extreme temperature events vary with different latitudes and longitudes in a relatively large spatial range.

[0095] Based on this, as an exemplary embodiment, obtaining, within a preset area, second location information of at least one target location whose location matching degree with the first location information is greater than a preset degree further includes: obtaining, within the preset area, second sub-target locations of other photovoltaic power stations as the second location information.

[0096] Embodiment 2 is an embodiment of the present invention, which provides an apparatus for constructing a photovoltaic power prediction data set, including: an acquisition module 501, configured to acquire historical meteorological data, historical power data, and historical satellite data of a target photovoltaic power station as an original data set;

[0097] a division module 502, configured to divide the original data set according to a preset extreme temperature division rule to obtain an original extreme temperature event data set;

[0098] a matching module 503, configured to match meteorological satellite observation data of the target photovoltaic power station in the historical satellite data based on the first location information of the target photovoltaic power station and time information corresponding to each extreme temperature event included in the extreme temperature event data set; wherein, the meteorological satellite observation data includes satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data;

[0099] a power prediction module 504, configured to train a satellite power prediction model based on the satellite remote sensing surface temperature data value, the satellite remote sensing surface irradiance data value, and the historical power data;

[0100] an expansion module 505, configured to expand the extreme temperature event data set based on the historical satellite data and the satellite power prediction model to obtain a target photovoltaic power prediction data set.

[0101] Embodiment 3, referring to Figure 3 is the third embodiment of the present invention, which is different from the previous two embodiments in that:

[0102] Figure 3 is a structural block diagram of an optional computer device according to an embodiment of the present application, as Figure 3 shown, including a processor 10, a communication interface 20, a memory 30, and a communication bus 40, wherein the processor 10, the communication interface 20, and the memory 30 complete mutual communication through the communication bus 40, and wherein,

[0103] the memory 30 is used to store a computer program;

[0104] when the processor 10 is configured to execute the computer program stored on the memory 30, it implements the method of any of the above embodiments.

[0105] Optionally, in this embodiment, the above communication bus may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 3 only a thick line is used to represent it in Figure 3 , but it does not mean that there is only one bus or one type of bus.

[0106] The communication interface is used for communication between the above computer device and other devices.

[0107] The memory may include RAM, and may also include non-volatile memory, for example, at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0108] The above processor may be a general-purpose processor, which may include but is not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it may also be a DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0109] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and will not be elaborated herein.

[0110] Those of ordinary skill in the art can understand that Figure 3 the structure shown is only schematic, and the device for implementing the method of any one of the above embodiments may be a terminal device, and the terminal device may be a smart phone (such as an Android phone, an IOS phone, etc.), a tablet computer, a palm computer, and a mobile Internet device (MID), a PAD, and other terminal devices. Figure 3 It does not limit the structure of the above electronic device. For example, the terminal device may further include more or fewer components (such as a network interface, a display device, etc.) than those shown in Figure 3 or have a different configuration from that shown in Figure 3 the figure.

[0111] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by a program instructing the relevant hardware of the terminal device, and the program can be stored in a computer-readable storage medium. The storage medium can include: a flash drive, ROM, RAM, a magnetic disk, or an optical disc, etc.

[0112] As an exemplary embodiment, the present application also provides a computer-readable storage medium, in which a computer program is stored. Among them, the computer program is set to execute the method steps of any one of the present embodiments when running.

[0113] Optionally, in the present embodiment, the above storage medium can be used for the program code for executing the method steps of the embodiments of the present application.

[0114] Optionally, in the present embodiment, the above storage medium can be located on at least one of the multiple network devices in the network shown in the above embodiments.

[0115] Optionally, in the present embodiment, the storage medium is set to store for executing the method in the above embodiments.

[0116] Optionally, the specific examples in the present embodiment can refer to the examples described in the above embodiments, and will not be elaborated herein.

[0117] Optionally, in the present embodiment, the above storage medium can include but is not limited to: various media such as a USB flash drive, ROM, RAM, a mobile hard disk, a magnetic disk, or an optical disc that can store program code.

[0118] The serial numbers of the above embodiments of the present application are only for description and do not represent the superiority or inferiority of the embodiments.

[0119] If the integrated unit in the above embodiments is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the above computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, 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 the storage medium and includes several instructions for causing one or more computer devices (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method in the above embodiments.

[0120] In several embodiments provided by the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may 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 coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in electrical or other forms.

[0121] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0122] In addition, in each embodiment of the present application, each functional unit 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 units can be implemented in the form of hardware or in the form of software functional units.

[0123] In the above embodiments of the present application, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] The above is only the preferred embodiment of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for constructing a photovoltaic power prediction data set, characterized in that Including: Obtaining historical data of the target photovoltaic power station as the original data set; Dividing the original data set according to a preset extreme temperature division rule to obtain an original extreme temperature event data set; Matching meteorological satellite observation data of the target photovoltaic power station in the historical data based on the first position information of the target photovoltaic power station and the time information corresponding to each extreme temperature event included in the extreme temperature event data set; Training a satellite power prediction model based on the meteorological satellite observation data and the original data set; Expanding the extreme temperature event data set based on the original data set and the satellite power prediction model to obtain a target photovoltaic power prediction data set.

2. The method for constructing a photovoltaic power prediction data set according to claim 1, wherein: The expanding the extreme temperature event data set based on the original data set and the satellite power prediction model to obtain a target photovoltaic power prediction data set includes: Matching historical satellite data based on the spatio-temporal characteristics or meteorological characteristics of the target photovoltaic power station to obtain matching satellite data; Inputting the matching satellite data into a pre-trained satellite power prediction model to obtain power prediction data; Dividing the matching satellite data and the power prediction data according to a preset extreme temperature division rule to obtain an expanded extreme temperature event data set; Combining the expanded extreme temperature event data set and the extreme temperature event data set to obtain the target photovoltaic power prediction data set; The historical data includes historical meteorological data, historical power data, and historical satellite data; The meteorological satellite observation data includes satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data.

3. The method for constructing a photovoltaic power prediction data set according to claim 2, wherein: The matching the historical satellite data based on the spatio-temporal characteristics or meteorological characteristics of the target photovoltaic power station includes: Matching the historical satellite data based on the spatio-temporal characteristics of the target photovoltaic power station includes obtaining, within a preset area, second position information of at least one target position whose position matching degree with the first position information is greater than a preset degree; Matching the historical satellite data based on the second position information and the time information to obtain the matching satellite data.

4. The method for constructing a photovoltaic power prediction data set according to claim 3, wherein: The obtaining, within a preset area, second position information of at least one target position whose position matching degree with the first position information is greater than a preset degree includes: Within a preset area, obtaining a first sub-target position whose straight-line distance from the target photovoltaic power station is less than a preset distance as the second position information.

5. The method for constructing a photovoltaic power prediction data set according to claim 4, characterized in that: The obtaining, within a preset area, second position information of at least one target position whose position matching degree with the first position information is greater than a preset degree further includes: Within a preset area, obtaining a second sub-target position of other photovoltaic power stations as the second position information.

6. The method for constructing a photovoltaic power prediction data set according to claim 5, wherein: The matching the historical satellite data based on the spatio-temporal characteristics or meteorological characteristics of the target photovoltaic power station further includes: Matching the historical satellite data based on the meteorological characteristics of the target photovoltaic power station includes performing similarity matching on the historical satellite data based on the meteorological satellite observation data to obtain a matching result; Selecting target satellite data whose matching degree is greater than a preset degree from the historical satellite data based on the matching result as the matching satellite data.

7. The method for constructing a photovoltaic power prediction data set according to claim 6, wherein: The preset extreme temperature division rules include a preset extreme high temperature division rule and a preset extreme low temperature division rule, and the historical meteorological data includes historical ambient temperature and historical photovoltaic module temperature; Dividing the original data set according to the preset extreme temperature division rules to obtain an original extreme temperature event data set, including: Extracting first sub-historical meteorological data with the historical ambient temperature greater than a first preset temperature, the historical photovoltaic module temperature greater than a second preset temperature, and the continuous duration greater than a first preset duration, and first sub-historical power data corresponding to the time series of the first sub-historical meteorological data as an original extreme high temperature event; The first preset temperature is less than the second preset temperature; Extracting second sub-historical meteorological data with the historical ambient temperature less than a third preset temperature and the continuous duration greater than a second preset duration, and second sub-historical power data corresponding to the time series of the second sub-historical meteorological data as an original extreme low temperature event; The second preset duration is greater than the first preset duration; Merging the original extreme high temperature events and the original extreme low temperature events to obtain the original extreme temperature event data set.

8. An apparatus using the method for constructing a photovoltaic power prediction data set according to any one of claims 1 to 7, characterized in that, Including: An acquisition module for acquiring historical meteorological data, historical power data, and historical satellite data of a target photovoltaic power station as an original data set; A division module for dividing the original data set according to the preset extreme temperature division rules to obtain an original extreme temperature event data set; A matching module for matching meteorological satellite observation data of the target photovoltaic power station in the historical satellite data based on the first position information of the target photovoltaic power station and the time information corresponding to each extreme temperature event included in the extreme temperature event data set; wherein, the meteorological satellite observation data includes satellite remote sensing surface temperature data and satellite remote sensing surface irradiance data; A power prediction module for training a satellite power prediction model based on the satellite remote sensing surface temperature data value, the satellite remote sensing surface irradiance data value, and the historical power data; An expansion module for expanding the extreme temperature event data set based on the historical satellite data and the satellite power prediction model to obtain a target photovoltaic power prediction data set.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method for constructing a photovoltaic power prediction data set according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method for constructing a photovoltaic power prediction data set according to any one of claims 1 to 7 are implemented.

Images