Distributed photovoltaic power generation prediction method and computing device

Abstract

The invention provides a distributed photovoltaic power generation prediction method and computing equipment, and is applied to the technical field of new energy prediction. The method comprises the following steps: acquiring basic data of a distributed power station, wherein the basic data comprises information of each transformer area in the distributed power station; predicting the power generation data through the selected power generation data prediction model, and summarizing prediction results to obtain a summarized prediction result; and splitting the summarized prediction result to obtain a prediction result of each transformer area. By using the method of the invention, through splitting and summarizing the prediction result to each transformer area, not only are the precision and reliability of distributed photovoltaic power station prediction improved, but also resource configuration can be reasonably optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy prediction, and in particular to a method and computing equipment for distributed photovoltaic power generation prediction. Background Art

[0002] In recent years, the installed capacity of distributed photovoltaic power generation has increased year by year. The installed capacity of distributed photovoltaic power generation in many provinces has reached the upper limit of regional power grid dispatching. In view of the small capacity of a single distributed photovoltaic power station and investment cost constraints, the prediction system and meteorological and modeling optimization solutions used in centralized photovoltaic power stations are not suitable for distributed photovoltaic power station prediction in terms of cost or basic data requirements.

[0003] In order to ensure that distributed photovoltaics are objective, measurable, adjustable and controllable, it is necessary to predict the power generation of distributed photovoltaics to guide the grid's dispatch of distributed photovoltaic power station power generation plans. Power station operation and maintenance manufacturers also need to understand future power generation capacity to manage power station power generation and maintenance plans.

[0004] Therefore, a method for distributed photovoltaic power generation prediction is needed, which can effectively realize the power prediction of distributed photovoltaic power stations and help grid dispatchers and power station operation and maintenance personnel to better manage and optimize the operation of distributed photovoltaic power stations. Summary of the invention

[0005] The present invention aims to provide a method and computing device for distributed photovoltaic power generation prediction, which can reasonably distribute the aggregated prediction results to each substation, thereby helping power grid dispatchers and power station operation and maintenance personnel to better manage and optimize the operation of distributed photovoltaic power stations.

[0006] According to one aspect of the present invention, a method for distributed photovoltaic power generation prediction is provided, comprising:

[0007] Obtain basic data of distributed power stations, including information of each substation in the distributed power station;

[0008] Predicting the power generation data through the selected power generation data prediction model, summarizing the prediction results, and obtaining a summary prediction result;

[0009] The aggregated prediction results are split to obtain prediction results for each station area.

[0010] According to some embodiments, the basic data of the distributed power station includes:

[0011] The latitude and longitude coordinates and rated capacity of each station area;

[0012] The operating data parameters of each substation include power generation or power generation.

[0013] According to some embodiments, the rationality of the splitting result is judged as follows:

[0014] The predicted result of each moment of the area allocation is not greater than the rated capacity of the area;

[0015] The prediction results allocated to each area at a certain prediction time are summed up, and the sum value is equal to the summary prediction result at the prediction time.

[0016] According to some embodiments, the power generation data is predicted by a selected power generation data prediction model, and the selected power generation data prediction model includes a single data source model:

[0017] The input of the single data source model includes the aggregated historical power generation data of distributed power stations;

[0018] The output of the single data source model includes a summary prediction result, and the summary prediction result is no greater than the summary power plant rated capacity.

[0019] According to some embodiments, the power generation data is predicted by a selected power generation data prediction model, and the selected power generation data prediction model includes a data inverse model:

[0020] The input of the data inverse model includes the aggregated historical power generation data of the distributed power stations, the aggregated rated capacity of the power stations and the historical numerical meteorological forecast values ​​of the power station area;

[0021] The output summary prediction target value of the data inversion model is reversely calculated, and the future summary power prediction value is reversed according to the historical data including the summary capacity and the power of electricity.

[0022] According to some embodiments, the power generation data is predicted by a selected power generation data prediction model, wherein the selected power generation data prediction model includes a non-numerical meteorological source model:

[0023] The input of the meteorological prediction model in the non-numerical meteorological source model is the historical meteorological station data collected by the power station;

[0024] The historical power data of the power plant and the historical weather station data of the power plant are used as modeling data of the power prediction model;

[0025] The input of the power prediction model includes future weather forecast data predicted based on historical weather station data of the power station;

[0026] The non-numerical meteorological source model is applied to the situation where only real-time ground meteorological station data is available and there is no external numerical meteorological forecast source.

[0027] According to some embodiments, the power generation data is predicted by a selected power generation data prediction model, and the selected power generation data prediction model includes a prediction model without power station information:

[0028] The input of the power station information-free prediction model is regional weather forecast data;

[0029] The summary theoretical prediction results are obtained through the theoretical prediction model;

[0030] The product of the rated capacity of the power station and the theoretical prediction of a single megawatt is obtained by converting the summarized theoretical prediction results.

[0031] According to some embodiments, splitting the aggregated prediction result includes:

[0032] Calculate the power generation efficiency and use the formula to calculate the power generation efficiency of each substation:

[0033] Pr=Q / (Cap*T)

[0034] Among them, Pr is the power generation efficiency, Q is the actual power generation, Cap is the rated capacity of each substation, and T is the peak sunshine hours.

[0035] According to some embodiments, splitting the aggregated prediction result further includes:

[0036] Calculate the splitting coefficient of each area, the calculation formula is:

[0037] Xn=0.5*(Cap n / sum(Cap n ))+0.5*(Pr n / sum(Pr n ))

[0038] Among them, Xn is the nth area split coefficient, Cap n is the rated capacity of the nth station area, Pr n is the power generation efficiency of the nth substation;

[0039] The prediction results of each substation are calculated using the split coefficient to form a prediction result set.

[0040] According to another aspect of the present invention, there is provided a computing device, comprising:

[0041] Processor; and

[0042] A memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform any of the aforementioned methods.

[0043] According to an example embodiment of the present invention, basic data of the distributed power station is obtained, the power generation data is predicted by a selected power generation data prediction model, the prediction results are summarized, and the most suitable prediction model is selected according to the characteristics of different substations in the distributed power station and the different historical data that can be obtained. This can significantly improve the accuracy of the prediction; the summarized prediction results are split, and the different conditions of each substation are combined during the splitting process to make the prediction results closer to the actual situation. The method of splitting the summarized prediction results into each substation not only improves the accuracy and reliability of the prediction, but also provides strong support for multiple aspects such as power station operation management and market transactions.

[0044] According to the example embodiments, based on the different characteristics of distributed power stations and the different historical data that can be obtained, multiple modeling methods are provided to choose from, including single data source model, data inversion model, non-numerical meteorological source model and non-power station information prediction model. By selecting different models in different situations, the model performance can be continuously evaluated and optimized, and the power generation of each substation can be predicted more accurately, thereby rationally allocating operation and maintenance resources.

[0045] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below.

[0047] Figure 1 A flow chart showing a method for distributed photovoltaic power generation prediction according to an example embodiment is shown.

[0048] Figure 2 A schematic block diagram of a single data source model for distributed photovoltaic power prediction according to an example embodiment is shown.

[0049] Figure 3 A schematic block diagram of a distributed photovoltaic power prediction data inversion model according to an example embodiment is shown.

[0050] Figure 4 A schematic block diagram of a numerical meteorological source-free model for distributed photovoltaic power prediction according to an example embodiment is shown.

[0051] Figure 5 A schematic block diagram of a power plant information-free prediction model for distributed photovoltaic power prediction according to an example embodiment is shown.

[0052] Figure 6 A block diagram of a computing device according to an example embodiment of the present invention is shown. DETAILED DESCRIPTION

[0053] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0054] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.

[0055] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0056] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0057] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the present inventive concept. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0058] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0059] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present invention, and therefore cannot be used to limit the protection scope of the present invention.

[0060] In order to adapt to distributed photovoltaic power stations, the present invention provides a method for distributed photovoltaic power generation prediction, which aggregates and predicts distributed photovoltaic power stations and reasonably splits the prediction results into single independent small-capacity power stations (hereinafter referred to as stations) in view of the small capacity of individual power stations, wide distribution of aggregated power stations, incomplete basic data collection of power stations, and scattered user demands for prediction results and prediction ranges.

[0061] Before describing the embodiments of the present application, some terms or concepts involved in the embodiments of the present application are explained.

[0062] STC (Standard Test Conditions) are standard test conditions used to evaluate the performance of photovoltaic modules. These conditions define a set of specific environmental parameters to compare the performance of different photovoltaic modules under the same conditions.

[0063] Exemplary embodiments of the present invention are described below with reference to the accompanying drawings.

[0064] Figure 1 A flow chart showing a method for distributed photovoltaic power generation prediction according to an example embodiment is shown.

[0065] According to an example embodiment, see Figure 1 , showing the method steps for distributed photovoltaic power generation prediction, through which the prediction accuracy can be improved and resource allocation can be optimized.

[0066] In S101, basic data of a distributed power station is obtained.

[0067] According to the example embodiment, the basic data of the distributed power station is obtained, and the basic data of the distributed power station that needs to be predicted is determined, including the information of each substation in the distributed power station, the longitude and latitude coordinates of each substation and the rated capacity Cap; the operating data parameters of each substation, including the generated power Pn or the generated power Qn, where the time resolution is less than or equal to 15 minutes, and the collected irradiance meteorological data of the sample area is obtained.

[0068] In S103, the power generation data is predicted using the selected power generation data prediction model, and the prediction results are summarized to obtain a summary prediction result.

[0069] According to the example embodiment, a variety of modeling methods are used to implement power summary prediction, and the summary power prediction value PI of the power station at each moment is obtained. The modeling method described in this example embodiment includes a single data source model, a data inversion model, a non-numerical meteorological source model, and a power station information-free prediction model. The power generation data is predicted by the selected power generation data prediction model, and the prediction results are summarized to obtain a summary prediction result. According to different data collection conditions, a suitable model can be selected to perform power prediction of distributed photovoltaic power stations. Each modeling method has its applicable scenarios and advantages. Through reasonable selection and application, the accuracy and reliability of the prediction can be improved. The final summary prediction result can be used to guide power grid scheduling and power station operation and maintenance.

[0070] In S105, the aggregated prediction result is split to obtain a prediction result for each station area.

[0071] According to an example embodiment, the summary power forecast value is split, including calculating the power generation efficiency, and the power generation efficiency of each substation is calculated by a formula, and the formula for calculating the power generation efficiency Pr is:

[0072] Pr=Q / (Cap*T)

[0073] in,

[0074] Q is the actual power generation (unit: MWh);

[0075] Cap is the rated capacity of each substation (unit: MW);

[0076] T is the peak sunshine hours (unit: h).

[0077] The peak sunshine hours T is the total daily radiation (kWh / m 2 ) and STC corresponding to 1000W / m 2 ratio.

[0078] According to an example embodiment, the summary power prediction value is split, and the calculation of each area split coefficient is also included. The area split coefficient is composed of two parameters: the area rated capacity Cap and the power generation efficiency Pr. The combination of the two parameters adopts a normalized calculation method. The calculation formula of the area split coefficient is:

[0079] Xn=0.5*(Cap n / sum(Cap n ))+0.5*(Pr n / sum(Pr n ))

[0080] in,

[0081] Xn is the splitting coefficient of the nth station area;

[0082] Cap n is the rated capacity of the nth substation;

[0083] Pr n is the power generation efficiency of the nth substation.

[0084] Then, the prediction results of each area are calculated by splitting coefficient to form a prediction result set. The calculation formula of the prediction result Pn of each area is:

[0085] Pn=PI*Xn

[0086] in,

[0087] Pn is the prediction result set of the nth station area;

[0088] PI summarizes the power forecast value;

[0089] Xn is the splitting coefficient of the nth station.

[0090] According to some embodiments, Pn is a set of prediction results, with one prediction value every 15 minutes, then the prediction value at each time point is 96, and the power prediction result of the nth substation in the next 24 hours is obtained, which consists of 96 prediction values, Pn = [P n1 ,P n2 ,......P n96 ].

[0091] In order to avoid incorrect allocation of prediction results to each substation after splitting, the rationality of the splitting results is judged, and two items are retained for rationality verification. The first item is that the prediction result of the substation allocation at each moment is not greater than the rated capacity of the substation; the second item is to sum up the prediction results allocated to each substation at a certain prediction moment, and the sum value is equal to the prediction result summarized at the prediction moment.

[0092] Figure 2 A schematic block diagram of a single data source model for distributed photovoltaic power prediction according to an example embodiment is shown.

[0093] See also Figure 2 According to an example embodiment, the input of the single data source model is the aggregated historical power generation data of distributed power stations and the aggregated power station rated capacity, and the output of the single data source model is the aggregated prediction result, which is not greater than the aggregated power station rated capacity.

[0094] The single data source model uses the distributed power station summary historical power generation data or the distributed summary power station historical power generation for modeling and prediction. The summary power station rated capacity is the basic information and does not need to be collected in real time. The historical power generation data is preprocessed, including operations such as removing outliers, filling missing values, and format normalization to ensure data quality, select a suitable prediction model, such as linear regression, ARIMA, random forest, etc., find the optimal parameter setting, so that the model can simulate the historical power generation data as accurately as possible, and use the trained single data model to predict the power generation in the future time period to obtain a summary prediction result.

[0095] Each modeling process is designed based on whether certain data can be collected and how many types of data can be collected. The single data model is suitable for modeling prediction under the condition that only power data can be collected. The single data source model is relatively simple and has fewer data requirements.

[0096] Figure 3 A schematic block diagram of a distributed photovoltaic power prediction data inversion model according to an example embodiment is shown.

[0097] See also Figure 3 According to the example embodiment, the input of the data inverse model is the distributed power station summary historical power generation data, the summary power station rated capacity and the historical numerical weather forecast value of the power station area; the output summary forecast target value of the data inverse model is reversely calculated, and the summary total power forecast value is reversed according to the historical data including the summary capacity and the power. The process of data collection and preprocessing is not described in detail here.

[0098] The data reverse inference model is based on historical data and estimates future power through modeling principles. Although the prediction accuracy of this model may be low, by using methods such as time series analysis, the summary prediction results can be reasonably distributed to each substation, generating a prediction result set for each substation, and generating prediction results with certain reference significance.

[0099] Figure 4 A schematic block diagram of a numerical meteorological source-free model for distributed photovoltaic power prediction according to an example embodiment is shown.

[0100] See also Figure 4 According to an example embodiment, the non-numerical meteorological source model is applied to the case where only real-time ground meteorological station data is available, and there is no external numerical meteorological forecast source. The input of the meteorological forecast model in the non-numerical meteorological source model is the historical meteorological station data collected by the power station; the historical power data of the power station and the historical meteorological station data of the power station are used as the modeling data of the power forecast model; the input of the power forecast model is the future meteorological forecast data predicted based on the historical meteorological station data of the power station, and the summary forecast result is obtained through the power forecast model.

[0101] The first step is to predict future meteorological data. The meteorological prediction model is built through the historical meteorological station data of the power station. The prediction of future meteorological data can be achieved by using methods such as time series analysis or sliding average filtering.

[0102] The second step is to build a power prediction model, using the power plant's historical power data and the power plant's historical weather station data as the modeling data for the power prediction model, using the power plant's historical weather station data as training input, and using the power plant's historical power data as target output to train the model; a convolutional neural network (CNN), support vector machine (SVM) or long short-term memory network (LSTM) can be used for modeling, and multiple modeling methods can be tried, and the prediction performance can be compared to select the model that best suits the specific application scenario. In addition, it is also possible to consider using an ensemble learning method to combine the results of multiple models to improve prediction accuracy.

[0103] A power prediction model between meteorology and power is established. In the third step, the meteorological forecast data is input into the trained power prediction model, and the meteorological forecast data is used as input to obtain the prediction result of future power.

[0104] This exemplary embodiment can obtain a relatively accurate future power prediction result by using a model trained with historical weather station data and historical power data, and predicting future weather data.

[0105] Figure 5 A schematic block diagram of a power plant information-free prediction model for distributed photovoltaic power prediction according to an example embodiment is shown.

[0106] See also Figure 5 According to the example embodiment, the input of the prediction model without power station information is regional weather forecast data, and the theoretical summary prediction result is obtained through the theoretical prediction model. The theoretical summary prediction result is converted to obtain the product result of the rated capacity of the power station and the theoretical prediction of a single megawatt. The conversion through the theoretical summary prediction result can provide strong data support for the operation and management of the power station, which is helpful to predict the power generation capacity of the power station in the future.

[0107] The prediction model without power station information can provide a preliminary prediction reference in the absence of historical data of power stations, and combine large-scale regional numerical meteorological information and standard prediction models to predict the power of unit installed capacity and daily power generation in the region.

[0108] The method for distributed photovoltaic power generation prediction proposed in the present invention summarizes and predicts the distributed photovoltaic power and splits the prediction results into each substation. The method can realize the summary prediction by large-capacity power stations, and comprehensively distribute the summary prediction results according to the capacity and power generation efficiency of each substation. Compared with the method of only distributing the summary prediction results according to the rated capacity of each substation, the method can more accurately distribute the prediction value. The prediction value allocated to the substation with low power generation efficiency is lower, and the prediction value allocated to the substation with high power generation efficiency is higher, thereby better ensuring the prediction accuracy of each substation.

[0109] Figure 6 A block diagram of a computing device according to an example embodiment of the present invention is shown.

[0110] like Figure 6 As shown, computing device 30 includes processor 12 and memory 14. Computing device 30 may also include bus 22, network interface 16, and I / O interface 18. Processor 12, memory 14, network interface 16, and I / O interface 18 may communicate with each other via bus 22.

[0111] The processor 12 may include one or more general-purpose CPUs (Central Processing Units, processors), microprocessors, or application-specific integrated circuits, etc., for executing relevant program instructions.

[0112] The memory 14 may include a machine system readable medium in the form of a volatile memory, such as a random access memory (RAM), a read-only memory (ROM) and / or a cache memory. The memory 14 is used to store one or more programs including instructions and data. The processor 12 can read the instructions stored in the memory 14 to execute the above-mentioned method according to the embodiment of the present invention.

[0113] The computing device 30 may also communicate with one or more networks via the network interface 16. The network interface 16 may be a wireless network interface.

[0114] The bus 22 may include an address bus, a data bus, a control bus, etc. The bus 22 provides a path for exchanging information between components.

[0115] It should be noted that, in the specific implementation process, the computing device 30 may also include other components necessary for normal operation. In addition, those skilled in the art may understand that the above device may only include components necessary for implementing the embodiments of this specification, and need not include all components shown in the figure.

[0116] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), a network storage device, a cloud storage device, or any type of medium or device suitable for storing instructions and / or data.

[0117] An embodiment of the present invention also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0118] Those skilled in the art can clearly understand that the technical solution of the present invention can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array, an integrated circuit, etc.

[0119] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0120] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] In the several embodiments provided by the present invention, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention.

[0125] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] The exemplary embodiments of the present invention are specifically shown and described above. It should be understood that the present invention is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present invention is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended clauses.

[0127] Those skilled in the art can clearly understand that the technical solution of the present invention can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array, an integrated circuit, etc.

[0128] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0129] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0130] In the several embodiments provided by the present invention, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention.

[0134] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] The exemplary embodiments of the present invention are specifically shown and described above. It should be understood that the present invention is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present invention is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended clauses.

Claims

1. A method for distributed photovoltaic power generation prediction, characterized in that: include: Obtain basic data of distributed power stations, including information of each substation in the distributed power station; Predicting the power generation data through the selected power generation data prediction model, summarizing the prediction results, and obtaining a summary prediction result; The aggregated prediction results are split to obtain prediction results for each station area.

2. The method according to claim 1, characterized in that The basic data of the distributed power station includes: The latitude and longitude coordinates and rated capacity of each station area; The operating data parameters of each substation include power generation or power generation.

3. The method according to claim 1, characterized in that It also includes judging the rationality of the split results: The predicted result of each moment of the area allocation is not greater than the rated capacity of the area; The prediction results allocated to each area at a certain prediction time are summed up, and the sum value is equal to the summary prediction result at the prediction time.

4. The method according to claim 1, characterized in that: The power generation data is predicted by a selected power generation data prediction model, wherein the selected power generation data prediction model includes a single data source model: The input of the single data source model includes the aggregated historical power generation data of distributed power stations; The output of the single data source model includes a summary prediction result, and the summary prediction result is no greater than the summary power plant rated capacity.

5. The method according to claim 1, characterized in that The power generation data is predicted by a selected power generation data prediction model, wherein the selected power generation data prediction model includes a data inverse model: The input of the data inverse model includes the aggregated historical power generation data of the distributed power stations, the aggregated rated capacity of the power stations and the historical numerical meteorological forecast values ​​of the power station area; The output summary prediction target value of the data inversion model is reversely calculated, and the future summary power prediction value is reversed according to the historical data including the summary capacity and the power of electricity.

6. The method according to claim 1, characterized in that The power generation data is predicted by a selected power generation data prediction model, wherein the selected power generation data prediction model includes a non-numerical meteorological source model: The input of the meteorological prediction model in the non-numerical meteorological source model is the historical meteorological station data collected by the power station; The historical power data of the power plant and the historical weather station data of the power plant are used as modeling data of the power prediction model; The input of the power prediction model includes future weather forecast data predicted based on historical weather station data of the power station; The non-numerical meteorological source model is applied to the situation where only real-time ground meteorological station data is available and there is no external numerical meteorological forecast source.

7. The method according to claim 1, characterized in that The power generation data is predicted by a selected power generation data prediction model, wherein the selected power generation data prediction model includes a prediction model without power station information: The input of the power station information-free prediction model is regional weather forecast data; The summary theoretical prediction results are obtained through the theoretical prediction model; The product of the rated capacity of the power station and the theoretical prediction of a single megawatt is obtained by converting the summarized theoretical prediction results.

8. The method according to claim 1, characterized in that The aggregated prediction results are split, including: Calculate the power generation efficiency and use the formula to calculate the power generation efficiency of each substation: Pr=Q / (Cap*T) Among them, Pr is the power generation efficiency, Q is the actual power generation, Cap is the rated capacity of each substation, and T is the peak sunshine hours.

9. The method according to claim 1, characterized in that: Splitting the aggregated prediction results further includes: Calculate the splitting coefficient of each area, the calculation formula is: Xn=0.5*(Cap n / sum(Cap n ))+0.5*(Pr n / sum(Pr n , Among them, Xn is the nth area split coefficient, Cap n is the rated capacity of the nth station area, Pr n is the power generation efficiency of the nth substation; The prediction results of each substation are calculated using the split coefficient to form a prediction result set.

10. A computing device, characterized in that include: processor; as well as A memory storing a computer program, which, when executed by the processor, enables the processor to perform the method according to any one of claims 1 to 9.

Images