Photovoltaic power generation power prediction method and device, equipment and storage medium

Abstract

The invention relates to the technical field of photovoltaic power generation, and discloses a photovoltaic power generation power prediction method, device and equipment and a storage medium, and the method comprises the steps: obtaining historical meteorological data and historical power generation power, building an operation state space based on the historical meteorological data, and obtaining a prediction result; the running state space is used for representing a mapping relation between each meteorological influence factor and the generated power, each meteorological influence factor has a respective weight coefficient, target meteorological data is obtained, and the generated power output characteristic of the photovoltaic power generation power is represented by the target meteorological data; and processing the target meteorological data based on the operation state weighted distance through the associated data model to obtain a photovoltaic power generation power prediction value. According to the method, the main meteorological influence factors of the photovoltaic power generation power are identified and determined, related data are acquired for quantitative analysis, the associated data model is established, and the operation state weighting distance is introduced, so that the power generation power characteristics of the photovoltaic power station are accurately predicted.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to a method, device, equipment and storage medium for predicting photovoltaic power generation. Background Art

[0002] Photovoltaic power generation is closely related to weather conditions, and the fluctuations in weather conditions can be described by multiple meteorological parameters. According to meteorological professional theory and analysis of the basic principles and working conditions of photovoltaic power generation, factors such as solar irradiance, ambient temperature, relative humidity, wind speed, wind direction, and air pressure will all affect photovoltaic power generation. However, the degree of influence of these multiple meteorological factors on photovoltaic power generation varies, and the degree of effect of the same factor under different operating conditions may also change. Moreover, these meteorological factors have multiple correlations and coupling relationships with each other, so they show obvious intermittent and random characteristics. However, photovoltaic output prediction is an important guarantee for supporting the safe and stable operation of the power grid. By predicting the output of photovoltaic power generation, it can better serve the dispatching and operation of the power grid and reduce the impact of photovoltaic power generation fluctuations on the power grid.

[0003] At present, the technology for predicting photovoltaic power generation output characteristics can be divided into two categories: physical model-based methods and data-driven methods. Specifically, the physical model method is based on numerical weather forecasts, ground-based all-sky images, satellite observation cloud maps and other data, starting from the atmospheric physical processes that affect the fluctuations in photovoltaic power generation; the data-driven method integrates historical libraries, according to the time series of data and statistical learning methods, through artificial neural networks, support vector machines, autoregressive models and regression analysis algorithms to achieve prediction.

[0004] However, both methods currently face the problem of being unable to fully and accurately obtain the characteristics of the multi-factor meteorological influencing factors of photovoltaic power generation and low prediction accuracy. Therefore, it is urgent to construct a more accurate prediction relationship model between photovoltaic power generation and multi-factor meteorological influencing factors to achieve accurate prediction of the power generation characteristics of photovoltaic power stations. Summary of the invention

[0005] In view of this, the present invention provides a photovoltaic power prediction method, device, equipment and storage medium to solve the problem that the photovoltaic power output characteristic prediction fails to fully consider multiple meteorological influencing factors and the prediction accuracy is low.

[0006] In a first aspect, the present invention provides a method for predicting photovoltaic power generation, the method comprising: Obtain historical meteorological data and historical power generation; historical meteorological data refers to data on meteorological influencing factors at historical moments; An operating state space is constructed based on historical meteorological data to generate an associated data model for characterizing the output characteristics of photovoltaic power generation; the operating state space is used to characterize the mapping relationship between various meteorological influencing factors and power generation; each meteorological influencing factor has its own weight coefficient; The target meteorological data is obtained, and the target meteorological data is processed based on the weighted distance of the operating state through the associated data model to obtain the predicted value of photovoltaic power generation; the target meteorological data is the data of the meteorological influencing factors at the target time.

[0007] The photovoltaic power generation prediction method provided by the embodiment of the present invention constructs an operating state space for a large number of historical meteorological data and historical power generation at historical moments to form an accurate correlation data model. By constructing a correlation data model based on historical meteorological data and historical power generation, it is used to characterize the mapping relationship between various meteorological influencing factors and power generation. This method can more accurately capture the complex relationship between photovoltaic power generation power and meteorological influencing factors, and utilize these relationships in combination with the weighted distance minimum principle to realize photovoltaic power generation prediction of target meteorological data, thereby improving the accuracy of the prediction.

[0008] In an optional implementation, the meteorological influencing factors include irradiance, ambient temperature, relative humidity and wind speed.

[0009] The photovoltaic power generation prediction method provided by the embodiment of the present invention takes into account that the types of meteorological influencing factors of photovoltaic power generation are various and numerous, and their degree of effect and path of effect on power generation are different. Regression analysis and path analysis are performed on each meteorological influencing factor, irradiance, ambient temperature, relative humidity and wind speed are determined as meteorological influencing factors, and the importance of each meteorological influencing factor is further determined. Compared with relying only on a single meteorological factor or performing isolated analysis and prediction on each meteorological factor, the present invention takes into account the diversity of meteorological influencing factors, can significantly reduce prediction errors, and makes the prediction of photovoltaic power generation more accurate.

[0010] In an optional implementation, obtaining target meteorological data includes: Get historical irradiance data; The historical irradiance data is input into the irradiance prediction model for processing to obtain the target irradiance at the target time.

[0011] The photovoltaic power generation prediction method provided by the embodiment of the present invention takes into account that photovoltaic power generation is directly affected by solar irradiance. Therefore, improving the prediction accuracy of irradiance can significantly improve the prediction accuracy of photovoltaic power generation. Specifically, based on historical irradiance data, a neural network prediction model for irradiance data is established, and the model is trained with a large amount of historical irradiance data to obtain the target irradiance, which not only makes the prediction result more accurate, but also makes the prediction process more scientific and systematic.

[0012] In an optional implementation, target meteorological data is acquired, and the target meteorological data is processed by a correlation data model to obtain a photovoltaic power generation power prediction value, including: Obtain the target irradiance, target ambient temperature, target relative humidity and target wind speed at the target time; Based on the target irradiance, target ambient temperature, target relative humidity and target wind speed, the predicted value vector of the meteorological influencing factor is calculated; Based on the predicted value vector of meteorological influencing factors and the associated data model, the predicted value of photovoltaic power generation is mapped.

[0013] The photovoltaic power prediction method provided by the embodiment of the present invention can more comprehensively reflect the actual situation by considering these factors at the same time and performing power prediction based on their predicted values, thereby improving the prediction accuracy. At the same time, in the prediction process, the model parameters and structure are continuously optimized, which can improve the model's adaptability to complex meteorological conditions and prediction accuracy, and further enhance the scientificity and reliability of the prediction.

[0014] In an optional implementation, obtaining historical meteorological data and historical power generation includes: Obtain real-time meteorological data and real-time power generation data corresponding to the real-time meteorological data; The real-time meteorological data that meets the preset range conditions and the real-time power generation corresponding to the real-time meteorological data are respectively stored in the historical meteorological data set and the historical power generation set to obtain an updated historical meteorological data set and the historical power generation set; The data in the updated historical meteorological data set and the historical power generation data set are obtained as historical meteorological data and historical power generation data.

[0015] The photovoltaic power prediction method provided in the embodiment of the present invention preprocesses the acquired data while continuously collecting and acquiring meteorological data and power generation data, that is, only data that meets preset conditions and is within the value range specified in the numerical table is recognized as valid data, thereby removing the influence of abnormal values ​​or noise data, so that the associated data model established based on these data is more stable and accurate.

[0016] In an optional embodiment, the method further includes: When real-time meteorological data identical to historical meteorological data is detected, the historical power generation corresponding to the historical meteorological data is updated to the real-time power generation, and the weight coefficient is updated based on the real-time meteorological data and the real-time power generation data corresponding to the real-time meteorological data; If the real-time meteorological data identical to the historical meteorological data is not detected, the real-time meteorological data and the real-time power generation corresponding to the real-time meteorological data are stored in the historical meteorological data set and the historical power generation set. The photovoltaic power generation prediction method provided by the embodiment of the present invention continuously collects the meteorological data and the corresponding power generation data of the photovoltaic power station during the operation of the photovoltaic power station, and compares the collected implementation meteorological data with the historical meteorological data. When the real-time meteorological data that is exactly the same as the historical meteorological data is detected, the corresponding historical power generation is updated to the latest real-time power generation, thereby ensuring the timeliness of the historical data. At the same time, by updating the weight coefficient based on the real-time data, the prediction model can be more adapted to the current meteorological conditions and power generation efficiency, thereby improving the adaptability and accuracy of the prediction model under different conditions.

[0017] In a second aspect, the present invention provides a photovoltaic power prediction device, the device comprising: An acquisition module is used to acquire historical meteorological data and historical power generation; the historical meteorological data is data on meteorological influencing factors at historical moments; A generation module is used to construct an operation state space based on historical meteorological data to generate an associated data model for characterizing the output characteristics of photovoltaic power generation; the operation state space is used to characterize the mapping relationship between various meteorological influencing factors and power generation; and each meteorological influencing factor has its own weight coefficient; The prediction module is used to obtain target meteorological data and process the target meteorological data through the associated data model to obtain the predicted value of photovoltaic power generation; the target meteorological data is the data of meteorological influencing factors at the target time.

[0018] Optionally, the prediction module further includes: Historical irradiance submodule, used to obtain historical irradiance data; The input submodule is used to input the historical irradiance data into the irradiance prediction model for processing to obtain the target irradiance at the target time.

[0019] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the photovoltaic power prediction method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the photovoltaic power prediction method of the first aspect or any corresponding embodiment thereof.

[0021] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the photovoltaic power prediction method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 is a schematic flow chart of a method for predicting photovoltaic power generation according to an embodiment of the present invention; Figure 2 is a flow chart of a photovoltaic power prediction method according to an embodiment of the present invention; Figure 3 is a structural block diagram of a photovoltaic power prediction device according to an embodiment of the present invention; Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] On the one hand, the current output characteristic prediction model fails to correctly identify and determine several major meteorological factors that have a greater impact on photovoltaic power generation; on the other hand, there are multiple correlations and coupling relationships among the meteorological factors, so how to define the weight coefficients of each meteorological factor and achieve accurate prediction is another difficulty.

[0026] Therefore, the present invention provides a method for predicting photovoltaic power generation, identifies and optimizes the input variables of the photovoltaic power generation prediction model, obtains the correlation between meteorological influencing factors and power generation, and uses the path analysis method to further quantitatively analyze the characteristics of each meteorological influencing factor on photovoltaic power generation, and realizes the power generation mapping method based on minimizing the weighted distance of the operating state by constructing the operating state space.

[0027] According to an embodiment of the present invention, an embodiment of a method for predicting photovoltaic power generation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] In this embodiment, a method for predicting photovoltaic power generation is provided. Figure 1 is a flow chart of a method for predicting photovoltaic power generation according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps: Step S101, obtaining historical meteorological data and historical power generation power.

[0029] Specifically, the historical meteorological data is data on meteorological influencing factors at historical moments.

[0030] In some optional implementations, the above step S101 includes: Obtain real-time meteorological data and real-time power generation data corresponding to the real-time meteorological data; The real-time meteorological data that meets the preset range conditions and the real-time power generation corresponding to the real-time meteorological data are respectively stored in the historical meteorological data set and the historical power generation set to obtain an updated historical meteorological data set and the historical power generation set; The data in the updated historical meteorological data set and the historical power generation data set are obtained as historical meteorological data and historical power generation data.

[0031] like Figure 2 As shown, during the operation of the grid-connected photovoltaic power station, new real-time meteorological data and the real-time power generation corresponding to the real-time meteorological data will continue to appear as time goes by. The corresponding relationship between the real-time meteorological data and the real-time power generation corresponding to the real-time meteorological data and the existing data in the associated data model can be used as the data basis for establishing and updating the associated data model in real time.

[0032] Since sensor failure, data transmission error, electromagnetic interference or other reasons may cause data loss and numerical anomalies, it is necessary to pre-process the real-time meteorological data generated based on the real-time operation data of the grid-connected photovoltaic power station, such as irradiance, ambient temperature, relative humidity, wind speed, and power generation, and screen the real-time meteorological data that meet the value range table and the power generation corresponding to the real-time meteorological data, and confirm this part of the data as valid data. Specifically, if the real-time meteorological data and its corresponding predicted power generation data are within the value range corresponding to the value range table, the data is considered to be valid data. Data beyond the value range is confirmed as abnormal data, and the valid data is stored in the historical meteorological data set and the historical power generation set.

[0033] By continuously collecting the operating status data of photovoltaic power stations as real-time power generation data corresponding to real-time meteorological data, the associated data model can be continuously updated. It can not only save the newly emerging operating status of the photovoltaic power station, making its description of the power output characteristics more accurate and detailed, but also remove the influence of outliers or noise data, and make the associated data model based on these data more stable and accurate.

[0034] Optionally, missing data and abnormal data can be supplemented or corrected through interpolation or other measures to make them valid data.

[0035] Several common abnormal data types are usually: 1) Empty data point: the data record of a certain point is empty or the data of a certain day is missing. 2) Zero data point: the data record of a certain point is zero or the data of a certain day is zero. 3) Continuous constant value: A continuous constant value is a set of data with exactly the same value over a continuous period of time on the curve. 4) Step value: It includes significant spike pulses on the curve, curve shapes with significant rising or falling edges, and some unusual data caused by interference.

[0036] Based on this, we can first identify the type of abnormal data, and then make targeted corrections based on the type of abnormal data, so that the abnormal data can be changed into valid data. Specifically, firstly, the abnormal data is roughly identified, and empty data points, zero data points, continuous constant value data, and outlier data are located. Some abnormal data are simply corrected. Then, the distributed photovoltaic output data is judged for regularity. The probability of misjudgment of values ​​with weak regularity is high, so it is not directly corrected. For load abnormal data with strong regularity, it is highly identifiable and correctable, so it can be directly corrected. For loads with obvious regularity, extract their characteristic curves, use the characteristic curves to compare with the distributed photovoltaic output curves, finely identify abnormal zero values, abnormal constant values, and abnormal jump values, and correct the abnormal data according to the characteristic curves. Finally, the corrected data is tested twice to restore the data of the abnormal data points.

[0037] Step S102: constructing an operating state space based on historical meteorological data to generate a correlation data model for characterizing photovoltaic power output characteristics.

[0038] Specifically, the operating state space is used to characterize the mapping relationship between various meteorological influencing factors and power generation.

[0039] Furthermore, each meteorological influencing factor has its own weight coefficient.

[0040] Furthermore, the weight coefficient of each meteorological influencing factor is calculated based on historical meteorological data through a neural network method.

[0041] Step S103, acquiring target meteorological data, and processing the target meteorological data based on the weighted distance of the operating state through the associated data model to obtain a predicted value of photovoltaic power generation.

[0042] Specifically, the target meteorological data is the data of meteorological influencing factors at the target time.

[0043] Furthermore, the format of the target meteorological data is consistent with the format of the historical meteorological data used when constructing the associated data model.

[0044] Furthermore, the target meteorological data is passed as input to the associated data model, and the photovoltaic power generation prediction value is mapped. The target meteorological data can be processed through the associated data model, and the associated data model can obtain the photovoltaic power generation prediction value based on the weighted distance of the operating state between the target meteorological data and the historical meteorological data.

[0045] Furthermore, the weighted distance of the operating state is used to characterize the difference between two different operating states. Since each set of meteorological factor data corresponds one-to-one to a point in the operating state space, the smaller the weighted distance between the two points, the more similar the two meteorological factor conditions are. Therefore, the power generation mapped by the point with a smaller weighted distance has a greater reference value for prediction. Therefore, based on the principle of minimizing the weighted distance of the operating state, one or several points in the operating state space that are most similar to the target meteorological factor conditions can be found for power generation mapping prediction.

[0046] In the embodiment of the present application, a regression analysis method is first used to study the correlation between photovoltaic power generation and multivariate meteorological influencing factors, and the main meteorological influencing factors that determine photovoltaic power generation are identified; secondly, the path analysis method is used to further quantitatively analyze the direct impact of each meteorological factor on photovoltaic power generation and the indirect impact through other factors, so as to determine the weight of each meteorological factor. Specifically, the direct effect coefficient and the indirect effect coefficient are first added together to obtain the total effect coefficient of each meteorological factor. Because the independent variables corresponding to each regression coefficient have different dimensions and values, the total effect coefficient of each meteorological factor needs to be normalized and its sum equal to 1, so as to eliminate the influence of different dimensions and values ​​on the partial regression coefficient, thereby obtaining the weight of each meteorological factor. .

[0047] The operating state space is established based on meteorological influencing factors and historical meteorological data. Each set of meteorological factor data and its corresponding power generation data correspond to a point in the operating state space. The space formed by each meteorological influencing factor is called the input feature space. The input feature space can describe the input state of the photovoltaic power station, and the associated data model is a nonlinear single-value mapping from the input feature space to the power generation. The nonlinear mapping that describes the power characteristics corresponds to a hyperplane in the operating state space. This hyperplane is actually a collection of some points in it. This set of records is called the associated data model. The first four items in the associated data model record are the input feature fields, and the last item is the power generation field.

[0048] Obtain the target meteorological data, input it into the associated data model, and predict the power generation of the target meteorological data by calculating the weighted distance of the operating state. Specifically, the weighted distance between two points in the operating state space reflects the similarity of the meteorological data between the two points. That is, the smaller the weighted distance, the more similar the meteorological factor data corresponding to the two operating state spaces are, and the more reference value the mapped power generation has for prediction. For a target meteorological data, calculate according to the weighted distance calculation formula:

[0049] in, and are the meteorological factor vectors of the two operating states respectively; and These two operating states are The value of the meteorological factor; It is The weight of a meteorological factor reflects the relative importance of the factor on photovoltaic power.

[0050] Calculate the weighted distance between the target meteorological data point and other points in the operating space, find the point with the smallest weighted distance, and predict the power generation.

[0051] Optionally, for a target meteorological data, the weighted distance between the target meteorological data point and other points in the operating space is calculated, and several points with smaller weighted distances are found. The power generation values ​​of the several points are averaged, median or weighted averaged to map the power generation power.

[0052] In some optional embodiments, the meteorological influencing factors include irradiance, ambient temperature, relative humidity and wind speed.

[0053] Through regression analysis, it can be found that the change trends of the power generation curve and the irradiance curve are very consistent. The correlation coefficient between power generation and irradiance is calculated. Therefore, irradiance is a very important meteorological influencing factor of photovoltaic power generation, and has a great effect on photovoltaic power generation. There is a strong negative correlation between the power generation curve and the ambient temperature. Ambient temperature is a relatively important meteorological influencing factor of photovoltaic power generation, and has a greater effect on photovoltaic power generation. There is a strong negative correlation between photovoltaic power generation and relative humidity. It can be seen that relative humidity is a relatively important meteorological influencing factor of photovoltaic power generation, and has a greater effect on photovoltaic power generation. There is no obvious rule between photovoltaic power generation and wind speed. The influence is sometimes positive and sometimes negative, and mostly positive. Wind speed has a certain influence on photovoltaic power generation. Therefore, photovoltaic power generation is taken as the dependent variable, and irradiance, ambient temperature, relative humidity and wind speed are taken as independent variables. The stepwise regression method is used to establish the multivariate linear regression equation between power generation and these meteorological influencing factors using software.

[0054] The residual path analysis factor reflects the importance of each meteorological influencing factor. In order to determine the weight of each meteorological influencing factor, the weight coefficient of each meteorological influencing factor is not the coefficient of each multivariate linear regression equation itself, but a path analysis of the meteorological influencing factor is required. Specifically, the direct effect coefficient and the indirect effect coefficient are first added together to obtain the total effect coefficient of each meteorological factor. Because the independent variables corresponding to each regression coefficient have different dimensions and values, the total effect coefficient of each meteorological factor needs to be normalized and its sum equal to 1 to eliminate the influence of different dimensions and values ​​on the partial regression coefficient, thereby obtaining the weight of each meteorological factor.

[0055] In some optional implementations, obtaining target meteorological data includes: Get historical irradiance data; The historical irradiance data is input into the irradiance prediction model for processing to obtain the target irradiance at the target time.

[0056] Use machine learning, deep learning or statistical models and other methods to build an irradiance prediction model based on historical irradiance data. Input the collected historical irradiance data into the irradiance prediction model for model training. Learn the law of irradiance change based on the model and predict the target irradiance at the target time accordingly.

[0057] In some optional implementations, target meteorological data is acquired, and the target meteorological data is processed by a correlation data model to obtain a photovoltaic power generation power prediction value, including: Obtain the target irradiance, target ambient temperature, target relative humidity and target wind speed at the target time; Based on the target irradiance, target ambient temperature, target relative humidity and target wind speed, the predicted value vector of the meteorological influencing factor is calculated; Based on the predicted value vector of meteorological influencing factors and the associated data model, the predicted value of photovoltaic power generation is mapped.

[0058] According to the forecast information of meteorological influencing factors, the target meteorological data is calculated. Specifically, the irradiance forecast value is first obtained by using the neural network forecast model as the target irradiance. The ambient temperature is obtained as the target ambient temperature, the relative humidity forecast value is obtained as the target relative humidity, and the wind speed forecast value is obtained as the target wind speed through weather forecast and other forecast methods. These four are combined into a forecast value vector of meteorological influencing factors. The vector corresponds one-to-one with the points on the input feature space in the constructed operation state space composed of these four. Specifically, the target meteorological data at the target time is composed of the target G Y is the predicted value of irradiance, T Y is the predicted value of ambient temperature, H Y is the predicted value of relative humidity, V Y is the predicted value of wind speed, so the predicted value vector can be expressed as (G Y , T Y , H Y , V Y ), input it into the associated data model to obtain the preset value of photovoltaic power generation power.

[0059] In some optional embodiments, the method further comprises: When real-time meteorological data identical to historical meteorological data is detected, the historical power generation corresponding to the historical meteorological data is updated to the real-time power generation data, and the weight coefficient is updated based on the real-time meteorological data and the real-time power generation data corresponding to the real-time meteorological data; If the real-time meteorological data identical to the historical meteorological data is not detected, the real-time meteorological data and the real-time power generation data corresponding to the real-time meteorological data are stored in the historical meteorological data set and the historical power generation set. like Figure 2As shown, after obtaining the real-time meteorological data and the power generation data corresponding to the real-time meteorological data, the pre-processed data is sequentially read into the records including the real-time meteorological data and the real-time power generation data corresponding to it in chronological order for verification. If there is historical meteorological data in the associated data model that has the same input feature field as the newly read record, the historical power generation corresponding to the historical meteorological data is updated to the real-time power generation data, and the weight coefficient is updated based on the real-time meteorological data and the real-time power generation data corresponding to the real-time meteorological data. The weight coefficient of the updated meteorological impact factor is calculated based on the neural network method. If there is no historical meteorological data that has the same input feature field as the newly read record, the newly acquired real-time meteorological data and the power generation data corresponding to the real-time meteorological data are stored in the historical meteorological data and the historical power generation data.

[0060] In this embodiment, a photovoltaic power prediction device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated here. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0061] This embodiment provides a photovoltaic power prediction device, such as Figure 3 As shown, including: The acquisition module 501 is used to acquire historical meteorological data and historical power generation; the historical meteorological data is data of meteorological influencing factors at historical moments; The generating module 502 is used to construct an operating state space based on historical meteorological data to generate an associated data model for characterizing the output characteristics of photovoltaic power generation; the operating state space is used to characterize the mapping relationship between each meteorological influencing factor and the power generation; each meteorological influencing factor has its own weight coefficient; The prediction module 503 is used to obtain target meteorological data and process the target meteorological data based on the weighted distance of the operating state through the associated data model to obtain the predicted value of photovoltaic power generation; the target meteorological data is the data of the meteorological influencing factors at the target time.

[0062] In some optional implementations, the acquisition module 501 includes: The real-time data acquisition submodule is used to acquire real-time meteorological data and real-time power generation data corresponding to the real-time meteorological data.

[0063] The updating submodule is used to store the real-time meteorological data that meets the preset range conditions and the real-time power generation corresponding to the real-time meteorological data into the historical meteorological data set and the historical power generation set respectively, to obtain the updated historical meteorological data set and the historical power generation set.

[0064] The historical data acquisition submodule is used to acquire the data in the updated historical meteorological data set and the historical power generation data set as historical meteorological data and historical power generation data.

[0065] In some optional embodiments, the device further comprises: The detection module is used to update the historical power generation corresponding to the historical meteorological data to the real-time power generation data when the real-time meteorological data that is the same as the historical meteorological data is detected, and to update the weight coefficient based on the real-time data.

[0066] The storage module is used to store the real-time meteorological data and the real-time power generation data corresponding to the real-time meteorological data into the historical meteorological data set and the historical power generation set if the real-time meteorological data identical to the historical meteorological data is not detected. In some optional implementations, the prediction module 503 includes: The historical irradiance submodule is used to obtain historical irradiance data.

[0067] The input submodule is used to input the historical irradiance data into the irradiance prediction model for processing to obtain the target irradiance at the target time.

[0068] In some optional implementations, the prediction module 503 further includes: The target data acquisition submodule is used to acquire the target irradiance, target ambient temperature, target relative humidity and target wind speed at the target time.

[0069] The calculation vector submodule is used to calculate the predicted value vector of meteorological influencing factors based on target irradiance, target ambient temperature, target relative humidity and target wind speed.

[0070] The mapping submodule is used to map the predicted value of photovoltaic power generation based on the predicted value vector of meteorological influencing factors and the associated data model.

[0071] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0072] The photovoltaic power prediction device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0073] The embodiment of the present invention also provides a computer device having the above Figure 3 The photovoltaic power generation prediction device is shown.

[0074] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0075] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0076] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0077] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0078] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0079] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0080] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0081] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0082] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0083] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for predicting photovoltaic power generation, characterized in that: The method comprises: Acquire historical meteorological data and historical power generation; the historical meteorological data is data of meteorological influencing factors at historical moments; An operating state space is constructed based on the historical meteorological data to generate an associated data model for characterizing the output characteristics of photovoltaic power generation; the operating state space is used to characterize the mapping relationship between each meteorological influencing factor and the power generation; each meteorological influencing factor has its own weight coefficient; Target meteorological data is acquired, and the target meteorological data is processed by the associated data model based on the weighted distance of the operating state to obtain a photovoltaic power generation power prediction value; the target meteorological data is data of meteorological influencing factors at the target moment.

2. The method according to claim 1, characterized in that The meteorological influencing factors include irradiance, ambient temperature, relative humidity and wind speed.

3. The method according to claim 2, characterized in that The step of obtaining target meteorological data comprises: Get historical irradiance data; The historical irradiance data is input into the irradiance prediction model for processing to obtain the target irradiance at the target time.

4. The method according to claim 2, characterized in that: The step of acquiring target meteorological data and processing the target meteorological data based on the weighted distance of the operating state through the associated data model to obtain a photovoltaic power generation power prediction value includes: Obtain the target irradiance, target ambient temperature, target relative humidity and target wind speed at the target time; Calculating a predicted value vector of a meteorological influencing factor based on the target irradiance, target ambient temperature, target relative humidity, and target wind speed; Based on the predicted value vector of the meteorological influencing factor and the associated data model, the photovoltaic power generation power prediction value is mapped.

5. The method according to any one of claims 1 to 4, characterized in that: The obtaining of historical meteorological data and historical power generation includes: Acquire real-time meteorological data and real-time power generation data corresponding to the real-time meteorological data; The real-time meteorological data satisfying the preset range conditions and the real-time power generation corresponding to the real-time meteorological data are stored in the historical meteorological data set and the historical power generation set respectively, so as to obtain an updated historical meteorological data set and the historical power generation set; The data in the updated historical meteorological data set and the historical power generation data set are obtained as historical meteorological data and historical power generation data.

6. The method according to claim 5, characterized in that The method further comprises: When the real-time meteorological data identical to the historical meteorological data is detected, the historical power generation corresponding to the historical meteorological data is updated to the real-time power generation data, and the weight coefficient is updated based on the real-time meteorological data and the real-time power generation data corresponding to the real-time meteorological data; If the real-time meteorological data identical to the historical meteorological data is not detected, the real-time meteorological data and the real-time power generation data corresponding to the real-time meteorological data are stored in the historical meteorological data set and the historical power generation set.

7. A photovoltaic power generation prediction device, characterized in that: The device comprises: An acquisition module is used to acquire historical meteorological data and historical power generation; the historical meteorological data is data of meteorological influencing factors at historical moments; A generation module is used to construct an operation state space based on the historical meteorological data to generate an associated data model for characterizing the output characteristics of photovoltaic power generation; the operation state space is used to characterize the mapping relationship between various meteorological influencing factors and power generation; and each meteorological influencing factor has its own weight coefficient; The prediction module is used to obtain target meteorological data and process the target meteorological data based on the weighted distance of the operating state through the associated data model to obtain a predicted value of photovoltaic power generation; the target meteorological data is the data of the meteorological influencing factors at the target moment.

8. The device according to claim 7, characterized in that The prediction module comprises: Historical irradiance submodule, used to obtain historical irradiance data; The input submodule is used to input the historical irradiance data into the irradiance prediction model for processing to obtain the target irradiance at the target time.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 6 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

Images