Solar irradiance interval prediction method and apparatus, computer device, and storage medium

Abstract

The present application relates to the technical field of interval prediction, and discloses a solar irradiance interval prediction method and apparatus, a computer device, and a storage medium. The method comprises: acquiring a historical environment parameter data set and a first environment parameter data set within a prediction pending period, and determining a first environment sample data set; establishing a target solar irradiance prediction model; inputting the first environment parameter data set into the target solar irradiance prediction model to obtain a solar irradiance prediction result within the prediction pending period; on the basis of the first environment sample data set, using a bootstrap sampling method to perform interval prediction on the solar irradiance prediction result within the prediction pending period to obtain a target solar irradiance interval prediction result within the prediction pending period. According to the present application, both the similarity and regularity of historical data and the complexity and accuracy of the model are considered. Furthermore, using the bootstrap sampling method to perform interval prediction on the solar irradiance prediction result effectively improve the reliability and confidence of the prediction result.

Description

Solar irradiance interval prediction method, device, computer equipment and storage medium Technical Field

[0001] The present application relates to the technical field of interval prediction, and in particular to a method, apparatus, computer equipment and storage medium for solar irradiance interval prediction. Background Art

[0002] Accurately predicting solar irradiance is fundamental to assessing power plant generation, ensuring power supply plans, and more effectively balancing the power grid. Currently, methods used for short-term solar irradiance forecasting primarily include physical modeling, statistical learning, artificial neural networks, deep learning, and cluster analysis. Physical modeling methods are computationally complex but can provide highly accurate predictions. Statistical methods, while not requiring complex physical models, offer high computational efficiency but suffer from lower accuracy and are significantly affected by data quality and feature selection. Artificial neural network methods can adapt to complex nonlinear relationships but require substantial data and computing resources and are sensitive to the choice of network structure and parameters. Deep learning methods, while requiring substantial data and computing resources, can provide highly accurate predictions.

[0003] However, the current short-term prediction methods for solar irradiance are all based on single-point predictions. For example, the above methods usually give a definite prediction value rather than a confidence interval of the prediction value, which cannot fully reflect the uncertainty of the prediction results, resulting in large errors in the prediction results.

[0004] Summary of the Invention

[0005] In view of this, the present application provides a solar irradiance interval prediction method, device, computer equipment and storage medium to solve the problem that the existing solar irradiance short-term prediction methods are all based on single-point prediction, which cannot fully reflect the uncertainty of the prediction results, resulting in large errors in the prediction results.

[0006] In a first aspect, the present application provides a solar irradiance interval prediction method for a photovoltaic power station; the solar irradiance interval prediction method includes:

[0007] Acquire a historical environmental parameter data set and a first environmental parameter data set of the photovoltaic power station within the period to be predicted; determine a first environmental sample data set based on the historical environmental parameter data set and the first environmental parameter data set; establish a target solar irradiance prediction model based on the first environmental sample data set; input the first environmental parameter data set into the target solar irradiance prediction model to obtain a solar irradiance prediction result within the period to be predicted; based on the first environmental sample data set, use an autonomous sampling method to perform interval prediction on the solar irradiance prediction result within the period to be predicted, and obtain a target solar irradiance interval prediction result within the period to be predicted.

[0008] The solar irradiance interval prediction method provided in this application selects the first environmental parameter dataset within the prediction period based on a historical environmental parameter dataset and uses the target solar irradiance prediction model to perform predictions. This method considers both the similarity and regularity of the historical data and the complexity and accuracy of the model. Furthermore, an autonomous sampling method is used to perform interval predictions on the solar irradiance prediction results, effectively increasing the reliability and confidence of the prediction results.

[0009] In an optional embodiment, determining the first environmental sample dataset based on the historical environmental parameter dataset and the first environmental parameter dataset includes:

[0010] A regression analysis is performed based on the historical environmental parameter data set, and a multiple linear regression function is constructed, which reflects the relationship between the environmental parameters and the collection time; the second environmental parameter data set is determined based on the multiple linear regression function; and the first environmental sample data set is determined based on the historical environmental parameter data set and the second environmental parameter data set.

[0011] This application determines the second environmental parameter data set by constructing a multivariate linear regression function that reflects the relationship between environmental parameters and collection time, taking into account the similarity and regularity of historical data, and providing data support for subsequent reduction of prediction errors.

[0012] In an optional embodiment, determining the first environmental sample dataset based on the historical environmental parameter dataset and the second environmental parameter dataset includes:

[0013] Calculate the Mahalanobis distance between the historical environmental parameter data corresponding to each preset collection time in the historical environmental parameter data set and the second environmental parameter data corresponding to the preset collection time in the second environmental parameter data set; determine the target period based on each Mahalanobis distance; and determine the first environmental sample data set in the historical environmental parameter data set based on the target period.

[0014] This application combines the Mahalanobis distance to determine the target period and the first environment sample data set, takes into account the correlation between various data features, and can effectively handle the problem of different measurement scales between different data features.

[0015] In an optional embodiment, establishing a target solar irradiance prediction model based on the first environmental sample data set includes:

[0016] Based on the first environmental sample data set, a first environmental sample data subset and a second environmental sample data subset are determined; the first environmental sample data subset is input into a preset neural network for training to obtain an initial solar irradiance prediction model; the initial solar irradiance prediction model is verified using the second environmental sample data subset to obtain a target solar irradiance prediction model.

[0017] This application uses the first environmental sample data subset to establish a target solar irradiance prediction model, and combines it with the second environmental sample data subset for verification, taking into account the complexity and accuracy of the model and improving the accuracy of the model prediction.

[0018] In an optional embodiment, based on the first environmental sample data set, an interval prediction is performed on the solar irradiance prediction result within the prediction period using an autonomous sampling method to obtain a target solar irradiance interval prediction result within the prediction period, including:

[0019] At least one second environmental sample data set is determined in the first environmental sample data set by using an autonomous sampling method; at least one target solar irradiance prediction model is established based on each second environmental sample data set; the first environmental parameter data set is input into each target solar irradiance prediction model respectively to obtain at least one solar irradiance prediction result; based on each solar irradiance prediction result and each preset interval prediction confidence value, at least one confidence interval range and at least one initial solar irradiance interval prediction result within the period to be predicted are determined; based on each confidence interval range, the accuracy of each initial solar irradiance interval prediction result is determined; based on each accuracy and each initial solar irradiance interval prediction result, the target solar irradiance interval prediction result within the period to be predicted is determined.

[0020] This application uses an autonomous sampling method to perform interval prediction on the solar irradiance prediction results. It does not require any assumptions about the original first environment sample data set. The distribution and parameters can be estimated directly from the first environment sample data set, and the uncertainty of the estimate can be quantified by calculating the confidence interval range, which effectively increases the reliability and confidence of the prediction results.

[0021] In an optional embodiment, based on each solar irradiance prediction result and each preset interval prediction confidence value, determining at least one confidence interval range and at least one initial solar irradiance interval prediction result within the period to be predicted includes:

[0022] Obtain the number of samples in each second environment sample data set; determine the average solar irradiance and the standard deviation of the solar irradiance based on each solar irradiance prediction result; determine at least one interval value based on the solar irradiance standard deviation, each preset interval prediction confidence value and each sample number; determine the confidence interval range corresponding to each preset interval prediction confidence value based on each interval value and the average solar irradiance value; determine at least one initial solar irradiance interval prediction result within the period to be predicted based on each confidence interval range.

[0023] This application quantifies the uncertainty of the estimate by calculating the confidence interval range, effectively increasing the reliability and confidence of the prediction results.

[0024] In an optional embodiment, determining the accuracy of each initial solar irradiance interval prediction result based on each confidence interval range includes:

[0025] The big data method is used to obtain the accuracy level of each solar irradiance interval prediction result corresponding to each confidence interval range; an evaluation index matrix is ​​established based on each accuracy level; a solar irradiance matrix is ​​established based on each solar irradiance prediction result; a membership matrix is ​​established based on the evaluation index matrix and the solar irradiance matrix; and the accuracy of each initial solar irradiance interval prediction result is determined based on the membership matrix and each solar irradiance prediction result.

[0026] This application quantifies the uncertainty of the estimate by calculating the confidence interval range, effectively increasing the reliability and confidence of the prediction results.

[0027] In a second aspect, the present application provides a solar irradiance interval prediction device for a photovoltaic power station; the solar irradiance interval prediction includes:

[0028] An acquisition module is used to obtain a historical environmental parameter data set and a first environmental parameter data set of a photovoltaic power station within a period to be predicted; a determination module is used to determine a first environmental sample data set based on the historical environmental parameter data set and the first environmental parameter data set; an establishment module is used to establish a target solar irradiance prediction model based on the first environmental sample data set; an input module is used to input the first environmental parameter data set into the target solar irradiance prediction model to obtain a solar irradiance prediction result within the period to be predicted; a prediction module is used to perform interval prediction on the solar irradiance prediction result within the period to be predicted based on the first environmental sample data set using an autonomous sampling method to obtain a target solar irradiance interval prediction result within the period to be predicted.

[0029] In a third aspect, the present application provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the solar irradiance interval prediction method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0030] In a fourth aspect, the present application provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the solar irradiance interval prediction method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0032] FIG1 is a schematic flow chart of a solar irradiance interval prediction method according to an embodiment of the present application;

[0033] FIG2 is a flow chart of another solar irradiance interval prediction method according to an embodiment of the present application;

[0034] FIG3 is a flow chart of another solar irradiance interval prediction method according to an embodiment of the present application;

[0035] FIG4 is a flow chart of a method for predicting solar irradiance intervals for a photovoltaic power station according to an embodiment of the present application;

[0036] FIG5 is a structural block diagram of a solar irradiance interval prediction device according to an embodiment of the present application;

[0037] FIG6 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0039] Accurate prediction of solar irradiance is the basis for evaluating power generation of power plants and ensuring power supply planning, as well as more efficient balancing of the power grid.

[0040] Therefore, the present invention provides a solar irradiance interval prediction method for photovoltaic power plants. By selecting target period retrieval conditions and using a target solar irradiance prediction model for prediction, the reliability and confidence of the prediction results can be increased.

[0041] According to an embodiment of the present application, an embodiment of a solar irradiance interval prediction method 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.

[0042] In this embodiment, a solar irradiance interval prediction method is provided, which can be used in a photovoltaic power station. FIG1 is a flow chart of the solar irradiance interval prediction method according to an embodiment of the present application. As shown in FIG1 , the process includes the following steps:

[0043] Step S101 : obtaining a historical environmental parameter dataset and a first environmental parameter dataset of a photovoltaic power station within a period to be predicted.

[0044] The historical environmental parameter dataset represents a collection of environmental parameters such as solar irradiance, temperature, and humidity collected by the photovoltaic power station during the historical collection period.

[0045] The first environmental parameter data set represents a set of environmental parameters collected by the photovoltaic power station during the period to be predicted, including solar irradiance, temperature, humidity, and the like.

[0046] Specifically, the historical environmental parameter data set includes several data sub-libraries storing environmental parameters of various categories, and each data sub-library corresponds to a category label.

[0047] A real-time environmental parameter data set is constructed based on the real-time environmental parameters collected by the photovoltaic power station, and the categories of various environmental parameters in the real-time environmental parameter data set are determined, such as temperature, humidity, wind speed, and irradiance.

[0048] Optionally, the real-time environmental parameter dataset is matched with the category labels of each data sub-library, and the environmental parameters whose environmental parameter categories in the real-time environmental parameter dataset fail to match the category labels of each data sub-library are marked as abnormal data and the abnormal data in the real-time environmental parameter dataset is deleted.

[0049] Finally, the real-time environmental parameter data set after deleting abnormal data is used as the first environmental parameter data set in the period to be predicted.

[0050] Step S102: Determine a first environmental sample data set based on the historical environmental parameter data set and the first environmental parameter data set.

[0051] The first environmental sample data set represents a set of environmental parameter data within a collection period that is similar to a historical collection period corresponding to the historical environmental parameter data set within the period to be predicted.

[0052] Step S103: establishing a target solar irradiance prediction model based on the first environmental sample data set.

[0053] Specifically, by using the first environmental sample data set to perform model training, a target solar irradiance prediction model that meets the conditions can be obtained.

[0054] Step S104: input the first environmental parameter data set into the target solar irradiance prediction model to obtain a solar irradiance prediction result within a period to be predicted.

[0055] Specifically, the first environmental parameter data set collected by the photovoltaic power station during the period to be predicted is input into the constructed target solar irradiance prediction model, and the solar irradiance prediction result during the corresponding period to be predicted can be output.

[0056] Step S105 , based on the first environmental sample data set, an autonomous sampling method is used to perform interval prediction on the solar irradiance prediction result within the prediction period to obtain a target solar irradiance interval prediction result within the prediction period.

[0057] Among them, autonomous sampling method refers to a method of continuous or discontinuous sample collection through a device according to a pre-established procedure without human intervention during the sampling process.

[0058] In this embodiment, the autonomous sampling method is used to perform interval prediction on the solar irradiance prediction results within the prediction period, and the distribution and parameters can be estimated directly from the first environmental sample data set, which effectively increases the reliability and confidence of the prediction results.

[0059] The solar irradiance interval prediction method provided in this embodiment selects the first environmental parameter dataset within the prediction period based on the historical environmental parameter dataset and uses the target solar irradiance prediction model to perform predictions. This method considers both the similarity and regularity of the historical data and the complexity and accuracy of the model. Optionally, an autonomous sampling method is used to perform interval predictions on the solar irradiance prediction results, effectively increasing the reliability and confidence of the prediction results.

[0060] In this embodiment, a solar irradiance interval prediction method is provided, which can be used in a photovoltaic power station. FIG2 is a flow chart of the solar irradiance interval prediction method according to an embodiment of the present application. As shown in FIG2 , the flow chart includes the following steps:

[0061] Step S201: Acquire a historical environmental parameter dataset and a first environmental parameter dataset of the photovoltaic power station within a period to be predicted. For details, refer to step S101 of the embodiment shown in FIG1 , which will not be described in detail here.

[0062] Step S202: Determine a first environmental sample data set based on the historical environmental parameter data set and the first environmental parameter data set.

[0063] Specifically, the above step S202 includes:

[0064] Step S2021: perform regression analysis based on the historical environmental parameter data set and construct a multiple linear regression function.

[0065] Among them, the multiple linear regression function reflects the relationship between environmental parameters and collection time.

[0066] Specifically, a regression analysis is performed with the collection time of each category of environmental parameters in several historical collection cycles in the historical environmental parameter data set as the independent variable, and the various categories of environmental parameters at different collection times in several historical collection cycles in the historical environmental parameter data set as the dependent variable. Based on the regression analysis results, a multiple linear regression function of the relationship between environmental parameters and collection time is constructed.

[0067] Step S2022: Determine a second environmental parameter data set based on a multiple linear regression function.

[0068] Specifically, a change trend curve of each category of environmental parameters that changes with time in the prediction period is established based on the multivariate linear regression function. The change trend curve of each category of environmental parameters uses the acquisition time as the horizontal coordinate and the environmental parameters of each type as the vertical coordinate. The environmental parameters of each type at different acquisition times in the change trend curve of each category of environmental parameters are used as the second environmental parameter data set.

[0069] Step S2023: Determine a first environmental sample data set based on the historical environmental parameter data set and the second environmental parameter data set.

[0070] Specifically, the second environmental parameter data set is used as a condition for determining the first environmental sample data set. Optionally, the first environmental sample data set can be obtained from the historical environmental parameter data set according to the condition.

[0071] In some optional implementations, step S2023 includes:

[0072] Step a1: calculating the Mahalanobis distance between the historical environmental parameter data corresponding to each preset collection time in the historical environmental parameter data set and the second environmental parameter data corresponding to the preset collection time in the second environmental parameter data set.

[0073] Step a2: determining a target period based on each Mahalanobis distance.

[0074] Step a3: Based on the target period, determine a first environmental sample data set in the historical environmental parameter data set.

[0075] Specifically, for each category of environmental parameter values ​​in the historical environmental parameter dataset, the Mahalanobis distance between the environmental parameter value and the corresponding environmental parameter value in the second environmental parameter dataset within the same acquisition time is obtained.

[0076] Then, the Mahalanobis distance values ​​of all categories of environmental parameters in each historical collection period in the historical environmental parameter dataset are accumulated to obtain the Mahalanobis total distance, and the historical collection period with the smallest Mahalanobis total distance is selected as the similar period, that is, the target period.

[0077] Finally, the environmental parameter data corresponding to the target period is selected from the historical environmental parameter data set as the first environmental sample data set.

[0078] Step S203: establishing a target solar irradiance prediction model based on the first environmental sample data set.

[0079] Specifically, the above step S203 includes:

[0080] Step S2031 : determining a first environment sample data subset and a second environment sample data subset based on the first environment sample data set.

[0081] Specifically, the first environment sample data set is divided into a first environment sample data subset and a second environment sample data subset, wherein the first environment sample data subset is used as a model training set, and the second environment sample data subset is used as a model testing set.

[0082] Step S2032: Input the first environmental sample data subset into a preset neural network for training to obtain an initial solar irradiance prediction model.

[0083] Specifically, a subset of environmental sample data is input into a preset neural network for training until the preset model loss function training is stable, an initial solar irradiance prediction model is output, and the model parameters of the initial solar irradiance prediction model are saved.

[0084] Step S2033: Verify the initial solar irradiance prediction model using the second environmental sample data subset to obtain a target solar irradiance prediction model.

[0085] Specifically, the second environmental sample data subset is used to perform similarity verification on the output data matrix of the initial solar irradiance prediction model after iterative training in step S2032. If the verification passes, the target solar irradiance prediction model is output.

[0086] If the verification fails, the model parameters are adjusted and retrained using the first environmental sample data subset until the output data matrix of the trained model can pass the similarity verification, and then the target solar irradiance prediction model is output.

[0087] Step S204: Input the first environmental parameter data set into the target solar irradiance prediction model to obtain the solar irradiance prediction result within the prediction period. For details, please refer to step S104 of the embodiment shown in FIG1 , which will not be described in detail here.

[0088] In step S205, based on the first environmental sample data set, an autonomous sampling method is used to perform interval prediction on the solar irradiance prediction results within the prediction period to obtain a target solar irradiance interval prediction result within the prediction period. For details, please refer to step S105 of the embodiment shown in FIG1 , which will not be repeated here.

[0089] The solar irradiance interval prediction method provided in this embodiment determines the second environmental parameter data set by constructing a multivariate linear regression function that reflects the relationship between the environmental parameters and the collection time, taking into account the similarity and regularity of historical data. Optionally, the target period and the first environmental sample data set are determined in combination with the Mahalanobis distance, taking into account the correlation between the various data features, and can effectively handle the problem of different measurement scales between different data features.

[0090] In this embodiment, a solar irradiance interval prediction method is provided, which can be used in a photovoltaic power station. FIG3 is a flow chart of the solar irradiance interval prediction method according to an embodiment of the present application. As shown in FIG3 , the process includes the following steps:

[0091] Step S301: Acquire a historical environmental parameter dataset and a first environmental parameter dataset of the photovoltaic power station within a period to be predicted. For details, refer to step S101 of the embodiment shown in FIG1 , which will not be described in detail here.

[0092] Step S302: Determine a first environmental sample dataset based on the historical environmental parameter dataset and the first environmental parameter dataset. For details, please refer to step S202 of the embodiment shown in FIG2 , which will not be described in detail here.

[0093] Step S303: Based on the first environmental sample data set, a target solar irradiance prediction model is established. For details, please refer to step S203 of the embodiment shown in FIG3 , which will not be described in detail here.

[0094] Step S304: Input the first environmental parameter data set into the target solar irradiance prediction model to obtain the solar irradiance prediction result within the prediction period. For details, please refer to step S104 of the embodiment shown in FIG1 , which will not be described in detail here.

[0095] Step S305 , based on the first environmental sample data set, an autonomous sampling method is used to perform interval prediction on the solar irradiance prediction result within the prediction period to obtain a target solar irradiance interval prediction result within the prediction period.

[0096] Specifically, the above step S305 includes:

[0097] Step S3051: Determine at least one second environmental sample data set from the first environmental sample data set using an autonomous sampling method.

[0098] Specifically, environmental parameters of various categories with similar periods but different collection times are used as sample data sets. The sampling size m and the number of sampling times k of the sample data set are determined. A sample of size m is randomly extracted from the sample data set with replacement, and this is repeated k times. Each sampled sample is marked as a Bootstrap sample, and finally k different Bootstrap samples are obtained; each Bootstrap sample is used as a second environmental sample data set.

[0099] Step S3052: Establish at least one target solar irradiance prediction model based on each second environment sample data set.

[0100] Specifically, by training each second environment sample data set, a target solar irradiance prediction model corresponding to each second environment sample data set can be established. The specific training process is described in detail in step S203 above and will not be repeated here.

[0101] Step S3053: input the first environmental parameter data set into each target solar irradiance prediction model respectively to obtain at least one solar irradiance prediction result.

[0102] Specifically, the first environmental parameter data set is input into each constructed target solar irradiance prediction model respectively, and the solar irradiance prediction result output by each target solar irradiance prediction model can be obtained.

[0103] Step S3054: Based on each solar irradiance prediction result and each preset interval prediction confidence value, determine at least one confidence interval range and at least one initial solar irradiance interval prediction result within the period to be predicted.

[0104] Among them, interval prediction means giving an interval estimate for the prediction of future or unknown data under a certain confidence level.

[0105] Specifically, by setting the preset interval prediction confidence value to different values, different confidence interval ranges can be obtained.

[0106] Optionally, different initial solar irradiance interval prediction results can be obtained according to different confidence interval ranges.

[0107] Step S3055: Determine the accuracy of each initial solar irradiance interval prediction result based on each confidence interval range.

[0108] Specifically, according to the description of step S3054, the initial solar irradiance interval prediction result represents an interval estimation result given for the prediction of the solar irradiance prediction result under a certain confidence level.

[0109] Therefore, the accuracy of the prediction results for each initial solar irradiance interval can be determined according to different confidence interval ranges.

[0110] Step S3056: Determine the target solar irradiance interval prediction result within the period to be predicted based on each accuracy and each initial solar irradiance interval prediction result.

[0111] Specifically, the initial solar irradiance interval prediction result with the highest accuracy is used as the target solar irradiance interval prediction result within the period to be predicted.

[0112] In some optional implementations, the above step S3054 includes:

[0113] Step b1: Obtain the number of samples in each second environment sample data set.

[0114] Step b2: determining the solar irradiance average value and the solar irradiance standard deviation based on each solar irradiance prediction result.

[0115] Step b3: determining at least one interval value based on the solar irradiance standard deviation, the prediction confidence value of each preset interval, and the number of each sample.

[0116] Step b4: determining the confidence interval range corresponding to each preset interval prediction confidence value based on each interval value and the average solar irradiance value.

[0117] Step b5: determining at least one initial solar irradiance interval prediction result within the period to be predicted based on each confidence interval range.

[0118] First, according to the description of step S3051, the number of samples in each second environment sample data set is k. Further, the k solar irradiance prediction results are sorted in descending order, and the solar irradiance average value v and the solar irradiance standard deviation s are calculated.

[0119] Next, the interval value is calculated using the following relationship (1):

[0120] Where: L represents the interval value; NORMSINV represents the inverse function of the standard normal distribution; Indicates the confidence value of the preset interval prediction; Indicates the confidence level.

[0121] Then, the confidence interval range corresponding to each preset interval prediction confidence value is determined to be: (vL, v+L).

[0122] Finally, the uncertainty of the estimate is quantified by the calculated confidence interval range, that is, an initial solar irradiance interval prediction result within the prediction period can be determined by each confidence interval range.

[0123] In some optional implementations, the above step S3055 includes:

[0124] Step c1, using a big data method to obtain the accuracy level of each solar irradiance interval prediction result corresponding to each confidence interval range.

[0125] Step c2: Establish an evaluation index matrix based on each accuracy level.

[0126] Step c3: establishing a solar irradiance matrix based on each solar irradiance prediction result.

[0127] Step c4: establishing a membership matrix based on the evaluation index matrix and the solar irradiance matrix.

[0128] Step c5: determining the accuracy of each initial solar irradiance interval prediction result based on the membership matrix and each solar irradiance prediction result.

[0129] First, the big data method is used to obtain the accuracy level of the solar irradiance interval prediction results corresponding to different confidence interval ranges, where the accuracy level can include 95%, 85%, 80%, and 75%.

[0130] Secondly, an evaluation index matrix for the accuracy of the prediction interval is established according to the accuracy levels corresponding to different confidence interval ranges, and a solar irradiance matrix is ​​established according to each solar irradiance prediction result predicted by the solar irradiance prediction model.

[0131] Then, the evaluation index matrix and the solar irradiance matrix are fused using the following relationship (2) to obtain the membership matrix that represents the fuzzy relationship between the solar irradiance prediction results predicted by the solar irradiance prediction model and the accuracy of the prediction interval: M = αM1 + βM2 (2)

[0132] Where: M represents the membership matrix; M1 represents the evaluation index matrix; M2 represents the solar irradiance matrix; α and β represent weighting parameters used to control the balance between the evaluation index matrix and the solar irradiance matrix in the membership matrix; “+” represents the addition of the elements at the corresponding positions of the evaluation index matrix and the solar irradiance matrix.

[0133] Finally, the corresponding confidence interval range can be determined based on each solar irradiance prediction result. Further, the accuracy of each initial solar irradiance interval prediction result can be determined in the membership matrix based on the confidence interval range.

[0134] The solar irradiance interval prediction method provided in this embodiment uses an autonomous sampling method to perform interval prediction on the solar irradiance prediction results. It does not require any assumptions about the original first environment sample data set, and can directly estimate the distribution and parameters from the first environment sample data set. The uncertainty of the estimate can be quantified by calculating the confidence interval range, effectively increasing the reliability and confidence of the prediction results.

[0135] In one example, a solar irradiance interval prediction method for a photovoltaic power station is provided, as shown in FIG4 , comprising the following steps:

[0136] Step S1: Acquire the real-time environmental parameters collected by the photovoltaic power station and mark the collection time, set the collection cycle, and perform data cleaning on the real-time environmental parameters based on the environmental parameter information in the historical database;

[0137] Step S2: Set similar cycle retrieval conditions according to the period to be predicted, extract sample data that meet the similar cycle retrieval conditions from the historical database, use the selected environmental parameters of each category of similar periods as input features and solar irradiance as output label to build a solar irradiance prediction model;

[0138] Step S3: Use the autonomous sampling method to perform interval prediction on the prediction results, and determine the accuracy of the prediction results based on the interval range of the prediction results.

[0139] Optionally, the process of performing data cleaning on the real-time environmental parameters according to the environmental parameter information in the historical database includes:

[0140] A real-time environmental parameter dataset is constructed based on the real-time environmental parameters collected by the photovoltaic power station, and the categories of each environmental parameter in the real-time environmental parameter dataset are determined; the historical database contains several data sub-databases that store environmental parameters of each category, and a category label is generated for each data sub-database; the real-time environmental parameter dataset is matched with the category label of each data sub-database, and the environmental parameters whose environmental parameter categories in the real-time environmental parameter dataset fail to match the category labels of each data sub-database are marked as abnormal data and the abnormal data in the real-time environmental parameter dataset are deleted.

[0141] Optionally, the process of setting a similar cycle retrieval condition according to the cycle to be predicted includes:

[0142] The collection time of each category of environmental parameters in several historical collection cycles of the historical database is used as the independent variable, and the various categories of environmental parameters at different collection times in several historical collection cycles of the historical database are used as the dependent variables for regression analysis. A multiple linear regression function is constructed to represent the relationship between environmental parameters and collection time. Based on the multiple linear regression function, a trend curve of each category of environmental parameters changing with time in the predicted period is established. The trend curve of each category of environmental parameters takes the collection time as the horizontal coordinate and the various types of environmental parameters as the vertical coordinate. The various types of environmental parameters at different collection times in the trend curve of each category of environmental parameters are used as similar period retrieval conditions.

[0143] Optionally, the process of extracting sample data that meets the similar period search condition from the historical database includes:

[0144] Determine the environmental parameter values ​​of each category at different collection times in the similar period retrieval condition, obtain the environmental parameter values ​​of each category at different collection times in several historical collection periods in the historical database, calculate the Mahalanobis distance between each category of environmental parameter value in the historical collection period and the corresponding environmental parameter value in the same collection time in the similar period retrieval condition, accumulate the Mahalanobis distance values ​​of all categories of environmental parameters in each historical collection period to obtain the Mahalanobis total distance, and select the historical collection period with the smallest Mahalanobis total distance as the similar period.

[0145] Optionally, the process of constructing a solar irradiance prediction model using the selected environmental parameters of each category in a similar period as input features and solar irradiance as output label includes:

[0146] A solar irradiance prediction model is constructed based on the RBN neural network. A historical data set is constructed according to the values ​​of various environmental parameters at different collection times in similar cycles. The historical data set is divided into a training set and a test set. The solar irradiance prediction model is trained in real time using the training set until the loss function of the solar irradiance prediction model is stable and the model parameters are saved. The output data matrix of the iteratively trained solar irradiance prediction model is then similarity verified using the test set. In the process of establishing the solar irradiance prediction model, environmental parameters include temperature, humidity, wind speed, irradiance and other parameters. 1,000 sets of data information on temperature, humidity, wind speed and irradiance in historical collection cycles are obtained. 950 sets of data are used as training sets and 50 sets of data are used as test sets to train the solar irradiance prediction model until the training is qualified.

[0147] The environmental parameters of various categories at different collection times in the period to be predicted are input into the solar irradiance prediction model verified by the test set, and the solar irradiance at different collection times in the period to be predicted is obtained according to the output layer of the solar irradiance prediction model.

[0148] Optionally, the process of performing interval prediction on the prediction results using the autonomous sampling method includes:

[0149] The environmental parameters of various categories with similar periods and different collection times are used as sample data sets, and the sampling size m and the number of extractions k of the sample data set are determined. A sample of size m is randomly extracted from the sample data set with replacement, and repeated k times. Each sampled sample is marked as a Bootstrap sample, and finally k different Bootstrap samples are obtained; each Bootstrap sample is used as a training set, and k solar irradiance prediction models are established according to the solar irradiance prediction model construction method. The environmental parameters of various categories with different collection times in the prediction period are input into the k solar irradiance prediction models to obtain k solar irradiance prediction results, and the k solar irradiance prediction results are sorted in order of solar irradiance from large to small, and the solar irradiance mean v and solar irradiance standard deviation s of the k solar irradiance prediction results are calculated to determine the interval prediction confidence. According to confidence The solar irradiance standard deviation s and the number of samples k determine the interval value L, and the confidence level is determined based on the interval value L and the solar irradiance mean v. By setting the confidence level to different values, you can get intervals with different confidence levels.

[0150] The interval value L and the confidence level For the specific process of the interval range, please refer to the description of step b5 above.

[0151] Optionally, the process of determining the accuracy of the prediction result according to the interval range of the prediction result includes:

[0152] The big data method is used to obtain the accuracy level of solar irradiance prediction results corresponding to different confidence intervals, including 95%, 85%, 80%, and 75%;

[0153] An evaluation index matrix for the accuracy of the prediction interval is established according to the accuracy levels corresponding to the interval ranges of different confidence levels, and a solar irradiance matrix is ​​established according to the solar irradiance predicted by the solar irradiance prediction model. A membership matrix representing the fuzzy relationship between the solar irradiance predicted by the solar irradiance prediction model and the accuracy of the prediction result is established according to the evaluation index matrix and the solar irradiance matrix. The specific process refers to the above-mentioned relationship (2); the accuracy of the predicted solar irradiance of the period to be predicted is obtained according to the membership matrix and the solar irradiance predicted by the solar irradiance prediction model.

[0154] In this embodiment, a solar irradiance interval prediction device is also provided, which is used to implement the above-mentioned embodiments and optional implementation methods. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

[0155] This embodiment provides a solar irradiance interval prediction device for a photovoltaic power station, as shown in FIG5 , including:

[0156] The acquisition module 501 is configured to acquire a historical environmental parameter dataset and a first environmental parameter dataset of a photovoltaic power station within a period to be predicted.

[0157] The determination module 502 is configured to determine a first environmental sample data set based on the historical environmental parameter data set and the first environmental parameter data set.

[0158] Establishing module 503, for establishing a target solar irradiance prediction model based on the first environmental sample data set;

[0159] The input module 504 is configured to input the first environmental parameter data set into the target solar irradiance prediction model to obtain a solar irradiance prediction result within a period to be predicted.

[0160] The prediction module 505 is used to perform interval prediction on the solar irradiance prediction result within the prediction period using the autonomous sampling method based on the first environmental sample data set to obtain the target solar irradiance interval prediction result within the prediction period.

[0161] In some optional implementations, the determining module 502 includes:

[0162] The analysis and construction unit is used to perform regression analysis based on the historical environmental parameter data set and construct a multiple linear regression function, which reflects the relationship between the environmental parameters and the collection time.

[0163] The first determining unit is configured to determine a second environmental parameter data set based on a multiple linear regression function.

[0164] The second determining unit is configured to determine the first environmental sample data set based on the historical environmental parameter data set and the second environmental parameter data set.

[0165] In some optional implementations, the second determining unit includes:

[0166] The calculation subunit is used to calculate the Mahalanobis distance between the historical environmental parameter data corresponding to each preset collection time in the historical environmental parameter data set and the second environmental parameter data corresponding to the preset collection time in the second environmental parameter data set.

[0167] The first determining subunit is configured to determine a target period based on each Mahalanobis distance.

[0168] The second determining subunit is configured to determine a first environmental sample data set in the historical environmental parameter data set based on a target period.

[0169] In some optional implementations, the establishing module 503 includes:

[0170] The third determining unit is configured to determine a first environment sample data subset and a second environment sample data subset based on the first environment sample data set.

[0171] The first input unit is used to input the first environmental sample data subset into a preset neural network for training to obtain an initial solar irradiance prediction model.

[0172] The verification unit is used to verify the initial solar irradiance prediction model using the second environmental sample data subset to obtain a target solar irradiance prediction model.

[0173] In some optional implementations, the prediction module 505 includes:

[0174] The fourth determining unit is configured to determine at least one second environmental sample data set from the first environmental sample data set by using an autonomous sampling method.

[0175] The establishing unit is configured to establish at least one target solar irradiance prediction model based on each second environment sample data set.

[0176] The second input unit is used to input the first environmental parameter data set into each target solar irradiance prediction model to obtain at least one solar irradiance prediction result.

[0177] The fifth determining unit is used to determine at least one confidence interval range and at least one initial solar irradiance interval prediction result within the period to be predicted based on each solar irradiance prediction result and each preset interval prediction confidence value.

[0178] The sixth determining unit is configured to determine the accuracy of each initial solar irradiance interval prediction result based on each confidence interval range.

[0179] The seventh determining unit is configured to determine a target solar irradiance interval prediction result within a period to be predicted based on each accuracy and each initial solar irradiance interval prediction result.

[0180] In some optional implementations, the fifth determining unit includes:

[0181] The first acquisition subunit is used to obtain the number of samples in each second environment sample data set.

[0182] The third determining subunit is configured to determine an average solar irradiance value and a standard deviation of the solar irradiance based on each solar irradiance prediction result.

[0183] The fourth determining subunit is configured to determine at least one interval value based on the solar irradiance standard deviation, each preset interval prediction confidence value, and each sample number.

[0184] The fifth determining subunit is configured to determine a confidence interval range corresponding to each preset interval prediction confidence value based on each interval value and the average solar irradiance value.

[0185] The sixth determining subunit is configured to determine at least one initial solar irradiance interval prediction result within the period to be predicted based on each confidence interval range.

[0186] In some optional implementations, the sixth determining unit includes:

[0187] The second acquisition subunit is used to obtain the accuracy level of each solar irradiance interval prediction result corresponding to each confidence interval range by using a big data method.

[0188] The first establishing subunit is used to establish an evaluation index matrix based on each accuracy level.

[0189] The second establishing subunit is used to establish a solar irradiance matrix based on each solar irradiance prediction result.

[0190] The third establishing subunit is used to establish a membership matrix based on the evaluation index matrix and the solar irradiance matrix.

[0191] The seventh determining subunit is configured to determine the accuracy of each initial solar irradiance interval prediction result based on the membership matrix and each solar irradiance prediction result.

[0192] 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.

[0193] The solar irradiance interval 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.

[0194] An embodiment of the present application also provides a computer device having the solar irradiance interval prediction device shown in FIG5 above.

[0195] Please refer to Figure 6, which is a structural diagram of a computer device provided by an optional embodiment of the present application. As shown in Figure 6, 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. The various components are connected to each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in or on the memory to display graphical information of a 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 6 takes a processor 10 as an example.

[0196] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may also optionally include a hardware chip. The hardware chip may be an application-specific 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.

[0197] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0198] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on 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 located 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.

[0199] 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.

[0200] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0201] The embodiments of the present application also provide a computer-readable storage medium. The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, 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 drive, etc.; optionally, the storage medium can also include a combination of the above-mentioned types of memory. 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.

[0202] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

Claims

1. A solar irradiance interval prediction method for a photovoltaic power station; characterized in that: The method comprises: Acquire a historical environmental parameter data set and a first environmental parameter data set of the photovoltaic power station within a period to be predicted; Determine a first environmental sample data set based on the historical environmental parameter data set and the first environmental parameter data set; Based on the first environmental sample data set, establishing a target solar irradiance prediction model; Inputting the first environmental parameter data set into the target solar irradiance prediction model to obtain a solar irradiance prediction result within the period to be predicted; Based on the first environmental sample data set, an autonomous sampling method is used to perform interval prediction on the solar irradiance prediction result within the period to be predicted, so as to obtain a target solar irradiance interval prediction result within the period to be predicted.

2. The method according to claim 1, characterized in that Determining a first environmental sample data set based on the historical environmental parameter data set and the first environmental parameter data set includes: Performing regression analysis based on the historical environmental parameter data set and constructing a multiple linear regression function, wherein the multiple linear regression function reflects the relationship between the environmental parameter and the collection time; Determining a second environmental parameter data set based on the multivariate linear regression function; The first environmental sample data set is determined based on the historical environmental parameter data set and the second environmental parameter data set.

3. The method according to claim 2, characterized in that Determining the first environmental sample data set based on the historical environmental parameter data set and the second environmental parameter data set includes: Calculate the Mahalanobis distance between the historical environmental parameter data corresponding to each preset collection time in the historical environmental parameter data set and the second environmental parameter data corresponding to the preset collection time in the second environmental parameter data set; determining a target period based on each of the Mahalanobis distances; Based on the target period, the first environmental sample data set is determined in the historical environmental parameter data set.

4. The method according to claim 1, characterized in that: Based on the first environmental sample data set, a target solar irradiance prediction model is established, including: Determine a first environment sample data subset and a second environment sample data subset based on the first environment sample data set; Inputting the first environmental sample data subset into a preset neural network for training to obtain an initial solar irradiance prediction model; The initial solar irradiance prediction model is verified using the second environmental sample data subset to obtain the target solar irradiance prediction model.

5. The method according to claim 1, characterized in that Based on the first environmental sample data set, an interval prediction is performed on the solar irradiance prediction result within the period to be predicted using an autonomous sampling method to obtain a target solar irradiance interval prediction result within the period to be predicted, including: Determine at least one second environmental sample data set in the first environmental sample data set by using an autonomous sampling method; Based on each of the second environment sample data sets, establishing at least one target solar irradiance prediction model; Inputting the first environmental parameter data set into each of the target solar irradiance prediction models respectively to obtain at least one solar irradiance prediction result; Based on each of the solar irradiance prediction results and each preset interval prediction confidence value, determine at least one confidence interval range and at least one initial solar irradiance interval prediction result within the period to be predicted; Determining the accuracy of each of the initial solar irradiance interval prediction results based on each of the confidence interval ranges; Based on each of the accuracies and each of the initial solar irradiance interval prediction results, the target solar irradiance interval prediction result within the period to be predicted is determined.

6. The method according to claim 5, characterized in that Based on each of the solar irradiance prediction results and each preset interval prediction confidence value, determining at least one confidence interval range and at least one initial solar irradiance interval prediction result within the period to be predicted, including: Obtaining the number of samples of each of the second environment sample data sets; Based on each of the solar irradiance prediction results, determine the solar irradiance average value and the solar irradiance standard deviation; Determine at least one interval value based on the solar irradiance standard deviation, each of the preset interval prediction confidence values ​​and each of the sample numbers; Determine the confidence interval range corresponding to each of the preset interval prediction confidence values ​​based on each of the interval values ​​and the average solar irradiance value; At least one initial solar irradiance interval prediction result within the period to be predicted is determined based on each of the confidence interval ranges.

7. The method according to claim 5, characterized in that Determining the accuracy of each of the initial solar irradiance interval prediction results based on each of the confidence interval ranges includes: Using big data methods to obtain the accuracy level of each solar irradiance interval prediction result corresponding to each confidence interval range; Establishing an evaluation index matrix based on each of the accuracy levels; Establishing a solar irradiance matrix based on each of the solar irradiance prediction results; Establishing a membership matrix based on the evaluation index matrix and the solar irradiance matrix; The accuracy of each of the initial solar irradiance interval prediction results is determined based on the membership matrix and each of the solar irradiance prediction results.

8. A solar irradiance interval prediction device for a photovoltaic power station; characterized in that: The device comprises: An acquisition module, used to acquire a historical environmental parameter data set and a first environmental parameter data set of the photovoltaic power station within a period to be predicted; A determination module, configured to determine a first environmental sample data set based on the historical environmental parameter data set and the first environmental parameter data set; An establishing module, used to establish a target solar irradiance prediction model based on the first environmental sample data set; An input module, used for inputting the first environmental parameter data set into the target solar irradiance prediction model to obtain a solar irradiance prediction result within the period to be predicted; A prediction module is used to perform interval prediction on the solar irradiance prediction result within the period to be predicted based on the first environmental sample data set by using an autonomous sampling method to obtain a target solar irradiance interval prediction result within the period to be predicted.

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 solar irradiance interval prediction method according to any one of claims 1 to 7 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 solar irradiance interval prediction method according to any one of claims 1 to 7.

Images