Photovoltaic data processing method and device, equipment and medium

Abstract

The invention discloses a photovoltaic data processing method and device, equipment and a medium, and relates to the technical field of new energy power generation. According to the embodiment of the invention, the first matching degree of the photovoltaic power and the irradiance is determined for each historical time point, and the first matching degree can reflect the matching relation between the photovoltaic power and the irradiance, namely, the matching relation between the photovoltaic power and the irradiance is fully considered when the abnormal photovoltaic data is identified, so that the identification accuracy of the abnormal photovoltaic data is improved. The method can accurately recognize the data with the photovoltaic power not matched with the irradiance, and improves the accuracy of the recognition result. Besides, according to the embodiment of the invention, the abnormal data can be corrected according to the first matching degree of the photovoltaic data in the preset time period, the data quality of the photovoltaic data is improved, the prediction effect of the model can be improved when the photovoltaic power prediction model is trained based on the photovoltaic data subsequently, and the prediction efficiency of the photovoltaic power prediction model is improved. And the accuracy of a photovoltaic power prediction result can be improved.

Description

Technical Field

[0001] The present application relates to the field of renewable energy power generation technology, and in particular to a method, device, equipment and medium for processing photovoltaic data. Background Art

[0002] In recent years, the proportion of renewable energy power generation has continued to increase, among which the installed capacity of photovoltaic power generation has increased significantly. Photovoltaic power generation is volatile and random. In order to cope with this uncertainty, reduce the difficulty of grid dispatching, and improve the stability of grid connection, it is necessary to predict photovoltaic power at different time periods.

[0003] At present, photovoltaic power prediction models are mainly used to predict photovoltaic power of different durations. The prediction effect of photovoltaic power prediction models is related to the data quality of photovoltaic data used in model training.

[0004] Due to reasons such as dust blocking photovoltaic panels and power rationing in electric fields, photovoltaic data are easily abnormal, and these abnormal data are usually mixed with normal data. If these photovoltaic data are directly used to train the photovoltaic power prediction model, it is easy to lead to a decrease in the prediction accuracy of the photovoltaic power prediction model, which will in turn have an adverse impact on power grid scheduling. Summary of the invention

[0005] The embodiments of the present application provide a photovoltaic data processing method, device, equipment and medium, which can not only accurately identify abnormal data in photovoltaic data, but also correct the abnormal data.

[0006] In a first aspect, an embodiment of the present application provides a method for processing photovoltaic data, comprising:

[0007] Obtain photovoltaic data of the photovoltaic electric field at N historical time points, the photovoltaic data including irradiance and photovoltaic power corresponding to the irradiance, where N is an integer greater than 1;

[0008] For each historical time point, determining a first matching degree between photovoltaic power and irradiance;

[0009] Determine abnormal data from each photovoltaic data according to the first matching degree of each historical time point;

[0010] According to the first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain the target data.

[0011] In some embodiments, the abnormal data includes first abnormal data and second abnormal data, and the abnormal data is determined from each photovoltaic data according to the first matching degree of each historical time point, including:

[0012] When the first matching degree does not belong to the first reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as the first abnormal data;

[0013] Determine photovoltaic data other than first abnormal data from each photovoltaic data to obtain first photovoltaic data;

[0014] For a preset time window, determining a difference index of each first photovoltaic data in the preset time window;

[0015] When the difference index is smaller than the reference index, all the first photovoltaic data within the preset time window are determined as second abnormal data.

[0016] In some embodiments, determining the difference index of each first photovoltaic data in a preset time window includes:

[0017] Determine the maximum value and the minimum value of each first photovoltaic data from the preset time window;

[0018] The difference between the maximum value and the minimum value is determined as a difference index of each first photovoltaic data in the preset time window.

[0019] In some embodiments, determining abnormal data from each photovoltaic data according to the first matching degree of each historical time point includes:

[0020] Determine a non-zero first matching degree from each first matching degree, and add each non-zero first matching degree to a first set;

[0021] Determine a first quantile and a second quantile of the first set according to each first matching degree in the first set, wherein the first quantile is smaller than the second quantile;

[0022] Determine a second reference matching degree interval according to the first quantile and the second quantile, and the quantile distance between the first quantile and the second quantile;

[0023] For each first matching degree in the first set, when the first matching degree does not belong to the second reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as abnormal data.

[0024] In some embodiments, determining abnormal data from each photovoltaic data according to the first matching degree of each historical time point includes:

[0025] Determine a non-zero first matching degree from each first matching degree, and add each non-zero first matching degree to a first set;

[0026] Determine the mean and standard deviation of each first matching degree in the first set;

[0027] Determine a third reference matching interval according to the mean and the standard deviation;

[0028] For each first matching degree in the first set, when the first matching degree does not belong to the third reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as abnormal data.

[0029] In some embodiments, the abnormal data includes abnormal power;

[0030] According to the first matching degree of each historical time point, abnormal data is determined from each photovoltaic data, including:

[0031] The historical time points corresponding to each photovoltaic data are divided into M time periods, where M is a positive integer;

[0032] For each time period, determine the third quantile, the fourth quantile and the fifth quantile of the first matching degree corresponding to each photovoltaic data in the time period, and the third quantile, the fourth quantile and the fifth quantile decrease in sequence;

[0033] According to the third quantile and the fourth quantile, the fourth quantile and the fifth quantile, and the irradiance at each historical time point in the time period, the power reference interval of the corresponding photovoltaic power at the corresponding historical time point is determined respectively;

[0034] When the photovoltaic power at the corresponding historical time point does not belong to the power reference interval at the corresponding historical time point, the photovoltaic power at the corresponding historical time point is determined as abnormal power.

[0035] In some embodiments, the abnormal data includes abnormal power;

[0036] According to the first matching degree of the photovoltaic data within the preset time period, the abnormal data is corrected to obtain the target data, including:

[0037] The historical time points corresponding to each photovoltaic data are divided into P time periods, where P is a positive integer;

[0038] For each time period, determine the sixth quantile and the seventh quantile of the first matching degree corresponding to each photovoltaic data in the time period, and the sixth quantile is less than the seventh quantile;

[0039] Determine at least one third matching degree from each first match, the third matching degree belonging to a fourth reference matching degree interval formed by a sixth quantile and a seventh quantile;

[0040] The abnormal power is replaced by the product of the mean value of each third matching degree and the irradiance corresponding to the abnormal power to obtain the target power.

[0041] In some embodiments, determining a first matching degree between photovoltaic power and irradiance includes:

[0042] Determine the ratio of photovoltaic power to irradiance;

[0043] The ratio is determined as a first matching degree of photovoltaic power to irradiance.

[0044] In a second aspect, an embodiment of the present application provides a photovoltaic data processing device, including: an acquisition module, a determination module, and a correction module;

[0045] An acquisition module is used to acquire photovoltaic data of the photovoltaic electric field at N historical time points, where the photovoltaic data includes irradiance and photovoltaic power corresponding to the irradiance, and N is an integer greater than 1;

[0046] A determination module, for determining a first matching degree between photovoltaic power and irradiance at each historical time point;

[0047] The determination module is further used to determine abnormal data from each photovoltaic data according to the first matching degree of each historical time point;

[0048] The correction module is used to correct the abnormal data according to the first matching degree of the photovoltaic data within a preset time period to obtain the target data.

[0049] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0050] processor;

[0051] a memory for storing computer program instructions;

[0052] When the computer program instructions are executed by the processor, the method according to the first aspect is implemented.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method described in the first aspect is implemented.

[0054] The embodiment of the present application obtains photovoltaic data of the photovoltaic electric field at N historical time points, and the photovoltaic data includes irradiance and photovoltaic power corresponding to the irradiance, where N is an integer greater than 1; for each historical time point, the first matching degree of photovoltaic power and irradiance is determined; according to the first matching degree of each historical time point, abnormal data is determined from each photovoltaic data; according to the first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain the target data. Because the first matching degree can reflect the matching relationship between irradiance and photovoltaic power, that is, when identifying abnormal photovoltaic data, the embodiment of the present application fully considers the matching relationship between irradiance and photovoltaic power, so that the data that does not match irradiance and photovoltaic power can be accurately identified, and the accuracy of the identification result is improved. In addition, the embodiment of the present application can also correct the abnormal data according to the first matching degree of photovoltaic data within a preset time period, improve the data quality of photovoltaic data, so that when the photovoltaic power prediction model is subsequently trained based on photovoltaic data, the prediction effect of the model can be improved, and then the accuracy of the photovoltaic power prediction result can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The features, advantages and technical effects of exemplary embodiments of the present application will be described below with reference to the accompanying drawings.

[0056] Figure 1 A flowchart of a photovoltaic data processing method provided in an embodiment of the present application;

[0057] Figure 2 A scatter diagram of irradiance and photovoltaic power provided in an embodiment of the present application;

[0058] Figure 3 A flowchart of another photovoltaic data processing method provided in an embodiment of the present application;

[0059] Figure 4 A schematic diagram of abnormal data identified based on the straight line method provided in an embodiment of the present application;

[0060] Figure 5 A flowchart of another photovoltaic data processing method provided in an embodiment of the present application;

[0061] Figure 6 A schematic diagram of abnormal data identified based on the quartile method provided in an embodiment of the present application;

[0062] Figure 7 A flowchart of another photovoltaic data processing method provided in an embodiment of the present application;

[0063] Figure 8 A schematic diagram of abnormal data identified based on the standard deviation method provided in an embodiment of the present application;

[0064] Fig. 9 A flowchart of another photovoltaic data processing method provided in an embodiment of the present application;

[0065] Fig.10 A schematic diagram of abnormal data identified based on a segmentation method provided in an embodiment of the present application;

[0066] Fig.11 A flowchart of another photovoltaic data processing method provided in an embodiment of the present application;

[0067] Fig.12 A schematic diagram of corrected abnormal data provided in an embodiment of the present application;

[0068] Fig.13 A structural diagram of a photovoltaic data processing device provided in an embodiment of the present application;

[0069] Fig.14 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In the detailed description below, many specific details are proposed to provide a comprehensive understanding of the present application. However, it is obvious to those skilled in the art that the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating examples of the present application. In the accompanying drawings and the following description, at least some of the known structures and technologies are not shown to avoid unnecessary ambiguity in the present application; and, for clarity, the size of some structures may be exaggerated. In addition, the features, structures or characteristics described below may be combined in one or more embodiments in any suitable manner.

[0071] The directional words appearing in the following description are all directions shown in the figures, and do not limit the specific structure of the guyed tower and wind turbine generator set of this application. In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "installation" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to the specific circumstances.

[0072] In recent years, the proportion of renewable energy power generation has continued to increase, among which the installed capacity of photovoltaic power generation has increased significantly. Photovoltaic power generation is volatile and random. In order to cope with this uncertainty, reduce the difficulty of grid dispatching, and improve the stability of grid connection, it is necessary to predict photovoltaic power at different time periods.

[0073] At present, photovoltaic power prediction models are mainly used to predict photovoltaic power of different durations. The prediction effect of photovoltaic power prediction models is related to the data quality of photovoltaic data used in model training.

[0074] Due to reasons such as dust blocking photovoltaic panels and power rationing in electric fields, photovoltaic data are easily abnormal, and these abnormal data are usually mixed with normal data. If these photovoltaic data are directly used to train the photovoltaic power prediction model, it is easy to lead to a decrease in the prediction accuracy of the photovoltaic power prediction model, which will in turn have an adverse impact on power grid scheduling.

[0075] In response to the above problems, the relevant technology currently mainly identifies abnormal data in photovoltaic data through certain technical means. Regarding the abnormal data, no relevant correction plan is currently provided. Moreover, when identifying abnormal data, the relevant technology ignores the correlation between irradiance and photovoltaic power, resulting in low accuracy of the identified abnormal data.

[0076] To this end, the embodiments of the present application provide a method, device, equipment and medium for processing photovoltaic data, which can not only accurately identify abnormal data in photovoltaic data, but also correct the abnormal data.

[0077] The photovoltaic data processing method, device, equipment and medium provided in the embodiments of the present application are described in detail below through specific embodiments.

[0078] Figure 1 A flowchart of a photovoltaic data processing method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the photovoltaic data processing method may include the following steps:

[0079] S110, obtaining photovoltaic data of the photovoltaic electric field at N historical time points.

[0080] The photovoltaic data includes irradiance and photovoltaic power corresponding to the irradiance, and N is an integer greater than 1.

[0081] S120: For each historical time point, determine a first matching degree between photovoltaic power and irradiance.

[0082] S130 . Determine abnormal data from each photovoltaic data according to the first matching degree of each historical time point.

[0083] S140: According to a first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain target data.

[0084] The embodiment of the present application obtains photovoltaic data of the photovoltaic electric field at N historical time points, and the photovoltaic data includes irradiance and photovoltaic power corresponding to the irradiance, where N is an integer greater than 1; for each historical time point, the first matching degree of photovoltaic power and irradiance is determined; according to the first matching degree of each historical time point, abnormal data is determined from each photovoltaic data; according to the first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain the target data. Because the first matching degree can reflect the matching relationship between irradiance and photovoltaic power, that is, when identifying abnormal photovoltaic data, the embodiment of the present application fully considers the matching relationship between irradiance and photovoltaic power, so that the data that does not match irradiance and photovoltaic power can be accurately identified, and the accuracy of the identification result is improved. In addition, the embodiment of the present application can also correct the abnormal data according to the first matching degree of photovoltaic data within a preset time period, improve the data quality of photovoltaic data, so that when the photovoltaic power prediction model is subsequently trained based on photovoltaic data, the prediction effect of the model can be improved, and then the accuracy of the photovoltaic power prediction result can be improved.

[0085] The above steps are described in detail below:

[0086] In S110 , the photovoltaic data here are measured data of the photovoltaic electric field at a historical time point. Exemplarily, the photovoltaic data may include irradiance and photovoltaic power corresponding to the irradiance.

[0087] For example, the photovoltaic data of the photovoltaic field at each historical time point can be obtained, and the photovoltaic data can be arranged in chronological order to facilitate the subsequent identification of abnormal photovoltaic data. Among them, the photovoltaic data at each historical time point is not empty, that is, photovoltaic data exists at each historical time point.

[0088] In S120 , the first matching degree is used to characterize the correlation between photovoltaic power and irradiance.

[0089] Exemplarily, a ratio of photovoltaic power to irradiance may be determined, and the ratio may be determined as a first matching degree of photovoltaic power to irradiance.

[0090] That is, for each historical time point, the ratio of the photovoltaic power to the corresponding irradiance at the historical time point can be determined to obtain the first matching degree of the photovoltaic electric field at the historical time point. Table 1 exemplarily lists the irradiance, photovoltaic power and first matching degree corresponding to some historical time points, where the K value represents the first matching degree.

[0091] Table 1 Irradiance, photovoltaic power and first matching degree corresponding to some historical time points

[0092]

[0093]

[0094] Based on the irradiance and photovoltaic power at each historical time point, we can get Figure 2 The scattered points shown. The horizontal axis represents irradiance and the vertical axis represents photovoltaic power.

[0095] The embodiment of the present application utilizes the correlation between photovoltaic power and irradiance to determine whether the photovoltaic data at each historical time point is abnormal, and is capable of identifying data where the irradiance does not match the photovoltaic power, thereby improving the accuracy of abnormal data identification results.

[0096] In S130 , it may be determined whether each photovoltaic data is abnormal based on the first matching degree of each historical time point.

[0097] The abnormal data here may be data indicating that the irradiance does not match the corresponding photovoltaic power, for example, it may include abnormal irradiance, abnormal photovoltaic power, or abnormal irradiance and photovoltaic power.

[0098] The present application determines whether each photovoltaic data is abnormal based on the first matching degree at each historical time point, and fully considers the correlation between irradiance and photovoltaic power, so as to improve the accuracy of abnormal data judgment results.

[0099] Exemplarily, data in which the first matching degree is a negative value, that is, data in which the irradiance is a negative value or the photovoltaic power is a negative value, is determined to be abnormal data.

[0100] Exemplarily, when the first matching degree is infinite, that is, the irradiance is 0, the data where the photovoltaic power is not 0 is determined to be abnormal data.

[0101] Exemplarily, when the first matching degree is 0, that is, the data when the irradiance is not 0 and the photovoltaic power is 0 is determined to be abnormal data.

[0102] Exemplarily, data indicating that photovoltaic power is greater than installed capacity may be determined as abnormal data.

[0103] For example, when the irradiance is low, for example, less than 200 W / m 3 When the irradiance is low, the photovoltaic power cannot reach the installed capacity. At this time, if the first matching degree is greater than the installed capacity / 200, it means that the photovoltaic power is obviously too high. In this case, the corresponding photovoltaic power can be determined as abnormal data.

[0104] For example, when the irradiance reaches the rated absorbed irradiance of the photovoltaic panel, the rated absorbed irradiance is generally lower than 1800W / m 3 When the photovoltaic power is close to the installed capacity, if the first matching degree is less than the installed capacity / 1800, it means that the photovoltaic power is obviously low. At this time, the corresponding photovoltaic power can be determined as abnormal data.

[0105] Of course, other methods, such as statistical methods such as the quartile method and the standard deviation method, may also be used in combination with the first matching degree to determine whether the photovoltaic data at each historical time point is abnormal, which is not limited in the embodiment of the present application.

[0106] In S140 , when it is determined that the photovoltaic data is abnormal, the abnormal data may be corrected according to the first matching degree of the photovoltaic data within a preset time period to obtain the target data.

[0107] In particular, when there is less historical photovoltaic data in the photovoltaic field, by correcting the abnormal data to normal data, it can be ensured that the amount of training data for the photovoltaic power prediction model will not be unable to be trained due to too much abnormal data being removed, thereby ensuring the stability of the model. The correction process for abnormal data can be referred to in the following embodiment.

[0108] The photovoltaic data actually obtained may include night data, that is, the irradiance and photovoltaic power are both 0. This part of the data is normal data. In order to avoid the impact of this part of the data on abnormal data, the night data can be deleted from the obtained photovoltaic data first, that is, the embodiment of the present application only identifies abnormalities in the photovoltaic data during the day.

[0109] The abnormal data identification process is described below through a specific embodiment.

[0110] Take the example that the abnormal data includes the first abnormal data and the second abnormal data. Figure 3 As shown, the photovoltaic data processing method may include the following steps:

[0111] S310, obtaining photovoltaic data of the photovoltaic field at N historical time points.

[0112] S320: For each historical time point, determine a first matching degree between photovoltaic power and irradiance.

[0113] S330: When the first matching degree does not belong to the first reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as first abnormal data.

[0114] S340 , determining photovoltaic data other than first abnormal data from each photovoltaic data to obtain first photovoltaic data.

[0115] S350: for a preset time window, determine a difference index of each first photovoltaic data in the preset time window.

[0116] S360: When the difference index is smaller than the reference index, all the first photovoltaic data within the preset time window are determined as second abnormal data.

[0117] S370: According to the first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain target data.

[0118] The processes of S310, S320 and S370 are the same as the processes of S110, S120 and S140 described above. For details, please refer to the above embodiments. For the sake of brevity, they will not be repeated here.

[0119] The other steps above are described in detail below:

[0120] In S330, the first reference matching degree interval may be a reference matching degree interval determined based on the irradiance and the installed capacity of the photovoltaic field.

[0121] For example, assuming that the irradiance is low, the corresponding value is 200W / m 3 The rated irradiance absorbed by the photovoltaic panel is 1800W / m 3 , the first reference matching interval can be set to [installed capacity / 1800, installed capacity / 200].

[0122] For example, when the irradiance is low, if the first matching degree is greater than the installed capacity / 200, it means that the corresponding photovoltaic power is obviously too high. In this case, the corresponding photovoltaic power can be determined as the first abnormal data.

[0123] For example, when the irradiance reaches the rated irradiance absorbed by the photovoltaic panel, the corresponding photovoltaic power should normally be close to the installed capacity. At this time, if the first matching degree is less than the installed capacity / 1800, it means that the photovoltaic power is obviously low. At this time, the corresponding photovoltaic power can be determined as the first abnormal data. In this way, data with mismatch between irradiance and photovoltaic power can be preliminarily screened out.

[0124] In S340 , after the first abnormal data is determined, the first abnormal data may be removed from the photovoltaic data acquired above, that is, the first photovoltaic data is the photovoltaic data other than the first abnormal data.

[0125] In S350, due to factors such as the earth's revolution and the environment, the photovoltaic power is generally constant only at night and when it is fully powered. For other time points, the photovoltaic power is generally not constant. Therefore, based on this characteristic, abnormal data can be further identified from the first photovoltaic data.

[0126] Exemplarily, a time window may be preset, and the size of the time window may be set according to actual needs. Taking the time window including three historical time points as an example, for each historical time point, the previous historical time point and the next historical time point of the historical time point may be divided into one time window.

[0127] The difference index is used to reflect the difference between the first photovoltaic data. The larger the difference index, the greater the difference between the first photovoltaic data, that is, the smaller the possibility that the first photovoltaic data in the time window is abnormal data. The smaller the difference index, the smaller the difference between the first photovoltaic data, that is, the greater the possibility that the first photovoltaic data in the time window is abnormal data.

[0128] For example, the maximum and minimum values ​​of each first photovoltaic data can be determined from a preset time window, and the difference between the maximum and minimum values ​​can be determined as the difference index of each first photovoltaic data in the preset time window. Based on the difference index, it can be determined whether the first photovoltaic data at each historical time point is abnormal.

[0129] After preliminarily screening out data that does not match irradiance and photovoltaic power, the embodiment of the present application can further determine the difference index of each first photovoltaic data in the preset time window based on the difference between the maximum and minimum values ​​of the first photovoltaic data in the preset time window, and further screen out abnormal photovoltaic data based on the difference index, thereby improving the accuracy of the abnormal data identification results.

[0130] Exemplarily, the difference between any two first photovoltaic data in the time window may also be determined as the difference indicator between the two first photovoltaic data.

[0131] In S360, illustratively, the reference index may be a value as small as possible. When the difference index is less than the reference index, it indicates that the difference between the first photovoltaic data in the time window is extremely small. At this time, the first photovoltaic data in the time window can be considered to be a constant value, that is, the first photovoltaic data at each historical time point in the time window are straightened. At this time, the first photovoltaic data in the time window can all be determined as second abnormal data.

[0132] The judgment process at each historical time point is similar, thereby all the straight line data can be determined to obtain the second abnormal data.

[0133] For example, the abnormal data identified by the above scheme can be found in Figure 4 , the data in the dotted box are abnormal data.

[0134] Exemplarily, when the difference index is greater than or equal to the reference index, it means that the difference between the first photovoltaic data is relatively large, and at this time, it can be preliminarily considered that the first photovoltaic data is normal.

[0135] The embodiment of the present application can first preliminarily screen out photovoltaic data whose irradiance and photovoltaic power do not match based on the common sense of the relationship between irradiance and photovoltaic power in the photovoltaic electric field, and then judge from the remaining photovoltaic data whether the photovoltaic data is a constant value in each time window, and further obtain abnormal data, thereby improving the accuracy of the abnormal data identification results.

[0136] Taking the identification of abnormal data based on the quartile method as an example, for example, Figure 5 As shown, the photovoltaic data processing method may include the following steps:

[0137] S510, obtaining photovoltaic data of a photovoltaic electric field at N historical time points.

[0138] S520: For each historical time point, determine a first matching degree between photovoltaic power and irradiance.

[0139] S530 , determining a non-zero first matching degree from each first matching degree, and adding each non-zero first matching degree to a first set.

[0140] S540: Determine a first quantile and a second quantile of the first set according to each first matching degree in the first set.

[0141] The first quantile is smaller than the second quantile.

[0142] S550: Determine a second reference matching degree interval according to the first quantile and the second quantile, and the quantile range between the first quantile and the second quantile.

[0143] S560 . For each first matching degree in the first set, if the first matching degree does not belong to the second reference matching degree interval, determine the photovoltaic data corresponding to the first matching degree as abnormal data.

[0144] S570: According to the first matching degree of the photovoltaic data within the preset time period, the abnormal data is corrected to obtain the target data.

[0145] The processes of S510, S520 and S570 are the same as the processes of S110, S120 and S140 described above. For details, please refer to the above embodiments. For the sake of brevity, they will not be repeated here.

[0146] The other steps above are described in detail below:

[0147] In S530, the first matching degree of 0 is usually nighttime data. The embodiment of the present application is mainly used to identify abnormalities in photovoltaic data during the day. Therefore, the part of 0 can be removed from each first matching degree. The embodiment of the present application adds non-zero first matching degrees to the first set in chronological order to facilitate subsequent screening of abnormal data.

[0148] In S540, quantiles are also called quantile points, which refer to numerical points that divide the probability distribution range of a random variable into several equal parts. Commonly used quantiles include quantiles (median), quartiles, percentiles, etc.

[0149] Taking quartiles as an example, illustratively, the first matching degrees in the first set may be arranged in order from small to large, and then each first matching degree in the first set may be equally divided into four parts.

[0150] Exemplarily, the first quantile may be the 25% position, that is, the first matching degree at one-quarter position, and the second quantile may be the 75% position, that is, the first matching degree at three-quarter position.

[0151] In S550, the quantile distance between the first quantile and the second quantile, that is, the difference between the second quantile and the first quantile, is exemplarily: Among them, I q is the quantile distance between the second quantile and the first quantile, is the second quantile of the first set, is the first quantile of the first set.

[0152] According to the first quantile and the second quantile, and the quantile distance between the second quantile and the first quantile, a second reference matching degree interval can be determined. The second reference matching degree interval is the interval to which the normal first matching degree belongs.

[0153] Exemplarily, the difference between the first quantile and the quantile range of the preset multiple can be used as the lower limit of the second reference matching degree interval, and the cumulative sum of the second quantile and the quantile range of the preset multiple can be used as the upper limit of the second reference matching degree interval.

[0154] Exemplarily, the second reference matching interval is Exemplarily, a1=a2=1.5.

[0155] In S560, after the second reference matching degree interval is determined, each first matching degree in the first set can be matched with the second reference matching degree interval. If the first matching degree is not in the second reference matching degree interval, the photovoltaic data corresponding to the first matching degree can be determined as abnormal data. If the first matching degree is in the second reference matching degree interval, the photovoltaic data corresponding to the first matching degree can be determined as normal data.

[0156] For example, the abnormal data identified based on the quartile method can be found in Figure 6 dotted frame.

[0157] The embodiment of the present application utilizes the quartile method, combined with the correlation between irradiance and photovoltaic power, to further identify abnormal data in which irradiance and photovoltaic power do not match, thereby improving the accuracy of abnormal data identification results.

[0158] Exemplarily, the above-mentioned scheme of identifying abnormal data through the quartile method can be executed separately, that is, directly based on the first matching degree of each historical time point obtained, combined with the quartile method to identify abnormal data, or it can be executed after the second abnormal data is obtained in the above-mentioned embodiment. That is, after the second abnormal data is identified based on the above-mentioned embodiment, the quartile method can be further combined to identify abnormal data from the photovoltaic data after the second abnormal data is removed. In this way, the layered progression of abnormal data is realized, and the accuracy of the abnormal data identification results is improved.

[0159] Taking the identification of abnormal data by standard deviation method as an example, for example, Figure 7 As shown, the photovoltaic data processing method may include the following steps:

[0160] S710 , obtaining photovoltaic data of a photovoltaic electric field at N historical time points.

[0161] S720: For each historical time point, determine a first matching degree between photovoltaic power and irradiance.

[0162] S730 , determine a non-zero first matching degree from each first matching degree, and add each non-zero first matching degree to a first set.

[0163] S740: Determine the mean and standard deviation of each first matching degree in the first set.

[0164] S750: Determine a third reference matching degree interval according to the mean and the standard deviation.

[0165] S760 . For each first matching degree in the first set, if the first matching degree does not belong to the third reference matching degree interval, determine the photovoltaic data corresponding to the first matching degree as abnormal data.

[0166] S770: According to the first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain target data.

[0167] Among them, the processes of S710, S720 and S770 are the same as the processes of S110, S120 and S140 mentioned above, and the process of S730 is the same as the process of S530 mentioned above. For details, please refer to the above embodiment. For the sake of concise description, they will not be repeated here.

[0168] The other steps above are described in detail below:

[0169] In S740, after the first set is determined, the mean and standard deviation of each first matching degree in the first set can be determined, so as to facilitate the subsequent determination of a third reference matching degree interval. The third reference matching degree interval is the interval to which the normal first matching degree belongs.

[0170] In S750, after the mean and standard deviation of each first matching degree are determined, a third reference matching degree interval can be determined based on the mean and the standard deviation.

[0171] Exemplarily, the deviation distance may be determined based on the standard deviation. For example, a preset multiple of the standard deviation may be determined as the deviation distance.

[0172] Exemplarily, the difference between the mean and the deviation distance may be used as the lower limit of the third reference matching degree interval, and the cumulative sum of the mean and the deviation distance may be used as the upper limit of the third reference matching degree interval.

[0173] Exemplarily, the third reference matching degree interval can be expressed as in, is the mean of the first matching degrees in the first set, is the deviation distance, exemplarily, is the standard deviation of each first matching degree in the first set. For example, n=3.

[0174] In S760, after the third reference matching degree interval is determined, each first match in the first set can be matched with the third reference matching degree interval. If the first matching degree is not in the third reference matching degree interval, the photovoltaic data corresponding to the first matching degree can be determined as abnormal data. If the first matching degree is in the third reference matching degree interval, the photovoltaic data corresponding to the first matching degree can be determined as normal data.

[0175] For example, the abnormal data identified based on the variance method can be found in Figure 8 The dashed box shown.

[0176] The embodiment of the present application utilizes the standard deviation method, combined with the correlation between irradiance and photovoltaic power, to further identify abnormal data in which irradiance and photovoltaic power do not match, thereby improving the accuracy of abnormal data identification results.

[0177] Exemplarily, the process of identifying abnormal data based on the standard deviation method can be performed independently or on the basis of the above embodiment, thereby improving the accuracy of the abnormal data identification result.

[0178] In some embodiments, each historical time point may be divided into multiple time periods, and then abnormal data may be identified based on each time period. For example, the abnormal data includes abnormal power. Fig. 9 As shown, the photovoltaic data processing method may include the following steps:

[0179] S910, obtaining photovoltaic data of a photovoltaic electric field at N historical time points.

[0180] S920: For each historical time point, determine a first matching degree between photovoltaic power and irradiance.

[0181] S930 , dividing the historical time points corresponding to each photovoltaic data into M time periods.

[0182] M is a positive integer.

[0183] S940: For each time period, determine the third quantile, the fourth quantile, and the fifth quantile of the first matching degree corresponding to each photovoltaic data in the time period.

[0184] The third quartile, fourth quartile and fifth quartile decrease in sequence.

[0185] S950. Determine power reference intervals for photovoltaic power at corresponding historical time points according to the third quantile and the fourth quantile, the fourth quantile and the fifth quantile, and the irradiance at each historical time point in the time period.

[0186] S960: When the photovoltaic power at the corresponding historical time point does not belong to the power reference interval at the corresponding historical time point, determine the photovoltaic power at the corresponding historical time point as abnormal power.

[0187] S970: According to the first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain target data.

[0188] The processes of S910, S920 and S970 are the same as the processes of S110, S120 and S140 described above. For details, please refer to the above embodiments. For the sake of brevity, they will not be repeated here.

[0189] The other steps above are described in detail below:

[0190] In S930, the embodiment of the present application does not limit the specific division method of the historical time points, for example, every 7 days of historical time points can be divided into a time period. If there is less photovoltaic data in a time period, the time period can be merged with an adjacent time period, for example, the time period can be merged with the previous time period, or the time period can be merged with the next time period.

[0191] Before dividing each historical time point, photovoltaic data with a first matching degree of 0 may be removed, that is, the embodiment of the present application identifies abnormal power based on a non-zero first matching degree, thereby ensuring the accuracy of the identification result.

[0192] In S940, for each time period, the first matching degrees may be arranged in ascending order, for ease of description, the first matching degrees after arrangement in each time period may be recorded as a second set.

[0193] The third quantile, the fourth quantile and the fifth quantile are respectively the first matching degrees of different positions in the second set, wherein the third quantile, the fourth quantile and the fifth quantile decrease in sequence.

[0194] Exemplarily, the third quantile may be the first matching degree of 90% of the positions in the second set, the fourth quantile may be the first matching degree of 50% of the positions in the second set, and the fifth quantile may be the first matching degree of 25% of the positions in the second set.

[0195] In S950, after the third quantile, the fourth quantile and the fifth quantile are determined, the power reference interval of the corresponding photovoltaic power at the corresponding historical time point can be determined based on the third quantile, the fourth quantile, the fourth quantile and the fifth quantile, and the irradiance at each historical time point in the time period.

[0196] Exemplarily, it is possible to determine from the second set that The first matching degree between , and the mean value of the first matching degree is recorded as Similarly, we can determine from the second set the The first matching degree between , and the mean value of the first matching degree is recorded as i represents the i-th data segment. is the third quantile, is the fourth quartile, The fifth quartile.

[0197] according to and Combined with the irradiance at each historical time point in the time period, the power reference interval corresponding to the photovoltaic power at each historical time point can be determined.

[0198] For example, irradiance can be compared to The product of irradiance and The product of is taken as the lower limit of the power reference range.

[0199] Considering that the irradiance has a certain deviation, when determining the upper limit of the power reference interval, the first variable can be accumulated on the basis of the actual irradiance. Similarly, when determining the lower limit of the power reference interval, the second variable can be subtracted from the actual irradiance. Exemplarily, the first variable can be the same as the second variable, for example, it can be set to 100. That is, the upper limit of the power reference interval is The lower limit of the power reference interval is

[0200] In S960, after the power reference interval corresponding to each historical time point is determined, the photovoltaic power at the corresponding historical time point can be matched with the corresponding power reference interval.

[0201] Exemplarily, if the photovoltaic power at the corresponding historical time point is not within the corresponding power reference interval, the photovoltaic power at the corresponding historical time point can be determined as abnormal power. If the photovoltaic power at the corresponding historical time point is within the corresponding power reference interval, the photovoltaic power at the corresponding historical time point can be determined as normal power.

[0202] The abnormal power identification process for each time period is similar. Repeat the above process for all time periods to identify abnormal data in all time periods.

[0203] The abnormal data identified by the above segmentation method can be seen in Fig.10 The dashed box shown. Fig.10 It can be seen that abnormal data can be further identified based on the segmentation method.

[0204] The embodiment of the present application utilizes a segmentation method, combined with the correlation between irradiance and photovoltaic power, so that photovoltaic abnormal data identification can adaptively identify abnormal data in different time periods according to the power generation rules in different time periods, thereby improving the accuracy of abnormal data identification results.

[0205] The embodiments of the present application can not only identify abnormal data in photovoltaic data, but also correct the abnormal data, thereby increasing the amount of available data and helping to improve the stability of the model when subsequently training a photovoltaic power prediction model based on the available data.

[0206] Taking abnormal data including abnormal power as an example, illustratively, Fig.11 As shown, the photovoltaic data processing method may include the following steps:

[0207] S1110. Obtain photovoltaic data of the photovoltaic field at N historical time points.

[0208] S1120: For each historical time point, determine a first matching degree between photovoltaic power and irradiance.

[0209] S1130 . Determine abnormal data from each photovoltaic data according to the first matching degree of each historical time point.

[0210] S1140 , dividing the historical time points corresponding to each photovoltaic data into P time periods.

[0211] P is a positive integer.

[0212] S1150 . For each time period, determine the sixth quantile and the seventh quantile of the first matching degree corresponding to each photovoltaic data in the time period.

[0213] The sixth quantile is smaller than the seventh quantile.

[0214] S1160: Determine at least one third matching degree from each first matching.

[0215] The third matching degree belongs to the fourth reference matching degree interval formed by the sixth quantile and the seventh quantile.

[0216] S1170: Replace the abnormal power with the product of the average value of each third matching degree and the irradiance corresponding to the abnormal power to obtain the target power.

[0217] Among them, the process of S1110-S1130 is the same as the process of S110-S130 mentioned above. For details, please refer to the above embodiment. For the sake of concise description, it will not be repeated here.

[0218] The other steps above are described in detail below:

[0219] In S1140, the process of dividing each historical time point may refer to the above embodiment, wherein P may be the same as M in the above embodiment.

[0220] In S1150, illustratively, for each time period, the normal first matching degrees in the time period may be arranged in order from small to large. For the convenience of description, the arranged first matching degrees in the time period may be recorded as a third set.

[0221] The sixth quantile and the seventh quantile are respectively the first matching degrees of different positions in the third set, wherein the sixth quantile is smaller than the seventh quantile.

[0222] Exemplarily, the sixth quantile may be the first matching degree of 10% of the positions in the third set, and the seventh quantile may be the first matching degree of 90% of the positions in the third set.

[0223] In S1160, it is possible to determine from the third set that The first matching degree between , and the mean value of the first matching degree is recorded as in, is the sixth quantile, is the seventh quantile, and j represents the jth time period.

[0224] according to and Combined with the irradiance at each historical time point in the time period, the power reference interval corresponding to the photovoltaic power at each historical time point can be determined.

[0225] The third matching degree is between The degree of match between, for example, and After confirmation, you can filter out the items between The matching degree between them is recorded as the third matching degree.

[0226] In S1170, after the third matching degrees are determined, the average of the third matching degrees can be determined, and the average The abnormal power is replaced by the product of the irradiance corresponding to the abnormal power in the time period to obtain the target power. The abnormal power here may include all the abnormal powers identified in the above embodiments.

[0227] Repeat the above process for each time period, and the abnormal power in each time period can be corrected to normal power. The photovoltaic data corrected by the above correction method can be seen in Fig.12 .

[0228] The embodiment of the present application divides each historical time point into multiple time periods. For each time period, according to the first matching degree corresponding to the normal photovoltaic data in the time period and the irradiance corresponding to the abnormal power, the abnormal power in the time period can be corrected to normal power, thereby increasing the amount of available data.

[0229] Exemplarily, in addition to the above-mentioned linear regression method for correcting abnormal power, a machine learning method such as support vector regression (SVR) may also be used to correct abnormal power.

[0230] The embodiment of the present application adopts different abnormal data identification methods according to the correlation between irradiance and photovoltaic power, and can identify different types of abnormal data, thereby ensuring the accuracy of the abnormal data identification results; at the same time, according to the first matching degree of normal photovoltaic data, the abnormal data can be quickly corrected through the time segmentation method, and at the same time, the abnormal data can be adaptively corrected according to the changes in the power generation law, thereby ensuring the availability of the corrected abnormal data.

[0231] Based on the same inventive concept, the present application embodiment also provides a photovoltaic data processing device. Fig.13 The photovoltaic data processing device provided in the embodiment of the present application is described in detail.

[0232] Fig.13 A structural diagram of a photovoltaic data processing device provided in an embodiment of the present application.

[0233] like Fig.13 As shown, the photovoltaic data processing device may include: an acquisition module 1300, a determination module 1301 and a correction module 1302;

[0234] An acquisition module 1300 is used to acquire photovoltaic data of a photovoltaic electric field at N historical time points, where the photovoltaic data includes irradiance and photovoltaic power corresponding to the irradiance, and N is an integer greater than 1;

[0235] A determination module 1301 is used to determine a first matching degree between photovoltaic power and irradiance for each historical time point;

[0236] The determination module 1301 is further used to determine abnormal data from each photovoltaic data according to the first matching degree of each historical time point;

[0237] The correction module 1302 is used to correct the abnormal data according to the first matching degree of the photovoltaic data within a preset time period to obtain the target data.

[0238] The embodiment of the present application obtains photovoltaic data of the photovoltaic electric field at N historical time points, and the photovoltaic data includes irradiance and photovoltaic power corresponding to the irradiance, where N is an integer greater than 1; for each historical time point, the first matching degree of photovoltaic power and irradiance is determined; according to the first matching degree of each historical time point, abnormal data is determined from each photovoltaic data; according to the first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain the target data. Because the first matching degree can reflect the matching relationship between irradiance and photovoltaic power, that is, when identifying abnormal photovoltaic data, the embodiment of the present application fully considers the matching relationship between irradiance and photovoltaic power, so that the data that does not match irradiance and photovoltaic power can be accurately identified, and the accuracy of the identification result is improved. In addition, the embodiment of the present application can also correct the abnormal data according to the first matching degree of photovoltaic data within a preset time period, improve the data quality of photovoltaic data, so that when the photovoltaic power prediction model is subsequently trained based on photovoltaic data, the prediction effect of the model can be improved, and then the accuracy of the photovoltaic power prediction result can be improved.

[0239] In some embodiments, the abnormal data includes first abnormal data and second abnormal data; the determination module 1301 is specifically used to:

[0240] When the first matching degree does not belong to the first reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as the first abnormal data;

[0241] Determine photovoltaic data other than first abnormal data from each photovoltaic data to obtain first photovoltaic data;

[0242] For a preset time window, determining a difference index of each first photovoltaic data in the preset time window;

[0243] When the difference index is smaller than the reference index, all the first photovoltaic data within the preset time window are determined as second abnormal data.

[0244] In some embodiments, the determination module 1301 is specifically configured to:

[0245] Determine the maximum value and the minimum value of each first photovoltaic data from the preset time window;

[0246] The difference between the maximum value and the minimum value is determined as a difference index of each first photovoltaic data in the preset time window.

[0247] In some embodiments, the determination module 1301 is specifically configured to:

[0248] Determine a non-zero first matching degree from each first matching degree, and add each non-zero first matching degree to a first set;

[0249] Determine a first quantile and a second quantile of the first set according to each first matching degree in the first set, wherein the first quantile is smaller than the second quantile;

[0250] Determine a second reference matching degree interval according to the first quantile and the second quantile, and the quantile distance between the first quantile and the second quantile;

[0251] For each first matching degree in the first set, when the first matching degree does not belong to the second reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as abnormal data.

[0252] In some embodiments, the determination module 1301 is specifically configured to:

[0253] Determine a non-zero first matching degree from each first matching degree, and add each non-zero first matching degree to a first set;

[0254] Determine the mean and standard deviation of each first matching degree in the first set;

[0255] Determine a third reference matching interval according to the mean and the standard deviation;

[0256] For each first matching degree in the first set, when the first matching degree does not belong to the third reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as abnormal data.

[0257] In some embodiments, the abnormal data includes abnormal power; the photovoltaic data processing device may further include:

[0258] A division module is used to divide the historical time points corresponding to each photovoltaic data into M time periods, where M is a positive integer;

[0259] The determination module 1301 is specifically used for:

[0260] For each time period, determine the third quantile, the fourth quantile and the fifth quantile of the first matching degree corresponding to each photovoltaic data in the time period, and the third quantile, the fourth quantile and the fifth quantile decrease in sequence;

[0261] According to the third quantile and the fourth quantile, the fourth quantile and the fifth quantile, and the irradiance at each historical time point in the time period, the power reference interval of the corresponding photovoltaic power at the corresponding historical time point is determined respectively;

[0262] When the photovoltaic power at the corresponding historical time point does not belong to the power reference interval at the corresponding historical time point, the photovoltaic power at the corresponding historical time point is determined as abnormal power.

[0263] In some embodiments, the abnormal data includes abnormal power;

[0264] The division module is also used to divide the historical time points corresponding to each photovoltaic data into P time periods, where P is a positive integer;

[0265] The determination module 1301 is further used to determine, for each time period, a sixth quantile and a seventh quantile of the first matching degree corresponding to each photovoltaic data in the time period, wherein the sixth quantile is smaller than the seventh quantile;

[0266] Determine at least one third matching degree from each first match, the third matching degree belonging to a fourth reference matching degree interval formed by a sixth quantile and a seventh quantile;

[0267] The correction module 1302 is specifically used for:

[0268] The abnormal power is replaced by the product of the mean value of each third matching degree and the irradiance corresponding to the abnormal power to obtain the target power.

[0269] In some embodiments, the determination module 1301 is specifically configured to:

[0270] Determine the ratio of irradiance to photovoltaic power;

[0271] The ratio is determined as a first matching degree of photovoltaic power to irradiance.

[0272] The photovoltaic data processing device provided in the embodiment of the present application can achieve Figure 1-12 To avoid repetition, each process in the photovoltaic data processing method embodiment is not described again.

[0273] Based on the same inventive concept, the embodiment of the present application also provides an electronic device, which may be, for example, a tablet computer, a notebook computer, a handheld computer, etc. Fig.14 The electronic device provided in the embodiments of the present application is described in detail.

[0274] like Fig.14 As shown, the electronic device may include a processor 141 and a memory 142 for storing computer program instructions.

[0275] The processor 141 may include a central processing unit (CPU) or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0276] The memory 142 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 142 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In one example, the memory 142 may include a removable or non-removable (or fixed) medium, or the memory 142 is a non-volatile solid-state memory. In one example, the memory 142 may be a read-only memory (ROM). In one example, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or a flash memory or a combination of two or more of these.

[0277] The processor 141 reads and executes the computer program instructions stored in the memory 142 to implement Figure 1-Figure 12 The method in the embodiment shown in the figure is achieved Figure 1-Figure 12 The corresponding technical effects achieved by executing the method in the illustrated embodiment are not described in detail here for the sake of brevity.

[0278] In one example, the electronic device may further include a communication interface 143 and a bus 144. Fig.14 As shown, the processor 141, the memory 142, and the communication interface 143 are connected via a bus 144 and communicate with each other.

[0279] The communication interface 143 is mainly used to implement communication between various modules, devices and / or equipment in the embodiments of the present application.

[0280] Bus 144 includes hardware, software or both, and each component of electronic device is coupled to each other.For example, but not limitation, bus 104 may include accelerated graphics port (Accelerated Graphics Port, AGP) or other graphics bus, enhanced industry standard architecture (Extended Industry Standard Architecture, EISA) bus, front side bus (Front Side Bus, FSB), Hyper Transport (Hyper Transport, HT) interconnection, industry standard architecture (Industry Standard Architecture, ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 144 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0281] After acquiring the photovoltaic data of the photovoltaic field at N historical time points, the electronic device can execute the photovoltaic data processing method in the embodiment of the present application, thereby realizing the combination Figure 1-12 The method for processing photovoltaic data described and Fig.13 A photovoltaic data processing apparatus is described.

[0282] In addition, in combination with the photovoltaic data processing method in the above embodiments, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any photovoltaic data processing method in the above embodiments is implemented.

[0283] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0284] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0285] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0286] The above reference is according to the method of the present application embodiment, the flow chart of the device (system) and the computer program product and / or the block diagram of the present application embodiment. It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0287] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for processing photovoltaic data, characterized in that: include: Acquire photovoltaic data of the photovoltaic electric field at N historical time points, the photovoltaic data including irradiance and photovoltaic power corresponding to the irradiance, where N is an integer greater than 1; For each historical time point, determining a first matching degree between the photovoltaic power and the irradiance; Determining abnormal data from each of the photovoltaic data according to the first matching degree of each of the historical time points; According to a first matching degree of the photovoltaic data within a preset time period, the abnormal data is corrected to obtain target data.

2. The method according to claim 1, characterized in that The abnormal data includes first abnormal data and second abnormal data, and determining the abnormal data from each photovoltaic data according to the first matching degree of each historical time point includes: When the first matching degree does not belong to a first reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as first abnormal data; Determine photovoltaic data other than the first abnormal data from each of the photovoltaic data to obtain first photovoltaic data; For a preset time window, determining a difference index of each of the first photovoltaic data in the preset time window; When the difference index is smaller than the reference index, all the first photovoltaic data within the preset time window are determined as second abnormal data.

3. The method according to claim 2, characterized in that The determining of the difference index of each of the first photovoltaic data in the preset time window includes: Determine the maximum value and the minimum value of each of the first photovoltaic data from the preset time window; The difference between the maximum value and the minimum value is determined as a difference index of each of the first photovoltaic data in the preset time window.

4. The method according to claim 1, characterized in that: The determining abnormal data from each photovoltaic data according to the first matching degree of each historical time point includes: Determine a non-zero first matching degree from each of the first matching degrees, and add each of the non-zero first matching degrees to a first set; Determine a first quantile and a second quantile of the first set according to each of the first matching degrees in the first set, wherein the first quantile is smaller than the second quantile; Determine a second reference matching degree interval according to the first quantile and the second quantile, and the quantile range between the first quantile and the second quantile; For each first matching degree in the first set, when the first matching degree does not belong to the second reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as abnormal data.

5. The method according to claim 1, characterized in that The determining abnormal data from each photovoltaic data according to the first matching degree of each historical time point includes: Determine a non-zero first matching degree from each of the first matching degrees, and add each of the non-zero first matching degrees to a first set; Determine a mean and a standard deviation of each of the first matching degrees in the first set; Determining a third reference matching degree interval according to the mean and the standard deviation; For each of the first matching degrees in the first set, when the first matching degree does not belong to the third reference matching degree interval, the photovoltaic data corresponding to the first matching degree is determined as abnormal data.

6. The method according to claim 1, characterized in that The abnormal data includes abnormal power; The determining abnormal data from each photovoltaic data according to the first matching degree of each historical time point includes: The historical time points corresponding to the photovoltaic data are divided into M time periods, where M is a positive integer; For each time period, determining the third quantile, the fourth quantile and the fifth quantile of the first matching degree corresponding to each photovoltaic data in the time period, wherein the third quantile, the fourth quantile and the fifth quantile decrease in sequence; Determine the power reference interval of the photovoltaic power corresponding to the historical time point according to the third quantile and the fourth quantile, the fourth quantile and the fifth quantile, and the irradiance at each historical time point in the time period; When the photovoltaic power at the corresponding historical time point does not belong to the power reference interval at the corresponding historical time point, the photovoltaic power at the corresponding historical time point is determined as abnormal power.

7. The method according to claim 1, characterized in that The abnormal data includes abnormal power; The step of correcting the abnormal data according to the first matching degree of the photovoltaic data within a preset time period to obtain target data includes: The historical time points corresponding to the photovoltaic data are divided into P time periods, where P is a positive integer; For each time period, determining the sixth quantile and the seventh quantile of the first matching degree corresponding to each photovoltaic data in the time period, the sixth quantile being smaller than the seventh quantile; Determine at least one third matching degree from each of the first matches, the third matching degree belonging to a fourth reference matching degree interval formed by the sixth quantile and the seventh quantile; The abnormal power is replaced by the product of the average value of each of the third matching degrees and the irradiance corresponding to the abnormal power to obtain the target power.

8. The method according to any one of claims 1 to 7, characterized in that: The determining a first matching degree between the photovoltaic power and the irradiance includes: determining a ratio of the photovoltaic power to the irradiance; The ratio is determined as a first matching degree between the photovoltaic power and the irradiance.

9. A photovoltaic data processing device, characterized in that: include: Acquisition module, determination module and correction module; The acquisition module is used to acquire photovoltaic data of the photovoltaic electric field at N historical time points, wherein the photovoltaic data includes irradiance and photovoltaic power corresponding to the irradiance, and N is an integer greater than 1; The determination module is used to determine a first matching degree between the photovoltaic power and the irradiance for each historical time point; The determination module is further used to determine abnormal data from each photovoltaic data according to the first matching degree of each historical time point; The correction module is used to correct the abnormal data according to the first matching degree of the photovoltaic data within a preset time period to obtain target data.

10. An electronic device, characterized in that: include: processor; a memory for storing computer program instructions; When the computer program instructions are executed by the processor, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images