Labeling method and device for abnormal photovoltaic data, storage medium and electronic equipment

Abstract

The application provides a method and device for marking abnormal photovoltaic data, a storage medium and an electronic device, and comprises the following steps: collecting a plurality of photovoltaic data groups, each of which comprises illumination intensity and output power; determining a plurality of extraction periods, and determining a photovoltaic data set corresponding to each extraction period in the plurality of photovoltaic data groups; performing quartile method operation on the illumination intensity and output power in each photovoltaic data set, and marking the photovoltaic data group where the abnormal photovoltaic data is located; and completing the marking of all abnormal photovoltaic data in the plurality of photovoltaic data groups. In the method provided by the application, each photovoltaic data is processed by quartile method to determine each photovoltaic data in an abnormal state, and the photovoltaic data in the abnormal state is marked, so that the abnormal photovoltaic data can be quickly determined, and the development of photovoltaic research is promoted.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, and in particular to a method and apparatus for marking abnormal photovoltaic data, a storage medium, and an electronic device. Background Technology

[0002] Solar energy is a clean and renewable resource with advantages such as zero pollution and zero emissions. With the improvement of solar photovoltaic (PV) panel technology, the photovoltaic power generation industry has developed rapidly. PV data refers to the data collected during the production process of the photovoltaic power generation industry, which includes data such as output power, irradiance, ambient temperature, and PV panel temperature. Among these, irradiance and output power are important bases for conducting research on photovoltaic forecasting, power generation performance evaluation, and optimized control.

[0003] In practical applications, equipment failures, communication failures, and reduced power output from photovoltaic modules can lead to an increased proportion of abnormal photovoltaic data, significantly hindering further research using photovoltaic data and negatively impacting power quality, reliability, and stability. Therefore, it is necessary to label the status of abnormal photovoltaic data to facilitate subsequent photovoltaic research. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method for marking abnormal photovoltaic data, so as to mark abnormal data in photovoltaic data and promote the development of photovoltaic research.

[0005] This invention also provides a marking device for abnormal photovoltaic data to ensure the practical implementation and application of the above method.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] A method for marking abnormal photovoltaic data includes:

[0008] Collect multiple photovoltaic data sets within a preset time period. Each photovoltaic data set includes the light intensity and output power of the photovoltaic panel at the collection time point of the photovoltaic data set.

[0009] Each photovoltaic data set is preprocessed, and a first tag is assigned to each photovoltaic data set.

[0010] In each of the aforementioned photovoltaic data groups, the first label of the photovoltaic data group with negative output power is changed to the second label;

[0011] Multiple extraction cycles are determined within the preset time period, and each photovoltaic data group corresponding to each extraction cycle is extracted from the multiple photovoltaic data groups to form a photovoltaic data set corresponding to each extraction cycle.

[0012] For all light intensities in each photovoltaic dataset, a preset quartile operation is performed, and the first label of the photovoltaic dataset containing light intensities that do not fall within the normal quartile range is changed to the second label.

[0013] For all output power in each photovoltaic data set, the quartile operation is performed, and the first label of the photovoltaic data group containing the output power that does not fall within the normal range of the quartile is changed to the second label.

[0014] All photovoltaic data groups marked with the second label are merged to complete the labeling of all abnormal photovoltaic data in the multiple photovoltaic data groups.

[0015] Optionally, in the above method, the collection of multiple photovoltaic data sets within a preset time period includes:

[0016] Multiple data collection time points are determined within the preset time period;

[0017] At each data collection point, the solar irradiance and output power of the photovoltaic panel at that time point are collected.

[0018] Optionally, in the above method, determining multiple extraction cycles within the preset time period includes:

[0019] The data collection time points within the preset time period are sorted in chronological order.

[0020] For each sorted collection time point, a predetermined number of collection time points are selected sequentially to form an extraction cycle.

[0021] Optionally, in the above method, the step of performing a preset quartile operation on all light intensities in each photovoltaic dataset, and changing the first label of the photovoltaic dataset containing light intensities that do not fall within the normal quartile range to a second label, includes:

[0022] All light intensities in each photovoltaic dataset are sorted in ascending order to obtain a first data sequence;

[0023] Determine the lower quartile Q1 and the upper quartile Q3 in the first data sequence;

[0024] Determine the normal data interval corresponding to the quartile method operation: [L,H]=[Q1-k L I QR Q3+k H I QR ];

[0025] Where Q1 is the lower quartile, k LQ3 is the lower limit coefficient of the interval, and Q4 is the upper quartile. H The upper limit coefficient of the interval distance, interquartile range I QR =Q3-Q1;

[0026] Change the first label of the photovoltaic data group containing light intensity that does not fall within the normal data range to the second label.

[0027] The above method, optionally, determines k. L With k H The process includes:

[0028] Calculate the standard deviation σ and mean μ of all light intensities in each of the photovoltaic datasets;

[0029] The coefficient of variation was obtained as follows:

[0030] If (1-C) v (less than C) v Then k L =(1-C v ) / 1.5、k H =C v ×1.5;

[0031] If (1-C) v () greater than C v Then k L =C v / 1.5、k H =(1-C v )×1.5.

[0032] Optionally, each of the above-described photovoltaic data sets may also include the acquisition time, photovoltaic panel temperature, ambient temperature, wind speed, and wind direction at the acquisition time point of the photovoltaic data set.

[0033] The above methods may also include:

[0034] All abnormal photovoltaic data and normal photovoltaic data from the multiple photovoltaic data groups are displayed in a preset chart.

[0035] A device for marking abnormal photovoltaic data, comprising:

[0036] The acquisition unit is used to acquire multiple photovoltaic data sets within a preset time period. Each photovoltaic data set includes the light intensity and output power of the photovoltaic panel at the acquisition time point of the photovoltaic data set.

[0037] A tagging unit is used to preprocess each of the photovoltaic data groups and tag each of the photovoltaic data groups with a first tag;

[0038] The modification unit is used to change the first tag of the photovoltaic data group with negative output power in each of the photovoltaic data groups to the second tag;

[0039] The determining unit is used to determine multiple extraction cycles within the preset time period, and extract each photovoltaic data group corresponding to each extraction cycle from the multiple photovoltaic data groups to form a photovoltaic data set corresponding to each extraction cycle.

[0040] The first operation unit is used to perform a preset quartile operation on all light intensities in each photovoltaic data set, and change the first label of the photovoltaic data group containing light intensities that do not fall within the normal range of the quartile method to the second label.

[0041] The second operation unit is used to perform the quartile operation on all output power in each photovoltaic data set, and change the first label of the photovoltaic data group containing the output power that does not fall within the normal range of the quartile method to the second label.

[0042] The merging unit is used to merge all photovoltaic data groups marked with the second tag in order to complete the marking of all abnormal photovoltaic data in the multiple photovoltaic data groups.

[0043] A storage medium comprising stored instructions, wherein, when the instructions are executed, the device in which the storage medium resides executes the aforementioned method for marking abnormal photovoltaic data.

[0044] An electronic device includes at least one processor, at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other via the bus; the processor is used to call program instructions in the memory to execute the above-mentioned method for marking abnormal photovoltaic data.

[0045] A method for marking abnormal photovoltaic data based on the above embodiments of the present invention includes: collecting multiple photovoltaic data groups within a preset time period, each photovoltaic data group including the light intensity and output power of the photovoltaic panel at the collection time point of the photovoltaic data group; preprocessing each photovoltaic data group to mark each photovoltaic data group with a first tag; changing the first tag of photovoltaic data groups with negative output power to a second tag; determining multiple extraction periods within the preset time period, and extracting each photovoltaic data group corresponding to each extraction period from the multiple photovoltaic data groups to form a photovoltaic data set corresponding to each extraction period; performing a preset quartile operation on all light intensities in each photovoltaic data set, changing the first tag of photovoltaic data groups with light intensities not falling within the normal quartile range to a second tag; performing the quartile operation on all output power in each photovoltaic data set, changing the first tag of photovoltaic data groups with output power not falling within the normal quartile range to a second tag; and merging all photovoltaic data groups marked with the second tag to complete the marking of all abnormal photovoltaic data in the multiple photovoltaic data groups. In the method provided by the embodiments of the present invention, the collected photovoltaic data are processed by a pre-set quartile method to identify the photovoltaic data in an abnormal state and mark the photovoltaic data in an abnormal state. This allows for the rapid identification of abnormal photovoltaic data and promotes the development of photovoltaic research. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0047] Figure 1 A flowchart illustrating the method for marking abnormal photovoltaic data provided in this embodiment of the invention;

[0048] Figure 2 An example diagram of the method for marking abnormal photovoltaic data provided in an embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram of the structure of the marking device for abnormal photovoltaic data provided in an embodiment of the present invention;

[0050] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0053] In this application, the terms "first" and "second" do not indicate an order of arrangement, but are only used to distinguish the names.

[0054] This invention provides a method for marking abnormal photovoltaic data. This method can be applied to various system platforms, and its execution entity can be a processor within the system platform. The method flowchart is shown below. Figure 1 As shown, it includes:

[0055] S101: Collect multiple photovoltaic data sets within a preset time period, each photovoltaic data set including the light intensity and output power of the photovoltaic panel at the collection time point of the photovoltaic data set;

[0056] In the method provided by the embodiments of the present invention, during the process of marking abnormal photovoltaic data, the data range of abnormal photovoltaic data to be marked is determined, that is, a time range is defined. The preset time period can be understood as a time period in the working cycle of the photovoltaic panel, which can be one month or ten days.

[0057] Within a preset time period, photovoltaic data of the photovoltaic panel is collected at preset time intervals, such as every 15 minutes. That is, at each collection time point, the corresponding light intensity and output power of the photovoltaic panel are obtained, and the light intensity and output power collected at the current collection time point are combined into a photovoltaic data set.

[0058] S102: Preprocess each photovoltaic data group and label each photovoltaic data group with a first tag;

[0059] In the method provided by the embodiments of the present invention, each photovoltaic data group is preprocessed and labeled. First, all photovoltaic data groups are labeled with a first label, which can be a character such as 0.

[0060] S103: Change the first label of the photovoltaic data group with negative output power included in each of the photovoltaic data groups to the second label;

[0061] In the method provided by the embodiments of the present invention, for each photovoltaic data group, if the output power contained in the photovoltaic data is negative, the first tag of the photovoltaic data group is changed to the second tag, and the second tag can be 1.

[0062] S104: Within the preset time period, determine multiple extraction cycles, and extract each photovoltaic data group corresponding to each extraction cycle from the multiple photovoltaic data groups to form a photovoltaic data set corresponding to each extraction cycle.

[0063] In the method provided by this invention, multiple extraction cycles are determined within the preset time period. Each extraction cycle includes multiple collection time points. For example, photovoltaic data from a photovoltaic panel is collected every fifteen minutes. The extraction cycle can be used to extract all photovoltaic data within one hour. For example, if 7:15, 7:30, and 7:45 on February 15, 2021 are used as collection points, the extraction cycle can be the duration of one extraction cycle from 7:00 to 8:00 on February 15, 2021.

[0064] In the method provided by the embodiments of the present invention, preferably, each photovoltaic data group corresponding to each extraction cycle is extracted from the plurality of photovoltaic data groups. Extraction can be performed from all photovoltaic data groups or from each photovoltaic data group labeled with the first label, and the effect achieved is equivalent.

[0065] S105: Perform a preset quartile operation on all light intensities in each photovoltaic data set, and change the first label of the photovoltaic data group containing light intensities that do not fall within the normal range of the quartile method to the second label;

[0066] In the method provided in this embodiment of the invention, the quartile method involves arranging the data in ascending order and then dividing it into four equal parts. The data at the first quartile point is the lower quartile, and the data at the third quartile point is the upper quartile.

[0067] S106: Perform the quartile operation on all output power in each photovoltaic data set, and change the first label of the photovoltaic data group containing the output power that does not fall within the normal range of the quartile method to the second label;

[0068] S107: Merge all photovoltaic data groups marked with the second label to complete the marking of all abnormal photovoltaic data in the plurality of photovoltaic data groups.

[0069] In the method provided by the embodiments of the present invention, the collected photovoltaic data are processed by a pre-set quartile method to identify the photovoltaic data in an abnormal state and mark the photovoltaic data in an abnormal state. This allows for the rapid identification of abnormal photovoltaic data and promotes the development of photovoltaic research.

[0070] The method provided in this embodiment of the invention includes the following steps: The process of collecting multiple photovoltaic data sets within a preset time period includes:

[0071] Multiple data collection time points are determined within the preset time period;

[0072] At each data collection point, the solar irradiance and output power of the photovoltaic panel at that time point are collected.

[0073] The method provided in this embodiment of the invention includes the process of determining multiple extraction cycles within the preset time period, comprising:

[0074] The data collection time points within the preset time period are sorted in chronological order.

[0075] For each sorted collection time point, a predetermined number of collection time points are selected sequentially to form an extraction cycle.

[0076] In the method provided by this embodiment of the invention, the step of performing a preset quartile operation on all light intensities in each photovoltaic data set, and changing the first label of the photovoltaic data group containing light intensities that do not fall within the normal quartile range to a second label, includes:

[0077] All light intensities in each photovoltaic dataset are sorted in ascending order to obtain a first data sequence;

[0078] Determine the lower quartile Q1 and the upper quartile Q3 in the first data sequence;

[0079] Determine the normal data interval corresponding to the quartile method operation: [L,H]=[Q1-k L I QR Q3+k H I QR ];

[0080] Where Q1 is the lower quartile, k L Q3 is the lower limit coefficient of the interval, and Q4 is the upper quartile. H The upper limit coefficient of the interval distance, interquartile range I QR=Q3-Q1;

[0081] Change the first label of the photovoltaic data group containing light intensity that does not fall within the normal data range to the second label.

[0082] In the method provided in this embodiment of the invention, k is determined. L With k H The process includes:

[0083] Calculate the standard deviation σ and mean μ of all light intensities in each of the photovoltaic datasets;

[0084] The coefficient of variation was obtained as follows:

[0085] If (1-C) v (less than C) v Then k L =(1-C v ) / 1.5、k H =C v ×1.5;

[0086] If (1-C) v () greater than C v Then k L =C v / 1.5、k H =(1-C v )×1.5.

[0087] In the method provided by the embodiments of the present invention, each photovoltaic data group also includes the acquisition time, photovoltaic panel temperature, ambient temperature, wind speed and wind direction at the acquisition time point of the photovoltaic data group.

[0088] The method provided in this embodiment of the invention further includes:

[0089] All abnormal photovoltaic data and normal photovoltaic data from the multiple photovoltaic data groups are displayed in a preset chart.

[0090] In summary, this invention relates to a method for identifying and marking outliers in photovoltaic data based on improved quartiles, in order to obtain the output characteristic curve of a normally operating photovoltaic array. To more clearly describe the above method, this invention provides a specific example, implemented as follows:

[0091] Two months of valid measured photovoltaic power data from the photovoltaic power station were collected. The measured data included time, irradiance, power, panel temperature, ambient temperature, wind speed, and wind direction. The data sampling period was from January 1, 2018 to February 28, 2018, with a time interval of 15 minutes, and the sampling time was from 8:00 AM to 4:00 PM.

[0092] The preprocessing of photovoltaic measured data involves adding a label "0" to all photovoltaic data and changing the label of data with negative power to "1".

[0093] Data is extracted at hourly intervals to form datasets for the corresponding time periods.

[0094] An improved quartile method was used to identify outlier data points in the datasets for each time period. Within each time period, the improved quartile method was applied once for both "power" and "illuminance," and data points not falling within the normal quartile range were labeled with "1." The resulting labeling results are R... i R p And find their union, i.e., R i ∪R p .

[0095] The corresponding parameters were calculated using the quartile method described above. Table 1 shows the statistical results of the output power, and Table 2 shows the statistical results of the illuminance.

[0096]

[0097] Table 1

[0098]

[0099] Table 2

[0100] As shown in Tables 1 and 2, the light intensity and power data from 8:00 to 16:00 are obtained by applying the method of this invention to the parameters calculated using the formula.

[0101] like Figure 2 As shown, after applying the method of this invention to the data at 9 o'clock, normal data labeled "0" are represented by black dots, and abnormal data labeled "1" are represented by circled dots.

[0102] By following the above four steps, we can achieve better identification and marking of abnormal photovoltaic power data and obtain photovoltaic power data of normal operation.

[0103] and Figure 1 Corresponding to the method for marking abnormal photovoltaic data shown, this embodiment of the invention also provides a device for marking abnormal photovoltaic data, used for... Figure 1 The specific implementation of the method shown is illustrated in the following diagram. Figure 3 As shown, it includes:

[0104] The acquisition unit 201 is used to acquire multiple photovoltaic data sets within a preset time period. Each photovoltaic data set includes the light intensity and output power of the photovoltaic panel at the acquisition time point of the photovoltaic data set.

[0105] The tagging unit 202 is used to preprocess each of the photovoltaic data groups and tag each of the photovoltaic data groups with a first tag;

[0106] The modification unit 203 is used to change the first tag of the photovoltaic data group with negative output power in each of the photovoltaic data groups to the second tag;

[0107] The determining unit 204 is used to determine multiple extraction cycles within the preset time period, and extract each photovoltaic data group corresponding to each extraction cycle from the multiple photovoltaic data groups to form a photovoltaic data set corresponding to each extraction cycle.

[0108] The first operation unit 205 is used to perform a preset quartile operation on all light intensities in each photovoltaic data set, and change the first label of the photovoltaic data group containing light intensities that do not fall within the normal range of the quartile method to the second label.

[0109] The second operation unit 206 is used to perform the quartile operation on all output power in each photovoltaic data set, and change the first label of the photovoltaic data group containing the output power that does not fall within the normal range of the quartile to the second label.

[0110] The merging unit 207 is used to merge all photovoltaic data groups marked with the second tag in order to complete the marking of all abnormal photovoltaic data in the plurality of photovoltaic data groups.

[0111] In the device provided by the embodiments of the present invention, the collected photovoltaic data are processed by a pre-set quartile method to identify the photovoltaic data in an abnormal state and mark the photovoltaic data in an abnormal state. This allows for the rapid identification of abnormal photovoltaic data and promotes the development of photovoltaic research.

[0112] The device provided in this embodiment of the invention includes a processor and a memory. Each of the above-mentioned units is stored in the memory as a program unit, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0113] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and the marking process for abnormal photovoltaic data can be dynamically executed by adjusting kernel parameters.

[0114] This invention provides a storage medium storing a program that, when executed by a processor, implements the aforementioned method for marking abnormal photovoltaic data.

[0115] This invention provides a processor for running a program, wherein the program executes the aforementioned method for marking abnormal photovoltaic data.

[0116] like Figure 4 As shown, this embodiment of the invention provides an electronic device 30, which includes at least one processor 301, at least one memory 302 connected to the processor 301, and a bus 303; wherein the processor 301 and the memory 302 communicate with each other through the bus 303; the processor 301 is used to call program instructions in the memory 302 to execute the above-mentioned method for marking abnormal photovoltaic data. The electronic device in this article may be a server, PC, etc.

[0117] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps, including:

[0118] Collect multiple photovoltaic data sets within a preset time period. Each photovoltaic data set includes the light intensity and output power of the photovoltaic panel at the collection time point of the photovoltaic data set.

[0119] Each photovoltaic data set is preprocessed, and a first tag is assigned to each photovoltaic data set.

[0120] In each of the aforementioned photovoltaic data groups, the first label of the photovoltaic data group with negative output power is changed to the second label;

[0121] Multiple extraction cycles are determined within the preset time period, and each photovoltaic data group corresponding to each extraction cycle is extracted from the multiple photovoltaic data groups to form a photovoltaic data set corresponding to each extraction cycle.

[0122] For all light intensities in each photovoltaic dataset, a preset quartile operation is performed, and the first label of the photovoltaic dataset containing light intensities that do not fall within the normal quartile range is changed to the second label.

[0123] For all output power in each photovoltaic data set, the quartile operation is performed, and the first label of the photovoltaic data group containing the output power that does not fall within the normal range of the quartile is changed to the second label.

[0124] All photovoltaic data groups marked with the second label are merged to complete the labeling of all abnormal photovoltaic data in the multiple photovoltaic data groups.

[0125] Optionally, in the above method, the collection of multiple photovoltaic data sets within a preset time period includes:

[0126] Multiple data collection time points are determined within the preset time period;

[0127] At each data collection point, the solar irradiance and output power of the photovoltaic panel at that time point are collected.

[0128] Optionally, the above method may involve determining multiple extraction cycles within the preset time period, including:

[0129] The data collection time points within the preset time period are sorted in chronological order.

[0130] For each sorted collection time point, a predetermined number of collection time points are selected sequentially to form an extraction cycle.

[0131] Optionally, in the above method, the step of performing a preset quartile operation on all light intensities in each photovoltaic dataset, and changing the first label of the photovoltaic dataset containing light intensities that do not fall within the normal quartile range to a second label, includes:

[0132] All light intensities in each photovoltaic dataset are sorted in ascending order to obtain a first data sequence;

[0133] Determine the lower quartile Q1 and the upper quartile Q3 in the first data sequence;

[0134] Determine the normal data interval corresponding to the quartile method operation: [L,H]=[Q1-k L I QR Q3+k H I QR ];

[0135] Where Q1 is the lower quartile, k L Q3 is the lower limit coefficient of the interval, and Q4 is the upper quartile. H The upper limit coefficient of the interval distance, interquartile range I QR =Q3-Q1;

[0136] Change the first label of the photovoltaic data group containing light intensity that does not fall within the normal data range to the second label.

[0137] The above method, optionally, determines k. L With k H The process includes:

[0138] Calculate the standard deviation σ and mean μ of all light intensities in each of the photovoltaic datasets;

[0139] The coefficient of variation was obtained as follows:

[0140] If (1-C)v (less than C) v Then k L =(1-C v ) / 1.5、k H =C v ×1.5;

[0141] If (1-C) v () greater than C v Then k L =C v / 1.5、k H =(1-C v )×1.5.

[0142] Optionally, each of the above-described photovoltaic data sets may also include the acquisition time, photovoltaic panel temperature, ambient temperature, wind speed, and wind direction at the acquisition time point of the photovoltaic data set.

[0143] The above methods may also include:

[0144] All abnormal photovoltaic data and normal photovoltaic data from the multiple photovoltaic data groups are displayed in a preset chart.

[0145] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0146] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0147] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for marking abnormal photovoltaic data, characterized in that, include: Collect multiple photovoltaic data sets within a preset time period. Each photovoltaic data set includes the light intensity and output power of the photovoltaic panel at the collection time point of the photovoltaic data set. Each photovoltaic data set is preprocessed, and a first tag is assigned to each photovoltaic data set. In each of the aforementioned photovoltaic data groups, the first label of the photovoltaic data group with negative output power is changed to the second label; Multiple extraction cycles are determined within the preset time period, and each photovoltaic data group corresponding to each extraction cycle is extracted from the multiple photovoltaic data groups to form a photovoltaic data set corresponding to each extraction cycle. A preset quartile operation is performed on all light intensities in each photovoltaic dataset. The first label of the photovoltaic dataset containing light intensities not falling within the normal quartile range is changed to a second label. This includes: sorting all light intensities in each photovoltaic dataset in ascending order to obtain a first data sequence; determining the lower quartile Q1 and upper quartile Q3 in the first data sequence; and determining the normal data range corresponding to the quartile operation: [L,H]=[Q1-k L I QR Q3+k H I QR ]; where Q1 is the lower quartile, k L Q3 is the lower limit coefficient of the interval, and Q4 is the upper quartile. H The upper limit coefficient of the interval distance, interquartile range I QR =Q3-Q1; Change the first label of the photovoltaic data group containing light intensity that does not fall within the normal data range to the second label; Determine k L With k H The process includes: calculating the standard deviation σ and mean μ of all light intensities in each photovoltaic dataset; and obtaining the coefficient of variation as follows: If (1-C) v (less than C) v Then k L =(1-C v ) / 1.5、k H =C v ×1.5; if (1-C v () greater than C v Then k L =C v / 1.5、k H =(1-C v )×1.5; For all output power in each photovoltaic data set, the quartile operation is performed, and the first label of the photovoltaic data group containing the output power that does not fall within the normal range of the quartile is changed to the second label. All photovoltaic data groups marked with the second label are merged to complete the labeling of all abnormal photovoltaic data in the multiple photovoltaic data groups.

2. The method according to claim 1, characterized in that, The collection of multiple photovoltaic data sets within a preset time period includes: Multiple data collection time points are determined within the preset time period; At each data collection point, the solar irradiance and output power of the photovoltaic panel at that time point are collected.

3. The method according to claim 2, characterized in that, The step of determining multiple extraction cycles within the preset time period includes: The data collection time points within the preset time period are sorted in chronological order. For each sorted collection time point, a predetermined number of collection time points are selected sequentially to form an extraction cycle.

4. The method according to claim 1, characterized in that, Each photovoltaic data set also includes the acquisition time, photovoltaic panel temperature, ambient temperature, wind speed, and wind direction at the acquisition time point of that photovoltaic data set.

5. The method according to claim 1, characterized in that, Also includes: All abnormal photovoltaic data and normal photovoltaic data from the multiple photovoltaic data groups are displayed in a preset chart.

6. A marking device for abnormal photovoltaic data, characterized in that, include: The acquisition unit is used to acquire multiple photovoltaic data sets within a preset time period. Each photovoltaic data set includes the light intensity and output power of the photovoltaic panel at the acquisition time point of the photovoltaic data set. A tagging unit is used to preprocess each of the photovoltaic data groups and tag each of the photovoltaic data groups with a first tag; The modification unit is used to change the first tag of the photovoltaic data group with negative output power in each of the photovoltaic data groups to the second tag; The determining unit is used to determine multiple extraction cycles within the preset time period, and extract each photovoltaic data group corresponding to each extraction cycle from the multiple photovoltaic data groups to form a photovoltaic data set corresponding to each extraction cycle. The first operation unit is used to perform a preset quartile operation on all light intensities in each photovoltaic data set, changing the first label of the photovoltaic data group containing light intensities that do not fall within the normal quartile range to a second label. This includes: sorting all light intensities in each photovoltaic data set in ascending order to obtain a first data sequence; determining the lower quartile Q1 and upper quartile Q3 in the first data sequence; and determining the normal data range corresponding to the quartile operation: [L,H]=[Q1-k L I QR Q3+k H I QR ]; where Q1 is the lower quartile, k L Q3 is the lower limit coefficient of the interval, and Q4 is the upper quartile. H The upper limit coefficient of the interval distance, interquartile range I QR =Q3-Q1; Change the first label of the photovoltaic data group containing light intensity that does not fall within the normal data range to the second label; Determine k L With k H The process includes: calculating the standard deviation σ and mean μ of all light intensities in each photovoltaic dataset; and obtaining the coefficient of variation as follows: If (1-C) v (less than C) v Then k L =(1-C v ) / 1.5、k H =C v ×1.5; if (1-C v () greater than C v Then k L =C v / 1.5、k H =(1-C v )×1.5; The second operation unit is used to perform the quartile operation on all output power in each photovoltaic data set, and change the first label of the photovoltaic data group containing the output power that does not fall within the normal range of the quartile method to the second label. The merging unit is used to merge all photovoltaic data groups marked with the second tag in order to complete the marking of all abnormal photovoltaic data in the multiple photovoltaic data groups.

7. A storage medium, characterized in that, The storage medium includes stored instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the marking method for abnormal photovoltaic data as described in any one of claims 1-5.

8. An electronic device, characterized in that, It includes at least one processor, and at least one memory and bus connected to the processor; wherein the processor and memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the method for marking abnormal photovoltaic data as described in any one of claims 1-5.

Images