Multi-tuple-based photovoltaic operation data quality quantitative evaluation method and electronic equipment

Abstract

The invention provides a multi-tuple-based photovoltaic operation data quality quantitative evaluation method and electronic equipment, and belongs to the technical field of photovoltaic data quality evaluation, and the method comprises the steps: constructing a data quality evaluation model through a plurality of tuples, converting the data quality evaluation model into a data quality evaluation metadata model based on the tuple information of each tuple and the relationship between the tuple information, and calculating the weighted weight of a first weight and a second weight based on the first weight of a first-level data quality evaluation factor and the second weight of a second-level data quality evaluation factor, and evaluating the data quality of the photovoltaic operation data set based on the weighted weights. According to the scheme, the evaluation accuracy of the photovoltaic operation data can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic data quality assessment, and in particular to a photovoltaic operation data quality quantitative assessment method based on multi-tuples and an electronic device. Background Art

[0002] At present, data quality assessment is being continuously studied at home and abroad. However, in terms of power data quality assessment, the assessment of photovoltaic operation data quality is still in its infancy, and a relatively complete photovoltaic operation data quality assessment framework has not yet been formed. Moreover, the assessment of data is simply based on qualitative methods, and the combination of qualitative and quantitative data quality assessment is not achieved. The accuracy of photovoltaic operation data quality assessment is low.

[0003] Therefore, how to improve the accuracy of PV operation data quality assessment has become an issue that needs to be resolved. Summary of the invention

[0004] The purpose of this application is to provide a quantitative evaluation method for photovoltaic operation data quality based on multi-tuples, which can solve the problem of low accuracy of photovoltaic operation data quality evaluation in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for quantitatively evaluating photovoltaic operation data quality based on a multi-tuple, the method comprising: A data quality assessment model is constructed based on multiple tuples, wherein each tuple is a set; Based on the tuple information of each tuple and the relationship between them, the data quality assessment model is transformed into a data quality assessment metadata model; wherein the data quality assessment metadata model includes a first-level data quality assessment factor and a second-level data quality assessment factor; Calculating a weighted weight of the first weight and the second weight based on the first weight of the first-level data quality assessment factor and the second weight of the second-level data quality assessment factor; The data quality of the PV operation dataset was evaluated based on weighted weights.

[0006] In a possible implementation of the first aspect, the multiple tuples include: a data set tuple, an evaluation indicator tuple, a constraint rule tuple, a weight tuple, an expected value tuple, and an evaluation result tuple; the data quality assessment metadata model includes: a data dictionary metamodel, an evaluation indicator metamodel, an evaluation algorithm metamodel, and an evaluation result metamodel; The tuple information of the data set tuple, the evaluation index tuple, the constraint rule tuple, the weight tuple, the expected value tuple and the evaluation result tuple are respectively: data set, evaluation index, constraint rule, weight, expected value and evaluation result; the first-level data quality evaluation factor is the data quality evaluation index, and the second-level data quality evaluation factor is the constraint rule corresponding to the evaluation index; Based on the tuple information of each tuple and the relationship between them, the data quality assessment model is transformed into a data quality assessment metadata model, including: Based on the data set, evaluation indicators, constraint rules, weights, expected values, and evaluation results and the relationships between them, the data quality evaluation model is transformed into a data dictionary metamodel, an evaluation indicator metamodel, an evaluation algorithm metamodel, and an evaluation result metamodel; The data dictionary metamodel includes: a data source describing database information, a data table describing table information in the data source, and a data item describing field information in the data table, which is used to store photovoltaic operation data describing an entity; Evaluation index metamodel, used to store evaluation indexes and their weights, expected values ​​of PV operation data under evaluation indexes, relationships between evaluation indexes and constraint rules, and relationships between constraint rules and entity PV operation data; Evaluation algorithm metamodel, which is used to store the function information of data quality evaluation, the selected evaluation indicators, constraint rules and the mapping relationship between algorithms; Evaluation result metamodel, used to store evaluation indicators and their result information.

[0007] In a possible implementation of the first aspect, the evaluation indicators include: correctness, completeness, precision and effectiveness; the constraint rule corresponding to correctness is a non-outlier constraint rule, the constraint rule corresponding to completeness is a non-empty constraint rule, the constraint rule corresponding to precision is a precision constraint rule, and the constraint rule corresponding to effectiveness is: a format validity constraint rule and a value range validity constraint rule; the method further includes: Based on correctness, completeness, accuracy and effectiveness, photovoltaic operation data are tested respectively using non-outlier constraint rules, non-empty constraint rules, accuracy constraint rules, format validity constraint rules and range validity constraint rules.

[0008] In a possible implementation of the first aspect, the non-abnormal value constraint rule is that the data on the data item is not abnormal data, the non-empty constraint rule is that the data on the data item is not empty or lacks a field, the accuracy constraint rule is whether the accuracy of the data on the data item is greater than a preset accuracy threshold, the format validity constraint rule is that the data of any field conforms to a preset valid format, and the value domain validity constraint rule is that the data of any field conforms to a preset value domain range; Based on correctness, completeness, accuracy and effectiveness, the non-abnormal value constraint rules, non-empty constraint rules, accuracy constraint rules, format validity constraint rules and value range validity constraint rules are used to detect photovoltaic operation data, including: The photovoltaic operation data to be clustered are randomly sampled to obtain sampling data; for the sampling data, a two-stage minimum spanning tree algorithm is used to generate the optimal initial cluster number and cluster center; a cluster analysis algorithm is used to perform secondary clustering on each initial cluster data, and the secondary clustering data with a data volume less than a preset value is regarded as an abnormal data class to determine the correct data in the photovoltaic operation data to be clustered; Determine whether the data bits of the data item to be detected are valid according to whether the data item to be detected is transmitted to the storage layer in the data quality assessment model, so as to determine whether the data item to be detected has integrity; detect whether the accuracy of the data item to be detected is greater than the preset accuracy threshold according to the preset accuracy threshold of the data item to be detected, so as to determine whether the data item to be detected has accuracy; Determine whether the format of the data item to be detected is consistent with the preset valid format, determine whether the format of the data item to be detected is valid, and detect whether the size of the data item to be detected is within the preset value range to determine whether the data item to be detected is valid.

[0009] In a possible implementation of the first aspect, for the sampled data, a two-stage minimum spanning tree algorithm is used to generate an optimal initial number of clusters and cluster centers, including: Calculate the distance between photovoltaic operation data at each moment; The distance between data is used as the weight between nodes in the minimum spanning tree, and the time when the data is located is used as the node identifier. The results of each distance calculation are read into the Map Reduce framework in sequence, and then read into the Map Reduce framework in the form of key-value pairs to generate a child minimum spanning tree; wherein the key-value pair is [distance, (first data, second data)] or [weight, (first endpoint, second endpoint)]; The image formed by the photovoltaic operation data at each moment is divided to obtain multiple sub-images; Merge the sub-minimum spanning trees generated by each subgraph to generate a global minimum spanning tree; The global minimum spanning tree is branched according to the preset threshold determined by the silhouette coefficient method, the connection between nodes beyond the threshold range is cut off, the interconnected nodes are clustered to obtain the clustering results, and the clustering effect is judged according to the silhouette coefficient; Among them, for a certain node, the calculation formula of the silhouette coefficient is as follows:

[0010] in, represents the silhouette coefficient corresponding to a node, i represents the node ordinal number, represents the average distance between the vector of point i and the points in the same cluster. It represents the minimum average distance between the vector of point i and the points in different clusters. The value of the silhouette coefficient is between [-1, 1]. Accordingly, for the entire data set, the calculation formula of the silhouette coefficient is as follows:

[0011] in, Represents the silhouette coefficient corresponding to the entire data set, n represents the amount of data in the data set; the preset threshold is determined according to SC.

[0012] In a possible implementation of the first aspect, an output result of the minimum spanning tree is a plurality of key-value pairs sorted in ascending order by weight; and branching the global minimum spanning tree according to a preset threshold determined by a silhouette coefficient method includes: The median of the weights in the key-value pairs is calculated based on each key-value pair; starting from the median, the weights greater than or equal to the median are used as the preset thresholds for clustering in turn, and the global minimum spanning tree is branched.

[0013] In a possible implementation of the first aspect, the first weight is an evaluation indicator weight, and the second weight is a constraint rule weight; and based on the first weight of the first-level data quality assessment factor and the second weight of the second-level data quality assessment factor, calculating the weighted weight of the first weight and the second weight includes: The hierarchical structure of the photovoltaic operation data evaluation index system is established by using the hierarchical analysis method; according to the hierarchical structure, the evaluation index judgment matrix and the constraint rule judgment matrix are constructed; each indicator in the evaluation index and each rule in the constraint rule are compared in pairs, and the importance degree is assigned according to the comparison result to obtain the importance scale value; according to the importance scale value, the evaluation index judgment matrix and the constraint rule judgment matrix are assigned respectively, and the first assignment result and the second assignment result are obtained respectively; According to the first assignment result, the first eigenvalue and the first eigenvector of the evaluation index judgment matrix are calculated to obtain the first maximum eigenvalue and the corresponding first eigenvector, and according to the second assignment result, the second eigenvalue and the second eigenvector of the constraint rule judgment matrix are calculated to obtain the second maximum eigenvalue and the corresponding second eigenvector, and the first eigenvector is used as the evaluation index weight, and the second eigenvector is used as the constraint rule weight; The weighted weight is calculated based on the evaluation index weight and the constraint rule weight. The specific calculation formula is as follows:

[0014] in, represents the weighted weight, represents the evaluation index weight, represents the weight of the constraint rule, and Indicates an ordinal number.

[0015] In a possible implementation manner of the first aspect, the method further includes: The consistency index of the judgment matrix is ​​calculated based on the maximum eigenvalue and the matrix order. The specific calculation formula is as follows:

[0016] in, represents the consistency index of the judgment matrix, represents the maximum eigenvalue, represents the matrix order; The consistency ratio is calculated based on the average random consistency index and the consistency index of the judgment matrix. The specific calculation formula is as follows:

[0017] in represents the consistency ratio, represents the average random consistency index; Determine whether the consistency ratio is less than the preset threshold. If the consistency ratio is less than the preset threshold, it is determined that the judgment matrix meets the target consistency. If the consistency ratio is greater than or equal to the preset threshold, it is determined that the judgment matrix does not meet the target consistency requirements and the judgment matrix is ​​corrected.

[0018] In a possible implementation of the first aspect, evaluating the data quality of the photovoltaic operation data set based on the weighted weight includes: Calculate the qualified rates of multiple PV operation data sets based on the amount of data that meets the evaluation indicators and the total amount of data; The comprehensive evaluation value of data quality is calculated based on the weighted weight and the qualified rate. The specific calculation formula is as follows:

[0019] in, Represents the comprehensive evaluation value of data quality, represents the qualified rate of each PV operation data set, and n represents the maximum ordinal number; Calculate individual expected values ​​of data quality based on each PV operation data set and the corresponding pass rate; The comprehensive expected value of data quality is calculated based on the weighted weight and expected value. The specific calculation formula is as follows:

[0020] in, Represents the comprehensive expected value of data quality, Indicates individual expected values ​​of data quality; The data quality difference value is calculated based on the comprehensive data quality evaluation value and the comprehensive data quality expected value. The specific calculation formula is as follows:

[0021] in, Indicates the data quality difference value; The data quality of each PV operation dataset was evaluated based on the data quality difference value.

[0022] In a possible implementation manner of the first aspect, the method further includes: The first evaluation level of the first data range of the comprehensive data quality evaluation value is classified as excellent, the second evaluation level of the second data range of the comprehensive data quality evaluation value is classified as good, and the third evaluation level of the third data range of the comprehensive data quality evaluation value is classified as poor; based on the first evaluation level, the second evaluation level and the third evaluation level, the data quality of each photovoltaic operation data set is evaluated.

[0023] In a second aspect, an embodiment of the present application provides a photovoltaic operation data quality quantitative assessment device based on a multi-tuple, the device comprising: A construction unit, used for constructing a data quality assessment model based on a plurality of tuples; wherein each tuple is a set; A transformation unit, used to transform the data quality assessment model into a data quality assessment metadata model based on tuple information of each tuple and the relationship between them; wherein the data quality assessment metadata model includes first-level data quality assessment factors and second-level data quality assessment factors; A calculation unit, configured to calculate a weighted weight of the first weight and the second weight based on the first weight of the first-level data quality assessment factor and the second weight of the second-level data quality assessment factor; An evaluation unit is used to evaluate the data quality of the photovoltaic operation data set based on the weighted weights.

[0024] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any one of the quantitative evaluation methods for photovoltaic operation data quality based on a multi-tuple in the first aspect described above is implemented.

[0025] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements any of the quantitative evaluation methods for photovoltaic operation data quality based on multi-tuples in the above-mentioned first aspect.

[0026] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is executed on an electronic device, the electronic device executes any one of the photovoltaic operation data quality quantitative assessment methods based on multi-tuples in the first aspect.

[0027] The solution of the present application constructs a data quality assessment model through multiple tuples, transforms the data quality assessment model into a data quality assessment metadata model based on the tuple information of each tuple and the relationship between them, calculates the weighted weight of the first weight and the second weight based on the first weight of the first-level data quality assessment factor and the second weight of the second-level data quality assessment factor, and evaluates the data quality of the photovoltaic operation data set based on the weighted weight.

[0028] This application scheme can improve the evaluation accuracy of photovoltaic operation data and has strong ease of use and practicality.

[0029] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0031] Figure 1 It is a schematic diagram of the steps of the photovoltaic operation data quality quantitative evaluation method based on multi-tuples provided in an embodiment of the present application; Figure 2 is a schematic diagram of a data dictionary metamodel provided in an embodiment of the present application; Figure 3 is a schematic diagram of an evaluation indicator metamodel provided in an embodiment of the present application; Figure 4 is a schematic diagram of an evaluation algorithm metamodel provided in an embodiment of the present application; Figure 5 is a schematic diagram of an evaluation result metamodel provided in an embodiment of the present application; Figure 6 It is a flowchart of Map Reduce of the minimum spanning tree algorithm provided in the embodiment of the present application; Figure 7 It is a schematic diagram of a process for generating a global minimum spanning tree provided in an embodiment of the present application; Figure 8 It is a schematic diagram of the hierarchical hierarchy of factors of the photovoltaic evaluation system provided in the embodiment of the present application; Fig. 9It is a schematic diagram of a process for generating a global minimum spanning tree provided in an embodiment of the present application; Fig.10 is a schematic diagram of the evaluation process provided in an embodiment of the present application; Fig.11 is a schematic diagram of the structure of a photovoltaic operation data quality quantitative assessment device based on multi-tuples provided in an embodiment of the present application; Fig.12 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0033] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or photovoltaic components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, photovoltaic components and / or combinations thereof.

[0034] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0035] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0036] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0037] In addition, in the description of the present application, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0038] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0039] In today's era of big data, photovoltaic operation data is growing exponentially. As important data reflecting the status of photovoltaic systems, its quality management has become a key link in data management in photovoltaic systems today, and data quality assessment is the basis of data quality management. However, the current evaluation of photovoltaic operation data generally takes a qualitative approach to judge data quality and lacks a quantitative evaluation method.

[0040] While photovoltaic operation data plays an increasingly important role, more and more research is being conducted on data quality issues. There are mainly the following ways to deal with photovoltaic operation data quality issues: data cleaning, data quality assessment, data quality process control management, etc. Among all the links in data quality management, data quality assessment is a necessary process and basic part of data quality management. It can comprehensively inspect and evaluate the quality status of the entire or partial data of the power system, reflect the current situation of the power system data quality, help relevant personnel to promptly discover data quality problems and take corresponding measures to process the data, thereby improving the credibility and effectiveness of the data.

[0041] At present, data quality assessment is being continuously studied at home and abroad. However, in terms of power data quality assessment, the assessment of photovoltaic operation data quality is still in its infancy, and a relatively complete photovoltaic operation data quality assessment framework has not yet been formed. Moreover, the assessment of data is simply based on qualitative methods, and the combination of qualitative and quantitative data quality assessment has not been achieved.

[0042] Simply relying on qualitative analysis cannot intuitively reflect the quality of photovoltaic operation data, and has limited effect on improving data quality. In addition, simply using abnormal data as an indicator for data evaluation cannot fully reflect the data situation. Therefore, an evaluation index system should be established. When establishing an evaluation index system, the differences in the importance of indicators should be considered. The differences in the importance of indicators should be reflected by assigning weights to indicators.

[0043] However, the existing weight assignment methods, whether subjective or objective, have certain limitations. In addition, most of the existing data evaluation and storage programs are developed for databases without considering their versatility and flexibility. Once the data model changes, a large number of code changes are required. In addition, the accuracy of photovoltaic operation data quality assessment is low. Therefore, in order to conduct a comprehensive and intuitive evaluation of the quality of photovoltaic operation data, it is necessary to establish a model that combines quantitative and qualitative data quality assessment based on the characteristics of the data.

[0044] In response to the above-mentioned defects, an embodiment of the present application provides a quantitative assessment method for photovoltaic operation data quality based on tuples, which constructs a data quality assessment model through multiple tuples, transforms the data quality assessment model into a data quality assessment metadata model based on tuple information of each tuple and the relationship between them, calculates the weighted weight of the first weight and the second weight based on the first weight of the first-level data quality assessment factor and the second weight of the second-level data quality assessment factor, and evaluates the data quality of the photovoltaic operation data set based on the weighted weight.

[0045] This application scheme can improve the evaluation accuracy of photovoltaic operation data and has strong ease of use and practicality.

[0046] The specific process implemented by this application is introduced below through specific embodiments.

[0047] See also Figure 1 , Figure 1 Schematic diagram of the steps of the method for quantitatively evaluating the quality of photovoltaic operation data based on multi-tuples provided in the embodiment of the present application. Figure 1 As shown, the method may include the following steps: S101, constructing a data quality assessment model based on multiple tuples; wherein each tuple is a set.

[0048] In some embodiments, the data quality assessment model is composed of a six-tuple: M=<D,I,R,W,E,S> . Each tuple represents a set. D: the data set to be evaluated, I: the indicator to be evaluated on the data set, R: the specific constraint rules under the evaluation indicator, W: the weight assigned to the evaluation indicator; E: the expected value given to indicator I, which is the expected target of the data compliance rate under the indicator; S: the final result corresponding to indicator I, which is the result obtained after detection.

[0049] S102, based on the tuple information of each tuple and the relationship between them, transform the data quality assessment model into a data quality assessment metadata model; wherein the data quality assessment metadata model includes first-level data quality assessment factors and second-level data quality assessment factors.

[0050] According to an embodiment of the present application, the plurality of tuples include: a data set tuple, an evaluation index tuple, a constraint rule tuple, a weight tuple, an expected value tuple, and an evaluation result tuple; the data quality evaluation metadata model includes: a data dictionary metamodel (such as Figure 2 As shown in ), evaluation indicator metamodel (such as Figure 3 As shown in ), the evaluation algorithm metamodel (as Figure 4 ) and the evaluation result metamodel (as shown in Figure 5 shown); The tuple information of the data set tuple, the evaluation index tuple, the constraint rule tuple, the weight tuple, the expected value tuple and the evaluation result tuple are respectively: data set, evaluation index, constraint rule, weight, expected value and evaluation result; the first-level data quality evaluation factor is the data quality evaluation index, and the second-level data quality evaluation factor is the constraint rule corresponding to the evaluation index; Based on the tuple information of each tuple and the relationship between them, the data quality assessment model is transformed into a data quality assessment metadata model, including: Based on the data set, evaluation indicators, constraint rules, weights, expected values, and evaluation results and the relationships between them, the data quality evaluation model is transformed into a data dictionary metamodel, an evaluation indicator metamodel, an evaluation algorithm metamodel, and an evaluation result metamodel; The data dictionary metamodel includes: a data source describing database information, a data table describing table information in the data source, and a data item describing field information in the data table, which is used to store photovoltaic operation data describing an entity; Evaluation index metamodel, used to store evaluation indexes and their weights, expected values ​​of PV operation data under evaluation indexes, relationships between evaluation indexes and constraint rules, and relationships between constraint rules and entity PV operation data; Evaluation algorithm metamodel, which is used to store the function information of data quality evaluation, the selected evaluation indicators, constraint rules and the mapping relationship between algorithms; Evaluation result metamodel, used to store evaluation indicators and their result information.

[0051] In some embodiments, the structure of each tuple of the evaluation model is designed in combination with the meta-model. These tables are used to store the data of each tuple, and data such as evaluation indicators are extracted from the tables during data evaluation. Constraint rules are called according to the selected indicators for different fields in the data table, and finally the corresponding algorithm is called to detect the data, and finally the final result is obtained through calculation.

[0052] According to an implementation of the present application, the evaluation indicators include: correctness, completeness, precision and effectiveness; the constraint rule corresponding to correctness is a non-outlier constraint rule, the constraint rule corresponding to completeness is a non-empty constraint rule, the constraint rule corresponding to accuracy is an accuracy constraint rule, and the constraint rule corresponding to effectiveness is: a format validity constraint rule and a value range validity constraint rule; the method also includes: Based on correctness, completeness, accuracy and effectiveness, photovoltaic operation data are tested respectively using non-outlier constraint rules, non-empty constraint rules, accuracy constraint rules, format validity constraint rules and range validity constraint rules.

[0053] Among them, correctness means that the data must truly and accurately reflect the operating status, completeness means describing whether there is data missing in the data table, precision means describing whether the accuracy of the attribute value meets the requirements, and validity includes two aspects: data format and numerical range.

[0054] According to an implementation of the present application, the non-abnormal value constraint rule is that the data on the data item is not abnormal data, the non-empty constraint rule is that the data on the data item is not empty or lacks a field, the accuracy constraint rule is whether the accuracy of the data on the data item is greater than a preset accuracy threshold, the format validity constraint rule is that the data of any field conforms to the preset valid format, and the value domain validity constraint rule is that the data of any field conforms to the preset value domain range; Based on correctness, completeness, accuracy and effectiveness, the non-abnormal value constraint rules, non-empty constraint rules, accuracy constraint rules, format validity constraint rules and value range validity constraint rules are used to detect photovoltaic operation data, including: The photovoltaic operation data to be clustered are randomly sampled to obtain sampling data; for the sampling data, a two-stage minimum spanning tree algorithm is used to generate the optimal initial cluster number and cluster center; a cluster analysis algorithm (such as k-means algorithm, k-means clustering algorithm, k-means clustering algorithm) is used to perform secondary clustering on each initial cluster data, and the secondary clustering data with a data volume less than a preset value is regarded as an abnormal data class to determine the correct data in the photovoltaic operation data to be clustered. The specific process diagram is as follows Figure 6 As shown; According to whether the data item to be detected is transmitted to the storage layer in the data quality assessment model, it is determined whether the data bit of the data item to be detected is valid, so as to determine whether the data item to be detected has integrity. If the data item to be detected cannot be transmitted to the storage layer in the data quality assessment model, it is determined that the data bit of the data item to be detected is invalid (null), and the data item to be detected does not have integrity.

[0055] According to a preset accuracy threshold of the data item to be detected, detecting whether the accuracy of the data item to be detected is greater than the preset accuracy threshold, so as to determine whether the data item to be detected has accuracy; Determine whether the format of the data item to be detected is consistent with the preset valid format, determine whether the format of the data item to be detected is valid, and detect whether the size of the data item to be detected is within the preset value range to determine whether the data item to be detected is valid.

[0056] According to an implementation of the present application, for the sampled data, a two-stage minimum spanning tree algorithm is used to generate the optimal initial number of clusters and cluster centers, including: Calculate the distance between photovoltaic operation data at each moment; The distance between data is used as the weight between nodes in the minimum spanning tree, and the time when the data is located is used as the node identifier. The results of each distance calculation are read into the Map Reduce framework in sequence, and then read into the Map Reduce framework in the form of key-value pairs to generate a child minimum spanning tree; wherein the key-value pair is [distance, (first data, second data)] or [weight, (first endpoint, second endpoint)]; The image formed by the photovoltaic operation data at each moment is divided to obtain multiple sub-images; The sub-minimum spanning trees generated by each sub-graph are merged, and the global minimum spanning tree is generated using the Kruskal algorithm. The specific process diagram is as follows Figure 7 As shown; The global minimum spanning tree is branched according to the preset threshold determined by the silhouette coefficient method, the connection between nodes beyond the threshold range is cut off, the interconnected nodes are clustered to obtain the clustering results, and the clustering effect is judged according to the silhouette coefficient; Among them, for a certain node, the calculation formula of the silhouette coefficient is as follows:

[0057] in, represents the silhouette coefficient corresponding to a node, i represents the node ordinal number, represents the average distance between the vector of point i and the points in the same cluster. It represents the minimum average distance between the vector of point i and the points in different clusters. The value of the silhouette coefficient is between [-1, 1]. Accordingly, for the entire data set, the calculation formula of the silhouette coefficient is as follows:

[0058] in, Represents the silhouette coefficient corresponding to the entire data set, n represents the amount of data in the data set; the preset threshold is determined according to SC.

[0059] According to an implementation manner of the present application, the output result of the minimum spanning tree is a plurality of key-value pairs sorted from small to large by weight; and the global minimum spanning tree is branched according to a preset threshold determined by the silhouette coefficient method, including: The median of the weights in the key-value pairs is calculated based on each key-value pair; starting from the median, the weights greater than or equal to the median are used as the preset thresholds for clustering in turn, and the global minimum spanning tree is branched.

[0060] S103: Calculate a weighted weight of the first weight and the second weight based on the first weight of the first-level data quality assessment factor and the second weight of the second-level data quality assessment factor.

[0061] According to an implementation manner of the present application, the first weight is the evaluation indicator weight, and the second weight is the constraint rule weight; based on the first weight of the first-level data quality evaluation factor and the second weight of the second-level data quality evaluation factor, the weighted weight of the first weight and the second weight is calculated, including: The hierarchical structure of the photovoltaic operation data evaluation index system is established by using the hierarchical analysis method; according to the hierarchical structure, the evaluation index judgment matrix and the constraint rule judgment matrix are constructed; each indicator in the evaluation index and each rule in the constraint rule are compared pairwise, and the importance degree is assigned according to the comparison result to obtain the importance scale value; according to the importance scale value, the evaluation index judgment matrix and the constraint rule judgment matrix are assigned respectively to obtain the first assignment result and the second assignment result respectively.

[0062] In some embodiments, the analytic hierarchy process is used to establish a photovoltaic operation data evaluation index system hierarchy, such as Figure 8 As shown. Combining the existing evaluation index importance measurement problem, a hierarchical structure is constructed. The hierarchy is divided into: target layer: evaluation index importance measurement; criterion layer: data quality evaluation index; measure layer: evaluation index constraint rules. Completeness, correctness, accuracy and effectiveness are selected as evaluation indicators.

[0063] In some embodiments, the importance degree is assigned a value of 1-9, and the importance scale values ​​are shown in Table 1. The evaluation index judgment matrix is ​​shown in Table 2, and the constraint rule judgment matrix is ​​shown in Table 3.

[0064] Table 1

[0065] Table 2

[0066] In one embodiment, Table 2 is:

[0067] Table 3

[0068] According to the first assignment result, the first eigenvalue and the first eigenvector of the evaluation index judgment matrix are calculated to obtain the first maximum eigenvalue and the corresponding first eigenvector, and according to the second assignment result, the second eigenvalue and the second eigenvector of the constraint rule judgment matrix are calculated to obtain the second maximum eigenvalue and the corresponding second eigenvector, and the first eigenvector is used as the evaluation index weight, and the second eigenvector is used as the constraint rule weight.

[0069] Combined with the photovoltaic data type evaluation standard, the linear weighted method is used for evaluation and a mathematical model is established. The weighted weight is calculated based on the evaluation index weight and the constraint rule weight. The specific calculation formula is as follows:

[0070] in, Represents the weighted weight of the constraint rules under each indicator of the entire photovoltaic evaluation system, represents the evaluation index weight, represents the weight of the constraint rule, and Indicates an ordinal number.

[0071] According to one embodiment of the present application, the method further includes: The consistency index of the judgment matrix is ​​calculated based on the maximum eigenvalue and the matrix order. The specific calculation formula is as follows:

[0072] in, represents the consistency index of the judgment matrix, represents the maximum eigenvalue, represents the matrix order; The consistency ratio is calculated based on the average random consistency index and the consistency index of the judgment matrix. The specific calculation formula is as follows:

[0073] in, represents the consistency ratio, represents the average random consistency index.

[0074] In one embodiment, the average random consistency index RI table is shown in Table 4. It is determined whether the consistency ratio is less than a preset threshold. If the consistency ratio is less than the preset threshold, it is determined that the judgment matrix meets the target consistency. If the consistency ratio is greater than or equal to the preset threshold, it is determined that the judgment matrix does not meet the target consistency requirement, and the judgment matrix is ​​corrected.

[0075] Table 4

[0076] In one embodiment, the consistency ratio CR is calculated and judged. When CR<0.1, it is considered that the judgment matrix meets the consistency requirement, and when CR>0.1, it is considered that the judgment matrix does not meet the consistency requirement and needs to be revised.

[0077] In one embodiment, the weighted weight calculation results of the impact indicators at each level are shown in Table 5.

[0078] Table 5

[0079] S104, evaluating the data quality of the photovoltaic operation data set based on the weighted weights.

[0080] According to an embodiment of the present application, evaluating the data quality of a photovoltaic operation data set based on weighted weights includes: Calculate the qualified rates of multiple PV operation data sets based on the amount of data that meets the evaluation indicators and the total amount of data; The comprehensive evaluation value of data quality is calculated based on the weighted weight and the qualified rate. The specific calculation formula is as follows:

[0081] in, Represents the comprehensive evaluation value of data quality, represents the qualified rate of each PV operation data set, and n represents the maximum ordinal number; Calculate individual expected values ​​of data quality based on each PV operation data set and the corresponding pass rate; The comprehensive expected value of data quality is calculated based on the weighted weight and expected value. The specific calculation formula is as follows:

[0082] in, Represents the comprehensive expected value of data quality, Indicates individual expected values ​​of data quality; The data quality difference value is calculated based on the comprehensive data quality evaluation value and the comprehensive data quality expected value. The specific calculation formula is as follows:

[0083] in, Indicates the data quality difference value; The data quality of each PV operation dataset was evaluated based on the data quality difference value.

[0084] In one embodiment, evaluation reflects the actual status of data quality, which is obtained by weighted average of the weight coefficient of the indicator and the percentage of data that meets the evaluation indicator; expected reflects the overall expectation of data quality, which is obtained by weighted average of the expected value of the percentage of data that meets the evaluation indicator under each indicator and the weight coefficient of the indicator; difference reflects the data quality status of the data relative to its expected value. If the difference is greater than 0, it means that the data quality is better than expected; otherwise, it means that the data quality is worse than expected.

[0085] According to one embodiment of the present application, the method further includes: The first evaluation level of the first data range of the comprehensive data quality evaluation value is classified as excellent, the second evaluation level of the second data range of the comprehensive data quality evaluation value is classified as good, and the third evaluation level of the third data range of the comprehensive data quality evaluation value is classified as poor; based on the first evaluation level, the second evaluation level and the third evaluation level, the data quality of each photovoltaic operation data set is evaluated.

[0086] In one embodiment, a grade is set for each data range of the comprehensive evaluation value, and it is intended to set the grade within [95, 100] as "excellent", the grade within [90, 95) as "good", the grade within [85, 90) as "medium", and the grade within [0, 85) as "poor". The qualitative and quantitative combination of data quality assessment is achieved by calculating the comprehensive evaluation value and setting the grade.

[0087] According to an implementation of the present application, the quality assessment model structure is divided into a storage layer, a computing layer, a control layer and an application layer. Fig. 9As shown in the figure, the specific functions are described as follows: Storage layer: The storage layer stores the photovoltaic operation data, and HDFS (Hadoop Distributed File System) reads the corresponding data to meet the upper-layer computing task requirements. Computing layer: The computing layer uses Map Reduce as a method to process tasks. The computing layer reads data from the storage layer by executing the computing tasks of the control layer. The computing layer uses Map and Reduce functions to implement parallel execution of computing tasks. Control layer: HiveQL and SQL constitute the main part of the control layer. HiveQL is used to parse the request of the application layer, and then a Map Reduce job is generated and passed to the computing layer. The results generated by the computing layer after calculation are returned to the user through the user interface of the application layer. SQL is used to manage Hive table information. Application layer: The application layer provides a series of user interfaces to facilitate operations such as submitting user requests and viewing data quality assessment results.

[0088] In some embodiments, the photovoltaic operation data quality assessment process based on the storage layer, computing layer, control layer and application layer is as follows: Import PV operation data and indicators into HDFS. When conducting data quality assessment, use HiveQL query statements to operate on the required data and extract data and required indicators and their constraint rules from the PV operation data warehouse. After the data acquisition work is completed, use MapReduce to combine the evaluation indicators and each data item in the data table to call the corresponding rules and corresponding detection methods from the evaluation rule table to detect the data. Finally, the evaluation results obtained after the data detection result is calculated are returned to the user and stored in the data warehouse on HDFS.

[0089] The embodiment of the present application provides a quantitative evaluation method for photovoltaic operation data quality based on tuples. A data quality evaluation model is constructed through multiple tuples. The data quality evaluation model is transformed into a data quality evaluation metadata model based on tuple information of each tuple and the relationship between them. Based on the first weight of the first-level data quality evaluation factor and the second weight of the second-level data quality evaluation factor, a weighted weight of the first weight and the second weight is calculated, and the data quality of the photovoltaic operation data set is evaluated based on the weighted weight.

[0090] This application scheme can improve the evaluation accuracy of photovoltaic operation data and has strong ease of use and practicality.

[0091] First of all, this evaluation method realizes the combination of qualitative and quantitative data quality evaluation. Compared with the previous simple data level, the quantitative results of data allow users to better understand the data quality. In addition, the use of hierarchical analysis method to calculate the evaluation index weights in a qualitative and quantitative way makes the evaluation results more in line with actual needs.

[0092] In addition, the sextuple-based evaluation model can achieve data quality assessment by adding or reducing fields on the basis of the original metamodel by changing or adding a small amount of code when the evaluation data or evaluation indicators increase. Therefore, the model has greater flexibility.

[0093] This solution aims at the problem of photovoltaic operation data quality assessment. It uses a six-tuple-based data quality assessment model to establish an evaluation index system for the model and quantify the importance of indicators by weight assignment. It also designs the structure and evaluation method of the model. The model can evaluate the data quality status by combining quantitative and qualitative methods.

[0094] A data quality assessment model based on six-tuples was established, and a corresponding storage table structure was designed for the model to store the corresponding information and reflect the relationship between the tuples. Secondly, based on the evaluation indicators, a corresponding evaluation method needs to be designed for each indicator to detect the data. Finally, based on the quantitative and qualitative characteristics of the evaluation model, each indicator is weighted to quantify its importance, and a weight calculation method needs to be designed during this period.

[0095] The k-means method based on agglomerative hierarchical clustering is used to detect abnormal data. The data is clustered once using the agglomerative hierarchical clustering method, and the clustering results are judged using the silhouette coefficient to obtain a more reasonable number of clusters and cluster centers, avoiding the phenomenon of unstable clustering results caused by the randomness of the selection of initial cluster centers and the number of clusters in traditional k-mean clustering.

[0096] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0097] Corresponding to the method of the above embodiment, Fig.11 A structural block diagram of a photovoltaic operation data quality quantitative assessment device based on multi-tuples provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0098] Reference Fig.11 , which includes: A construction unit 111 is used to construct a data quality assessment model based on multiple tuples, wherein each tuple is a set; A transformation unit 112, configured to transform the data quality assessment model into a data quality assessment metadata model based on tuple information of each tuple and the relationship between them; wherein the data quality assessment metadata model includes a first-level data quality assessment factor and a second-level data quality assessment factor; A calculation unit 113, configured to calculate a weighted weight of the first weight and the second weight based on the first weight of the first-level data quality assessment factor and the second weight of the second-level data quality assessment factor; The evaluation unit 114 is used to evaluate the data quality of the photovoltaic operation data set based on the weighted weight.

[0099] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0100] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0101] Fig.12 FIG. 1 is a schematic diagram of the structure of an electronic device 12 provided in an embodiment of the present application. Fig.12 As shown, the electronic device 12 of this embodiment includes: at least one processor 121 ( Fig.12 Only one is shown in the figure), a memory 123, and a computer program 122 stored in the memory 123 and executable on at least one processor 121, and when the processor 121 executes the computer program 122, the steps in the above method embodiment are implemented.

[0102] The electronic device 12 may be a computing device such as a desktop computer, a notebook, a PDA, or a mobile phone. The electronic device 12 may include, but is not limited to, a processor 121 and a memory 123. Those skilled in the art will appreciate that Fig.12 It is only an example of the electronic device 12 and does not constitute a limitation on the electronic device 12. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0103] The processor 121 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware photovoltaic modules, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0104] In some embodiments, the memory 123 may be an internal storage unit of the electronic device 12, such as a hard disk or memory of the electronic device 12. In other embodiments, the memory 123 may also be an external storage device of the electronic device 12, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital card (SecureDigital, SD), a flash card (Flash Card), etc. equipped on the electronic device 12. Further, the memory 123 may also include both an internal storage unit of the electronic device 12 and an external storage device. The memory 123 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as program codes of computer programs, etc. The memory 123 may also be used to temporarily store data that has been output or is to be output.

[0105] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, when the present application implements all or part of the processes in the above-mentioned embodiment method, it can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps applied to the above-mentioned method embodiment. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may at least include: any entity or device that can carry the computer program code to the computing device / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, such as USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable storage media cannot be electric carrier signals and telecommunication signals.

[0106] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0107] An embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the steps in the above-mentioned method embodiments.

[0108] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0109] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0110] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. The device / electronic device embodiments described above are merely schematic, and the division of the above modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or photovoltaic components can be combined or integrated into another system, and some features can be ignored and not executed. Another point is that the indirect coupling, direct coupling or communication connection between each other shown or discussed can be an indirect coupling, direct coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0111] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A quantitative evaluation method for photovoltaic operation data quality based on multi-tuples, characterized in that: The method comprises: A data quality assessment model is constructed based on multiple tuples, wherein each tuple is a set; Based on the tuple information of each tuple and the relationship between them, the data quality assessment model is transformed into a data quality assessment metadata model; wherein the data quality assessment metadata model includes a first-level data quality assessment factor and a second-level data quality assessment factor; Calculating a weighted weight of the first weight and the second weight based on a first weight of the first-level data quality assessment factor and a second weight of the second-level data quality assessment factor; The data quality of the photovoltaic operation data set is evaluated based on the weighted weights.

2. The photovoltaic operation data quality quantitative evaluation method based on multi-tuple according to claim 1 is characterized in that: The multiple tuples include: a data set tuple, an evaluation index tuple, a constraint rule tuple, a weight tuple, an expected value tuple, and an evaluation result tuple; the data quality evaluation metadata model includes: a data dictionary metamodel, an evaluation index metamodel, an evaluation algorithm metamodel, and an evaluation result metamodel; The tuple information of the data set tuple, the evaluation index tuple, the constraint rule tuple, the weight tuple, the expected value tuple and the evaluation result tuple are respectively: data set, evaluation index, constraint rule, weight, expected value and evaluation result; the first-level data quality assessment factor is the data quality assessment index, and the second-level data quality assessment factor is the constraint rule corresponding to the evaluation index; Based on the tuple information of each tuple and the relationship between them, the data quality assessment model is transformed into a data quality assessment metadata model, including: Based on the data set, evaluation indicators, constraint rules, weights, expected values, and evaluation results and the relationship between them, the data quality evaluation model is transformed into a data dictionary metamodel, an evaluation indicator metamodel, an evaluation algorithm metamodel, and an evaluation result metamodel; The data dictionary metamodel includes: a data source describing database information, a data table describing table information in the data source, and a data item describing field information in the data table, which is used to store photovoltaic operation data describing an entity; The evaluation index metamodel is used to store the evaluation index and its weight, the expected value of the photovoltaic operation data under the evaluation index, the relationship between the evaluation index and the constraint rule, and the relationship between the constraint rule and the photovoltaic operation data of the entity; The evaluation algorithm metamodel is used to store function information of data quality evaluation, selected evaluation indicators, constraint rules and mapping relationships between algorithms; The evaluation result meta-model is used to store the evaluation indicators and their result information.

3. The photovoltaic operation data quality quantitative evaluation method based on multi-tuple according to claim 2 is characterized in that: The evaluation indicators include: correctness, completeness, precision and effectiveness; the constraint rules corresponding to correctness are non-outlier constraint rules, the constraint rules corresponding to completeness are non-empty constraint rules, the constraint rules corresponding to accuracy are precision constraint rules, and the constraint rules corresponding to effectiveness are: format validity constraint rules and value range validity constraint rules; the method also includes: Based on correctness, completeness, accuracy and effectiveness, the photovoltaic operation data are respectively detected by non-abnormal value constraint rules, non-empty constraint rules, accuracy constraint rules, format validity constraint rules and value range validity constraint rules.

4. The photovoltaic operation data quality quantitative evaluation method based on multi-group according to claim 3 is characterized in that: The non-abnormal value constraint rule is that the data on the data item is not abnormal data, the non-empty constraint rule is that the data on the data item is not empty or missing fields, the accuracy constraint rule is whether the accuracy of the data on the data item is greater than the preset accuracy threshold, the format validity constraint rule is that the data in any field conforms to the preset valid format, and the value range validity constraint rule is that the data in any field conforms to the preset value range; Based on correctness, completeness, accuracy and effectiveness, non-abnormal value constraint rules, non-empty constraint rules, accuracy constraint rules, format validity constraint rules and value range validity constraint rules, the photovoltaic operation data is tested respectively, including: The photovoltaic operation data to be clustered are randomly sampled to obtain sampled data; for the sampled data, a two-stage minimum spanning tree algorithm is used to generate the optimal initial cluster number and cluster center; a cluster analysis algorithm is used to perform secondary clustering on each initial cluster data, and the secondary clustering data with a data volume less than a preset value is regarded as an abnormal data class to determine the correct data in the photovoltaic operation data to be clustered; Determining whether the data bits of the data item to be detected are valid according to whether the data item to be detected is transmitted to the storage layer in the data quality assessment model, so as to determine whether the data item to be detected has integrity; According to the preset accuracy threshold of the data item to be detected, detecting whether the accuracy of the data item to be detected is greater than the preset accuracy threshold, so as to determine whether the data item to be detected has accuracy; Determine whether the format of the data item to be detected is consistent with the preset valid format, determine whether the format of the data item to be detected is valid, and detect whether the size of the data item to be detected is within the preset value range to determine whether the data item to be detected is valid.

5. The photovoltaic operation data quality quantitative evaluation method based on multi-group according to claim 4 is characterized in that: For the sampled data, a two-stage minimum spanning tree algorithm is used to generate the optimal initial number of clusters and cluster centers, including: Calculate the distance between photovoltaic operation data at each moment; The distance between data is used as the weight between nodes in the minimum spanning tree, the time when the data is located is used as the node identifier, and each distance calculation result is read into the Map Reduce framework in sequence, and read into the MapReduce framework in the form of a key-value pair to generate a child minimum spanning tree; wherein the key-value pair is [distance, (first data, second data)] or [weight, (first endpoint, second endpoint)]; The image formed by the photovoltaic operation data at each moment is divided to obtain multiple sub-images; Merge the sub-minimum spanning trees generated by each subgraph to generate a global minimum spanning tree; The global minimum spanning tree is branched according to a preset threshold value determined by the silhouette coefficient method, the connection between nodes beyond the threshold range is cut off, the interconnected nodes are clustered to obtain a clustering result, and the clustering effect is judged according to the silhouette coefficient; Among them, for a certain node, the calculation formula of the silhouette coefficient is as follows: in, Represents the silhouette coefficient corresponding to a node, i represents the node ordinal number, express i The average distance from a point vector to the points in the same cluster, express i The minimum average distance between a point vector and its different cluster points, the value of the silhouette coefficient is between [-1, 1]; Accordingly, for the entire data set, the calculation formula of the silhouette coefficient is as follows: in, Represents the silhouette coefficient corresponding to the entire data set, n Indicates the amount of data in the data set; the preset threshold is based on SC Sure.

6. The photovoltaic operation data quality quantitative evaluation method based on multi-group according to claim 5 is characterized in that: The output of the minimum spanning tree is a number of key-value pairs sorted from small to large by weight; Branching the global minimum spanning tree according to a preset threshold determined by the silhouette coefficient method includes: Calculate the median of the weights in the key-value pairs based on each key-value pair; Starting from the median, weights greater than or equal to the median are sequentially used as preset thresholds for clustering, and the global minimum spanning tree is branched.

7. The photovoltaic operation data quality quantitative evaluation method based on multi-tuples according to claim 2 is characterized in that: The first weight is the evaluation index weight, and the second weight is the constraint rule weight; Calculating a weighted weight of the first weight and the second weight based on the first weight of the first-level data quality assessment factor and the second weight of the second-level data quality assessment factor includes: The hierarchical structure of the photovoltaic operation data evaluation index system is established using the analytic hierarchy process; According to the hierarchical structure, construct an evaluation index judgment matrix and a constraint rule judgment matrix; Compare each indicator in the evaluation indicator and each rule in the constraint rule in pairs, assign a value to the importance degree according to the comparison result, and obtain an importance scale value; Assigning values ​​to the evaluation index judgment matrix and the constraint rule judgment matrix according to the importance scale value, respectively, to obtain a first assignment result and a second assignment result; Calculate the first eigenvalue and the first eigenvector of the evaluation index judgment matrix according to the first assignment result to obtain the first maximum eigenvalue and the corresponding first eigenvector, and calculate the second eigenvalue and the second eigenvector of the constraint rule judgment matrix according to the second assignment result to obtain the second maximum eigenvalue and the corresponding second eigenvector, use the first eigenvector as the evaluation index weight, and use the second eigenvector as the constraint rule weight; The weighted weight is calculated based on the evaluation index weight and the constraint rule weight. The specific calculation formula is as follows: in, represents the weighted weight, represents the evaluation index weight, represents the weight of the constraint rule, and Indicates an ordinal number.

8. The photovoltaic operation data quality quantitative evaluation method based on multi-group according to claim 7 is characterized in that: The method further comprises: The consistency index of the judgment matrix is ​​calculated based on the maximum eigenvalue and the matrix order. The specific calculation formula is as follows: in, represents the consistency index of the judgment matrix, represents the maximum eigenvalue, represents the matrix order; The consistency ratio is calculated according to the average random consistency index and the consistency index of the judgment matrix. The specific calculation formula is as follows: in, represents the consistency ratio, represents the average random consistency index; Determine whether the consistency ratio is less than a preset threshold. If the consistency ratio is less than the preset threshold, determine that the judgment matrix meets the target consistency. If the consistency ratio is greater than or equal to the preset threshold, determine that the judgment matrix does not meet the target consistency requirements, and correct the judgment matrix.

9. The photovoltaic operation data quality quantitative evaluation method based on multi-tuples according to claim 7 is characterized in that: The data quality of the photovoltaic operation data set is evaluated based on the weighted weights, including: Calculating the qualified rate of multiple photovoltaic operation data sets according to the amount of data that meets the evaluation index and the total amount of data; The comprehensive evaluation value of data quality is calculated based on the weighted weight and the qualified rate. The specific calculation formula is as follows: in, Represents the comprehensive evaluation value of data quality, represents the pass rate of each PV operation data set, n Indicates the maximum ordinal number; Calculate individual expected values ​​of data quality based on each PV operation data set and the corresponding pass rate; The comprehensive expected value of data quality is calculated based on the weighted weight and expected value. The specific calculation formula is as follows: in, Represents the comprehensive expected value of data quality, Indicates individual expected values ​​of data quality; The data quality difference value is calculated based on the comprehensive data quality evaluation value and the comprehensive data quality expected value. The specific calculation formula is as follows: in, Indicates the data quality difference value; The data quality of each PV operation dataset was evaluated based on the data quality difference value.

10. The photovoltaic operation data quality quantitative evaluation method based on multi-tuples according to claim 9 is characterized in that: The method further comprises: Classifying a first evaluation level of a first data range of the comprehensive evaluation value of data quality as excellent, a second evaluation level of a second data range of the comprehensive evaluation value of data quality as good, and a third evaluation level of a third data range of the comprehensive evaluation value of data quality as poor; The data quality of each photovoltaic operation data set is evaluated based on the first evaluation level, the second evaluation level, and the third evaluation level.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for quantitatively evaluating photovoltaic operation data quality based on multi-tuples according to any one of claims 1 to 10 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for quantitatively evaluating photovoltaic operation data quality based on multi-tuples according to any one of claims 1 to 11 is implemented.

Images