Power grid distribution transformer level data quality tagging method and system based on comprehensive evaluation

Abstract

The invention discloses a comprehensive evaluation-based power grid distribution transformer level data quality tagging method and system. The method comprises the following steps of: obtaining ledger and measurement data of a distribution transformer and a line, distribution transformer uploading power failure signal data and line power failure data; establishing a distribution transformer voltage measurement label, a distribution transformer flow measurement label, a distribution transformer power measurement label, a distribution transformer power collection and outage event label, a distribution transformer fusion terminal outage event label, a distribution transformer line-to-line relation label, a distribution transformer equipment parameter quality label, a distribution transformer ledger relevance label, a distribution transformer meter label and a distribution transformer marketing and distribution through label according to the acquired data; solving the weight of each feature tag item by using a variable coefficient method based on the feature tags, and establishing a comprehensive evaluation model; and performing batch evaluation on the data quality of each distribution transformer by using the comprehensive evaluation model. According to the method, data labels related to the distribution transformer are established, the quality condition of the distribution transformer data is reasonably marked through the comprehensive evaluation model, and available, usable and easy-to-use data are provided for companies in an assisted mode.

Description

Technical Field

[0001] The present invention belongs to the field of medium-voltage distribution network distribution transformer-level data quality analysis, and specifically relates to a power grid distribution transformer-level data quality labeling method and system based on comprehensive evaluation. Background Art

[0002] Digital transformation is an inevitable choice to adapt to the trend of integration of energy revolution and digital revolution, and is an inherent requirement for building a new power system. Doing a good job in data quality management and improving the quality of power grid data application are key prerequisites for the company's digital transformation.

[0003] The existing technology does not mark and evaluate the data availability of distribution transformers and the status of line-to-line transformer relationships, which results in errors in judgment caused by interference factors when users use or manage line losses. For example, it may cause misjudgment of power outage distribution transformers and the section to which the distribution transformers belong, making it impossible to determine solutions in a timely manner, and the differences in data precision and accuracy of sensor equipment of different distribution transformers may lead to misleading data integration analysis. In order to further improve the data collection and availability of distribution transformers and assist in decision-making on the reliable operation of distribution networks, the data quality evaluation of distribution transformers is crucial and needs to be solved urgently.

[0004] The power grid data governance work is carried out from different business areas, adhering to the principles of "promoting governance through use, prioritizing urgent use, and collaborative governance", building a data quality evaluation model, and realizing data quality labeling at the power grid distribution and transformation equipment level, helping to provide the company with available, usable, and easy-to-use data. Summary of the invention

[0005] Purpose of the invention: The purpose of the present invention is to provide a method and system for labeling power grid distribution transformer-level data quality based on comprehensive evaluation, which can solve the problem that the prior art cannot reasonably determine the validity of the data records sent by the distribution transformer.

[0006] Technical solution: A method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation of the present invention comprises:

[0007] Data acquisition: obtain the ledger and measurement data of distribution transformers and lines, the power outage signal data sent by distribution transformers, and the power outage data of lines;

[0008] Establishment of characteristic labels: Based on the acquired data, distribution transformer voltage measurement labels, distribution transformer current measurement labels, distribution transformer power measurement labels, distribution transformer power outage event labels, distribution transformer fusion terminal power outage event labels, distribution transformer line-transformer relationship labels, distribution transformer equipment parameter quality labels, distribution transformer ledger relevance labels, distribution transformer meter labels, and distribution transformer operation and distribution connection labels are established;

[0009] Model establishment: Based on the feature labels, the coefficient of variation method is used to obtain the weight of each feature label item and establish a comprehensive evaluation model;

[0010] Data quality assessment: Use a comprehensive evaluation model to conduct batch evaluation of the data quality of each distribution transformer.

[0011] Furthermore, the ledgers and measurement data of the distribution transformer and the line include the basic information of the line and the distribution transformer maintained in the PMS system and the marketing system, the power measurement, power factor value, voltage measurement of the line and the distribution transformer, and the current measurement data of the distribution transformer;

[0012] The power outage signal data sent by the distribution transformer includes the power outage information sent by all distribution transformers in the distribution network and the power outage information data of the fusion terminal;

[0013] The line outage record includes line fault and plan information, weekly maintenance plan-related line plan information, outage reliability system line and distribution transformer-level outage data.

[0014] Furthermore, the establishment process of the distribution transformer voltage measurement tag, the distribution transformer current measurement tag, and the distribution transformer power measurement tag is as follows:

[0015] By checking the missing and abnormal conditions of distribution transformer voltage measurement, a distribution transformer voltage measurement quality characteristic label is established; by checking the missing and abnormal conditions of distribution transformer current measurement, a distribution transformer current measurement quality characteristic label is established; by checking the missing and abnormal conditions of distribution transformer power measurement, a distribution transformer power measurement quality characteristic label is established.

[0016] Furthermore, the establishment process of the distribution transformer power outage event label, the distribution transformer fusion terminal power outage event label, and the distribution transformer line transformer relationship label is as follows:

[0017] By verifying the authenticity of the power outage events sent from the power supply system to the distribution transformer, a characteristic label of the quality data sent from the power supply system to the distribution transformer is established; by verifying the authenticity of the power outage events sent from the power supply system to the distribution transformer, a characteristic label of the quality data sent from the power supply system to the distribution transformer fusion terminal is established; by calculating the voltage correlation coefficient index, a characteristic label of whether the distribution transformer line-transformer relationship is abnormal is established.

[0018] Furthermore, the establishment process of the distribution transformer equipment parameter quality label, distribution transformer ledger association label, distribution transformer meter label, and distribution transformer operation and distribution connection label is as follows:

[0019] By comparing the judgment capacity and maintenance capacity parameters of the distribution transformer models in the system, the distribution transformer equipment parameter quality characteristic label is established; by matching and integrating the terminal ledger information, the distribution transformer ledger association quality label is established; by comparing the distribution transformer commissioning time with the current metering information reception situation, the distribution transformer meter quality label is established; by comparing the relationship between the user access point and the special transformer ledger, the distribution transformer operation and distribution quality label is established.

[0020] Furthermore, based on the feature labels, the coefficient of variation method is used to obtain the weight of each feature label item and establish a comprehensive evaluation model, including:

[0021] The characteristic label data of distribution transformers are integrated and extracted to form a sample set for distribution transformer data quality evaluation. The weight of each characteristic label item is obtained according to the coefficient of variation method, and a comprehensive evaluation model is established.

[0022] Furthermore, the comprehensive evaluation model is used to evaluate the data quality of each distribution transformer in batches, including:

[0023] The label item feature data of each distribution transformer is batch generated and the required feature value evaluation weight is calculated, which is sent to the comprehensive evaluation model for calculation, and finally the data quality evaluation results corresponding to each distribution transformer are output.

[0024] Based on the same inventive concept, a power grid distribution transformer-level data quality labeling system based on comprehensive evaluation of the present invention comprises:

[0025] Data acquisition module, used to obtain the ledger and measurement data of distribution transformers and lines, power outage signal data sent by distribution transformers, and power outage data of lines;

[0026] The feature label establishment module is used to establish distribution transformer voltage measurement labels, distribution transformer current measurement labels, distribution transformer power measurement labels, distribution transformer power outage event labels, distribution transformer fusion terminal power outage event labels, distribution transformer line-transformer relationship labels, distribution transformer equipment parameter quality labels, distribution transformer ledger association labels, distribution transformer meter labels, and distribution transformer operation and distribution connection labels based on the acquired data;

[0027] The model building module is used to obtain the weight of each feature label item based on the feature label using the coefficient of variation method and establish a comprehensive evaluation model;

[0028] The data quality assessment module is used to evaluate the data quality of each distribution transformer in batches using a comprehensive evaluation model.

[0029] Based on the same inventive concept, a power grid distribution transformer-level data quality labeling device based on comprehensive evaluation of the present invention includes a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the above-mentioned power grid distribution transformer-level data quality labeling method based on comprehensive evaluation.

[0030] Based on the same inventive concept, a computer-readable storage medium of the present invention stores a computer program thereon, and when the program is executed by a processor, the steps of the above-mentioned method for quality labeling of power grid distribution transformer-level data based on comprehensive evaluation are implemented.

[0031] Beneficial effects: Compared with the prior art, the significant technical effects of the present invention are:

[0032] The present invention learns the changing characteristics of massive historical data in a data-driven manner, combines multi-source data such as line outage or fault records, line and distribution transformer measurement data, multi-system ledger data, distribution transformer uploading outage records, etc., extracts a total of 10 relevant feature labels related to distribution transformer data quality, and rationally judges the real data quality of distribution transformer with a comprehensive evaluation model, thus avoiding the problem of a large amount of dirty, messy and poor data when using distribution transformer data to a certain extent.

[0033] The present invention comprehensively considers the data quality conditions involved in various aspects of distribution transformers, including distribution transformer measurement, distribution transformer power outage events, distribution transformer uploading equipment, distribution transformer ledgers and other data characteristics, and comprehensively evaluates the data quality information of each distribution transformer with high credibility.

[0034] The present invention can be used to perform data availability marking processing on all distribution transformers. The calculation is simple and the principle is clear. It can help distribution network operators to timely discover the equipment operation status and data transmission status, effectively help improve the quality of basic data of distribution networks, support the construction of smart distribution networks, and has good application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of a method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation disclosed in an embodiment of the present invention;

[0036] Figure 2 A curve diagram of the voltage of the distribution transformer and the connected bus disclosed in the embodiment of the present invention;

[0037] Figure 3 A curve diagram of the voltage of the distribution transformer and the nearby busbars disclosed in an embodiment of the present invention;

[0038] Figure 4 A schematic diagram of the structure of a power grid distribution transformer-level data quality labeling system based on comprehensive evaluation disclosed in an embodiment of the present invention;

[0039] Figure 5 The present invention discloses a schematic diagram of the structure of a power grid distribution transformer-level data quality labeling device based on comprehensive evaluation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The technical solution of the present invention is described in detail below in conjunction with specific implementation methods and the accompanying drawings of the specification.

[0041] See also Figure 1 , Figure 1 The present invention discloses a flow chart of a method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation. Figure 1The described method for labeling power grid distribution transformer-level data quality is applied to power systems, such as for medium voltage distribution network distribution transformer-level data quality analysis, etc., and the embodiments of the present invention do not limit this. Figure 1 As shown, the power grid distribution transformer level data quality labeling method based on comprehensive evaluation may include the following operations:

[0042] S1. Data acquisition: Obtain the ledger and measurement data of distribution transformers and lines, the power outage signal data sent by distribution transformers, and the power outage data of lines. The details are as follows:

[0043] Ledgers and measurement data of distribution transformers and lines: basic information of lines and distribution transformers maintained in the PMS system and marketing system, power measurement, power factor value, voltage measurement of lines and distribution transformers, and current measurement data of distribution transformers.

[0044] Power outage signal data sent by distribution transformers: power outage information sent by all distribution transformers in the distribution network and integrated terminal power outage information data.

[0045] Line power outage records: line fault and plan information, line plan information related to weekly maintenance plan, power outage reliability system line and distribution transformer level power outage data.

[0046] In this embodiment, the customer service power outage information releases the fault and plan information of the relevant lines, the plan information of the weekly maintenance plan related lines, the power outage reliability system lines and the distribution transformer level power outage data.

[0047] In this embodiment, the power consumption information collection system exports the active power, current, and voltage measurement data of the distribution transformer sampled every 15 minutes, the distribution transformer power factor, the relationship with the line, the commissioning information, the medium voltage user access point and other ledger data;

[0048] Export the account data such as the relationship between distribution transformer and line in the marketing system; the active power measurement data of the switch is sampled every 15 minutes. The aforementioned sampling frequency of sampling every 15 minutes can be modified according to the actual situation;

[0049] Export data such as the installation status of the distribution transformer fusion terminal, power outage events sent by the fusion terminal, and the commissioning date of the fusion terminal on the data platform;

[0050] In the D5000 system, the line active power data sampled every 15 minutes and sent by the line circuit breaker switch is obtained;

[0051] Obtain the provincial telecommunications mid-week maintenance plan, 95598 related faults and planned event records;

[0052] Obtain the transformer-level and line-level power outage event records within the power outage reliability system;

[0053] The above-mentioned systems are systems existing in the prior art.

[0054] S2. Establishment of feature labels: Based on the acquired data, establish distribution transformer voltage measurement labels, distribution transformer current measurement labels, distribution transformer power measurement labels, distribution transformer power outage event labels, distribution transformer fusion terminal power outage event labels, distribution transformer line-transformer relationship labels, distribution transformer equipment parameter quality labels, distribution transformer ledger association labels, distribution transformer meter labels, and distribution transformer operation and distribution connection labels.

[0055] In this embodiment, 10 feature tags are established, including distribution transformer voltage measurement, distribution transformer current measurement, distribution transformer power measurement, distribution transformer power outage event, distribution transformer fusion terminal power outage event, distribution transformer line transformer relationship, distribution transformer equipment parameter quality, distribution transformer account relevance, distribution transformer meter, and distribution transformer operation and distribution connection status. The specific steps of step S2 are as follows:

[0056] S2.1. By checking the missing and abnormal conditions of distribution transformer voltage measurement, establish the distribution transformer voltage measurement quality feature label. The details are as follows:

[0057] Distribution Transformer DT k The voltage measurement data is U k =[u k,1 ,u k,2 ,…,u k,i ,…,u k,m ], m represents the number of sampling points of distribution transformer voltage measurement data;

[0058] For distribution transformer DT k Time collection k,j Check the voltage data to see if there are any abnormalities below. If so, record it as the abnormal time point:

[0059] Abnormal situation 1: No data was collected;

[0060] Abnormal situation 2: The voltage value is 0, the same as the value at other time points on the day;

[0061] Abnormal situation 3: The voltage value is negative;

[0062] Abnormal situation 4: The voltage value is the same as the data of the previous 10 sampling points and the value is greater than 0;

[0063] Abnormal situation 5: The voltage value exceeds the normal qualified range corresponding to the voltage level;

[0064] Abnormal situation 6: The voltage value is zero or empty for 5 or more days among the sampling points at the same time in the previous 7 days;

[0065] Abnormal situation 7: The voltage value drops to zero or is empty for 5 or more times during the day;

[0066] Abnormal situation 8: The voltage value is zero or empty, but the distribution transformer has not sent a power outage event, and the distribution transformer has not experienced a power outage. The definition of no power outage in the distribution transformer is: the distribution transformer simultaneously meets the conditions of not sending a power outage event to the user, not sending a power outage event to the fusion terminal, no power outage in the power outage reliability system, and no planned or fault power outage record for the line to which it belongs;

[0067] Traversing distribution transformer DT k Voltage data of each sampling point, calculate the distribution transformer DT k The number of sampling abnormal time points;

[0068] Traverse all distribution transformers and obtain the number of abnormal time points of the sampling points of each distribution transformer;

[0069] According to the number of abnormal time points of voltage measurement collection of each distribution transformer, the quartile method is used to divide it into four labels: very low credibility, low credibility, medium credibility, and high credibility;

[0070] Finally, all distribution transformers are labeled with distribution transformer voltage measurement feature labels, which are divided into four types: extremely low reliability, low reliability, medium reliability, and high reliability.

[0071] S2.2. Establish the quality characteristic label of distribution transformer current measurement by checking the missing and abnormal conditions of distribution transformer current measurement. The details are as follows:

[0072] Distribution Transformer DT k The current measurement data is I k =[i k,1 ,i k,2 ,…,i k,i ,…,i k,m ], m represents the number of sampling points of distribution transformer current measurement data;

[0073] For distribution transformer DT k Time Collection k,j Check the current data to see if there are any abnormal conditions below. If so, record it as the abnormal time point:

[0074] Abnormal situation 1: No data was collected;

[0075] Abnormal situation 2: The current value is the same as the data of the previous 10 sampling points and the value is neither 0 nor empty;

[0076] Abnormal situation 3: The current value exceeds the standard deviation range of plus or minus 10 on the day;

[0077] Abnormal situation 4: The current value is empty for 5 or more days among the sampling points at the same time in the previous 7 days;

[0078] Abnormal situation 5: The current value is empty for 5 or more times in the same day;

[0079] Abnormal situation 6: The current value is zero or empty, but the distribution transformer has not sent a power outage event, and the distribution transformer has not experienced a power outage. The definition of no power outage in the distribution transformer is: the distribution transformer simultaneously meets the conditions of not sending a power outage event to the user, not sending a power outage event to the fusion terminal, no power outage in the power outage reliability system, and no planned or fault power outage record on the line.

[0080] Traversing distribution transformer DT k Current data of each sampling point, calculate the distribution transformer DT k The number of sampling abnormal time points;

[0081] Traverse all distribution transformers and obtain the number of abnormal time points of the sampling points of each distribution transformer;

[0082] According to the number of abnormal time points of current measurement and collection of each distribution transformer, the quartile method is used to divide it into four labels: very low credibility, low credibility, medium credibility, and high credibility;

[0083] Finally, all distribution transformers are labeled with distribution transformer current measurement feature labels, which are divided into four types: extremely low reliability, low reliability, medium reliability, and high reliability.

[0084] S2.3. By checking the missing and abnormal conditions of distribution transformer power measurement, establish the distribution transformer power measurement quality feature label. The details are as follows:

[0085] Distribution Transformer DT k The active power measurement data is P k =[p k,1 ,p k,2 ,…,p k,i ,…,p k,m ], m represents the number of sampling points of active power measurement data of distribution transformer. Note that the active power measurement here is the actual power consumption after multiplying the power factor value;

[0086] For distribution transformer DT k Time collection k,j Check the active power data to see if there is any abnormality. If so, record it as the abnormal time point. The abnormality here is the same as the 6 abnormalities diagnosed in the current value in step 2.

[0087] Traversing distribution transformer DT k Active power data of each sampling point, calculate the distribution transformer DT k The number of sampling abnormal time points;

[0088] Traverse all distribution transformers and obtain the number of abnormal time points of the sampling points of each distribution transformer;

[0089] According to the abnormal time points of active power measurement collection of each distribution transformer, the quartile method is used to divide it into four labels: very low credibility, low credibility, medium credibility, and high credibility;

[0090] Finally, all distribution transformers are labeled with distribution transformer active power measurement feature labels, which are divided into four types: extremely low reliability, low reliability, medium reliability, and high reliability.

[0091] S2.4. By verifying the authenticity of the power outage event sent from the power supply system to the distribution transformer, establish the characteristic label of the quality data sent from the power supply system to the distribution transformer. The details are as follows:

[0092] Distribution Transformer DT k The power outage event data sent is E k =[e k,1,s ,e k,1,e ,e k,2,s ,e k,2,e ,…,i k,i,s ,i k,i,e ,…,i k,m,s ,i k,m,e ], m represents the number of power outage events sent by the distribution transformer, s represents the start power outage event of the power outage event, and e represents the end power outage event of the power outage event, i.e., the power restoration event;

[0093] For distribution transformer DT k Check whether the following abnormal conditions exist in the power outage event sent up. If so, record it as an abnormal power outage event sent up:

[0094] Abnormal situation 1: only power outage events or only power restoration events are sent;

[0095] Abnormal situation 2: The start and end time of the power outage event differ by more than 15 minutes, but the voltage value at the corresponding time is not zero or empty, and there is no related power outage record in the distribution transformer and line-level power outage events;

[0096] Abnormal situation 3: The distribution transformer sends out power or restore power three or more times within one hour;

[0097] Abnormal situation 4: The distribution transformer has more than 10 power outages or power restoration events on the same day;

[0098] Abnormal situation 5: The distribution transformer power outage event occurs at the same time for 3 or more days in the previous 7 days;

[0099] Abnormal situation 6: The distribution transformer did not send a power outage event, but a power outage actually occurred in the distribution transformer. The actual power outage of the distribution transformer is defined as: the distribution transformer power outage event record existing in the power outage reliability system;

[0100] Traversing distribution transformer DT k All the power outage data sent up, request the distribution transformer DT k Send an abnormal number of power outage events;

[0101] Traverse all distribution transformers to obtain the number of abnormal uplink outage events and the ratio of the abnormal number of uplink outage events to the total number of uplink outage events for each distribution transformer;

[0102] According to the proportion of abnormal number of power outage events in each distribution transformer, the quartile method is used to divide them into four labels: extremely low credibility, low credibility, medium credibility, and high credibility;

[0103] Finally, all distribution transformers are labeled with distribution transformer power outage event feature labels, which are divided into four types: extremely low credibility, low credibility, medium credibility, and high credibility.

[0104] S2.5. By verifying the authenticity of the power outage event sent by the fusion terminal equipment to the distribution transformer, establish the characteristic label of the quality data sent by the distribution transformer fusion terminal power outage event. The details are as follows:

[0105] Based on the power outage event sent by the distribution transformer fusion terminal device, the power outage event labeling logic in step S2.4 is used to obtain the distribution transformer fusion terminal power outage event feature label.

[0106] S2.6. By calculating the voltage correlation coefficient index, establish a characteristic label of whether the distribution transformer line transformer relationship is abnormal. The details are as follows:

[0107] Based on the obtained data of the distribution transformers in the marketing system and the line data in the procurement system, as well as the voltage measurement data of the distribution transformers and the lines, check whether the following abnormal conditions exist. If so, record it as a line-transformer relationship abnormality:

[0108] Abnormal situation 1: Obtain the voltage measurement values ​​of the distribution transformer and the line in the past 4 days, and calculate the Pearson correlation coefficient of the voltage between the distribution transformer and the line every day as the self-voltage correlation coefficient. When the self-voltage correlation coefficient is low, find the information of other busbars near the distribution transformer according to the geographical coordinate ledger of the distribution transformer, and calculate the daily correlation coefficient value between the distribution transformer and the nearby busbars as the nearby voltage correlation coefficient. Based on the calculated self- and nearby voltage correlation coefficients, judge whether the line-to-line relationship is abnormal. That is, when the self-voltage correlation coefficient between the distribution transformer and the line is low for 3 days or more and the nearby voltage correlation coefficient is high for 3 days or more, it is considered that the distribution transformer has an abnormal line-to-line relationship, otherwise it is normal;

[0109] Abnormal situation 2: If the line account of the distribution transformer in the marketing system is inconsistent with the line account in the procurement system, it is recorded as an abnormal situation of the line-to-line relationship of the distribution transformer.

[0110] Traverse all distribution transformers and obtain the abnormal situation of line-transformation relationship of each distribution transformer;

[0111] According to the abnormal situation of the line-transformer relationship on each distribution transformer, two labels are divided into normal line-transformer relationship and abnormal line-transformer relationship;

[0112] Finally, all distribution transformers are labeled with line-transformation relationship feature labels.

[0113] S2.7. By comparing the judgment capacity and maintenance capacity parameters of the distribution transformer models in the system, establish the distribution transformer equipment parameter quality feature label. The details are as follows:

[0114] Check the records of all distribution transformers in use in the procurement system, and check the distribution transformer models and capacities maintained in the distribution transformer in use system. If they are inconsistent, the quality of the distribution transformer equipment parameters is poor, otherwise the quality parameters of the distribution transformer equipment are good;

[0115] Finally, the equipment parameter quality labels of all distribution transformers are obtained, which are divided into two types: better and worse.

[0116] S2.8. By matching the user and integrating the terminal account information, establish the distribution transformer account correlation quality label. The details are as follows:

[0117] Based on the fusion terminal equipment in operation, check whether the distribution transformer fusion terminal ledger can be associated with the marketing ledger information. If not, the distribution transformer ledger has poor correlation. Otherwise, the distribution transformer ledger has good correlation. For other users, the default ledger correlation is good.

[0118] Finally, the ledger association labels of all distribution transformers are obtained, which are divided into two types: better and worse.

[0119] S2.9. By comparing the commissioning time of the distribution transformer with the current metering information reception situation, establish the distribution transformer meter quality label. The details are as follows:

[0120] For public transformer users whose commissioning date is more than one month from the current time, if their meter information cannot be queried at present, it is recorded as no distribution transformer meter, otherwise it is recorded as having a distribution transformer meter. The distribution transformer metering labels of other users are defaulted to be available;

[0121] Finally, the meter status labels of all distribution transformers are obtained, which are divided into two types: yes and no.

[0122] S2.10. By comparing the relationship between the user access point and the special transformer ledger, establish the quality label of the distribution transformer operation and distribution connection. The details are as follows:

[0123] Based on the obtained distribution transformer ledger, the dedicated transformer users are screened out. If the user has the following abnormal conditions, the distribution and operation connectivity is poor, otherwise it is good. The public transformer users are good by default:

[0124] Abnormal situation 1: The dedicated transformer does not maintain the medium voltage user access point;

[0125] Abnormal situation 2: The line information of the medium-voltage user access point maintained by the dedicated transformer user is inconsistent with the line information of the distribution transformer;

[0126] Finally, the operation and distribution data labels of all distribution transformers are obtained. The labels are divided into two types: better and worse.

[0127] After completing the above steps, you can establish 10 feature tags, including distribution transformer voltage measurement, distribution transformer current measurement, distribution transformer power measurement, distribution transformer power outage events, distribution transformer fusion terminal power outage events, distribution transformer line-transformer relationship, distribution transformer equipment parameter quality, distribution transformer ledger correlation, distribution transformer metering, and distribution transformer operation and distribution integration, and digitally map each tag to prepare for the data input of the subsequent model.

[0128] S3. Model establishment: Based on the feature labels, the coefficient of variation method is used to obtain the weight of each feature label item and establish a comprehensive evaluation model.

[0129] The characteristic label data of distribution transformers are integrated and extracted to form a sample set for distribution transformer data quality evaluation. The weight of each characteristic label item is obtained according to the coefficient of variation method, and a comprehensive evaluation model is established.

[0130] By using the existing mature model variation coefficient method, based on the characteristic label data of each distribution transformer obtained above, the weight value of each characteristic label item is obtained, and a comprehensive evaluation model based on the weight coefficient is established.

[0131] When calculating the weight value of the feature label item, keep the original value for the positive index whose value is larger, and recalculate the negative index whose value is smaller, according to the following formula:

[0132]

[0133] Where k is a specified arbitrary coefficient, which can be 0.1, 0.2, etc., max|x j | indicates the maximum absolute value of the indicator data, x ij A value of indicator data.

[0134] Then, each feature data is standardized and the variance V of each feature data is calculated. j , on this basis, the weight of each feature data is calculated, and the calculation formula is as follows:

[0135]

[0136] A comprehensive evaluation model is established based on the above calculated indicator weight data.

[0137] S4. Data quality assessment: Use the comprehensive evaluation model to conduct batch evaluation on the data quality of each distribution transformer.

[0138] After the comprehensive evaluation model is established, the data quality of each distribution transformer is evaluated based on the obtained label weights. That is, the label item feature data of each distribution transformer is batch generated and the required feature value evaluation weights are calculated, which are sent to the comprehensive evaluation model for calculation, and finally the data quality evaluation results corresponding to each distribution transformer are output.

[0139] For example, if we conduct a batch evaluation of data quality for a distribution transformer in a district or county under a city for one day, the results are as follows:

[0140] Distribution Transformer Data Quality Number of distribution transformers Proportion Very low credibility 125 1％ Lower credibility 498 4％ Medium confidence 6479 52％ Higher credibility 5358 43％ total 12460 /

[0141] Select a distribution transformer with lower credibility, combine its measurement and go to the site to check the terminal side. It is found that the terminal connection position, that is, the line-to-line relationship status is wrong. Further check the voltage fluctuation trend of the distribution transformer and the busbar, such as Figure 2 As shown in Figure 2, it is found that the voltage fluctuation trends of the distribution transformer and the connected bus are quite different, while the voltage fluctuation trends of the distribution transformer and the nearby bus are relatively consistent, such as Figure 3 As shown, there is a delay in sending the measurement data. By adjusting the distribution transformer connection position and calibrating the clock again, the line-transformer relationship status and measurement upload time of the distribution transformer are normal.

[0142] In this case, based on the low credibility label of the distribution transformer, the municipal personnel went to the site to check the actual situation of the distribution transformer, and finally located that the connection position of the distribution transformer was wrong and the equipment had clock lag problems, which led to abnormal line-transformer relationship status and delayed data upload. After on-site adjustments, the line-transformer relationship and data upload were normal, and the switch was then placed in a very high credibility label. This shows that the patent can be actually put into use to guide municipalities to check and adjust distribution transformers with low credibility, forming an application closed loop.

[0143] The technical solution of the present invention establishes data labels related to distribution transformers, and reasonably marks the quality of distribution transformer data with a comprehensive evaluation model, helping to provide companies with available, usable and easy-to-use data.

[0144] Example 2

[0145] See also Figure 4 , Figure 4 The present invention discloses a structural diagram of a power distribution transformer-level data quality labeling system based on comprehensive evaluation, which can implement medium-voltage distribution network distribution transformer-level data quality analysis, specifically including:

[0146] Data acquisition module, used to obtain the ledger and measurement data of distribution transformers and lines, power outage signal data sent by distribution transformers, and power outage data of lines;

[0147] The feature label establishment module is used to establish distribution transformer voltage measurement labels, distribution transformer current measurement labels, distribution transformer power measurement labels, distribution transformer power outage event labels, distribution transformer fusion terminal power outage event labels, distribution transformer line-transformer relationship labels, distribution transformer equipment parameter quality labels, distribution transformer ledger association labels, distribution transformer meter labels, and distribution transformer operation and distribution connection labels based on the acquired data;

[0148] The model building module is used to obtain the weight of each feature label item based on the feature label using the coefficient of variation method and establish a comprehensive evaluation model;

[0149] The data quality assessment module is used to evaluate the data quality of each distribution transformer in batches using a comprehensive evaluation model.

[0150] In an optional embodiment, a method for labeling data quality at the power grid distribution transformer level based on comprehensive evaluation includes: a) obtaining the ledgers and measurement data of the distribution transformer and the line, the power outage signal data sent by the distribution transformer, and the power outage data of the line; b) establishing various feature labels based on the acquired data; c) using the coefficient of variation method based on the feature labels to obtain the weight of each feature label item and establish a comprehensive evaluation model; d) using the comprehensive evaluation model to batch evaluate the data quality of each distribution transformer.

[0151] Example 3

[0152] See also Figure 5 , Figure 5 The present invention discloses a schematic diagram of a device for labeling power grid distribution and transformer-level data quality based on comprehensive evaluation. Figure 5 The described device can be applied in a power system, such as for data quality analysis at the distribution transformer level in a medium voltage distribution network, etc., and the embodiments of the present invention are not limited thereto.

[0153] like Figure 5 As shown, the device may include a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method described in the above embodiment and can achieve the technical effect consistent with the above method.

[0154] The memory may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The device may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the memory may be used to read and write non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). A program / utility having a set (at least one) of program modules may be stored in, for example, the memory, such program modules including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include the implementation of a network environment. The program modules typically perform the functions and / or methods in the embodiments described herein.

[0155] The processor executes various functional applications and data processing by running the program stored in the memory, such as implementing the method provided in the first embodiment of the present invention.

[0156] Example 4

[0157] Embodiment 4 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in the above embodiment are implemented and the technical effect consistent with the above method can be achieved.

[0158] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0159] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0160] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0161] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0162] Of course, the storage medium containing computer executable instructions provided by an embodiment of the present invention, whose computer executable instructions are not limited to the above method operations, can also execute related operations in the method provided by any embodiment of the present invention.

[0163] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation, characterized in that: include: Data acquisition: obtain the ledger and measurement data of distribution transformers and lines, the power outage signal data sent by distribution transformers, and the power outage data of lines; Establishment of characteristic labels: Based on the acquired data, distribution transformer voltage measurement labels, distribution transformer current measurement labels, distribution transformer power measurement labels, distribution transformer power outage event labels, distribution transformer fusion terminal power outage event labels, distribution transformer line-transformer relationship labels, distribution transformer equipment parameter quality labels, distribution transformer ledger relevance labels, distribution transformer meter labels, and distribution transformer operation and distribution connection labels are established; Model establishment: Based on the feature labels, the coefficient of variation method is used to obtain the weight of each feature label item and establish a comprehensive evaluation model; Data quality assessment: Use a comprehensive evaluation model to conduct batch evaluation of the data quality of each distribution transformer.

2. The method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation according to claim 1 is characterized in that: The records and measurement data of the distribution transformer and the line include the basic information of the line and the distribution transformer maintained in the PMS system and the marketing system, the power measurement, power factor value, voltage measurement of the line and the distribution transformer, and the current measurement data of the distribution transformer; The power outage signal data sent by the distribution transformer includes the power outage information sent by all distribution transformers in the distribution network and the power outage information data of the fusion terminal; The line outage record includes line fault and plan information, weekly maintenance plan-related line plan information, outage reliability system line and distribution transformer-level outage data.

3. The method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation according to claim 1 is characterized in that: The establishment process of the distribution transformer voltage measurement tag, distribution transformer current measurement tag, and distribution transformer power measurement tag is as follows: By checking the missing and abnormal conditions of distribution transformer voltage measurement, a distribution transformer voltage measurement quality characteristic label is established; by checking the missing and abnormal conditions of distribution transformer current measurement, a distribution transformer current measurement quality characteristic label is established; by checking the missing and abnormal conditions of distribution transformer power measurement, a distribution transformer power measurement quality characteristic label is established.

4. The method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation according to claim 1 is characterized in that: The establishment process of the distribution transformer power outage event label, the distribution transformer fusion terminal power outage event label, and the distribution transformer line transformer relationship label is as follows: By verifying the authenticity of the power outage events sent from the power supply system to the distribution transformer, a characteristic label of the quality data sent from the power supply system to the distribution transformer is established; by verifying the authenticity of the power outage events sent from the power supply system to the distribution transformer, a characteristic label of the quality data sent from the power supply system to the distribution transformer fusion terminal is established; by calculating the voltage correlation coefficient index, a characteristic label of whether the distribution transformer line-transformer relationship is abnormal is established.

5. The method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation according to claim 1 is characterized in that: The establishment process of the distribution transformer equipment parameter quality label, distribution transformer ledger association label, distribution transformer meter label, and distribution transformer operation and distribution connection label is as follows: By comparing the judgment capacity and maintenance capacity parameters of the distribution transformer models in the system, the distribution transformer equipment parameter quality characteristic label is established; by matching and integrating the terminal ledger information, the distribution transformer ledger association quality label is established; by comparing the distribution transformer commissioning time with the current metering information reception situation, the distribution transformer meter quality label is established; by comparing the relationship between the user access point and the special transformer ledger, the distribution transformer operation and distribution quality label is established.

6. The method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation according to claim 1, characterized in that: Based on the feature labels, the coefficient of variation method is used to obtain the weight of each feature label item and establish a comprehensive evaluation model, including: The characteristic label data of distribution transformers are integrated and extracted to form a sample set for distribution transformer data quality evaluation. The weight of each characteristic label item is obtained according to the coefficient of variation method, and a comprehensive evaluation model is established.

7. The method for labeling power grid distribution transformer-level data quality based on comprehensive evaluation according to claim 1, characterized in that: The comprehensive evaluation model is used to evaluate the data quality of each distribution transformer in batches, including: The label item feature data of each distribution transformer is batch generated and the required feature value evaluation weight is calculated, which is sent to the comprehensive evaluation model for calculation, and finally the data quality evaluation results corresponding to each distribution transformer are output.

8. A power grid distribution and transformation data quality labeling system based on comprehensive evaluation, characterized in that: include: Data acquisition module, used to obtain the ledger and measurement data of distribution transformers and lines, power outage signal data sent by distribution transformers, and power outage data of lines; The feature label establishment module is used to establish distribution transformer voltage measurement labels, distribution transformer current measurement labels, distribution transformer power measurement labels, distribution transformer power outage event labels, distribution transformer fusion terminal power outage event labels, distribution transformer line-transformer relationship labels, distribution transformer equipment parameter quality labels, distribution transformer ledger association labels, distribution transformer meter labels, and distribution transformer operation and distribution connection labels based on the acquired data; The model building module is used to obtain the weight of each feature label item based on the feature label using the coefficient of variation method and establish a comprehensive evaluation model; The data quality assessment module is used to evaluate the data quality of each distribution transformer in batches using a comprehensive evaluation model.

9. A power grid distribution and transformation level data quality labeling device based on comprehensive evaluation, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method for quality labeling of power grid distribution transformer-level data based on comprehensive evaluation as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for quality labeling of power grid distribution transformer-level data based on comprehensive evaluation as claimed in any one of claims 1 to 7.

Images