Electric quantity data confidence evaluation method and device and computer equipment

Abstract

The invention relates to an electric quantity data confidence evaluation method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring first metering file data and first acquisition data; cleaning the first metering file data and the first acquisition data to generate a data cleaning index, second metering file data and second acquisition data; performing data verification in combination with the second metering archive data, the second acquisition data and the marketing archive data to generate a data verification index, third metering archive data and third acquisition data; generating statistical electric quantity based on the third metering file data and the third acquisition data, and monitoring an electric quantity repair index; and assigning the weight of each data index, and obtaining the confidence coefficient of the electric quantity data according to the calculation result and the weight of each data index. By adopting the method, data quality full-link monitoring can be carried out, the problems that index evaluation and data application are disjointed and consideration factors are not comprehensive are solved, and improvement of the electric quantity data application level is promoted.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular, to a method, device, computer device, storage medium, and computer program product for evaluating the confidence level of electricity quantity data. Background Art

[0002] With the development of power technology, electricity quantity data has been uniformly collected, stored, and applied at the network level, and relevant application supports have been carried out for customers, enterprises, and the government. The electricity quantity data comes from the provincial metering automation system and the marketing management system, where the archive data comes from the marketing management system and the collected data comes from the metering automation system. If there are any data problems at the source end, it will affect the effectiveness of data application. However, there is still a certain gap between the current quality of electricity quantity data and the requirements of electricity quantity data application.

[0003] To ensure the practicality of electricity quantity data, the current method for ensuring data quality is to evaluate metering data from two dimensions: basic management and operation and maintenance management. Basic management mainly includes terminal coverage rate and file consistency rate, and operation and maintenance management mainly includes automatic meter reading rate and data upload timeliness rate. The management of improving the quality of electricity quantity data requires not only reasonable evaluation means but also a convenient management mode.

[0004] However, the current evaluation method of electricity quantity data can no longer objectively reflect the quality of application data. There is a certain gap between the traditional basic data index evaluation and the quality requirements of data supply, and it can no longer meet the requirements of more and more in-depth data applications for data quality. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for evaluating the confidence level of electricity quantity data, which can improve the timeliness, consistency, integrity, accuracy, and effectiveness of electricity quantity data.

[0006] In a first aspect, the present application provides a method for evaluating the confidence level of electricity quantity data. The method includes:

[0007] Obtain first metering archive data and first collected data; the first metering archive data is the original archive data, and the first collected data is the original collected data;

[0008] Clean the first metering archive data and the first collected data to generate a data cleaning index, second metering archive data, and second collected data;

[0009] Perform data verification by combining the second metering archive data, the second collected data, and the marketing archive data to generate a data verification index, third metering archive data, and third collected data;

[0010] Generate statistical electricity consumption based on the third metering archive data and the third acquisition data, and monitor the electricity consumption repair index;

[0011] Assign weights to the data cleaning index, the data verification index, and the electricity consumption repair index, and obtain the confidence level of the electricity consumption data based on the calculation results and weights of the data cleaning index, the data verification index, and the electricity consumption repair index.

[0012] In one embodiment, cleaning the first metering archive data and the first acquisition data to generate a data cleaning index, the second metering archive data, and the second acquisition data includes:

[0013] Formulate data cleaning rules for the first metering archive data and the first acquisition data respectively;

[0014] Process the first metering archive data and the first acquisition data respectively according to the data cleaning rules to generate a data cleaning index, the second metering archive data, and the second acquisition data; the data cleaning index includes the qualified rate of metering archive data cleaning and the qualified rate of acquisition data cleaning.

[0015] In one embodiment, combining the second metering archive data, the second acquisition data, and the marketing archive data for data verification to generate a data verification index, the third metering archive data, and the third acquisition data includes:

[0016] Obtain the consistency rate of the marketing metering archive and the third metering archive data based on the second metering archive data and the marketing archive data;

[0017] Obtain the missing rate of the meter reading, the abnormal rate of the meter reading, and the third acquisition data by performing data verification on the second acquisition data.

[0018] In one embodiment, generating statistical electricity consumption based on the third metering archive data and the third acquisition data, and monitoring the electricity consumption repair index includes:

[0019] Statistical total electricity consumption for repairing the electricity meter and the total electricity consumption of the electricity meter to generate the electricity meter electricity consumption repair rate;

[0020] Obtain the total electricity consumption of the metering point based on the total electricity consumption of the electricity meter, obtain the total electricity consumption for repairing the metering point based on the total electricity consumption for repairing the electricity meter, and combine the total electricity consumption of the metering point and the electricity consumption for repairing the metering point to generate the electricity consumption repair rate of the metering point;

[0021] Obtain the total electricity consumption of the user through the total electricity consumption of the metering point, obtain the total electricity consumption for repairing the user through the total electricity consumption for repairing the metering point, and combine the total electricity consumption of the user and the total electricity consumption for repairing the user to generate the electricity consumption repair rate of the user.

[0022] In one embodiment, before statistically calculating the total electricity consumption for repairing the electricity meter and the total electricity consumption of the electricity meter to generate the electricity meter electricity consumption repair rate, it includes:

[0023] Set the first power repair method and the second power repair method to generate the missing power data of the electricity meter; the first power repair method is to obtain the average power of the operating electricity meter in the interval and use the average power of the interval as the repair data for the missing power of the electricity meter, and the second power repair method is to obtain the daily average power of the electricity meter in the marketing archive data and use the daily average power as the repair data for the missing power of the electricity meter;

[0024] According to the missing situation of the electricity meter data, select the first power repair method or the second power repair method to repair the missing power data of the electricity meter.

[0025] In one of the embodiments, assign weights to the data cleaning index, the data verification index, and the power repair index, and obtain the power data confidence level according to the calculation results and weights of the data cleaning index, the data verification index, and the power repair index, including:

[0026] Perform normalization processing on the data cleaning index, the data verification index, and the power repair index;

[0027] Perform normalization processing on the normalized indexes to obtain the weights of the data cleaning index, the data verification index, and the power repair index;

[0028] Assign weights to the data cleaning index, the data verification index, and the power repair index, and obtain the power data confidence level within the interval.

[0029] In a second aspect, the present application also provides a device for evaluating the confidence level of power data. The device includes:

[0030] An acquisition module for acquiring the first measurement archive data and the first acquisition data; the first measurement archive data is the original archive data, and the first acquisition data is the original acquisition data;

[0031] A data cleaning module for cleaning the first measurement archive data and the first acquisition data to generate a data cleaning index, the second measurement archive data, and the second acquisition data;

[0032] A data verification module for combining the second measurement archive data, the second acquisition data, and the marketing archive data for data verification to generate a data verification index, the third measurement archive data, and the third acquisition data;

[0033] A power repair module for generating statistical power based on the third measurement archive data and the third acquisition data and monitoring the power repair index;

[0034] A confidence level module for assigning weights to the data cleaning index, the data verification index, and the power repair index, and obtaining the power data confidence level according to the calculation results and weights of the data cleaning index, the data verification index, and the power repair index.

[0035] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Obtain first metering archive data and first acquisition data; the first metering archive data is original archive data, and the first acquisition data is original acquisition data;

[0037] Clean the first metering archive data and the first acquisition data to generate a data cleaning index, second metering archive data, and second acquisition data;

[0038] Combine the second metering archive data, the second acquisition data, and marketing archive data for data verification to generate a data verification index, third metering archive data, and third acquisition data;

[0039] Generate a statistical electricity quantity based on the third metering archive data and the third acquisition data, and monitor the electricity quantity repair index;

[0040] Assign weights to the data cleaning index, the data verification index, and the electricity quantity repair index, and obtain the confidence level of the electricity quantity data according to the calculation results and weights of the data cleaning index, the data verification index, and the electricity quantity repair index.

[0041] In a fourth aspect, the present application also provides a computer-readable storage medium. On the computer-readable storage medium, a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0042] Obtain first metering archive data and first acquisition data; the first metering archive data is original archive data, and the first acquisition data is original acquisition data;

[0043] Clean the first metering archive data and the first acquisition data to generate a data cleaning index, second metering archive data, and second acquisition data;

[0044] Combine the second metering archive data, the second acquisition data, and marketing archive data for data verification to generate a data verification index, third metering archive data, and third acquisition data;

[0045] Generate a statistical electricity quantity based on the third metering archive data and the third acquisition data, and monitor the electricity quantity repair index;

[0046] Assign weights to the data cleaning index, the data verification index, and the electricity quantity repair index, and obtain the confidence level of the electricity quantity data according to the calculation results and weights of the data cleaning index, the data verification index, and the electricity quantity repair index.

[0047] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0048] Acquire first measurement archive data and first acquisition data; the first measurement archive data is original archive data, and the first acquisition data is original acquisition data;

[0049] Cleaning the first metrology file data and the first collected data, and generating a data cleaning index, a second metrology file data, and a second collected data;

[0050] Performing data verification in combination with the second measurement file data, the second collection data and the marketing file data to generate a data verification index, a third measurement file data and the third collection data;

[0051] Generate power statistics based on third-party metering archive data and third-party collected data, and monitor power repair index;

[0052] The weights of the data cleaning index, the data verification index and the power repair index are assigned, and the confidence of the power data is obtained according to the calculation results and weights of the data cleaning index, the data verification index and the power repair index.

[0053] The above-mentioned electricity data confidence assessment method, device, computer equipment, storage medium and computer program product, through monitoring points in the data cleaning process, data verification process and electricity repair process, arranges a set of hierarchical detection indicator systems to achieve full-link monitoring of data quality, solving the problem of disconnection between indicator evaluation and data application and incomplete consideration of factors. The weights of data cleaning, data verification and electricity repair indicators at the monitoring points are adjusted to build a model that is more in line with the data characteristics. The confidence of electricity data is calculated through these monitoring indicators, and the accuracy and availability of electricity data are evaluated, laying a solid foundation for establishing an electricity data governance system and promoting the improvement of electricity data application level. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is an application environment diagram of a method for assessing the confidence level of electric quantity data in an embodiment;

[0055] Figure 2 is a flow chart of a method for evaluating the confidence level of electric quantity data in one embodiment;

[0056] Figure 3 is a flow chart of a method for evaluating the confidence level of electric quantity data in another embodiment;

[0057] Figure 4 is a structural block diagram of a device for evaluating the confidence level of electric quantity data in one embodiment;

[0058] Figure 5 It is the internal structure diagram of a computer device in an embodiment. Specific implementation manners

[0059] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] Currently, the evaluation method of power consumption data can no longer objectively reflect the quality of application data. There is a certain gap between the traditional basic data index evaluation method and the requirements of data supply quality, and it can no longer meet the requirements of more and more in-depth data applications for data quality. During the data collection process, problems such as inaccurate archive sources often occur. The archive data in the provincial marketing management system is irregular, incomplete, and inaccurate. There are inconsistencies in the synchronization results of multiple systems for the marketing archive data synchronized from the network-level data center to the network-level power consumption platform and the archive data synchronized from the provincial marketing management system to the provincial metering automation system. The collected data of the metering automation system is inaccurate and incomplete due to equipment software and hardware problems. There are certain gaps in the remote and local communication capabilities, operation and maintenance timeliness, and data supply response speed during data transmission, etc.

[0061] The power consumption data confidence evaluation method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or other network servers. The marketing archive data is stored in the server. The collected metering archive data and collected data are uploaded to the server. In the server, data cleaning, data collection, and power consumption repair are performed on the marketing archive data, metering archive data, and collected data, and a data cleaning index, a data collection index, and a power consumption repair index are generated. Weights are assigned to the data cleaning index, data verification index, and power consumption repair index. According to the calculation results and weights of the data cleaning index, data verification index, and power consumption repair index, the power consumption data confidence is obtained. Among them, the terminal 102 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0062] In one embodiment, as Figure 2As shown, a method for evaluating the confidence level of power consumption data is provided. Taking the server in Figure 1 as an example, the method includes the following steps:

[0063] Step 202: Obtain the first metering file data and the first collection data. The first metering file data is the original file data, and the first collection data is the original collection data.

[0064] Among them, the metering file data is the user information stored in the server, including user basic information, power consumption situation, power supply record, power consumption cost, power consumption equipment and power consumption behavior, etc. For example, the user's name, the user's power consumption type (residential, commercial, industrial, etc.), power supply time, power outage record and voltage fluctuation, etc.; the collection data comes from the metering automation system, including meter code data, power factor, power supply frequency, maximum demand and period energy consumption data, etc.

[0065] Step 204: Clean the first metering file data and the first collection data to generate a data cleaning index, the second metering file data and the second collection data.

[0066] Step 206: Combine the second metering file data, the second collection data and the marketing file data for data verification to generate a data verification index, the third metering file data and the third collection data.

[0067] Among them, the marketing file data comes from the marketing system, including user basic information, power consumption situation, power supply record, power consumption cost, power consumption equipment and power consumption behavior, etc., and its data type is the same as that of the metering file data, such as the electricity charge calculation method and the electricity charge payment record.

[0068] Step 208: Generate a statistical power consumption based on the third metering file data and the third collection data, and monitor the power consumption repair index.

[0069] Step 210: Assign weights to the data cleaning index, the data verification index and the power consumption repair index, and obtain the confidence level of the power consumption data according to the calculation results and weights of the data cleaning index, the data verification index and the power consumption repair index.

[0070] Specifically, the collected measurement archive data and the collected data are subjected to data cleaning to generate the second measurement archive data and the second collected data after data cleaning, and a data cleaning index is obtained. Among them, the data cleaning index includes the qualified rate of collected data cleaning and the qualified rate of archive data cleaning. Combining the second measurement archive data and the marketing archive data, the consistency rate of the marketing measurement archive is obtained. It can be set that when the consistency rate of the marketing measurement archive is lower than 99%, the consistency rate of the marketing measurement archive is low. The meter reading data in the third collected data is verified to obtain the number of abnormal meter readings and the number of missing meter readings. Based on the number of abnormal meter readings, the number of missing meter readings, and the total number of electric energy meters, the missing rate of meter readings and the abnormal rate of meter readings are generated. Based on the third measurement archive data and the third collected data, the statistical electricity consumption is generated, and the electricity consumption repair index is monitored. The weights of the data cleaning index, the data verification index, and the electricity consumption repair index are assigned by the K-L (Kullback-Leibler, relative entropy) distance method. Through the weighted analysis method, combining the calculation results and weights of the data cleaning index, the data verification index, and the electricity consumption repair index, the confidence level of the electricity consumption data is obtained.

[0071] In the above method for evaluating the confidence level of electricity consumption data, starting from the basic data, the data cleaning index, the data verification index, and the electricity consumption repair index are obtained, and each link in the data processing process such as data cleaning, data verification, and data processing is monitored to establish a full-link monitoring index for data quality. It solves the problems of the disconnection between index evaluation and data application and the incomplete consideration of factors. According to the weights of the data cleaning, data verification, and electricity consumption repair indexes at the monitoring points, the model is adjusted to be more in line with the data characteristic law. Through these monitoring index data, the confidence level of the electricity consumption data can be obtained, so as to evaluate the accuracy and usability of the electricity consumption data. It lays a foundation for establishing an electricity consumption data governance system and promotes the improvement of the application level of electricity consumption data.

[0072] In one embodiment, cleaning the first measurement archive data and the first collected data to generate a data cleaning index, the second measurement archive data, and the second collected data includes: formulating data cleaning rules for the first measurement archive data and the first collected data respectively; processing the first measurement archive data and the first collected data according to the data cleaning rules respectively to generate a data cleaning index, the second measurement archive data, and the second collected data; the data cleaning index includes the qualified rate of measurement archive data cleaning and the qualified rate of collected data cleaning.

[0073] Specifically, the data in the first collected data is verified. The unqualified types of collected data include empty data IDs, non-standard formats, illegal values, etc. The unqualified collected data is removed to obtain the number of qualified collected data. According to the ratio of the number of qualified collected data to the total number of collected data, the cleaning qualification rate of the collected data is obtained. The data in the metering archive data is verified. The unqualified types of metering archive data include illegal verification values, illegal lengths, null values, duplicate data, and logical errors, etc. The unqualified metering archive data is removed to obtain the number of qualified metering archive data. According to the ratio of the number of qualified metering archive data to the total number of metering archive data, the cleaning qualification rate of the metering archive data is obtained. In addition, according to the requirements for power consumption data processing, methods such as sampling inspection, comprehensive inspection, and Six Sigma method can be selected to analyze the cleaning qualification rate of the data.

[0074] In this embodiment, by generating the cleaning qualification rate of the collected data and the cleaning qualification rate of the metering archive data, the quality of the collected data is controlled. These unqualified data types may have a negative impact on data analysis and decision-making. Inaccurate, incomplete, or error-containing data may lead to misleading analysis results and incorrect decisions. By monitoring and managing the data quality, the interference of data quality problems on the power consumption data analysis can be reduced, thereby improving the accuracy and credibility of the power consumption data evaluation.

[0075] In one embodiment, data verification is performed by combining the second metering archive data, the second collected data, and the marketing archive data. Generating the data verification index, the third metering archive data, and the third collected data includes: obtaining the marketing metering archive consistency rate and the third metering archive data based on the second metering archive data and the marketing archive data; obtaining the missing meter code rate, the abnormal meter code rate, and the third collected data by performing data verification on the second collected data.

[0076] Specifically, the marketing archive data and the second metering archive data in the server are statistically analyzed to obtain the amount of consistent data in the two groups of data, that is, the number of consistent marketing and metering archives. Based on the number of consistent marketing and metering archives, the marketing metering archive consistency rate is obtained according to the following formula.

[0077]

[0078] In the verification of meter code data, the situations of missing meter codes and abnormal meter codes are analyzed separately. Among them, missing meter codes include the starting code being empty, the stopping code being empty, and both the starting code and the stopping code being empty, etc. The number of missing meter codes is counted, and based on the ratio of the number of missing meter codes to the total number of electricity meters, the missing meter code rate is obtained. Abnormal meter codes include the starting code being less than 0, the stopping code being less than 0, both the starting code and the stopping code being less than 0 at the same time, the starting code being greater than the stopping code, the total not matching the peak, valley, flat, and spike, the frozen meter code of the operating electricity meter (total active power in the forward direction) having a deviation of more than ±10% when added to the peak, valley, flat, and spike, the metering point being for time-of-use billing but the peak, valley, and flat being empty, the frozen meter codes of the operating electricity meter (peak, valley, flat) being empty, but the metering point being for time-of-use billing or the electricity consumption category being industrial users, etc. The number of abnormal meter codes is counted, and based on the ratio of the number of abnormal meter codes to the total number of electricity meters, the abnormal meter code rate is obtained. Abnormal meter code data means the unreliability of the electricity metering system, which can lead to incomplete or unreliable data, affecting electricity metering management and decision-making; analyzing electricity data based on abnormal meter code data may lead to incorrect judgments and decisions, further affecting the energy efficiency and management of electricity.

[0079] In this embodiment, by analyzing the marketing archive data and the second metering archive data, the consistency rate of the marketing metering archive is obtained, and the accuracy of user information is considered to avoid the situation where statistical data is abnormal due to user information during the quantification of electricity data, making the evaluation of electricity data more objective. Counting the missing meter code rate and the abnormal meter code rate in the meter code data helps to obtain more reliable and accurate electricity consumption data, and in terms of management, decision-making, and analysis, it can avoid misleading analysis, thereby improving the quality of electricity data decision-making and evaluation.

[0080] In one embodiment, statistical electricity is generated based on the third metering archive data and the third acquisition data, and the monitored electricity repair index includes: counting the total repaired electricity of the electricity meters and the total electricity of the electricity meters to generate the electricity meter electricity repair rate; obtaining the total electricity of the metering point based on the total electricity of the electricity meters, obtaining the total repaired electricity of the metering point based on the total repaired electricity of the electricity meters, and combining the total electricity of the metering point and the repaired electricity of the metering point to generate the metering point electricity repair rate; obtaining the total electricity of the user through the total electricity of the metering point, obtaining the total repaired electricity of the user through the total repaired electricity of the metering point, and combining the total electricity of the user and the total repaired electricity of the user to generate the user electricity repair rate.

[0081] Among them, the user electricity is aggregated layer by layer from the electricity meter electricity and the metering point electricity, and finally, according to different requirements, it can be aggregated into business data such as industry electricity and regional electricity.

[0082] Specifically, a monitoring point is set at the electricity meter to obtain the electricity quantity missing data of the electricity meter. The electricity quantity missing data of the electricity meter includes the missing measurement period, the missing date and time, the missing electricity consumption value, the missing peak-valley-flat electricity quantity data, the missing load curve data, etc. According to the actual data monitoring requirements, different missing data can be selected for analysis. The total repaired electricity quantity of the electricity meter is determined through the electricity quantity data repair method, and the electricity quantity repair rate of the electricity meter is obtained according to the ratio of the total repaired electricity quantity of the electricity meter to the total electricity quantity of the electricity meter. The total electricity quantity of the measurement point is aggregated from the electricity quantity of the electricity meter. The total electricity quantity of the electricity meter is aggregated into the total electricity quantity of the measurement point, and the total repaired electricity quantity of the electricity meter is aggregated into the total repaired electricity quantity of the measurement point. The electricity quantity repair rate of the measurement point is generated through the total repaired electricity quantity of the measurement point and the total electricity quantity of the measurement point. Similarly, the total electricity quantity of the user is aggregated from the total electricity quantity of the measurement point. The total electricity quantity of the measurement point is aggregated into the total electricity quantity of the user, and the total repaired electricity quantity of the measurement point is aggregated into the total repaired electricity quantity of the user. The electricity quantity repair rate of the user is generated through the total repaired electricity quantity of the user and the total electricity quantity of the user.

[0083] In this embodiment, monitoring electricity is respectively set at the electricity meter, the measurement point and the user to monitor the full-link data, and the influence of the electricity quantity repair index of each monitoring point on the electricity quantity data is analyzed. The accuracy of electricity quantity measurement at different monitoring points can be understood. This helps with energy analysis and efficiency improvement. For monitoring points with poor measurement accuracy, corresponding measures can be taken for adjustment and improvement to improve the efficiency of electricity quantity. According to the electricity quantity repair rate, the influence of the repair index of the electricity quantity data on the evaluation of the electricity quantity data can be found, so as to evaluate the electricity quantity data more accurately.

[0084] In one embodiment, before calculating the total repaired electricity quantity of the electricity meter and the total electricity quantity of the electricity meter to generate the electricity quantity repair rate of the electricity meter, it includes: setting a first electricity quantity repair method and a second electricity quantity repair method to generate the electricity quantity missing data of the electricity meter; the first electricity quantity repair method is to obtain the average electricity quantity in the interval of the operating electricity meter and use the average electricity quantity in the interval as the repair data for the missing electricity quantity of the electricity meter, and the second electricity quantity repair method is to obtain the daily average electricity quantity of the electricity meter in the marketing archive data and use the daily average electricity quantity as the repair data for the missing electricity quantity of the electricity meter; according to the electricity meter data missing situation, select the first electricity quantity repair method or the second electricity quantity repair method to repair the electricity quantity missing data of the electricity meter.

[0085] Specifically, according to the electricity meter data missing situation, different data repair methods can be selected. For example, when there is missing data in the electricity meter, it is judged whether there has been missing data in the electricity meter within the fixed time limit of this monitoring point. If not, the average value within the fixed time limit is used as the filling value for the missing value of the electricity meter data. If it is found that there is one or more data missing within the fixed time limit of the monitoring point, then the daily average electricity quantity of the electricity meter read last month in the marketing archive data is selected as the filling value for the missing value of the electricity meter data. Further, the fixed time limit can be set according to the data accuracy requirements, such as 3 days, 5 days, 7 days, etc., to meet the needs of data evaluation.

[0086] In this embodiment, according to the situation of missing electricity meter data and the requirements of data evaluation, different electricity quantity data repair methods are set, which can restore the integrity of electricity quantity data, improve the accuracy of data, and improve the management effect of electric energy data. Through a variety of electricity meter data repair methods, the electricity quantity data can be compared and verified, which helps to improve the reliability and availability of the electricity quantity data and supports accurate electricity quantity data management and evaluation.

[0087] In one embodiment, weights are assigned to the data cleaning index, the data verification index, and the electricity quantity repair index. According to the calculation results and weights of the data cleaning index, the data verification index, and the electricity quantity repair index, the confidence level of the electricity quantity data is obtained, including: normalizing the data cleaning index, the data verification index, and the electricity quantity repair index; normalizing the normalized indexes to obtain the weights of the data cleaning index, the data verification index, and the electricity quantity repair index; assigning weights to the data cleaning index, the data verification index, and the electricity quantity repair index, and obtaining the confidence level of the electricity quantity data within the interval.

[0088] Specifically, the method of K-L (Kullback-Leibler, relative entropy) distance is used to solve the objective weights of the data indicators. Considering the comprehensive symmetric K-L distance, H(S, E) represents the comprehensive weighted K-L distance of S with respect to E, and H(E, S) represents the comprehensive weighted K-L distance of E with respect to S. Then the comprehensive symmetric K-L distance of S with respect to E is shown in formula (1):

[0089] D(S, E) = H(S, E) + H(E, S) (1)

[0090] Suppose there are m data indicators. According to formula (1), the pairwise symmetric K-L distances z of each data quality indicator are calculated t (t = 1, 2…, m).

[0091] The sum K of the pairwise symmetric K-L distances of each index is obtained t (t = 1, 2, ……m), and the sum is obtained from formula (2).

[0092] , t = 1, 2 ,…, m (2)

[0093] For the obtained sum K of the pairwise symmetric K-L distances of each normalized index t Normalization is performed to obtain the objective weight W of each index t , and the objective weight W t is obtained from formula (3).

[0094] , t = 1, 2, ……m (3)

[0095] The weighted average method is used to assign weight values to the corresponding indicators. Assuming that the calculation result of the i-th indicator is Ri and the weight value of the indicator is Wi, the confidence level of the data set for T days is obtained according to formula (4):

[0096] (4)

[0097] In the formula, Ri is the qualified rate of collected data cleaning, the qualified rate of archive data cleaning, the consistency rate of marketing measurement archives, the missing rate of meter codes, the abnormal rate of meter codes, the repair rate of electricity meter electricity, the repair rate of measurement point electricity, and the repair rate of user electricity.

[0098] In this embodiment, the weights of the data indicators are solved by the K-L distance method, so that the weights of the data indicators have more strict definitions and explanations, which helps to construct a model that better conforms to the data characteristic laws, makes the confidence evaluation more objective, and calculates the confidence index of the electricity data through the data indicators of each data processing link, quantitatively characterizing the accuracy and availability of the electricity data.

[0099] In one embodiment, as Figure 3 shown, a method for evaluating the confidence level of electricity data is provided, including the following steps:

[0100] Step 302, obtain the first measurement archive data and the first collected data; the first measurement archive data is the original archive data, and the first collected data is the original collected data.

[0101] Step 304, formulate data cleaning rules for the first measurement archive data and the first collected data respectively.

[0102] Step 306, process the first measurement archive data and the first collected data respectively according to the data cleaning rules to generate a data cleaning index, the second measurement archive data, and the second collected data; the data cleaning index includes the qualified rate of measurement archive data cleaning and the qualified rate of collected data cleaning.

[0103] Step 308, obtain the consistency rate of marketing measurement archives and the third measurement archive data according to the second measurement archive data and the marketing archive data.

[0104] Step 310, obtain the missing rate of meter codes, the abnormal rate of meter codes, and the third collected data by performing data verification on the second collected data.

[0105] Step 312, setting a first electricity quantity repair method and a second electricity quantity repair method to generate missing electricity quantity data of the electric energy meter; the first electricity quantity repair method is to obtain the interval average electricity quantity of the running electric energy meter, and use the interval average electricity quantity as the repair data of the missing electricity quantity of the electric energy meter; the second electricity quantity repair method is to obtain the daily average electricity quantity of the electric energy meter in the marketing archive data, and use the daily average electricity quantity as the repair data of the missing electricity quantity of the electric energy meter.

[0106] Step 314: According to the missing data of the electric energy meter, the first electric energy repair method or the second electric energy repair method is selected to repair the missing electric energy meter electric energy data.

[0107] Step 316, the total amount of electricity repaired by the energy meter and the total amount of electricity in the energy meter are counted to generate the energy meter electricity repair rate.

[0108] Step 318, obtaining the total electricity of the metering point according to the total electricity of the electric energy meter, obtaining the total repaired electricity of the metering point according to the repaired total electricity of the electric energy meter, and generating the metering point electricity repair rate by combining the total electricity of the metering point and the repaired electricity of the metering point.

[0109] Step 320, the total power of the user is obtained through the total power of the metering point, the total power of the user is obtained through the total power of the metering point repair, and the total power of the user is combined with the total power of the user to generate the user power repair rate.

[0110] Step 322, normalize the data cleaning index, the data verification index and the power repair index.

[0111] Step 324, normalize the normalized indexes to obtain the weights of the data cleaning index, the data verification index, and the power repair index.

[0112] Step 326, assigning weights to the data cleaning index, the data verification index, and the power repair index, and obtaining the confidence level of the power data within the interval.

[0113] In this embodiment, according to the calculation process of electricity data, a set of hierarchical monitoring indicator systems are designed for metering archive data, marketing archive data, and collected data, and monitoring points are deployed for the data processing processes of data cleaning, data verification, and electricity repair, so as to achieve full-link monitoring of data quality, and solve the problem of disconnection between indicator evaluation and data application and incomplete consideration of factors. The KL distance method is used to solve the weights of data indicators, and a model that is more in line with the laws of data characteristics is constructed to make the confidence evaluation more objective. The confidence of electricity data is calculated through these monitoring indicators, and the accuracy and availability of electricity data are evaluated, which lays a solid foundation for establishing an electricity data governance system, promotes the improvement of the application level of electricity data, and provides guarantees for enterprise business decision-making data.

[0114] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are displayed sequentially, these steps are not necessarily executed sequentially in the indicated order. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0115] Based on the same inventive concept, an embodiment of the present application also provides a power data confidence evaluation device for implementing the power data confidence evaluation method described above. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the power data confidence evaluation device provided below can refer to the limitations on the power data confidence evaluation method in the above text, and will not be repeated here.

[0116] In one embodiment, as Figure 4 shown, a power data confidence evaluation device is provided, including: an acquisition module 402, a data cleaning module 404, a data verification module 406, a power repair module 408, and a confidence module 410, where:

[0117] The acquisition module 402 is used to acquire first metering archive data and first acquisition data; the first metering archive data is original archive data, and the first acquisition data is original acquisition data.

[0118] The data cleaning module 404 is used to clean the first metering archive data and the first acquisition data to generate a data cleaning index, second metering archive data, and second acquisition data.

[0119] The data verification module 406 is used to perform data verification by combining the second metering archive data, the second acquisition data, and the marketing archive data to generate a data verification index, third metering archive data, and third acquisition data.

[0120] The power repair module 408 is used to generate statistical power based on the third metering archive data and the third acquisition data, and monitor the power repair index.

[0121] The confidence module 410 is used to assign weights to the data cleaning index, the data verification index, and the power repair index, and obtain the power data confidence according to the calculation results and weights of the data cleaning index, the data verification index, and the power repair index.

[0122] In one embodiment, the data cleaning module 404 further includes:

[0123] A rule module for formulating data cleaning rules for the first metering file data and the first acquisition data respectively.

[0124] A processing module for processing the first metering file data and the first acquisition data according to the data cleaning rules respectively to generate a data cleaning index, second metering file data, and second acquisition data; the data cleaning index includes the qualified rate of metering file data cleaning and the qualified rate of acquisition data cleaning.

[0125] In one embodiment, the data verification module 406 further includes:

[0126] An archive verification module for obtaining the consistency rate of the marketing metering archive and the third metering file data based on the second metering file data and the marketing archive data.

[0127] An acquisition verification module for obtaining the missing meter reading rate, the abnormal meter reading rate, and the third acquisition data by performing data verification on the second acquisition data.

[0128] In one embodiment, the power repair module 408 further includes:

[0129] A watt-hour meter repair module for counting the total watt-hour of watt-hour meter repair and the total watt-hour of the watt-hour meter to generate a watt-hour meter power repair rate.

[0130] A metering point repair module for obtaining the total watt-hour of the metering point based on the total watt-hour of the watt-hour meter, obtaining the total watt-hour of metering point repair based on the total watt-hour of watt-hour meter repair, and generating a metering point power repair rate by combining the total watt-hour of the metering point and the repaired watt-hour of the metering point.

[0131] A user repair module for obtaining the total watt-hour of the user based on the total watt-hour of the metering point, obtaining the total watt-hour of user repair based on the total watt-hour of metering point repair, and generating a user power repair rate by combining the total watt-hour of the user and the total watt-hour of user repair.

[0132] In one embodiment, the power repair module 408 further includes:

[0133] A repair processing module for setting a first power repair method and a second power repair method to generate watt-hour meter power missing data; the first power repair method is to obtain the average power in the interval of the operating watt-hour meter and use the average power in the interval as the repair data for the missing watt-hour of the watt-hour meter, and the second power repair method is to obtain the daily average power of the watt-hour meter in the marketing archive data and use the daily average power as the repair data for the missing watt-hour of the watt-hour meter.

[0134] A selection module for selecting the first power repair method or the second power repair method to repair the watt-hour meter power missing data according to the missing situation of the watt-hour meter data.

[0135] In one embodiment, the confidence module 410 further includes:

[0136] A data specification module for normalizing the data cleaning index, the data verification index, and the power repair index.

[0137] A weight module for normalizing the normalized indexes to obtain the weights of the data cleaning index, the data verification index, and the power repair index.

[0138] An assignment module for assigning weights to the data cleaning index, the data verification index, and the power repair index, and obtaining the confidence of the power data within the interval.

[0139] Each module in the above power data confidence evaluation device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0140] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store marketing archive data, metering archive data, acquisition data, and data indicators. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used for communicating with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for evaluating the confidence of power data.

[0141] Those skilled in the art can understand that Figure 4 the structure shown in

[0142] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the foregoing method embodiments are implemented.

[0143] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

[0144] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

[0145] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0146] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0147] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0148] The above-described embodiments merely represent several implementation manners of this application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application should be subject to the appended claims.

Claims

1. A method for evaluating the confidence of electric quantity data, characterized in that: The method comprises: Acquire first measurement archive data and first collected data; the first measurement archive data is original archive data, and the first collected data is original collected data; Cleaning the first metrology file data and the first collected data, and generating a data cleaning index, a second metrology file data, and a second collected data; Performing data verification in combination with the second measurement file data, the second collection data and the marketing file data to generate a data verification index, a third measurement file data and the third collection data; Generate power statistics based on third-party metering archive data and third-party collected data, and monitor power repair index; The weights of the data cleaning index, the data verification index and the power repair index are assigned, and the confidence of the power data is obtained according to the calculation results and weights of the data cleaning index, the data verification index and the power repair index.

2. The method according to claim 1, characterized in that The cleaning of the first metering file data and the first collected data to generate the data cleaning index, the second metering file data and the second collected data comprises: Formulate data cleaning rules for the first metrology archive data and the first collected data respectively; The first metrology archive data and the first collected data are processed respectively according to the data cleaning rule to generate a data cleaning index, a second metrology archive data and a second collected data; the data cleaning index includes a metrology archive data cleaning pass rate and a collected data cleaning pass rate.

3. The method according to claim 1, characterized in that The combining of the second metering archive data, the second collected data and the marketing archive data to perform data verification and generate the data verification index, the third metering archive data and the third collected data comprises: Obtaining the marketing measurement file consistency rate and the third measurement file data according to the second measurement file data and the marketing file data; By performing data verification on the second collected data, the table code missing rate, the table code abnormality rate and the third collected data are obtained.

4. The method according to claim 1, characterized in that: The generating of statistical power based on the third metering archive data and the third collected data and monitoring the power repair index includes: Count the total amount of electricity meter repaired and the total amount of electricity meter, and generate the electricity meter electricity repair rate; The total electricity of the metering point is obtained according to the total electricity of the electric energy meter, the total electricity of the metering point is obtained according to the total electricity of the electric energy meter, and the metering point electricity repair rate is generated by combining the total electricity of the metering point and the metering point repair electricity; The total power consumption of the user is obtained through the total power consumption of the metering point, and the total power consumption of the user is obtained through the total power consumption of the metering point repair. The user power repair rate is generated by combining the total power consumption of the user and the total power consumption of the user repair.

5. The method according to claim 4, characterized in that Before the total amount of electricity meter repaired and the total amount of electricity meter are counted and the electricity meter electricity repair rate is generated, the following steps are included: A first power repair method and a second power repair method are set to generate missing power data of the electric energy meter; the first power repair method is to obtain the interval average power of the running electric energy meter, and use the interval average power as the repair data of the missing power of the electric energy meter; the second power repair method is to obtain the daily average power of the electric energy meter in the marketing archive data, and use the daily average power as the repair data of the missing power of the electric energy meter; According to the missing data of the electric energy meter, the first electric quantity repair method or the second electric quantity repair method is selected to repair the missing electric quantity data of the electric energy meter.

6. The method according to claim 1, characterized in that The weights of the data cleaning index, the data verification index and the power repair index are assigned, and the confidence of the power data is obtained according to the calculation results and weights of the data cleaning index, the data verification index and the power repair index, including: Standardize the data cleaning index, data verification index and power repair index; The normalized indexes are normalized to obtain the weights of the data cleaning index, the data verification index, and the power repair index; The weights of the data cleaning index, the data verification index and the power repair index are assigned, and the confidence of the power data within the interval is obtained.

7. A device for evaluating the confidence level of electric quantity data, characterized in that: The device comprises: An acquisition module, used to acquire first measurement archive data and first collected data; the first measurement archive data is original archive data, and the first collected data is original collected data; A data cleaning module, used for cleaning the first metering file data and the first collected data, and generating a data cleaning index, a second metering file data and a second collected data; A data verification module, used to perform data verification on the second metering file data, the second collected data and the marketing file data, and generate a data verification index, a third metering file data and the third collected data; An electricity repair module, used to generate statistical electricity based on the third metering archive data and the third collected data, and monitor the electricity repair index; The confidence module is used to assign weights to the data cleaning index, the data verification index and the power repair index, and obtain the power data confidence according to the calculation results and weights of the data cleaning index, the data verification index and the power repair index.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images