Digital meter data credibility evaluation method and equipment based on index combination

Abstract

The invention relates to a digital meter data credibility evaluation method and device based on index combination, and the method comprises the following steps: obtaining the attributes of a digital meter to be evaluated, the data of the digital meter to be evaluated in a certain time window, and a preset credibility evaluation system, the credibility evaluation system comprises a fitness index, an accuracy index and an integrity index; judging whether the current application scene requirement is met or not based on the attribute of the digital meter to be evaluated, if so, setting the value of the fitness index as 1, and obtaining the values of the accuracy index and the integrity index based on the data of the digital meter to be evaluated in a certain time window; and integrating the value of each evaluation index in the credibility evaluation system to obtain the data credibility of the digital meter to be evaluated. Compared with the prior art, the method has the advantages that the credibility of the digital meter data is accurately evaluated, the rationalization level of the evaluation process and the interpretability and objectivity of the evaluation result are improved, and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent power system, and in particular to a method and device for evaluating the credibility of digital meter data based on an indicator combination. Background Art

[0002] The construction of digital meters is an important part of building a modern equipment management system, an important measure to improve the level of equipment intelligence and the quality and efficiency of substation operation and inspection, and an important foundation for the digital transformation of substation profession. With the rapid development of science and technology, digitalization has profoundly changed the way various industries operate, and the power industry is no exception. As an intermediate link in the transmission of electric energy, the substation connects the production side and the use side, plays an important role in the entire power grid, and is a key link in ensuring the stability of the power grid. The management and operation level of the substation reflects the level of power use. With the advancement of science and technology and the continuous increase in people's electricity consumption, the substation is also constantly upgrading, and comprehensive real-time monitoring of the operation of the substation is becoming more and more necessary. Therefore, the digitalization of substation meters is of great significance as an important part of the intelligent transformation of the power system.

[0003] The digitalization of substation meters is a key step in the transformation and upgrading of the power industry. By improving data collection and analysis capabilities, realizing remote monitoring and control of equipment, and promoting the transformation and upgrading of the power industry, meter digitalization will promote the intelligent transformation of the power system, improve the efficiency and reliability of the power system, and provide strong support for the sustainable development of the power industry. Power companies and relevant stakeholders should actively promote the application of meter digitalization and jointly create a new future for the power industry.

[0004] A large number of digital meters are used in substation equipment, which brings convenience but also brings some problems, such as digital meter security, reliability, data management and other issues. Among them, the reliability problem of digital meters is more prominent. The reliability problems of digital meters mainly include the following aspects: Data collection accuracy: The data collection accuracy of digital meters is affected by many factors, such as grid voltage, current, frequency and other factors, which may cause inaccurate data collection of digital meters. Information transmission reliability: The information transmission reliability of digital meters is also affected by many factors, such as communication network, communication protocol and other factors, which may cause unreliable information transmission of digital meters. Adaptability to harsh environments: The adaptability of digital meters in harsh environments is also a problem. For example, high temperature, low temperature, humidity and other environments may affect the normal operation of digital meters. On-site operation stability: The stability of digital meters during on-site operation is also a problem. For example, factors such as grid load changes and grid failures may affect the stable operation of digital meters. Therefore, it is necessary to ensure the normal and reliable operation of digital meter equipment through verification and calibration. Traditional laboratory verification cannot be verified online and takes a long time, which cannot meet the verification needs of digital meters for long-term operation on site.

[0005] Therefore, it is necessary to study the data credibility evaluation method for substation digital meters, which is also of great significance to ensure the accuracy and reliability of the basic status data of substation equipment. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for evaluating the credibility of digital meter data based on indicator combination, combining the characteristics of data in different dimensions, to achieve accurate evaluation of the credibility of digital meter data, and to improve the rationality level of the evaluation process and the interpretability and objectivity of the evaluation results.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] A method for evaluating the credibility of digital meter data based on an indicator combination comprises the following steps:

[0009] Acquire the attributes of the digital meter to be evaluated, the data of the digital meter to be evaluated within a certain time window, and a preset credibility evaluation system, wherein the credibility evaluation system includes a fitness index, an accuracy index, and a completeness index;

[0010] Based on the properties of the digital meter to be evaluated, determine whether it meets the requirements of the current application scenario. If so, set the value of the fitness index to 1, and obtain the values ​​of the accuracy index and the completeness index based on the digital meter data to be evaluated within the certain time window. If not, set the value of the fitness index to 0;

[0011] The data credibility of the digital meter to be evaluated is obtained by synthesizing the values ​​of each evaluation index in the credibility evaluation system.

[0012] Furthermore, the digital meter attributes to be evaluated include meter measurement intervals.

[0013] Furthermore, the value of the accuracy index is determined based on the average value of the standard errors of the digital meter data to be evaluated within the certain time window.

[0014] Furthermore, the calculation expression of the standard error is:

[0015]

[0016] Where SE is the standard error, SD is the moving standard deviation, and m is the time window size for collecting data.

[0017] Furthermore, the value of the completeness index is determined based on the relationship between the actual quantity and the expected quantity of the digital meter data to be evaluated within the certain time window.

[0018] Furthermore, the calculation formula of the value of the integrity index is:

[0019]

[0020] In the formula, count(Exp v ) is the expected number of data, count(Obt v ) is the actual amount of data, and C is the completeness index.

[0021] Furthermore, the calculation formula for the values ​​of the evaluation indicators in the credibility evaluation system is as follows:

[0022] R=S×(w a A+w c C)

[0023] Where R is the reliability result of the digital meter, w a is the weight of the accuracy index A, w c is the weight of the completeness index C.

[0024] Furthermore, the weight of each evaluation index is obtained using the CRITIC weighting method.

[0025] The present invention also provides a computer-readable storage medium, comprising one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the method for evaluating the credibility of digital meter data based on indicator combination as described above.

[0026] The present invention also provides an electronic device, comprising one or more processors, a memory and one or more programs stored in the memory, wherein the one or more programs include instructions for executing the method for evaluating the credibility of digital meter data based on indicator combination as described above.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention designs a credibility evaluation system based on the relevant data of online monitoring of digital meters, combines the characteristics of data in different dimensions, realizes accurate evaluation of the credibility of digital meter data, improves the rationality level of the evaluation process, and ensures the accuracy and reliability of the basic status data of substation equipment.

[0029] 2. The present invention takes the applicability index as the premise for the establishment of credibility, and weights each evaluation index through the CRITIC weight method, so as to obtain more accurate and reliable evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the process of the present invention;

[0031] Figure 2 It is a schematic diagram of the overall framework of the present invention. DETAILED DESCRIPTION

[0032] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0033] Example 1

[0034] This embodiment provides a method for evaluating the credibility of digital meter data based on an indicator combination. Figure 1 As shown, the following steps are included:

[0035] S1, obtaining the attributes of the digital meter to be evaluated, the digital meter data to be evaluated within a certain time window, and a preset credibility evaluation system, wherein the credibility evaluation system includes a fitness index, an accuracy index, and a completeness index;

[0036] S2. Determine whether the properties of the digital meter to be evaluated meet the requirements of the current application scenario based on the properties of the digital meter to be evaluated. If yes, set the value of the fitness index to 1, and obtain the values ​​of the accuracy index and the completeness index based on the digital meter data to be evaluated within the certain time window. If no, set the value of the fitness index to 0;

[0037] S3. Obtain the data credibility of the digital meter to be evaluated by comprehensively analyzing the values ​​of each evaluation index in the credibility evaluation system.

[0038] refer to Figure 2 As shown, the credibility evaluation system constructed in this embodiment combines the characteristics of data in different dimensions to evaluate data credibility, and sets data quality indicators in different dimensions as key indicators for credibility evaluation, including fitness indicators, accuracy indicators and completeness indicators. Specifically:

[0039] (1) Suitability (S): The suitability of a digital meter is used to evaluate whether the meter meets the requirements of the current application scenario.

[0040] In this embodiment, the attributes of the digital meter to be evaluated include the meter measurement interval, and the value of the fitness index is determined based on the measurement interval. The measurement interval of the digital meter is denoted as [a, b]. If the measurement data in the application scenario is within the measurement range of the digital meter, the digital meter is applicable to the application scenario, that is, the fitness S=1; otherwise, if the measurement data in the application scenario exceeds the measurement range of the digital meter, the digital meter is not applicable to the application scenario, that is, the fitness S=0.

[0041] (2) Accuracy (A): The accuracy of digital meter data is a measure of how accurately the meter data represents the physical phenomenon it estimates.

[0042] In this embodiment, the value of the accuracy index is determined based on the standard error average value of the digital meter data to be evaluated within the certain time window, and the specific process includes:

[0043] 201) Calculate the moving standard deviation (SD). The moving standard deviation (SD) is used to calculate the change of the digital meter data value v relative to its average value. The specific calculation expression is as follows:

[0044]

[0045] In the formula, v i is the i-th data collected, is the average value of the data, n is the number of collected data, and m is the time window size of the online monitoring system to collect data.

[0046] 202) The digital meter data is quantified into standard error (SE), and its specific calculation expression is as follows:

[0047]

[0048] 203) The accuracy (A) of the collected data is calculated based on the average value of the standard error (SE), and the specific calculation expression is as follows:

[0049]

[0050]

[0051] (3) Completeness (C): The completeness of digital meter data is an estimate of how much usable data the online monitoring system receives within a certain time interval.

[0052] In this embodiment, the value of the completeness index is determined based on the relationship between the actual quantity and the expected quantity of the digital meter data to be evaluated within the certain time window.

[0053] Based on the time delay between two consecutive recorded sensor data values, a certain number of data values, the expected number, is expected within the defined time window. If a sensor does not produce any value or produces a NULL data value within the defined time window, it is marked as missing. Due to these missing values, the actual number of recorded data is less than the expected number.

[0054] The completeness of the data is obtained through the relationship between the actual amount of data and the expected amount. The specific calculation formula is as follows:

[0055]

[0056] In the formula, count(Exp v ) is the expected number of data, count(Obt v ) is the actual amount of data.

[0057] In this embodiment, when the values ​​of the evaluation indicators in the credibility evaluation system are comprehensively considered, the applicability indicator is used as the premise for the credibility to be established, and the accuracy indicator and the completeness indicator are weighted to determine the final data credibility of the digital meter to be evaluated. That is, the calculation formula for the values ​​of the evaluation indicators in the credibility evaluation system is:

[0058] R=S×(w a A+w c C)

[0059] Where R is the reliability result of the digital meter, w a is the weight of the accuracy index A, w c is the weight of the completeness index C, and satisfies w a +w c =1.

[0060] In this embodiment, the weight of each evaluation index is obtained using the CRITIC weight method. Figure 2 As shown in the figure, the process of using the CRITIC weighting method to weight evaluation indicators includes:

[0061] Assume that there are t digital meters as samples to be evaluated and p data quality indicators to form the original indicator data matrix:

[0062]

[0063] In the formula, x ij Represents the value of the jth evaluation index in the ith sample.

[0064] The elements in the indicator data matrix are forward processed, and the specific calculation formula is as follows:

[0065]

[0066] In the formula, x i ' j is the index value after positive processing, min(x j ) is the minimum value of the jth row of the original indicator data matrix, max(x j ) is the maximum value of the j-th row of the original indicator data matrix.

[0067] The standard deviation is used to represent the comparability of the jth indicator:

[0068]

[0069] In the formula, is the average value of the data in the jth column of the matrix after forward processing.

[0070] Set variable f j The contradiction between the indicator j and other indicators is measured. The specific calculation formula is as follows:

[0071]

[0072] In the formula, r aj is the correlation coefficient between index j and index a, and the specific calculation formula is as follows:

[0073]

[0074] In the formula, is the average value of the data in column a of the matrix after forward processing.

[0075] Set the information carrying capacity of indicator j to C j , the specific calculation formula is as follows:

[0076] C j =σ j f j

[0077] The weight of index j is obtained by the information carrying capacity. The specific calculation formula is as follows:

[0078]

[0079] In the formula, wj is the weight of indicator j among all indicators.

[0080] If the above method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0081] Example 2

[0082] This embodiment provides an electronic device, including one or more processors, a memory and one or more programs stored in the memory, wherein the one or more programs include instructions for executing the method for evaluating the credibility of digital meter data based on indicator combination as described in Example 1.

[0083] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0085] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0086] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for evaluating the credibility of digital meter data based on indicator combination, characterized in that: The following steps are involved: Acquire the attributes of the digital meter to be evaluated, the data of the digital meter to be evaluated within a certain time window, and a preset credibility evaluation system, wherein the credibility evaluation system includes a fitness index, an accuracy index, and a completeness index; Based on the properties of the digital meter to be evaluated, determine whether it meets the requirements of the current application scenario. If so, set the value of the fitness index to 1, and obtain the values ​​of the accuracy index and the completeness index based on the digital meter data to be evaluated within the certain time window. If not, set the value of the fitness index to 0; The data credibility of the digital meter to be evaluated is obtained by synthesizing the values ​​of each evaluation index in the credibility evaluation system.

2. The method for evaluating the credibility of digital meter data based on indicator combination according to claim 1 is characterized in that: The digital meter attributes to be evaluated include the meter measurement interval.

3. The method for evaluating the credibility of digital meter data based on indicator combination according to claim 1 is characterized in that: The value of the accuracy index is determined based on the standard error average of the digital meter data to be evaluated within the certain time window.

4. The method for evaluating the credibility of digital meter data based on indicator combination according to claim 3 is characterized in that: The calculation expression of the standard error is: Where SE is the standard error, SD is the moving standard deviation, and m is the time window size for collecting data.

5. The method for evaluating the credibility of digital meter data based on indicator combination according to claim 1 is characterized in that: The value of the completeness index is determined based on the relationship between the actual quantity and the expected quantity of the digital meter data to be evaluated within the certain time window.

6. The method for evaluating the credibility of digital meter data based on indicator combination according to claim 5 is characterized in that: The calculation formula of the value of the completeness index is: In the formula, count(Exp v ) is the expected number of data, count(Obt v ) is the actual amount of data, and C is the completeness index.

7. The method for evaluating the credibility of digital meter data based on indicator combination according to claim 1 is characterized in that: The calculation formula for the values ​​of each evaluation index in the credibility evaluation system is as follows: R=S×(w a A+w c C) Where R is the reliability result of the digital meter, w a is the weight of the accuracy index A, w c is the weight of the completeness index C.

8. The method for evaluating the credibility of digital meter data based on indicator combination according to claim 7 is characterized in that: The weight of each evaluation indicator is obtained using the CRITIC weighting method.

9. A computer-readable storage medium, characterized in that: It comprises one or more programs executed by one or more processors of an electronic device, wherein the one or more programs comprise instructions for executing the method for evaluating the credibility of digital meter data based on indicator combination as claimed in any one of claims 1 to 8.

10. An electronic device, characterized in that: The system comprises one or more processors, a memory and one or more programs stored in the memory, wherein the one or more programs include instructions for executing the method for evaluating the credibility of digital meter data based on indicator combination as described in any one of claims 1 to 8.

Images