A method and system for determining the identification accuracy of a non-intrusive load identification module

Through the waveform file library and multi-dimensional evaluation system, the problem of identification effect evaluation and unified evaluation of non-intervention load identification modules on different electrical types is solved, and the accuracy score and unified testing platform of load identification modules are achieved, improving the Consistency of test data and fairness of evaluation.

CN112861354BActive Publication Date: 2024-11-01CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110181856.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-02-08
Publication Date
2024-11-01
Estimated Expiration
2041-02-08

AI Technical Summary

Technical Problem

When testing in a laboratory environment, the existing non-intervention load identification technology cannot effectively evaluate the identification effect of different electrical appliance types, and the load identification modules of each manufacturer lack a unified detection platform, resulting in the identification modules being unable to be evaluated in a unified manner.

Method used

By obtaining the waveform file library, configuring the test station information, initializing the module to be tested, and broadcasting the voltage and current data through SPI, obtaining the module identification data, calculating the identification accuracy score, and using a multi-dimensional evaluation system for fair evaluation.

Benefits of technology

A unified test of multiple load identification modules is realized, data consistency is ensured, reasonable evaluation results are obtained, and the testing level and characteristics of the module are reflected, providing a standard for upgrading and development of residential power load identification modules. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112861354B_ABST
    Figure CN112861354B_ABST
Patent Text Reader

Abstract

The present invention relates to a method and system for determining the identification accuracy of a non-intrusive load identification module, comprising: obtaining a waveform file library for testing, selecting at least one waveform file as a required waveform file, and connecting all the required files in sequence to form a test scheme; configuring the station information of at least one load identification module to be tested, and performing initialization operations on each test station and the corresponding identification module to be tested; broadcasting the voltage data and current data in each required waveform file to the identification module to be tested corresponding to each test station through SPI, and obtaining the identification data generated by each identification module to be tested in each identification time period; for any identification module to be tested, determining the identification accuracy score of any identification module to be tested according to the identification data generated by the identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files, and determining the identification accuracy according to the identification accuracy score.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent electricity technology, and more specifically, to a method and system for determining the identification accuracy of a non-intrusive load identification module. Background Art

[0002] Non-intrusive load identification technology has been integrated into the new generation of smart meters, which are endowed with load identification capabilities through non-intrusive load identification modules. At present, the industry's tests on non-intrusive load identification technology are mostly conducted in a laboratory environment using an empirical method, that is, the smart meter is connected in series to the power circuit of a real electrical appliance and tested by controlling the operation of the appliance. However, the types of electrical appliances in the laboratory are limited in number, and it is impossible to provide a rich variety of electrical appliance types to test the universality of the load identification algorithm for different electrical appliances. Moreover, the empirical method cannot guarantee the traceability and consistency of the data. There is no unified testing platform for the load identification modules of each manufacturer, and it is impossible to test the identification level of each load identification module. A test method for power identification modules is needed to uniformly evaluate the identification modules of each manufacturer. Summary of the invention

[0003] The present invention provides a method and system for determining the identification accuracy of a non-intrusive load identification module, so as to solve the problem of how to determine the identification accuracy of the non-intrusive load identification module.

[0004] In order to solve the above problem, according to one aspect of the present invention, a method for determining the identification accuracy of a non-intrusive load identification module is provided, the method comprising:

[0005] Acquire a waveform file library for testing, select at least one waveform file from the waveform file library as a required waveform file according to the test requirements, and connect all the required files in sequence according to the test requirements to form a test plan;

[0006] Configure the station information of at least one load identification module to be tested, perform initialization operation on each test station according to the configured station information, and perform initialization operation on the identification module to be tested corresponding to each test station;

[0007] Broadcasting the voltage data and current data in each demand waveform file in the test scheme to the identification module to be tested corresponding to each test station through SPI, and obtaining the identification data generated by each identification module to be tested in each identification time period according to a preset time interval;

[0008] For any identification module to be tested, the identification accuracy score of any identification module to be tested is determined based on the identification data generated by any identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files, and the identification accuracy of any identification module to be tested is determined based on the identification accuracy score of any identification module to be tested.

[0009] Preferably, each waveform file includes: a COMTRADE waveform data file, a COMTRADE attribute file and a standard identification result file; wherein the COMTRADE waveform data file stores voltage data and current data; the COMTRADE attribute file stores detailed configuration information of the COMTRADE waveform data file; and the standard result file stores the type of electrical equipment corresponding to the waveform data and the power consumption information of each type of electrical equipment.

[0010] Preferably, the identification data includes: the type of electrical equipment identified by each identification module to be tested in each identification time period and the identified power consumption of different electrical equipment types in the identification time period.

[0011] Preferably, the workstation information of configuring at least one load identification module to be tested includes:

[0012] Configure the module information of the identification module to be tested corresponding to each test station, whether to refresh the FLASH record during the test, and whether to calibrate the time at a fixed point.

[0013] Preferably, the method determines the recognition accuracy score of any recognition module to be tested according to the recognition data generated by any recognition module to be tested in all recognition time periods and the standard recognition results corresponding to all required waveform files in the following manner, including:

[0014]

[0015] Score i =α i ×(1-|1-Q i-test / Q i-real |)×100%,

[0016] K i =Q i-real / Q real-total ,

[0017] Among them, Score case Score the recognition accuracy of any identification module to be tested; n is the sum of the number of types of electrical equipment corresponding to all demand waveform files; Score iK is the recognition accuracy score corresponding to the i-th electrical equipment type; i is the weight coefficient corresponding to the i-th electrical equipment type; α i is the identification result coefficient corresponding to the i-th electrical equipment type, and different identification results correspond to different identification result coefficients; Q i-test is the identified power consumption of the i-th power-consuming equipment type in all demand waveform files; Q i-real is the actual power consumption of the i-th power-consuming equipment type in all demand waveform files; Q real-total It is the sum of the actual power consumption corresponding to n types of electrical equipment.

[0018] According to another aspect of the present invention, a system for determining the identification accuracy of a non-intrusive load identification module is provided, the system comprising:

[0019] A test scheme determination unit, used to obtain a waveform file library for testing, select at least one waveform file from the waveform file library as a required waveform file according to the test requirements, and connect all the required files in sequence according to the test requirements to form a test scheme;

[0020] An initialization unit, used to configure the station information of at least one load identification module to be tested, perform an initialization operation on each test station according to the configured station information, and perform an initialization operation on the identification module to be tested corresponding to each test station;

[0021] An identification data acquisition unit, used to broadcast the voltage data and current data in each required waveform file in the test scheme to the identification module to be tested corresponding to each test station through SPI, and acquire the identification data generated by each identification module to be tested in each identification time period according to a preset time interval;

[0022] The identification accuracy determination unit is used to determine the identification accuracy score of any identification module to be tested based on the identification data generated by the identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files, and determine the identification accuracy of any identification module to be tested based on the identification accuracy score of the identification module to be tested.

[0023] Preferably, each waveform file includes: a COMTRADE waveform data file, a COMTRADE attribute file and a standard identification result file; wherein the COMTRADE waveform data file stores voltage data and current data; the COMTRADE attribute file stores detailed configuration information of the COMTRADE waveform data file; and the standard result file stores the identification type of the waveform file, information of electrical equipment running in different time periods and power consumption information of each electrical equipment within a preset period.

[0024] Preferably, the identification data includes: the type of electrical equipment identified by each identification module to be tested in each identification time period and the identified power consumption of different electrical equipment types in the identification time period.

[0025] Preferably, the initialization unit configures the station information of at least one load identification module to be tested, including:

[0026] Configure the module information of the identification module to be tested corresponding to each test station, whether to refresh the FLASH record during the test, and whether to calibrate the time at a fixed point.

[0027] Preferably, the recognition accuracy determination unit,

[0028] The identification accuracy score of any identification module to be tested is determined according to the identification data generated by any identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files in the following manner, including:

[0029]

[0030] Score i =α i ×(1-|1-Q i-test / Q i-real |)×100%,

[0031] K i =Q i-real / Q real-total ,

[0032] Among them, Score case Score the recognition accuracy of any identification module to be tested; n is the sum of the number of types of electrical equipment corresponding to all demand waveform files; Score i K is the recognition accuracy score corresponding to the i-th electrical equipment type; i is the weight coefficient corresponding to the i-th electrical equipment type; α i is the identification result coefficient corresponding to the i-th electrical equipment type, and different identification results correspond to different identification result coefficients; Q i-test is the identified power consumption of the i-th power-consuming equipment type in all demand waveform files; Q i-real is the actual power consumption of the i-th power-consuming equipment type in all demand waveform files; Q real-total It is the sum of the actual power consumption corresponding to n types of electrical equipment.

[0033] The present invention provides a method and system for determining the identification accuracy of a non-intrusive load identification module, which can conveniently construct various required test schemes, and can test multiple load identification modules at the same time through digital waveform playback, which can effectively ensure the consistency of test data of all identification modules, and after the test is completed, a reasonable and fair evaluation result can be obtained through a multi-dimensional comprehensive evaluation system. The evaluation result can clearly reflect the test level and test characteristics of the identification module, and can also provide a strong standard for the upgrade and development of residential power load identification modules, which can effectively solve the problem that identification modules of various manufacturers cannot be uniformly judged. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0035] Figure 1 A flowchart of a method 100 for determining the identification accuracy of a non-intrusive load identification module according to an embodiment of the present invention;

[0036] Figure 2 A platform architecture diagram of a non-intrusive load identification module digital test system according to an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of the operation of the digital test system software according to an embodiment of the present invention;

[0038] Figure 4 A schematic diagram of a file included in a waveform file according to an embodiment of the present invention;

[0039] Figure 5 A schematic diagram of a test scheme configuration according to an embodiment of the present invention;

[0040] Figure 6 A schematic diagram of a test station configuration according to an embodiment of the present invention;

[0041] Figure 7 is a schematic diagram of a testing process according to an embodiment of the present invention;

[0042] Figure 8 is a schematic diagram of test results according to an embodiment of the present invention;

[0043] Fig. 9 Schematic diagram of the structure of a system 900 for determining the identification accuracy of a non-intrusive load identification module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] Now, exemplary embodiments of the present invention are described with reference to the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely and to fully convey the scope of the present invention to those skilled in the art. The terms used in the exemplary embodiments shown in the accompanying drawings are not intended to limit the present invention. In the accompanying drawings, the same units / elements are marked with the same reference numerals.

[0045] Unless otherwise specified, the terms (including technical terms) used herein have the commonly understood meanings to those skilled in the art. In addition, it is understood that the terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.

[0046] Figure 1 FIG. 1 is a flow chart of a method 100 for determining the identification accuracy of a non-intrusive load identification module according to an embodiment of the present invention. Figure 1 As shown, the method for determining the identification accuracy of the non-intrusive load identification module provided by the embodiment of the present invention can conveniently construct various required test schemes, and can test multiple load identification modules at the same time through digital waveform playback, which can effectively ensure the consistency of the test data of all identification modules, and after the test is completed, through a multi-dimensional comprehensive evaluation system, a reasonable and fair evaluation result can be obtained, and the evaluation result can clearly reflect the test level and test characteristics of the identification module, and can also provide a strong standard for the upgrade and development of residential power load identification modules, which can effectively solve the problem that the identification modules of various manufacturers cannot be uniformly judged. The method 100 for determining the identification accuracy of the non-intrusive load identification module provided by the embodiment of the present invention starts from step 101, and in step 101, a waveform file library for testing is obtained, and at least one waveform file is selected from the waveform file library as a required waveform file according to the test requirements, and all the required files are sequentially connected according to the test requirements to form a test scheme.

[0047] Preferably, each waveform file includes: a COMTRADE waveform data file, a COMTRADE attribute file and a standard identification result file; wherein the COMTRADE waveform data file stores voltage data and current data; the COMTRADE attribute file stores detailed configuration information of the COMTRADE waveform data file; and the standard result file stores the type of electrical equipment corresponding to the waveform data and the power consumption information of each type of electrical equipment.

[0048] In the present invention, the platform architecture of the non-intrusive load identification module digital test system is as follows: Figure 2As shown, the test host of the digital test system is connected to multiple test slaves via Ethernet. The test host issues cases, performs identification evaluation and report generation through the digital identification test module. Each test slave can be connected to multiple identification modules. The test system can test multiple identification modules at the same time to ensure the consistency of the test.

[0049] In the present invention, when testing, different residential power load identification modules need to be inserted into Figure 2 At the workstation of the digital test platform shown in FIG. 1 , turn on the power switch of the digital test platform and configure the test plan. The schematic diagram of the digital test system software operation is shown in FIG. Figure 3 The process of configuring the test plan includes: first, import the test waveform files from the folder on the computer. Each waveform file has a file name such as Figure 4 As shown, it includes: 1. COMTRADE waveform data files storing voltage data and current data; 2. COMTRADE attribute files storing detailed configuration information of COMTRADE waveform data files; 3. Standard result files, which store the identification type and power consumption details of waveform files, and are used for comparing the standard result information of test results later, which mainly include the specific types of electrical equipment running in each time period and the power consumption information of the equipment in a period; then, build a test plan through the operating software. Among them, a test plan usually consists of multiple waveform files, such as 10 single-device waveform files, 10 dual-device waveform files and 10 multi-device waveform files. Different test plans are used to test different performance characteristics of the identification module. The process of test plan configuration is as follows Figure 5 shown.

[0050] In step 102, the station information of at least one load identification module to be tested is configured, each test station is initialized according to the configured station information, and the identification module to be tested corresponding to each test station is initialized.

[0051] Preferably, the workstation information of configuring at least one load identification module to be tested includes:

[0052] Configure the module information of the identification module to be tested corresponding to each test station, whether to refresh the FLASH record during the test, and whether to calibrate the time at a fixed point.

[0053] In the present invention, by operating the software, the station information is configured, generally, the information of the identification module waiting for testing in the station can be configured, whether to refresh the FLASH record during the test, whether to calibrate the time at a fixed point during the test, etc. The process of test station configuration is as follows Figure 6In addition, when the test starts, the test platform will initialize the selected test station, and then initialize the identification module of each selected station, including handshake, time calibration and configuration.

[0054] In step 103, the voltage data and current data in each required waveform file in the test scheme are broadcasted to the identification module to be tested corresponding to each test station via SPI, and the identification data generated by each identification module to be tested in each identification time period is obtained at a preset time interval.

[0055] Preferably, the identification data includes: the type of electrical equipment identified by each identification module to be tested in each identification time period and the identified power consumption of different electrical equipment types in the identification time period.

[0056] In the present invention, after the initialization operation is completed, the test platform starts to broadcast the voltage data and current data in the COMTRADE waveform data file in the waveform file in the test plan to each identification module to be tested through SPI for the selected test station, so that each identification module to be tested processes the broadcast data in real time and regularly generates identification data for a period of time, including the type of running equipment identified in this period and the power consumption of the equipment in this period. The test platform regularly calls for identification data. During the test, the process information of the test can be viewed, such as Figure 7 As shown, you can view the system log of the specific test process, which contains the specific test process, the current test step, and important test message information; you can view the current test progress of each waveform file and the overall approximate progress; you can view the identification data of the currently tested waveform file.

[0057] In step 104, for any identification module to be tested, the identification accuracy score of any identification module to be tested is determined based on the identification data generated by the identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files, and the identification accuracy of any identification module to be tested is determined based on the identification accuracy score of the identification module to be tested.

[0058] Preferably, the method determines the recognition accuracy score of any recognition module to be tested according to the recognition data generated by any recognition module to be tested in all recognition time periods and the standard recognition results corresponding to all required waveform files in the following manner, including:

[0059]

[0060] Score i =α i ×(1-|1-Q i-test / Qi-real |)×100%,

[0061] K i =Q i-real / Q real-total ,

[0062] Among them, Score case Score the recognition accuracy of any identification module to be tested; n is the sum of the number of types of electrical equipment corresponding to all demand waveform files; Score i K is the recognition accuracy score corresponding to the i-th electrical equipment type; i is the weight coefficient corresponding to the i-th electrical equipment type; α i is the identification result coefficient corresponding to the i-th electrical equipment type, and different identification results correspond to different identification result coefficients; Q i-test is the identified power consumption of the i-th power-consuming equipment type in all demand waveform files; Q i-real is the actual power consumption of the i-th power-consuming equipment type in all demand waveform files; Q real-total It is the sum of the actual power consumption corresponding to n types of electrical equipment.

[0063] In the present invention, after the test is completed, the digital testing platform compares all the identification data called up (including the type of electrical equipment and the identified power consumption of the electrical equipment) with the standard results (the standard result file when configuring the plan, including the standard results of each waveform file), and scores the accuracy using the evaluation method in the evaluation system.

[0064] Among them, for any identification module to be tested, the identification accuracy score of any identification module to be tested is determined according to the identification data generated by the identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files, including:

[0065]

[0066] Score i =α i ×(1-|1-Q i-test / Q i-real |)×100%,

[0067] K i =Q i-real / Q real-total ,

[0068] Among them, Score case Score the recognition accuracy of any identification module to be tested; n is the sum of the number of types of electrical equipment corresponding to all demand waveform files; Scorei K is the recognition accuracy score corresponding to the i-th electrical equipment type; i is the weight coefficient corresponding to the i-th electrical equipment type; α i is the identification result coefficient corresponding to the i-th electrical equipment type, and different identification results correspond to different identification result coefficients; Q i-test is the identified power consumption of the i-th power-consuming equipment type in all demand waveform files; Q i-real is the actual power consumption of the i-th power-consuming equipment type in all demand waveform files; Q real-total is the sum of the actual power consumption corresponding to n types of electrical equipment. The load identification electrical equipment type coefficient α is determined according to the identification result, where if the identification result is the correct specific category, α=1; if the identification result is the correct general category, α=0.8; if the identification result is an untrusted category, α=0.5; if the identification result is an unknown category, α=0.2; if the identification result is empty, α=0; if the identification result is an incorrect category, α=-1.

[0069] Then, the accuracy of the module to be identified is determined according to the preset grade rules based on the accuracy score. The grade rules can be set according to the needs. For example, the accuracy score can be set to [90, 100] points, then the accuracy grade is excellent; the accuracy score can be set to [80, 90) points, then the accuracy grade is good; the accuracy score can be set to [60, 80) points, then the accuracy grade is fair; the accuracy score can be set to [0, 60) points, then the accuracy grade is poor.

[0070] In addition, after the test is completed, you can view the test result score and specific details, such as Figure 8 As shown, including: the total score of each waveform file and the score of each scoring item of the identification modules of different manufacturers in the whole solution can be viewed; the identification data of all identification times of the identification modules of different manufacturers in the whole test process can be viewed; the identification capabilities and characteristics of different manufacturers can be obtained by comparing the scoring details of different manufacturers.

[0071] The method of determining the identification accuracy of the non-intrusive load identification module of the present invention can effectively ensure the consistency of the test data of all identification modules through digital waveform playback. At the same time, it can very conveniently construct various required test schemes; and after the test is completed, a reasonable and fair evaluation result is obtained through a multi-dimensional comprehensive evaluation system. The evaluation results can clearly reflect the test level and test characteristics of the identification module. Through this digital testing platform and test evaluation system, a unified, fair and convenient platform is provided for identification modules of different manufacturers, and it also provides a strong standard and foundation for the upgrade and development of residential power load identification modules.

[0072] Fig. 9 FIG. 9 is a schematic diagram of a system 900 for determining the identification accuracy of a non-intrusive load identification module according to an embodiment of the present invention. Fig. 9 As shown, the system 900 for determining the identification accuracy of a non-intrusive load identification module provided by an embodiment of the present invention includes: a test scheme determination unit 901, an initialization unit 902, an identification data acquisition unit 903 and an identification accuracy determination unit 904.

[0073] Preferably, the test scheme determination unit 901 is used to obtain a waveform file library for testing, and select at least one waveform file from the waveform file library as a required waveform file according to the test requirements, and connect all the required files in sequence according to the test requirements to form a test scheme.

[0074] Preferably, each waveform file includes: a COMTRADE waveform data file, a COMTRADE attribute file and a standard identification result file; wherein the COMTRADE waveform data file stores voltage data and current data; the COMTRADE attribute file stores detailed configuration information of the COMTRADE waveform data file; and the standard result file stores the identification type of the waveform file, information of electrical equipment running in different time periods and power consumption information of each electrical equipment within a preset period.

[0075] Preferably, the initialization unit 902 is used to configure the station information of at least one load identification module to be tested, perform initialization operation on each test station according to the configured station information, and perform initialization operation on the identification module to be tested corresponding to each test station.

[0076] Preferably, the initialization unit 902 configures the station information of at least one load identification module to be tested, including:

[0077] Configure the module information of the identification module to be tested corresponding to each test station, whether to refresh the FLASH record during the test, and whether to calibrate the time at a fixed point.

[0078] Preferably, the identification data acquisition unit 903 is used to broadcast the voltage data and current data in each demand waveform file in the test scheme to the identification module to be tested corresponding to each test station through SPI, and obtain the identification data generated by each identification module to be tested in each identification time period at a preset time interval.

[0079] Preferably, the identification data includes: the type of electrical equipment identified by each identification module to be tested in each identification time period and the identified power consumption of different electrical equipment types in the identification time period.

[0080] Preferably, the identification accuracy determination unit 904 is used to determine the identification accuracy score of any identification module to be tested based on the identification data generated by the identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files, and determine the identification accuracy of any identification module to be tested based on the identification accuracy score of the identification module to be tested.

[0081] Preferably, the recognition accuracy determination unit 904,

[0082] The identification accuracy score of any identification module to be tested is determined according to the identification data generated by any identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files in the following manner, including:

[0083]

[0084] Score i =α i ×(1-|1-Q i-test / Q i-real |)×100%,

[0085] K i =Q i-real / Q real-total ,

[0086] Among them, Score case Score the recognition accuracy of any identification module to be tested; n is the sum of the number of types of electrical equipment corresponding to all demand waveform files; Score i K is the recognition accuracy score corresponding to the i-th electrical equipment type; i is the weight coefficient corresponding to the i-th electrical equipment type; α i is the identification result coefficient corresponding to the i-th electrical equipment type, and different identification results correspond to different identification result coefficients; Q i-test is the identified power consumption of the i-th power-consuming equipment type in all demand waveform files; Q i-real is the actual power consumption of the i-th power-consuming equipment type in all demand waveform files; Q real-total It is the sum of the actual power consumption corresponding to n types of electrical equipment.

[0087] The system 900 for determining the identification accuracy of a non-intrusive load identification module according to an embodiment of the present invention corresponds to the method 100 for determining the identification accuracy of a non-intrusive load identification module according to another embodiment of the present invention, and will not be described in detail herein.

[0088] The invention has been described above with reference to a few embodiments. However, it is readily apparent to a person skilled in the art that other embodiments than the ones disclosed above are equally within the scope of the invention, as defined by the appended patent claims.

[0089] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a / said / the [means, components, etc.]" are to be openly interpreted as at least one instance of the means, components, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not necessarily have to be performed in the exact order disclosed, unless explicitly stated otherwise.

[0090] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0091] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0093] 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 The steps for the functions specified in one or more boxes.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for determining the identification accuracy of a non-intrusive load identification module, It is characterized in that The method comprises: Acquire a waveform file library for testing, select at least one waveform file from the waveform file library as a required waveform file according to the test requirements, and connect all the required files in sequence according to the test requirements to form a test plan; Configure the station information of at least one load identification module to be tested, perform initialization operation on each test station according to the configured station information, and perform initialization operation on the identification module to be tested corresponding to each test station; Broadcasting the voltage data and current data in each demand waveform file in the test scheme to the identification module to be tested corresponding to each test station through SPI, and obtaining the identification data generated by each identification module to be tested in each identification time period according to a preset time interval; For any identification module to be tested, determine the identification accuracy score of any identification module to be tested according to the identification data generated by the identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files, and determine the identification accuracy of any identification module to be tested according to the identification accuracy score of the identification module to be tested; The method determines the recognition accuracy score of any identification module to be tested according to the recognition data generated by any identification module to be tested in all recognition time periods and the standard recognition results corresponding to all required waveform files in the following manner, including: Score i =α i ×(1-|1-Q i-test / Q i-real |)×100%, K i =Q i-real / Q real-total , Among them, Score case Score the recognition accuracy of any identification module to be tested; n is the sum of the number of types of electrical equipment corresponding to all demand waveform files; Score i K is the recognition accuracy score corresponding to the i-th electrical equipment type; i is the weight coefficient corresponding to the i-th electrical equipment type; α i is the identification result coefficient corresponding to the i-th electrical equipment type, and different identification results correspond to different identification result coefficients; Q i-test is the identified power consumption of the i-th power-consuming equipment type in all demand waveform files; Q i-real is the actual power consumption of the i-th power-consuming equipment type in all demand waveform files; Q real-total It is the sum of the actual power consumption corresponding to n types of electrical equipment.

2. The method according to claim 1, It is characterized in that Each waveform file includes: a COMTRADE waveform data file, a COMTRADE attribute file and a standard identification result file; wherein the COMTRADE waveform data file stores voltage data and current data; the COMTRADE attribute file stores detailed configuration information of the COMTRADE waveform data file; and the standard identification result file stores the type of electrical equipment corresponding to the waveform data and the power consumption information of each type of electrical equipment.

3. The method according to claim 1, It is characterized in that The identification data includes: the type of electric device identified by each identification module to be tested in each identification time period and the identified power consumption of different types of electric devices in the identification time period.

4. The method according to claim 1, It is characterized in that The workstation information of configuring at least one load identification module to be tested includes: Configure the module information of the identification module to be tested corresponding to each test station, whether to refresh the FLASH record during the test, and whether to calibrate the time at a fixed point.

5. A system for determining the identification accuracy of a non-intrusive load identification module, It is characterized in that The system comprises: A test scheme determination unit, used to obtain a waveform file library for testing, select at least one waveform file from the waveform file library as a required waveform file according to the test requirements, and connect all the required files in sequence according to the test requirements to form a test scheme; An initialization unit, used to configure the station information of at least one load identification module to be tested, perform an initialization operation on each test station according to the configured station information, and perform an initialization operation on the identification module to be tested corresponding to each test station; An identification data acquisition unit, used to broadcast the voltage data and current data in each required waveform file in the test scheme to the identification module to be tested corresponding to each test station through SPI, and acquire the identification data generated by each identification module to be tested in each identification time period according to a preset time interval; An identification accuracy determination unit is used to determine, for any identification module to be tested, an identification accuracy score of the identification module to be tested according to the identification data generated by the identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files, and determine the identification accuracy of the identification module to be tested according to the identification accuracy score of the identification module to be tested; The identification accuracy determination unit determines the identification accuracy score of any identification module to be tested according to the identification data generated by any identification module to be tested in all identification time periods and the standard identification results corresponding to all required waveform files in the following manner, including: Score i =α i ×(1-|1-Q i-test / Q i-real |)×100%, K i =Q i-real / Q real-total , Among them, Score case Score the recognition accuracy of any identification module to be tested; n is the sum of the number of types of electrical equipment corresponding to all demand waveform files; Score i K is the recognition accuracy score corresponding to the i-th electrical equipment type; i is the weight coefficient corresponding to the i-th electrical equipment type; α i is the identification result coefficient corresponding to the i-th electrical equipment type, and different identification results correspond to different identification result coefficients; Q i-test is the identified power consumption of the i-th power-consuming equipment type in all demand waveform files; Q i-real is the actual power consumption of the i-th power-consuming equipment type in all demand waveform files; Q real-total It is the sum of the actual power consumption corresponding to n types of electrical equipment.

6. The system according to claim 5, It is characterized in that Each waveform file includes: a COMTRADE waveform data file, a COMTRADE attribute file and a standard identification result file; wherein the COMTRADE waveform data file stores voltage data and current data; the COMTRADE attribute file stores detailed configuration information of the COMTRADE waveform data file; and the standard identification result file stores the identification type of the waveform file, information on electrical equipment running in different time periods, and power consumption information of each electrical equipment within a preset period.

7. The system according to claim 5, It is characterized in that The identification data includes: the type of electric device identified by each identification module to be tested in each identification time period and the identified power consumption of different types of electric devices in the identification time period.

8. The system according to claim 5, It is characterized in that The initialization unit configures the station information of at least one load identification module to be tested, including: Configure the module information of the identification module to be tested corresponding to each test station, whether to refresh the FLASH record during the test, and whether to calibrate the time at a fixed point.