Non-intrusive load identification equipment cloud collaborative test method and system

Abstract

The invention belongs to the technical field of non-intrusive load identification, and discloses a non-intrusive load identification equipment cloud collaborative test method and system. The method comprises the following steps: performing a first identification accuracy test on the non-intrusive load identification equipment to obtain a first identification result; acquiring load characteristics required for identifying the electric equipment which is not accurately identified during the first identification accuracy test, and upgrading the non-intrusive load identification equipment through the cloud according to the load characteristics; performing a second identification accuracy test on the upgraded non-intrusive load identification equipment to obtain a second identification result; and calculating the first identification result and the second identification result through a preset weight to obtain a final identification evaluation result. According to the invention, the load identification demonstration platform is adopted to carry out multiple rounds of tests, and the platform is upgraded according to feedback data, so that the test environment is more suitable for different types of load characteristics, and the adaptability and generalization ability of equipment are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of non-intrusive load identification, and in particular relates to a cloud-based collaborative testing method and system for non-intrusive load identification equipment. Background Art

[0002] Non-Intrusive Load Monitoring (NILM) is a technology that analyzes the total load data in a power system to identify and decompose the operating status and power consumption of individual electrical devices. NILM is based on fundamental power system principles and signal processing methods. Sensors installed at power inlets collect data on electrical quantities such as total current and voltage. Using this data, specific algorithms and models are used to decompose the total load into the load components of individual electrical devices. Its core approach is to utilize the unique electrical characteristics exhibited by electrical devices during operation, such as current waveform, power factor, and harmonic characteristics, to distinguish between different devices and identify their operating status.

[0003] Non-intrusive load identification technology is a key sensing technology supporting the construction of new power systems and an important foundation for digital construction on the power consumption side. Its technical development and application model has gradually shifted from small-scale pilot projects to large-scale installation and popularization. The scale of application of related products and systems has also continued to increase. The application of load identification technology has spawned a series of emerging industries in the power industry and has received widespread attention from industry enterprises.

[0004] After years of application of recognition technology, users generally reported that recognition applications performed only through local devices were insufficient in recognition capabilities in personalized scenarios. Summary of the Invention

[0005] The purpose of the present invention is to provide a non-intrusive load identification device cloud collaborative testing method and system to solve the technical problem of insufficient identification capability of local devices in personalized scenarios.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a non-intrusive load identification device cloud collaborative testing method, comprising the following steps: Conducting a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result; Obtain the load characteristics required to identify electrical equipment that was not accurately identified during the first identification accuracy test, and upgrade the non-intrusive load identification equipment based on the load characteristics through the cloud; Conduct a second identification accuracy test on the upgraded non-intrusive load identification equipment and obtain a second identification result; The first identification result and the second identification result are calculated by preset weights to obtain the final identification evaluation result.

[0007] A further improvement of the present invention is that the step of performing a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result specifically includes: Connect the electrical equipment to the circuit and operate it, and record the start and stop time and power consumption of the electrical equipment in real time as real data; Acquire data synchronously recorded by a non-intrusive load identification device as identification data; The identification data is compared with the real data, and the comparison result obtained is used as the first identification result.

[0008] A further improvement of the present invention is that the step of obtaining and identifying the load characteristics required for the electrical equipment that was not accurately identified during the first identification accuracy test, and upgrading the non-intrusive load identification device based on the load characteristics via the cloud specifically includes: The load characteristics required for identifying unidentified electrical equipment are uploaded to the cloud; the cloud issues auxiliary identification questions based on the load characteristics required for identifying unidentified electrical equipment, and obtains the correct electrical equipment category uploaded; the cloud upgrades the non-intrusive load identification equipment based on the load characteristics required for identifying unidentified electrical equipment and the correct electrical equipment category.

[0009] A further improvement of the present invention includes the following steps: the cloud updates the load characteristic waveform library based on the load characteristics required for identifying unidentified electrical equipment and auxiliary identification problems.

[0010] A further improvement of the present invention is as follows: in the step of performing a first identification accuracy test on the non-intrusive load identification device, when performing the first identification accuracy test on the non-intrusive load identification device, a recorder with a sampling rate of not less than 10KHz is used to record the test waveform throughout the entire process, and the standard information of the start and stop time, power consumption, appliance category and operating status of the electrical equipment is recorded to generate a test waveform library.

[0011] A further improvement of the present invention is that the step of performing a second identification accuracy test on the upgraded non-intrusive load identification device to obtain a second identification result specifically includes: Obtain the load waveform data during the first identification accuracy test of the non-intrusive load identification device, and process the load waveform data to obtain the operating load waveform of the electrical equipment and the standard answer; The operating load waveform of the electrical equipment is sent to the upgraded non-intrusive load identification device for load identification to obtain a second identification result.

[0012] In a second aspect, the present invention provides a non-intrusive load identification device cloud collaborative testing system, comprising the following steps: A first testing module is used to perform a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result; The upgrade module is used to obtain the load characteristics required to identify electrical equipment that was not accurately identified during the first identification accuracy test, and to upgrade the non-intrusive load identification equipment based on the load characteristics through the cloud; A second test module is used to perform a second identification accuracy test on the upgraded non-intrusive load identification device to obtain a second identification result; The comprehensive identification module is used to calculate the first identification result and the second identification result through preset weights to obtain the final identification evaluation result.

[0013] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor performs the steps of the cloud-based collaborative testing method for non-intrusive load identification equipment when executing the computer program.

[0014] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the cloud-based collaborative testing method for non-intrusive load identification equipment.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a cloud-based collaborative testing method for a non-intrusive load identification device, comprising the following steps: performing a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result; obtaining load characteristics required to identify electrical equipment that was not accurately identified during the first identification accuracy test, and upgrading the non-intrusive load identification device via the cloud based on the load characteristics; performing a second identification accuracy test on the upgraded non-intrusive load identification device to obtain a second identification result; and calculating the first and second identification results using preset weights to obtain a final identification evaluation result. Through a cloud-based feedback mechanism, the present invention optimizes and upgrades the identification capabilities of the non-intrusive load identification device, thereby improving the accuracy of final load identification.

[0016] Furthermore, the present invention uses a load identification empirical platform to conduct multiple rounds of testing and upgrades the platform based on feedback data, making the test environment more adaptable to different types of load characteristics and improving the adaptability and generalization capabilities of the equipment.

[0017] Furthermore, the present invention transfers part of the calculation and optimization tasks to the cloud through cloud collaborative processing, reducing the computing burden of local devices and improving test efficiency and real-time performance.

[0018] Furthermore, the present invention adopts a multi-round test and weight distribution mechanism to make the final evaluation result more reliable, reduce the deviation caused by a single test error, and improve the robustness of the system.

[0019] Furthermore, the present invention makes the method applicable to different types of non-intrusive load identification equipment through iterative optimization of load data, thereby improving the versatility of the test.

[0020] Furthermore, the present invention enables device manufacturers or developers to quickly discover problems and optimize algorithms through the cloud data distribution and feedback mechanism, shortening the optimization cycle and improving the iteration efficiency of the system.

[0021] In conclusion, the present invention realizes efficient and accurate load identification capability testing through cloud collaboration and optimization and upgrading of the load identification demonstration platform, which helps to improve the overall performance and practical value of non-intrusive load identification equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flowchart of a cloud-based collaborative testing method for non-intrusive load identification equipment according to an embodiment of the present invention is provided; Figure 2 This is a structural block diagram of a cloud-based collaborative testing system for non-intrusive load identification equipment according to an embodiment of the present invention; Figure 3 A flowchart of a cloud-based collaborative testing method for a non-intrusive load identification device according to an embodiment of the present invention is provided; Figure 4 This is an application system diagram of Example 6; Figure 5 This is the system diagram of the simulation test platform; Figure 6 The figure is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0024] Example 1: See also Figure 1 As shown, an embodiment of the present invention provides a non-intrusive load identification device cloud collaborative testing method, comprising the following steps: S1. Performing a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result; S2. Obtain the load characteristics required to identify the electrical equipment that was not accurately identified during the first identification accuracy test, and upgrade the non-intrusive load identification device based on the load characteristics through the cloud; S3. performing a second identification accuracy test on the upgraded non-intrusive load identification device to obtain a second identification result; S4. Calculate the first identification result and the second identification result by using preset weights to obtain a final identification evaluation result.

[0025] Example 2: See also Figure 2 As shown, the present invention provides a non-intrusive load identification equipment cloud collaborative testing system, comprising the following steps: A first testing module is used to perform a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result; The upgrade module is used to obtain the load characteristics required to identify electrical equipment that was not accurately identified during the first identification accuracy test, and to upgrade the non-intrusive load identification equipment based on the load characteristics through the cloud; A second test module is used to perform a second identification accuracy test on the upgraded non-intrusive load identification device to obtain a second identification result; The comprehensive identification module is used to calculate the first identification result and the second identification result through preset weights to obtain the final identification evaluation result.

[0026] In a specific embodiment, it also includes a question interaction module, which is used to obtain the start and stop time and power consumption inside the non-intrusive load identification device as identification data, and continuously traverse the identification data at the same time. If the device type of the non-intrusive load identification device cannot be identified through the identification data, the load characteristics required for identifying the non-intrusive load identification device are recorded, and the first identification result and load characteristics are uploaded; based on the load characteristics and identification data, the device type of the non-intrusive load identification device is analyzed, and the preset auxiliary identification questions are issued, and the interactive results of the auxiliary identification questions are received in feedback.

[0027] In one embodiment, the question interaction module analyzes the type of the non-intrusive load identification device based on the load characteristics and identification data, which may be a water heater, electric blanket, or kettle, and issues the following auxiliary identification questions: "You started a new electrical appliance on XX / XX / XX. What is it ()? A water heater; B electric blanket; C kettle; D none of the above."

[0028] Example 3: This embodiment, based on the above embodiment, uses a load identification demonstration platform and a non-intrusive load identification device to conduct a first identification accuracy test. The steps for obtaining the first identification result are further defined. The specific contents are as follows: S11. Connect the electrical equipment to the circuit and operate it, and record the start and stop time and power consumption of the electrical equipment in real time as real data; S12. Acquire data synchronously recorded by the non-intrusive load identification device as identification data; S13: Compare the identified data with the real data, and use the obtained comparison result as the first identification result.

[0029] In one specific implementation, the present invention uses a load identification verification platform to conduct a first-pass accuracy test of non-intrusive load identification equipment. The platform connects single-phase or three-phase electricity meters to several outlets, simulating a low-voltage consumer power circuit. The non-intrusive load identification equipment under test is then connected to the circuit at the meter point to perform load identification within the circuit.

[0030] Testers simulated real-life electricity usage scenarios by plugging the non-intrusive load identification device into an outlet, operating the electrical equipment, and recording the start and stop times and power consumption of each device. After the test, a host computer read the identification data of the device under test and compared the start and stop times and power consumption recorded during the test to obtain the first identification result.

[0031] Among them, the test personnel use a recorder with a sampling rate of no less than 10KHz to record the test waveform throughout the process, and accurately record standard information such as start time, stop time, power consumption, appliance type, operating status, etc. to generate a test waveform library.

[0032] This embodiment ensures the objectivity of the test results by comparing real data (the start and stop times and power consumption of loop monitoring) with identification data (records inside the non-intrusive load identification device), avoiding errors or deviations caused by relying solely on the device's self-test data. This embodiment directly compares the start and stop times and power consumption, which can accurately measure the device's identification capabilities and discover problems such as false alarms, missed alarms, or identification delays in specific operating conditions, providing a reliable basis for subsequent optimization. This embodiment does not rely on a specific load model and can be applied to various load types (such as constant power equipment, variable power equipment, etc.), enhancing the universality and applicability of the test method. This embodiment forms quantifiable indicators by comparing specific data such as start and stop time errors and power consumption deviations, which facilitates equipment manufacturers, researchers, or users to evaluate and improve load identification algorithms.

[0033] In a specific embodiment, step S1 tests the non-intrusive load identification device in multiple scenarios to obtain an identification accuracy as a first identification result; for example, 50 scenarios are tested, 30 scenarios are tested accurately, and an identification accuracy of 60% is obtained as the first identification result.

[0034] Example 4: This embodiment is based on the above embodiment. For example, in a test of 50 scenarios, 20 scenarios failed to accurately identify the electrical equipment. The steps for obtaining the load characteristics required for identifying the electrical equipment that was not accurately identified during the first identification accuracy test are defined. The steps for upgrading the non-intrusive load identification device based on the load characteristics through the cloud are defined. The specific method is as follows: Upload the load characteristics required to identify unidentified electrical equipment to the cloud; The cloud sends auxiliary identification questions based on the load characteristics required to identify unidentified electrical equipment and obtains the correct electrical equipment category uploaded; The cloud upgrades the non-intrusive load identification device based on the load characteristics and correct electrical equipment categories required to identify unidentified electrical equipment.

[0035] In a specific embodiment, if there is an electrical equipment category that cannot be accurately identified in the identification data, the load data Q for the electrical equipment category is synchronously recorded, processed and extracted to extract the load characteristics required to identify the electrical equipment type, and the recorded load characteristics are uploaded to the corresponding cloud master station in the form of 256 bytes per identification cycle.

[0036] In one specific embodiment, the device provider obtains the first identification data of the device under test and its simultaneously uploaded load characteristics. Based on this information, the device provider analyzes the types of potential electrical devices within the circuit. Based on the interaction between the master station and the user via a mobile app, the cloud master station can ask the tester a certain number of standardized questions to assist in identification.

[0037] Example question: "You started a new electrical equipment on XX / XX / XX. What is it? A water heater; B electric blanket; C kettle; D none of the above.

[0038] The provider of the equipment under test, relying on the obtained auxiliary identification information and the results of interaction with the user, stores the load characteristics and the uploaded corresponding correct electrical equipment category into the load characteristic waveform library, updates the load characteristic waveform library, and stores the updated load characteristic waveform library in the tested equipment (non-intrusive load identification equipment) for remote upgrade.

[0039] This embodiment records load characteristics and uploads them to the cloud. This method can supplement identification data deficiencies, providing the system with more comprehensive information and improving the success rate of device type identification. This embodiment utilizes interactive mechanisms to assist in identification problems (such as user feedback and contextual information analysis), effectively addressing the inadequacy of load characteristics alone in accurately identifying device types, thereby optimizing identification results. Through iterative instructions and remote upgrades, this embodiment continuously optimizes the load characteristics database and dynamically updates the identification algorithm, enhancing generalization capabilities and adapting to diverse device types and complex load scenarios. This embodiment's remote upgrade mechanism allows non-intrusive load identification devices to receive the latest algorithm updates after cloud-based optimization, reducing reliance on local computing resources and avoiding long-term misidentification issues caused by device hardware limitations. This embodiment records load characteristics when identification fails, which can be used to train and improve the model, continuously enhancing non-intrusive load identification capabilities, enabling it to better handle similar situations in the future and improving the system's long-term performance. Through precise problem analysis and interactive feedback, this embodiment reduces false positives and missed negatives, increasing user trust in the device while reducing the need for manual user intervention and improving automation.

[0040] Example 5: This embodiment, based on the above embodiment, conducts a second identification accuracy test on the upgraded non-intrusive load identification device, and further defines the steps for obtaining the second identification result, as follows: The second recognition accuracy test uses a simulation test platform to perform a recognition accuracy simulation test on the device under test.

[0041] The so-called simulation test uses the load waveform data recorded during the first identification accuracy test. After format conversion and data playback order adjustment, it generates new operating data and standard answers for similar electrical equipment. This data is directly sent to the device under test in digital format for load identification testing. Identification data B and identification evaluation result B are obtained. Identification evaluation result B serves as the second identification result.

[0042] In a specific embodiment, corresponding to the first recognition, the second recognition is also tested on 50 scenes, 40 of which are tested accurately, and the recognition accuracy is 80%, which is used as the second recognition result.

[0043] This embodiment adjusts load waveform data to encompass a wider range of load characteristics, ensuring more scientific and systematic test data and reducing environmental interference with test results. This embodiment uses standard answers as a reference, providing a clear evaluation benchmark for testing. This allows accurate measurement of the identification capabilities of non-intrusive load identification equipment and reduces bias caused by differences in test environments. By providing operating data from similar electrical equipment, this embodiment tests the equipment's ability to identify different but similar load patterns, improving its generalization capabilities and enabling more accurate identification of similar appliances. By comparing the second identification results with the standard answers, this embodiment analyzes device error patterns, providing specific data support for algorithm optimization and improving the model's accuracy and robustness. This embodiment combines the load waveform data from the first test to form a complete test-optimize-retest closed loop, ensuring that improvements to the load identification equipment are based on solving real-world problems rather than random adjustments. Because the test data more closely matches real-world load characteristics and is supplemented by standard answers, this embodiment makes testing more targeted, effectively reducing false positives and false negatives in actual use and increasing user trust.

[0044] Example 6: See also Figure 3 、 Figure 4 and Figure 5 This embodiment provides a specific application case of a non-intrusive load identification device cloud collaborative testing method: First, the load identification verification platform was used to conduct the first identification accuracy test of non-intrusive load identification equipment. Testers simulated real-life power usage scenarios by plugging the appliance under test into an outlet, then sequentially plugging in a TV, microwave oven, kettle, and other appliances. They operated the devices and recorded the start and stop times and power consumption of each device.

[0045] After the test is complete, the host computer reads the identification data A from the non-intrusive load identification device and compares the start and stop times and power consumption recorded during the test to obtain identification evaluation result A, which serves as the first identification result. In one specific embodiment, the tester uses a waveform recorder with a sampling rate of no less than 10 kHz to record the entire test waveform, accurately recording standard information such as start and stop times, power consumption, appliance type, and operating status to generate a test waveform library. The device under test then generates identification data for analyzing the electrical devices within the circuit as required.

[0046] If there are electrical equipment categories that cannot be accurately identified in the identification data, resulting in low accuracy of the first identification result (some scenarios cannot be identified or are identified incorrectly), it is necessary to synchronously record the load characteristics required for the identification of the electrical equipment category and upload the recorded load characteristics to the corresponding cloud master station in the form of 256 bytes per identification cycle.

[0047] The DUT provider will obtain the DUT's identification data A and its simultaneously uploaded load characteristics. Based on this information, the DUT provider will analyze the type of electrical equipment within the circuit. Based on the interaction between the master station and the user via a mobile app, the master station will ask the tester a set number of standardized questions to assist in identification.

[0048] Questions such as: You started a new electrical equipment on XX / XX / XX, what is it ()? A. Water heater; B. Electric blanket; C. Kettle; D. None of the above.

[0049] The provider of the equipment under test, relying on the obtained auxiliary identification information and the results of interaction with the user, stores the load characteristics and the uploaded corresponding correct electrical equipment category into the load characteristic waveform library, updates the load characteristic waveform library, and stores the updated load characteristic waveform library in the tested equipment (non-intrusive load identification equipment) for remote upgrade.

[0050] After the remote upgrade of the device under test, the second round of testing begins. This second round uses a simulation test platform to test the device's identification accuracy. The simulation test uses the load waveform data recorded in the first round, converts its format, and adjusts the data playback sequence to generate new operating data and standard answers for similar electrical equipment. This data is sent directly to the device under test in digital format for load identification testing. Identification data B and identification evaluation result B are obtained, with identification evaluation result B serving as the second identification result.

[0051] The first identification result and the second identification result are both load identification accuracies for a certain type of equipment.

[0052] Finally, the first identification result and the second identification result are comprehensively adopted, and the final identification evaluation result is calculated based on the weight ratio of 0.5 and 0.5.

[0053] The final identification evaluation result = 0.5 × the first identification result + 0.5 × the second identification result.

[0054] In a specific embodiment, the first recognition result is 60%, the second recognition result is 80%, and the final recognition evaluation result is 70%.

[0055] Example 7: See also Figure 6 As shown, the present invention also provides an electronic device 100 for implementing a cloud-based collaborative testing method for a non-intrusive load identification device; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0056] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the cloud-based collaborative testing method for non-intrusive load identification equipment described in the above embodiment by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the electronic device 100 (such as audio data). In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0057] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 using various interfaces and lines.

[0058] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a non-intrusive load identification device cloud collaborative testing method. The processor 102 can execute the plurality of instructions to implement: Conducting a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result; Obtain the load characteristics required to identify electrical equipment that was not accurately identified during the first identification accuracy test, and upgrade the non-intrusive load identification equipment based on the load characteristics through the cloud; Conduct a second identification accuracy test on the upgraded non-intrusive load identification equipment and obtain a second identification result; The first identification result and the second identification result are calculated by preset weights to obtain the final identification evaluation result.

[0059] If the module / unit integrated in the electronic device 100 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 present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0060] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, 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 magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 produce 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 flowcharts and / or block diagrams. 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.

[0062] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device 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.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the 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 by the scope of protection of the claims of the present invention.

Claims

1. A cloud-based collaborative testing method for non-intrusive load identification equipment, characterized in that: The following steps are involved: Conducting a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result; Obtain the load characteristics required to identify electrical equipment that was not accurately identified during the first identification accuracy test, and upgrade the non-intrusive load identification equipment based on the load characteristics through the cloud; Conduct a second identification accuracy test on the upgraded non-intrusive load identification equipment and obtain a second identification result; The first identification result and the second identification result are calculated by preset weights to obtain the final identification evaluation result.

2. The cloud-based collaborative testing method for non-intrusive load identification equipment according to claim 1, characterized in that: The step of performing a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result specifically includes: Connect the electrical equipment to the circuit and operate it, and record the start and stop time and power consumption of the electrical equipment in real time as real data; Acquire data synchronously recorded by a non-intrusive load identification device as identification data; The identification data is compared with the real data, and the comparison result obtained is used as the first identification result.

3. The cloud-based collaborative testing method for non-intrusive load identification equipment according to claim 2, characterized in that: The step of obtaining and identifying the load characteristics required for the electrical equipment that was not accurately identified during the first identification accuracy test, and upgrading the non-intrusive load identification device based on the load characteristics through the cloud specifically includes: The load characteristics required for identifying unidentified electrical equipment are uploaded to the cloud; the cloud issues auxiliary identification questions based on the load characteristics required for identifying unidentified electrical equipment, and obtains the correct electrical equipment category uploaded; the cloud upgrades the non-intrusive load identification equipment based on the load characteristics required for identifying unidentified electrical equipment and the correct electrical equipment category.

4. The cloud-based collaborative testing method for non-intrusive load identification equipment according to claim 3, characterized in that: The following steps are also included: The cloud updates the load characteristic waveform library based on the load characteristics required to identify unidentified electrical equipment and the correct electrical equipment category.

5. The cloud-based collaborative testing method for non-intrusive load identification equipment according to claim 1, characterized in that: In the step of performing the first identification accuracy test on the non-intrusive load identification device, when performing the first identification accuracy test on the non-intrusive load identification device, a recorder with a sampling rate of not less than 10KHz is used to record the test waveform throughout the entire process, and standard information such as the start and stop time, power consumption, appliance category and operating status of the electrical equipment is recorded to generate a test waveform library.

6. The cloud-based collaborative testing method for intrusive load identification equipment according to claim 1, characterized in that: The step of performing a second identification accuracy test on the upgraded non-intrusive load identification device to obtain a second identification result specifically includes: Obtain the load waveform data during the first identification accuracy test of the non-intrusive load identification device, and process the load waveform data to obtain the operating load waveform of the electrical equipment and the standard answer; The operating load waveform of the electrical equipment is sent to the upgraded non-intrusive load identification device for load identification to obtain a second identification result.

7. The cloud-based collaborative testing system for non-intrusive load identification equipment is characterized by: The following steps are involved: A first testing module is used to perform a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result; The upgrade module is used to obtain the load characteristics required to identify electrical equipment that was not accurately identified during the first identification accuracy test, and to upgrade the non-intrusive load identification equipment based on the load characteristics through the cloud; A second test module is used to perform a second identification accuracy test on the upgraded non-intrusive load identification device to obtain a second identification result; The comprehensive identification module is used to calculate the first identification result and the second identification result through preset weights to obtain the final identification evaluation result.

8. The cloud-based collaborative testing system for non-intrusive load identification equipment according to claim 7, characterized in that: The step of performing a first identification accuracy test on the non-intrusive load identification device to obtain a first identification result specifically includes: Connect the electrical equipment to the circuit and operate it, and record the start and stop time and power consumption of the electrical equipment in real time as real data; Acquire data synchronously recorded by a non-intrusive load identification device as identification data; The identification data is compared with the real data, and the comparison result obtained is used as the first identification result.

9. The non-intrusive load identification equipment cloud collaborative testing system according to claim 8, characterized in that: The step of obtaining and identifying the load characteristics required for the electrical equipment that was not accurately identified during the first identification accuracy test, and upgrading the non-intrusive load identification device based on the load characteristics through the cloud specifically includes: The load characteristics required for identifying unidentified electrical equipment are uploaded to the cloud; the cloud issues auxiliary identification questions based on the load characteristics required for identifying unidentified electrical equipment, and obtains the correct electrical equipment category uploaded; the cloud upgrades the non-intrusive load identification equipment based on the load characteristics required for identifying unidentified electrical equipment and the correct electrical equipment category.

10. The cloud-based collaborative testing system for non-intrusive load identification equipment according to claim 7, characterized in that: In the step of performing the first identification accuracy test on the non-intrusive load identification device, when performing the first identification accuracy test on the non-intrusive load identification device, a recorder with a sampling rate of not less than 10KHz is used to record the test waveform throughout the entire process, and standard information such as the start and stop time, power consumption, appliance category and operating status of the electrical equipment is recorded to generate a test waveform library.

11. The cloud-based collaborative testing system for intrusive load identification equipment according to claim 7, characterized in that: The step of performing a second identification accuracy test on the upgraded non-intrusive load identification device to obtain a second identification result specifically includes: Obtain the load waveform data during the first identification accuracy test of the non-intrusive load identification device, and process the load waveform data to obtain the operating load waveform of the electrical equipment and the standard answer; The operating load waveform of the electrical equipment is sent to the upgraded non-intrusive load identification device for load identification to obtain a second identification result.

12. An electronic 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 cloud-based collaborative testing method for non-intrusive load identification equipment according to any one of claims 1 to 6 are implemented.

13. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cloud-based collaborative testing method for non-intrusive load identification equipment according to any one of claims 1 to 6 are implemented.

Images