KR20230158249A - Load signature-based behavioral appliance identification method, apparatus, and system - Google Patents

Abstract

A load signature-based home appliance identification method, a home appliance identification device, and a home appliance identification system are disclosed. A method for identifying an operating home appliance according to an embodiment includes: acquiring a plurality of sample blocks by sampling a power signal of the home appliance; An operation of signal processing the plurality of sample blocks to extract harmonic components of each sample block; Obtaining information about the Euclidean distance of each sample block based on the harmonic components; And it may include an operation of obtaining a load signature table of the home appliance based on the information about the Euclidean distance.

Description

Load signature-based operating appliance identification method, operating appliance identification device, and operating appliance identification system {LOAD SIGNATURE-BASED BEHAVIORAL APPLIANCE IDENTIFICATION METHOD, APPARATUS, AND SYSTEM}

The disclosure below relates to a load signature-based home appliance identification method, a home appliance identification device, and a home appliance identification system.

Non-Intrusive Load Monitoring (NILM) technology is a technology that identifies the type of home appliance operating in a household by analyzing power signals measured at a point in the household distribution network.

Non-intrusive load monitoring technology is divided into low-speed sampling method and high-speed sampling method depending on the signal collection cycle. The low-speed sampling method usually collects signals at a sampling rate lower than 1Hz, and the high-speed sampling method collects signals at a sampling rate of 1Hz to several MHz.

The low-speed sampling method can only measure the power consumption of devices (e.g. home appliances) over time. The high-speed sampling method can not only measure the power consumption of the device, but also perform analysis on the harmonic components of the sample signal. Compared to low-speed sampling methods, more information can be obtained about operating home appliances by using high-speed sampling methods. High-speed sampling method can have better home appliance identification ability.

The NILM algorithm can identify operating home appliances by comparing power signals sampled from the power grid with load signatures that represent the unique characteristics of the device (e.g. home appliance). Load signatures can have a significant impact on the performance of NILM. The values used for load signatures are very diverse, including power magnitude, harmonic content, current, and voltage. The value used for the load signature may differ depending on the NILM algorithm. The more components that make up the load signature, and the more inaccurate the values of the components that make up the load signature, the worse the performance of the NILM algorithm may be. Techniques for generating load signatures that are accurate and have a small number of components may be required.

According to an embodiment, it is possible to provide a technology for generating a load signature table whose components are the harmonic component values of a power signal corresponding to the stable state of the home appliance (e.g., a power signal output when the home appliance is in a stable state).

However, technical challenges are not limited to the above-mentioned technical challenges, and other technical challenges may exist.

A method for identifying an operating home appliance according to an embodiment includes: acquiring a plurality of sample blocks by sampling a power signal of the home appliance; An operation of signal processing the plurality of sample blocks to extract harmonic components of each sample block; Obtaining information about a Euclidean distance of each sample block based on the harmonic components; And it may include an operation of obtaining a load signature table of the home appliance based on the information about the Euclidean distance.

The method of identifying an operating home appliance may further include identifying an operating home appliance based on the load signature table.

The information about the Euclidean distance may be obtained based on the distance between harmonic components of adjacent sample blocks.

The information about the Euclidean distance may include at least one of the average of the Euclidean distance or the separation rate of the Euclidean distance.

The load signature table of the home appliance may include harmonic component values of the power signal corresponding to the stable state of the home appliance.

The operation of obtaining information about the Euclidean distance includes calculating the Euclidean distance between adjacent sample blocks; Obtaining a cumulative Euclidean distance based on the calculation result; calculating an average Euclidean distance based on the accumulated Euclidean distance; and calculating a separation rate of the Euclidean distance based on the average value of the Euclidean distance.

Obtaining the load signature table includes comparing information on the Euclidean distance and a threshold for each sample block; Setting the operating state of the home appliance based on the comparison result; and an operation of obtaining a load signature table based on the setting result.

The comparing operation may include comparing an average Euclidean distance and a first threshold value; Comparing the separation rate of the Euclidean distance and a second threshold; and generating a state transition signal in response to a case where at least one of the average value of the Euclidean distance or the separation rate of the Euclidean distance is greater than a threshold.

The operating state of the home appliance may include at least one of a ready state, a stable state, or a transition state.

An operating appliance identification device according to an embodiment includes a memory that stores one or more instructions; and a processor for executing the instruction, and when the instruction is executed, the processor samples a power signal of the home appliance to obtain a plurality of sample blocks, and performs signal processing on the plurality of sample blocks to obtain each of the sample blocks. It is possible to extract harmonic components, obtain information about the Euclidean distance of each sample block based on the harmonic components, and obtain a load signature table of the home appliance based on the information about the Euclidean distance. .

The processor may identify an operating home appliance based on the load signature table.

The information about the Euclidean distance may be obtained based on the distance between harmonic components of adjacent sample blocks.

The information about the Euclidean distance may include at least one of the average value of the Euclidean distance or the separation rate of the Euclidean distance.

The load signature table of the home appliance may include harmonic component values of the power signal corresponding to the stable state of the home appliance.

The processor calculates the Euclidean distance between adjacent sample blocks, obtains a cumulative Euclidean distance based on the calculation result, calculates an average value of the Euclidean distance based on the cumulative Euclidean distance, and The separation rate of the Euclidean distance can be calculated based on the average value of the Euclidean distance.

The processor may compare information about the Euclidean distance and a threshold for each sample block, set the operating state of the home appliance based on the comparison result, and obtain a load signature table based on the setting result.

The processor compares the average value of the Euclidean distances with a first threshold value, compares the separation rate of the Euclidean distances with a second threshold value, and compares the average value of the Euclidean distances or the separation rate of the Euclidean distances. A state transition signal may be generated in response to a case where at least one of them is greater than the threshold.

The operating state of the home appliance may include at least one of a ready state, a stable state, or a transition state.

An operating home appliance identification system according to an embodiment includes a plurality of home appliances connected to a household distribution network; And a working home appliance identification device for identifying an operating home appliance among the plurality of home appliances, wherein the working home appliance identification device samples a power signal of the home appliance to obtain a plurality of sample blocks, and uses the plurality of sample blocks as a signal. Process to extract harmonic components of each of the sample blocks, obtain information about the Euclidean distance of each sample block based on the harmonic components, and create a load signature table of home appliances based on the information about the Euclidean distance. can be obtained.

Figure 1 shows an operating home appliance identification system according to one embodiment.
Figure 2 shows a schematic block diagram of the operating appliance identification device shown in Figure 1.
Figure 3 shows a flowchart of a method for identifying an operating appliance according to an embodiment.
Figure 4 shows an example of harmonic components extracted from a sample block.
Figure 5 shows a flowchart of an operation for obtaining information about the Euclidean distance.
Figure 6 shows a flowchart of an operation to obtain a load signature table.
Figure 7 shows a flowchart of an operation for comparing information on the Euclidean distance and a threshold for each sample block.
Figure 8 shows a flowchart of an operation for setting the operating state of a home appliance based on a threshold comparison result.
Figure 9 shows a flowchart of an operation for obtaining a load signature table based on a result of setting the operating state of a home appliance.
Figure 10 shows an example of a load signature table.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be changed and implemented in various forms. Accordingly, the actual implementation form is not limited to the specific disclosed embodiments, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical idea described in the embodiments.

Terms such as first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from another component. For example, a first component may be named a second component, and similarly, the second component may also be named a first component.

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected or connected to the other component, but that other components may exist in between.

Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of the described features, numbers, steps, operations, components, parts, or combinations thereof, and are intended to indicate the presence of one or more other features or numbers, It should be understood that this does not exclude in advance the possibility of the presence or addition of steps, operations, components, parts, or combinations thereof.

As used herein, “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C”, and “A Each of phrases such as “at least one of , B, or C” may include any one of the items listed together in the corresponding phrase, or any possible combination thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art. Terms as defined in commonly used dictionaries should be interpreted as having meanings consistent with the meanings they have in the context of the related technology, and unless clearly defined in this specification, should not be interpreted in an idealized or overly formal sense. No.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and overlapping descriptions thereof will be omitted.

Figure 1 shows an operating home appliance identification system according to one embodiment.

The operating home appliance identification system 10 according to an embodiment may generate a load signature table (eg, the load signature table of FIG. 10) including information related to the unique characteristics of the home appliance. The load signature table may have harmonic component values of a power signal corresponding to the stable state of the home appliance (e.g., a power signal output when the home appliance is in a stable state) as its components. The values of the elements of the load signature table can be accurate, and the operating appliance identification system 10 can accurately identify the operating appliance. The number of components of the load signature table may be minimized, and the operating home appliance identification system 10 can quickly identify operating home appliances.

The operating home appliance identification system 10 may identify an operating home appliance based on the load signature table. The operating home appliance identification system 10 can identify operating home appliances by comparing components included in the load signature table and power signals sampled from the power grid. The operating home appliance identification system 10 can quickly and accurately identify operating home appliances.

The home appliance identification system 10 may include a home appliance identification device 100 and a plurality of home appliances (eg, TV, air conditioner, fan). A plurality of home appliances may be connected to the household distribution network 30. The sampling device 20 may sample power signals from home appliances connected to the household distribution network 30 . The household distribution network 30 may be connected to the utility distribution network 50 through a power meter 40 .

Figure 2 shows a schematic block diagram of the device for identifying a home appliance shown in Figure 1, and Figure 3 shows a flowchart of a method for identifying a home appliance according to an embodiment.

Referring to FIGS. 2 and 3 , the home appliance identification device 100 may perform a home appliance identification method. The operating appliance identification device 100 may include a memory 110 and a processor 130.

The memory 110 may store a load signature table (eg, the load signature table of FIG. 10). The load signature table may have harmonic component values of a power signal corresponding to the stable state of the home appliance (e.g., a power signal output when the home appliance is in a stable state) as its components.

The memory 110 may store instructions (eg, programs) that can be executed by the processor 130 . For example, the instructions may include instructions for executing the operation of the processor 130 and/or the operation of each component of the processor 130.

The processor 130 may process data stored in the memory 110. The processor 130 may execute computer-readable code (eg, software) stored in the memory 110 and instructions triggered by the processor 130 .

The processor 130 may be a data processing device implemented in hardware that has a circuit with a physical structure for executing desired operations. For example, the intended operations may include code or instructions included in the program.

For example, data processing devices implemented in hardware include microprocessors, central processing units, processor cores, multi-core processors, and multiprocessors. , ASIC (Application-Specific Integrated Circuit), and FPGA (Field Programmable Gate Array).

Processor 130 may generate a load signature table. The processor 130 may identify an operating home appliance based on the load signature table.

Referring to FIG. 3, in operation 310, the processor 130 may obtain a plurality of sample blocks by sampling the power signal of the home appliance. A sample block may be a collection of sampled power signals. A sample block may consist of 2^n sample signals (e.g., sampled power signals). For example, a sample block may consist of 2048 sample signals. Adjacent sample blocks may include several sample signals in common (e.g., sample blocks may overlap each other). Sampling of the power signal may be performed through the sampling device 20 of FIG. 1. The sampling rate may vary depending on the size of the power signal (or the size of the harmonic component of the power signal).

In operation 330, the processor 130 performs signal processing (e.g., fast Fourier transform (FFT)) on the plurality of sample blocks to obtain harmonic components of each sample block (e.g., 1st (60 Hz) harmonic component, 3rd order). (120Hz) harmonic component, 5th order (180Hz) harmonic component) can be extracted.

In operation 350, the processor 130 may obtain information about the Euclidean distance of each sample block based on the harmonic components. Information about the Euclidean distance may be obtained based on the distance between harmonic components of adjacent sample blocks. Information about the Euclidean distance may include at least one of the average value of the Euclidean distance or the separation rate of the Euclidean distance.

In operation 370, the processor 130 may obtain a load signature table of a home appliance based on information about the Euclidean distance. The load signature table of a home appliance may include harmonic component values of a power signal corresponding to the stable state of the home appliance (e.g., a power signal output when the home appliance is in a stable state).

Hereinafter, the operation of acquiring information about the Euclidean distance and the operation of generating the load signature table of the home appliance based on the obtained information about the Euclidean distance will be described in detail.

Figure 4 shows an example of harmonic components extracted from a sample block.

The processor (processor 130 in FIG. 2) performs signal processing (e.g., fast Fourier transform, FFT) on a plurality of sample blocks to obtain harmonic components (e.g., 1) for each sample block (e.g., B1, B2). The first (60Hz) harmonic component, the third (120Hz) harmonic component, and the fifth (180Hz) harmonic component can be extracted.

The first harmonic component value of sample block B1 may be 0.0194, the third harmonic component value may be 0.0082, and the fifth harmonic component value may be 0.0095. The 1st harmonic component value of the sample block Bn may be 0.0198, the 3rd harmonic component value may be 0.0082, and the 5th harmonic component value may be 0.0096. If the harmonic component value of the sample block Ba is significantly different from the harmonic component value of the adjacent sample block (e.g., the sample block Ba and the adjacent sample block Ba-1), at the time corresponding to the sample block Ba, the operating state of the home appliance There may be a transition, or the operating state of the home appliance may be unstable.

The processor 130 may define the operating state of the home appliance based on information about the Euclidean distance of each sample block and generate a load signature table of the home appliance based on the defined operating state of the home appliance.

Figure 5 shows a flowchart of an operation for obtaining information about the Euclidean distance.

In operation 351, the processor (e.g., processor 130 of FIG. 2) may calculate the Euclidean distance between adjacent sample blocks through Equation 1.

[Equation 1]

In equation 1, is the Euclidean distance between sample block B1 and sample block B2, is the first harmonic component of sample block B1, may be the 5th harmonic component of sample block B2.

In operation 353, the processor 130 may obtain the cumulative Euclidean distance based on the calculation result. For example, the processor 130 may obtain the Euclidean distance accumulated up to the sample block Ba.

At operation 355, the processor 130 may calculate an average value of the Euclidean distance based on the cumulative Euclidean distance. The average value of the Euclidean distance of the sample block Ba can be calculated through Equation 2.

[Equation 2]

In equation 2, is the average value of the Euclidean distance, is the Euclidean distance between the sample block Bi and the sample block Bj, j may be a value 1 larger than i, and N may have the same value as a. The processor 130 may obtain the average value of the Euclidean distance of the sample block Ba based on the Euclidean distance accumulated up to the sample block Ba.

At operation 357, the processor 130 may calculate the separation rate of the Euclidean distance based on the average value of the Euclidean distance. The separation ratio of the Euclidean distance of sample block Ba can be calculated through Equation 3.

[Equation 3]

In equation 3, may be the separation rate of the Euclidean distance. is the Euclidean distance between the sample block Bi and the sample block Bj, j may be a value 1 larger than i, and N may have the same value as a. The processor 130 may use the average value of the Euclidean distance and the separation rate of the Euclidean distance obtained for each sample block. The separation ratio is a value to find the point where the harmonic component value of a random sample block Ba becomes larger than the harmonic component value of the adjacent sample block by a certain amount, and is the average value of the Euclidean distance calculated up to the sample block Ba and between adjacent sample blocks (e.g. : This is the ratio value of the Euclidean distance values of sample block Ba and sample block Ba-1). Hereinafter, the operation of obtaining a load signature table based on information about the Euclidean distance will be described in detail.

Figure 6 shows a flowchart of an operation to obtain a load signature table.

In operation 371, a processor (e.g., processor 130 of FIG. 2) may compare information about the Euclidean distance and a threshold for each sample block. The processor 130 may compare the average value of the Euclidean distance and the first threshold, and may compare the threshold of the Euclidean distance with the first threshold.

In operation 373, the processor 130 may set the operating state of the home appliance based on the comparison result. The operating state of the home appliance may include at least one of a ready state, a steady state, or a transition state.

In operation 373, the processor 130 may obtain a load signature table based on the setting result.

Figure 7 shows a flowchart of an operation for comparing information on the Euclidean distance and a threshold for each sample block.

Referring to FIG. 7, an operating home appliance identification device (e.g., the operating home appliance identification device 100 of FIG. 1) determines whether the power consumption state of an operating home appliance is a stable state or a transition state (e.g., from a stable state A to another stable state B). It can be determined whether the state is transitioning to .

In operation 371-1, the processor (e.g., processor 130 of FIG. 2) may compare the average value of the Euclidean distance of a random sample block Bx with a first threshold.

In operation 371-2, the processor 130 may compare the separation rate of the Euclidean distance of a random sample block Bx with a second threshold.

In operation 371-3, the processor 130 may generate a state transition signal in response when at least one of the average value of the Euclidean distance or the separation rate of the Euclidean distance is greater than the threshold.

Figure 8 shows a flowchart of an operation for setting the operating state of a home appliance based on a threshold comparison result.

Referring to FIG. 8, the operating home appliance identification device (e.g., the operating home appliance identification device 100 of FIG. 1) determines the operating state of the home appliance as a ready state (or unstable state), a stable state, or a transition state (e.g., stable state A). It can be set to at least one of the states transitioning from to another stable state B.

In operation 373-1, the processor (eg, processor 130 of FIG. 2) may check whether a state transition signal occurred in the previous step.

In operation 373-2, the processor 130 may add 1 to the state maintenance period when a state transition signal does not occur.

In operation 373-3, the processor 130 may check whether the state maintenance period is greater than a specified period. The designated period may be set to prevent frequent transitions of operating states.

In operation 373-4, the processor 130 may set the operating state of the home appliance to the ready state in response to a case where the state maintenance period is less than a specified period. The ready state may be a state set in response to noise. The processor 130 may set the operating state of the home appliance to the ready state for any sample block Bz.

In operation 373-5, the processor 130 may add 1 to the state continuation period in response to a case where the state maintenance period is greater than a specified period. The processor 130 may have determined that the operating state of the home appliance is stable for any sample block Bx in which operation 373-5 is performed.

In operation 373-6, the processor 130 may accumulate harmonic component values by order (eg, 1st, 3rd, and 5th order) for any sample block Bx.

In operation 373-7, the processor 130 may set the operating state of the home appliance to a stable state for a random sample block Bx.

At operation 373-8, the processor 130 may initialize the state maintenance period in response to the state transition signal.

In operation 373-9, the processor 130 may store the state continuous maintenance period and initialize the state continuous maintenance period.

In operation 373-10, the processor 130 may store the accumulated harmonic component value while the operating state of the home appliance is in a stable state and initialize the accumulated harmonic component value.

In operation 373-11, the processor 130 may set the operating state of the home appliance to a transition state for any sample block By.

Figure 9 shows a flowchart of an operation for obtaining a load signature table based on a result of setting the operating state of a home appliance.

In operation 375-1, the processor (eg, processor 130 in FIG. 2) may identify a section in which the operating state of the home appliance is set to a stable state.

In operation 373-2, the processor 130 may read the harmonic component accumulation value of an arbitrary section A set to a stable state (e.g., an arbitrary steady state section A) and the continuous maintenance period of the steady state section A.

In operation 373-3, the processor 130, for an arbitrary steady state section A, divides the accumulated harmonic component value for each order of section A by the continuous maintenance period of section A to obtain a component (e.g., representative value) of the load signature table. can be obtained. For any steady-state interval A, components (e.g., representative values) of the load signature table can be calculated through Equation 4.

[Equation 4]

Representative value = cumulative value of harmonic components by order in the steady state section / steady state maintenance period

In operation 373-4, the processor 130 may check whether any steady state interval A is the last steady state interval.

At operation 373-5, the processor 130 may retrieve the next steady state interval information. For example, the processor 130 can read an arbitrary steady state interval B.

Figure 10 shows an example of a load signature table.

The operating home appliance identification system 10 may generate a load signature table containing information related to the unique characteristics of the home appliance. The load signature table may include harmonic component values of a power signal corresponding to the stable state of the home appliance (e.g., a power signal output when the home appliance is in a stable state).

When the home appliance is a washing machine, the washing machine operates and can have various stable states, such as a rinsing state and a spin-drying state. Referring to Figure 10, home appliance 1 operates and may have two stable states (eg, A, B). However, the stable state of home appliances is not limited to two.

Components (eg, representative values) included in the load signature table may be accurate, and the operating appliance identification system 10 may accurately identify the operating appliance based on the load signature table. The number of components of the load signature table may be minimized, and the operating home appliance identification system 10 can quickly identify operating home appliances.

The embodiments described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, and a field programmable gate (FPGA). It may be implemented using a general-purpose computer or a special-purpose computer, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and software applications running on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and thus stored or executed in a distributed manner. Software and data may be stored on a computer-readable recording medium.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. A computer-readable medium may store program instructions, data files, data structures, etc., singly or in combination, and the program instructions recorded on the medium may be specially designed and constructed for the embodiment or may be known and available to those skilled in the art of computer software. there is. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

The hardware devices described above may be configured to operate as one or multiple software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on this. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims (20)

An operation of sampling a power signal of a home appliance to obtain a plurality of sample blocks;
An operation of signal processing the plurality of sample blocks to extract harmonic components of each sample block;
Obtaining information about the Euclidean distance of each sample block based on the harmonic components; and
An operation of obtaining a load signature table of the home appliance based on the information about the Euclidean distance.
Including, a method of identifying an operating home appliance.
According to paragraph 1,
An operation of identifying an operating home appliance based on the load signature table.
A method for identifying an operating home appliance, further comprising:
According to paragraph 1,
The information about the Euclidean distance is,
Obtained based on the distance between harmonic components of adjacent sample blocks,
How to identify motion home appliances.
According to paragraph 1,
The information about the Euclidean distance is,
Containing at least one of the average value of the Euclidean distance or the separation rate of the Euclidean distance,
How to identify motion home appliances.
According to paragraph 1,
The load signature table of the home appliance is,
Containing harmonic component values of the power signal corresponding to the stable state of the home appliance,
How to identify motion home appliances.
According to paragraph 1,
The operation of obtaining information about the Euclidean distance is,
An operation to calculate a Euclidean distance between adjacent sample blocks;
Obtaining a cumulative Euclidean distance based on the calculation result;
calculating an average Euclidean distance based on the accumulated Euclidean distance; and
An operation of calculating the separation rate of the Euclidean distance based on the average value of the Euclidean distance
Including, a method of identifying an operating home appliance.
According to paragraph 1,
The operation of obtaining the load signature table is:
An operation of comparing information about the Euclidean distance and a threshold for each sample block;
Setting the operating state of the home appliance based on the comparison result; and
Operation of obtaining a load signature table based on the setting result
Including, a method of identifying an operating home appliance.
In clause 7,
The comparison operation is,
Comparing the average Euclidean distance and a first threshold;
Comparing the separation rate of the Euclidean distance and a second threshold; and
An operation of generating a state transition signal in response when at least one of the average value of the Euclidean distance or the separation rate of the Euclidean distance is greater than a threshold value.
Including, a method of identifying an operating home appliance.
In clause 7,
The operating state of the home appliance is,
Comprising at least one of a ready state, a steady state, or a transition state,
How to identify motion home appliances.
A computer program combined with hardware and stored in a computer-readable recording medium to execute the method of any one of claims 1 to 9.
A memory that stores one or more instructions; and
Processor for executing the instructions
Including,
When the instruction is executed, the processor:
Obtain a plurality of sample blocks by sampling the power signal of the home appliance,
Processing the plurality of sample blocks to extract harmonic components of each sample block,
Obtain information about the Euclidean distance of each sample block based on the harmonic components,
Obtaining a load signature table of the home appliance based on the information about the Euclidean distance,
Motion home appliance identification device.
According to clause 11,
The processor,
Identifying an operating home appliance based on the load signature table,
Motion home appliance identification device.
According to clause 11,
The information about the Euclidean distance is,
Obtained based on the distance between harmonic components of adjacent sample blocks,
Motion home appliance identification device.
According to clause 11,
The information about the Euclidean distance is,
Containing at least one of the average value of the Euclidean distance or the separation rate of the Euclidean distance,
Motion home appliance identification device.
According to clause 11,
The load signature table of the home appliance is,
Containing harmonic component values of the power signal corresponding to the stable state of the home appliance,
Motion home appliance identification device.
According to clause 11,
The processor,
Calculate the Euclidean distance between adjacent sample blocks,
Obtain the cumulative Euclidean distance based on the calculation results,
Calculate the average value of the Euclidean distance based on the cumulative Euclidean distance,
Calculating the separation rate of the Euclidean distance based on the average value of the Euclidean distance,
Motion home appliance identification device.
According to clause 11,
The processor,
Compare the information about the Euclidean distance and the threshold for each sample block,
Setting the operating state of the home appliance based on the comparison result,
Obtaining a load signature table based on the setting result,
Motion home appliance identification device.
According to clause 17,
The processor,
Compare the average value of the Euclidean distance and the first threshold,
Compare the separation rate of the Euclidean distance and the second threshold,
Generating a state transition signal in response when at least one of the average value of the Euclidean distance or the separation rate of the Euclidean distance is greater than a threshold value,
Motion home appliance identification device.
According to clause 17,
The operating state of the home appliance is,
Comprising at least one of a ready state, a steady state, or a transition state,
Motion home appliance identification device.
In the operating home appliance identification system,
A plurality of home appliances connected to the household distribution network; and
An operating appliance identification device that identifies an operating appliance among the plurality of appliances.
Including,
The operating home appliance identification device,
Obtain a plurality of sample blocks by sampling the power signal of the home appliance,
Processing the plurality of sample blocks to extract harmonic components of each sample block,
Obtain information about the Euclidean distance of each sample block based on the harmonic components,
Obtaining a load signature table of home appliances based on the information about the Euclidean distance,
Motion home appliance identification system.