KR20130056036A - Method, apparatus, and computer-readable recording medium for identifying appliance, and power monitoring system - Google Patents

Abstract

PURPOSE: A device identification method, a device identification device, a computer readable recording medium, and a power monitoring system are provided to automatically monitor devices and to identify a kind of the devices. CONSTITUTION: A power signal sets a plurality of time sections(T1,T2) according to timing(S120). One or more time sections(T1) are selected from a plurality of the time sections. The plurality of the time sections is set. One or more power signal parameters are measured in the selected time section(S130). A kind of devices is determined by comparing the measured power signal parameter with the stored power signal parameter(S140). [Reference numerals] (S110) Receive power signals from a device; (S120) Divide the power signals into one or more time sections according to power signal received timings, and select at least one time section in which the device is in an on state for a predetermined time or more from one or more time sections; (S130) Measure at least one power signal parameter among the deviation degree of power signal change in the on state of the selected time section, the slope of the power signal in the on state of the selected time section, the switching frequency of on state and off state in the selected time section, and the duty cycle of the selected time section; (S140) Determine the kind of the device by comparing the measured power signal parameter with pre-stored power signal parameters

Description

Device identification methods, device identification devices, computer readable recording media for device identification methods, and power monitoring systems {METHOD, APPARATUS, AND COMPUTER-READABLE RECORDING MEDIUM FOR IDENTIFYING APPLIANCE, AND POWER MONITORING SYSTEM}

The present invention relates to a device identification method, a device identification device, a computer readable recording medium for a device identification method, and a power monitoring system, and more particularly, to identify the type of device currently being monitored automatically without user intervention. A device identification method, a device identification device, a computer readable recording medium for the device identification method, and a power monitoring system.

When the user is aware of the energy use status of various devices, the user can control the energy use by himself and thus, the energy saving effect can be seen. In order for the user to be aware of the energy usage of the device, monitoring of the energy usage of the device must be preceded. The most effective way to monitor energy usage is to collect and display the energy conditions used by each device in real time. In this way, it is known that by monitoring the current state of energy use, it brings about a certain energy saving effect.

However, a system that monitors power to a device in real time connects an information collection device called a smart plug to a monitored device, and a human manually checks which device the smart plug is connected to. You must inform. Therefore, there is a problem of using a monitoring system (for example, Shwetak N. Patel et al, "At the Flick of a Switch: Dectecting and Classifying Unique Electrical Events on the Residential Power Line," UbiComp 2007, pp271-). 288, 2007).

On the other hand, what can be easily thought of as an automatic device identification method is a standardized method in which a sensor node and a device communicate with each other to obtain an identifier, but this can be applied to existing home appliances that do not conform to the standard. There is no problem.

An object of the present invention is to solve the above-mentioned problems.

In addition, the present invention provides a device identification method, a device identification device, a computer readable recording medium for the device identification method, and a power monitoring system capable of automatically identifying the type of device currently being monitored without user intervention. The purpose.

In order to accomplish the above object, a representative structure of the present invention is as follows.

According to one aspect of the invention, (a) receiving a power signal from a device, (b) selecting at least one time interval in which the device is on for at least a predetermined time based on the power signal (C) a degree of deviation of the change of the power signal in the on state of the selected time interval, the slope of the power signal in the on state of the selected time interval, an on state and an off state in the selected time interval Measuring a power signal parameter of at least one of a frequency at which is changed and a duty cycle of the selected time interval, and (d) comparing the measured power signal parameter with previously stored power signal parameters, wherein A device identification method is provided that includes determining a type of device.

According to another aspect of the present invention, a power signal receiver for receiving a power signal from a device, selecting a time interval for selecting at least one time interval in which the device is on for a predetermined time or more based on the power signal The deviation degree of the change of the power signal in the on state of the selected time interval, the slope of the power signal in the on state of the selected time interval, the frequency of changing the on state and off state in the selected time interval, And a power signal parameter measuring unit for measuring at least one power signal parameter of a duty cycle of the selected time interval, and comparing the measured power signal parameter with previously stored power signal parameters to determine a type of the device. An apparatus identification apparatus is provided that includes an apparatus type determination unit that determines.

According to another aspect of the invention, at least one sensor node connected to a power cable of the device and periodically measuring and transmitting the power signal of the device, and using the power signal transmitted by the sensor node, the sensor node And a server for identifying a type of device to which the device is connected, wherein the server comprises: a sink node receiving the power signal, and at least one time in which the device is on for a predetermined time or more based on the power signal. A time section selector for selecting a section, a degree of deviation of the change of the power signal in the on state of the selected time section, a slope of the power signal in the on state of the selected time section, an on state and an off state in the selected time section ( off) a power signal parameter of at least one of a frequency of changing states and a duty cycle of the selected time interval. A power monitoring system is provided that includes a power signal parameter measuring unit for measuring a meter, and a device type determination unit that determines the type of the device by comparing the measured power signal parameter with previously stored power signal parameters.

According to the present invention, the effect of automatically identifying the type of the device currently being monitored without the user's operation is achieved.

1 is a flowchart illustrating a device identification method according to an embodiment of the present invention.
2 is a graph showing the current consumption received from the device in chronological order.
3 is a diagram illustrating power signal parameters measured from power signals of various devices.
4 is a diagram illustrating a state in which a plurality of on states exist in a selected time interval.
5 is a block diagram illustrating a power monitoring system according to another embodiment of the present invention.
6 is a diagram illustrating a user interface.

DETAILED DESCRIPTION OF THE INVENTION The following detailed description of the invention refers to the accompanying drawings that show, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different, but need not be mutually exclusive. For example, certain features, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in connection with an embodiment. It is also to be understood that the position or arrangement of the individual components within each disclosed embodiment may be varied without departing from the spirit and scope of the invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is to be limited only by the appended claims, along with the full scope of equivalents to which such claims are entitled, if properly explained. In the drawings, like reference numerals refer to the same or similar functions throughout the several views.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, so that those skilled in the art can easily carry out the present invention.

1 is a flowchart illustrating a device identification method according to an embodiment of the present invention.

In the device identification method according to an embodiment of the present invention, a power signal is received from the device in chronological order (S110).

2 is a graph showing the current consumption received from the device in chronological order. Although the power signal received from the device is shown in FIG. 2 as a current consumption amount, the power signal may be an actual power amount or a reactive power amount.

Next, a plurality of time periods T1 and T2 are set for the power signal according to the timing at which the power signal is received (S120). In FIG. 2, the number of time intervals is illustrated as two, but the number of time intervals is not limited thereto. For example, three or more time periods may be set or one time period may be set. It is also possible to mechanically set an arbitrary time period without determining whether the power signal is on.

Meanwhile, the time of each of the time intervals T1 and T2 may be 2 hours, but is not limited thereto and may be variously modified to 1 hour or 3 hours. In a typical situation, if the time for the device to operate in an on state (that is, the time from the off state to the off state after turning on again) can be known, the time intervals T1, T2) Each time can be set as an intermediate value between the minimum time and the maximum time. For example, if the device often operates on for 1 to 3 hours, the time of each of the time intervals T1 and T2 may be set to 2 hours.

In operation S120, at least one time interval T1 in which the device is on for a predetermined time or more is selected from the plurality of time intervals T1 and T2. Referring to FIG. 2, of the two time intervals T1 and T2, the time interval T1 is selected because the on state is longer than a predetermined time, whereas the time interval T2 is not longer than the constant time. Because it is not selected. On the other hand, even in a section in which the on-state signal is measured, it may not be selected as a time section in the on-state for a predetermined time or more when the system cannot classify the noise.

In the selected time interval T1, the power signal parameter may be measured, and the type of the device may be determined using the measured parameter (the power signal parameter measurement and the device type determination will be described later). On the other hand, the power signal parameter may not be measured for the target device in the non-selected time period T2. Or, it can be determined that no target device is operating.

To determine whether the device is in the on state, the power signal value is compared with a predetermined threshold value, and then, if the power signal value is greater than the threshold value, it is determined to be in an on state, and if the power signal value is less than the threshold value, it is determined to be in an off state. Can be. Here, the threshold value may be greater than the power signal value in the standby state of the device and less than the power signal value in the normal operating state of the device.

As another method of determining the on state of the device, it is determined that the on state of the device starts when the power signal value of the device increases by a certain amount or more within a predetermined time, and when the power signal value of the device decreases by a certain amount or more within a certain time. It can be determined that the on state of the device is terminated. That is, it can be determined that there is a change in the on state and the off state when the change width of the power signal value is equal to or greater than a certain magnitude.

In order to select a time period in which the device is on for more than a predetermined time, the ratio (time on state) between the time that the device is on and the time of each time interval within each time period is obtained. You can select a time interval where the ratio is above a certain ratio. Referring to FIG. 2, a time section T1 having a high ratio in the on state OS1 may be selected, and a time section T2 having a low ratio in the on state OS2 may not be selected. On the other hand, it is possible to select a time interval in which the on state of the device is 25% or more (off state is 75% or less). The 25% figure can be varied in many ways.

In the above, in order to select a time section (T1 of FIG. 1) in a predetermined time on state, time sections T1 and T2 are set (S120) and a time section T1 among the set time sections T1 and T2. It is shown to select. However, without setting the time intervals T1 and T2, the time interval T1 in the ON state for a predetermined time may be selected immediately. For example, when a state in which the on state continues for a predetermined time or longer while monitoring the power signal is detected, the time interval T1 may be selected such that the on state is included for a predetermined time or more.

Referring back to FIG. 1, after setting a plurality of time intervals of the power signal (S120), at least one power signal parameter is measured in the selected time interval (S130). The measured power signal parameters are i) the degree of deviation of the change of the power signal in the on state of the selected time interval (hereinafter referred to as the degree of change) (VO), ii) the slope of the power signal in the on state of the selected time interval (SO). iii) how often the on and off states change in the selected time period (ZC), and iv) the duty cycle (DC) of the selected time period.

The change degree VO of the power signal and the slope SO of the power signal are parameters measured in the on state of the selected time interval. The degree of change (VO) of the power signal can be obtained by dividing the standard deviation of the power signal in the on state by the average of the power signal in the on state. An example of obtaining the slope SO of the power signal will be described. Curve fitting the received power signal pattern. You can use the linear regression method here. It is an algorithm that determines the final values of a and b by minimizing errors while adjusting the values of a and b through iteration, assuming that the current data can be represented in one dimension (y = ax + b). . The a value thus obtained may be the slope SO of the power signal.

The frequency (ZC) and the duty cycle (DC) in which the on state and the off state are switched are parameters measured over the selected time interval. The frequency ZC at which the on state and the off state are changed may be set to the number of times the on state and the off state are alternated per unit time in the selected time interval. The duty cycle DC may be set to a value obtained by dividing the time of the on state by the time of the off state in the selected time interval, or may be set to a value obtained by dividing the time of the on state by the time of the selected time interval.

All of the four power signal parameters described above may be measured and used, or only some of the four power signal parameters may be measured and used. For example, only the frequency (ZC) of switching on and off states may be measured and used, or the frequency (C) of switching between on and off states (ZC) and on-state may be measured and used. In addition, the two parameters and the duty cycle may be measured and used.

On the other hand, it has been described above that the power signal parameter is not measured for the device in the time interval T2 not selected in step S120.

3 is a diagram illustrating power signal parameters measured from power signals of various devices. In Fig. 3, the horizontal axis represents time and the vertical axis represents current consumption, and each of the time intervals T11, T21, ... is set to 2 hours, while in Fig. 3, only some of the four power signal parameters are measured. Although shown, all four power signal parameters may be measured, or power signal parameters other than those shown may be measured.

3 (a) shows the power signal parameter measured in the refrigerator. The duty cycle DC is measured in the time interval T11 and the slope SO of the power signal is measured in the time interval T12. . It can be seen that the power signal decreases as time passes in the time period T12.

3 (b) shows the power signal parameter measured in the Kimchi refrigerator, measuring the duty cycle DC in the time interval T21 and measuring the frequency ZC at which the on and off states are switched in the time interval T22. It was.

Figure 3 (c) shows the power signal parameters measured in the rice cooker, the duty cycle (DC) was measured in the time interval (T31).

3 (d) shows power signal parameters measured in the TV, and the change degree VO of the power signal in the time interval T41 and the time interval T42 was measured.

3 (e) shows the power signal parameters measured in the washing machine, and the change degree VO of the power signal was measured in the time interval T51.

4 is a diagram illustrating a state in which a plurality of on states exist in a selected time interval.

Referring to FIG. 4, a plurality of on states OS3 and OS4 may exist in the selected time interval T3. In this case, the average of the degree of change VO of the power signal and the average of the slope SO of the power signal measured in each of the plurality of on states OS3 and OS4 may be further measured. The average value thus obtained may be used as the degree of change VO of the power signal and the slope SO of the power signal in the selected time interval T3.

Referring back to FIG. 1, after measuring at least one power signal parameter in the selected time interval (S130), the measured power signal parameter is compared with previously stored power signal parameters to determine the type of device ( S140 of FIG. 1).

K-nearest neighbor (K-NN) rules can be used to determine the type of device. In detail, assuming that all four power signal parameters VO, SO, DC, and ZC are used, four parameters of one device may be expressed as one vector (hereinafter, referred to as a power signal parameter vector). . Euclidean distances between power signal parameter vectors measured from a device to be identified and power signal parameter vectors previously measured from different types of devices are obtained. Then, select power signal parameter vectors corresponding to K (K is a natural number) Euclidean distances in the smallest order of Euclidean distances, and select the most of the K types of devices corresponding to the selected K power signal parameter vectors. It can be judged as a kind that occupies a large number or a majority.

Meanwhile, a method such as a support vector machine (SVM) may be used to determine the type of device.

The device identification method according to another embodiment of the present invention may measure power signal characteristics of a plurality of devices of different types, store them in a database, and determine the type of the device using the stored power signal characteristics.

Specifically, the device identification method according to another embodiment of the present invention, the step of receiving a power signal from a plurality of devices of different types, for each of the plurality of devices in the state that the device is on for a predetermined time or more Selecting at least one time interval, measuring power signal parameters for each of the plurality of devices, and storing the type and measured power signal parameters of each of the plurality of devices in a database do.

Next, when a power signal is received from a device whose type is unknown, the type of the device may be determined by measuring the power signal parameter of the device and comparing the measured power signal parameter with the power signal parameter stored in the database. Can be.

According to an embodiment of the present invention, the method may further include generating a power control signal for the determined device with reference to the information on the type of the device determined according to the above-described process. Thus, since the power control signal according to the type of the device is generated based on the result of determining the type of the device, there is an effect that the customized control according to the type of the device is enabled.

5 is a block diagram illustrating a power monitoring system according to another embodiment of the present invention.

Referring to FIG. 5, the power monitoring system 500 according to another embodiment of the present invention may include sensor nodes 520_1, 520_2,..., 520_n and a server 530. The server 530 may include a time section selector 550, a power signal parameter measurer 560, and a device type determiner 570.

The function of each of the blocks shown in FIG. 5 will be described below.

The sensor nodes 520_1, 520_2, ..., 520_n may be attached to the devices 510_1, 510_2, ..., 510_n, respectively. The sensor nodes 520_1, 520_2,..., 520_n are connected to power cables of the devices 510_1, 510_2,..., 510_n and power signals PS1, PS2,... Of the devices 510_1, 510_2,. PSn is periodically measured and transmitted to the server 530. It has been described above that the power signals PS1, PS2,..., PSn may be at least one of the current consumption amount, the effective power amount, or the reactive power amount.

The sink node 540 receives the power signals PS1, PS2,..., PSn from the sensor nodes 520_1, 520_2,..., 520_n. The time section selector 550 divides the power signal into a plurality of time sections according to the timing at which the power signals PS1, PS2, ..., PSn are received, and the power signals PS1, PS2, ..., among the plurality of time sections. PSn) selects at least one time interval in which the devices 510_1, 510_2, ..., 510_n are in the on state for a predetermined time or more. The time section selector 550 sets one or more time sections of the power signals PS1, PS2,..., PSn according to the timing at which the power signals PS1, PS2,. At least one time interval in which the devices 510_1, 510_2,..., 510_n are on for a predetermined time or more may be selected. The time section selector 550 may not select a time section in which one or more time periods are included in the noise even if the device is not in the on state for more than a predetermined time or an on state. The power signal parameter may not be measured for a time section not selected by the time section selection unit 550.

The power signal parameter measuring unit 560 may include a change in the power signal VO in the on state of the selected time interval, a slope SO of the power signal in the on state of the selected time interval, and an on state and an off state in the selected time interval. The power signal parameters PSP1, PSP2,..., PSPn of at least one of the changing frequency ZC and the duty cycle DC of the selected time interval are measured. The device type determination unit 570 compares the measured power signal parameters PSP1, PSP2,..., And PSPn with the power signal parameters stored in the database 590, and the devices 510_1, 510_2,..., 510_n Type).

The power monitoring system 500 according to another embodiment of the present invention may further include a user interface. Hereinafter, the user interface will be described with reference to FIG. 6.

6 is a diagram illustrating a user interface.

Referring to FIG. 6, the user interface 600 may display a result of analyzing a type of the determined device and a power signal of the determined device. The device's power consumption can be graphed in real time. You can also compare past power usage with current usage, making it easier to see how much power you are using compared to the past. As shown in the lower left of FIG. 6, the power consumption rank and specific gravity of each device may be displayed, and as shown in the middle of the right side of FIG. 6, an estimated power consumption of one month may be displayed. For example, you can forecast and show monthly power consumption based on data collected for several days from the beginning of the month and past usage. Also, as shown in the lower right of FIG. 6, an energy saving tip may be displayed.

On the other hand, it is noted that the contents shown in FIG. 6 are merely examples and may be variously changed. For example, some of the contents of FIG. 6 may be deleted, and another analysis result of the power signal may be displayed as a graph.

The embodiments of the present invention described above can be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, and the like, alone or in combination. Program instructions recorded on the computer-readable recording medium may be those specially designed and configured for the present invention, or may be known and available to those skilled in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs, DVDs, and magneto-optical media such as floptical disks. media), and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform the process according to the invention, and vice versa.

Although the present invention has been described by specific embodiments such as specific components and the like, but the embodiments and the drawings are provided to assist in a more general understanding of the present invention, the present invention is not limited to the above embodiments. For those skilled in the art, various modifications and variations can be made from such descriptions.

Therefore, the spirit of the present invention should not be construed as being limited to the above-described embodiments, and all of the equivalents or equivalents of the claims, as well as the following claims, I will say.

500: power monitoring system
510_1, 510_2,... 510_n: Devices
520_1, 520_2,... 520_n: sensor nodes
540: sink node
550: time interval selection unit
560: power signal parameter setting
570: device type determination unit
590: database

Claims (26)

(a) receiving a power signal from a device,
(b) selecting at least one time interval in which the device is on for a predetermined time or more based on the power signal,
(c) the degree of deviation of the change of the power signal in the on state of the selected time interval, the slope of the power signal in the on state of the selected time interval, and the frequency at which the on and off states of the selected time interval are changed. Measuring a power signal parameter of at least one of a duty cycle of the selected time interval, and
(d) comparing the measured power signal parameter with previously stored power signal parameters to determine the type of device;
Device identification method comprising a. The method of claim 1,
The step (b)
Set one or more time intervals of the power signal in accordance with the timing at which the power signal was received,
And selecting at least one time interval in which the device is in an on state for a predetermined time from among the one or more time intervals. The method of claim 1,
The step (b)
The time period when the device is not in the on state for a predetermined time or even when the on state is measured, does not select a time interval that includes a predetermined ratio or more,
The device identification method, characterized in that the power signal parameter is not measured or it is determined that the device is not operating for the non-selected time period. The method of claim 1,
(e) generating a power control signal for the determined device by referring to the information on the type of the determined device;
Device identification method further comprising. The method of claim 1,
The power signal is,
And at least one of current consumption, effective power, and reactive power. The method of claim 1,
The step (c)
When there are a plurality of on states in the selected time interval, at least one power signal parameter of an average of a variation degree of a variation of the power signal measured in each of the plurality of on states and an average of a slope are further measured. Device identification method. The method of claim 1,
The step (b)
And selecting a time interval in which the on state of the device is 25% or more and the off state is 75% or less. The method of claim 1,
The step (b)
By comparing the power signal value of the device with a threshold value, it is determined whether the device is in an on state,
The threshold value is,
And greater than a power signal value in a standby state of the device and less than a power signal value in a normal operating state of the device. The method of claim 1,
The step (b)
If the power signal value of the device increases more than a certain amount within a certain time, it is determined that the on state of the device is started,
And determining that the on state of the device is terminated when the power signal value of the device decreases by more than the predetermined size within the predetermined time. The method of claim 1,
The step (d)
Obtaining Euclidean distances between the vector including the measured power signal parameter and each of the vectors including the stored power signal parameters,
Device identification, characterized in that for determining the type of device having the measured power signal parameter based on the type of the device indicated by the vectors corresponding to the small K (K is a natural number) Euclidean distance of the Euclidean distance Way. The method of claim 1,
Before the step (a)
(f) receiving power signals from a plurality of devices of different types,
(g) for each of the plurality of devices, divide the power signal into one or more time intervals according to a timing at which the power signal is received, and wherein the device is on for more than a predetermined time of the one or more time intervals; Selecting at least one time interval in a state,
(h) a deviation degree of the change of the power signal in the on state of the selected time interval, the slope of the power signal in the on state of the selected time interval, and the on state in the selected time interval, for each of the plurality of devices And measuring a power signal parameter of at least one of a frequency at which an off state is changed, and a duty cycle of the selected time interval, and
(i) storing the type of each of the plurality of devices and the measured power signal parameters;
Further comprising:
The step (d)
And comparing the power signal parameter measured in step (c) with the power signal parameters stored in step (i). The method of claim 1,
The variation degree of the change of the power signal is,
And a standard deviation of the power signal in the on state of the selected time interval divided by an average of the power signal in the on state of the selected time interval. A power signal receiver for receiving a power signal from a device,
A time interval selector configured to select at least one time interval in which the device is on for a predetermined time or more based on the power signal;
A degree of variation in the change of the power signal in the on state of the selected time interval, a slope of the power signal in the on state of the selected time interval, a frequency of changing an on state and an off state in the selected time interval, and the A power signal parameter measuring unit measuring at least one power signal parameter of a duty cycle of the selected time interval;
A device type determination unit which determines the type of the device by comparing the measured power signal parameter with previously stored power signal parameters,
Device identification device having a. The method of claim 13,
The time section selector,
Set one or more time intervals of the power signal in accordance with the timing at which the power signal was received,
And selecting at least one time interval in which the device is in an on state for a predetermined time from among the one or more time intervals. The method of claim 13,
The time section selector,
The time period when the device is not in the on state for a predetermined time or even when the on state is measured, does not select a time interval that includes a predetermined ratio or more,
The apparatus for identifying a device, characterized in that the power signal parameter is not measured or it is determined that the device is not operating for the non-selected time period. The method of claim 13,
A power control signal generator for generating a power control signal for the determined device with reference to the information on the type of the determined device.
Device identification apparatus further comprising a. The method of claim 13,
The power signal is,
And at least one of current consumption, effective power, and reactive power. The method of claim 13,
The power signal parameter measuring unit,
When there are a plurality of on states in the selected time interval, at least one power signal parameter of an average of a variation degree of a variation of the power signal measured in each of the plurality of on states and an average of a slope are further measured. Device identification apparatus. The method of claim 13,
The time section selector,
And selecting a time interval in which the on state of the device is 25% or more and the off state is 75% or less. The method of claim 13,
The time section selector,
By comparing the power signal value of the device with a threshold value, it is determined whether the device is in an on state,
The threshold value is,
And greater than a power signal value in a standby state of the device and less than a power signal value in a normal operating state of the device. The method of claim 13,
The time section selector,
If the power signal value of the device increases more than a certain amount within a certain time, it is determined that the on state of the device is started,
And determine that the on state of the device is terminated when the power signal value of the device decreases by more than the predetermined size within the predetermined time. The method of claim 13,
The device type determination unit,
Obtaining Euclidean distances between the vector including the measured power signal parameter and each of the vectors including the stored power signal parameters,
Device identification, characterized in that for determining the type of device having the measured power signal parameter based on the type of the device indicated by the vectors corresponding to the small K (K is a natural number) Euclidean distance of the Euclidean distance Device. The method of claim 13,
The variation degree of the change of the power signal is,
And a standard deviation of the power signal in the on state of the selected time interval divided by an average of the power signal in the on state of the selected time interval. At least one sensor node connected to a power cable of a device and periodically measuring and transmitting a power signal of the device, and
A server for identifying the type of device to which the sensor node is connected, by using the power signal transmitted by the sensor node;
And,
The server comprises:
A sink node for receiving the power signal,
A time for dividing the power signal into one or more time intervals according to a timing at which the power signal is received, and selecting at least one time interval in which the device is on for a predetermined time or more among the one or more time intervals. Segment Selector,
A degree of variation in the change of the power signal in the on state of the selected time interval, a slope of the power signal in the on state of the selected time interval, a frequency of changing an on state and an off state in the selected time interval, and the A power signal parameter measuring unit measuring at least one power signal parameter of a duty cycle of the selected time interval;
A device type determination unit which determines the type of the device by comparing the measured power signal parameter with previously stored power signal parameters,
Power monitoring system comprising a. 25. The method of claim 24,
A user interface for displaying the type of the determined device and a result of analyzing the power signal of the determined device;
Power monitoring system characterized in that it further comprises. 13. A computer program for executing the method according to any one of claims 1 to 12.

Images