JP6791152B2 - Estimator, estimation method, and program - Google Patents

Description

The present invention relates to an estimation device, an estimation method, and a program.

Patent Document 1 discloses a technique of extracting a feature amount from measurement data detected by a measurement sensor installed near a feeder inlet and estimating an operating state of an electric device group based on the feature amount.

The power consumption value or the current consumption value of each of a plurality of electric devices can be estimated by using the technique described in Patent Document 1. That is, the above estimation can be realized by preparing a plurality of teacher data having feature quantities included in the measurement data during operation at a plurality of power consumption values or current consumption values for each electrical device. In the technique of estimating the power consumption value or the current consumption value of each of such electric devices, there are the following problems.

Inverter equipment (electric equipment equipped with an inverter) takes a large number of power consumption values and current consumption values. When estimating the operating state of an inverter device, a large number of power consumption values or a large number of teacher data corresponding to each of the current consumption values (example: teacher data corresponding to each power consumption value of 1 W: current consumption value of 10 mA each) By using the teacher data corresponding to the above, the accuracy of estimating the power consumption value or the current consumption value of the electric device is improved. However, as the number of teacher data increases, problems such as an increase in the calculation cost required for machine learning occur.

On the other hand, a small number of teacher data corresponding to each of a small number of power consumption values or current consumption values (example: teacher data corresponding to each power consumption value of 200 W, teacher data corresponding to each of the current consumption values of 2 A) By using it, the calculation cost required for machine learning can be reduced. However, as the number of teacher data decreases, problems such as deterioration of the accuracy of estimating the power consumption value or the current consumption value of the electric device occur.

Patent No. 3403368

As described above, Patent Document 1 has a problem that good estimation accuracy cannot be realized while reducing the calculation cost. An object of the present invention is to provide a technique for solving the above problems.

According to the present invention
A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means executes the estimation process selected by the selection means , and
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group provides an estimation device in which the number of the teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group .

Further, according to the present invention,
Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input receiving means for accepting a user input for selecting either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of
A display means for displaying the estimation result based on the estimation process selected by the user input on the display.
Have,
When the selected estimation process is switched while the display means is displaying the estimation result on the display, the estimation result to be displayed on the display is estimated after the switching. An estimation device for switching to the estimation result based on the processing is provided.

Further, according to the present invention,
The computer
A data acquisition process for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation step of executing a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection step of selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
And run
In the estimation step, the estimation process selected in the selection step is executed .
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group provides an estimation method in which the number of the teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group .

Further, according to the present invention,
Computer,
Data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored,
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group.
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
To function as
The estimation means executes the estimation process selected by the selection means , and
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group is provided with a program in which the number of the teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group .

Further, according to the present invention,
The computer
Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input reception process that accepts user input to select either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of
A display process for displaying the estimation result based on the estimation process selected by the user input on the display, and
And run
In the display step, when the selected estimation process is switched while the estimation result is displayed on the display, the estimation result displayed on the display is estimated after the switching. An estimation method for switching to the estimation result based on the process is provided.

Further, according to the present invention,
Computer,
Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input receiving means that accepts user input to select either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of the above.
A display means for displaying an estimation result based on the estimation process selected by the user input on a display.
To function as
When the selected estimation process is switched while the display means is displaying the estimation result on the display, the estimation result to be displayed on the display is estimated after the switching. A program for switching to the estimation result based on the process is provided.

According to the present invention, a technique for achieving good estimation accuracy while reducing calculation costs is realized.

The above-mentioned objectives and other objectives, features and advantages will be further clarified by the preferred embodiments described below and the accompanying drawings below.

It is a figure which conceptually shows an example of the hardware composition of the apparatus of this embodiment. This is an example of a functional block diagram of the estimation device of the present embodiment. This is an example of a functional block diagram of the estimation unit of the present embodiment. It is a figure which shows an example of the information stored in the estimation part of this embodiment schematically. It is a flowchart which shows an example of the processing flow of the estimation apparatus of this embodiment. It is a flowchart which shows an example of the processing flow of the estimation apparatus of this embodiment. This is an example of a functional block diagram of the estimation device of the present embodiment. It is a flowchart which shows an example of the processing flow of the estimation apparatus of this embodiment. This is an example of a functional block diagram of the estimation device of the present embodiment. This is an example of a functional block diagram of the estimation device of the present embodiment. It is a figure which shows an example of the information stored in the estimation part of this embodiment schematically. It is a flowchart which shows an example of the processing flow of the estimation apparatus of this embodiment. This is an example of a functional block diagram of the estimation device of the present embodiment. This is an example of a functional block diagram of the estimation device of the present embodiment. It is a flowchart which shows an example of the processing flow of the estimation apparatus of this embodiment. This is an example of a functional block diagram of the estimation device of the present embodiment. This is an example of a functional block diagram of the estimation device of the present embodiment. This is an example of the UI screen displayed by the estimation device of the present embodiment. This is an example of the UI screen displayed by the estimation device of the present embodiment.

First, an example of the hardware configuration of the device (estimation device) of the present embodiment will be described. Each part of the device of the present embodiment is stored in a storage unit (stored from the stage of shipping the device in advance) such as a CPU (Central Processing Unit) of an arbitrary computer, a memory, a program loaded in the memory, and a hard disk for storing the program. In addition to the programs provided, it can also store programs downloaded from storage media such as CDs (Compact Discs) and servers on the Internet), and by any combination of hardware and software centered on the network connection interface. It will be realized. And, it is understood by those skilled in the art that there are various modifications of the realization method and the device.

FIG. 1 is a diagram conceptually showing an example of a hardware configuration of the device (estimation device) of the present embodiment. As shown in the figure, the device of the present embodiment includes, for example, a CPU 1A, a RAM (Random Access Memory) 2A, a ROM (Read Only Memory) 3A, a communication unit 8A, an auxiliary storage device 9A, etc., which are interconnected by a bus 10A. Have. The device of the present embodiment may further include a display control unit 4A, a display 5A, an operation reception unit 6A, an operation unit 7A, and the like. Further, although not shown, the device of the present embodiment may also include other elements such as a microphone and a speaker. Moreover, it is not necessary to have a part of the elements shown in the figure.

The CPU 1A controls the entire computer of the device together with each element. The ROM 3A includes an area for storing a program for operating a computer, various application programs, various setting data used when the program operates, and the like. The RAM 2A includes an area for temporarily storing data such as a work area for operating a program. The auxiliary storage device 9A is, for example, an HDD (Hard Disc Drive), and can store a large amount of data.

The display 5A is, for example, a display device (LED (Light Emitting Diode) display, liquid crystal display, organic EL (Electro Luminescence) display, etc.). The display 5A may be a touch panel display integrated with the touch pad. The display control unit 4A reads the data stored in the VRAM (Video RAM), performs a predetermined process on the read data, and then sends the data to the display 5A to display various screens. The operation reception unit 6A receives various operations via the operation unit 7A. The operation unit 7A includes operation keys, operation buttons, switches, a jog dial, a touch panel display, a keyboard, and the like. The communication unit 8A connects to a network such as the Internet or a LAN (Local Area Network) by wire and / or wirelessly, and communicates with other electronic devices. Further, the communication unit 8A can directly connect to another electronic device by wire and / or wirelessly to perform communication.

Hereinafter, the present embodiment will be described. The functional block diagram used in the description of the following embodiment shows the block of the functional unit, not the configuration of the hardware unit. In these figures, each device is described to be realized by one device, but the means for realizing the device is not limited to this. That is, it may be a physically separated configuration or a logically separated configuration. The same components are designated by the same reference numerals, and the description thereof will be omitted as appropriate.

<First Embodiment>
First, the outline of the present embodiment will be described. The estimation device of the present embodiment can execute an estimation process (first estimation process) that emphasizes estimation accuracy and an estimation process (second estimation process) that emphasizes calculation cost.

According to such an estimation device of the present embodiment, a plurality of estimation processes are executed in a situation where estimation accuracy is important, a second estimation process is executed in a situation where calculation cost is important, and so on. The estimation process can be used properly. Therefore, a good balance between the estimation accuracy and the calculation cost can be maintained as compared with the configuration in which the estimation processing always emphasizes the estimation accuracy and the configuration in which the estimation processing always emphasizes the calculation cost. As a result, good estimation accuracy can be achieved while reducing the calculation cost.

Next, the configuration of the present embodiment will be described in detail. FIG. 2 shows an example of a functional block diagram of the estimation device 10 of the present embodiment. As shown in the figure, the estimation device 10 includes a data acquisition unit 11, an estimation unit 12, and a selection unit 13.

The data acquisition unit 11 acquires measurement data (instantaneous waveform data; waveform data according to the AC frequency; the same applies hereinafter) of the current consumption or power consumption of the entire plurality of electrical devices to be monitored. The data acquisition unit 11 acquires measurement data from one or a plurality of measurement sensors installed at arbitrary positions such as a distribution board, each branch of the distribution board, an outlet, and a table tap. The data acquisition unit 11 can acquire time-series measurement data from a predetermined measurement sensor.

In addition, the data acquisition unit 11 may further acquire the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of electrical devices to be monitored. For example, the data acquisition unit 11 may acquire the instantaneous value from the measurement sensor.

A plurality of electric devices connected to the wiring on the downstream side of the installation position of the measurement sensor and receiving power are the electric devices to be monitored.

The estimation unit 12 estimates the current consumption value or the power consumption value of each of the plurality of electric devices. FIG. 3 shows an example of a functional block diagram of the estimation unit 12. As shown in the figure, the estimation unit 12 has an estimation processing execution unit 14 and a teacher data storage unit 15.

The teacher data storage unit 15 is a teacher that associates the current consumption value or the power consumption value with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each electrical device to be monitored. Have multiple data.

FIG. 4 schematically shows an example of teacher data stored by the teacher data storage unit 15. In the illustrated example, the electric device ID (identification), which is identification information for identifying each of the electric devices to be monitored, the power consumption, and the feature amount included in the measurement data while each electric device is operating at each power consumption. And the first flag information are associated with each other. The power consumption may be replaced with the current consumption.

The feature quantities extracted from the measurement data vary. For example, the frequency intensity / phase (harmonic component) of the current consumption, the phase, the change in the current consumption, the average value, the peak value, the effective value, the peak factor, the waveform power factor, etc. It may be the convergence time of the current change, the energizing time, the peak position, the time difference between the peak position of the power supply voltage and the peak position of the current consumption, the power factor, and the like. The examples are not limited to the above.

The illustrated electric device ID "000001" is an inverter device, and takes a plurality of power consumption values and current consumption values during operation. Therefore, teacher data corresponding to each of a plurality of power consumption values and / or current consumption values is registered in association with the electric device. That is, in association with the electric device ID "000001", each of the plurality of power consumption values (representative values) taken by the electric device and the feature amount included in the measurement data while the electric device is operating at each power consumption value. A plurality of teacher data associated with are registered. It should be noted that the power consumption value and / or the current consumption value value (representative value) for registering the teacher data in association with each inverter device and how to determine the number are design matters and may differ for each electric device. .. In the case of the illustrated example of the electric device ID "000001", the power consumption value (representative value) is set in units of 50 W, and the teacher data corresponding to each is registered.

On the other hand, the electric device ID "000002" is not an inverter device and takes one power consumption value and one current consumption value during operation (note that "one power consumption value and current consumption value" here is pinpoint. It does not mean the value of, but is a concept that allows a deviation of less than a predetermined value.) Therefore, the teacher data corresponding to one power consumption value and / or current consumption value is registered in association with the electric device.

The inverter device (electric device including an inverter) is, for example, an air conditioner, a PC (Personal Computer), or the like. An electric device that is not an inverter device (an electric device that does not have an inverter) is, for example, lighting.

Returning to FIG. 3, the estimation processing execution unit 14 consumes the current consumption value or the consumption of each of the plurality of electric devices based on the measurement data acquired by the data acquisition unit 11 and the teacher data stored in the teacher data storage unit 15. Estimate the power value.

The estimation processing execution unit 14 may estimate the current consumption value or the power consumption value of each of the plurality of electric devices by the first estimation processing that emphasizes the estimation accuracy and the second estimation processing that emphasizes the calculation cost. it can. The estimation process execution unit 14 executes the estimation process selected by the selection unit 13 described below.

The first estimation process estimates the current consumption value or the power consumption value of each electric device based on the first teacher data group. The second estimation process estimates the current consumption value or the power consumption value of each electric device based on the second teacher data group in which the number of teacher data data is smaller than that of the first teacher data group.

That is, the number of teacher data used for the estimation process differs between the first estimation process and the second estimation process. Specifically, in the first teacher data group, the number of teacher data corresponding to each of the inverter devices (second electric devices) is larger than that in the second teacher data group.

More specifically, the first teacher data group uses N teacher data corresponding to each of the current consumption value or the power consumption value as the teacher data of the second electric device in the second electric device. Including. On the other hand, the second teacher data group includes M teacher data corresponding to each of the current consumption value or the power consumption value as the teacher data of the electric device of the second 2-1. Then, the relationship of N> M is satisfied. As a result, the relationship of (the number of teacher data of the first teacher data group)> (the number of teacher data of the second teacher data group) is established.

For example, in the first estimation process, the estimation process execution unit 14 uses all of the teacher data stored in the teacher data storage unit 15 (example: all of the teacher data shown in FIG. 4) to perform the estimation process. Do. On the other hand, in the second estimation process, the estimation process execution unit 14 uses only a part of the teacher data stored in the teacher data storage unit 15, for example, the teacher data with the first flag in FIG. , Perform estimation processing.

In the case of the above example, the first teacher data group includes teacher data corresponding to each of the power consumption values (500 W, 450 W, 400 W ...) for each 50 W as the teacher data of the electric device ID "000001". On the other hand, the second teacher data group includes teacher data corresponding to each of the power consumption values (500 W, 400 W ...) for each 100 W as the teacher data of the electric device ID "000001".

As another example of the second estimation process, for example, in FIG. 4, the teacher data stored in the teacher data storage unit 15 is clustered into a plurality of groups, and the teacher data compressed by averaging within the same group is used. , The estimation process may be performed.

The second estimation process may be divided into the second 1st to 2nd estimation processes in which the number of teacher data used is different from each other. In each case, the number of teacher data used is smaller than that of the first estimation process. In the first 2-1 to second 2-n estimation processes, the number of teacher data (teacher data used for estimation) corresponding to each of the inverter devices (second electric devices) is different from each other.

Hereinafter, the number of teacher data used in the second estimation process is the smallest, and the teacher data used in the second and second estimation processes, the second and third estimation processes, and the number after the hyphen increases. It is assumed that the number of data of is increased.

For example, in the teacher data group shown in FIG. 4, a flag column corresponding to each of the estimation processes 2-1 to 2-n may be provided. Then, when performing each estimation process, the estimation process execution unit 14 may perform the estimation process using only the teacher data in which the flag corresponding to each estimation process is set. As another example, for example, in the estimation processing of the 2-1st to the 2nd n, the teacher data stored in the teacher data storage unit 15 in FIG. 4 is clustered into a plurality of groups having different numbers from each other, and the same group. The estimation process may be performed using the teacher data that has been averaged and compressed in the above.

The time unit (time interval) at which the estimation is performed may be different between the first estimation process and the second estimation process. Specifically, the second estimation process uses a smaller number of teacher data than the first estimation process, and the processing time can be shortened. Therefore, the time unit of estimation of the second estimation process may be smaller than the time unit of estimation of the first estimation process. That is, the first estimation process estimates the state for each time t1 (current consumption value or power consumption value of each of the plurality of electric devices), and the second estimation process estimates the state for each time t2 (each of the plurality of electric devices). When estimating the current consumption value or the power consumption value), the relationship of t1> t2 may be satisfied. Since the first estimation process emphasizes the estimation accuracy, the time interval (hour unit) for estimation is longer than that of the second estimation process, which emphasizes the calculation cost. On the contrary, since the second estimation process emphasizes the calculation cost, the time interval (time unit) for estimation is shorter than that of the first estimation process. In this way, it is preferable to obtain the optimum estimation accuracy according to the processing content. In addition, t1 = t2 may be set.

Here, an example of the estimation process by the estimation process execution unit 14 will be described. First, the estimation processing execution unit 14 creates a plurality of total teacher data by adding the teacher data of a plurality of electric devices using the teacher data group (first teacher data group or second teacher data group) to be processed. To do.

For example, the teacher data corresponding to the electric device ID "000001", the power consumption "500W", and the feature amount "○○○" shown in FIG. 4, and the electric device ID "000002", the power consumption "125W", and the feature amount "○" By adding up the teacher data corresponding to "x" (adding the feature amounts), the electric device ID "000001" operates at the power consumption "500 W", and the electric device ID "000002" consumes the power "125 W". The total teacher data including the feature quantity included in the measurement data can be obtained when operating in.

After that, the estimation processing execution unit 14 selects the teacher data group to be processed (the first teacher data group or the second teacher data group) and a plurality of total teacher data created by using the teacher data group to be processed. An estimation model is generated by the machine learning used. The estimation model can be, for example, a multiple regression analysis, a neural network, a hidden Markov model, or the like.

Then, the estimation processing execution unit 14 inputs the feature amount extracted from the measurement data acquired by the data acquisition unit 11 into the generated estimation model, thereby inputting the estimation result (current consumption value or power consumption of each of the plurality of electric devices). Value) can be obtained.

The estimation processing execution unit 14 may correct the estimation result (current consumption value or power consumption value of each of the plurality of electric devices) obtained as described above. For example, the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the plurality of electric devices to be monitored is the ratio of the current consumption value or the power consumption value of each of the plurality of electric devices obtained as the above estimation result. The corrected current consumption value or power consumption value of each of the plurality of electric devices may be obtained by proportionally dividing by.

Returning to FIG. 2, the selection unit 13 selects one from a plurality of estimation processes including the first estimation process and the second estimation process. When the second estimation process is divided into the 2-1 to 2-n estimation processes, the selection unit 13 performs the first estimation process and the 2-1 to 2-n estimation processes. Select one from the list.

In this embodiment, the selection algorithm by the selection unit 13 is not limited. An example of the selection algorithm by the selection unit 13 will be described in the following embodiment.

Next, an example of the processing flow of the estimation device 10 of the present embodiment will be described with reference to the flowchart of FIG.

First, the data acquisition unit 11 acquires measurement data (processing target) of current consumption or power consumption of the entire plurality of electrical devices to be monitored (S10).

After that, the selection unit 13 selects one from a plurality of estimation processes including the first estimation process and the second estimation process (S11).

Then, the estimation unit 12 processes the measurement data acquired in S10 by the estimation process selected by the selection unit 13 in S11, and estimates the current consumption value or the power consumption value of each of the plurality of electric devices (S12).

As described above, the estimation device 10 of the present embodiment executes an estimation process (first estimation process) that emphasizes estimation accuracy and an estimation process (second estimation process) that emphasizes calculation cost. Can be done.

According to the estimation device 10 of the present embodiment, the first estimation process is executed when the estimation accuracy is important, and the second estimation process is executed when the calculation cost is important. A plurality of estimation processes can be used properly according to the above. Therefore, a good balance between the estimation accuracy and the calculation cost can be maintained as compared with the configuration in which the estimation processing always emphasizes the estimation accuracy and the configuration in which the estimation processing always emphasizes the calculation cost. As a result, good estimation accuracy can be achieved while reducing the calculation cost.

Further, by appropriately designing the selection algorithm of the selection unit 13, the first estimation process and the second estimation process can be appropriately selected according to the situation. As a result, good estimation accuracy can be achieved while reducing the calculation cost.

<Second embodiment>
The present embodiment is different from the first embodiment in that the first estimation process or the second estimation process is selected based on the current consumption value or the power consumption value of the entire plurality of electric devices. Other configurations are the same as in the first embodiment.

An example of the functional block diagram of the estimation device 10 of the present embodiment is shown in FIG. 2 as in the first embodiment.

The data acquisition unit 11 acquires the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of electrical devices to be monitored. For example, the data acquisition unit 11 may acquire the instantaneous value from the measurement sensor.

In the selection unit 13, the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of monitored electric devices acquired by the data acquisition unit 11 exceeds a predetermined first threshold value (design matter). If so, select a second estimation process. Then, when the current consumption value (instantaneous value) or the power consumption value (instantaneous value) is lower than the first threshold value, the selection unit 13 selects the first estimation process.

The current consumption value (instantaneous value) or power consumption value (instantaneous value) of the entire plurality of monitored electric devices to be compared with the first threshold value may be the measured value itself or for a predetermined time (eg, for a predetermined time). It may be a statistical value (eg, average value, maximum value, minimum value, mode value, intermediate value, etc.) of measured values of 1 minute, 5 minutes, and 15 minutes.

When the second estimation process is divided into the second to second to second estimation processes, the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of electrical devices to be monitored When exceeds the first threshold value (design matter), the selection unit 13 selects one of the 2-1 estimation process and the 2-n estimation process. The selection unit 13 performs the second estimation process from the second estimation process to the second estimation process as the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of monitored electric devices increases. It is configured to select in this order.

For example, when the current consumption value (instantaneous value) or power consumption value (instantaneous value) of a plurality of electrical devices to be monitored is equal to or greater than the first threshold value (design matter) and less than the first threshold value (design matter). , Select the second estimation process, and if it is equal to or greater than the first threshold (design matter) and less than the first threshold (design matter), select the second estimation process. It is in good condition.

When the current consumption value (instantaneous value) or power consumption value (instantaneous value) of the entire plurality of monitored electric devices is relatively large (when the first threshold value is exceeded), many electric devices may be in operation. There is sex. In this case, as the total teacher data described in the first embodiment, not only the total teacher data obtained by adding the teacher data of a small number of electric devices but also the total teacher data obtained by adding the teacher data of a large number of electric devices is created. There is a need. As a result, the number of total teacher data tends to increase, and the estimated calculation cost increases.

Therefore, in the present embodiment, in such a case, the second estimation process that emphasizes the calculation cost is selected.

On the other hand, when the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of monitored electric devices is relatively small (below the first threshold value), many electric devices are in operation. There is no such thing, and a limited number of electrical devices are in operation. In this case, as the total teacher data described in the first embodiment, only the total teacher data obtained by adding the teacher data of a small number of electric devices needs to be created, and the total teacher data obtained by adding the teacher data of a large number of electric devices is used. No need to create. As a result, the number of total teacher data tends to decrease, and the estimated calculation cost decreases.

Therefore, in the present embodiment, in such a case, the first estimation process that emphasizes the estimation accuracy is selected.

The estimation processing execution unit 14 of the estimation unit 12 has an upper limit of the number of units corresponding to the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the plurality of electric devices to be monitored, and the teacher data of the plurality of electric devices. May be created by adding up the total teacher data.

For example, when the number of units corresponding to the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of a plurality of electric devices to be monitored is "3", the estimation processing execution unit 14 has two electric devices. The total teacher data which is the sum of the teacher data of the above and the total teacher data which is the sum of the teacher data of three electric devices is created, and the total teacher data which is the sum of the teacher data of four or more electric devices is not created.

The estimation processing execution unit 14 may hold in advance corresponding information in which the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of electrical devices to be monitored is associated with the above number. Good. Then, based on the corresponding information and the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of monitored electric devices acquired by the data acquisition unit 11, the total number of teacher data data is calculated. It may be specified.

Other configurations of the estimation unit 12 are the same as those of the first embodiment.

Next, an example of the processing flow of the estimation device 10 of the present embodiment will be described with reference to the flowchart of FIG.

First, the data acquisition unit 11 acquires measurement data (processing target) of current consumption or power consumption of the entire plurality of electrical devices to be monitored (S30). In addition, the data acquisition unit 11 acquires the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of electrical devices to be monitored (S31).

After that, the selection unit 13 compares the magnitude of the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of electrical devices to be monitored with the first threshold value.

When the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the plurality of electric devices to be monitored exceeds the first threshold value (Yes in S32), the selection unit 13 selects the second estimation process. (S34). On the other hand, when the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of electrical devices to be monitored is lower than the first threshold value (No in S32), the selection unit 13 performs the first estimation process. Select (S34).

Then, the estimation unit 12 processes the measurement data acquired in S30 by the estimation process selected by the selection unit 13 in S33 or S34, and estimates the current consumption value or the power consumption value of each of the plurality of electric devices (S35). ).

According to the present embodiment, the same effects as those of the first embodiment can be realized.

Further, according to the present embodiment, the estimation process can be selected based on the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of electrical devices to be monitored.

When the current consumption value (instantaneous value) or power consumption value (instantaneous value) of the entire plurality of monitored electric devices is relatively large (when the first threshold value is exceeded), many electric devices may be in operation. There is sex. In this case, as the total teacher data described in the first embodiment, not only the total teacher data obtained by adding the teacher data of a small number of electric devices but also the total teacher data obtained by adding the teacher data of a large number of electric devices is created. There is a need. As a result, the number of total teacher data tends to increase, and the estimated calculation cost increases.

Therefore, in this embodiment, in such a case, the second estimation process that emphasizes the calculation cost is selected instead of the first estimation process that emphasizes the estimation accuracy. Therefore, the calculation cost becomes too high, and inconveniences such as spending a large amount of time on the calculation can be reduced.

On the other hand, when the current consumption value (instantaneous value) or the power consumption value (instantaneous value) of the entire plurality of monitored electric devices is relatively small (below the first threshold value), many electric devices are in operation. There is no such thing, and a limited number of electrical devices are in operation. In this case, as the total teacher data described in the first embodiment, only the total teacher data obtained by adding the teacher data of a small number of electric devices needs to be created, and the total teacher data obtained by adding the teacher data of a large number of electric devices is used. No need to create. As a result, the number of total teacher data tends to decrease, and the estimated calculation cost decreases.

Therefore, in the present embodiment, in such a case, the first estimation process that emphasizes the estimation accuracy is selected instead of the second estimation process that emphasizes the calculation cost. Therefore, an estimation result with good accuracy can be obtained without increasing the calculation cost.

As described above, according to the present embodiment, since it is possible to execute an appropriate estimation process according to the situation, the configuration is such that the estimation process always emphasizes the estimation accuracy or the estimation process always emphasizes the calculation cost. In comparison, a good balance between estimation accuracy and calculation cost can be maintained. As a result, good estimation accuracy can be achieved while reducing the calculation cost.

<Third embodiment>
In the present embodiment, the number of operating electric devices is estimated before estimating the current consumption value or the power consumption value of each of the plurality of electric devices, and the first estimation process or the second estimation is performed based on the estimated number of electric devices. It differs from the first embodiment in that the process is selected. Other configurations are the same as in the first embodiment.

FIG. 7 shows an example of a functional block diagram of the estimation device 10 of the present embodiment. As shown in the figure, the estimation device 10 includes a data acquisition unit 11, an estimation unit 12, a selection unit 13, and a first preprocessing unit 16. The configuration of the data acquisition unit 11 is the same as that of the first embodiment.

The first preprocessing unit 16 estimates the number of operating electric devices based on the measurement data acquired by the data acquisition unit 11.

For example, the first preprocessing unit 16 performs the above estimation by using the teacher data in which each of the monitored electric devices and the feature amount included in the measurement data while each electric device is in operation are associated with each other. May be good.

The teacher data used in the estimation of the estimation unit 12 described in the first embodiment is the current consumption value or the power consumption value and the measurement data during operation at the current consumption value or the power consumption value for each electric device. It is associated with the feature amount included in. Therefore, when the electric device is an inverter device, the number of operating states (power consumption value or current consumption value) of the teacher data corresponding to the electric device becomes a plurality of states (number of states).

On the other hand, the teacher data used in the estimation of the first preprocessing unit 16 includes the binary value (state) of whether each electric device is operating or not, and the feature amount included in the measurement data in each state. Is associated with. Therefore, regardless of whether the electric device is an inverter device or not, the number of states of the teacher data corresponding to one electric device may be one (state: operating).

As described above, in the estimation performed by the first preprocessing unit 16, since the number of states of the teacher data to be used may be one, the accuracy may be coarsened and the number of data of the teacher data can be reduced. Therefore, the calculation cost can be reduced in the estimation performed by the first preprocessing unit 16 as compared with the estimation performed by the estimation unit 12.

Hereinafter, the teacher data used in the estimation performed by the first preprocessing unit 16 is referred to as "preprocessing teacher data". Further, the teacher data obtained by adding up a plurality of preprocessing teacher data is referred to as "preprocessing combined teacher data".

Here, an example of estimation processing by the first preprocessing unit 16 will be described. First, the first preprocessing unit 16 creates a plurality of preprocessing total teacher data by adding up the preprocessing teacher data of a plurality of electric devices.

For example, by adding the feature amount of the preprocessing teacher data of the electric device ID "000001" and the feature amount of the preprocessing teacher data of the electric device ID "000002", the electric device ID "000001" and the electric device It is possible to create preprocessing total teacher data including the feature amount included in the measurement data while the ID "000002" is in operation.

After that, the first preprocessing unit 16 generates an estimation model by machine learning using the preprocessing teacher data and the preprocessing total teacher data. The estimation model can be, for example, a multiple regression analysis, a neural network, a hidden Markov model, or the like.

Then, the first preprocessing unit 16 obtains an estimation result (operating electric device ID) by inputting the feature amount extracted from the measurement data acquired by the data acquisition unit 11 into the generated estimation model. Can be done. After that, by counting the number of electric devices estimated to be in operation, the number of electric devices in operation can be estimated.

When the number of units estimated by the first preprocessing unit 16 exceeds a predetermined second threshold value, the selection unit 13 selects the second estimation process. Then, when the number of units estimated by the first preprocessing unit 16 is lower than the second threshold value, the selection unit 13 selects the first estimation process.

When the second estimation process is divided into the 2-1 to 2-n estimation processes, the number of units estimated by the first pre-processing unit 16 in the selection unit 13 sets a predetermined second threshold value. If it exceeds, one of the second estimation process and the second estimation process is selected from the second estimation process. The selection unit 13 is configured to select the second estimation process from the second estimation process in this order as the number of units estimated by the first preprocessing unit 16 increases.

For example, when the number of units estimated by the first preprocessing unit 16 is equal to or greater than the second threshold value (design matter) and less than the second threshold value (design matter), the second estimation process is selected and the second estimation process is selected. When the threshold value (design matter) of 2 ′ or more and less than the threshold value (design matter) of the second ″, the estimation process of the second 2-2 is selected, and so on.

When the number of operating electric devices is relatively large (when the number exceeds the second threshold value), a small number of total teacher data (used in the processing of the estimation unit 12) described in the first embodiment. It is necessary to create not only the total teacher data obtained by adding the teacher data of the electric equipment but also the total teacher data obtained by adding the teacher data of many electric equipment. As a result, the number of total teacher data tends to increase, and the estimated calculation cost increases.

Therefore, in the present embodiment, in such a case, the second estimation process that emphasizes the calculation cost is selected.

On the other hand, when the number of operating electric devices is relatively small (below the second threshold value), the combination of the total teacher data (used in the processing of the estimation unit 12) described in the first embodiment. Since the number is relatively small, it is possible to use the teacher data that can finely estimate the operating state (power consumption or current consumption) of each device as the teacher data of each device for generating the total teacher data (for example, estimation). If the desired operating state is power consumption, the teacher data of each electric device with finer resolution of power consumption can be used). As a result, the resolution of the total teacher data can be made finer, and the estimation accuracy can be improved.

Therefore, in the present embodiment, in such a case, the first estimation process that emphasizes the estimation accuracy is selected.

The estimation processing execution unit 14 of the estimation unit 12 may create total teacher data by adding up the teacher data of the number of electric devices corresponding to the number of devices estimated by the first preprocessing unit 16. The number corresponding to the number of devices estimated by the first preprocessing unit 16 is the number (value) itself estimated by the first preprocessing unit 16. In consideration of the estimation error of the first preprocessing unit 16, the number obtained by adding a predetermined value (design matter) to the number (value) estimated by the first preprocessing unit 16 and / or the number subtracted. Further, the number may be set according to the number of devices estimated by the first preprocessing unit 16. The predetermined value may be plural.

For example, when the number of units estimated by the first preprocessing unit 16 is "7", the estimation processing execution unit 14 creates total teacher data by adding the teacher data of the seven electric devices. In addition, in consideration of the estimation error of the first preprocessing unit 16, "1" may be added to the estimated value to create total teacher data by adding the teacher data of eight electric devices. Further, the total teacher data may be created by subtracting "1" from the estimated value and adding up the teacher data of the six electric devices. Further, the total teacher data may be created by adding the teacher data of the electric equipment for the number obtained by adding "2" to the estimated value and / or the number obtained by subtracting the number. Then, the estimation processing execution unit 14 does not create the total teacher data which is the sum of the teacher data of the other electric devices.

Other configurations of the estimation unit 12 are the same as those of the first embodiment.

Next, an example of the processing flow of the estimation device 10 of the present embodiment will be described with reference to the flowchart of FIG.

First, the data acquisition unit 11 acquires measurement data (processing target) of current consumption or power consumption of the entire plurality of electrical devices to be monitored (S20).

After that, the first preprocessing unit 16 estimates the number of operating electric devices based on the measurement data acquired in S20 (S21).

Then, the selection unit 13 compares the number of units estimated in S21 with the second threshold value.

When the number of units estimated in S21 exceeds the second threshold value (Yes in S22), the selection unit 13 selects the second estimation process (S24). On the other hand, when the number of units estimated in S21 is lower than the second threshold value (No in S22), the selection unit 13 selects the first estimation process (S24).

Then, the estimation unit 12 processes the measurement data acquired in S20 by the estimation process selected by the selection unit 13 in S23 or S24, and estimates the current consumption value or the power consumption value of each of the plurality of electric devices (S25). ).

According to the present embodiment, the same effects as those of the first embodiment can be realized.

Further, according to the present embodiment, before estimating the current consumption value or the power consumption value of each of the plurality of electric devices, the number of operating electric devices is estimated, and the estimation process is selected based on the estimated number of electric devices. be able to.

When the number of operating electric devices is relatively large (when the number exceeds the second threshold value), a small number of total teacher data (used in the processing of the estimation unit 12) described in the first embodiment. It is necessary to create not only the total teacher data obtained by adding the teacher data of the electric equipment but also the total teacher data obtained by adding the teacher data of many electric equipment. As a result, the number of total teacher data tends to increase, and the estimated calculation cost increases.

Therefore, in this embodiment, in such a case, the second estimation process that emphasizes the calculation cost is selected instead of the first estimation process that emphasizes the estimation accuracy. Therefore, the calculation cost becomes too high, and inconveniences such as spending a large amount of time on the calculation can be reduced.

On the other hand, when the number of operating electric devices is relatively small (below the second threshold value), the total teacher data (used in the processing of the estimation unit 12) described in the first embodiment is used. It is only necessary to create the total teacher data by adding the teacher data of a small number of electric devices, and it is not necessary to create the total teacher data by adding the teacher data of a large number of electric devices. As a result, the number of total teacher data tends to decrease, and the estimated calculation cost decreases.

Therefore, in the present embodiment, in such a case, the first estimation process that emphasizes the estimation accuracy is selected instead of the second estimation process that emphasizes the calculation cost. Therefore, an estimation result with good accuracy can be obtained without increasing the calculation cost.

As described above, according to the present embodiment, since it is possible to execute an appropriate estimation process according to the situation, the configuration is such that the estimation process always emphasizes the estimation accuracy or the estimation process always emphasizes the calculation cost. In comparison, a good balance between estimation accuracy and calculation cost can be maintained. As a result, good estimation accuracy can be achieved while reducing the calculation cost.

<Fourth Embodiment>
The present embodiment differs from the first embodiment in that it accepts a user input for selecting an estimation process and selects a first estimation process or a second estimation process according to the user input. Other configurations are the same as in the first embodiment.

FIG. 9 shows an example of a functional block diagram of the estimation device 10 of the present embodiment. As shown in the figure, the estimation device 10 includes a data acquisition unit 11, an estimation unit 12, a selection unit 13, and an input reception unit 17. The configuration of the data acquisition unit 11 and the estimation unit 12 is the same as that of the first embodiment.

The input receiving unit 17 accepts user input for selecting the estimation process. The user selects the first estimation process or the second estimation process. When the second estimation process is divided into the 2-1 to 2-n estimation processes, the user can select from the first estimation process and the 2-1 to 2-n estimation processes. Select one.

The selection unit 13 selects one of the estimation processes according to the user input received by the input reception unit 17. Specifically, the selection unit 13 selects the estimation process selected by the user.

According to the present embodiment described above, the same effects as those of the first embodiment can be realized.

Further, according to the present embodiment, the user can select the estimation process. Therefore, the current consumption value or the power consumption value of each of the plurality of electric devices can be estimated by the estimation process that the user truly desires.

<Fifth Embodiment>
In the present embodiment, it is estimated whether or not each electric device is in operation before estimating the current consumption value or the power consumption value of each of the plurality of electric devices. Then, the current consumption value or the power consumption value of an electric device that is not an inverter device, that is, an electric device that takes one power consumption value and a current consumption value during operation is determined based on the above estimation result.

That is, when it is estimated that the product is not in operation, the power consumption value is 0W or the current consumption value is 0A. On the other hand, when it is estimated that the electric device is in operation, one value taken by the electric device is determined as the current power consumption value or the estimated value of the current consumption value.

After that, the power consumption value or the current consumption value of each inverter device is estimated based on the teacher data group excluding the teacher data of the electric device estimated to be stopped.

FIG. 10 shows an example of a functional block diagram of the estimation device 10 of the present embodiment. As shown in the figure, the estimation device 10 includes a data acquisition unit 11, an estimation unit 12, a selection unit 13, and a second preprocessing unit 18. The configuration of the data acquisition unit 11 is the same as that of the first embodiment.

The second preprocessing unit 18 estimates whether each of the plurality of electric devices is operating or stopped based on the measurement data acquired by the data acquisition unit 11. The second preprocessing unit 18 estimates whether each of the plurality of electric devices is operating or stopped by the same estimation processing as the estimation processing by the first preprocessing unit 16 described in the third embodiment. Can be done.

The estimation unit 12 determines the current consumption value and the power consumption value of each of the first electric devices (electric devices other than the inverter device) that take one current consumption value and the power consumption value during operation of the second preprocessing unit 18. Determined based on the estimation results.

For example, the estimation unit 12 is for identifying either the first electric device (electric device other than the inverter device) or the second electric device (inverter device) for each of the monitored electric devices as shown in FIG. Information is retained in advance. In the illustrated information, the electric device ID, which is identification information for identifying each of the electric devices to be monitored, the second flag, and the power consumption are associated with each other. And only the second electric device has the second flag. Further, only one power consumption value taken during operation of each electric device is registered only in the first electric device.

Using such information, the estimation unit 12 can identify whether each of the monitored electric devices corresponds to the first electric device or the second electric device. Then, in the first electric device, the estimated value of the power consumption value or the current consumption value is determined based on the estimation result by the second preprocessing unit 18.

For example, the estimation unit 12 determines 0W or 0A as an estimated value of the power consumption value or the current consumption value of the first electric device estimated to be stopped. Then, the estimation unit 12 sets a value associated with each of the first electric devices in the information shown in FIG. 11 as an estimated value of the power consumption value or the current consumption value of the first electric device estimated to be in operation. To determine.

In addition, the estimation unit 12 determines the current consumption value and the power consumption value of each of the second electric devices (inverter devices) that take a plurality of current consumption values and power consumption values during operation, and is estimated to be stopped. The first estimation process based on the first teacher data group that does not include the teacher data of the first electric device (including the first electric device and the second electric device), or the electric device estimated to be stopped (first electricity). It is estimated by a second estimation process based on a second teacher data group that does not include the teacher data of the device (including the device and the second electrical device). In other words, an estimate based on a first teacher data group or a second teacher data group containing only the teacher data of the electrical equipment estimated to be in operation (including the first electrical equipment and the second electrical equipment). Execute the process.

The estimation unit 12 is a power consumption value of not only the first electric device but also a part of the second electric device, that is, the second electric device estimated to be stopped by the second preprocessing unit 18. Alternatively, the current consumption value may also be determined based on the estimation result of the second pretreatment unit 18. Specifically, even if the estimation unit 12 determines 0W or 0A as the estimated value of the power consumption value or the current consumption value of the second electric device estimated to be stopped by the second preprocessing unit 18. Good. Then, the estimation unit 12 estimates the power consumption value or the current consumption value of the electric device estimated to be in operation by the second preprocessing unit 18 by the first estimation process or the second estimation process. You may.

The estimation unit 12 may correct the estimation result (current consumption value or power consumption value of each of the plurality of electric devices) by the same method as the method described in the first embodiment. Further, the estimation unit 12 calculates the power value obtained by subtracting the estimated power of the non-inverter device from the power consumption value of the entire plurality of electric air devices to be monitored, and obtains the power consumption of each of the plurality of inverter devices obtained as the estimation result. By apportioning by the value, the corrected power consumption value of each of the plurality of inverter devices may be obtained.

The estimation unit 12 may create only the total teacher data obtained by adding the teacher data of all the electric devices estimated to be in operation. That is, it is not necessary to create the total teacher data by adding the teacher data of some of the electric devices estimated to be in operation. In this way, the number of total teacher data can be reduced, which is preferable.

Other configurations of the estimation unit 12 are the same as those of the first embodiment.

The selection unit 13 may select the first estimation process or the second estimation process in the processes described in the second to fourth embodiments.

In addition, the selection unit 13 may select the estimation process based on the number of the second electric devices estimated to be in operation by the second preprocessing unit 18. For example, when the number of the second electric devices estimated to be in operation by the second preprocessing unit 18 exceeds a predetermined third threshold value (design matter), the selection unit 13 performs the second estimation process. When the number of the second electric devices estimated to be in operation by the second preprocessing unit 18 is less than the third threshold value, the first estimation process is selected.

When the second estimation process is divided into the second 1st to 2nd-n estimation processes, the selection unit 13 is the second electrical device estimated to be in operation by the second preprocessing unit 18. When the number of units exceeds a predetermined third threshold value, one of the second estimation process and the second 2-n estimation process is selected. The selection unit 13 selects the 2-n estimation process from the 2-1 estimation process in this order as the number of the second electric devices estimated to be in operation by the second preprocessing unit 18 increases. It is configured to do.

For example, when the number of the second electric devices estimated to be in operation by the second preprocessing unit 18 is equal to or more than the third threshold value (design matter) and less than the third threshold value (design matter), the second The estimation process of -1 is selected, and if it is equal to or more than the third threshold (design matter) and less than the threshold of the third'(design matter), the estimation process of 2-2 is selected, and so on. ..

Next, an example of the processing flow of the estimation device 10 of the present embodiment will be described with reference to the flowchart of FIG.

First, the data acquisition unit 11 acquires measurement data (processing target) of the current consumption or power consumption of the entire plurality of electrical devices to be monitored (S40).

After that, the second preprocessing unit 18 estimates whether each of the plurality of electric devices is operating or stopped based on the measurement data acquired in S40 (S41).

Then, the estimation unit 12 sets the current consumption value and the power consumption value of each of the first electric devices (electric devices other than the inverter device) that take one current consumption value and the power consumption value during operation to the second preprocessing unit. It is determined based on the estimation result of 18 (S42).

Further, the estimation unit 12 is an electric device estimated to be in operation by the second preprocessing unit 18 among the second electric devices (inverter devices) that take a plurality of current consumption values and power consumption values during operation. The number of units is counted (S43).

Then, the selection unit 13 compares the number of units counted in S43 with the third threshold value.

When the number of units counted in S43 exceeds the third threshold value (Yes in S44), the selection unit 13 selects the second estimation process (S46). On the other hand, when the number of units counted in S43 is lower than the third threshold value (No in S44), the selection unit 13 selects the first estimation process (S45).

Then, the estimation unit 12 processes the measurement data acquired in S40 by the estimation process selected by the selection unit 13 in S45 or S46, and estimates the current consumption value or the power consumption value of each of the second electric devices ( S47).

According to the present embodiment described above, the same effects as those of the first to fourth embodiments can be realized.

Further, in the case of the present embodiment, the estimated value of the current consumption value or the power consumption value of some electric devices (electric devices other than the inverter device) is determined based on the estimation result by the second preprocessing unit 18 having a small calculation cost. However, only the current consumption value or the power consumption value of some other electric devices (inverter devices) can be obtained by the estimation process by the estimation unit 12.

In the estimation process by the estimation unit 12, only the teacher data of the electric device estimated to be in operation is used, and it is not necessary to use the teacher data of the electric device estimated to be stopped. Therefore, the number of teacher data to be used can be reduced. As a result, the calculation cost can be reduced.

<Sixth Embodiment>
In the present embodiment, time-series measurement data is processed in chronological order, and the current consumption value or power consumption value of each of the plurality of electric devices is estimated in chronological order. Then, based on the measurement data of the timing of the processing target and the teacher data of each of the plurality of electric devices, before estimating the current consumption value or the power consumption value of each of the plurality of electric devices at the timing of the processing target, the processing target Judge the degree of similarity between the timing measurement data and the timing measurement data earlier than that. Then, when they are similar by a predetermined level or more, the estimation result of the timing before that is adopted as the estimation result of the timing of the processing target (current consumption value or power consumption value of each of the plurality of electric devices).

An example of the functional block diagram of the estimation device 10 of the present embodiment is shown in FIGS. 2, 7, 9 or 10 as in the first to fifth embodiments. The configuration of the first preprocessing unit 16, the input receiving unit 17, and the second preprocessing unit 18 is the same as that of the first to fifth embodiments.

The data acquisition unit 11 acquires time-series measurement data and processes it in chronological order. Other configurations of the data acquisition unit 11 are the same as those of the first to fifth embodiments.

The estimation unit 12 processes the time-series measurement data in chronological order, and estimates the time-series current consumption value or power consumption value of each of the plurality of electric devices. The estimation unit 12 can execute a third estimation process in addition to the first estimation process and the second estimation process.

In the third estimation process, the estimation unit 12 determines the estimation result of the current consumption value or the power consumption value of each of the plurality of electric devices at the timing before the timing of the processing target (first timing) at the timing of the processing target. It is adopted as the estimation result of (first timing). In the third estimation process, the estimation process using the teacher data is not executed.

The selection unit 13 makes a third estimation when the difference between the measurement data at the timing to be processed and the measurement data at the timing before that (eg, the data immediately before in time) is less than a predetermined threshold value. Select a process.

When the difference exceeds a predetermined threshold value, the selection unit 13 selects the first estimation process or the second estimation process. For example, the selection unit 13 may select the first estimation process or the second estimation process in the processes described in the second to fifth embodiments.

The difference between the measurement data at the timing of the processing target and the measurement data at the timing before that (eg, the data one before in time) is the measurement data (instantaneous waveform data. Waveform data according to the AC frequency. ), Or the difference of a predetermined feature amount extracted from the measurement data. The difference referred to here may be the distance between the feature amount vectors of the waveforms, or the sum of the absolute values of the differences between the feature amounts.

According to the present embodiment described above, the same effects as those of the first to fifth embodiments can be realized.

Further, in the case of the present embodiment, when the measurement data at the timing of the processing target and the measurement data at the timing before that (eg, the data immediately before in time) are similar to each other by a predetermined level or more, the processing target The estimation result of the current consumption value or the power consumption value of each of the plurality of electric devices at the timing before the timing (first timing) can be adopted as the estimation result of the timing (first timing) to be processed. ..

Therefore, instead of performing estimation processing based on the teacher data for all of the plurality of measurement data (instantaneous waveform data. Waveform data according to the AC frequency) arranged in chronological order, the estimation processing for some measurement data is omitted. it can. As a result, the calculation cost can be reduced.

<7th Embodiment>
In the present embodiment, the reliability of the result of estimating whether or not each electric device is in operation is calculated before estimating the current consumption value or the power consumption value of each of the plurality of electric devices. Then, when the reliability exceeds a predetermined level, a process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices is executed, and when the reliability is lower than the predetermined level, the current consumption value of each of the plurality of electric devices is executed. Alternatively, a warning is output without executing the process of estimating the power consumption value.

If the reliability of the estimation result of whether or not the electric device is in operation is lower than a predetermined level, there is a possibility that some of the electric devices in operation have no teacher data registered. Under such circumstances, even if the current consumption value or the power consumption value of each of the plurality of electric devices is estimated, a result with sufficient accuracy cannot be obtained.

Therefore, in the present embodiment, when the reliability exceeds the predetermined level, the process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices is executed, but when the reliability is lower than the predetermined level, the process is executed. , Does not execute the process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices, and outputs a warning.

FIG. 13 shows an example of a functional block diagram of the estimation device 10 of the present embodiment. As shown in the figure, the estimation device 10 includes a data acquisition unit 11, an estimation unit 12, a selection unit 13, and a third preprocessing unit 19. Although not shown, the estimation device 10 may further include any one of the first preprocessing unit 16, the input receiving unit 17, and the second preprocessing unit 18. The configurations of the data acquisition unit 11, the selection unit 13, the first preprocessing unit 16, the input receiving unit 17, and the second preprocessing unit 18 are the same as those in the first to sixth embodiments.

The third preprocessing unit 19 calculates the reliability of the result of estimating whether each of the plurality of electric devices is operating or stopped. The estimation of whether each of the plurality of electric devices is operating or stopped can be realized by the same estimation processing as the estimation processing by the first preprocessing unit 16 described in the third embodiment. The method for calculating the reliability of the estimated result is not particularly limited, and any conventional method can be adopted.

When the reliability calculated by the third preprocessing unit 19 exceeds a predetermined level (when the reliability exceeds a predetermined level), the estimation unit 12 performs a process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices. Run. The estimation unit 12 estimates the current consumption value or the power consumption value of each of the plurality of electric devices by the method described in the first to sixth embodiments. For example, the estimation unit 12 executes the estimation process selected by the selection unit 13.

On the other hand, when the reliability calculated by the third preprocessing unit 19 is lower than the predetermined level (when the reliability is not higher than the predetermined level), the estimation unit 12 estimates the current consumption value or the power consumption value of each of the plurality of electric devices. Outputs a warning without executing any processing. The means of warning are various and can be realized through any output device such as a display, a speaker, a warning lamp and the like. Further, the warning output does not have to be in real time, and the period when the reliability falls below a predetermined level after the fact may be collectively output as a report.

The estimation device 10 of the present embodiment may further have a registration unit 20 as shown in the functional block diagram of FIG.

When the reliability calculated by the third preprocessing unit 19 is lower than a predetermined level, the registration unit 20 extracts a feature amount from the measurement data acquired by the data acquisition unit 11 and uses the teacher data storage unit 15 (database) as teacher data. ).

When the reliability calculated by the third preprocessing unit 19 is lower than the predetermined level, the measurement data may include components of electrical equipment for which teacher data is not registered. By registering the feature amount extracted from such measurement data in the teacher data storage unit 15 (database), it is possible to register teacher data including components of electrical equipment in which teacher data is not registered.

The registration unit 20 may check whether the extracted teacher data (feature amount) has already been registered in the teacher data storage unit 15, and if not, register the teacher data including the extracted feature amount. .. Then, if it has already been registered, it is not necessary to newly register the teacher data including the extracted feature amount.

In this case, it is probable that the reliability calculated by the third preprocessing unit 19 was lowered not because the teacher data was registered incorrectly but because of other reasons such as a power supply voltage drop. In this case, the registration unit 20 may output a warning to that effect. The means of warning are various and can be realized through any output device such as a display, a speaker, a warning lamp and the like.

Next, an example of the processing flow of the estimation device 10 of the present embodiment will be described with reference to the flowchart of FIG.

First, the data acquisition unit 11 acquires measurement data (processing target) of current consumption or power consumption of the entire plurality of electrical devices to be monitored (S50).

After that, the third preprocessing unit 19 estimates whether each of the plurality of electric devices is operating or stopped (S51) based on the measurement data acquired in S40, and calculates the reliability of the result (S52). ).

The estimation unit 12 compares the reliability calculated in S52 with a predetermined threshold value.

When the reliability calculated in S52 exceeds a predetermined threshold value (Yes in S53), the estimation unit 12 executes a process of estimating the current consumption or power consumption of each of the plurality of electric devices (S57). That is, the processes described in the first to sixth embodiments, for example, S11 to S12 in FIG. 5, S31 to S35 in FIG. 6, S21 to S25 in FIG. 8, S42 to S47 in FIG. 12, and the like are executed. ..

On the other hand, when the reliability calculated in S52 is less than a predetermined threshold value (No in S53), the estimation unit 12 does not execute the process of estimating the current consumption or power consumption of each of the plurality of electric devices, and outputs a warning. (S54).

Then, the registration unit 20 extracts the feature amount from the measurement data acquired in S50 (S55) and registers it in the teacher data storage unit 15 (database) (S56).

According to the present embodiment described above, the same effects as those of the first to fourth embodiments can be realized.

Further, in the case of the present embodiment, before estimating the current consumption value or the power consumption value of each of the plurality of electric devices, the reliability of the result of estimating whether or not each electric device is in operation is calculated, and the reliability is determined. If it falls below a predetermined level, a warning can be output without executing the process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices.

If the reliability of the estimation result of whether or not the electric device is in operation is lower than a predetermined level, there is a possibility that some of the electric devices in operation have no teacher data registered. Under such circumstances, even if the current consumption value or the power consumption value of each of the plurality of electric devices is estimated, a result with sufficient accuracy cannot be obtained.

In the present embodiment, under the situation where such a sufficiently accurate result cannot be obtained, the process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices is not executed. Therefore, the processing load is reduced.

<8th Embodiment>
In the present embodiment, the current consumption value or the power consumption value (estimation result) of each of the plurality of electric devices estimated by the first estimation process or the second estimation process can be displayed on the display. In addition, user input for selecting the first estimation process and the second estimation process can be accepted.

Then, the estimation result displayed on the display can be switched between the estimation result by the first estimation process and the estimation result by the second estimation process according to the user input.

FIG. 16 shows an example of a functional block diagram of the estimation device 10 of the present embodiment. As shown in the figure, the estimation device 10 has an input receiving unit 17 and a display unit 21.

FIG. 17 shows another example of the functional block diagram of the estimation device 10 of the present embodiment. As shown in the figure, the estimation device 10 may further include a data acquisition unit 11, an estimation unit 12, and a selection unit 13. The configurations of the data acquisition unit 11, the estimation unit 12, and the selection unit 13 are the same as those in the first to seventh embodiments.

The input receiving unit 17 accepts user input for selecting either the first estimation process or the second estimation process.

The display unit 21 displays the estimation result based on the estimation process selected by the user input on the display. Further, when the selected estimation process is switched while the display unit 21 is displaying the estimation result on the display, the estimation result displayed on the display is changed to the estimation process after the switching. Switch to based estimation results.

18 and 19 show an example of a UI (User Interface) screen displayed by the estimation device 10 of the present embodiment.

On the UI screen, a graph showing time on the horizontal axis and power consumption and reliability on the vertical axis is displayed. In the graph, the estimation results of the time-series power consumption values of the plurality of electric devices estimated by the estimation unit 12 are displayed as a stacked graph.

In addition, the graph shows the reliability of the estimation result by the estimation unit 12. The method of calculating the reliability of the estimation result by the estimation unit 12 is not particularly limited, and any conventional method can be adopted.

Further, on the UI screen, a GUI (Graphical User Interface) component that accepts user input for selecting the first estimation process and the second estimation process is displayed. By moving the knob in the left-right direction, the first estimation process (focusing on accuracy) or the second estimation process (focusing on calculation cost) can be selected.

In FIG. 18, the second estimation process (emphasis on calculation cost) is selected. Then, the graph shows the estimation result estimated by the second estimation process. In this case, the reliability is relatively low. When the GUI component is operated in this state and switched to select the first estimation process (emphasis on accuracy), the UI screen switches to the state shown in FIG.

In FIG. 19, the first estimation process (focusing on accuracy) is selected. Then, the graph shows the estimation result estimated by the first estimation process. In this case, the reliability is relatively high. When the GUI component is operated in this state and switched to select the second estimation process (emphasis on calculation cost), the UI screen switches to the state shown in FIG.

From FIGS. 18 and 19, it can be seen that in this example, the time unit (time interval) for estimating is different between the first estimation process (focusing on accuracy) and the second estimation process (focusing on calculation cost). Specifically, while the first estimation process estimates the state about every 3 hours (see FIG. 19), the second estimation process estimates the state about every 30 minutes (Fig. 19). 18). Since the first estimation process emphasizes the estimation accuracy, the time interval (hour unit) for estimation is longer than that of the second estimation process, which emphasizes the calculation cost. On the contrary, since the second estimation process emphasizes the calculation cost, the time interval (time unit) for estimation is shorter than that of the first estimation process.

According to the present embodiment described above, the same effects as those of the first to seventh embodiments can be realized.

Further, by accepting the selection of the first estimation process and the second estimation process from the user and displaying the respective estimation results, the information truly desired by the user can be provided.

<9th embodiment>
The data acquisition unit 11 of the present embodiment acquires measurement data from each of the plurality of measurement sensors. A plurality of measurement sensors are installed, for example, at each branch of the distribution board. The teacher data storage unit 15 of the estimation unit 12 stores the teacher data of each of a plurality of electric devices connected to the wiring on the downstream side of each measurement sensor and receiving power supply. Then, the estimation processing execution unit 14 is based on the measurement data acquired by the data acquisition unit 11 for each measurement sensor and the teacher data stored by the teacher data storage unit 15 for each measurement sensor, and a plurality of electricity for each measurement sensor. Estimate the current consumption value or power consumption value of each device. The selection unit 13 selects the estimation process for each measurement sensor.

As described above, according to the present embodiment, the estimation process can be selected for each measurement sensor. That is, it is possible to realize a situation in which the second estimation process is selected corresponding to the second measurement sensor when the first estimation process is selected corresponding to the first measurement sensor.

The operating status of the electrical equipment to be monitored may differ for each measurement sensor. For example, a situation in which a large number of monitored electric devices corresponding to the first measurement sensor are in operation, while most of the monitored electric devices corresponding to the second measurement sensor are stopped and only a small number are in operation. Can occur. According to the present embodiment in which the estimation process can be selected for each measurement sensor, an appropriate estimation process according to the situation of each measurement sensor can be determined for each measurement sensor. As a result, good estimation accuracy can be achieved while reducing the calculation cost.

Hereinafter, an example of the reference form will be added.
1. 1. A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means is an estimation device that executes an estimation process selected by the selection means.
2. 2. In the estimation device according to 1.
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group is an estimation device in which the number of teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group.
3. 3. In the estimation device according to 2.
The first teacher data group includes the teacher data corresponding to each of N current consumption values or power consumption values as the teacher data of the second electric device in the second electric device.
The second teacher data group includes the teacher data corresponding to each of M current consumption values or power consumption values as the teacher data of the second electric device.
N is an estimator larger than M.
4. In the estimation device according to any one of 1 to 3,
It further has a first pretreatment means for estimating the number of the electrical devices in operation based on the measurement data.
When the number of units estimated by the first preprocessing means exceeds a predetermined threshold value, the selection means selects the second estimation process, and the number of units estimated by the first preprocessing means is the predetermined threshold value. If the value is less than, the estimation device selects the first estimation process.
5. In the estimation device according to any one of 1 to 3,
When the current consumption value or the power consumption value of the entire plurality of electric devices exceeds a predetermined threshold value, the selection means selects the second estimation process, and the current consumption value or the power consumption value is the predetermined value. An estimation device that selects the first estimation process when it falls below the threshold value.
6. In the estimation device according to any one of 1 to 3,
It also has an input receiving means that accepts user input to select estimation processing.
The selection means is an estimation device that selects one of the estimation processes according to the user input.
7. In the estimation device according to any one of 1 to 3,
Further, it has a second pretreatment means for estimating whether each of the plurality of electric devices is operating or stopped based on the measurement data.
The estimation means determines the current consumption value and the power consumption value of each of the first electric devices that take one current consumption value and the power consumption value during operation based on the estimation result of the second pretreatment means. Estimator.
8. In the estimation device according to 7.
The estimation means includes the teacher data of the electric device estimated to be stopped, with the current consumption value and the power consumption value of each of the second electric devices having a plurality of current consumption values and power consumption values during operation. Not the first estimation process estimated based on the first teacher data group, or the second estimation based on the second teacher data group that does not include the teacher data of the electrical device estimated to be stopped. Estimator that estimates by the estimation process of.
9. In the estimation device according to 7 or 8,
When the number of the second electric devices estimated to be in operation by the second pretreatment means exceeds a predetermined threshold value, the selection means selects the second estimation process and selects the second pretreatment. An estimation device that selects the first estimation process when the number of the second electrical devices estimated to be in operation by the processing means falls below a predetermined threshold value.
10. In the estimation device according to any one of 1 to 9.
The data acquisition means acquires the measurement data in time series and obtains the measurement data.
The estimation means processes the time-series measurement data to estimate the time-series current consumption value or power consumption value of each of the plurality of electric devices.
The estimation means is a third estimation process that employs the estimation result of the current consumption value or the power consumption value of each of the plurality of electric devices at the timing before the first timing as the estimation result of the first timing. Further run,
The selection means estimates that the third estimation process is selected when the difference between the measurement data at the first timing and the measurement data at a timing prior to the first timing is less than a predetermined threshold value. apparatus.
11. In the estimation device according to any one of 1 to 10.
Further, it has a third pretreatment means for calculating the reliability of the result of estimating whether each of the plurality of electric devices is operating or stopped.
When the reliability calculated by the third pretreatment means exceeds a predetermined level, the estimation means executes a process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices, and the third estimation means. An estimation device that outputs a warning without executing the process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices when the reliability calculated by the pretreatment means of the above is lower than a predetermined level.
12. In the estimation device according to 11.
An estimation device further comprising a registration means that extracts a feature amount from the measurement data and registers it in a database as teacher data when the reliability calculated by the third preprocessing means is lower than a predetermined level.
13. Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input receiving means for accepting a user input for selecting either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of
A display means for displaying the estimation result based on the estimation process selected by the user input on the display.
Have,
When the selected estimation process is switched while the display means is displaying the estimation result on the display, the estimation result to be displayed on the display is estimated after the switching. An estimation device that switches to the estimation result based on the processing.
14. The computer
A data acquisition process for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation step of executing a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection step of selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
And run
In the estimation step, an estimation method for executing the estimation process selected in the selection step.
14-2. In the estimation method described in 14.
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group is an estimation method in which the number of teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group.
14-3. In the estimation method described in 14-2,
The first teacher data group includes the teacher data corresponding to each of N current consumption values or power consumption values as the teacher data of the second electric device in the second electric device.
The second teacher data group includes the teacher data corresponding to each of M current consumption values or power consumption values as the teacher data of the second electric device.
N is an estimation method larger than M.
14-4. In the estimation method according to any one of 14 to 14-3.
The computer further executes a first pretreatment step of estimating the number of operating electrical devices based on the measurement data.
In the selection step, when the number of units estimated in the first pretreatment step exceeds a predetermined threshold value, the second estimation process is selected, and the number of units estimated in the first pretreatment step is the predetermined threshold value. If the value is less than, the estimation method selects the first estimation process.
14-5. In the estimation method according to any one of 14 to 14-3.
In the selection step, when the current consumption value or the power consumption value of the entire plurality of the electric devices exceeds a predetermined threshold value, the second estimation process is selected, and the current consumption value or the power consumption value is the predetermined value. An estimation method that selects the first estimation process when the value is below the threshold value.
14-6. In the estimation method according to any one of 14 to 14-3.
The computer further performs an input receiving process that accepts user input to select estimation processing.
In the selection step, an estimation method that selects one of the estimation processes according to the user input.
14-7. In the estimation method according to any one of 14 to 14-3.
The computer further performs a second pretreatment step of estimating whether each of the plurality of electrical devices is up or down based on the measurement data.
In the estimation step, the current consumption value and the power consumption value of each of the first electric devices that take one current consumption value and power consumption value during operation are determined based on the estimation result in the second pretreatment step. Estimating method to do.
14-8. In the estimation method described in 14-7,
In the estimation step, the current consumption value and the power consumption value of each of the second electric devices that take a plurality of current consumption values and power consumption values during operation include the teacher data of the electric device estimated to be stopped. Not the first estimation process estimated based on the first teacher data group, or the second estimation based on the second teacher data group that does not include the teacher data of the electrical device estimated to be stopped. Estimating method to estimate by the estimation process of.
14-9. In the estimation method described in 14-7 or 14-8,
In the selection step, when the number of the second electric devices estimated to be in operation by the second pretreatment step exceeds a predetermined threshold value, the second estimation process is selected and the second pretreatment process is performed. An estimation method for selecting the first estimation process when the number of the second electrical devices estimated to be in operation by the processing step falls below a predetermined threshold value.
14-10. In the estimation method according to any one of 14 to 14-9.
In the data acquisition step, the measurement data in time series is acquired, and the measurement data is acquired.
In the estimation step, the time-series measurement data is processed to estimate the time-series current consumption value or power consumption value of each of the plurality of electric devices.
In the estimation step, a third estimation process that employs the estimation result of the current consumption value or the power consumption value of each of the plurality of electric devices at the timing prior to the first timing as the estimation result of the first timing. Further run,
In the selection step, when the difference between the measurement data at the first timing and the measurement data at a timing prior to the first timing is less than a predetermined threshold value, the estimation of selecting the third estimation process. Method.
14-11. In the estimation method according to any one of 14 to 14-10.
The computer further executes a third pretreatment step of calculating the reliability of the result of estimating whether each of the plurality of electric devices is operating or stopped.
In the estimation step, when the reliability calculated in the third pretreatment step exceeds a predetermined level, a process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices is executed, and the third When the reliability calculated in the pretreatment step of the above is lower than a predetermined level, an estimation method that outputs a warning without executing the process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices.
14-12. In the estimation method described in 14-11,
An estimation method in which the computer further executes a registration step of extracting a feature amount from the measurement data and registering it in a database as teacher data when the reliability calculated in the third preprocessing step is lower than a predetermined level.
15. Computer,
Data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored,
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group.
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
To function as
The estimation means is a program that executes an estimation process selected by the selection means.
15-2. In the program described in 15.
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group is a program in which the number of teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group.
15-3. In the program described in 15-2
The first teacher data group includes the teacher data corresponding to each of N current consumption values or power consumption values as the teacher data of the second electric device in the second electric device.
The second teacher data group includes the teacher data corresponding to each of M current consumption values or power consumption values as the teacher data of the second electric device.
N is a program larger than M.
15-4. In the program described in any of 15 to 15-3,
The computer is further made to function as a first preprocessing means for estimating the number of operating electrical devices based on the measurement data.
When the number of units estimated by the first preprocessing means exceeds a predetermined threshold value, the selection means selects the second estimation process, and the number of units estimated by the first preprocessing means is the predetermined threshold value. If the value is less than, the program selects the first estimation process.
15-5. In the program described in any of 15 to 15-3,
When the current consumption value or the power consumption value of the entire plurality of electric devices exceeds a predetermined threshold value, the selection means selects the second estimation process, and the current consumption value or the power consumption value is the predetermined value. A program that selects the first estimation process when it falls below the threshold.
15-6. In the program described in any of 15 to 15-3,
The computer is further made to function as an input receiving means for receiving user input for selecting estimation processing.
The selection means is a program that selects one of the estimation processes according to the user input.
15-7. In the program described in any of 15 to 15-3,
The computer is further made to function as a second preprocessing means for estimating whether each of the plurality of electrical devices is operating or stopped based on the measurement data.
The estimation means determines the current consumption value and the power consumption value of each of the first electric devices that take one current consumption value and the power consumption value during operation based on the estimation result of the second pretreatment means. program.
15-8. In the program described in 15-7
The estimation means includes the teacher data of the electric device estimated to be stopped, with the current consumption value and the power consumption value of each of the second electric devices having a plurality of current consumption values and power consumption values during operation. Not the first estimation process estimated based on the first teacher data group, or the second estimation based on the second teacher data group that does not include the teacher data of the electrical device estimated to be stopped. A program that estimates by the estimation process of.
15-9. In the program described in 15-7 or 15-8
When the number of the second electric devices estimated to be in operation by the second pretreatment means exceeds a predetermined threshold value, the selection means selects the second estimation process and selects the second pretreatment. A program that selects the first estimation process when the number of the second electric devices estimated to be in operation by the processing means falls below a predetermined threshold value.
15-10. In the program described in any of 15 to 15-9
The data acquisition means acquires the measurement data in time series and obtains the measurement data.
The estimation means processes the time-series measurement data to estimate the time-series current consumption value or power consumption value of each of the plurality of electric devices.
The estimation means is a third estimation process that employs the estimation result of the current consumption value or the power consumption value of each of the plurality of electric devices at the timing before the first timing as the estimation result of the first timing. Further run,
The selection means is a program that selects the third estimation process when the difference between the measurement data at the first timing and the measurement data at a timing prior to the first timing is less than a predetermined threshold value. ..
15-11. In the program described in any of 15 to 15-10
The computer is further made to function as a third preprocessing means for calculating the reliability of the result of estimating whether each of the plurality of electric devices is operating or stopped.
When the reliability calculated by the third pretreatment means exceeds a predetermined level, the estimation means executes a process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices, and the third estimation means. A program that outputs a warning without executing the process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices when the reliability calculated by the pretreatment means of the above is lower than a predetermined level.
15-12. In the program described in 15-11
A program that further functions the computer as a registration means that extracts a feature amount from the measurement data and registers it in a database as teacher data when the reliability calculated by the third preprocessing means is lower than a predetermined level.
16. The computer
Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input reception process that accepts user input to select either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of
A display process for displaying the estimation result based on the estimation process selected by the user input on the display, and
And run
In the display step, when the selected estimation process is switched while the estimation result is displayed on the display, the estimation result displayed on the display is estimated after the switching. An estimation method for switching to the estimation result based on the process.
17. Computer,
Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input receiving means that accepts user input to select either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of the above.
A display means for displaying an estimation result based on the estimation process selected by the user input on a display.
To function as
When the selected estimation process is switched while the display means is displaying the estimation result on the display, the estimation result to be displayed on the display is estimated after the switching. A program that switches to the estimation result based on the processing.

This application claims priority based on Japanese application Japanese Patent Application No. 2015-191726 filed on September 29, 2015, and incorporates all of its disclosures herein.

Claims (16)

A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means executes the estimation process selected by the selection means , and
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group is an estimation device in which the number of teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group . In the estimation device according to claim 1 ,
The first teacher data group includes the teacher data corresponding to each of N current consumption values or power consumption values as the teacher data of the second electric device in the second electric device.
The second teacher data group includes the teacher data corresponding to each of M current consumption values or power consumption values as the teacher data of the second electric device.
N is an estimator larger than M. A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means executes the estimation process selected by the selection means , and
It further has a first pretreatment means for estimating the number of the electrical devices in operation based on the measurement data.
When the number of units estimated by the first preprocessing means exceeds a predetermined threshold value, the selection means selects the second estimation process, and the number of units estimated by the first preprocessing means is the predetermined threshold value. If the value is less than, the estimation device selects the first estimation process . A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means executes the estimation process selected by the selection means , and
When the current consumption value or the power consumption value of the entire plurality of electric devices exceeds a predetermined threshold value, the selection means selects the second estimation process, and the current consumption value or the power consumption value is the predetermined value. An estimation device that selects the first estimation process when it falls below the threshold value . A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means executes the estimation process selected by the selection means , and
It also has an input receiving means that accepts user input to select estimation processing.
The selection means is an estimation device that selects one of the estimation processes according to the user input . A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means executes the estimation process selected by the selection means , and
Further, it has a second pretreatment means for estimating whether each of the plurality of electric devices is operating or stopped based on the measurement data.
The estimation means determines the current consumption value and the power consumption value of each of the first electric devices that take one current consumption value and the power consumption value during operation based on the estimation result of the second pretreatment means. Estimator. In the estimation device according to claim 6 ,
The estimation means includes the teacher data of the electric device estimated to be stopped, with the current consumption value and the power consumption value of each of the second electric devices having a plurality of current consumption values and power consumption values during operation. Not the first estimation process estimated based on the first teacher data group, or the second estimation based on the second teacher data group that does not include the teacher data of the electrical device estimated to be stopped. Estimator that estimates by the estimation process of. In the estimation device according to claim 6 or 7 .
When the number of the second electric devices estimated to be in operation by the second pretreatment means exceeds a predetermined threshold value, the selection means selects the second estimation process and selects the second pretreatment. An estimation device that selects the first estimation process when the number of the second electrical devices estimated to be in operation by the processing means falls below a predetermined threshold value. A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means executes the estimation process selected by the selection means , and
The data acquisition means acquires the measurement data in time series and obtains the measurement data.
The estimation means processes the time-series measurement data to estimate the time-series current consumption value or power consumption value of each of the plurality of electric devices.
The estimation means is a third estimation process that employs the estimation result of the current consumption value or the power consumption value of each of the plurality of electric devices at the timing before the first timing as the estimation result of the first timing. Further run,
The selection means estimates that the third estimation process is selected when the difference between the measurement data at the first timing and the measurement data at a timing prior to the first timing is less than a predetermined threshold value. apparatus. A data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
Have,
The estimation means executes the estimation process selected by the selection means , and
Further, it has a third pretreatment means for calculating the reliability of the result of estimating whether each of the plurality of electric devices is operating or stopped.
When the reliability calculated by the third pretreatment means exceeds a predetermined level, the estimation means executes a process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices, and the third estimation means. An estimation device that outputs a warning without executing the process of estimating the current consumption value or the power consumption value of each of the plurality of electric devices when the reliability calculated by the pretreatment means of the above is lower than a predetermined level . In the estimation device according to claim 10 ,
An estimation device further comprising a registration means that extracts a feature amount from the measurement data and registers it in a database as teacher data when the reliability calculated by the third preprocessing means is lower than a predetermined level. Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input receiving means for accepting a user input for selecting either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of
A display means for displaying the estimation result based on the estimation process selected by the user input on the display.
Have,
When the selected estimation process is switched while the display means is displaying the estimation result on the display, the estimation result to be displayed on the display is estimated after the switching. An estimation device that switches to the estimation result based on the processing. The computer
A data acquisition process for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored, and
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation step of executing a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and
A selection step of selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
And run
In the estimation step, the estimation process selected in the selection step is executed .
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group is an estimation method in which the number of teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group . Computer,
Data acquisition means for acquiring measurement data of current consumption or power consumption of a plurality of electrical devices to be monitored,
A first teacher having a plurality of teacher data in which a current consumption value or a power consumption value is associated with a feature amount included in the measurement data during operation at the current consumption value or the power consumption value for each of the electric devices. A first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group, and a second teacher having a smaller number of teacher data than the first teacher data group. An estimation means that executes a second estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the data group.
A selection means for selecting one from a plurality of estimation processes including the first estimation process and the second estimation process.
To function as
The estimation means executes the estimation process selected by the selection means , and
Among the plurality of the electric devices, a first electric device that takes one current consumption value and a power consumption value during operation, and a second electric device that takes a plurality of current consumption values and power consumption values during operation. Includes electrical equipment,
The first teacher data group is a program in which the number of teacher data corresponding to each of the second electric devices is larger than that of the second teacher data group . The computer
Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input reception process that accepts user input to select either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of
A display process for displaying the estimation result based on the estimation process selected by the user input on the display, and
And run
In the display step, when the selected estimation process is switched while the estimation result is displayed on the display, the estimation result displayed on the display is estimated after the switching. An estimation method for switching to the estimation result based on the process. Computer,
Each of a plurality of monitored electric devices has a plurality of teacher data in which the current consumption value or the power consumption value is associated with the feature amount included in the measurement data during operation at the current consumption value or the power consumption value. The first estimation process for estimating the current consumption value or the power consumption value of each of the plurality of electric devices based on the one teacher data group, and the second estimation process in which the number of the teacher data is smaller than that of the first teacher data group. An input receiving means that accepts user input to select either the current consumption value or the second estimation process for estimating the power consumption value of each of the plurality of electric devices based on the teacher data group of the above.
A display means for displaying an estimation result based on the estimation process selected by the user input on a display.
To function as
When the selected estimation process is switched while the display means is displaying the estimation result on the display, the estimation result to be displayed on the display is estimated after the switching. A program that switches to the estimation result based on the processing.

Images