WO2015151558A1 - 監視装置、監視システム、監視方法及びプログラム - Google Patents
監視装置、監視システム、監視方法及びプログラム Download PDFInfo
- Publication number
- WO2015151558A1 WO2015151558A1 PCT/JP2015/051788 JP2015051788W WO2015151558A1 WO 2015151558 A1 WO2015151558 A1 WO 2015151558A1 JP 2015051788 W JP2015051788 W JP 2015051788W WO 2015151558 A1 WO2015151558 A1 WO 2015151558A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- waveform data
- monitoring
- unit
- teacher
- difference
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R21/00—Arrangements for measuring electric power or power factor
- G01R21/133—Arrangements for measuring electric power or power factor by using digital technique
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R21/00—Arrangements for measuring electric power or power factor
- G01R21/06—Arrangements for measuring electric power or power factor by measuring current and voltage
Definitions
- the present invention relates to a monitoring device, a monitoring system, a monitoring method, and a program.
- each electrical device can be ascertained, for example, by attaching a measuring instrument to each electrical device.
- a measuring instrument to each electric device.
- the work burden of attaching a measuring instrument to each electric device is large.
- the number of measuring instruments also increases, increasing the cost burden.
- a measuring instrument is installed in a power supply trunk such as a power supply inlet and a distribution board, and the measurement data (total current consumption waveform, etc.) measured by the measuring instrument is used.
- a technique for estimating the operating state is disclosed.
- a feature amount (teacher feature amount) at the time of operation of each electric device is prepared in advance, and a combined teacher feature amount obtained by combining the teacher feature amounts in all aspects is prepared.
- the operating state of each electrical device is estimated based on the feature amount extracted from the measurement data measured by the power supply trunk and the teacher feature amount (including the combined teacher feature amount) prepared in advance.
- Patent Document 3 discloses a technique for generating a teacher feature value indicating a feature value during operation of each electrical device. Specifically, the electrical equipment in the house to be measured is operated one by one, and predetermined data (current consumption, etc.) is individually measured. And the feature-value is extracted from the measured data of each electric equipment, and the extracted feature-value is preserve
- Patent Document 4 discloses a power consumption measurement system including data extraction means and estimation means.
- the data extraction means extracts current waveform data averaged over one cycle of the commercial frequency of the total load current based on the total load current and voltage measured at a predetermined location on the service area, and the averaged current waveform From the data, the convex point information relating to the convex point indicating the point at which the change in the current value changes from increase to decrease, or the point at which the change from decrease to increase is extracted.
- the estimation means holds in advance an estimation model that associates the type of electrical equipment, convex point information, and power consumption, and based on the convex point information extracted by the data extraction means and the estimation model, the electric device in operation The power consumption is estimated individually.
- Patent Document 5 discloses a remote electrical device monitoring method for estimating the operating status of a plurality of electrical devices used by electric power consumers.
- the total load current is measured from the power customer's power line, and the total load current is converted into current for each fundamental and harmonic, and the time difference between the current for each fundamental and harmonic is taken.
- To generate current change data Then, the current change for each fundamental wave and harmonic is separated for each component estimated as a device group having the same harmonic intensity ratio by independent component analysis.
- the operating condition (current change) for every apparatus of a monitoring mode apparatus is estimated from the waveform of the current change for every same harmonic intensity ratio component.
- Patent Document 6 discloses a power consumption estimation device that estimates the power consumption of a load device that is supplied with power from an electric power system.
- the apparatus receives an operating state signal indicating a value corresponding to the operating state of the load device, and determines whether the load device is an operating load device in the operating state based on the value indicated by the received operating state signal. Then, as the estimated power consumption of the new active load device, the fluctuation amount of the total power consumption before and after the change is assigned, and previously assigned to the active load device as the estimated power consumption of the active load devices other than the new active load device. Assign estimated power consumption.
- Japanese Patent No. 3403368 Japanese Patent No. 4556511 Japanese Patent No. 4433890 JP 2011-232061 A Japanese Patent Laid-Open No. 2003-9430 JP 2010-169567 A
- the inventors of the present invention have a monitoring feature amount extracted from measurement data (such as a total consumption current waveform within a predetermined unit) measured by a distribution board, a teacher feature amount prepared for each monitored electrical device, and A technique for calculating the power consumption (instantaneous value) of each monitoring target electrical device based on the teacher feature amount (summation teacher feature amount) for each combination of the monitoring target electrical devices generated by combining these is studied.
- the combination which prepares the total teacher feature amount is a further subdivided combination of the monitoring target electric devices. As a result, the number of teacher feature amounts to be prepared further increases.
- an object of the present invention is to provide a technique capable of reducing the number of teacher feature amounts (including the combined teacher feature amount) used for estimating the power consumption of each monitored electrical device.
- a first monitoring difference group consisting of at least one difference among at least one feature quantity extracted from each of the waveform data and the waveform data at the second timing, and each of the monitoring target electrical devices
- a monitoring device is provided.
- a first monitoring difference group consisting of at least one difference among at least one feature quantity extracted from each of the waveform data and the waveform data at the second timing, and each of the monitoring target electrical devices
- a program for functioning as a server is provided.
- the monitoring device Obtain monitoring waveform data for each unit, which is at least one of the total current consumption, total input voltage, and total power consumption measured by the measuring instrument installed in the unit where the monitored electrical equipment is installed.
- a relay device that transmits to the monitoring device;
- a monitoring system is provided.
- the present invention it is possible to reduce the number of teacher feature values (including the combined teacher feature value) used for estimating the operating state of the electrical device.
- Each unit included in the apparatus according to the present embodiment includes a CPU (Central Processing Unit) of an arbitrary computer, a memory, a program loaded in the memory (a program stored in the memory from the stage of shipping the apparatus in advance, a CD ( Compact Disc) and other storage media and programs downloaded from servers on the Internet), storage units such as hard disks that store the programs, and any combination of hardware and software, mainly a network connection interface It is realized by. It will be understood by those skilled in the art that there are various modifications to the implementation method and apparatus.
- a CPU Central Processing Unit
- FIG. 1 is a diagram conceptually illustrating an example of a hardware configuration of an apparatus according to the present embodiment.
- the apparatus according to the present embodiment includes, for example, a CPU 1A, a RAM (Random Access Memory) 2A, a ROM (Read Only Memory) 3A, a display control unit 4A, a display 5A, and operation reception that are connected to each other via a bus 10A.
- other elements such as an input / output interface connected to an external device by wire, a microphone, and a speaker may be provided.
- the CPU 1A controls the entire computer of the apparatus together with each element.
- the ROM 3A includes an area for storing programs for operating the computer, various application programs, various setting data used when these programs operate.
- 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 includes a display device (LED (Light Emitting Diode) display, liquid crystal display, organic EL (Electro Luminescence) display, etc.) and the like.
- the display 5A may be a touch panel display integrated with a touch pad.
- the display control unit 4A reads data stored in a VRAM (Video RAM), performs predetermined processing 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 is wired and / or wirelessly connected to a network such as the Internet or a LAN (Local Area Network) and communicates with other electronic devices.
- the monitoring apparatus 10 estimates the power consumption (operating state) of each monitored electrical device at a predetermined timing. Then, management information indicating the power consumption (operating state) of each estimated electrical device to be monitored is held.
- the monitoring apparatus 10 monitors a change in power consumption (change in operating state) of the monitoring target electrical device. And if the change of the power consumption of a monitoring object electric equipment (change of an operating state) is detected, the above-mentioned management information will be updated based on the detected result. Then, by referring to the management information, the monitoring device 10 estimates the power consumption (operating state) of each monitoring target electrical device at a predetermined timing.
- FIG. 2 an example of the functional block diagram of the monitoring apparatus 10 of this embodiment is shown.
- the monitoring apparatus 10 includes a storage unit 11, a waveform data acquisition unit 12 for each unit, a first estimation unit 13, and a second estimation unit 14.
- FIG. 26 shows another example of a functional block diagram of the monitoring apparatus 10 of the present embodiment.
- the monitoring apparatus 10 is different from the example of FIG.
- the storage unit 11 is provided in a device different from the monitoring device 10.
- the monitoring device 10 communicates with the device by wire and / or wireless, and acquires information stored in the storage unit 11.
- the storage unit 11 stores teacher difference information that is at least one of the following (1) to (3) in association with each monitoring target electric device.
- Waveform data of a difference between at least one waveform data among current consumption, input voltage and power consumption in the first operating state and waveform data in the second operating state (2) (1) ) At least one type of feature extracted from the difference waveform data (3) at least one type of feature extracted from each of the waveform data in the first operating state and the waveform data in the second operating state Difference in quantity
- the first operating state and the second operating state correspond to a state in which predetermined power different from each other is being consumed.
- the feature amount may be anything that can be extracted from the above waveform data.
- the feature amount is not limited to the example here.
- FIG. 3 schematically shows an example of teacher difference information corresponding to the above (2) and (3).
- a teacher data ID, a device ID, a first operating state, a second operating state, and a feature amount are associated with each other.
- the teacher difference information of the teacher data ID “0001-003” includes the teacher feature amount when the power consumption of the monitoring target electric device having the device ID “0001” is changed from 5 W to 10 W.
- the teacher feature amount may be one type of feature amount or a combination of a plurality of types of feature amounts.
- Such teacher difference information can be generated as follows, for example.
- the range from 0 W to the rated power is divided into arbitrary groups with a predetermined power value width for each electric appliance to be monitored.
- the power value width and the number of groups of each group can be determined for each electric appliance to be monitored.
- the range from 0 W to 1200 W (rated power) is divided into a plurality of groups with a power value width of 5 W.
- the representative value may be, for example, a statistical value (average value, maximum value, minimum value, median value, etc.) of the power value band included in each group.
- one of the power values of each group is consumed from the instructor waveform data for each device, which is at least one waveform data of current consumption, input voltage and power consumption prepared in advance for each monitored electrical device.
- Waveform data (e.g., waveform data for a predetermined period) is extracted. Then, the extracted waveform data is associated with each group. It should be noted that waveform data corresponding to each group (e.g., when a plurality of waveform data for a predetermined period are taken out from the device-specific teacher waveform data, any of them may be used as representative waveform data. The averaged data may be used as representative waveform data.
- the representative value (power consumption) and the waveform data when the power value of each group is consumed are associated with each group.
- Waveform data (representative waveform data) associated with each group is handled as waveform data in an operating state in which power of the representative value of each group is consumed.
- the difference in waveform data associated with each group eg, difference obtained by subtracting one from the other and vice versa
- the waveform data of (1) is obtained by calculating. Further, by extracting a predetermined feature amount from the obtained waveform data of (1), the feature amount of (2) is obtained.
- the feature quantity (3) is obtained.
- the storage unit 11 may further store the combined teacher difference information generated by combining the teacher difference information (see FIG. 3) corresponding to each monitored electrical device.
- FIG. 5 schematically shows an example of the combined teacher difference information.
- the teacher data ID, the combined teacher feature amount, and the state are associated with each other.
- the combined teacher difference information of the teacher data ID “(0001-003) + (0002-003)” includes the teacher difference information of the teacher data ID “0001-003” and the teacher data ID “0002-003” shown in FIG. It is generated based on the teacher difference information.
- the power consumption of the monitored electrical device with the device ID “0001” has changed from 5 W to 10 W
- the power consumption of the monitored electrical device with the device ID “0002” has changed from 10 W to 50 W.
- Current teacher feature value total teacher feature value).
- the summation teacher difference information does not need to correspond to all combinations of the plurality of monitoring target electric devices, and may be a part thereof. That is, when the summation teacher difference information is stored in the storage unit 11 in advance, the number of monitored electrical devices equal to or less than the number + ⁇ (design items) predicted to change simultaneously in the operating state is extracted from a plurality of monitored electrical devices. The total teacher difference information corresponding to only the combinations generated in the above may be stored in the storage unit 11.
- the number of electrical devices to be monitored is M
- the number of electrical devices to be monitored whose operating state changes at the same time is set to 2 and ⁇ is set to 1, arbitrarily 3 from M
- the combined teacher difference information corresponding to only the combination at the time of taking out and the combination at the time of taking out two arbitrarily may be stored in the storage unit 11.
- the combination when three arbitrarily taken out from M monitored electric devices and the combination when two arbitrarily taken out from M monitored electric devices correspond to each monitored electric device. Further subdivided by a plurality of attached teacher difference information (see FIG. 3).
- the monitoring target electric device M1 has the (M) -1 teacher difference information in which (the first operating state, the second operating state) is (5 W being consumed, 10 W being consumed), and (10 W It is assumed that only the M1-2th difference information that is being consumed (5W being consumed) is associated.
- the monitoring target electric device M2 has (Min.
- the combination of (M1, M2) is (M1-1 teacher difference information, M2-1 teacher difference information), (M1-1 teacher difference information, M2-2 teacher difference information), (M1-1 teacher difference information, M2-3 teacher difference information), (M1-1 teacher difference information, M2-4 teacher difference information), (M1-1 teacher difference information, M2- 5th teacher difference information), (M1-1 teacher difference information, M2-6 teacher difference information), (M1-2 teacher difference information, M2-1 teacher difference information), (M1-2) Teacher difference information, M2-2 teacher difference information), (M1-2 teacher difference information, M2-3 teacher difference information), (M1-2 teacher difference information, M2-4 teacher difference information) ), (M1-2 teacher difference information, M2-5 teacher difference information), (M1-2 teacher difference information, M2) It is subdivided into a combination of -6 teacher difference information).
- the storage unit 11 can store summation teacher difference information corresponding to each of these combinations.
- the unit-by-unit waveform data acquisition unit 12 calculates the total current consumption in the unit in which the monitored electrical equipment is installed (home, branching unit of distribution board, company, one floor of a building, etc.).
- the monitoring unit waveform data that is at least one of the total input voltage and the total power consumption is acquired.
- Such unit-by-unit monitoring waveform data can be acquired via a measuring instrument installed in the vicinity of a power supply trunk such as a distribution board.
- the unit-by-unit waveform data acquisition unit 12 may acquire the unit-by-unit monitoring waveform data by real-time processing, or collect a predetermined time (eg, 1 minute, 30 minutes, 1 hour, 24 hours) by batch processing. May be obtained.
- a predetermined time eg, 1 minute, 30 minutes, 1 hour, 24 hours
- the waveform data acquisition part 12 for every unit acquires the waveform data for monitoring for every unit by real-time processing.
- the first estimation unit 13 stores the first monitoring difference group including at least one of the following (4) and (5) extracted from the monitoring waveform data for each unit, and the storage unit 11 stores the first estimation difference group. Based on the teacher difference information, a change in the operating state of at least a part of the monitoring target electric appliance is estimated.
- the waveform data for monitoring for each unit is divided along a time axis in accordance with a predetermined rule, thereby being divided into a plurality of processing unit groups.
- the waveform data for monitoring for each unit is divided every time T (eg, every predetermined cycle), thereby dividing the data into a plurality of processing unit groups.
- T e.g., every predetermined cycle
- the length of one processing unit group is set to time T (for example, a predetermined period), and the group is shifted by a predetermined time t (greater than 0), thereby forming a plurality of processing unit groups. It is divided.
- T for example, a predetermined period
- t greater than 0
- the waveform data of the first timing is waveform data included in one of the plurality of processing unit groups (first processing unit group) set as described above.
- the waveform data at the second timing is waveform data included in a processing unit group (second processing unit group) different from the first processing unit group.
- the first processing unit group and the second processing unit group are two processing unit groups that are temporally continuous (eg, two processing unit groups in which numbers are consecutive in the examples shown in FIGS. 6 and 7). May be.
- the feature amount of (4) is obtained.
- the feature amount of (5) is obtained by calculating a difference between the extracted feature amounts.
- the first estimation unit 13 includes a first monitoring difference group including at least one of (4) and (5), teacher difference information illustrated in FIG. And, based on the total teacher difference information shown in FIG. 5, whether or not there is a change in the power consumption of at least a part of the monitored electrical equipment, and details of the change (if any monitored electrical equipment is operating Which operating state has changed from the state).
- the first estimation unit 13 generates an estimation model using the teacher difference information (see FIG. 3) and the combined teacher difference information (see FIG. 5) as teacher data, and adds the first monitoring difference group to the generated estimation model.
- An estimation result may be obtained by inputting a value (feature value).
- the first monitoring difference group is composed of feature quantities of the same type as the feature quantities (including the combined feature quantities) used for generating the estimation model used by the first estimation unit 13.
- the estimation model can be, for example, one using multiple regression analysis, a neural network, a genetic algorithm, or the like.
- the first estimation unit 13 When the storage unit 11 does not store the combined teacher difference information illustrated in FIG. 5, the first estimation unit 13 generates the combined teacher difference information using the teacher difference information stored in the storage unit 11. When the storage unit 11 holds the waveform data of the difference (1), the first estimation unit 13 uses the waveform data to generate the feature (2). The combined teacher difference information is generated using the generated feature amount.
- the second estimation unit 14 estimates the operating state of each monitored electrical device based on the estimation result of the first estimation unit 13.
- the 2nd estimation part 14 estimates the power consumption of the monitoring object electric equipment.
- the second estimation unit 14 estimates the power consumption of each monitored electrical device at a predetermined timing. Then, management information (FIG. 8) indicating the estimated content is generated and held. Then, after the timing when the management information is generated, the management information is updated based on the change in the power consumption of the monitoring target electrical device estimated by the first estimation unit 13.
- the predetermined timing at which the second estimation unit 14 estimates the power consumption of each of the monitoring target electrical devices the initial stage of starting the monitoring process by the monitoring device 10 or in addition to this, The timing of every predetermined time (for example, every 30 minutes, every 1 hour, every 6 hours, etc.) while continuing is considered.
- ⁇ Power consumption estimation process 1> For example, in a state in which the power supply state of all the monitoring target electrical devices is turned off, the monitoring apparatus 10 receives an input indicating that from, for example, a user. Then, the 2nd estimation part 14 estimates the power consumption of all the monitoring object electric equipment at the time of receiving the said input as power consumption 0W. This process is suitable for the case where the monitoring process by the monitoring apparatus 10 is performed at the first stage of starting.
- the storage unit 11 stores teacher data as illustrated in FIG. 9 or 10.
- the teacher data shown in FIG. 9 associates teacher feature quantities at each power consumption with each monitored electrical device.
- the teacher feature amount in this case is a feature amount extracted from waveform data at each power consumption (eg, waveform data for a predetermined period).
- a device ID, a teacher data ID, a power value band, a representative value, a teacher feature amount, and a state are associated with each other.
- the range from 0 W to the rated power is divided into arbitrary groups with a predetermined power value width for each monitoring target electric device.
- the power value width and the number of groups of each group can be determined for each electric appliance to be monitored. Then, a representative value and a teacher feature amount are generated for each group.
- the range from 0 W to 1200 W (rated power) is divided into a plurality of groups with a power value width of 5 W.
- the statistical values (average value, maximum value, minimum value, median value, etc.) of the power value bands included in each group are used as representative values.
- a feature amount extracted from waveform data eg, waveform data for a predetermined period
- any power in the power value band included in each group is consumed is used as a teacher feature amount.
- Each teacher data ID shown in FIG. 9 corresponds to each group described above, and a power value band indicates a power value band included in each group.
- the teacher data shown in FIG. 10 associates teacher feature quantities at each power consumption with each monitored electrical device.
- the teacher feature amount in this case is a feature amount extracted from waveform data at each power consumption (eg, waveform data for a predetermined period).
- the device ID, the teacher data ID, the power value band, the representative value, the teacher feature amount, and the state are associated with each other.
- a group for generating a representative value and a teacher feature amount is set partially in the range from 0 W to the rated power for each monitoring target electric device.
- the power value width and the number of groups of each group can be determined for each electric appliance to be monitored.
- a representative value and a teacher feature amount are generated for each group.
- groups are set from 605W to 610W, 1107W to 1112W, and the like.
- the statistical values (average value, maximum value, minimum value, median value, power consumption having the highest appearance frequency, etc.) of the power value bands included in each group are used as representative values.
- a feature amount extracted from waveform data eg, waveform data for a predetermined period
- any power in the power value band included in each group is consumed is used as a teacher feature amount.
- a group for generating representative values and teacher feature values is partially set in a range from 0 W to rated power.
- the frequency analysis of the power consumption is performed for each monitoring target electric device using the device-specific teacher waveform data for a predetermined time.
- a means for frequency analysis for example, a means for generating a frequency distribution curve and analyzing it, a means for generating a histogram and analyzing it, or a power consumption band (0 W) that can be actually consumed by the processing target electric device.
- a means for dividing the power consumption of a larger power than the standard power) into a plurality of groups and counting the power consumption of each group is conceivable, but is not limited thereto.
- the generation of the frequency distribution curve may be realized, for example, by executing kernel density estimation.
- kernel density estimation for example, a Gaussian kernel can be used as the kernel function, and a Silverman bandwidth can be used as the bandwidth.
- Other kernel functions eg, polynomials
- bandwidths can also be used.
- FIG. 12 shows an example of the generated frequency distribution curve. The horizontal axis is power consumption, and the vertical axis is the appearance frequency.
- a group can be set so as to include a power value having a relatively high frequency of appearance.
- a low power consumption band eg, 10% or less of the rated power value
- the storage unit 11 may further store teacher data including a combined teacher feature amount generated using teacher data in which teacher feature amounts at the time of power consumption are associated with each monitored electric device. .
- the total teacher feature amount corresponds to all combinations of a plurality of electric appliances to be monitored. Further, the combination is subdivided according to a plurality of operating states that can be taken by a plurality of monitoring target electric devices, but it corresponds to all the subdivided combinations.
- the second estimation unit 14 calculates the power consumption of the monitoring target electrical device based on the teacher data and the feature amount extracted from the unit-by-unit monitoring waveform data acquired by the unit-by-unit waveform data acquisition unit 12. It may be estimated.
- the second estimation unit 14 generates an estimation model by using these teacher data, and inputs the feature amount extracted from the waveform data for monitoring for each unit to the generated estimation model, so that the estimation result ( You may obtain the power consumption of the monitoring object electric equipment.
- the estimation model can be, for example, one using multiple regression analysis, a neural network, a genetic algorithm, or the like.
- This process is performed at the first stage of starting the monitoring process by the monitoring device 10, and every predetermined time (eg, every 30 minutes, every hour, every 6 hours while the monitoring process by the monitoring device 10 is continued) Etc.).
- the second estimation unit 14 refers to management information (see FIG. 8) generated by the power consumption estimation processes 1 and 2 and updated based on the estimation result by the first estimation unit 13.
- the power consumption of each monitored electrical device at other timings can also be estimated.
- the waveform data acquisition unit 12 for each unit obtains the waveform data for monitoring for each unit, which is at least one waveform data among the total current consumption, the total input voltage, and the total power consumption in the unit in which the monitoring target electrical device is installed. Obtain (S10).
- the unit-by-unit waveform data acquisition unit 12 acquires the unit-by-unit monitoring waveform data from a measuring device installed in a predetermined unit by real-time processing. In this case, the unit-by-unit waveform data acquisition unit 12 continues to acquire the unit-by-unit monitoring waveform data. Alternatively, the unit-by-unit waveform data acquisition unit 12 collectively acquires the unit-by-unit monitoring waveform data for a predetermined time by batch processing.
- the second estimation unit 14 extracts a predetermined type of feature amount from the waveform data for a predetermined period (for processing target) in the waveform data for monitoring per unit acquired in S10. Then, the power consumption of each of the plurality of electric appliances to be monitored is estimated, and management information (FIG. 8) is generated.
- the second estimation unit 14 obtains teacher data including teacher feature amounts corresponding to each power consumption of the monitoring target electrical device acquired from the storage unit 11 and a combined teacher feature amount generated using the teacher feature amounts.
- An estimation model is generated using the included teacher data, and a monitoring feature is input to the generated estimation model, thereby obtaining an estimation result (power consumption of each monitoring target electrical device).
- the second estimation unit 14 calculates the teacher feature amount corresponding to each power consumption of the monitoring target electrical device acquired from the storage unit 11.
- Teacher data including the combined teacher feature amount is generated using the teacher data included.
- the second estimation unit 14 stores the monitoring target electric device.
- Teacher waveform data for each device is acquired from the storage unit 11, and teacher data including teacher feature amounts corresponding to each power consumption is generated using the teacher waveform data for each device.
- teacher data including the combined teacher feature amount is generated using the teacher data including the teacher feature amount corresponding to each generated power consumption.
- the second estimation unit 14 generates the teacher data including the teacher feature amount corresponding to each power consumption of the generated monitoring target electrical device, and the teacher data including the sum teacher feature amount generated using the teacher feature amount.
- An estimation model is generated by using it, and a monitoring feature is input to the generated estimation model, thereby obtaining an estimation result (power consumption of each monitoring target electrical device).
- the monitoring target electrical devices that are the targets of the processing of the second estimation unit 14 are determined in advance (all). For this reason, the estimated model may be generated in advance and stored in the storage unit 11. And the 2nd estimation part 14 takes out the said estimation model from the memory
- the first estimation unit 13 extracts difference information (first monitoring difference group) composed of predetermined type feature amounts from the unit-by-unit monitoring waveform data acquired in S10 (S12).
- the first estimation unit 13 sets the waveform data after the timing at which the power consumption of the plurality of monitoring target electrical devices is estimated in S11 as the processing target, and sets the waveform data for the latest predetermined period as the second timing.
- Waveform data for a predetermined period before (for example, immediately before) is set as waveform data of the first timing, and difference information is generated using these waveform data.
- the first estimation unit 13 processes waveform data after the timing at which the power consumption of the plurality of monitoring target electrical devices is estimated in S11 in the waveform data for monitoring for each unit for a predetermined time.
- the waveform data of the predetermined processing target for a predetermined period is set as the waveform data of the second timing, and the waveform data of the predetermined period before (for example, immediately before) is set as the waveform data of the first timing. Set and extract difference information using them.
- the first estimation unit 13 estimates whether or not there is a change in the power consumption in the monitored electrical device after the timing at which the power consumption of the plurality of monitored electrical devices is estimated in S11, and if there is, estimates the details. (S13). That is, the first estimation unit 13 uses the difference information (first monitoring difference group) extracted in S12 to change the change between the first timing and the second timing set in S12. Estimate whether or not there was, and if so, details.
- the first estimation unit 13 acquires the difference information (first monitoring difference group) extracted in S12, the teacher difference information including the teacher feature amount (FIG. 3) from the storage unit 11, and The total teacher difference information (FIG. 5) generated using these is acquired. And the 1st estimation part 13 uses the teacher difference information (FIG. 3) containing the acquired teacher feature-value, and the total teacher difference information (FIG. 5) produced
- An estimation model is generated, and an estimation result is obtained by inputting the value (feature value) of the first monitoring difference group into the generated estimation model.
- the first estimation unit 13 uses the teacher difference information (FIG. 3) including the teacher feature amount acquired from the storage unit 11. Thus, total teacher difference information (FIG. 5) is generated. Further, the storage unit 11 stores the waveform data of the difference between the waveform data in the first operation state and the waveform data in the second operation state, and the teacher difference information including the teacher feature amount (FIG. When 3) is not stored, the first estimation unit 13 acquires the difference waveform data from the storage unit 11, and uses the difference waveform data to transmit the teacher difference information including the teacher feature amount (FIG. 3). Is generated. Further, the combined teacher difference information (FIG. 5 and the like) is generated using the teacher difference information (FIG. 3) including the generated teacher feature amount. Note that the total teacher difference information to be generated may correspond to only combinations that are generated by taking out the monitoring target electrical devices that are equal to or less than the number + ⁇ (design items) predicted to change simultaneously in the operating state.
- the first estimation unit 13 uses the teacher difference information (FIG. 3) including the generated teacher feature value and the combined teacher difference information (FIG. 5) generated using these as teacher data.
- An estimation model is generated, and an estimation result is obtained by inputting the value (feature value) of the first monitoring difference group into the generated estimation model.
- the estimated model may be generated in advance and stored in the storage unit 11. And the 1st estimation part 13 may take out the said estimation model from the memory
- the first estimation unit 13 performs estimation based on the latest predetermined period of waveform data, and then inputs the estimation result to the second estimation unit 14.
- the first estimation unit 13 performs estimation based on waveform data for one predetermined period or performs estimation based on a predetermined number of waveform data for a predetermined period. Then, the estimation result is input to the second estimation unit 14.
- the second estimation unit 14 that has received the estimation result from the first estimation unit 13 checks whether or not the power consumption of the monitoring target electrical device has changed. When there is a change (Yes in S14), the second estimation unit 14 updates the management information based on the estimation result (S16), and then proceeds to S15. On the other hand, when there is no change (No in S14), the process proceeds to S15 as it is. In S15, the 2nd estimation part 14 estimates the power consumption of each of several monitoring object electric equipment based on the newest management information. In the case of batch processing, the second estimation unit 14 tracks the presence / absence of a change as a processing target in order from the previous estimation result in time, and updates management information as necessary.
- the power consumption of each monitored electrical device at a certain time is estimated by the above processing. Then, the above process is repeated.
- a change in power consumption of each monitored electrical device within a certain time is estimated by the above processing.
- the current power consumption of each of the plurality of electric appliances to be monitored can be specified by referring to the management information held by the second estimation unit 14.
- the 1st estimation part 13 is the teacher difference from which the 1st operation state (operation state before a change) corresponds with the present operation state among several teacher difference information matched with the monitoring object electric equipment.
- the total teacher difference information may be generated using only the information.
- the first estimation unit 13 includes the teacher difference information in which the first operating state (the operating state before the change) matches the current operating state, and the combined teacher difference information generated using the teacher difference information.
- the estimation model may be generated using only In this way, the number of teacher difference information (including total teacher difference information) to be used can be further reduced.
- the monitoring device 10 is installed in a unit such as a predetermined home, company, or building.
- a plurality of electrical devices 60 are installed in the unit.
- Each electric device 60 receives supply of electric power through the distribution board 40 installed in the unit.
- the flow of electric power is indicated by a dotted line.
- the solid line shows the data flow.
- a measuring instrument 50 is installed near the distribution board 40 and measures current consumption, input voltage, power consumption, and the like. Measurement data measured by the measuring device 50 is transmitted to the monitoring device 10.
- the monitoring device 10, the distribution board 40, and the measuring instrument 50 are in a state in which data communication is possible by a LAN, a dedicated cable for connecting a plurality of devices, or the like.
- the monitoring device 10 is connected to a terminal device 70 owned by the user via a network 30 such as the Internet.
- the electric device 60 and the monitoring device 10 may be in a state where they can communicate with each other.
- the electrical device 60 may have a function of connecting to a network such as a LAN.
- the monitoring device 10 provides the estimation result to the user via its own output device or the terminal device 70.
- predetermined data is stored in the storage unit 11 by the following preparation.
- each electric device 60 is operated individually.
- the monitoring apparatus 10 accepts input of information for identifying the electric device 60 being operated from, for example, a user, and each piece of measurement data measured by the measuring instrument 50 is used as the device-specific teacher waveform data of each monitoring target electric device. Get as.
- the monitoring apparatus 10 can store the acquired teacher waveform data for each device of each monitored electric device in the storage unit 11.
- the monitoring device 10 generates teacher difference information that is at least one of the above (1) to (3) by using the acquired teacher-specific teacher waveform data of each monitored electrical device, and stores it in the storage unit 11. It can be memorized.
- the monitoring apparatus 10 may generate summation teacher difference information using the teacher difference information and store the summation teacher difference information in the storage unit 11.
- teacher waveform data for each device of a wide variety of electric devices on the market and predetermined teacher characteristics extracted from the teacher waveform data for each device.
- the amount or teacher difference information that is at least one of the above (1) to (3) may be stored.
- the monitoring apparatus 10 identifies each electric equipment 60 installed in the predetermined unit by the manual input which operated the monitoring apparatus 10, the input via the terminal device 70, or the communication with each electric equipment 60. Get information. Thereafter, the monitoring device 10 may access the server and acquire the device-specific teacher waveform data, teacher feature amount, or teacher difference information of each identified electrical device 60 and store the teacher waveform data in the storage unit 11.
- the monitoring apparatus 10 can generate teacher difference information that is at least one of the above (1) to (3) by using these pieces of information, and store the teacher difference information in the storage unit 11. Furthermore, the monitoring apparatus 10 may generate summation teacher difference information using the teacher difference information and store the summation teacher difference information in the storage unit 11.
- the monitoring apparatus 10 acquires information for identifying each electric device 60 installed in a predetermined unit
- the monitoring apparatus 10 accesses the server to transmit the teacher waveform data for each device and the teacher feature amount of each identified electric device 60.
- teacher difference information that is at least one of the above (1) to (3) is acquired, and various data is stored in the storage unit 11 in the same manner as described above.
- it is at least one of the device-specific teacher waveform data, the teacher feature amount, or the above-described (1) to (3) of one or more electric devices 60 in the above process.
- the monitoring apparatus 10 may output information that prompts the user to operate the electric device 60 that has not been acquired, to the user.
- the monitoring apparatus 10 is the teacher which is at least one of said apparatus 1 teacher waveform data, a teacher feature-value, or said (1) thru
- the above-described estimation process is executed by the unit-by-unit waveform data acquisition unit 12, the first estimation unit 13, and the second estimation unit 14. Is done.
- the relay device 20 is installed in a unit such as a predetermined home, company, or building.
- a plurality of electrical devices 60 are installed in the unit.
- Each electric device 60 receives supply of electric power through the distribution board 40 installed in the unit.
- the flow of electric power is indicated by a dotted line.
- the solid line shows the data flow.
- a measuring instrument 50 is installed near the distribution board 40 and measures current consumption, input voltage, power consumption, and the like.
- the measurement data measured by the measuring device 50 is transmitted to the relay device 20.
- the relay device 20, the distribution board 40, and the measuring device 50 are in a state in which data communication is possible by a LAN, a dedicated cable that connects a plurality of devices, or the like.
- the relay device 20 is connected to a terminal device 70 owned by the user via a network 30 such as the Internet.
- the electrical device 60 and the relay device 20 may be in a state where data communication is possible.
- the electrical device 60 may have a function of connecting to a network such as a LAN.
- the monitoring device 10 is installed outside a predetermined unit.
- the monitoring device 10 may be a so-called cloud server.
- the monitoring device 10 can communicate data with the relay device 20 and the terminal device 70 via the network 30.
- the monitoring device 10 acquires the waveform data for monitoring for each unit via the relay device 20.
- the monitoring device 10 provides the estimation result to the user via the relay device 20 or the terminal device 70.
- the relay device 20 when the relay device 20 acquires measurement data (such as teacher waveform data for each device, waveform data for monitoring for each unit) from the measuring device 50, the relay device 20 transfers the acquired measurement data to the monitoring device 10.
- the relay device 20 receives input of information for identifying the electrical device 60 corresponding to each teacher data generation measurement data from the user, for example, similarly to the example shown in FIG.
- the identification information of the electric device 60 corresponding to can also be transferred to the monitoring device 10.
- the relay device 20 acquires data (such as information for identifying the electric device 60 installed in the unit) from the electric device 60 installed in the predetermined unit, the relay device 20 uses the acquired data as the teacher data generation device 10. Forward to.
- the relay device 20 when the relay device 20 receives input of predetermined information (such as information for identifying the electric device 60 installed in the unit) from the user, the relay device 20 transfers the acquired information to the teacher data generation device 10. Also in the application example, predetermined data is stored in the storage unit 11 by the same preprocessing as in the application example illustrated in FIG.
- FIG. 16 an example of the functional block diagram of the monitoring apparatus 10 of this embodiment is shown.
- the monitoring apparatus 10 includes a storage unit 11, a waveform data acquisition unit 12 for each unit, a first estimation unit 13, a second estimation unit 14, and an output unit 15.
- the configurations of the storage unit 11, the unit-by-unit waveform data acquisition unit 12, the first estimation unit 13, and the second estimation unit 14 are the same as those in the first embodiment.
- the monitoring apparatus of this embodiment can also be set as the structure which does not have the memory
- the output unit 15 outputs estimation results (power consumption of each monitored electrical device (instantaneous value, history of power consumption within a predetermined period)) by the first estimation unit 13 and the second estimation unit 14.
- the output unit 15 can output the estimation result via an output device such as a display, a printer, or a mailer.
- the address information of the transmission destination of the estimation result is registered in the output unit 15 in advance.
- the output part 15 transmits an estimation result to a predetermined transmission destination using predetermined address information.
- Fig. 17 shows an example of an output example. According to the estimation result shown in FIG. 17, the user can easily calculate the total power consumption (instantaneous value) at a certain point in time within a unit and the power consumption (instantaneous value) of each monitored electrical device installed in the unit. Can grasp.
- the monitoring apparatus 10 estimates the power supply state (operating state) of each monitored electrical device at a predetermined timing, that is, whether the power supply is on or off. And the management information which shows the power supply state (operating state) of each estimated electrical equipment to be monitored is held.
- the monitoring apparatus 10 monitors a change in power supply state (change in operating state) of the monitoring target electrical device. And if the change of the power supply state (change of an operation state) of the monitoring object electric equipment is detected, the above-mentioned management information will be updated based on the detected result. Then, by referring to the management information, the monitoring target electric device in the power ON state at a predetermined timing is estimated.
- the monitoring apparatus 10 estimates the power ON state by using the teacher feature amount corresponding to each power consumption of each monitoring target electrical device estimated to be the power ON state, and the combined teacher feature amount generated therefrom.
- the power consumption of each monitored electrical device is estimated. Note that the power consumption of the monitoring target electrical device estimated to be in the power OFF state can be estimated to be 0 W, for example.
- the monitoring device 10 includes a storage unit 11, a unit-by-unit waveform data acquisition unit 12, a first estimation unit 13, and a second estimation unit 14. Further, as shown in FIG. 16, the monitoring apparatus 10 can further include an output unit 15.
- the configurations of the unit-by-unit waveform data acquisition unit 12 and the output unit 15 are the same as those in the first and second embodiments.
- the monitoring apparatus of this embodiment can also be set as the structure which does not have the memory
- FIG. 18 schematically shows an example of teacher difference information stored in the storage unit 11 of the present embodiment.
- a teacher data ID, a device ID, a first operating state, a second operating state, and a feature amount are associated with each other.
- the teacher difference information of the teacher data ID “0001-001” includes a feature amount when the power state of the monitoring target electric device with the device ID “0001” changes from the power OFF state to the power ON state.
- the feature amount may be one type of feature amount or a combination of a plurality of types of feature amounts.
- the storage unit 11 may further store summation teacher difference information generated by combining difference information corresponding to each monitoring target electric device as shown in FIG. FIG. 19 schematically shows an example of the combined teacher difference information.
- the combined teacher difference information of the teacher data ID “(0001 ⁇ 001) + (0002 ⁇ 001)” includes the teacher difference information of the teacher data ID “0001-001” and the teacher data ID “0002-001” shown in FIG. It is generated based on the teacher difference information.
- the summation teacher difference information indicates that the power state of the monitored electrical device with the device ID “0001” changes from the power off state to the power on state, and the power state of the monitored electrical device with the device ID “0002” is It includes the feature amount (total feature amount) when the power supply is turned off.
- the first estimation unit 13 is different from the first embodiment in that a change in the power supply state is estimated as a change in the operating state of at least a part of the monitored electrical equipment.
- Other configurations are the same as those of the first embodiment.
- the first estimation unit 13 estimates the power supply state of each monitored electrical device at a predetermined timing. Then, management information (FIG. 20) indicating the estimated contents is generated and held. Then, after a predetermined timing, a change in the power supply state of the monitoring target electrical device is monitored, and when the change is detected, the management information (FIG. 20) is updated.
- the first estimation unit 13 estimates the power supply state of each monitoring target electrical device, the first stage of starting the monitoring process by the monitoring apparatus 10, or in addition to this, the monitoring process by the monitoring apparatus 10
- the timing of every predetermined time for example, every 30 minutes, every 1 hour, every 6 hours, etc.
- ⁇ Power supply state estimation process 1> For example, in a state in which the power supply state of all the monitoring target electrical devices is turned off, the monitoring apparatus 10 receives an input indicating that from, for example, a user. Then, the 1st estimation part 13 estimates the power supply state of all the electric appliances to be monitored at the time of receiving the said input as a power supply OFF state. This process is suitable for the case where the monitoring process by the monitoring apparatus 10 is performed at the first stage of starting.
- the monitoring apparatus 10 accepts input of information indicating the power supply state of each monitored electrical device at a certain timing (eg, at that time, a certain time on a certain day) from a user at a predetermined timing. .
- the 1st estimation part 13 estimates the power supply state of each monitoring object electric equipment in the timing based on the input content.
- the 1st estimation part 13 utilizes the difference information corresponding to each monitoring object electric equipment as shown in FIG. 18, and the total teacher difference information as shown in FIG. 19 produced
- the process of estimating the change in the power supply state of the monitoring target electrical device after the timing at which the power supply state is estimated can be realized in the same manner as the process of estimating the change in power consumption of each monitoring target electrical device in the first embodiment. . Therefore, the description here is omitted.
- the first estimation unit 13 refers to the management information (see FIG. 20) generated by, for example, the power supply state estimation processes 1 and 2 and updated based on the estimation result thereafter, thereby determining the power supply state estimation.
- the timing at which the power supply state of the monitoring target electrical device is estimated by the processing 1 and 2 it is possible to estimate the power supply state of each monitoring target electrical device at other timings.
- the second estimation unit 14 estimates only the power consumption of the monitoring target electrical devices that the first estimation unit 13 has estimated to be in the power-on state, and estimates the power consumption. That is, the second estimation unit 14 determines the teacher feature amount corresponding to each power consumption of the monitoring target electrical device estimated by the first estimation unit 13 as being in the power-on state, and the combined teacher feature amount generated from them. The power consumption of each of the monitoring target electrical devices to be processed is estimated. Note that the power consumption of the monitoring target electrical device estimated to be in the power OFF state can be estimated to be 0 W, for example.
- the processing by the second estimation unit 14 can be realized in the same manner as the “power consumption estimation processing 2” described in the first embodiment (only the points to be processed are different). Compared to the first embodiment, this embodiment has a smaller number of monitoring target electrical devices to be processed. On the other hand, compared with the present embodiment, the first embodiment is less frequently executed.
- the waveform data acquisition unit 12 for each unit obtains the waveform data for monitoring for each unit, which is at least one waveform data among the total current consumption, the total input voltage, and the total power consumption in the unit in which the monitoring target electrical device is installed. Obtain (S20).
- the first estimation unit 13 estimates the power supply state of the monitoring target electrical device at a certain timing, and generates management information (FIG. 20) (S21).
- the first estimation unit 13 extracts difference information (first monitoring difference group) configured by a predetermined type of feature amount from the unit-by-unit monitoring waveform data acquired in S10 (S22). Thereafter, the first estimation unit 13 uses the difference information (first monitoring difference group) extracted in S12, and after the timing at which the power supply states of the plurality of monitoring target electrical devices are estimated in S21. It is estimated whether or not there has been a change in the power supply state of the electrical equipment, and if so, the details (how the power supply state of which monitored electrical equipment has changed) (S23).
- the first estimation unit 13 updates the management information based on the estimation result (S25), and then proceeds to S26. On the other hand, when there is no change (No in S24), the process proceeds to S26 as it is. In S26, the 1st estimation part 13 estimates the power supply state of each of several monitoring object electric equipment based on the newest management information. Then, the estimation result is input to the second estimation unit 14.
- the second estimation unit 14 estimates only the power consumption of the monitoring target electrical device by setting only the monitoring target electrical device estimated to be in the power ON state as a processing target (S27).
- the power supply states of a plurality of electric appliances to be monitored are estimated (first process).
- the monitoring target electrical device estimated to be in the power-on state is set as the processing target, the teacher feature amount corresponding to each power consumption of the processing target monitoring target electrical device, and the total generated by using these
- the power consumption of each monitoring target electrical device is estimated using the teacher feature amount (second processing).
- the number of teacher data (see FIGS. 18 and 19) used to estimate the power supply state that takes only two states, the power-on state and the power-off state is the power consumption that takes many states (eg, 5 W, 10 W, 15 W) is less than the number of teacher data (see FIGS. 18 and 19) used to estimate.
- a change in the power state is detected using the difference information. It is rare that the power supply states of a large number of monitored electrical devices change simultaneously. For this reason, the number of combinations to be considered can be reduced, and the number of teacher data can be reduced.
- this embodiment consists of two processes of a process for estimating the power supply state and a process for estimating the power consumption. Compared to estimating the power consumption of each monitored electrical device using the teacher feature values corresponding to each power consumption and the combined teacher feature values generated using these, the processing burden can be reduced .
- the monitoring apparatus 10 monitors a change in power consumption (change in operating state) of a monitoring target electrical device. Then, using the teacher feature value corresponding to each power consumption of each monitored electrical device that was not estimated to have a change in power consumption (change in operating state), and the combined teacher feature value generated from them The power consumption of each of these monitoring target electric devices is estimated. In addition, it is estimated that the operation state of the monitoring target electrical equipment estimated to have changed is consuming the changed power.
- the monitoring device 10 includes a storage unit 11, a unit-by-unit waveform data acquisition unit 12, a first estimation unit 13, and a second estimation unit 14. Further, as shown in FIG. 16, the monitoring apparatus 10 can further include an output unit 15.
- the configurations of the storage unit 11, the waveform data acquisition unit 12 for each unit, and the output unit 15 are the same as those in the first to third embodiments.
- the monitoring apparatus of this embodiment can also be set as the structure which does not have the memory
- the first estimation unit 13 estimates a change in power consumption of the plurality of monitoring target electrical devices between the first timing in the unit-by-unit monitoring waveform data and the subsequent second timing. This process is as described in the first embodiment.
- the second estimation unit 14 estimates the power consumption at the second timing with the monitoring target electrical device that has not been estimated by the first estimation unit 13 as having a change in power consumption. Note that, in the monitoring target electrical device that is estimated to have a change in power consumption by the first estimation unit 13, the estimated power consumption after the change is estimated as the power consumption at the second timing.
- the process of estimating the power consumption of each of the monitoring target electrical devices at the second timing is the same as the first estimation unit in the process of the second estimation unit 14 described in the third embodiment. 13, it can be realized by substituting for the monitoring target electric device that has not been estimated that there is a change in power consumption.
- the second estimation unit 14 includes a teacher feature amount corresponding to each power consumption of each of the monitoring target electrical devices to be processed, a combined teacher feature amount generated using these, and a monitoring waveform for each unit. Based on the feature amount extracted from the data (the feature amount extracted from the waveform data at the second timing), the power consumption of the monitoring target electrical device can be estimated.
- the second estimation unit 14 estimates the power consumption of the other monitoring target electrical devices in a process considering that the component is included in the waveform data for monitoring for each unit.
- the component is a component that appears in the waveform data for monitoring for each unit when the monitoring target electrical device that is estimated to have a change in power consumption by the first estimation unit 13 consumes the estimated power after the change. Means that.
- Examples of processing that takes into account that the component is included in the unit-by-unit monitoring waveform data include subtracting the component from the unit-by-unit monitoring waveform data, and features extracted from the unit-by-unit monitoring waveform data.
- a process of subtracting the feature amount corresponding to the component from the amount can be considered, but is not limited thereto.
- the waveform data acquisition unit 12 for each unit obtains the waveform data for monitoring for each unit, which is at least one waveform data among the total current consumption, the total input voltage, and the total power consumption in the unit in which the monitoring target electrical device is installed. Obtain (S30).
- the first estimation unit 13 extracts difference information (first monitoring difference group) composed of predetermined types of feature amounts from the unit-by-unit monitoring waveform data acquired in S30 (S31). After that, the first estimation unit 13 uses the difference information (first monitoring difference group) extracted in S31 to determine whether or not there is a change in power consumption in the monitoring target electrical device, and if so, details thereof. (Which monitored electric device has changed from which power consumption to which power consumption) is estimated (S32).
- the second estimation unit 14 estimates only the power consumption of the monitoring target electrical device by setting only the monitoring target electrical device that is not estimated to have a change in power consumption as a processing target (S33).
- a change in power consumption of a plurality of electric appliances to be monitored is estimated (first process).
- the monitoring target electrical equipment that is not estimated to have a change in power consumption is set as the processing target, and the teacher feature amount corresponding to each power consumption of the processing target monitoring target electrical equipment is used.
- the power consumption of each monitored electrical device is estimated using the generated combined teacher feature amount (second process).
- a change in power consumption is detected using difference information. As described above, it is rare that the power consumption of a large number of monitored electrical devices changes simultaneously. For this reason, the number of combinations to be considered can be reduced, and the number of teacher data can be reduced.
- this embodiment consists of two processes, a process for estimating the change in power consumption and a process for estimating the power consumption. Compared to estimating the power consumption of each monitored electrical device using the teacher feature values corresponding to each power consumption and the combined teacher feature values generated using these, the processing burden is reduced. Can be reduced.
- the monitoring device 10 monitors a change in the power supply state (change in operating state) of the monitoring target electrical device. After that, it is assumed that there is a change in the power supply status, and the monitored electrical equipment excluding the monitored electrical equipment whose post-change status is estimated to be in the power OFF status is processed, and each power consumption is supported.
- the power consumption of each of these monitoring target electrical devices is estimated using the teacher feature values and the combined teacher feature values generated from them. It should be noted that the monitoring target electrical equipment that is not the target of processing can be estimated to have, for example, power consumption of 0 W.
- the monitoring device 10 includes a storage unit 11, a unit-by-unit waveform data acquisition unit 12, a first estimation unit 13, and a second estimation unit 14. Further, as shown in FIG. 16, the monitoring apparatus 10 can further include an output unit 15.
- the configurations of the storage unit 11, the waveform data acquisition unit 12 for each unit, and the output unit 15 are the same as those in the first to fourth embodiments.
- the monitoring apparatus of this embodiment can also be set as the structure which does not have the memory
- the first estimation unit 13 estimates the change in the power supply state of the plurality of monitoring target electrical devices between the first timing in the unit-by-unit monitoring waveform data and the second timing thereafter. This processing is as described in the third embodiment.
- the second estimator 14 is configured to monitor the electric power to be monitored except for the electric appliance to be monitored which is estimated by the first estimator 13 to have a change in the power supply state and the state after the change is estimated to be the power OFF state
- the device is a processing target, and the power consumption at the second timing is estimated.
- the power consumption of the monitoring object electric equipment which is not a process target can be estimated to be 0 W, for example.
- the process of estimating the power consumption of each of the monitoring target electrical devices at the second timing is the same as the first estimation unit in the process of the second estimation unit 14 described in the third embodiment. 13, it can be realized by replacing the monitoring target electrical device excluding the monitoring target electrical device in which it is estimated that there is a change in the power supply state and the state after the change is estimated to be the power supply OFF state.
- the second estimation unit 14 includes a teacher feature amount corresponding to each power consumption of each of the monitoring target electrical devices to be processed, a combined teacher feature amount generated using these, and a monitoring waveform for each unit. Based on the feature amount extracted from the data (the feature amount extracted from the waveform data at the second timing), the power consumption of the monitoring target electrical device can be estimated.
- the waveform data acquisition unit 12 for each unit obtains the waveform data for monitoring for each unit, which is at least one waveform data among the total current consumption, the total input voltage, and the total power consumption in the unit in which the monitoring target electrical device is installed. Obtain (S40).
- the first estimation unit 13 extracts difference information (first monitoring difference group) composed of a predetermined type of feature amount from the unit-by-unit monitoring waveform data acquired in S40 (S41). Thereafter, the first estimation unit 13 uses the difference information (first monitoring difference group) extracted in S42 to determine whether or not there is a change in the power supply state of the monitoring target electrical device, and if so, details thereof. (How the power state of which monitoring target electrical device has changed) is estimated (S42).
- the second estimator 14 excluding monitoring target electrical equipment that is estimated by the first estimator 13 that there is a change in the power supply state and that the changed state is estimated to be the power supply OFF state. Only the target electric device is set as a processing target, and the power consumption of the monitoring target electric device is estimated (S43).
- a change in the power supply state of a plurality of electric appliances to be monitored is estimated (first process). After that, it is estimated that there is a change in the power supply state, and only the monitoring target electrical equipment excluding the monitoring target electrical equipment in which the state after the change is estimated to be the power OFF state is set as the processing target, and the processing target is monitored.
- the power consumption of each monitoring target electrical device is estimated using the teacher feature amount corresponding to each power consumption of the target electrical device and the combined teacher feature amount generated using the teacher feature amount (second processing). .
- a change in the power supply state is detected using the difference information.
- the power supply states of a large number of monitored electrical devices change simultaneously. For this reason, the number of combinations to be considered can be reduced, and the number of teacher data can be reduced.
- this embodiment consists of two processes of the process which estimates the change of a power supply state, and the process which estimates power consumption, but sets all the monitoring object electric equipment as a process object, and all the monitoring object electric equipments. Compared to estimating the power consumption of each monitored electrical device using the teacher feature values corresponding to each power consumption and the combined teacher feature values generated using these, the processing burden is reduced. Can be reduced.
- the monitoring device 10 monitors both the change in the power supply state and the change in the power consumption of the monitoring target electrical device. After that, the monitored electrical equipment that is estimated to have a change in power consumption and the monitored electrical equipment that is estimated to have a change in power supply state and the state after the change is estimated to be a power OFF state
- the power consumption of each of these monitoring target electrical devices is determined by using the supervised electrical devices other than both as processing targets and using the teacher feature values corresponding to each power consumption and the combined teacher feature values generated from them. Is estimated. Also in this modification, the same operation effect is realized.
- monitoring of changes in the operating state (change in power supply state, change in power consumption) using the difference information in the first to fifth embodiments is executed in a plurality of steps.
- the present inventors have found that some of the various feature quantities extracted from the unit-by-unit monitoring waveform data are specific to the specific monitoring target electrical equipment. That is, some of the feature quantities extracted from the unit-by-unit monitoring waveform data include only the components of some of the monitoring target electrical devices and do not include the components of other monitoring target electrical devices.
- the change in the operating state of the other monitoring target electrical equipment is estimated (second step).
- the feature amount used in the second step may include a component of the monitoring target electrical device that is the processing target in the first step. For this reason, when it is estimated that there is a change in the operating state of some of the monitoring target electrical devices in the first step, in the second step, the change in the operating state of some of the monitoring target electrical devices estimated in the first step is performed. Considering (subtracting that amount, etc.), the change in the operating state of other monitored electrical devices is estimated.
- the change in the operating state of some of the monitoring target electrical devices is performed using only the teacher difference information of some of the monitoring target electrical devices and the combined teacher difference information. Can be estimated. Since the feature quantity constituting the teacher difference information handled in the first step does not include components of other monitored electric devices, it is not necessary to set the other monitored electric devices as processing targets in this step.
- other monitoring target electric devices are obtained by using only the teacher difference information of the other monitoring target electric devices excluding the monitoring target electric device that is the processing target in the first step and their summation teacher difference information.
- the power consumption of the device can be estimated.
- the number of teacher difference information (including total teacher difference information) used for monitoring changes in the operating state of the monitoring target electrical device using teacher difference information is reduced. Can do.
- FIG. 24 shows an example of a functional block diagram of the monitoring apparatus 10 of the present embodiment.
- the monitoring device 10 of this embodiment includes a storage unit 11, a unit-by-unit waveform data acquisition unit 12, a first estimation unit 13, a second estimation unit 14, and a third estimation unit 16. And have. Furthermore, you may have the output part 15.
- FIG. The configurations of the storage unit 11, the waveform data acquisition unit 12 for each unit, the second estimation unit 14, and the output unit 15 are the same as those in the first to fifth embodiments.
- the monitoring apparatus of this embodiment can also be set as the structure which does not have the memory
- the first estimator 13 is based on the difference information (first monitoring difference group) composed of specific types of feature amounts extracted from the unit-by-unit monitoring waveform data.
- a change in operating state (at least one of a change in power supply state and a change in power consumption) is estimated.
- the difference information composed of the feature amount of the type extracted from the waveform data for monitoring for each unit does not include the components of other monitored electrical devices.
- the first estimation unit 13 uses the teacher difference information of a part of the monitoring target electric devices configured by a specific type of feature amount, the summation teacher difference information obtained by adding the difference, and the unit-by-unit monitoring. Based on the difference information (first monitoring difference group) composed of the feature quantity of the type extracted from the waveform data, changes in the operating state of some of the monitored electrical devices (changes in power supply state and power consumption) At least one of the changes in (1).
- FIG. 25 shows an example of a motor having four poles. In the case of the motor, it makes 1/2 rotation per cycle. In the case of a motor with 6 poles, it rotates 1/3 per cycle.
- the first estimation unit 13 changes the operating state (power supply) of some of the monitoring target electrical devices based on a part of the first monitoring difference group (1-1 monitoring difference group). Monitoring at least one of a change in state and a change in power consumption), and monitoring some of the other parts based on the other part of the first monitoring difference group (1-2 monitoring difference group) A change in the operating state of the target electrical device (at least one of a change in the power supply state and a change in power consumption) may be estimated.
- the 1-1 monitoring difference group is composed of feature amounts derived from components of frequencies corresponding to 1 ⁇ 2 period (25 Hz for eastern Japan, 30 Hz for west Japan).
- the difference group for use may be configured with a feature amount derived from a component of a frequency corresponding to the 1/3 period (about 17 Hz in the case of eastern Japan, 20 Hz in the case of west Japan).
- the first monitoring difference group is divided into two groups, but it may be divided into more groups.
- the third estimator 16 is based on a monitoring difference group (second monitoring difference group) composed of different types of feature quantities from the feature quantities constituting the first monitoring difference group.
- a change in the operating state of the monitoring target electrical device (at least one of a change in the power supply state and a change in power consumption) is estimated.
- the third estimator 16 excludes monitored electrical devices that have been estimated by the first estimator 13 to have a change in operating state (at least one of a change in power supply state and a change in power consumption) (which is a processing target).
- a change in operating state (at least one of a change in power supply state and a change in power consumption) of at least a part of the monitored electrical device is estimated.
- the third estimator 16 determines that at least a part of the power supply states of the monitored electrical devices excluding the monitored electrical device whose power state change has been estimated by the first estimator 13 is the power ON state and the power source. It can be estimated that there has been a change between the OFF states or a change in power consumption.
- the third estimation unit 16 has a power-on state in which at least a part of the monitored electrical devices other than the monitored electrical device whose power consumption has been estimated by the first estimation unit 13 is excluded. And a change in power consumption can be estimated.
- the estimation process by the third estimation unit 16 can be realized in the same manner as the estimation process by the first estimation unit 13.
- the third estimation unit 16 is a process considering that the component is included in the second monitoring difference group, and changes in the operating state of other monitored electric devices (changes in the power supply state). And at least one of changes in power consumption).
- the component refers to a change in the operating state (power supply state) estimated by the first estimation unit 13 in which the monitoring target electrical device whose change in operating state (at least one of a change in power supply state and a change in power consumption) is estimated. This means a component that appears in the monitoring waveform data for each unit when at least one of the following change and power consumption change is performed.
- Examples of processing that takes into account that the component is included in the unit-by-unit monitoring waveform data include subtracting the component from the unit-by-unit monitoring waveform data, and features extracted from the unit-by-unit monitoring waveform data.
- a process of subtracting the feature amount corresponding to the component from the amount can be considered, but is not limited thereto.
- the second estimation unit 14 is estimated by the third estimation unit 16 after a predetermined timing (after the timing when the management information is generated).
- the management information is further updated based on the change in the operating state of the monitoring target electrical device.
- the same effects as those of the first and fifth embodiments can be obtained.
- teacher data teacher difference used in the process is divided. The number of information and total teacher difference information) can be reduced.
- FIG. 21 An example of a functional block diagram of the monitoring device 10 of the present embodiment is the same as that of FIGS.
- the configurations of the storage unit 11, the unit-by-unit waveform data acquisition unit 12, and the output unit 15 are the same as those in the first to sixth embodiments.
- the monitoring apparatus of this embodiment can also be set as the structure which does not have the memory
- At least one of the first estimation unit 13 and the third estimation unit 16 generates an estimation model using the teacher data, and inputs a predetermined feature amount extracted from the monitoring waveform data for each unit to the generated estimation model. Without obtaining the estimation result, the predetermined feature amount extracted from the monitoring waveform data for each unit, and the teacher feature amount (including the combined teacher feature amount) included in the teacher difference information (including the combined teacher difference information), Are sequentially matched to identify a teacher feature amount (including a combined teacher feature amount) that matches a predetermined feature amount extracted from the waveform data for monitoring for each unit.
- At least one of the first estimator 13 and the third estimator 16 performs the process of generating the combined teacher feature value and the matching process in parallel. That is, when one summation teacher feature value is generated, collation processing is performed, and when there is no matching, another summation teacher feature value is generated. When a combined teacher feature value that matches a predetermined feature value extracted from the unit-by-unit monitoring waveform data is found, the process of generating the combined teacher feature value and the matching process are ended.
- Other configurations of the first estimation unit 13 and the third estimation unit 16 are the same as those in the first to sixth embodiments.
- the second estimation unit 14 generates an estimation model using the teacher data, and obtains an estimation result by inputting a predetermined feature amount extracted from the unit-by-unit monitoring waveform data to the generated estimation model.
- the predetermined feature amount extracted from the waveform data for monitoring for each unit and the teacher feature amount (including the combined teacher feature amount) included in the teacher data are collated in order, so that the waveform data for unit monitoring is A teacher feature amount (including a combined teacher feature amount) matching the extracted predetermined feature amount can be specified.
- the second estimation unit 14 performs the process of generating the combined teacher feature value and the matching process in parallel. That is, when one summation teacher feature value is generated, collation processing is performed, and when there is no matching, another summation teacher feature value is generated. When a combined teacher feature value that matches a predetermined feature value extracted from the unit-by-unit monitoring waveform data is found, the process of generating the combined teacher feature value and the matching process are ended.
- Other configurations of the second estimation unit 14 are the same as those in the first to sixth embodiments.
- advice for power saving can be given.
- the monitoring device 10 of the first to seventh embodiments it is possible to confirm the time change of the operating state of the electrical equipment in one day (from 0:00 to 24:00). Based on such output, it is possible to specify a time zone or the like in which the electric device is frequently used, and to give advice such as consciously reducing the use in that time.
- the timing of electrical equipment maintenance eg, cleaning of an air conditioner
- the accumulated operation time of each electrical device can be calculated by accumulating the estimation results. For example, it is possible to make a notification that prompts maintenance at a timing when the accumulated time reaches a predetermined value.
- current consumption, power consumption, voltage, measurement characteristics, and the like may change due to failure of electrical equipment or aging of some components. Therefore, for example, when such a change is detected, a notification for urging maintenance can be performed.
- advice on the use of a refrigerator can be given.
- the current consumption, the power consumption, the voltage, the measurement feature amount, and the like can be changed according to the state of loading inside the refrigerator.
- the monitoring device 10 of the first to seventh embodiments such a change can be detected. Based on this change, it is possible to notify a warning of overpacking or a reminder to increase the stockpile because the internal items are low.
- the monitoring device 10 of the first to seventh embodiments it is possible to detect whether or not the usage pattern of the electrical device is different from the usual by comparing the past estimation result history. it can. If the usage pattern of electrical equipment is different from usual, there may be some change in the service recipient (electric equipment user) (eg, illness, involvement in an incident, etc.). Therefore, in such a case, a warning can be notified to the contact information registered in advance.
- the service recipient electrical equipment user
- the user's life rhythm and the like are estimated based on the usage pattern of the electrical equipment (e.g., the usage pattern in one day). Can do. For this reason, lifestyle rhythms are improved for users with irregular lifestyle rhythms (eg, many activities at night (using many electrical devices at night), daytime activities and nighttime activities appear irregularly, etc.) Can be warned to do.
- irregular lifestyle rhythms eg, many activities at night (using many electrical devices at night), daytime activities and nighttime activities appear irregularly, etc.
- a first monitoring difference group consisting of at least one difference among at least one feature quantity extracted from each of the waveform data and the waveform data at the second timing, and each of the monitoring target electrical devices
- a difference between at least one waveform data in the current consumption, input voltage, and power consumption in the first operating state and the waveform data in the second operating state in association with each of the monitoring target electrical devices Waveform data, at least one feature amount extracted from the waveform data of the difference, and each of the waveform data in the first operating state and the waveform data in the second operating state
- the monitoring apparatus further has a memory
- At least one type of feature amount extracted from the waveform data of the difference between the waveform data of the first timing and the waveform data of the second timing in the waveform data for monitoring per unit, and the first timing A second monitoring object comprising at least one of at least one feature amount difference extracted from each of the waveform data and the waveform data at the second timing, which is different from the first monitoring difference group.
- the monitoring apparatus which further has a 3rd estimation means which estimates the change of the operating state of at least one part in the said monitoring object electric equipment based on a difference group and the said teacher difference information. 4).
- the monitoring device estimates that the power state of at least some of the monitoring target electrical devices among the monitoring target electrical devices has changed between a power ON state and a power OFF state
- the third estimating means is configured such that at least a part of the power supply states in the monitored electric equipment excluding the monitored electric equipment whose change in power supply state is estimated by the first estimating means is a power ON state and a power supply.
- the monitoring device estimates a change in power consumption of a part of the monitored electrical equipment
- the third estimating means is configured such that at least a part of the power supply states of the monitored electric appliances excluding the monitored electric appliances whose power consumption is estimated by the first estimating means are a power ON state and a power supply.
- the second estimation unit holds management information indicating an operating state of each of the monitoring target electric devices at a predetermined timing, and the monitoring target electric device estimated by the first estimation unit after the predetermined timing.
- the monitoring device further updates the management information based on a change in an operating state of the monitoring target electrical device estimated by the third estimating device after the predetermined timing. 8). 2 and the monitoring device according to any one of 3 to 7 dependent on 2,
- the storage means is associated with each of the monitored electrical devices, and is extracted from the device-specific teacher waveform data, which is at least one waveform data among current consumption, input voltage, and power consumption, and the device-specific teacher waveform data. Storing at least one of the teacher feature values in a predetermined operating state,
- the second estimation unit is operated by the first estimation unit based on the feature amount extracted from the unit-by-unit monitoring waveform data and the teacher feature amount extracted from the device-specific teacher waveform data.
- the monitoring apparatus which estimates the operation state of at least one part in the said monitoring object electric equipment which was not estimated that there existed a change of a state. 9.
- a monitoring apparatus further comprising output means for outputting an estimation result. 10.
- Computer Waveform data acquisition means for each unit for acquiring waveform data for monitoring for each unit, which is at least one waveform data among the total current consumption, the total input voltage and the total power consumption in the unit in which the electrical equipment to be monitored is installed; At least one type of feature amount extracted from the waveform data of the difference between the waveform data of the first timing and the waveform data of the second timing in the waveform data for monitoring per unit, and the first timing
- a first monitoring difference group consisting of at least one difference among at least one feature quantity extracted from each of the waveform data and the waveform data at the second timing, and each of the monitoring target electrical devices
- First estimating means for estimating a change in at least a part of the operating state of the monitored electrical equipment based on teacher difference information relating to a difference between the first operating state and the second operating state;
- Second estimation means for estimating an operating state of each of the monitoring target electrical devices based on an estimation result of the first estimation means; Program to function as.
- Said computer further A difference between at least one waveform data in the current consumption, input voltage, and power consumption in the first operating state and the waveform data in the second operating state in association with each of the monitoring target electrical devices Waveform data, at least one feature amount extracted from the waveform data of the difference, and each of the waveform data in the first operating state and the waveform data in the second operating state
- Said computer further At least one type of feature amount extracted from the waveform data of the difference between the waveform data of the first timing and the waveform data of the second timing in the waveform data for monitoring per unit, and the first timing
- a second monitoring object comprising at least one of at least one feature amount difference extracted from each of the waveform data and the waveform data at the second timing, which is different from the first monitoring difference group.
- the program for functioning as a 3rd estimation means which estimates the change of the operation state of at least one part in the said monitoring object electric equipment based on a difference group and the said teacher difference information. 10-4.
- the third estimation means at least a part of the power supply states in the monitoring target electrical equipment excluding the monitoring target electrical equipment estimated by the first estimation means for the change in power supply state is a power ON state and a power supply.
- the program which makes the said 2nd estimation means further update the said management information based on the change of the operation state of the said monitoring object electric equipment which the said 3rd estimation means estimated after the said predetermined timing. 10-8.
- the second estimation means is operated by the first estimation means based on the feature amount extracted from the unit-by-unit monitoring waveform data and the teacher feature amount extracted from the device-specific teacher waveform data.
- Said computer further A program for functioning as output means for outputting an estimation result.
- Computer A unit-by-unit waveform data acquisition step of acquiring unit-by-unit monitoring waveform data that is at least one waveform data among total current consumption, total input voltage, and total power consumption in the unit in which the electrical equipment to be monitored is installed; At least one type of feature amount extracted from the waveform data of the difference between the waveform data of the first timing and the waveform data of the second timing in the waveform data for monitoring per unit, and the first timing
- a first monitoring difference group consisting of at least one difference among at least one feature quantity extracted from each of the waveform data and the waveform data at the second timing, and each of the monitoring target electrical devices
- the monitoring method according to 11, The computer is A difference between at least one waveform data in the current consumption, input voltage, and power consumption in the first operating state and the waveform data in the second operating state in association with each of the monitoring target electrical devices Waveform data, at least one feature amount extracted from the waveform data of the difference, and each of the waveform data in the first operating state and the waveform data in the second operating state A monitoring method for storing the teacher difference information, which is at least one of at least one type of feature amount difference. 11-3.
- the computer further comprises: At least one type of feature amount extracted from the waveform data of the difference between the waveform data of the first timing and the waveform data of the second timing in the waveform data for monitoring per unit, and the first timing
- a second monitoring object comprising at least one of at least one feature amount difference extracted from each of the waveform data and the waveform data at the second timing, which is different from the first monitoring difference group.
- the first estimation step it is estimated that the power state of at least some of the monitoring target electrical devices among the monitoring target electrical devices has changed between a power ON state and a power OFF state
- the third estimation step at least a part of the power supply states in the monitoring target electrical equipment excluding the monitoring target electrical equipment in which a change in power supply state is estimated in the first estimation step is a power ON state and a power supply
- the first estimation step a change in power consumption of a part of the monitoring target electrical device is estimated
- at least a part of the power supply states of the monitoring target electric devices excluding the monitoring target electric device whose power consumption has been estimated in the first estimation step are a power ON state and a power supply
- the computer holds management information indicating an operating state of each of the monitoring target electrical devices at a predetermined timing, and the second estimation step estimates the first estimation step after the predetermined timing.
- the management information is further updated based on a change in the operating state of the monitoring target electrical device estimated in the third estimation step after the predetermined timing. 11-8. 11-2 and the monitoring method according to any one of 11-3 to 11-7 subordinate to 11-2,
- the computer is associated with each of the electrical devices to be monitored and is extracted from the instructor waveform data for each device that is at least one waveform data among current consumption, input voltage, and power consumption, and the instructor waveform data for each device.
- the operation is performed in the first estimation step based on the feature amount extracted from the unit-by-unit monitoring waveform data and the teacher feature amount extracted from the device-specific teacher waveform data.
- the computer further comprises: A monitoring method for executing an output process for outputting an estimation result.
- a monitoring device obtain monitoring waveform data for each unit, which is at least one of the total current consumption, total input voltage, and total power consumption measured by the measuring instrument installed in the unit where the monitored electrical equipment is installed.
- a relay device that transmits to the monitoring device; Having a surveillance system.
Abstract
Description
監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得手段と、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定手段と、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定手段と、
を有する監視装置が提供される。
コンピュータを、
監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得手段、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定手段、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定手段、
として機能させるためのプログラムが提供される。
コンピュータが、
監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得工程と、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定工程と、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定工程と、
を実行する監視方法が提供される。
前記監視装置と、
監視対象電気機器が設置された単位内に設置された測定器が測定した、総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得し、前記監視装置に送信する中継装置と、
を有する監視システムが提供される。
本実施形態の概要について説明する。本実施形態の監視装置10は、まず、所定のタイミングにおける監視対象電気機器各々の消費電力(稼働状態)を推定する。そして、推定した監視対象電気機器各々の消費電力(稼働状態)を示す管理情報を保持しておく。
(2) (1)の差分の波形データから抽出された少なくとも1種類の特徴量
(3) 第1の稼働状態の時の波形データ及び第2の稼働状態の時の波形データ各々から抽出された少なくとも1種類の特徴量の差分
(5) 第1のタイミングの波形データ及び第2のタイミングの波形データ各々から抽出された少なくとも1種類の特徴量の差分
例えば、監視対象電気機器すべての電源状態を電源OFFにした状態で、監視装置10は、その旨を示す入力を例えばユーザから受付ける。すると、第2の推定部14は、当該入力を受付けた時点における監視対象電気機器すべての消費電力を、消費電力0Wと推定する。当該処理は、監視装置10による監視処理を開始する最初の段階で行う場合に適している。
例えば、記憶部11は、図9又は10に示すような教師データを記憶しておく。
本実施形態は、出力部15を有する点で第1の実施形態と異なる。図16に、本実施形態の監視装置10の機能ブロック図の一例を示す。図示するように、監視装置10は、記憶部11と、単位毎波形データ取得部12と、第1の推定部13と、第2の推定部14と、出力部15とを有する。記憶部11、単位毎波形データ取得部12、第1の推定部13及び第2の推定部14の構成は第1の実施形態と同様である。なお、本実施形態の監視装置は、第1の実施形態と同様に、記憶部11を有さない構成とすることもできる(図26参照)。
本実施形態の概要について説明する。本実施形態の監視装置10は、まず、所定のタイミングにおける監視対象電気機器各々の電源状態(稼働状態)、すなわち、電源ON状態及び電源OFF状態のいずれであるかを推定する。そして、推定した監視対象電気機器各々の電源状態(稼働状態)を示す管理情報を保持しておく。
例えば、監視対象電気機器すべての電源状態を電源OFFにした状態で、監視装置10は、その旨を示す入力を例えばユーザから受付ける。すると、第1の推定部13は、当該入力を受付けた時点における監視対象電気機器すべての電源状態を、電源OFF状態と推定する。当該処理は、監視装置10による監視処理を開始する最初の段階で行う場合に適している。
他の例として、例えば、監視装置10は、所定のタイミングで、あるタイミング(例:その時点、ある日のある時刻)における監視対象電気機器各々の電源状態を示す情報の入力を、ユーザから受付ける。第1の推定部13は、入力された内容に基づいて、そのタイミングにおける監視対象電気機器各々の電源状態を推定する。
本実施形態の概要について説明する。本実施形態の監視装置10は、監視対象電気機器の消費電力の変化(稼働状態の変化)を監視する。その後、消費電力の変化(稼働状態の変化)があると推定されなかった監視対象電気機器各々の各消費電力に対応した教師特徴量、及び、それらから生成される合算教師特徴量を利用して、これらの監視対象電気機器各々の消費電力を推定する。なお、変化があると推定された監視対象電気機器の稼働状態は、変化後の電力を消費中であると推定される。
本実施形態の概要について説明する。本実施形態の監視装置10は、監視対象電気機器の電源状態の変化(稼働状態の変化)を監視する。その後、電源状態の変化があると推定され、かつ、変化後の状態が電源OFF状態であると推定された監視対象電気機器を除く監視対象電気機器を処理対象とし、各々の各消費電力に対応した教師特徴量、及び、それらから生成される合算教師特徴量を利用して、これらの監視対象電気機器各々の消費電力を推定する。なお、処理対象外の監視対象電気機器は、例えば消費電力0Wと推定することができる。
本実施形態では、第1乃至第5の実施形態における差分情報を利用した稼働状態の変化(電源状態の変化、消費電力の変化)の監視を、複数のステップに分けて実行する。
本実施形態の監視装置10の機能ブロック図の一例は、図2、16及び24と同様である。記憶部11、単位毎波形データ取得部12、出力部15の構成は第1乃至第6の実施形態と同様である。なお、本実施形態の監視装置は、第1乃至第6の実施形態と同様に、記憶部11を有さない構成とすることもできる(図21参照)。
1. 監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得手段と、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定手段と、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定手段と、
を有する監視装置。
2. 1に記載の監視装置において、
前記監視対象電気機器各々に対応付けて、第1の稼働状態の時の消費電流、入力電圧及び消費電力の中の少なくとも1つの波形データと第2の稼働状態の時の前記波形データとの差分の波形データ、当該差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1の稼働状態の時の前記波形データ及び前記第2の稼働状態の時の前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つである前記教師差分情報を記憶する記憶手段をさらに有する監視装置。
3. 1又は2に記載の監視装置において、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなり、前記第1の監視用差分グループと異なる第2の監視用差分グループ、及び、前記教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第3の推定手段をさらに有する監視装置。
4. 3に記載の監視装置において、
前記第1の推定手段は、前記監視対象電気機器の中の少なくとも一部の前記監視対象電気機器の電源状態が電源ON状態及び電源OFF状態の間で変化したことを推定し、
前記第3の推定手段は、前記第1の推定手段により電源状態の変化を推定された前記監視対象電気機器を除く前記監視対象電気機器の中の少なくとも一部の電源状態が電源ON状態及び電源OFF状態の間で変化したこと、又は、消費電力の変化を推定する監視装置。
5. 3に記載の監視装置において、
前記第1の推定手段は、前記監視対象電気機器の中の一部の消費電力の変化を推定し、
前記第3の推定手段は、前記第1の推定手段により消費電力の変化を推定された前記監視対象電気機器を除く前記監視対象電気機器の中の少なくとも一部の電源状態が電源ON状態及び電源OFF状態の間で変化したこと、又は、消費電力の変化を推定する監視装置。
6. 1から5のいずれかに記載の監視装置において、
前記第2の推定手段は、所定のタイミングにおける前記監視対象電気機器各々の稼働状態を示す管理情報を保持し、前記所定のタイミング以降に前記第1の推定手段が推定した前記監視対象電気機器の稼働状態の変化に基づいて、前記管理情報を更新する監視装置。
7. 3に従属する6に記載の監視装置において、
前記第2の推定手段は、前記所定のタイミング以降に前記第3の推定手段が推定した前記監視対象電気機器の稼働状態の変化に基づいて、前記管理情報をさらに更新する監視装置。
8. 2、及び、2に従属する3から7のいずれかに記載の監視装置において、
前記記憶手段は、前記監視対象電気機器各々に対応付けて、消費電流、入力電圧及び消費電力の中の少なくとも1つの波形データである機器毎教師波形データ、及び、前記機器毎教師波形データから抽出される所定の稼働状態時の教師特徴量の少なくとも一方を記憶し、
前記第2の推定手段は、前記単位毎監視用波形データから抽出された特徴量、及び、前記機器毎教師波形データから抽出された前記教師特徴量に基づいて、前記第1の推定手段により稼働状態の変化があると推定されなかった前記監視対象電気機器の中の少なくとも一部の稼働状態を推定する監視装置。
9. 1から8のいずれかに記載の監視装置において、
推定結果を出力する出力手段をさらに有する監視装置。
10. コンピュータを、
監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得手段、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定手段、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定手段、
として機能させるためのプログラム。
10-2. 1に記載のプログラムにおいて、
前記コンピュータを、さらに、
前記監視対象電気機器各々に対応付けて、第1の稼働状態の時の消費電流、入力電圧及び消費電力の中の少なくとも1つの波形データと第2の稼働状態の時の前記波形データとの差分の波形データ、当該差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1の稼働状態の時の前記波形データ及び前記第2の稼働状態の時の前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つである前記教師差分情報を記憶する記憶手段として機能させるためのプログラム。
10-3. 10又は10-2に記載のプログラムにおいて、
前記コンピュータを、さらに、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなり、前記第1の監視用差分グループと異なる第2の監視用差分グループ、及び、前記教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第3の推定手段として機能させるためのプログラム。
10-4. 10-3に記載のプログラムにおいて、
前記第1の推定手段に、前記監視対象電気機器の中の少なくとも一部の前記監視対象電気機器の電源状態が電源ON状態及び電源OFF状態の間で変化したことを推定させ、
前記第3の推定手段に、前記第1の推定手段により電源状態の変化を推定された前記監視対象電気機器を除く前記監視対象電気機器の中の少なくとも一部の電源状態が電源ON状態及び電源OFF状態の間で変化したこと、又は、消費電力の変化を推定させるプログラム。
10-5. 10-3に記載のプログラムにおいて、
前記第1の推定手段に、前記監視対象電気機器の中の一部の消費電力の変化を推定させ、
前記第3の推定手段に、前記第1の推定手段により消費電力の変化を推定された前記監視対象電気機器を除く前記監視対象電気機器の中の少なくとも一部の電源状態が電源ON状態及び電源OFF状態の間で変化したこと、又は、消費電力の変化を推定させるプログラム。
10-6. 10から10-5のいずれかに記載のプログラムにおいて、
前記第2の推定手段に、所定のタイミングにおける前記監視対象電気機器各々の稼働状態を示す管理情報を保持させ、前記所定のタイミング以降に前記第1の推定手段が推定した前記監視対象電気機器の稼働状態の変化に基づいて、前記管理情報を更新させるプログラム。
10-7. 10-3に従属する10-6に記載のプログラムにおいて、
前記第2の推定手段に、前記所定のタイミング以降に前記第3の推定手段が推定した前記監視対象電気機器の稼働状態の変化に基づいて、前記管理情報をさらに更新させるプログラム。
10-8. 10-2、及び、10-2に従属する10-3から10-7のいずれかに記載のプログラムにおいて、
前記記憶手段に、前記監視対象電気機器各々に対応付けて、消費電流、入力電圧及び消費電力の中の少なくとも1つの波形データである機器毎教師波形データ、及び、前記機器毎教師波形データから抽出される所定の稼働状態時の教師特徴量の少なくとも一方を記憶させ、
前記第2の推定手段に、前記単位毎監視用波形データから抽出された特徴量、及び、前記機器毎教師波形データから抽出された前記教師特徴量に基づいて、前記第1の推定手段により稼働状態の変化があると推定されなかった前記監視対象電気機器の中の少なくとも一部の稼働状態を推定させるプログラム。
10-9. 10から10-8のいずれかに記載のプログラムにおいて、
前記コンピュータを、さらに、
推定結果を出力する出力手段として機能させるためのプログラム。
11. コンピュータが、
監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得工程と、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定工程と、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定工程と、
を実行する監視方法。
11-2. 11に記載の監視方法において、
前記コンピュータが、
前記監視対象電気機器各々に対応付けて、第1の稼働状態の時の消費電流、入力電圧及び消費電力の中の少なくとも1つの波形データと第2の稼働状態の時の前記波形データとの差分の波形データ、当該差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1の稼働状態の時の前記波形データ及び前記第2の稼働状態の時の前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つである前記教師差分情報を記憶しておく監視方法。
11-3. 11又は11-2に記載の監視方法において、
前記コンピュータが、さらに、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなり、前記第1の監視用差分グループと異なる第2の監視用差分グループ、及び、前記教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第3の推定工程を実行する監視方法。
11-4. 11-3に記載の監視方法において、
前記第1の推定工程では、前記監視対象電気機器の中の少なくとも一部の前記監視対象電気機器の電源状態が電源ON状態及び電源OFF状態の間で変化したことを推定し、
前記第3の推定工程では、前記第1の推定工程で電源状態の変化を推定された前記監視対象電気機器を除く前記監視対象電気機器の中の少なくとも一部の電源状態が電源ON状態及び電源OFF状態の間で変化したこと、又は、消費電力の変化を推定する監視方法。
11-5. 11-3に記載の監視方法において、
前記第1の推定工程では、前記監視対象電気機器の中の一部の消費電力の変化を推定し、
前記第3の推定工程では、前記第1の推定工程で消費電力の変化を推定された前記監視対象電気機器を除く前記監視対象電気機器の中の少なくとも一部の電源状態が電源ON状態及び電源OFF状態の間で変化したこと、又は、消費電力の変化を推定する監視方法。
11-6. 11から11-5のいずれかに記載の監視方法において、
前記コンピュータは、所定のタイミングにおける前記監視対象電気機器各々の稼働状態を示す管理情報を保持しておき、前記第2の推定工程では、前記所定のタイミング以降に前記第1の推定工程で推定した前記監視対象電気機器の稼働状態の変化に基づいて、前記管理情報を更新する監視方法。
11-7. 11-3に従属する11-6に記載の監視方法において、
前記第2の推定工程では、前記所定のタイミング以降に前記第3の推定工程で推定した前記監視対象電気機器の稼働状態の変化に基づいて、前記管理情報をさらに更新する監視方法。
11-8. 11-2、及び、11-2に従属する11-3から11-7のいずれかに記載の監視方法において、
前記コンピュータは、前記監視対象電気機器各々に対応付けて、消費電流、入力電圧及び消費電力の中の少なくとも1つの波形データである機器毎教師波形データ、及び、前記機器毎教師波形データから抽出される所定の稼働状態時の教師特徴量の少なくとも一方を記憶しておき、
前記第2の推定工程では、前記単位毎監視用波形データから抽出された特徴量、及び、前記機器毎教師波形データから抽出された前記教師特徴量に基づいて、前記第1の推定工程で稼働状態の変化があると推定されなかった前記監視対象電気機器の中の少なくとも一部の稼働状態を推定する監視方法。
11-9. 11から11-8のいずれかに記載の監視方法において、
前記コンピュータが、さらに、
推定結果を出力する出力工程を実行する監視方法。
12. 1から9のいずれかに記載の監視装置と、
監視対象電気機器が設置された単位内に設置された測定器が測定した、総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得し、前記監視装置に送信する中継装置と、
を有する監視システム。
Claims (12)
- 監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得手段と、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定手段と、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定手段と、
を有する監視装置。 - 請求項1に記載の監視装置において、
前記監視対象電気機器各々に対応付けて、第1の稼働状態の時の消費電流、入力電圧及び消費電力の中の少なくとも1つの波形データと第2の稼働状態の時の前記波形データとの差分の波形データ、当該差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1の稼働状態の時の前記波形データ及び前記第2の稼働状態の時の前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つである前記教師差分情報を記憶する記憶手段をさらに有する監視装置。 - 請求項1又は2に記載の監視装置において、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなり、前記第1の監視用差分グループと異なる第2の監視用差分グループ、及び、前記教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第3の推定手段をさらに有する監視装置。 - 請求項3に記載の監視装置において、
前記第1の推定手段は、前記監視対象電気機器の中の少なくとも一部の前記監視対象電気機器の電源状態が電源ON状態及び電源OFF状態の間で変化したことを推定し、
前記第3の推定手段は、前記第1の推定手段により電源状態の変化を推定された前記監視対象電気機器を除く前記監視対象電気機器の中の少なくとも一部の電源状態が電源ON状態及び電源OFF状態の間で変化したこと、又は、消費電力の変化を推定する監視装置。 - 請求項3に記載の監視装置において、
前記第1の推定手段は、前記監視対象電気機器の中の一部の消費電力の変化を推定し、
前記第3の推定手段は、前記第1の推定手段により消費電力の変化を推定された前記監視対象電気機器を除く前記監視対象電気機器の中の少なくとも一部の電源状態が電源ON状態及び電源OFF状態の間で変化したこと、又は、消費電力の変化を推定する監視装置。 - 請求項1から5のいずれか1項に記載の監視装置において、
前記第2の推定手段は、所定のタイミングにおける前記監視対象電気機器各々の稼働状態を示す管理情報を保持し、前記所定のタイミング以降に前記第1の推定手段が推定した前記監視対象電気機器の稼働状態の変化に基づいて、前記管理情報を更新する監視装置。 - 請求項3に従属する請求項6に記載の監視装置において、
前記第2の推定手段は、前記所定のタイミング以降に前記第3の推定手段が推定した前記監視対象電気機器の稼働状態の変化に基づいて、前記管理情報をさらに更新する監視装置。 - 請求項2、及び、請求項2に従属する請求項3から7のいずれか1項に記載の監視装置において、
前記記憶手段は、前記監視対象電気機器各々に対応付けて、消費電流、入力電圧及び消費電力の中の少なくとも1つの波形データである機器毎教師波形データ、及び、前記機器毎教師波形データから抽出される所定の稼働状態時の教師特徴量の少なくとも一方を記憶し、
前記第2の推定手段は、前記単位毎監視用波形データから抽出された特徴量、及び、前記機器毎教師波形データから抽出された前記教師特徴量に基づいて、前記第1の推定手段により稼働状態の変化があると推定されなかった前記監視対象電気機器の中の少なくとも一部の稼働状態を推定する監視装置。 - 請求項1から8のいずれか1項に記載の監視装置において、
推定結果を出力する出力手段をさらに有する監視装置。 - コンピュータを、
監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得手段、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定手段、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定手段、
として機能させるためのプログラム。 - コンピュータが、
監視対象電気機器が設置された単位内における総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得する単位毎波形データ取得工程と、
前記単位毎監視用波形データの中の第1のタイミングの波形データと第2のタイミングの波形データとの差分の波形データから抽出された少なくとも1種類の特徴量、及び、前記第1のタイミングの前記波形データ及び前記第2のタイミングの前記波形データ各々から抽出された少なくとも1種類の特徴量の差分の中の少なくとも1つからなる第1の監視用差分グループ、及び、前記監視対象電気機器各々の第1の稼働状態時と第2の稼働状態時との差分に関する教師差分情報に基づいて、前記監視対象電気機器の中の少なくとも一部の稼働状態の変化を推定する第1の推定工程と、
前記第1の推定手段の推定結果に基づいて、前記監視対象電気機器各々の稼働状態を推定する第2の推定工程と、
を実行する監視方法。 - 請求項1から9のいずれか1項に記載の監視装置と、
監視対象電気機器が設置された単位内に設置された測定器が測定した、総消費電流、総入力電圧及び総消費電力の中の少なくとも1つの波形データである単位毎監視用波形データを取得し、前記監視装置に送信する中継装置と、
を有する監視システム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/300,512 US10401403B2 (en) | 2014-03-31 | 2015-01-23 | Monitoring device, monitoring system, monitoring method, and non-transitory storage medium |
JP2016511412A JP6583265B2 (ja) | 2014-03-31 | 2015-01-23 | 監視装置、監視システム、監視方法及びプログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014-071122 | 2014-03-31 | ||
JP2014071122 | 2014-03-31 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015151558A1 true WO2015151558A1 (ja) | 2015-10-08 |
Family
ID=54239901
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2015/051788 WO2015151558A1 (ja) | 2014-03-31 | 2015-01-23 | 監視装置、監視システム、監視方法及びプログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US10401403B2 (ja) |
JP (1) | JP6583265B2 (ja) |
WO (1) | WO2015151558A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPWO2015151789A1 (ja) * | 2014-03-31 | 2017-04-13 | 日本電気株式会社 | 教師データ生成装置、電気機器監視システム、教師データ生成方法及びプログラム |
WO2018101363A1 (ja) * | 2016-11-30 | 2018-06-07 | 日本電気株式会社 | 状態推定装置と方法とプログラム |
JPWO2021260922A1 (ja) * | 2020-06-26 | 2021-12-30 | ||
WO2022113201A1 (ja) * | 2020-11-25 | 2022-06-02 | 三菱電機ビルテクノサービス株式会社 | 消費電力監視装置及びプログラム |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10175276B2 (en) | 2014-11-26 | 2019-01-08 | Sense Labs, Inc. | Identifying and categorizing power consumption with disaggregation |
US9152737B1 (en) | 2014-11-26 | 2015-10-06 | Sense Labs, Inc. | Providing notifications to a user |
US20180254661A1 (en) * | 2015-09-03 | 2018-09-06 | Nec Corporation | Information output apparatus, and information output method |
US10393779B2 (en) * | 2016-03-31 | 2019-08-27 | Oracle International Corporation | Systems and methods for providing statistical dynamic meter data validation |
US9699529B1 (en) * | 2017-02-22 | 2017-07-04 | Sense Labs, Inc. | Identifying device state changes using power data and network data |
US9800958B1 (en) | 2017-02-22 | 2017-10-24 | Sense Labs, Inc. | Training power models using network data |
US10750252B2 (en) * | 2017-02-22 | 2020-08-18 | Sense Labs, Inc. | Identifying device state changes using power data and network data |
US10740691B2 (en) | 2018-10-02 | 2020-08-11 | Sense Labs, Inc. | Identifying devices connected to a smart plug |
US11768228B2 (en) | 2019-07-11 | 2023-09-26 | Sense Labs, Inc. | Current transformer with calibration information |
USD944731S1 (en) | 2019-07-11 | 2022-03-01 | Sense Labs, Inc. | Electrical current sensor |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006353005A (ja) * | 2005-06-16 | 2006-12-28 | Sanyo Electric Co Ltd | ホームネットワークシステム |
JP2013009500A (ja) * | 2011-06-24 | 2013-01-10 | Fujitsu Ltd | 電力管理装置 |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3403368B2 (ja) | 1999-02-01 | 2003-05-06 | 財団法人電力中央研究所 | 電気機器モニタリングシステム及び動作異常警報システム |
AUPQ113799A0 (en) * | 1999-06-22 | 1999-07-15 | University Of Queensland, The | A method and device for measuring lymphoedema |
JP4454001B2 (ja) | 2001-06-19 | 2010-04-21 | 財団法人電力中央研究所 | 遠隔電気機器監視方法及び装置並びにそれを利用した消費電力推定方法及び装置 |
JP4433890B2 (ja) | 2004-06-04 | 2010-03-17 | 三菱電機株式会社 | 電気機器稼動状態推定システムおよび電気機器稼動状態推定用データベース構築方法 |
US7308193B2 (en) * | 2006-02-28 | 2007-12-11 | Richard Halsall | Non-metallic heating element for use in a fluid heater |
JP4565511B2 (ja) | 2006-08-02 | 2010-10-20 | 国立大学法人名古屋大学 | 電気機器稼働状態推定システム |
US7973387B2 (en) * | 2007-06-08 | 2011-07-05 | Continental Automotive Systems Us, Inc. | Insulated gate bipolar transistor |
JP5007310B2 (ja) | 2009-01-23 | 2012-08-22 | 日本電信電話株式会社 | 電力消費量推定装置および電力消費量推定方法 |
JP5010011B2 (ja) | 2010-04-23 | 2012-08-29 | 三菱電機株式会社 | 消費電力測定システム及び消費電力測定方法 |
US9464820B2 (en) * | 2013-03-15 | 2016-10-11 | Marchi Thermal Systems | Surface mounted heater with universal seal fitting |
US10172387B2 (en) * | 2013-08-28 | 2019-01-08 | Rai Strategic Holdings, Inc. | Carbon conductive substrate for electronic smoking article |
US9684025B2 (en) * | 2013-11-26 | 2017-06-20 | The United States Of America As Represented By The Secretary Of The Navy | DUT continuity test with only digital IO structures apparatus and methods associated thereof |
US9995781B2 (en) * | 2014-08-25 | 2018-06-12 | Texas Instruments Incorporated | Ground fault detection for PCB and isolation grounds |
JP6162679B2 (ja) * | 2014-12-19 | 2017-07-12 | ファナック株式会社 | コモン信号の故障箇所を検出するマトリクス回路 |
-
2015
- 2015-01-23 JP JP2016511412A patent/JP6583265B2/ja active Active
- 2015-01-23 WO PCT/JP2015/051788 patent/WO2015151558A1/ja active Application Filing
- 2015-01-23 US US15/300,512 patent/US10401403B2/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006353005A (ja) * | 2005-06-16 | 2006-12-28 | Sanyo Electric Co Ltd | ホームネットワークシステム |
JP2013009500A (ja) * | 2011-06-24 | 2013-01-10 | Fujitsu Ltd | 電力管理装置 |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPWO2015151789A1 (ja) * | 2014-03-31 | 2017-04-13 | 日本電気株式会社 | 教師データ生成装置、電気機器監視システム、教師データ生成方法及びプログラム |
US10466283B2 (en) | 2014-03-31 | 2019-11-05 | Nec Corporation | Training data generation device, electrical device monitoring system, training data generation method, and non-transitory storage medium |
WO2018101363A1 (ja) * | 2016-11-30 | 2018-06-07 | 日本電気株式会社 | 状態推定装置と方法とプログラム |
JPWO2021260922A1 (ja) * | 2020-06-26 | 2021-12-30 | ||
WO2021260922A1 (ja) * | 2020-06-26 | 2021-12-30 | 三菱電機株式会社 | データ量十分性判定装置、データ量十分性判定方法、データ量十分性判定プログラム、学習モデル生成システム、学習済みの学習モデル生成方法、及び学習済みの学習モデル生成プログラム |
JP7211562B2 (ja) | 2020-06-26 | 2023-01-24 | 三菱電機株式会社 | データ量十分性判定装置、データ量十分性判定方法、データ量十分性判定プログラム、学習モデル生成システム、学習済みの学習モデル生成方法、及び学習済みの学習モデル生成プログラム |
WO2022113201A1 (ja) * | 2020-11-25 | 2022-06-02 | 三菱電機ビルテクノサービス株式会社 | 消費電力監視装置及びプログラム |
JP7442678B2 (ja) | 2020-11-25 | 2024-03-04 | 三菱電機ビルソリューションズ株式会社 | 消費電力監視装置及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
US20170176503A1 (en) | 2017-06-22 |
JPWO2015151558A1 (ja) | 2017-04-13 |
US10401403B2 (en) | 2019-09-03 |
JP6583265B2 (ja) | 2019-10-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6583265B2 (ja) | 監視装置、監視システム、監視方法及びプログラム | |
JP6958599B2 (ja) | 監視装置、監視システム、監視方法及びプログラム | |
JP6232020B2 (ja) | 電力需要の管理機能を有するサーバ、通信機器、システムおよび電力使用管理方法 | |
WO2015008645A1 (ja) | 監視装置、監視方法及びプログラム | |
JP6724922B2 (ja) | 教師データ提供装置、推定装置、推定システム、教師データ提供方法、推定方法、及び、プログラム | |
JP6465106B2 (ja) | 教師データ生成装置、電気機器監視システム、教師データ生成方法及びプログラム | |
JP5520807B2 (ja) | 住宅用電気機器メンテナンス管理装置及び住宅用電気機器メンテナンスシステム | |
WO2015139125A1 (en) | System and method for monitoring, analyzing and acting upon electricity patterns | |
US20150355246A1 (en) | Apparatus, server, system and method for energy measuring | |
CN102713962A (zh) | 节能诊断系统 | |
JP6547631B2 (ja) | 監視装置、監視システム、監視方法、補正情報作成装置、補正情報作成方法及びプログラム | |
WO2017038364A1 (ja) | 情報出力装置、情報出力方法、及び、プログラム | |
JP6597606B2 (ja) | 監視システム、監視機器、サーバ、監視機器の動作方法、サーバの動作方法、及び、プログラム | |
JP2015102526A (ja) | 電力推定装置及び電力推定方法 | |
JP2015021775A (ja) | 監視装置、監視方法及びプログラム | |
JP5734157B2 (ja) | 設備制御システム、電力管理システム、設備制御装置、及び設備制御方法 | |
WO2021214533A1 (en) | Device and method for auditing electrical energy | |
WO2016084904A1 (ja) | 電力管理装置、電力管理方法、及び、プログラム | |
JP6062289B2 (ja) | 消費電力監視システム | |
JP2016095583A (ja) | 防犯情報処理装置 | |
JP2017078956A (ja) | 統合管理装置、統合管理システム、及び、管理方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15772751 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2016511412 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15300512 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 15772751 Country of ref document: EP Kind code of ref document: A1 |