WO2015008645A1 - 監視装置、監視方法及びプログラム - Google Patents
監視装置、監視方法及びプログラム Download PDFInfo
- Publication number
- WO2015008645A1 WO2015008645A1 PCT/JP2014/068068 JP2014068068W WO2015008645A1 WO 2015008645 A1 WO2015008645 A1 WO 2015008645A1 JP 2014068068 W JP2014068068 W JP 2014068068W WO 2015008645 A1 WO2015008645 A1 WO 2015008645A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- value
- time
- time point
- state
- Prior art date
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims description 121
- 230000008859 change Effects 0.000 claims description 196
- 230000008569 process Effects 0.000 claims description 70
- 238000005259 measurement Methods 0.000 claims description 66
- 238000012806 monitoring device Methods 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 28
- 239000000284 extract Substances 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000000926 separation method Methods 0.000 description 25
- 238000000605 extraction Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 17
- 238000001514 detection method Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000010923 batch production Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R21/00—Arrangements for measuring electric power or power factor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
- Y04S20/20—End-user application control systems
- Y04S20/242—Home appliances
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/10—Energy trading, including energy flowing from end-user application to grid
Definitions
- the present invention relates to a monitoring device, a monitoring method, and a program.
- HEMS Home Energy Management System
- Patent Document 1 discloses a technique for grasping the power consumption of an individual electric device by providing a dedicated power consumption measuring device for the individual electric device.
- Patent Documents 2 and 3 disclose techniques for estimating the operating state of an electric device without directly measuring the power consumption of the individual electric device. Specifically, each electrical device that has been held in advance by installing a measurement sensor that measures characteristic quantities such as power supply current, power supply voltage, or calculated values such as statistics obtained from them on a power supply trunk such as a switchboard A technique for estimating which electrical device is in operation using the characteristic amount (reference information) during operation of the sensor and the measurement result of the measurement sensor is disclosed.
- Patent Document 4 discloses a technique for generating a feature amount (reference information) necessary for estimating the operating state of each individual electric device as described above. Specifically, a technique is disclosed in which electric devices are operated one by one, predetermined data (current consumption, etc.) are individually measured, and feature amounts are extracted from the measured data of each electric device and stored. .
- Patent Document 5 discloses a technique for accurately detecting the operating state of an electric device without requiring learning of a combination of the operating states of the electric device.
- Patent Document 6 discloses a technique for managing the specification of an electric device in use and the usage state of the electric device without changing or adding functions to the electric device.
- Patent Document 7 mechanically extracts classification feature values that statistically match the operator's classification intention by a general procedure simply by the operator specifying the global intention for classification. Techniques for disclosing are disclosed.
- JP 2007-225374 A Japanese Patent No. 3403368 Japanese Patent No. 4556511 Japanese Patent No. 4433890 JP 2012-189526 A JP 2004-222375 A JP-A-4-273590
- the first technique the technique for estimating the operating state of the electrical equipment
- the reference data In the case of the first technology, it is necessary to prepare in advance the feature values (reference data) of each electric device and the feature values (reference data) when a plurality of electric devices are operating.
- the reference data prepared in advance is different for each home, store, etc. For this reason, reference data cannot be stored in the system in advance from the shipping stage.
- the reference data needs to be customized for each home or store. Conventionally, there has been no technique for efficiently creating such reference data and storing it in the system.
- Patent Document 4 discloses means for individually performing measurement processing on a plurality of electric devices, extracting feature amounts from the measured data, and storing them in the system.
- users at homes and stores may find it troublesome to perform such measurement processing.
- As a means for solving the inconvenience there may be a means in which a provider who provides the system of the first technology visits each home or each store, performs measurement processing, and stores it in the system.
- the type and number of electrical devices used in each home, each store, etc. vary depending on replacement. In each case, it is inefficient for the system provider to go to each home or each store and perform the measurement process. None of Patent Documents 1 to 7 discloses means for solving such a problem.
- the present invention compares a feature quantity (reference data) of each of a plurality of electrical devices and / or a feature quantity (reference data) obtained by combining them with a feature quantity extracted from measured waveform data. It is an object of the present invention to provide a new technique for creating reference data (teacher data) used in a technique for estimating an operating state of an electrical device.
- Acquisition means for acquiring first time-series data that is time-series data of measured values and / or feature quantities related to the electrical equipment group; Any one of a data value at a first time point in the first time series data and a statistical value of a plurality of data values from a time point going back a predetermined time before the first time point to the first time point.
- the electrical device corresponding to the pre-change data value and the post-change data value satisfying the predetermined condition Registration / update means for storing the feature quantity extracted from any of the waveform data of the total current consumption, total power consumption and total input voltage of the group in the feature quantity storage means;
- a monitoring device is provided.
- Computer An acquisition step of acquiring first time-series data which is time-series data of measured values and / or feature quantities related to the electrical equipment group; Any one of a data value at a first time point in the first time series data and a statistical value of a plurality of data values from a time point going back a predetermined time before the first time point to the first time point.
- the electrical device corresponding to the pre-change data value and the post-change data value satisfying the predetermined condition A registration / update step of storing in the feature amount storage means the feature amount extracted from any of the waveform data of the total current consumption, total power consumption and total input voltage of the group;
- Computer An acquisition means for acquiring first time-series data that is time-series data of measured values and / or feature quantities related to the electrical equipment group; Any one of a data value at a first time point in the first time series data and a statistical value of a plurality of data values from a time point going back a predetermined time before the first time point to the first time point.
- the electrical device corresponding to the pre-change data value and the post-change data value satisfying the predetermined condition Registration / update means for storing the feature quantity extracted from any of the waveform data of the total current consumption, total power consumption and total input voltage of the group in the feature quantity storage means;
- a program for functioning as a server is provided.
- the feature amount (reference data) of each of the plurality of electrical devices and / or the feature amount (reference data) obtained by combining them is compared with the feature amount extracted from the measured waveform data.
- a new technique for creating reference data (teacher data) used in the technique for estimating the operating state of an electrical device is realized.
- the apparatus of this embodiment and each unit included in the apparatus include a CPU (Central Processing Unit), a memory, and a program loaded in the memory (a program stored in the memory from the stage of shipping the apparatus in advance).
- a CPU Central Processing Unit
- a memory a program loaded in the memory (a program stored in the memory from the stage of shipping the apparatus in advance).
- CDs Compact Discs
- other storage media and programs downloaded from servers on the Internet
- storage units such as hard disks for storing the programs, and network connection interfaces, hardware and software Realized by any combination of It will be understood by those skilled in the art that there are various modifications to the implementation method and apparatus.
- 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, and other devices that are wired and / or wirelessly connected to each other via a bus 6A.
- It includes an input / output interface (I / F) 4A for communication, an auxiliary storage device 5A such as a hard disk or a portable storage medium, and the like.
- the input / output I / F 4 may be connected to a user interface device such as a display device or an input device, or may be connected to another device, or a network such as the Internet or a LAN (Local Area Network). It may be connected.
- each device is described as being realized by one device, but the means for realizing it is not limited to this. That is, it may be a physically separated configuration or a logically separated configuration.
- the monitoring apparatus includes a feature amount (reference data) of each of a plurality of electrical devices held in advance and / or a feature amount (reference data) obtained by combining them, and measured current consumption and power consumption.
- the reference data (teacher data) used in the technology for estimating the operating state of the electrical equipment by comparing with the feature quantity extracted from the waveform data such as the input voltage is the waveform data ( (Example: current consumption, power consumption, input voltage, etc.) Details will be described below.
- FIG. 2 shows an example of a functional block diagram of the present embodiment.
- the monitoring apparatus 100 includes an acquisition unit 101, a registration / update unit 102, and a feature amount storage unit 103.
- the feature amount storage unit 103 includes at least one of a state feature amount storage unit 104 and a device-specific feature amount storage unit 105.
- a state feature amount storage unit 104 includes at least one of a state feature amount storage unit 104 and a device-specific feature amount storage unit 105.
- the acquisition unit 101 acquires first time-series data that is time-series data of measurement values and / or feature amounts related to the electrical equipment group.
- the electrical device group only needs to be able to measure at least the total current consumption, the total power consumption, and the total input voltage.
- the electrical device group may be a plurality of electrical devices that receive power supply through one distribution board. It may be a plurality of electrical devices that receive power supply via an outlet, may be a plurality of electrical devices that receive power supply via a single table tap, or may be other units Good.
- the measured value can be changed by a change in one operating state in the electrical equipment group (eg, switching of power ON / OFF, etc.), for example, the total current consumption, the total power consumption, the total power consumption of the electrical equipment group.
- the temperature, heat quantity, etc. of distribution boards, outlets, table taps, etc. that distribute power to the input voltage and electrical equipment group can be considered.
- the first time-series data composed of such measurement values can be obtained by installing a predetermined measurement device on, for example, a distribution board, an outlet, a table tap or the like and using the measurement device.
- the feature amount is extracted from the waveform data of any of the total current consumption, total power consumption, and total input voltage of the electrical equipment group.
- the feature amount is the frequency intensity / phase (harmonic component), phase, change in current consumption, average value, peak value, effective value, crest factor, waveform rate, current change convergence time, energization time, It may be the peak position, the time difference between the peak position of the power supply voltage and the peak position of the current consumption, the power factor, or the like.
- the first time-series data composed of such feature amounts is, for example, a predetermined measuring device is installed on a distribution board, an outlet, a table tap, etc., and predetermined waveform data is acquired using the measuring device, It is obtained by extracting a predetermined feature amount from the waveform data.
- the registration / update unit 102 includes a data value at the first time point in the first time-series data, and a statistical value of a plurality of data values from a time point that goes back a predetermined time before the first time point to the first time point.
- a data value before state change, a data value at a second time after the first time, and a plurality of data from the second time to a time after a predetermined time from the second time The data value before the state change and the data value after the state change satisfying a predetermined value that is the difference value with the data value after the state change which is one of the statistical values of the values are specified in the first time-series data.
- the registration / update unit 102 uses waveform data of any one of the total current consumption, the total power consumption, and the total input voltage of the electrical device group corresponding to the pre-state change data value and the post-state change data value satisfying a predetermined condition.
- the extracted feature quantity is stored in the feature quantity storage unit 103. Details will be described below.
- FIG. 3 shows the first time series data. Data at each time point is schematically shown by black circles. Each data is time-series data at time t intervals. The data on the left side of the figure is the earlier measured timing.
- the data at the first time point shown in the figure is any one piece of data included in the first time series data.
- the data at the second time point is data located behind the data at the first time point in the first time-series data (eg, one backward).
- the data at the first time point and the data at the second time point may be temporally adjacent to each other in the first time-series data.
- a plurality of data A are a plurality of data from a time point that goes back a predetermined time (design matter) before the first time point to the first time point.
- the plurality of data B is a plurality of data from the second time point to a time point advanced after a predetermined time (design matter) from the second time point.
- Data before state change is data at the first time point or a plurality of data A.
- the “data after state change” is data at the second time point or a plurality of data B.
- the data value at the first time point is the “data value before the state change”.
- the data before the state change is a plurality of data A
- the statistical value of the values of the plurality of data A is the “data value before the state change”.
- the statistical value can be an average value, a median value, a mode value, or the like.
- the data value at the second time point is “data value after state change”.
- the data after state change is a plurality of data B
- the statistical value of the values of the plurality of data B is “data value after state change”.
- the statistical value can be an average value, a median value, a mode value, or the like.
- the following four patterns can be considered as a combination of the data value before the state change and the data value after the state change.
- Data value at the first time point, data value at the second time point data value at the first time point, statistical value of the plurality of data B values
- the registration / update unit 102 specifies, in the first time-series data, the data before the state change and the data after the state change where the difference value between the data value before the state change and the data value after the state change satisfies the predetermined condition.
- the predetermined condition is, for example, that the absolute value of the difference value is greater than or equal to a predetermined threshold (or greater than the predetermined threshold).
- the threshold value may be set in advance.
- the boundary between the first time point and the second time point when the measured value or the feature value is changed by a predetermined level (predetermined threshold value) or more can be determined as a boundary where the operating state of the electric device has changed.
- predetermined threshold value By appropriately setting the predetermined threshold value, it is possible to detect a boundary or the like when the power supply of the electric device is switched on / off.
- the influence of the noise component can be reduced compared to the case where the data value at the first time point is used. As a result, it is possible to improve the accuracy of detecting the boundary where the operating state of the electric device has changed (the boundary between the power ON / OFF switching).
- the post-change data value is a statistical value of a plurality of data B values
- the influence of the noise component can be reduced compared to the case where the data value at the second time point is used. As a result, it is possible to improve the accuracy of detecting the boundary where the operating state of the electric device has changed (the boundary between the power ON / OFF switching).
- the registration / update unit 102 analyzes the first time-series data and identifies the timing at which the operating state of the electrical device has changed, the timing (the data value before the state change and the data value after the state change satisfying the predetermined condition)
- the feature quantity extracted from any one of the waveform data of the total current consumption, the total power consumption, and the total input voltage of the electrical device group corresponding to the timing at which is measured is stored in the feature quantity storage unit 103.
- “Waveform data corresponding to the timing at which the pre-change data value and the post-change data value satisfying a predetermined condition” mean waveform data having a predetermined length including a portion measured at the timing.
- the first time series data and the waveform data may be configured such that the measurement timing can be associated with the measurement time or the like.
- the registration / update unit 102 may execute at least one of the following three processes. -The feature amount extracted from the waveform data of the part corresponding to the data value before the state change (the part corresponding to the data before the state change) and the part corresponding to the data value after the state change (the part corresponding to the data after the state change) The difference value with the feature-value extracted from the waveform data of this is memorize
- the feature amount extracted from the waveform data of the portion corresponding to the data value before the state change (portion corresponding to the data before the state change) is stored in the state feature amount storage unit 104 as the feature amount of the first electrical device group. processing.
- the feature amount extracted from the waveform data of the portion corresponding to the data value after state change is stored in the state feature amount storage unit 104 as the feature amount of the second electrical device group. processing.
- the first time-series data includes a boundary at which the operating state of the electrical device has changed (eg, a boundary at which the power supply is turned on / off), that is, a data value before a state change (data before a state change) that satisfies the predetermined condition. ) And post-change data values (post-change data). Therefore, the first time-series data is divided into a plurality of groups (hereinafter referred to as “electrical device state common group”) by dividing the first time-series data at the boundary where the operating state of the electric device has changed.
- a predetermined feature amount may be extracted from the waveform data corresponding to each of a plurality of electrical equipment state common groups, and these may be stored in the state feature quantity storage unit 104 as feature quantities of a plurality of electrical equipment groups.
- the difference value of each feature amount of two groups that are temporally continuous may be calculated and stored in the feature amount storage unit 105 for each device as the feature amount of the electrical device.
- the registration / update unit 102 uses each of the time-series data of a plurality of types of feature amounts.
- the above process may be executed. For example, as described above, the registration / update unit 102 divides the first time-series data at a boundary where the operating state of the electrical device has changed, thereby separating a plurality of groups (hereinafter, “electrical device state common group”). Divide into Then, for each group, statistical values (average value, median value, mode value, etc.) of data (feature amount) included in each group are calculated, and these are stored as feature amounts of a plurality of electrical equipment groups. The information may be stored in the unit 103. Further, a difference value between feature amounts of two temporally continuous groups may be calculated and stored in the feature amount storage unit 103 as a feature amount of the electrical device.
- FIG. 4 schematically shows an example of information stored in the feature amount storage unit 105 for each device.
- the device-specific feature quantity storage unit 105 shown in the figure stores the feature quantity registered by the registration / update unit 102 in association with the serial number.
- the first time point and the second time point are the boundaries where the operating state of the electric device has changed (the power ON / OFF state). It can be determined that this is the boundary of switching. In other words, it can be determined that there is one electrical device that is operating before the first time point and at least one after the second time point, and not operating on the other side.
- the feature-value difference value extracted from the waveform data corresponding to the pre-change data and the post-change data is stored for each device.
- the feature quantities of each electric device actually used in each unit eg, each home, each building, etc.
- the combination of operating electrical devices is different between the first time point and the second time point.
- the combination at the first time point and the combination at the second time point are combinations of electrical devices actually used in each unit (eg, each home, each building, etc.).
- the feature amount extracted from the waveform data corresponding to the pre-state change data and the post-state change data By storing at least one of the feature quantities extracted from the corresponding waveform data in the state feature quantity storage unit 104, a combination of electrical devices actually used in each unit (eg, each home, each building, etc.) Can be collected efficiently.
- the processing by the monitoring apparatus 100 may be real-time processing or batch processing.
- the first time series data may be associated with time information.
- the measurement time may be associated with each data (current value, power value).
- the first time-series data is time-series data of feature amounts calculated based on time-series data of current consumption or time-series data of power consumption, it is used for calculation for each feature amount.
- the measurement time of the waveform data may be associated. This assumption is the same in all the following embodiments.
- FIG. 2 A functional block diagram of the monitoring apparatus 100 of the present embodiment is shown in FIG. 2 as in the first embodiment.
- the monitoring device 100 of this embodiment is based on the configuration of the monitoring device 100 of the first embodiment, and the configuration of the registration / update unit 102 is different. This will be described below.
- the registration / update unit 102 executes a process of updating the feature amount storage unit 103 when there is pre-change data and post-change data that satisfy the predetermined condition in the first time-series data.
- the feature quantity extracted from the waveform data corresponding to the newly specified pre-state change data and post-state change data is already registered in the feature quantity storage unit 103. If registered, the registered feature value is changed (updated) to a new value. For example, the average value of two or more feature quantities that are close to each other is rewritten. How to determine the predetermined level of approximation is a matter of design.
- the feature quantity stored in the feature quantity storage unit 103 is not fixed with a value obtained once from measured data, but is corrected (averaged or the like) with a value obtained thereafter. Can do. For this reason, when a noise component is included in the feature amount, it can be reduced. Since the noise component is lower in terms of probability, the influence of noise becomes smaller as the number of correction processes increases.
- FIG. 2 A functional block diagram of the monitoring apparatus 100 of the present embodiment is shown in FIG. 2 as in the first embodiment.
- the monitoring device 100 of this embodiment is based on the configuration of the monitoring device 100 of the first embodiment, and the configuration of the registration / update unit 102 is different. This will be described below.
- the registration / update unit 102 sets the newly specified pre-state change data and post-state change data to the newly specified data. It is confirmed whether the feature quantity extracted from the corresponding waveform data and the feature quantity that approximates a predetermined level or more are stored in the feature quantity storage unit 103. If not stored, the feature value is stored in the feature value storage unit 103 as described in the first embodiment. On the other hand, if it is stored, as described in the second embodiment, processing for updating the feature amount storage unit 103 is executed.
- the process of registering the feature value and the process of updating can be performed in parallel.
- FIG. 5 shows an example of a functional block diagram of the monitoring apparatus 100 of the present embodiment.
- the monitoring apparatus 100 includes an acquisition unit 101, a registration / update unit 102, a feature amount storage unit 103, and an input reception unit 107.
- the feature amount storage unit 103 includes at least one of a state feature amount storage unit 104 and a device-specific feature amount storage unit 105.
- the configuration of the acquisition unit 101 is the same as in the first to third embodiments.
- the input receiving unit 107 changes the state from the state (first state) when the pre-change data is measured. Accepts user input of information for identifying an electrical device whose power has been switched on / off when the state changes to the state when the subsequent data is measured (second state).
- the means for accepting user input is not particularly limited, and can be realized using a conventional input device and output device.
- the input receiving unit 107 receives an input from the user will be described for the case where the process of the monitoring apparatus 100 is a real-time process and the case of a batch process.
- the input reception unit 107 uses the same as a trigger, as shown in FIG.
- Such an input reception screen may be displayed.
- the screen shown in FIG. 6 is a “screen for selecting and inputting the type of the electrical device whose power is switched ON / OFF now”. A plurality of electric devices are listed on the screen, and one of them can be selected.
- the input receiving unit 107 may display the screen and notify the user that the screen is displayed and is waiting for input using any notification means such as sound, light, and vibration.
- the registration / update unit 102 displays the screen that has received the input in the identification information that has received the input.
- the feature quantities of the first electrical device calculated based on the data before the state change and the data after the state change that are the triggers are associated with each other and stored in the feature quantity storage unit 105 for each device.
- FIG. 7 schematically shows an example of information stored in the device feature quantity storage unit 105 of the present embodiment.
- the registration / update unit 102 when the pre-state change data and the post-state change data satisfying the predetermined condition are extracted, the pre-state change data and the state change
- the feature amount of the first electrical device calculated based on the post-data is associated with the time of the first time point or the second time point and stored in the device feature amount storage unit 105.
- time information can be associated with the first time-series data.
- FIG. 8 schematically shows another example of information stored in the device-specific feature amount storage unit 105 of the present embodiment. The data acquisition date and time shown is the time at the first time point or the second time point.
- the input reception unit 107 may display an input reception screen as shown in FIG. 9 at a predetermined timing using information stored in the device feature quantity storage unit 105 as shown in FIG.
- the screen shown in FIG. 9 is a “screen for selecting and inputting the type of electric device whose power is switched ON / OFF at a predetermined time”.
- the predetermined time is the time at the first time point or the second time point, and the display of the information is realized by using information stored in the device-specific feature amount storage unit 105 (data acquisition date and time in FIG. 8).
- the A plurality of electric devices are listed on the screen, and one of them can be selected.
- the registration / update unit 102 displays the identification information that has been received as the predetermined information displayed on the input screen. Is stored in the device-specific feature amount storage unit 105 in association with the feature amount associated with the time (see FIG. 8).
- the feature quantity generated from the first time-series data can be associated with the type of electric device having the feature quantity.
- the input receiving unit 107 further receives at least one of information for identifying a plurality of electrical devices operating in the first state and information for identifying a plurality of electrical devices operating in the second state. May be accepted.
- the input receiving unit 107 receives an input from the user will be described for the case where the process of the monitoring apparatus 100 is a real-time process and the case of a batch process.
- the input reception unit 107 When the process of the monitoring device 100 is a real-time process, when the pre-state change data and the post-state change data satisfying the predetermined condition are extracted, the input reception unit 107 is triggered by the data as shown in FIG. An input acceptance screen may be displayed.
- the screen shown in FIG. 13 is a “screen for selecting and inputting the type of the electrical device currently in operation”. “Now” here corresponds to “second state”. A plurality of electric devices are listed on the screen, and one or more of them can be selected.
- the input receiving unit 107 may display the screen and notify the user that the screen is displayed and is waiting for input using any notification means such as sound, light, and vibration.
- the registration / update unit 102 displays the screen that has received the input in the identification information that has received the input.
- the feature quantity extracted from the post-state change data serving as a trigger is associated and stored in the state feature quantity storage unit 104.
- FIG. 14 schematically shows an example of information stored in the state feature amount storage unit 104 of the present embodiment.
- the registration / update unit 102 extracts the pre-state change data and the post-state change data that satisfy the predetermined condition, and extracts the data from each of the data.
- the feature quantity is stored in the state feature quantity storage unit 104 in association with the time period in which each state is maintained.
- the means for specifying the time period in which each state is maintained is not particularly limited. For example, if multiple boundaries where the operating state of the electrical equipment fluctuates in the first time series data (the boundary between power ON / OFF switching) are extracted, a certain state is maintained for the time zone from these boundaries to the boundaries. Time period can be determined. As described in the first embodiment, time information can be associated with the first time-series data.
- FIG. 15 schematically shows another example of information stored in the state feature amount storage unit 104 of the present embodiment. The data acquisition date and time shown in the figure indicates the time period in which each state is maintained.
- the input reception unit 107 may display an input reception screen as shown in FIG. 16 at a predetermined timing using information stored in the state feature amount storage unit 104 as shown in FIG.
- the screen shown in FIG. 16 is a “screen for selecting and inputting the type of electrical equipment that was operating at a predetermined time”.
- the predetermined time is an arbitrary time in the time period in which each state is maintained, and the information is displayed using information stored in the state feature amount storage unit 104 (data acquisition date and time in FIG. 15). Realized. A plurality of electric devices are listed on the screen, and one or more of them can be selected.
- the registration / update unit 102 displays the identification information that has been received as the predetermined information displayed on the input screen. Is stored in the state feature amount storage unit 104 in association with the feature amount associated with the time (see FIG. 15).
- the type of the operating electrical device can be associated with the feature amount in the state in which the plurality of electrical devices are operating.
- FIG. 10 shows an example of a functional block diagram of the monitoring apparatus 100 of the present embodiment.
- the monitoring apparatus 100 includes an acquisition unit 101, a registration / update unit 102, a feature amount storage unit 103, and an estimation unit 108.
- the feature amount storage unit 103 includes at least one of a state feature amount storage unit 104 and a device-specific feature amount storage unit 105. Further, an input receiving unit 107 may be included.
- the configurations of the acquisition unit 101, registration / update unit 102, feature amount storage unit 103, and input reception unit 107 are the same as those in the first to fourth embodiments.
- the estimation unit 108 is extracted from the feature data stored in the feature storage unit 103 and the waveform data of any of the total current consumption, total power consumption, and total input voltage of the electrical device group acquired by the acquisition unit 101.
- the operating state of the electrical device group within a predetermined unit eg, home, building, etc.
- the estimation unit 108 is one of the feature amounts of each electrical device stored in the device-specific feature amount storage unit 105, a combined feature amount that is arbitrarily combined (for example, added together), or a state feature.
- the processing by the estimation unit 108 is the same as that disclosed in Patent Documents 2 to 4, detailed description thereof is omitted here.
- the estimation part 108 performs the said process using the data which the acquisition part 101 acquired in real time.
- the monitoring device 100 may include an output unit that outputs the estimation result of the estimation unit 108.
- the output unit can output the estimation result via any output device such as a display, e-mail, printer, or speaker.
- the estimation unit 108 can estimate the type of the electric device that is in operation (power ON) as the estimation result. For example, the total feature amount obtained by adding the feature amounts of serial number 0001 (associated device information: television) and sequence number 0003 (associated device information: refrigerator), and the feature amount extracted from the waveform data Are matched, the estimation unit 108 can estimate that the television and the refrigerator are in operation. Then, the output unit may display information as shown in FIG.
- the estimation unit 108 when the feature amount storage unit 105 for each device stores the feature amounts as illustrated in FIG. 4, that is, when the type of the electrical device is not associated with each feature amount, the estimation unit 108 operates. Instead of estimating the type of the electric device in the middle, the number of electric devices in operation (power ON) may be estimated. For example, when the total feature amount obtained by adding the feature amounts of serial numbers 0001 and 0003 to 0006 matches the feature amount extracted from the waveform data, the estimation unit 108 is operating five electrical devices. It can be estimated that there is. And an output part may display information as shown in Drawing 11 on display 110, for example.
- FIG. 10 shows an example of a functional block diagram of the monitoring apparatus 100 of the present embodiment.
- the monitoring apparatus 100 includes an acquisition unit 101, a registration / update unit 102, a feature amount storage unit 103, and an estimation unit 108.
- the feature amount storage unit 103 includes a state feature amount storage unit 104 and a device-specific feature amount storage unit 105. Further, an input receiving unit 107 may be included.
- the configurations of the acquisition unit 101, registration / update unit 102, feature amount storage unit 103, and input reception unit 107 are the same as those in the first to fifth embodiments.
- the configuration of the estimation unit 108 is based on a feature amount stored in the feature amount storage unit 103 and a feature amount extracted from the waveform data acquired by the acquisition unit 101 (eg, home, building, etc.).
- the process of estimating the operation state of a plurality of electrical devices in (1) first, the process of estimating the operation state of the electrical device using the feature quantity stored in the state feature quantity storage unit 104 is performed.
- the state cannot be specified, that is, when the feature quantity to be matched is not stored in the state feature quantity storage unit 104
- the feature quantity stored in the device-specific feature quantity storage unit 105 is used to determine the state of the electrical device. This is different from the first to fifth embodiments in that the operating state is estimated. Other configurations are the same as those of the first to fifth embodiments.
- the monitoring device 100 is in an instruction waiting state for outputting the operating state of the electrical equipment (S1). This state is maintained until an output instruction is received (No in S1). On the other hand, if an output instruction is accepted (Yes in S1), the process proceeds to step S2.
- the output instruction may be a user input.
- a predetermined timing for example, a predetermined time of the day (9 o'clock, 12 o'clock, etc.) is monitored in the monitoring apparatus 100 and output when the timing comes. An instruction may be input.
- the acquisition unit 101 acquires at least one waveform data among the total current consumption, the total power consumption, and the total input voltage of the electrical device group. Thereafter, in S3, the estimation unit 108 calculates (acquires) a predetermined feature amount from the waveform data. In S4, the estimation unit 108 collates the calculated feature amount with the feature amount (see FIG. 1420 or FIG. 15) stored in the state feature amount storage unit 104.
- the monitoring apparatus 100 uses the electrical device associated with the feature quantity in the information stored in the state feature quantity storage unit 104.
- Information indicating that is operating is output to the user (S6).
- the estimation unit 108 uses the feature quantity stored in the device-specific feature quantity storage unit 105 (FIGS. 4 and 8). Or, refer to FIG. 9), and collation processing with the feature amount calculated in S3 is performed (S7). And the monitoring apparatus 100 outputs the estimation result by the estimation part 108 toward a user (refer FIG. 12 or FIG. 13).
- the state feature amount stored in the state feature amount storage unit 104 is a feature amount of the operating state of the electrical device group actually used simultaneously in each unit (eg, each home, each building, etc.). For this reason, the feature amount stored in the state feature amount storage unit 104 is included in the total feature amount obtained by adding and combining the feature amounts of the respective electrical devices stored in the device-specific feature amount storage unit 105. It is considered that there is a higher possibility of matching with the feature amount extracted from the waveform data than the feature amount.
- the feature amount stored in the state feature amount storage unit 104 is preferentially used to estimate the operating state of the electrical device, so that the processing speed is reduced as described above, and the burden on the computer is large. It becomes possible to reduce problems such as becoming.
- the monitoring apparatus 100 of this embodiment has the same configuration as the monitoring apparatus 100 of the first to sixth embodiments, and the difference value between the data value before the state change and the data value after the state change is equal to or greater than a predetermined threshold (or , Greater than a predetermined threshold value), a predetermined threshold value used for the process of determining whether the value is a predetermined number of times a variance value of a plurality of data A values or a predetermined value of a variance value of a plurality of data B values. “Several times”, or “the larger of the variance values of the plurality of data A values and the variance values of the plurality of data B values”.
- the definitions of the plurality of data A and the plurality of data B are the same as those described in the first embodiment with reference to FIG.
- the predetermined number of times is a design matter.
- the present embodiment it is possible to reduce the influence of noise components included in the first time series data. As a result, it is possible to improve the accuracy of detecting the boundary where the operating state of the electric device has changed (the boundary between the power ON / OFF switching).
- FIG. 18 shows an example of a functional block diagram of the monitoring apparatus of the present embodiment.
- the monitoring device 100 includes a measurement unit 2, a storage unit 3, a feature amount extraction unit 4, a state separation unit 5, a device separation unit 6, a database update / addition system 10, a discriminator 11, and the like.
- the database update / addition system 10 includes a comparison unit 7, an update / addition unit 8, and an electric device DB 9.
- the installation position of the monitoring device 100 is not particularly limited, and may be installed in each unit (home, building, etc.), or may be installed in a data center that collectively manages a plurality of units.
- the measurement unit 22 measures a current waveform and a voltage waveform (hereinafter referred to as a current voltage waveform) flowing through the power supply backbone.
- the data measured here may be data other than the current voltage waveform, such as a current execution value, a voltage effective value, and power.
- the storage unit 3 stores the measurement data measured by the measurement unit 2. Note that the measurement data stored in the storage unit 3 is stored with information such as measurement time and measurement ID added thereto, and is distinguished from other measurement data.
- the storage unit 3 may be in a device including the measurement unit 2 or may be in a place away from the device including the measurement unit 2. In the latter case, the measurement data measured by the measurement unit 2 is input to the storage unit 3 and stored by wired and / or wireless communication.
- the feature amount extraction unit 4 extracts feature amounts from the measurement data stored in the storage unit 3.
- the feature quantity extracted here may be anything such as the intensity or phase of the fundamental wave or the harmonic wave, or the total power consumption.
- the feature quantity may be the measurement data itself measured by the measurement unit 2. Note that the feature amount conversion by the feature amount extraction unit 4 may be performed inside the measurement apparatus or at a location away from the measurement apparatus.
- the state separation unit 5 separates the feature amount extracted by the feature amount extraction unit 4 for each operation state of the device. This process corresponds to the process of dividing the first time-series data described in the first embodiment into the electric equipment state common group.
- the state separation unit 5 includes pre-state change data that satisfies the first condition from the feature amounts extracted by the feature amount extraction unit 4 (corresponding to the first time-series data acquired by the acquisition unit 101). And extract data after state change. Then, by separating the first time-series data at the boundary between the data at the first time point and the data at the second time point included in the extracted data before the state change and data after the state change, the first time Separate series data into electrical equipment state common groups. Thereafter, the state separation unit 5 may calculate a statistical value by using a plurality of data values included in each electric equipment state common group. And the calculated value is good also as a feature-value of each electric equipment state common group.
- the device separation unit 6 calculates the difference between the feature amounts of the two groups that are temporally continuous in the first time-series data, which are the feature amounts of the electrical device state common group separated by the state separation unit 5. By doing so, the characteristic amount at the time of operation of the electric device whose operation state fluctuates (power ON / OFF) at the time of the state transition is acquired.
- the processing uses a statistical value of a plurality of data values of the electrical equipment state common group including the data before the state change as a representative value before the state change, and a plurality of data of the electrical equipment state common group including the data after the state change. This is equivalent to a process of calculating a difference value between the statistical value of the value as a representative value after the state change and calculating the difference value.
- the comparison unit 7 compares the feature amount of the electrical device acquired by the device separation unit 6 with the feature amount stored in the electrical device DB (database) 9, and the feature amount (value is the same) of the same electrical device. It is determined whether or not there is a feature amount approximated to a predetermined level or more. If there is a feature quantity of the same electrical device, the update / add unit 8 updates the electrical device DB 9. On the other hand, when there is no feature quantity of the same electrical device, the update / add unit 8 registers the feature quantity in the electrical device DB 9.
- the database update / addition system 10 is a system in which the comparison unit 7 and the update / addition unit 8 are continuously operated every time extraction data is sent from the device separation unit 6.
- the comparison unit 7 and the update / add unit 8 correspond to the registration / update unit 102 described in the above embodiment.
- the electric device DB 9 corresponds to the device-specific feature amount storage unit 105 described in the above embodiment.
- the discriminator 11 creates a predetermined discriminant function using data stored in the electrical equipment DB 9 and inputs it to the estimation unit 13.
- the feature amount extraction unit 12 converts the measurement data measured by the measurement unit 2 into a feature amount for estimating the operating state of the electrical equipment.
- the estimation unit 13 estimates the operation status and power consumption of each device using the feature amount extracted by the feature amount extraction unit 12 using the discrimination function obtained by the classifier 11.
- the estimation process by the estimation unit 13 uses, for example, a method such as a neural network, but other methods may be used.
- the classifier 11 corresponds to the estimation unit 108 described in the above embodiment.
- the result display unit 14 displays the estimation result obtained by the estimation unit 13 to the user.
- the estimation result display means may be displayed by any means, such as a means for displaying directly from household devices or a means for referring to an external database by a browser or the like.
- the feature quantity stored in the electrical device DB 9 is unclear as to which device state it represents, it is preferable to associate it with the device.
- a method of association for example, a method of displaying data stored in the electrical device DB 9 to the user using the result display unit 14 and having the user directly input the data can be considered (the above embodiment). This corresponds to the configuration of the input receiving unit 107 described in the above).
- a method of probabilistically determining an electric device used from data such as a current waveform shape, power value, time variation of harmonic intensity, and a time zone in which the feature amount group is used may be used.
- data existing on a network such as weather and temperature may be used, or information such as a temperature sensor and an optical sensor installed in the vicinity of an electric device whose power is estimated may be used.
- the frequency of data detection can be counted by comparing the feature amount obtained from the measurement data with the feature amount existing in the existing database, so that the feature with high accuracy can be obtained.
- the amount of features that are not suitable for power estimation calculations at that time is calculated with high accuracy by lowering the priority using the detection frequency at that time. Is possible.
- the frequency of detection by time is, for example, the same detection frequency integrated for one week (here, arbitrary), arranged for each week.
- the week when the frequency of the stove becomes zero when April is reached is a predetermined number of times (example: (3 times)
- a simple estimator as described above can be made.
- FIG. 19 shows an example of a functional block diagram of the monitoring apparatus of the present embodiment.
- the monitoring apparatus 100 of the present embodiment is further provided with a database update / addition system 18 as compared with the monitoring apparatus 100 (see FIG. 18) of the eighth embodiment, and further includes a comparison unit 15 and an update / addition unit 16. And it differs in having measurement DB17.
- Configuration of measurement unit 2, storage unit 3, feature amount extraction unit 4, state separation unit 5, device separation unit 6, comparison unit 7, update / addition unit 8, electric device DB 9, feature amount extraction unit 12 and result display unit 14 Is the same as in the eighth embodiment.
- the comparison unit 15 compares the feature amount of each of the plurality of states acquired by the state separation unit 5 (feature amount of each electrical device state common group) with the feature amount stored in the measurement DB 17 to obtain the same It is determined whether or not there is a feature amount (a feature amount whose value approximates a predetermined level or more) in the state (the operating state of the electrical device).
- the update / addition unit 16 updates the measurement DB 17.
- the update / addition unit 16 registers the feature amount in the measurement DB 17.
- the database update / addition system 10 is a system that continuously operates the comparison unit 15 and the update / addition unit 16 every time extraction data is sent from the device separation unit 6.
- the comparison unit 15 and the update / addition unit 16 correspond to the registration / update unit 102 described in the above embodiment.
- the measurement DB 17 corresponds to the state feature amount storage unit 104 described in the above embodiment.
- the classifier 11 and the estimation unit 13 can have the same configuration as the estimation unit 108 described in the above embodiment.
- the frequency of detection of the measurement state existing in the measurement value database 17 can be counted. If this detection frequency is used, features that are not suitable for power estimation calculation at that time (such as using a stove feature for summer power estimation) are used to lower the priority by using the detection frequency at that time. High calculation is possible.
- FIG. 20 shows an example of a functional block diagram of the monitoring apparatus of this embodiment.
- the monitoring device 100 of the present embodiment is different from the monitoring device 100 of the ninth embodiment (see FIG. 19) in that the monitoring device 100 can communicate with the master system 22.
- Measurement unit 2 storage unit 3, feature amount extraction unit 4, state separation unit 5, device separation unit 6, comparison unit 7, update / addition unit 8, classifier 11, feature amount extraction unit 12, estimation unit 13, result display
- the configurations of the unit 14, the comparison unit 15, the update / addition unit 16, and the measurement DB 17 are the same as those in the ninth and tenth embodiments.
- the master system 22 includes a comparison unit 19, an update / addition unit 20, and a master DB 21.
- the master DB 21 is a database that can store the feature amounts and use states of electric devices that integrate data sent from a plurality of users, and also data that associates the electric devices with the feature amounts.
- the comparison unit 19 compares the feature quantity stored in the electrical device DB 9 with the feature quantity stored in the master DB 21, and compares the feature quantity of the same electrical device (a feature quantity whose value approximates a predetermined level or more). ). If there is a feature quantity of the same electrical device, the update / add unit 20 updates the master DB 21. On the other hand, when there is no feature quantity of the same electrical device, the update / addition unit 20 registers the feature quantity in the master DB 21.
- the master system 22 is a system in which the comparison unit 19 and the update / addition unit 20 are continuously operated every time a feature amount stored in the electrical device DB 9 is sent from the monitoring device 100.
- the monitoring device 100 can communicate with the master system 22 to acquire a feature value stored in the master DB 21 and store it in the electrical device DB 9.
- the master DB 21 may have any internal configuration such as saved data.
- the master DB 21 may be used in the form of storing data for each unit (eg, home, building, etc.), or may be used as a backup of the data of each unit.
- a database in which data obtained in each unit is integrated may be created, or data may be integrated in a certain region.
- the feature amount registered in the master DB 21 is a data table in which the feature amount and the electrical device are statistically associated with each other using the result of the association between the feature amount and the electrical device registered by the various users in the electrical device DB 9. You may have. For example, for one feature value, the probability of being an electric stove is 70%, and the probability of being a dryer is 30%. You may have a database attached. It should be noted that the feature amount and the information on the electric device associated here may be acquired by the user of each unit (eg, home, building, etc.) and stored in the electric device DB 9 in each unit.
- the user of each unit can associate the feature amount with the electric device only by acquiring the data table existing in the master DB 21, so that the user Can eliminate the burden of registering the device by themselves.
- the master DB 21 can integrate feature amounts transmitted from a plurality of units (eg, home, building, etc.), it can have highly accurate feature amounts. Therefore, if a feature quantity required by a user of each unit (eg, home, building, etc.) exists in the master DB 21, the user may acquire the feature quantity from the master DB 21. As a result, the user can register an accurate feature amount in the electric device DB 9.
- the measuring unit 2 uses the current / voltage sensor installed in the power supply trunk before or after branching of the distribution board to which the electrical equipment 1a to 1c is connected after branching to obtain current and voltage waveform data. Measurement is performed for a plurality of periods of a reference wave of 50 Hz or 60 Hz, and this is used as measurement data. Although the voltage waveform is taken directly from the distribution board, it may be taken from a normal power source below the distribution board such as an outlet. The measurement data is measured at a certain period (for example, every 5 seconds), and the measurement data of one or more times is stored in the storage unit 3.
- the time-series measurement data stored in the storage unit 3 is converted into time-series feature data by the feature extraction unit 4.
- the feature amount data extracted by the feature amount extraction unit 4 varies depending not only on the type of device but also on the state of the device. Hereinafter, these feature amount data are collectively expressed as feature amount data.
- the state separation unit 5 First, a feature amount data set in which feature amount data extracted by the feature amount extraction unit 4 from measurement data stored in the storage unit 3 is collected in a specific period (for example, 1 hour). Make.
- the state separation unit 5 dynamically determines a threshold for detecting a change in the operating state of the electrical equipment (switching of power ON / OFF) depending on the magnitude of noise in the feature data. Specifically, for example, paying attention to arbitrary data (data at the first time point in FIG. 3), a plurality of data A up to a predetermined number (for example, 30) before that is set as data before state change. . Further, the data after the first time point of interest (the data at the second time point) is used as the data after the state change.
- the threshold value is a value obtained by multiplying the variance value of the pre-change data by a predetermined value (eg, 10 times).
- the state separation unit 5 determines whether or not the difference value between the average value of the data before the state change and the data after the state change is equal to or greater than the determined threshold value. If it is equal to or greater than the threshold value, it is determined that a predetermined condition is satisfied, and the boundary between the first time point and the second time point is determined as the time point when the operating state of the electrical device has changed (switching of power ON / OFF).
- the detection method of the fluctuation (switching of power ON / OFF) of the operating state of the electrical equipment may be other than the time order. For example, you can select a feature data set for a specific period (for example, 1 hour), select the smallest feature value in that period, and select the largest feature value in that order. You may group by.
- the threshold value may be determined using a threshold value that can be set using the magnitude of noise or the like, or a threshold value that can be set by the designer or administrator.
- FIG. 21 shows an example of data in the case where the detection processing of the change point (switching of power ON / OFF) of the operating state of the electric device described above is performed in the three types of the electric device a, the electric device b, and the electric device c.
- FIG. 21 shows measurement data (time change in feature amount intensity), instantaneous difference value (absolute value of difference value between data before state change and data after state change), threshold value (dispersion value of data before state change) from the top. It is the figure which showed each time change in the order of the value multiplied by the predetermined multiple, the space
- the state separation unit 5 converts the time-series feature amount data created by the feature amount extraction unit 4 into a plurality of groups (electricity) at the point of change in the operating state of the electrical equipment (switching of power ON / OFF). Device status common group). If this method is used, it becomes possible to detect and separate even a switch automatically switched by an electric device regardless of the will of the human. This eliminates the need for the user to distinguish between a switch automatically changed by the device and a switch changed by the user's intention.
- the feature amount of each electrical device is calculated. Specifically, the statistical value of each of the plurality of groups separated by the state separation unit 5 is calculated, and the statistical value of the first group and the statistical value of the group whose time series order is immediately before and / or immediately after that The difference value is calculated. Then, the calculated difference value is used as a feature amount of a certain electric device.
- FIG. 22 shows data representing the feature amounts of the single devices of the electric device a, the electric device b, and the electric device c separated by the device separation unit 6.
- the comparison unit 7 compares a certain feature value generated by the device separation unit 6 with the feature value stored in the electrical device DB 99. For example, assuming that the electrical device DB 9 has the feature amount and the distribution information of each electrical device, first, the feature amount generated by the device separation unit 6 is closest to the feature amount of the electrical device in the electrical device DB 9. It is determined whether it is within a range of a constant multiple of the variance of the characteristic amount of the electric device. If the feature amount is within the range of variance, the comparison unit 7 determines that the data is the same data, and the update / add unit 8 calculates the average and variance with weighting the frequency, and uses it as the update data. Is registered in the electric equipment DB 9 as follows.
- the comparison unit 7 determines that the data is different, and the update / addition unit 8 registers it in the electrical device DB 9 as a feature quantity of a new electrical device that has not yet been registered.
- the data storage method may be in any form other than the average value and error listed above, such as all feature data obtained by measurement, or data distribution such as a histogram. Under the user, the same power consumption fluctuation may occur several times, such as turning on / off a specific light within a certain period of time. By combining data, it is possible to prevent an increase in the amount of data and an increase in useless calculation time.
- the feature amount data collection system proceeds in parallel with the determination of the operation state and power consumption of the device, data is continuously and automatically collected while the device relating to the system of the present invention is turned on. Will continue. Therefore, the feature amount obtained by the present invention has the feature that the accuracy is automatically improved and the feature amount data that has caused the malfunction can be recorded without missing.
- the estimation process cannot be performed in the initial state where the data is not registered. Therefore, during this time, a comment such as “the operating state of the electrical device cannot be specified because the collected data is insufficient” may be output to the user. Then, an instantaneous value such as a power value or a current value may be output.
- the feature amount is extracted from the actual measurement value measured at each home and the like, and is registered in the electric device DB 9, so that the new electric device can be newly created without troublesome setting when introducing the new electric device.
- the feature amount of the electric device can be registered in the electric device DB 9.
- Acquisition means for acquiring first time-series data that is time-series measurement data related to electrical equipment, or time-series data of a feature amount calculated based on the measurement data;
- first time series data the data of the first time point from the data value of the first time point or the data of the first time series data that goes back a predetermined time before the first time point.
- a data value before a state change which is a statistical value of a plurality of data values up to and a second time point located one time later than the data at the first time point in the first time series data State that is a statistical value of a plurality of data values from data value or data at the second time point to data at a time point that is a predetermined time later than the data at the second time point in the first time series data
- a first process of registering a representative value before state change which is a value calculated using the data value before state change, in a state feature amount storage unit included in the feature amount storage unit as a feature amount of the first state
- a second state-registered representative value which is a value calculated using the data value after the state change, is registered in the state feature amount storage unit as a feature amount in a second state different from the first state
- Processing A third process of registering a difference value between the representative value before the state change and the representative value after the state change as
- Registration / update means for executing at least one of the fourth processes; Having a monitoring device. 2.
- the registration / update unit And determining means for transmitting at least one of the representative value before the state change, the representative value after the state change, and the difference value between the representative value before the state change and the representative value after the state change. 3.
- the monitoring device according to The determination unit determines that the predetermined condition is satisfied when a difference value between the data value before the state change and the data value after the state change is equal to or greater than a predetermined threshold. 4).
- the monitoring device includes a plurality of data values from data at a time point going back a predetermined time before the first time point to data at the first time point in the first time series data, or the second data A monitoring device that calculates the predetermined threshold value using a plurality of data values from data at a time point to data at a time point that is a predetermined time later than the data at the second time point in the first time-series data . 5.
- the registration / update means has a feature amount that approximates the representative value before the state change by a predetermined level or more.
- the registration / update unit has a feature amount that approximates the representative value after the state change by a predetermined level or more.
- the registration / update unit determines whether the difference value between the representative value before the state change and the representative value after the state change is a predetermined value. Check whether the feature quantity that approximates the level or more is stored in the feature quantity storage means for each device, A monitoring device that executes the third process when not stored, and executes the fourth process when stored. 8).
- Information identifying the electrical device that was operating in the first state, information identifying the electrical device that was operating in the second state, and changing from the first state to the second state An input receiving means for receiving at least one user input in the information for identifying the electrical device whose power is switched ON / OFF when changing;
- the registration / updating unit is a process of associating information identifying an electrical device that was operating in the first state with the feature amount of the first state stored in the feature amount storage unit, A process of associating information for identifying an electrical device that was operating in the second state with the feature quantity in the second state stored in the quantity storage means, and the feature quantity stored in the feature quantity storage means At least one of the processes for associating the feature quantity of the first electric device with information for identifying the electric device whose power is switched ON / OFF when the first state is changed to the second state.
- the monitoring apparatus which further has an estimation means which estimates the operation state of several electric equipment using the feature-value memorize
- a data value before a state change which is a statistical value of a plurality of data values up to and a second time point located one time later than the data at the first time point in the first time series data State that is a statistical value of a plurality of data values from data value or data at the second time point to data at a time point that is a predetermined time later than the data at the second time point in the first time series data
- a first process of registering a representative value before state change which is a value calculated using the data value before state change, in a state feature amount storage unit included in the feature amount storage unit as a feature amount of the first state
- a second state-registered representative value which is a value calculated using the data value after the state change, is registered in the state feature amount storage unit as a feature amount in a second state different from the first state
- Processing A third process of registering a difference value between the representative value before the state change and the representative value after the state change as
- the registration / update step A determining step of passing at least one of the representative value before the state change, the representative value after the state change, and the difference value between the representative value before the state change and the representative value after the state change. 10-3.
- a monitoring method that, in the determination step, determines that the predetermined condition is satisfied when a difference value between the data value before the state change and the data value after the state change is equal to or greater than a predetermined threshold.
- the registration / update step when a difference value between the data value before the state change and the data value after the state change satisfies the predetermined condition, a feature amount that approximates the representative value before the state change by a predetermined level or more is the state feature.
- Check whether it is stored in the quantity storage means A monitoring method that executes the first process when not stored, and executes the fourth process when stored. 10-6.
- the registration / update step when a difference value between the data value before the state change and the data value after the state change satisfies the predetermined condition, a feature amount that approximates the representative value after the state change by a predetermined level or more is the state feature. Check whether it is stored in the quantity storage means, A monitoring method that executes the second process when not stored, and executes the fourth process when stored. 10-7.
- the registration / update step when a difference value between the data value before the state change and the data value after the state change satisfies the predetermined condition, a difference value between the representative value before the state change and the representative value after the state change is predetermined.
- Information identifying the electrical device that was operating in the first state, information identifying the electrical device that was operating in the second state, and changing from the first state to the second state An input receiving step of receiving at least one user input in the information for identifying the electric device whose power is switched on / off when changing,
- a process of associating information for identifying an electrical device that was operating in the first state with the feature amount in the first state stored in the feature amount storage unit, the feature A process of associating information for identifying an electrical device that was operating in the second state with the feature quantity in the second state stored in the quantity storage means, and the feature quantity stored in the feature quantity storage means At least one of the processes for associating the feature quantity of the first electric device with information for identifying the electric device whose power is switched ON / OFF when the first state is changed to the second state.
- a data value before a state change which is a statistical value of a plurality of data values up to and a second time point located one time later than the data at the first time point in the first time series data State that is a statistical value of a plurality of data values from data value or data at the second time point to data at a time point that is a predetermined time later than the data at the second time point in the first time series data
- a first process of registering a representative value before state change which is a value calculated using the data value before state change, in a state feature amount storage unit included in the feature amount storage unit as a feature amount of the first state
- a second state-registered representative value which is a value calculated using the data value after the state change, is registered in the state feature amount storage unit as a feature amount in a second state different from the first state
- Processing A third process of registering a difference value between the representative value before the state change and the representative value after the state change as
- Registration / update means for executing at least one of the fourth processes; Program to function as. 11-2.
- the computer It is determined whether or not a difference value between the representative value before the state change and the representative value after the state change satisfies the predetermined condition. If the predetermined condition is satisfied, the registration / update unit includes the representative value before the state change.
- a predetermined threshold In the program described in 11-3, In the determination means, a plurality of data values from data at a time point that goes back a predetermined time before the first time point to data at the first time point in the first time series data, or the second data.
- the computer Information identifying the electrical device that was operating in the first state, information identifying the electrical device that was operating in the second state, and changing from the first state to the second state Further functioning as an input accepting means for accepting at least one user input in the information for identifying the electric device whose power is switched ON / OFF when changing, A process of associating the registration / update unit with information for identifying an electrical device operating in the first state, to the feature amount of the first state stored in the feature amount storage unit; A process of associating information for identifying an electrical device that was operating in the second state with the feature quantity in the second state stored in the quantity storage means, and the feature quantity stored in the feature quantity storage means At least one of the processes for associating the feature quantity of the first electric device with information for identifying the electric device whose power is switched ON / OFF when the first state is changed to the second state.
- Said computer further A program that functions as an estimation unit that estimates operating states of a plurality of electrical devices using the feature amount stored in the feature amount storage unit and the measurement data acquired by the acquisition unit.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Water Supply & Treatment (AREA)
- Theoretical Computer Science (AREA)
- Power Engineering (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
Description
電気機器群に関する測定値及び/又は特徴量の時系列なデータである第1の時系列データを取得する取得手段と、
前記第1の時系列データにおける第1の時点のデータ値、及び、前記第1の時点より所定時間前にさかのぼった時点から前記第1の時点までの複数のデータ値の統計値のいずれかである状態変化前データ値と、前記第1の時点より後の第2の時点のデータ値、及び、前記第2の時点から前記第2の時点より所定時間後に進んだ時点までの複数のデータ値の統計値のいずれかである状態変化後データ値との差分値が所定の条件を満たす場合、前記所定の条件を満たす前記状態変化前データ値及び前記状態変化後データ値に対応する前記電気機器群の総消費電流、総消費電力及び総入力電圧のいずれかの波形データから抽出された特徴量を、特徴量記憶手段に記憶する登録・更新手段と、
を有する監視装置が提供される。
コンピュータが、
電気機器群に関する測定値及び/又は特徴量の時系列なデータである第1の時系列データを取得する取得工程と、
前記第1の時系列データにおける第1の時点のデータ値、及び、前記第1の時点より所定時間前にさかのぼった時点から前記第1の時点までの複数のデータ値の統計値のいずれかである状態変化前データ値と、前記第1の時点より後の第2の時点のデータ値、及び、前記第2の時点から前記第2の時点より所定時間後に進んだ時点までの複数のデータ値の統計値のいずれかである状態変化後データ値との差分値が所定の条件を満たす場合、前記所定の条件を満たす前記状態変化前データ値及び前記状態変化後データ値に対応する前記電気機器群の総消費電流、総消費電力及び総入力電圧のいずれかの波形データから抽出された特徴量を、特徴量記憶手段に記憶する登録・更新工程と、
を実行する監視方法が提供される。
コンピュータを、
電気機器群に関する測定値及び/又は特徴量の時系列なデータである第1の時系列データを取得する取得手段、
前記第1の時系列データにおける第1の時点のデータ値、及び、前記第1の時点より所定時間前にさかのぼった時点から前記第1の時点までの複数のデータ値の統計値のいずれかである状態変化前データ値と、前記第1の時点より後の第2の時点のデータ値、及び、前記第2の時点から前記第2の時点より所定時間後に進んだ時点までの複数のデータ値の統計値のいずれかである状態変化後データ値との差分値が所定の条件を満たす場合、前記所定の条件を満たす前記状態変化前データ値及び前記状態変化後データ値に対応する前記電気機器群の総消費電流、総消費電力及び総入力電圧のいずれかの波形データから抽出された特徴量を、特徴量記憶手段に記憶する登録・更新手段、
として機能させるためのプログラムが提供される。
なお、本実施形態の装置及び当該装置が備える各部は、任意のコンピュータのCPU(Central Processing Unit)、メモリ、メモリにロードされたプログラム(あらかじめ装置を出荷する段階からメモリ内に格納されているプログラムのほか、CD(Compact Disc)等の記憶媒体やインターネット上のサーバ等からダウンロードされたプログラムも含む)、そのプログラムを格納するハードディスク等の記憶ユニット、ネットワーク接続用インタフェイスを中心にハードウェアとソフトウェアの任意の組合せによって実現される。そして、その実現方法、装置にはいろいろな変形例があることは、当業者には理解されるところである。
本実施形態の監視装置は、予め保持している複数の電気機器各々の特徴量(参照データ)、及び/又は、それらを組み合わせた特徴量(参照データ)と、測定された消費電流、消費電力、入力電圧などの波形データから抽出された特徴量とを比較することで電気機器の稼動状態を推定する技術において利用される参照データ(教師データ)を、日常の中で測定された波形データ(例:消費電流、消費電力、入力電圧等)から自動的に生成し、記憶する機能を有する。以下、詳細に説明する。
・状態変化前データ値に対応する部分(状態変化前データに対応する部分)の波形データから抽出された特徴量と、状態変化後データ値に対応する部分(状態変化後データに対応する部分)の波形データから抽出された特徴量との差分値を、第1の電気機器の特徴量として機器毎特徴量記憶部105に記憶する処理。
・状態変化前データ値に対応する部分(状態変化前データに対応する部分)の波形データから抽出された特徴量を、第1の電気機器群の特徴量として状態特徴量記憶部104に記憶する処理。
・状態変化後データ値に対応する部分(状態変化後データに対応する部分)の波形データから抽出された特徴量を、第2の電気機器群の特徴量として状態特徴量記憶部104に記憶する処理。
本実施形態の監視装置100の機能ブロック図は、第1の実施形態と同様に図2で示される。本実施形態の監視装置100は、第1の実施形態の監視装置100の構成を基本とし、登録・更新部102の構成が異なる。以下、説明する。
本実施形態の監視装置100の機能ブロック図は、第1の実施形態と同様に図2で示される。本実施形態の監視装置100は、第1の実施形態の監視装置100の構成を基本とし、登録・更新部102の構成が異なる。以下、説明する。
図5に、本実施形態の監視装置100の機能ブロック図の一例を示す。図示するように、本実施形態の監視装置100は、取得部101と、登録・更新部102と、特徴量記憶部103と、入力受付部107とを有する。特徴量記憶部103は、状態特徴量記憶部104及び機器毎特徴量記憶部105の少なくとも一方を有する。取得部101の構成は、第1乃至第3の実施形態と同様である。
図10に、本実施形態の監視装置100の機能ブロック図の一例を示す。図示するように、本実施形態の監視装置100は、取得部101と、登録・更新部102と、特徴量記憶部103と、推定部108と、を有する。特徴量記憶部103は、状態特徴量記憶部104及び機器毎特徴量記憶部105の少なくとも一方を有する。なお、さらに、入力受付部107を有してもよい。取得部101、登録・更新部102、特徴量記憶部103、及び、入力受付部107の構成は、第1乃至第4の実施形態と同様である。
図10に、本実施形態の監視装置100の機能ブロック図の一例を示す。図示するように、本実施形態の監視装置100は、取得部101と、登録・更新部102と、特徴量記憶部103と、推定部108と、を有する。特徴量記憶部103は、状態特徴量記憶部104と機器毎特徴量記憶部105を有する。なお、さらに、入力受付部107を有してもよい。取得部101、登録・更新部102、特徴量記憶部103、及び、入力受付部107の構成は、第1乃至第5の実施形態と同様である。
本実施形態の監視装置100は、第1乃至第6の実施形態の監視装置100と同様の構成を有し、状態変化前データ値と状態変化後データ値の差分値が所定の閾値以上(又は、所定の閾値より大)であるか判定する処理に利用される所定の閾値を、「複数のデータAの値の分散値の所定数倍」、「複数のデータBの値の分散値の所定数倍」、又は、「複数のデータAの値の分散値と複数のデータBの値の分散値のうち、大きいほうの所定数倍」とする点で異なる。複数のデータA、及び、複数のデータBの定義は、図3を用いて第1の実施形態で説明した通りであるので、ここでの説明は省略する。なお、所定数倍の値は設計的事項である。
図18に、本実施形態の監視装置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100は、測定部2と、保存部3と、特徴量抽出部4と、状態分離部5と、機器分離部6と、データベース更新追加システム10と、識別機11と、特徴量抽出部12と、推定部13と、結果表示部14とを有する。データベース更新追加システム10は、比較部7と、更新・追加部8と、電気機器DB9とを有する。監視装置100の設置位置は特段制限されず、各単位(家庭、建物など)内に設置されてもよいし、複数の単位をまとめて管理するデータセンター内に設置されてもよい。
図19に、本実施形態の監視装置の機能ブロック図の一例を示す。図示するように、本実施形態の監視装置100は、第8の実施形態の監視装置100(図18参照)と比べて、データベース更新追加システム18が、さらに、比較部15、更新・追加部16及び測定DB17を有する点で異なる。測定部2、保存部3、特徴量抽出部4、状態分離部5、機器分離部6、比較部7、更新・追加部8、電気機器DB9、特徴量抽出部12及び結果表示部14の構成は、第8の実施形態と同様である。
図20に、本実施形態の監視装置の機能ブロック図の一例を示す。図示するように、本実施形態の監視装置100は、第9の実施形態の監視装置100(図19参照)と比べて、監視装置100がマスタシステム22と通信可能になっている点で異なる。測定部2、保存部3、特徴量抽出部4、状態分離部5、機器分離部6、比較部7、更新・追加部8、識別機11、特徴量抽出部12、推定部13、結果表示部14、比較部15、更新・追加部16及び測定DB17の構成は、第9及び第10の実施形態と同様である。
本実施形態では、図20の構成における監視装置100の具体例を説明する。
1. 電気機器に関する時系列な測定データ、又は、前記測定データに基づいて算出された特徴量の時系列なデータである第1の時系列データを取得する取得手段と、
前記第1の時系列データにおいて、第1の時点のデータの値又は前記第1の時系列データ内で前記第1の時点より所定時間前にさかのぼった時点のデータから前記第1の時点のデータまでの複数のデータの値の統計値である状態変化前データ値と、前記第1の時系列データ内で前記第1の時点のデータより時間的に1つ後方に位置する第2の時点のデータの値又は前記第2の時点のデータから前記第1の時系列データ内で前記第2の時点のデータより所定時間後に進んだ時点のデータまでの複数のデータの値の統計値である状態変化後データ値との差分値が所定の条件を満たす場合、
前記状態変化前データ値を利用して算出された値である状態変化前代表値を、第1の状態の特徴量として特徴量記憶手段が有する状態特徴量記憶手段に登録する第1の処理、
前記状態変化後データ値を利用して算出された値である状態変化後代表値を、前記第1の状態とは異なる第2の状態の特徴量として前記状態特徴量記憶手段に登録する第2の処理、
前記状態変化前代表値と前記状態変化後代表値の差分値を、第1の電気機器の特徴量として前記特徴量記憶手段が有する機器毎特徴量記憶手段に登録する第3の処理、及び、
前記状態変化前代表値、前記状態変化後代表値、及び、前記状態変化前代表値と前記状態変化後代表値の差分値の中の少なくとも1つを用いて、前記特徴量記憶手段を更新する第4の処理の中の少なくとも1つを実行する登録・更新手段と、
を有する監視装置。
2. 1に記載の監視装置において、前記状態変化前代表値と前記状態変化後代表値の差分値が前記所定の条件を満たすか否か判定し、前記所定の条件を満たす場合、前記登録・更新手段に、前記状態変化前代表値、前記状態変化後代表値、前記状態変化前代表値と前記状態変化後代表値の差分値の中の少なくとも1つを送信する判定手段をさらに有する監視装置。
3. 2に記載の監視装置において、
前記判定手段は、前記状態変化前データ値と前記状態変化後データ値との差分値が所定の閾値以上である場合、前記所定の条件を満たすと判断する監視装置。
4. 3に記載の監視装置において、
前記判定手段は、前記第1の時系列データ内で前記第1の時点より所定時間前にさかのぼった時点のデータから前記第1の時点のデータまでの複数のデータの値、又は、前記第2の時点のデータから前記第1の時系列データ内で前記第2の時点のデータより所定時間後に進んだ時点のデータまでの複数のデータの値を利用して前記所定の閾値を算出する監視装置。
5. 1から4のいずれかに記載の監視装置において、
前記登録・更新手段は、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化前代表値と所定レベル以上近似する特徴量が前記状態特徴量記憶手段に記憶されているか確認し、
記憶されていない場合は前記第1の処理を実行し、記憶されている場合は前記第4の処理を実行する監視装置。
6. 1から5のいずれかに記載の監視装置において、
前記登録・更新手段は、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化後代表値と所定レベル以上近似する特徴量が前記状態特徴量記憶手段に記憶されているか確認し、
記憶されていない場合は前記第2の処理を実行し、記憶されている場合は前記第4の処理を実行する監視装置。
7. 1から6のいずれかに記載の監視装置において、
前記登録・更新手段は、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化前代表値と前記状態変化後代表値の差分値と所定レベル以上近似する特徴量が前記機器毎特徴量記憶手段に記憶されているか確認し、
記憶されていない場合は前記第3の処理を実行し、記憶されている場合は前記第4の処理を実行する監視装置。
8. 1から7のいずれかに記載の監視装置において、
前記第1の状態の時に稼働していた電気機器を識別する情報、前記第2の状態の時に稼働していた電気機器を識別する情報、及び、前記第1の状態から前記第2の状態に変化する際に電源のON/OFFを切り替えた電気機器を識別する情報の中の少なくとも1つのユーザ入力を受付ける入力受付手段をさらに有し、
前記登録・更新手段は、前記特徴量記憶手段に記憶されている前記第1の状態の特徴量に、前記第1の状態の時に稼働していた電気機器を識別する情報を対応付ける処理、前記特徴量記憶手段に記憶されている前記第2の状態の特徴量に、前記第2の状態の時に稼働していた電気機器を識別する情報を対応付ける処理、前記特徴量記憶手段に記憶されている前記第1の電気機器の特徴量に、前記第1の状態から前記第2の状態に変化する際に電源のON/OFFを切り替えた電気機器を識別する情報を対応付ける処理の中の少なくとも1つを実行する監視装置。
9. 1から8のいずれかに記載の監視装置において、
前記特徴量記憶手段に記憶されている特徴量と、前記取得手段が取得した前記測定データとを利用して、複数の電気機器の稼動状態を推定する推定手段をさらに有する監視装置。
10. コンピュータが、
電気機器に関する時系列な測定データ、又は、前記測定データに基づいて算出された特徴量の時系列なデータである第1の時系列データを取得する取得ステップと、
前記第1の時系列データにおいて、第1の時点のデータの値又は前記第1の時系列データ内で前記第1の時点より所定時間前にさかのぼった時点のデータから前記第1の時点のデータまでの複数のデータの値の統計値である状態変化前データ値と、前記第1の時系列データ内で前記第1の時点のデータより時間的に1つ後方に位置する第2の時点のデータの値又は前記第2の時点のデータから前記第1の時系列データ内で前記第2の時点のデータより所定時間後に進んだ時点のデータまでの複数のデータの値の統計値である状態変化後データ値との差分値が所定の条件を満たす場合、
前記状態変化前データ値を利用して算出された値である状態変化前代表値を、第1の状態の特徴量として特徴量記憶手段が有する状態特徴量記憶手段に登録する第1の処理、
前記状態変化後データ値を利用して算出された値である状態変化後代表値を、前記第1の状態とは異なる第2の状態の特徴量として前記状態特徴量記憶手段に登録する第2の処理、
前記状態変化前代表値と前記状態変化後代表値の差分値を、第1の電気機器の特徴量として前記特徴量記憶手段が有する機器毎特徴量記憶手段に登録する第3の処理、及び、
前記状態変化前代表値、前記状態変化後代表値、及び、前記状態変化前代表値と前記状態変化後代表値の差分値の中の少なくとも1つを用いて、前記特徴量記憶手段を更新する第4の処理の中の少なくとも1つを実行する登録・更新ステップと、
を実行する監視方法。
10-2. 10に記載の監視方法において、前記状態変化前代表値と前記状態変化後代表値の差分値が前記所定の条件を満たすか否か判定し、前記所定の条件を満たす場合、前記登録・更新ステップに、前記状態変化前代表値、前記状態変化後代表値、前記状態変化前代表値と前記状態変化後代表値の差分値の中の少なくとも1つを渡す判定ステップをさらに実行する監視方法。
10-3. 10-2に記載の監視方法において、
前記判定ステップでは、前記状態変化前データ値と前記状態変化後データ値との差分値が所定の閾値以上である場合、前記所定の条件を満たすと判断する監視方法。
10-4. 10-3に記載の監視方法において、
前記判定ステップでは、前記第1の時系列データ内で前記第1の時点より所定時間前にさかのぼった時点のデータから前記第1の時点のデータまでの複数のデータの値、又は、前記第2の時点のデータから前記第1の時系列データ内で前記第2の時点のデータより所定時間後に進んだ時点のデータまでの複数のデータの値を利用して前記所定の閾値を算出する監視方法。
10-5. 10から10-4のいずれかに記載の監視方法において、
前記登録・更新ステップでは、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化前代表値と所定レベル以上近似する特徴量が前記状態特徴量記憶手段に記憶されているか確認し、
記憶されていない場合は前記第1の処理を実行し、記憶されている場合は前記第4の処理を実行する監視方法。
10-6. 10から10-5のいずれかに記載の監視方法において、
前記登録・更新ステップでは、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化後代表値と所定レベル以上近似する特徴量が前記状態特徴量記憶手段に記憶されているか確認し、
記憶されていない場合は前記第2の処理を実行し、記憶されている場合は前記第4の処理を実行する監視方法。
10-7. 10から10-6のいずれかに記載の監視方法において、
前記登録・更新ステップでは、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化前代表値と前記状態変化後代表値の差分値と所定レベル以上近似する特徴量が前記機器毎特徴量記憶手段に記憶されているか確認し、
記憶されていない場合は前記第3の処理を実行し、記憶されている場合は前記第4の処理を実行する監視方法。
10-8. 10から10-7のいずれかに記載の監視方法において、
前記第1の状態の時に稼働していた電気機器を識別する情報、前記第2の状態の時に稼働していた電気機器を識別する情報、及び、前記第1の状態から前記第2の状態に変化する際に電源のON/OFFを切り替えた電気機器を識別する情報の中の少なくとも1つのユーザ入力を受付ける入力受付ステップをさらに実行し、
前記登録・更新ステップでは、前記特徴量記憶手段に記憶されている前記第1の状態の特徴量に、前記第1の状態の時に稼働していた電気機器を識別する情報を対応付ける処理、前記特徴量記憶手段に記憶されている前記第2の状態の特徴量に、前記第2の状態の時に稼働していた電気機器を識別する情報を対応付ける処理、前記特徴量記憶手段に記憶されている前記第1の電気機器の特徴量に、前記第1の状態から前記第2の状態に変化する際に電源のON/OFFを切り替えた電気機器を識別する情報を対応付ける処理の中の少なくとも1つを実行する監視方法。
10-9. 10から10-8のいずれかに記載の監視方法において、
前記特徴量記憶手段に記憶されている特徴量と、前記取得ステップで取得した前記測定データとを利用して、複数の電気機器の稼動状態を推定する推定ステップをさらに実行する監視方法。
11. コンピュータを、
電気機器に関する時系列な測定データ、又は、前記測定データに基づいて算出された特徴量の時系列なデータである第1の時系列データを取得する取得手段、
前記第1の時系列データにおいて、第1の時点のデータの値又は前記第1の時系列データ内で前記第1の時点より所定時間前にさかのぼった時点のデータから前記第1の時点のデータまでの複数のデータの値の統計値である状態変化前データ値と、前記第1の時系列データ内で前記第1の時点のデータより時間的に1つ後方に位置する第2の時点のデータの値又は前記第2の時点のデータから前記第1の時系列データ内で前記第2の時点のデータより所定時間後に進んだ時点のデータまでの複数のデータの値の統計値である状態変化後データ値との差分値が所定の条件を満たす場合、
前記状態変化前データ値を利用して算出された値である状態変化前代表値を、第1の状態の特徴量として特徴量記憶手段が有する状態特徴量記憶手段に登録する第1の処理、
前記状態変化後データ値を利用して算出された値である状態変化後代表値を、前記第1の状態とは異なる第2の状態の特徴量として前記状態特徴量記憶手段に登録する第2の処理、
前記状態変化前代表値と前記状態変化後代表値の差分値を、第1の電気機器の特徴量として前記特徴量記憶手段が有する機器毎特徴量記憶手段に登録する第3の処理、及び、
前記状態変化前代表値、前記状態変化後代表値、及び、前記状態変化前代表値と前記状態変化後代表値の差分値の中の少なくとも1つを用いて、前記特徴量記憶手段を更新する第4の処理の中の少なくとも1つを実行する登録・更新手段、
として機能させるためのプログラム。
11-2. 11に記載のプログラムにおいて、
前記コンピュータを、
前記状態変化前代表値と前記状態変化後代表値の差分値が前記所定の条件を満たすか否か判定し、前記所定の条件を満たす場合、前記登録・更新手段に、前記状態変化前代表値、前記状態変化後代表値、前記状態変化前代表値と前記状態変化後代表値の差分値の中の少なくとも1つを送信する判定手段としてさらに機能させるためのプログラム。
11-3. 11-2に記載のプログラムにおいて、
前記判定手段に、前記状態変化前データ値と前記状態変化後データ値との差分値が所定の閾値以上である場合、前記所定の条件を満たすと判断させるプログラム。
11-4. 11-3に記載のプログラムにおいて、
前記判定手段に、前記第1の時系列データ内で前記第1の時点より所定時間前にさかのぼった時点のデータから前記第1の時点のデータまでの複数のデータの値、又は、前記第2の時点のデータから前記第1の時系列データ内で前記第2の時点のデータより所定時間後に進んだ時点のデータまでの複数のデータの値を利用して前記所定の閾値を算出させるプログラム。
11-5. 11から11-4のいずれかに記載のプログラムにおいて、
前記登録・更新手段に、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化前代表値と所定レベル以上近似する特徴量が前記状態特徴量記憶手段に記憶されているか確認させ、
記憶されていない場合は前記第1の処理を実行させ、記憶されている場合は前記第4の処理を実行させるプログラム。
11-6. 11から11-5のいずれかに記載のプログラムにおいて、
前記登録・更新手段に、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化後代表値と所定レベル以上近似する特徴量が前記状態特徴量記憶手段に記憶されているか確認させ、
記憶されていない場合は前記第2の処理を実行させ、記憶されている場合は前記第4の処理を実行させるプログラム。
11-7. 11から11-6のいずれかに記載のプログラムにおいて、
前記登録・更新手段に、前記状態変化前データ値と前記状態変化後データ値の差分値が前記所定の条件を満たす場合、前記状態変化前代表値と前記状態変化後代表値の差分値と所定レベル以上近似する特徴量が前記機器毎特徴量記憶手段に記憶されているか確認させ、
記憶されていない場合は前記第3の処理を実行させ、記憶されている場合は前記第4の処理を実行させるプログラム。
11-8. 11から11-7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、
前記第1の状態の時に稼働していた電気機器を識別する情報、前記第2の状態の時に稼働していた電気機器を識別する情報、及び、前記第1の状態から前記第2の状態に変化する際に電源のON/OFFを切り替えた電気機器を識別する情報の中の少なくとも1つのユーザ入力を受付ける入力受付手段としてさらに機能させ、
前記登録・更新手段に、前記特徴量記憶手段に記憶されている前記第1の状態の特徴量に、前記第1の状態の時に稼働していた電気機器を識別する情報を対応付ける処理、前記特徴量記憶手段に記憶されている前記第2の状態の特徴量に、前記第2の状態の時に稼働していた電気機器を識別する情報を対応付ける処理、前記特徴量記憶手段に記憶されている前記第1の電気機器の特徴量に、前記第1の状態から前記第2の状態に変化する際に電源のON/OFFを切り替えた電気機器を識別する情報を対応付ける処理の中の少なくとも1つを実行させるプログラム。
11-9. 11から11-8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、
前記特徴量記憶手段に記憶されている特徴量と、前記取得手段が取得した前記測定データとを利用して、複数の電気機器の稼動状態を推定する推定手段として機能させるプログラム。
Claims (9)
- 電気機器群に関する測定値及び/又は特徴量の時系列なデータである第1の時系列データを取得する取得手段と、
前記第1の時系列データにおける第1の時点のデータ値、及び、前記第1の時点より所定時間前にさかのぼった時点から前記第1の時点までの複数のデータ値の統計値のいずれかである状態変化前データ値と、前記第1の時点より後の第2の時点のデータ値、及び、前記第2の時点から前記第2の時点より所定時間後に進んだ時点までの複数のデータ値の統計値のいずれかである状態変化後データ値との差分値が所定の条件を満たす場合、前記所定の条件を満たす前記状態変化前データ値及び前記状態変化後データ値に対応する前記電気機器群の消費電流、消費電力及び入力電圧のいずれかの波形データから抽出された特徴量を、特徴量記憶手段に記憶する登録・更新手段と、を有する監視装置。 - 請求項1に記載の監視装置において、
前記登録・更新手段は、
前記状態変化前データ値に対応する部分の前記波形データから抽出された特徴量と、前記状態変化後データ値に対応する部分の前記波形データから抽出された特徴量との差分値を、第1の電気機器の特徴量として前記特徴量記憶手段に記憶する処理、
前記状態変化前データ値に対応する部分の前記波形データから抽出された特徴量を、第1の電気機器群の特徴量として前記特徴量記憶手段に記憶する処理、及び、
前記状態変化後データ値に対応する部分の前記波形データから抽出された特徴量を、第2の電気機器群の特徴量として前記特徴量記憶手段に記憶する処理、
の中の少なくとも1つを実行する監視装置。 - 請求項1または2に記載の監視装置において、
前記所定の条件は、前記第1の時点より所定時間前にさかのぼった時点のデータ値から前記第1の時点のデータ値までの複数のデータ値、又は、前記第2の時点のデータ値から前記第2の時点より所定時間後に進んだ時点のデータ値までの複数のデータ値を利用して決定した所定の閾値以上である監視装置。 - 請求項1から3のいずれか1項に記載の監視装置において、
前記登録・更新手段は、前記波形データから抽出された前記特徴量と所定レベル以上近似する特徴量が前記特徴量記憶手段に記憶されているか確認し、記憶されている場合、前記波形データから抽出された前記特徴量と、記憶されている特徴量とに基づいて、登録されている値を更新する監視装置。 - 請求項1から4のいずれか1項に記載の監視装置において、
前記登録・更新手段は、前記波形データから抽出された前記特徴量と所定レベル以上近似する特徴量が前記特徴量記憶手段に記憶されているか確認し、記憶されていない場合、前記波形データから抽出された前記特徴量を前記特徴量記憶手段に記憶する監視装置。 - 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1の状態の時に稼働していた電気機器を識別する情報、前記第2の状態の時に稼働していた電気機器を識別する情報、及び、前記第1の状態から前記第2の状態に変化する際に電源のON/OFFを切り替えた電気機器を識別する情報の中の少なくとも1つのユーザ入力を受付ける入力受付手段をさらに有し、
前記登録・更新手段は、前記特徴量記憶手段に記憶されている前記第1の状態の特徴量に、前記第1の状態の時に稼働していた電気機器を識別する情報を対応付ける処理、前記特徴量記憶手段に記憶されている前記第2の状態の特徴量に、前記第2の状態の時に稼働していた電気機器を識別する情報を対応付ける処理、前記特徴量記憶手段に記憶されている前記第1の電気機器の特徴量に、前記第1の状態から前記第2の状態に変化する際に電源のON/OFFを切り替えた電気機器を識別する情報を対応付ける処理の中の少なくとも1つを実行する監視装置。 - 請求項1から6のいずれか1項に記載の監視装置において、
前記特徴量記憶手段に記憶されている特徴量と、前記取得手段が取得した前記測定データとを利用して、複数の電気機器の稼動状態を推定する推定手段をさらに有する監視装置。 - コンピュータが、
電気機器群に関する測定値及び/又は特徴量の時系列なデータである第1の時系列データを取得する取得工程と、
前記第1の時系列データにおける第1の時点のデータ値、及び、前記第1の時点より所定時間前にさかのぼった時点から前記第1の時点までの複数のデータ値の統計値のいずれかである状態変化前データ値と、前記第1の時点より後の第2の時点のデータ値、及び、前記第2の時点から前記第2の時点より所定時間後に進んだ時点までの複数のデータ値の統計値のいずれかである状態変化後データ値との差分値が所定の条件を満たす場合、前記所定の条件を満たす前記状態変化前データ値及び前記状態変化後データ値に対応する前記電気機器群の総消費電流、総消費電力及び総入力電圧のいずれかの波形データから抽出された特徴量を、特徴量記憶手段に記憶する登録・更新工程と、
を実行する監視方法。 - コンピュータを、
電気機器群に関する測定値及び/又は特徴量の時系列なデータである第1の時系列データを取得する取得手段、
前記第1の時系列データにおける第1の時点のデータ値、及び、前記第1の時点より所定時間前にさかのぼった時点から前記第1の時点までの複数のデータ値の統計値のいずれかである状態変化前データ値と、前記第1の時点より後の第2の時点のデータ値、及び、前記第2の時点から前記第2の時点より所定時間後に進んだ時点までの複数のデータ値の統計値のいずれかである状態変化後データ値との差分値が所定の条件を満たす場合、前記所定の条件を満たす前記状態変化前データ値及び前記状態変化後データ値に対応する前記電気機器群の総消費電流、総消費電力及び総入力電圧のいずれかの波形データから抽出された特徴量を、特徴量記憶手段に記憶する登録・更新手段、
として機能させるためのプログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/905,585 US11002773B2 (en) | 2013-07-17 | 2014-07-07 | Monitoring apparatus, monitoring method, and storage medium |
JP2015527255A JP6455431B2 (ja) | 2013-07-17 | 2014-07-07 | 監視装置、監視方法及びプログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013148325 | 2013-07-17 | ||
JP2013-148325 | 2013-07-17 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015008645A1 true WO2015008645A1 (ja) | 2015-01-22 |
Family
ID=52346113
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/068068 WO2015008645A1 (ja) | 2013-07-17 | 2014-07-07 | 監視装置、監視方法及びプログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US11002773B2 (ja) |
JP (1) | JP6455431B2 (ja) |
WO (1) | WO2015008645A1 (ja) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016157927A1 (ja) * | 2015-03-31 | 2016-10-06 | 日本電気株式会社 | データ処理装置、データ処理方法、及び、プログラム |
WO2016157926A1 (ja) * | 2015-03-31 | 2016-10-06 | 日本電気株式会社 | データ処理装置、データ処理方法、及び、プログラム |
JP2017011963A (ja) * | 2015-06-25 | 2017-01-12 | 東芝ライテック株式会社 | 情報処理システム、情報処理方法、及びプログラム |
WO2017047296A1 (ja) * | 2015-09-17 | 2017-03-23 | 日本電気株式会社 | 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 |
WO2017126705A1 (ja) * | 2016-01-21 | 2017-07-27 | インフォメティス株式会社 | 機種識別システム、機種識別方法、および、機種識別プログラム |
JP2017201267A (ja) * | 2016-05-06 | 2017-11-09 | 日本電信電話株式会社 | 電流波形抽出方法 |
WO2018047263A1 (ja) * | 2016-09-08 | 2018-03-15 | 三菱電機株式会社 | 消費電力調整装置、消費電力調整システム、消費電力調整方法、及び、プログラム |
CN108885448A (zh) * | 2016-03-23 | 2018-11-23 | 日本电气株式会社 | 数据处理装置、数据处理系统、数据处理方法和程序 |
CN109711943A (zh) * | 2018-12-28 | 2019-05-03 | 杭州数梦工场科技有限公司 | 订单统计方法、装置及系统 |
JP2019140861A (ja) * | 2018-02-15 | 2019-08-22 | 中電技術コンサルタント株式会社 | 電力データ処理システム及び電力データ処理システムを用いて電力データを処理する方法 |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101557116B1 (ko) * | 2013-11-13 | 2015-10-02 | 주식회사 케이티 | 개별 부하의 운영상태를 추정하는 장치 및 방법 |
US20180254661A1 (en) * | 2015-09-03 | 2018-09-06 | Nec Corporation | Information output apparatus, and information output method |
JPWO2018146747A1 (ja) * | 2017-02-08 | 2019-02-14 | 三菱電機株式会社 | 情報処理装置、情報処理方法及び情報処理プログラム |
JP6993832B2 (ja) * | 2017-10-04 | 2022-01-14 | 株式会社日立製作所 | 分散エネルギーリソース管理装置、管理方法並びに管理システム |
JP7238508B2 (ja) * | 2019-03-19 | 2023-03-14 | 日本電気株式会社 | 分類装置、分類方法及び分類プログラム |
US20230010757A1 (en) * | 2021-07-12 | 2023-01-12 | PassiveLogic, Inc. | Device energy use determination |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012016270A (ja) * | 2010-07-02 | 2012-01-19 | Jiaotong Univ | 電気機器の状態を識別する電力監視装置とその電力監視方法 |
JP2013079853A (ja) * | 2011-10-03 | 2013-05-02 | Mitsubishi Electric Corp | 状態診断装置、状態診断システム及びプログラム |
JP2013518556A (ja) * | 2010-01-25 | 2013-05-20 | ジェネヴァ クリーンテック インコーポレイテッド | 家電機器の自動検出 |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH04273590A (ja) | 1991-02-28 | 1992-09-29 | Mitsubishi Heavy Ind Ltd | クラス分類用特徴量抽出装置 |
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 |
JP4048128B2 (ja) | 2003-01-10 | 2008-02-13 | 松下電工株式会社 | 電気機器管理システム |
GB2408592B (en) * | 2003-11-27 | 2005-11-16 | James Ian Oswald | Household energy management system |
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 |
JP2007225374A (ja) | 2006-02-22 | 2007-09-06 | Nec Corp | 電力測定システムおよびその測定方法 |
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 |
US20100070227A1 (en) * | 2008-09-18 | 2010-03-18 | Searete Llc, A Limited Liability Corporation Of The State Of Delaware | System and method for identifying appliances by electrical characteristics |
US9020769B2 (en) | 2009-01-26 | 2015-04-28 | Geneva Cleantech Inc. | Automatic detection of appliances |
WO2011148531A1 (ja) * | 2010-05-25 | 2011-12-01 | 三菱電機株式会社 | 電力情報管理装置及び電力情報管理システム及び電力情報管理方法 |
JP5218483B2 (ja) * | 2010-07-09 | 2013-06-26 | ソニー株式会社 | 電力コントロール装置 |
JP5751872B2 (ja) | 2011-03-14 | 2015-07-22 | 三菱電機株式会社 | 機器状態検出装置及び機器状態検出システム |
-
2014
- 2014-07-07 WO PCT/JP2014/068068 patent/WO2015008645A1/ja active Application Filing
- 2014-07-07 US US14/905,585 patent/US11002773B2/en active Active
- 2014-07-07 JP JP2015527255A patent/JP6455431B2/ja active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013518556A (ja) * | 2010-01-25 | 2013-05-20 | ジェネヴァ クリーンテック インコーポレイテッド | 家電機器の自動検出 |
JP2012016270A (ja) * | 2010-07-02 | 2012-01-19 | Jiaotong Univ | 電気機器の状態を識別する電力監視装置とその電力監視方法 |
JP2013079853A (ja) * | 2011-10-03 | 2013-05-02 | Mitsubishi Electric Corp | 状態診断装置、状態診断システム及びプログラム |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016157926A1 (ja) * | 2015-03-31 | 2016-10-06 | 日本電気株式会社 | データ処理装置、データ処理方法、及び、プログラム |
US10712375B2 (en) | 2015-03-31 | 2020-07-14 | Nec Corporation | Data processing device, data processing method, and non-transitory storage medium |
US10712374B2 (en) | 2015-03-31 | 2020-07-14 | Nec Corporation | Data processing device, data processing method, and non-transitory storage medium |
JPWO2016157926A1 (ja) * | 2015-03-31 | 2018-01-25 | 日本電気株式会社 | データ処理装置、データ処理方法、及び、プログラム |
JPWO2016157927A1 (ja) * | 2015-03-31 | 2018-01-25 | 日本電気株式会社 | データ処理装置、データ処理方法、及び、プログラム |
WO2016157927A1 (ja) * | 2015-03-31 | 2016-10-06 | 日本電気株式会社 | データ処理装置、データ処理方法、及び、プログラム |
JP2017011963A (ja) * | 2015-06-25 | 2017-01-12 | 東芝ライテック株式会社 | 情報処理システム、情報処理方法、及びプログラム |
JPWO2017047296A1 (ja) * | 2015-09-17 | 2018-07-05 | 日本電気株式会社 | 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 |
WO2017047296A1 (ja) * | 2015-09-17 | 2017-03-23 | 日本電気株式会社 | 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 |
JP2019053342A (ja) * | 2016-01-21 | 2019-04-04 | インフォメティス株式会社 | 機種識別システム、機種識別方法、および、機種識別プログラム |
WO2017126705A1 (ja) * | 2016-01-21 | 2017-07-27 | インフォメティス株式会社 | 機種識別システム、機種識別方法、および、機種識別プログラム |
US11281979B2 (en) | 2016-01-21 | 2022-03-22 | Informetis Corporation | Model identification system, model identification method, and model identification program |
CN108885448A (zh) * | 2016-03-23 | 2018-11-23 | 日本电气株式会社 | 数据处理装置、数据处理系统、数据处理方法和程序 |
US20190087186A1 (en) * | 2016-03-23 | 2019-03-21 | Nec Corporation | Data processing apparatus, data processing system, data processing method, and non-transitory storage medium |
US10831184B2 (en) | 2016-03-23 | 2020-11-10 | Nec Corporation | Data processing apparatus, data processing system, data processing method, and non-transitory storage medium |
JP2017201267A (ja) * | 2016-05-06 | 2017-11-09 | 日本電信電話株式会社 | 電流波形抽出方法 |
WO2018047263A1 (ja) * | 2016-09-08 | 2018-03-15 | 三菱電機株式会社 | 消費電力調整装置、消費電力調整システム、消費電力調整方法、及び、プログラム |
JP2019140861A (ja) * | 2018-02-15 | 2019-08-22 | 中電技術コンサルタント株式会社 | 電力データ処理システム及び電力データ処理システムを用いて電力データを処理する方法 |
CN109711943A (zh) * | 2018-12-28 | 2019-05-03 | 杭州数梦工场科技有限公司 | 订单统计方法、装置及系统 |
Also Published As
Publication number | Publication date |
---|---|
JP6455431B2 (ja) | 2019-01-23 |
JPWO2015008645A1 (ja) | 2017-03-02 |
US11002773B2 (en) | 2021-05-11 |
US20160154038A1 (en) | 2016-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6455431B2 (ja) | 監視装置、監視方法及びプログラム | |
CN105612546B (zh) | 用于能量测量的装置、服务器、系统和方法 | |
Reinhardt et al. | On the accuracy of appliance identification based on distributed load metering data | |
US20150377935A1 (en) | Signal identification methods and systems | |
JP6593325B2 (ja) | 監視装置、監視システム、監視方法及びプログラム | |
Ma et al. | Toward energy-awareness smart building: Discover the fingerprint of your electrical appliances | |
US20150268281A1 (en) | System and method for monitoring, analyzing and acting upon electricity patterns | |
KR101422682B1 (ko) | 전력 인입점 에너지 계측 장치 및 이를 통한 에너지 계측 정보 레이블링 시스템 | |
Batra et al. | Indic: Improved non-intrusive load monitoring using load division and calibration | |
JP2009047694A (ja) | コグニティブ電力メータ | |
JP6280485B2 (ja) | 省エネルギ支援システムおよび省エネルギ支援方法 | |
JP2013109742A (ja) | ユーザーフィードバック情報に基づく電気器具検出方法とシステム | |
JPWO2015151558A1 (ja) | 監視装置、監視システム、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 | |
KR101608328B1 (ko) | 전력소비 패턴 분석을 통한 디바이스 인식장치 및 그 방법 | |
WO2013011425A1 (en) | Multi-modal data improvement for power disaggregation systems | |
US20150355247A1 (en) | Apparatus, server, system and method for energy measuring | |
US11482861B2 (en) | Apparatus, server, system and method for energy measuring | |
JPWO2015151789A1 (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 | |
Englert et al. | Electricity-metering in a connected world: Virtual sensors for estimating the electricity consumption of iot appliances | |
JP6221443B2 (ja) | 監視装置、監視方法及びプログラム | |
KR102087026B1 (ko) | 시계열 분석 기법을 이용한 소비전력 패턴 분류 방법 및 장치 | |
JP6641235B2 (ja) | 負荷推定装置及び負荷推定方法 | |
US20230032081A1 (en) | Server, communicating device and system having function of managing power demand and method of managing power usage thereof | |
EP2650831A1 (en) | A method for determining an electricity consumption profile of a facility and a system |
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: 14825960 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015527255 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14905585 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: 14825960 Country of ref document: EP Kind code of ref document: A1 |