WO2015087473A1 - 需要予測装置、節電支援システム - Google Patents
需要予測装置、節電支援システム Download PDFInfo
- Publication number
- WO2015087473A1 WO2015087473A1 PCT/JP2014/005301 JP2014005301W WO2015087473A1 WO 2015087473 A1 WO2015087473 A1 WO 2015087473A1 JP 2014005301 W JP2014005301 W JP 2014005301W WO 2015087473 A1 WO2015087473 A1 WO 2015087473A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- power
- unit
- information
- power saving
- value
- Prior art date
Links
- 238000004134 energy conservation Methods 0.000 title 1
- 238000003860 storage Methods 0.000 claims abstract description 53
- 238000000605 extraction Methods 0.000 claims abstract description 52
- 239000000284 extract Substances 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims description 37
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 9
- 238000005265 energy consumption Methods 0.000 abstract 1
- 238000005406 washing Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000009825 accumulation Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 4
- 230000014509 gene expression Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000004378 air conditioning Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010411 cooking Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00004—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the power network being locally controlled
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
- H04Q9/02—Automatically-operated arrangements
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/10—The network having a local or delimited stationary reach
- H02J2310/12—The local stationary network supplying a household or a building
- H02J2310/14—The load or loads being home appliances
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
- H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
- H02J2310/62—The condition being non-electrical, e.g. temperature
- H02J2310/64—The condition being economic, e.g. tariff based load management
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
- Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
- Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
- Y02B70/3225—Demand response systems, e.g. load shedding, peak shaving
-
- 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
- Y04S20/222—Demand response systems, e.g. load shedding, peak shaving
-
- 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
-
- 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
- Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards
Definitions
- the present invention relates to a demand prediction device and a power saving support system, and in particular, a demand prediction device for predicting a power consumption state by a consumer, and a consumer by using a power consumption state predicted using the demand prediction device.
- the present invention relates to a power saving support system that supports power saving.
- an object of the present invention is to provide a demand prediction device that can predict information about power used in a building in a unit of a branch circuit without imposing a burden on the user in the building of the customer. Furthermore, the objective of this invention is providing the power saving assistance system using this demand prediction apparatus.
- the demand prediction device includes an acquisition unit that acquires, from a measurement device, a power value consumed for each of a plurality of branch circuits branched by a distribution board provided in a building of a power consumer,
- the first storage unit that stores the power information including the power value and date / time for each branch circuit acquired by the acquisition unit and the related information related to the power information in association with each other, and stores the information in the first storage unit
- the feature extraction unit that extracts the feature amount in the power information for each of the branched circuits, and the related information stored in the first storage unit is used as a condition for explaining the variation of the feature amount, and from the condition, the A rule extraction unit for extracting a rule for deriving a feature value, a second storage unit for storing the rule extracted by the rule extraction unit, and a target value for power saving in a predetermined target period are set for the building If the subject A prediction unit that obtains the related information in the period, and applies the rule stored in the second storage unit to the obtained related information, thereby
- a power saving support system includes the above-described demand prediction device and a presentation device that presents the method for power saving measures from the demand prediction device.
- the related information is used for each branch circuit.
- a rule for predicting the feature value of the power value is extracted for each building. Furthermore, using this rule, the feature value of the power value in the target period during which power is saved for the corresponding consumer is predicted. Therefore, there is an advantage that information regarding the power used in the building can be predicted in units of branch circuits without imposing a burden on the user in the building of the consumer.
- FIG. 1 is a block diagram illustrating a first embodiment.
- FIG. 3 is an operation explanatory diagram of the first embodiment.
- FIG. 6 is a block diagram illustrating another configuration of the first embodiment.
- FIG. 6 is a block diagram illustrating a second embodiment.
- the demand prediction apparatus 10 As shown in FIG. 1, the demand prediction apparatus 10 described below includes an acquisition unit 11, a first storage unit 12, a feature extraction unit 13, a rule extraction unit 14, a second storage unit 15, and a prediction unit 16. Prepare.
- the acquisition unit 11 acquires, from the measurement device 23, the power value consumed for each of the plurality of branch circuits 22 branched by the distribution board 21 provided in the building 20 of the power consumer.
- the first storage unit 12 stores the power information including the power value and date / time for each branch circuit 22 acquired by the acquiring unit 11 and related information related to the power information in association with each other.
- the feature extraction unit 13 extracts a feature amount in the power information for each branch circuit 22 stored in the first storage unit 12.
- the rule extraction unit 14 uses the related information stored in the first storage unit 12 as a condition for explaining the variation of the feature value, and extracts a rule for deriving the feature value from the condition.
- the second storage unit 15 stores the rules extracted by the rule extraction unit 14.
- the prediction unit 16 predicts a feature amount for each branch circuit 22 in the target period when a power saving target value in the predetermined target period is set for the building 20.
- the prediction unit 16 acquires related information in the target period in order to predict the feature amount for each branch circuit 22, and applies the rule stored in the second storage unit 15 to the acquired related information.
- the demand prediction apparatus 10 includes a third storage unit 17, a countermeasure determination unit 18, and an output unit 42.
- the third storage unit 17 stores names that specify the plurality of branch circuits 22 in association with the plurality of branch circuits 22, respectively.
- the measure determining unit 18 uses the branch circuit 22 and the power saving measure that are targets of the power saving measure in order to achieve the target value among the plurality of branch circuits 22 on the condition that the prediction unit 16 predicts the feature amount and related information for the target period. The method is determined.
- the output unit 42 extracts a name for the branch circuit 22 determined by the measure determining unit 18 as a power saving measure target with reference to the third storage unit 17, and uses the name to provide a power saving measure method to the presentation device 30. Let them present.
- the feature extraction unit 13 has a function of calculating the variance of the period during which power is consumed for each branch circuit 22 using the power information.
- the measure determining unit 18 causes the presentation device 30 to present a peak shift as the best power saving measure and presents a peak cut as the next best power save measure when there is a branch circuit 22 whose variance is greater than or equal to a predetermined reference value. 30 is desirable.
- the peak shift means a measure for not using the electrical load 24 connected to the branch circuit 22 in the target period, and the peak cut is the target period for the branch circuit 22 having a relatively large power predicted by the prediction unit 16 as a feature amount. This means measures to reduce power consumption.
- the measure determining unit 18 selects and presents a time zone in which the target electrical load 24 can be used from a time zone in which the electrical load 24 has been used in the past. It is desirable.
- the time zone in which the electrical load 24 has been used in the past is selected by using the power information stored in the first storage unit 12.
- the related information includes at least one type of information selected from the group of calendar information, weather information, user information, and building information.
- the calendar information includes the season and the day of the week, and the weather information includes the weather and the outside temperature.
- the user information is an attribute of a user who uses power in the building 20, and the building information is an attribute of the building 20.
- the acquiring unit 11 acquires the power values measured by the plurality of measuring devices 23 provided in the buildings 20 of the plurality of consumers, in addition to the power value measured by the measuring device 23 in the building 20.
- the rule extraction unit 14 includes an evaluation unit 141 and a grouping unit 142 as shown in FIG.
- the evaluation unit 141 obtains an evaluation value indicating the degree of similarity between the buildings 20 for the rules extracted for each of all the buildings 20 of the building 20 and the plurality of buildings 20.
- the grouping unit 142 compiles these rules into one rule when the evaluation values of rules obtained from two or more buildings 20 out of all the buildings 20 are similar within a predetermined range.
- the second storage unit 15 stores the rules in association with the two or more buildings 20 so that the rules compiled by the grouping unit 142 are applied to the two or more buildings 20 corresponding thereto. It is desirable to do.
- each dwelling unit may be regarded as one building 20 in the present embodiment, or the entire dwelling unit may be referred to as one building 20 as in the case of performing high-voltage collective power reception.
- the building 20 means a building occupied by a customer from whom the electric utility collects charges.
- the demand prediction apparatus 10 described below includes a computer that executes a program that realizes the functions described below as a main hardware element.
- This program may be provided through a telecommunication line such as the Internet in addition to being stored in advance in a ROM (Read Only Memory).
- the program may be provided by a computer-readable recording medium.
- the building 20 includes a distribution board 21 that receives commercial power supplied by an electric power company.
- the distribution board 21 branches the received power to a plurality of branch circuits 22 and distributes the power to a plurality of electric loads 24 used in the building 20.
- the measuring device 23 measures the power consumed for each branch circuit 22.
- the measuring device 23 employs either a configuration built in the distribution board 21 or a configuration arranged outside the distribution board 21.
- the measuring device 23 monitors the passing current for each branch circuit 22 with a Rogowski coil or a clamp-type current sensor, and uses the integrated value of the product of the monitored current value and the voltage value between the lines of the branch circuit 22 as a power value. calculate. That is, the power value measured by the measuring device 23 is not actually instantaneous power but an amount of power per predetermined unit time (for example, selected in a range of about 30 seconds to 10 minutes). In general, the instantaneous power for each branch circuit 22 fluctuates with time even within a unit time, but in this embodiment, the fluctuation of the instantaneous power within the unit time is not taken into account, and the integrated power in the unit time is taken into account. Use quantity as power value. This power value can be regarded as equivalent to the average power value in unit time.
- the power value measured by the measuring device 23 is input information to the demand prediction device 10 together with related information.
- the demand prediction device 10 includes an acquisition unit 11 that acquires a power value.
- the power value acquired from the measurement device 23 through the acquisition unit 11 is associated with the date and time and is stored in the first storage unit 12 as power information. Is done.
- the date and time is measured by a built-in clock 19 such as a real-time clock built in the demand prediction apparatus 10.
- the power information includes the power value for each unit time and the date and time when the power value was obtained.
- the related information is information that is assumed to be related to the power consumed by the electrical load 24 used in the building 20, and includes at least one of calendar information, weather information, user information, and building information. Including.
- Calendar information includes seasons (four seasons, 24th season etc.) and days of the week (separate holidays and weekdays). Seasons are related to temperature trends and sunshine hours, and days of the week are related to the types of living behavior and timing (time) of residents, so the power consumed by the electrical load 24 used for air conditioning, lighting, cooking, etc. It is assumed to be related.
- the weather information includes the weather (sunny weather, cloudy weather, rainy weather, etc.) and the outside temperature. The weather and outside air temperature are also easily assumed to be related to the power consumed by the electric load 24 used for air conditioning, lighting, cooking, and the like.
- the user information is an attribute of a user who uses the electrical load 24 in the building 20, and includes the family configuration (number of people, gender, age group, etc.), income, values (energy saving orientation, comfort orientation, etc.) in the building 20. Including.
- the user attribute is expected to reflect the power consumption tendency of the entire building 20.
- the building information includes the geographical position of the house (region, topography, etc.), the type of building (separate from a detached house and an apartment house), and the room configuration (2LDK, 3LDK, etc.). Such building information is expected to relate to the power consumed by the electrical load 24 used for air conditioning, lighting, and the like.
- the demand prediction apparatus 10 includes an input unit 43 for receiving user information and building information, and a communication unit 44 serving as an interface with a telecommunication line. User information, building information, and the like are input to the input unit 43 using an input device capable of interactive input.
- the demand prediction apparatus 10 can select a configuration provided in the building 20 and a configuration provided in the server. Moreover, you may employ
- the acquisition unit 11, the first storage unit 12, the feature extraction unit 13, the rule extraction unit 14, and the second storage unit 15 are provided in the server, and the prediction unit 16, the third storage unit 17, and the countermeasure determination unit 18 are provided. May be provided in the building 20.
- the output unit 42 and the input unit 43 can be configured to connect a dedicated operation indicator that is also used as the presentation device 30 and the input device.
- a terminal device that can communicate with the demand prediction device 10 can also be used as the presentation device 30 and the input device.
- the output unit 42 and the input unit 43 communicate with the terminal device through the communication unit 44.
- a terminal device capable of communicating with the server through an electric communication line such as the Internet or a mobile telephone network may be used as both the presentation device 30 and the input device.
- the output unit 42 and the input unit 43 communicate with the terminal device through the communication unit 44.
- the terminal device a smartphone, a tablet terminal, or the like can be adopted in addition to a personal computer.
- the output unit 42 and the input unit 43 can adopt the same configuration as that in the case where the demand prediction device 10 is provided in the building 20. Further, in this configuration, a component having a large processing load can be provided on a server having a high processing capacity, and a component requiring individual processing for each building 20 can be provided on the building 20 side. Is possible. That is, the throughput can be shortened and an increase in communication traffic can be suppressed.
- the acquisition unit 11 acquires the power value for each branch circuit 22 measured by the measurement device 23, and the first storage unit 12 measures the power value acquired by the acquisition unit 11 and the built-in clock 19.
- the date and time are stored in association with each other.
- the feature extraction unit 13 extracts the feature value of the power value.
- the accumulation period is preferably several years. However, if the feature extraction unit 13 extracts the feature amount after a long accumulation period, the operation start is delayed. Therefore, the feature amount is extracted with a relatively short period of about one month as the accumulation period, and thereafter, an appropriate accumulation period is set. It is desirable to gradually increase accuracy by opening and extracting feature quantities.
- the feature extraction unit 13 obtains, as the feature amount, the power consumption amount for each branch circuit 22 in units of days and the maximum value of the power value in units of days for each branch circuit 22. Further, the feature extraction unit 13 extracts a period of continuous use of the electrical load 24 for each branch circuit 22. That is, the feature extraction unit 13 estimates the standby power value for each branch circuit 22 based on the change in the power value during the accumulation period stored in the first storage unit 12, and the power value continues with respect to the standby power. And determine the period of increase.
- the comparison value V1 to be compared with the power value is variably set, and the range satisfying the condition that the time during which the power value is equal to or less than the comparison value exceeds a predetermined maintenance time is satisfied.
- the minimum value of the comparison value is obtained by using the minimum value as the maximum value in standby power.
- the maintenance time is set to a time slightly shorter than the period in which the electrical load 24 is estimated not to be used.
- the illustrated example shows an operation of searching for standby power by gradually reducing the comparison value V1.
- the feature extraction unit 13 estimates standby power for each branch circuit 22, and when a period in which the power value is equal to or higher than standby power continues, the electrical load 24 connected to the branch circuit 22 is used ( It is in operation).
- the feature extraction unit 13 refers to a period in which the electric load 24 is continuously used as a period in which the electric power value is continuously increased. I can judge.
- the electrical load 24 is continuously used at the location corresponding to the branch circuit 22 (generally a room). Is determined to be a period (t1-t2).
- the feature extraction unit 13 can determine the period during which the electric load 24 is used, it can obtain the time when the operation of the electric load 24 starts and the time when the operation ends.
- the feature amount extracted by the feature extraction unit 13 includes, for example, the maximum value of the power value for each branch circuit 22 during the use period of the electric load 24 and the amount of power consumed during the use period of the electric load 24. Further, the feature amount extracted by the feature extraction unit 13 may include a time t1 at which the use of the electric load 24 is started and a time t2 at which the use is ended.
- the feature extraction unit 13 calculates the variance of the period during which power is consumed for each branch circuit 22. It is desirable to have a function.
- the feature extraction unit 13 may treat the output setting state as a feature amount together with the power value for the electric load 24 capable of adjusting the output.
- the electric load 24 is an air conditioner
- a set state such as a set temperature and an air volume may be used as the feature amount.
- the feature amount extracted by the feature extraction unit 13 is input to the rule extraction unit 14 together with the related information when the feature amount is obtained, and the rule extraction unit 14 evaluates the relationship between the feature amount and the related information. Is done. That is, a rule for deriving a feature amount is extracted using the related information as a condition for explaining the variation of the feature amount.
- the rule extraction unit 14 can evaluate a correlation coefficient between a feature quantity and individual related information, and can derive a feature quantity using the relevant information as a condition when the absolute value of the correlation coefficient exceeds a predetermined threshold.
- the rules are expressed in the form of, for example, a mathematical expression using related information as an explanatory variable, a data table in which related information and feature quantities are associated with each other.
- the rule may be expressed by a production rule in which when the related information is established, the feature amount of the corresponding branch circuit 22 is obtained.
- the related information for deriving the feature amount may be a single condition, but often includes a plurality of conditions. Further, the rules can be set for each building 20. In other words, there is a possibility that the number of combinations for extracting the rule that links the feature quantity to the related information may be very large. Therefore, it is desirable to provide the rule extraction unit 14 on a server with high processing capability.
- the related information uses season (spring, summer, autumn and winter), distinction between weekdays and holidays, and weather (sunny weather, rainy weather).
- the feature amount uses the daily power consumption for each branch circuit 22 and the maximum daily power value for each branch circuit 22.
- the relationship between the related information and the feature amount can be expressed in a table format as shown in Table 1.
- Table 1 includes the average value and variance of the number of times that the electrical load 24 is operated in one day, the operation time in one use, the start time, and the end time.
- the related information and feature amount shown in Table 1 are examples, and it is possible to increase the variable of the weather that is the related information (for example, cloudy weather, snowfall, etc.), and it is also possible to increase the types of related information. (For example, temperature, humidity, etc.)
- the rule extraction unit 14 may divide the feature quantity into a plurality of sections (for example, divide the maximum power value into three sections), obtain the occurrence frequency for each section, and generate a histogram.
- the rules extracted by the rule extraction unit 14 are stored in the second storage unit 15 as a database (knowledge base). If a rule is registered in the second storage unit 15 in advance, it is possible to obtain a feature amount by applying the corresponding rule when related information is given. Therefore, when the target value of power saving in the predetermined target period is set for the building 20, if the related information in the target period is acquired, the feature amount in the target period can be obtained.
- the target value may be set by the building 20 for power saving, and may be given as demand response information (DR information) for requesting power saving from an electric power company.
- the prediction unit 16 first acquires related information in the target period when the target value of power saving in the target period is set.
- the process of acquiring related information includes a process of acquiring information from another server through a telecommunication line. For example, if the related information is weather, information that predicts the weather in the target period may be acquired from a server having weather forecast information.
- the prediction unit 16 applies the rule stored in the second storage unit 15 to the acquired related information and predicts the feature value regarding the power value.
- the prediction unit 16 obtains the season, weekday and holiday, and weather as related information for the corresponding day. Furthermore, the prediction unit 16 extracts a rule applicable to the acquired related information from the second storage unit 15 and obtains the maximum value of the power value as the feature amount using the extracted rule.
- the target value When the target value is given by a power saving request from an electric power company, the maximum power value of the entire building 20 (house) in a predetermined time zone becomes the target value. Therefore, in this case, the sum of the power values of all the branch circuits 22 in the building 20 (house) is obtained, and it is determined whether or not power saving is performed based on whether or not the total power value exceeds the target value in the target period. It becomes a standard. As described above, when it is possible to predict whether or not the power value consumed by the building 20 during the target period exceeds the target value, the demand prediction device 10 outputs the predicted result from the output unit 42 and sends it to the appropriate presentation device 30. Let them present. By presenting to the presentation device 30 whether or not the target value can be achieved in the target period, the user can make a decision as to whether or not to save power.
- the presentation device 30 may be a dedicated display device that combines a flat panel display such as a liquid crystal display and a touch panel or push button switch.
- a terminal device such as a personal computer, a smartphone, or a tablet terminal can be used as the presentation device 30.
- the demand prediction apparatus 10 has a function of showing power saving measures for achieving the target value when the target value cannot be achieved. Therefore, the demand prediction device 10 includes a countermeasure determining unit 18. The measure determining unit 18 determines whether the power value set for the target period can achieve the target value by comparing the feature amount predicted by the predicting unit 16 with the target value, and when the target value cannot be achieved. Establish a method to save power.
- the power value can achieve the target value is set for the power saving request because the target value is set for the maximum value of the power value.
- the maximum value of the power value is less than or equal to the target value. This means that the target value has been achieved.
- the target value of the power value is set for the power consumption, so if the power consumption during the target period is less than or equal to the target value, the target value has been achieved. become. Below, the case where the target value with respect to a power-saving request
- the countermeasure determining unit 18 employs two types of peak shift and peak cut as power saving countermeasure methods.
- the peak shift means a measure for shifting the time zone in which the electric load 24 is operated from the target period so that the electric load 24 connected to the branch circuit 22 is not used in the target period.
- the peak cut means a measure for reducing the power consumed in the target period for the branch circuit 22 having a relatively large power predicted by the prediction unit 16 as a feature value.
- the measure determining unit 18 may employ either peak shift or peak cut as a power saving measure.
- the measure determining unit 18 may include adjusting the output of the electrical load 24 as a power saving measure option. For example, when the electric load 24 is an air conditioner, adjusting the set temperature, the air volume, etc. will adjust the output of the electric load 24. Since power saving measures can be set for each branch circuit 22, different power saving measures are determined for each branch circuit 22. In addition, it is preferable that a plurality of power saving measures can be selected for the branch circuit 22 and which power saving measures are adopted according to the related information or the feature amount.
- the measure determining unit 18 stores options for the power saving measure method so that the predictor 16 can select the power save measure according to the condition when the feature amount is predicted in the target period.
- the measure determining unit 18 includes a database (knowledge base) that stores rules for selecting a method for saving power. Options for power saving measures are determined in advance, and a rule for selecting which option under what conditions is registered in the measure determining unit 18 according to the building 20.
- the measure determination unit 18 determines the peak shift It is desirable to adopt this in preference to peak cut. That is, a large dispersion of at least one of the start time and the end time means that there is a large variation in the time zone in which the corresponding electric load 24 is used. This change is expected to be easily accepted by users.
- the measure determination unit 18 evaluates whether the variance is equal to or greater than a predetermined reference value. To do. Then, when there is a branch circuit 22 whose variance is greater than or equal to a predetermined reference value, the measure determining unit 18 employs peak shift as the best power saving measure and employs peak cut as the next best power save measure. The power saving measure adopted by the measure determining unit 18 is presented to the presentation device 30 through the output unit 42.
- the name of the electrical load 24 that occupies the branch circuit 22 that is the target of power saving measures, or the location (room) corresponding to the branch circuit 22 that is the target of power saving measures. is preferably shown on the presentation device 30. That is, by presenting the name of the electrical load 24 or the location on the presentation device 30, it becomes easier for the user to understand which electrical load 24 or at which location the power saving measure should be taken.
- the third storage unit 17 stores names specifying the plurality of branch circuits 22 in association with the plurality of branch circuits 22, respectively.
- the information stored in the third storage unit 17 is written according to the building 20 by the user or the contractor before operating the demand prediction device 10. Information may be written into the third storage unit 17 using an operating device (such as a touch panel or a keyboard) provided in the presentation device 30 described above.
- the electrical load 24 or the place (room) corresponds to the branch circuit 22 on a one-to-one basis.
- the branch circuit 22 is named as “living air conditioner” “Japanese-style air conditioner” “western-style air conditioner” “living room (outlet)” “kitchen / lavatory” “washing machine” “refrigerator” “western room (outlet)”. Can be specified.
- the measure determining unit 18 determines the branch circuit 22 that is the target of the power saving measure
- the measure determining unit 18 extracts the name corresponding to the branch circuit 22 from the third storage unit 17, and the power save target target indicated by the name is the power save measure target.
- the presentation apparatus 30 is made to present the method.
- the measure determining unit 18 may present a time zone in which the target electrical load 24 can be used to the presentation device 30.
- This time zone may be selected from a time zone in which the target electrical load 24 has been used in the past.
- the first storage unit 12 records the use of the target electrical load 24 in a time zone that is not the target period, the time zone in which the target electrical load 24 can be used in that time zone. It is recommended as.
- the time zone may be selected from the one with the higher frequency of use.
- the past unit can be used as the selection criterion, as well as the past performance as a selection criterion.
- the motivation to implement power saving measures by peak shift by presenting the corresponding time zone to the user Can be given.
- Table 2 shows an example of a power saving countermeasure method for each branch circuit 22 registered in the countermeasure determination unit 18.
- Table 2 shows an example of the content presented to the presentation device 30 in accordance with the power saving countermeasure method.
- the power saving measures include “reduction of use time (deletion of drying)” and “shift of start time”. "Recommended time zone”.
- the prediction unit 16 predicts a feature amount, which is the amount of power consumption per day, on the condition that the related information is a summer holiday. Furthermore, the prediction unit 16 selects the branch circuit 22 having the maximum power consumption, and predicts the feature amount (for example, the maximum value of the power value) in the time period that is the target period for the selected branch circuit 22. Here, the prediction unit 16 may obtain the maximum value of the power value in the power saving request time zone (target period) for all the branch circuits 22.
- the target value can be achieved by reducing the power value of the branch circuit 22 having the largest power value.
- the name of the branch circuit 22 predicted by the prediction unit 16 that the maximum power value is the largest in the target time period is “living air conditioner”.
- the most effective way to reduce the power value is to select a power saving measure that reduces the power consumed by the “living air conditioner”. Therefore, the user can be presented with a power saving measure method by showing the presentation device 30 the specific presentation contents such as “Can you reduce the power consumption of the air conditioner in the living room”?
- branch circuit 22 having the largest power value next to “living air conditioner” is predicted to be “living (outlet)”.
- specific details such as “Can you turn off any electrical devices you use in the living room?” "Can you reduce the power consumption of the electrical devices you use in the living room?” By this, it is possible to show the user the next best power saving countermeasure method.
- the user can select a method that is easy for the user to save power.
- FIG. 3 shows a configuration in which the demand prediction device 10 is provided separately from the building 20 and collects power values measured by the measuring device 23 from a plurality of buildings 20. In the illustrated example, only one building 20 is illustrated, but it is assumed that a plurality of buildings 20 exist in addition to the building 20 in the implementation.
- the rule extraction unit 14 evaluates in order to find a rule common to two or more buildings 20 in all the buildings 20 of the illustrated building 20 and a plurality of buildings 20 not illustrated.
- the rule extraction unit 14 uses user information and building information as related information.
- the user information is information related to user attributes in the building 20
- the building information is information related to building attributes in the building 20.
- the rule extraction unit 14 extracts the rule for deriving the feature amount from the related information as described above for each building 20, and then the evaluation unit 141 determines the similarity between the buildings 20 for the rule extracted for each building 20. An evaluation value representing the degree is obtained.
- the degree of similarity can be determined by the formula type and the coefficient if the rule is expressed by a mathematical expression, and by the distance between data included in the data table if the rule is expressed by a data table. It is possible. In the latter case, the distance may be either the Euclidean distance or the Manhattan distance.
- the grouping unit 142 uses the evaluation values obtained by the evaluation unit 141 and combines the rules obtained for different buildings 20 into one rule when the evaluation values are similar within a predetermined range.
- the rules are mathematical expressions, for example, the rules can be combined into one by using an average value of coefficients included in a plurality of mathematical expressions or a weighted average value.
- the rule is a data table, for example, the rules can be combined into one by using an average value or a weighted average value of data included in the data table.
- the rules set in this way are relatively likely to be applied to the building 20 in which at least one of the user information and the building information is similar. Therefore, by applying the obtained rule to the power information and related information for each building 20 stored in the first storage unit 12, can the rule obtained by the grouping unit 142 be applied to the corresponding building 20? What is necessary is just to verify. The rule verified to be applicable is applied to the building 20 in which at least one of the user information and the building information is similar.
- the demand prediction apparatus 10 when a rule is shared by a plurality of buildings 20, power values must be collected from the plurality of buildings 20. That is, it is desirable that the demand prediction apparatus 10 that performs this process is shared by a plurality of buildings 20. Therefore, it is desirable that the demand prediction device 10 is configured by a server configured to acquire the power value measured by the measurement device 23 provided for each building 20 by communication.
- the presentation apparatus 30 since the presentation apparatus 30 should just be communicable with a server, as above-mentioned, it implement
- the demand prediction apparatus 10 shown in FIG. 1 is provided for each building 20, and the server is provided with a configuration corresponding to the acquisition unit 11, the first storage unit 12, and the rule extraction unit 14, and extracted by the server.
- the structure which provides a rule to the demand prediction apparatus 10 of the building 20 may be sufficient.
- the case where the building 20 is a detached house or an apartment house is assumed, and a case in which a power saving measure method is shown for each branch circuit 22 in the building 20 is illustrated.
- a configuration may be adopted in which a method for power saving measures is individually presented to a dwelling unit with high power consumption instead of the branch circuit 22.
- a dwelling unit terminal that also serves as an intercom device installed for each dwelling unit can be used as the presentation device 30.
- the demand prediction device 10 estimates the feature quantity corresponding to each of the plurality of electric loads 24 that consumes power using the feature quantity extracted by the feature extraction unit 13.
- the unit 41 is provided.
- the rule extraction unit 14 determines a rule for deriving a feature amount related to the electrical load 24 from related information when the estimation unit 41 estimates the feature amount of the electrical load 24 among the plurality of electrical loads 24. It is desirable to have a function of extracting. It is desirable that the prediction unit 16 has a function of predicting a feature amount corresponding to each of the plurality of electric loads 24 in the target period.
- the demand prediction device 10 desirably includes a third storage unit 17, a countermeasure determination unit 18, and an output unit 42.
- the third storage unit 17 stores names that respectively identify the plurality of electrical loads 24 in association with the plurality of electrical loads 24.
- the measure determining unit 18 uses the electrical load 24 that is a target of power saving measures in order to achieve the target value among the plurality of electrical loads 24 on the condition that the prediction unit 16 predicts the feature amount and the related information for the target period. Determine how to save electricity.
- the output unit 42 refers to the third storage unit 17 to extract the name of the electric load 24 determined by the measure determining unit 18 as a power saving measure target, and uses the name to provide a method for power saving measure to the presentation device 30. Let them present.
- the feature extraction unit 13 desirably has a function of calculating the variance of the period during which power is consumed for each electrical load 24 using the power information.
- the countermeasure determining unit 18 causes the presentation device 30 to present a peak shift as the best power saving measure when there is an electric load 24 whose variance is equal to or greater than a predetermined reference value, and presents a peak cut as the next best power saving measure. 30 is desirable.
- the peak shift means a measure not to use the electric load 24 in the target period, and the peak cut reduces the power consumed in the target period for the electric load 24 that has a relatively large power predicted by the prediction unit 16 as a feature amount. Means countermeasures.
- the first embodiment presents a power saving countermeasure method in units of the branch circuit 22, while this embodiment describes a technique for presenting a power saving countermeasure method in units of the electrical load 24.
- the estimation unit 41 estimates the feature amount for each electrical load 24 that has consumed power, using the feature amount extracted by the feature extraction unit 13. With this configuration, even when a plurality of electrical loads 24 are connected to one branch circuit 22, it is possible to individually extract feature amounts of the electrical loads 24 connected to the target branch circuit 22. .
- the estimation unit 41 is made to learn in advance a rule for associating the feature value of the power value with each electrical load 24, and the estimation unit 41 can estimate the electrical load 24 by applying the learned rule to the feature value. It is.
- each feature of the electrical load 24 is associated with the electrical load 24 using a feature amount extracted from the power value when it is known that the electrical load 24 is in use.
- the feature amount includes, for example, the magnitude of standby power when the electric load 24 is not used, the range of change in the power value when the use of the electric load 24 is started, and the power value during use of the electric load 24.
- the maximum value and the usage period of the electric load 24 are used in combination. It is possible to derive a rule for specifying the electric load 24 from the condition obtained by combining these feature amounts.
- the acquisition unit 11 acquires a power amount per unit time of about 30 seconds to 10 minutes as a power value, compared with a case where the electric load 24 is estimated using an instantaneous value of power, the power There is no need to increase the sampling cycle for obtaining the value. Therefore, the power sensor (current sensor) used in the measurement device 23 can be provided at a lower cost than a high-speed configuration with a short sampling cycle. That is, in this embodiment, when estimating the electrical load 24 from the power value, it is not necessary to perform frequency analysis of the power waveform to detect a fundamental wave or a harmonic, and the electrical load 24 can be simply configured with a simple configuration. It can be estimated.
- the estimation unit 41 can estimate the type of the electric load 24 from the feature value of the power value. That is, for the branch circuit 22 corresponding to a living room outlet, the feature extraction unit 13 estimates the value of standby power as in the first embodiment. When the power value increases with respect to the standby power value, the feature extraction unit 13 extracts the power value increment as a feature amount, and the estimation unit 41 collates this feature amount with the database. The type is estimated.
- the electric load 24 used may vary depending on the increment of the power value. Can be presumed to be a television receiver.
- the type of the electrical load 24 can be estimated. Therefore, a feature amount is derived for each electrical load 24 using the related information as a condition. It becomes possible to extract rules. That is, the rule extraction unit 14 of this embodiment extracts a rule for each type of the electrical load 24 estimated by the estimation unit 41. For the electrical loads 24 corresponding to the branch circuit 22 on a one-to-one basis, the rules are extracted in units of the branch circuit 22 as in the first embodiment. The technique for extracting the rules is the same as in the first embodiment. That is, the feature quantity derived on the condition of the relevant information in the rule is different from that in the first embodiment in that it is not in each branch circuit 22 but in each electric load 24. Become a function.
- the prediction unit 16 predicts the electrical load 24 with relatively large power consumption in the target period in which the target value needs to be achieved, and the countermeasure determination unit 18 determines the corresponding electrical load 24. Establish a method to save power. Note that the power saving request requires that the maximum power value of the entire building 20 in the target period be equal to or less than the target value.
- the measure determining unit 18 determines a power saving measure method so that the power value is equal to or lower than the target value. For example, it is assumed that the washing machine is not operating before the target period, and it is predicted that the period during which the washing machine and the air conditioner in the living room are simultaneously operated is included in the time period of the target period.
- the measure determining unit 18 extracts methods for power saving measures such as a peak cut for reducing the power consumption of the air conditioner in the living room and a peak shift for shifting the operation time of the washing machine. Further, the measure determining unit 18 determines whether or not a peak shift is possible in the corresponding building 20 from the dispersion of at least one of the operation time, the start time, and the end time when the washing machine has been operated in the past. To do. That is, the measure determining unit 18 estimates that the peak shift is possible when the time zone in which the washing machine is used varies.
- the peak shift is proposed so that the time zone in which the washing machine is used is shifted to a time zone different from the target period, and the air conditioner can be used in the target period.
- the electric load 24 capable of peak shift includes a washing machine and a dishwasher.
- the user can easily accept the time zone in which the peak shift is performed by proposing a time zone in which the unit price of the electricity bill is low.
- the countermeasure determination part 18 may propose a peak shift so that a dishwasher may be used in the time zone when the power consumption by the other electric load 24 predicted by the prediction part 16 is small.
- the set temperature and the air volume can be included in the power saving measures.
- information that the power value is XX [W] when the set temperature is 26 ° C. and the air volume is strong is stored in the first storage unit 12 as power information, and the set temperature is set during the power saving request target period. Is assumed to be 26 ° C. and the air volume is predicted to be strong.
- the measure determining unit 18 sets the set temperature to 28 ° C. and the air volume to be weak.
- the power value can be reduced by Y [W].
- the present embodiment is the same as the first embodiment except that when a plurality of electrical loads 24 are connected to one branch circuit 22, the electrical loads 24 are distinguished and power saving measures can be taken for each electrical load 24. It is. Therefore, also in this embodiment, the buildings 20 in which at least one of the user information and the building information is similar can be handled as a group for a plurality of buildings 20.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Power Engineering (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Computer Networks & Wireless Communication (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
Description
図1に示すように、以下に説明する需要予測装置10は、取得部11と第1の記憶部12と特徴抽出部13と規則抽出部14と第2の記憶部15と予測部16とを備える。取得部11は、電力の需要家の建物20に設けられた分電盤21で分岐された複数の分岐回路22に対してそれぞれ消費された電力値を計測装置23から取得する。第1の記憶部12は、取得部11が取得した分岐回路22ごとの電力値および日時を含む電力情報と、電力情報に関連した関連情報とを対応付けて記憶する。特徴抽出部13は、第1の記憶部12に格納された分岐回路22ごとの電力情報における特徴量を抽出する。規則抽出部14は、第1の記憶部12に格納された関連情報を特徴量の変動を説明する条件とし、当該条件から特徴量を導き出す規則を抽出する。第2の記憶部15は、規則抽出部14が抽出した前記規則を格納する。予測部16は、建物20に対して所定の対象期間における節電の目標値が設定された場合に、対象期間における分岐回路22ごとの特徴量を予測する。予測部16は、分岐回路22ごとの特徴量を予測するために、対象期間における関連情報を取得し、取得した関連情報に第2の記憶部15に格納された前記規則を適用する。
本実施形態において、図4に示すように、需要予測装置10は、特徴抽出部13が抽出した特徴量を用いて電力を消費した複数の電気負荷24の各々に対応する特徴量を推定する推定部41を備える。この構成において、規則抽出部14は、推定部41が複数の電気負荷24のうちの電気負荷24の特徴量を推定している場合に、当該電気負荷24に関する特徴量を関連情報から導き出す規則を抽出する機能を有することが望ましい。予測部16は、対象期間における複数の電気負荷24の各々に対応する特徴量を予測する機能を有することが望ましい。
Claims (10)
- 電力の需要家の建物に設けられた分電盤で分岐された複数の分岐回路に対してそれぞれ消費された電力値を計測装置から取得する取得部と、
前記取得部が取得した前記分岐回路ごとの電力値および日時を含む電力情報と、前記電力情報に関連した関連情報とを対応付けて記憶する第1の記憶部と、
前記第1の記憶部に格納された前記分岐回路ごとの前記電力情報における特徴量を抽出する特徴抽出部と、
前記第1の記憶部に格納された前記関連情報を前記特徴量の変動を説明する条件とし、当該条件から前記特徴量を導き出す規則を抽出する規則抽出部と、
前記規則抽出部が抽出した前記規則を格納する第2の記憶部と、
前記建物に対して所定の対象期間における節電の目標値が設定された場合に、前記対象期間における前記関連情報を取得し、取得した前記関連情報に前記第2の記憶部に格納された前記規則を適用することによって、前記対象期間における前記分岐回路ごとの前記特徴量を予測する予測部とを備える
ことを特徴とする需要予測装置。 - 前記複数の分岐回路をそれぞれ特定する名称を、前記複数の分岐回路にそれぞれ対応付けて格納した第3の記憶部と、
前記予測部が前記対象期間について予測した前記特徴量および前記関連情報を条件として、前記複数の分岐回路のうち前記目標値を達成するために節電対策の対象になる分岐回路と節電対策の方法とを定める対策決定部と、
前記対策決定部が節電対策の対象として定めた前記分岐回路について前記第3の記憶部を参照して前記名称を抽出し、当該名称を用いて前記節電対策の方法を提示装置に提示させる出力部とをさらに備える
請求項1記載の需要予測装置。 - 前記特徴抽出部は、前記電力情報を用いて前記分岐回路ごとに電力が消費されている期間の分散を算出する機能を有し、
前記対策決定部は、
前記分散が所定の基準値以上である分岐回路が存在する場合に、
最善の節電対策として、当該分岐回路に接続された電気負荷を前記対象期間に使用しないピークシフトを前記提示装置に提示させ、
次善の節電対策として、前記予測部が前記特徴量として予測した電力が相対的に大きい分岐回路について前記対象期間に消費する電力を低減させるピークカットを前記提示装置に提示させる
請求項2記載の需要予測装置。 - 前記特徴抽出部が抽出した前記特徴量を用いて電力を消費した複数の電気負荷の各々に対応する前記特徴量を推定する推定部をさらに備え、
前記規則抽出部は、前記推定部が前記複数の電気負荷のうちの電気負荷の前記特徴量を推定している場合に、当該電気負荷に関する前記特徴量を前記関連情報から導き出す規則を抽出する機能をさらに有し、
前記予測部は、前記対象期間における前記複数の電気負荷の各々に対応する前記特徴量を予測する機能をさらに有する
請求項1記載の需要予測装置。 - 前記複数の電気負荷をそれぞれ特定する名称を、前記複数の電気負荷にそれぞれ対応付けて格納した第3の記憶部と、
前記予測部が前記対象期間について予測した前記特徴量および前記関連情報を条件として、前記複数の電気負荷のうち前記目標値を達成するために節電対策の対象になる電気負荷と節電対策の方法とを定める対策決定部と、
前記対策決定部が節電対策の対象として定めた前記電気負荷について前記第3の記憶部を参照して前記名称を抽出し、当該名称を用いて前記節電対策の方法を提示装置に提示させる出力部とをさらに備える
請求項4記載の需要予測装置。 - 前記特徴抽出部は、前記電力情報を用いて前記電気負荷ごとに電力が消費されている期間の分散を算出する機能を有し、
前記対策決定部は、
前記分散が所定の基準値以上である電気負荷が存在する場合に、
最善の節電対策として、当該電気負荷を前記対象期間に使用しないピークシフトを前記提示装置に提示させ、
次善の節電対策として、前記予測部が前記特徴量として予測した電力が相対的に大きい電気負荷について前記対象期間に消費する電力を低減させるピークカットを前記提示装置に提示させる
請求項5記載の需要予測装置。 - 前記対策決定部は、
前記節電対策としてピークシフトを提示する場合に、前記第1の記憶部に格納された前記電力情報を用いることにより、対象となる電気負荷を使用可能とする時間帯を、当該電気負荷が過去に使用された時間帯から選択して提示する
請求項3又は6記載の需要予測装置。 - 前記関連情報は、季節および曜日を含むカレンダー情報と、天候、外気温を含む気象情報と、前記建物において電力を使用する利用者の属性である利用者情報と、前記建物の属性である建物情報との群から選択される少なくとも1種類の情報を含む
請求項1~7のいずれか1項に記載の需要予測装置。 - 前記取得部は、前記建物における前記計測装置が計測した電力値に加えて、複数の需要家の建物にそれぞれ設けられた複数の計測装置が計測した電力値を取得し、
前記規則抽出部は、
前記建物と前記複数の建物との全ての建物の各々について抽出した前記規則について前記建物間での類似の程度を表す評価値を求める評価部と、
前記全ての建物のうちの2つ以上の建物から得られた前記規則について前記評価値が所定範囲で類似する場合にこれらの規則を1つの規則にまとめるグループ化部とを備え、
前記第2の記憶部は、
前記グループ化部がまとめた前記規則が該当する前記2つ以上の建物に適用されるように、前記2つ以上の建物にそれぞれ対応付けて前記規則を格納する
請求項1~8のいずれか1項に記載の需要予測装置。 - 請求項2~7のいずれか1項に記載の需要予測装置と、前記需要予測装置から前記節電対策の方法を提示する提示装置とを備える
ことを特徴とする節電支援システム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/039,182 US20160366496A1 (en) | 2013-12-13 | 2014-10-20 | Demand prediction system, energy conservation assisting system |
JP2015552292A JPWO2015087473A1 (ja) | 2013-12-13 | 2014-10-20 | 需要予測装置、節電支援システム |
EP14870193.1A EP3082074A4 (en) | 2013-12-13 | 2014-10-20 | DEVICE FOR DEMAND PRESENTATION, ASSISTANCE SYSTEM FOR ENERGY CONSERVATION |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013257671 | 2013-12-13 | ||
JP2013-257671 | 2013-12-13 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015087473A1 true WO2015087473A1 (ja) | 2015-06-18 |
Family
ID=53370810
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/005301 WO2015087473A1 (ja) | 2013-12-13 | 2014-10-20 | 需要予測装置、節電支援システム |
Country Status (4)
Country | Link |
---|---|
US (1) | US20160366496A1 (ja) |
EP (1) | EP3082074A4 (ja) |
JP (1) | JPWO2015087473A1 (ja) |
WO (1) | WO2015087473A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017073905A (ja) * | 2015-10-08 | 2017-04-13 | 株式会社 日立産業制御ソリューションズ | 設備電力制御システム及び設備電力制御方法 |
WO2017126453A1 (ja) * | 2016-01-19 | 2017-07-27 | パナソニックIpマネジメント株式会社 | エネルギー管理装置、及び、プログラム |
CN108572631A (zh) * | 2018-03-08 | 2018-09-25 | 华南理工大学 | 一种基于二型模糊认知图的智能控制系统及方法 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6168459B2 (ja) * | 2012-04-19 | 2017-07-26 | パナソニックIpマネジメント株式会社 | 生活行動推定装置、プログラム、コンピュータ読み取り可能な記録媒体 |
US10671946B2 (en) * | 2016-02-28 | 2020-06-02 | Quabbin Patent Holdings, Inc. | Multinodal power sensing, aggregation, and transmission |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002176729A (ja) | 2000-12-08 | 2002-06-21 | Hitachi Ltd | インセンティブ電力負荷制御方法およびシステム |
JP2008089434A (ja) * | 2006-10-02 | 2008-04-17 | Matsushita Electric Works Ltd | 電力監視システム |
JP2008225826A (ja) * | 2007-03-13 | 2008-09-25 | Osaka Gas Co Ltd | 省エネ行動支援システム |
WO2011024366A1 (ja) * | 2009-08-28 | 2011-03-03 | パナソニック株式会社 | 利用時間変更支援装置およびその方法 |
JP2011176984A (ja) * | 2010-02-25 | 2011-09-08 | Toshiba Corp | エネルギー配分計算装置 |
JP2013003864A (ja) * | 2011-06-17 | 2013-01-07 | Yahoo Japan Corp | 節電情報提供装置、方法、システム及びプログラム |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004173342A (ja) * | 2002-11-18 | 2004-06-17 | Hitachi Ltd | 運転支援システム及び運転支援コンピュータプログラム |
JP2008054439A (ja) * | 2006-08-25 | 2008-03-06 | Toyota Motor Corp | 電力システム |
US8626902B2 (en) * | 2010-12-03 | 2014-01-07 | International Business Machines Corporation | Modeling and reducing power consumption in large IT systems |
US20120284096A1 (en) * | 2011-05-04 | 2012-11-08 | Naini Rose Gomes | Resource Usage Reduction via Incentives |
US20130144451A1 (en) * | 2011-10-25 | 2013-06-06 | San Diego State University Research Foundation | Residential and commercial energy management system |
AU2012211386A1 (en) * | 2012-02-17 | 2012-08-30 | Commonwealth Scientific And Industrial Research Organisation | Method and system for resource management |
JP6277537B2 (ja) * | 2012-04-09 | 2018-02-14 | パナソニックIpマネジメント株式会社 | エネルギー管理装置、エネルギー管理システム、エネルギー管理方法、およびプログラム |
-
2014
- 2014-10-20 EP EP14870193.1A patent/EP3082074A4/en not_active Withdrawn
- 2014-10-20 WO PCT/JP2014/005301 patent/WO2015087473A1/ja active Application Filing
- 2014-10-20 JP JP2015552292A patent/JPWO2015087473A1/ja active Pending
- 2014-10-20 US US15/039,182 patent/US20160366496A1/en not_active Abandoned
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002176729A (ja) | 2000-12-08 | 2002-06-21 | Hitachi Ltd | インセンティブ電力負荷制御方法およびシステム |
JP2008089434A (ja) * | 2006-10-02 | 2008-04-17 | Matsushita Electric Works Ltd | 電力監視システム |
JP2008225826A (ja) * | 2007-03-13 | 2008-09-25 | Osaka Gas Co Ltd | 省エネ行動支援システム |
WO2011024366A1 (ja) * | 2009-08-28 | 2011-03-03 | パナソニック株式会社 | 利用時間変更支援装置およびその方法 |
JP2011176984A (ja) * | 2010-02-25 | 2011-09-08 | Toshiba Corp | エネルギー配分計算装置 |
JP2013003864A (ja) * | 2011-06-17 | 2013-01-07 | Yahoo Japan Corp | 節電情報提供装置、方法、システム及びプログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP3082074A4 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017073905A (ja) * | 2015-10-08 | 2017-04-13 | 株式会社 日立産業制御ソリューションズ | 設備電力制御システム及び設備電力制御方法 |
WO2017126453A1 (ja) * | 2016-01-19 | 2017-07-27 | パナソニックIpマネジメント株式会社 | エネルギー管理装置、及び、プログラム |
CN108572631A (zh) * | 2018-03-08 | 2018-09-25 | 华南理工大学 | 一种基于二型模糊认知图的智能控制系统及方法 |
CN108572631B (zh) * | 2018-03-08 | 2019-12-10 | 华南理工大学 | 一种基于二型模糊认知图的智能控制系统及方法 |
Also Published As
Publication number | Publication date |
---|---|
EP3082074A4 (en) | 2016-11-30 |
US20160366496A1 (en) | 2016-12-15 |
EP3082074A1 (en) | 2016-10-19 |
JPWO2015087473A1 (ja) | 2017-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Reinhardt et al. | On the accuracy of appliance identification based on distributed load metering data | |
WO2015087473A1 (ja) | 需要予測装置、節電支援システム | |
CN105612546B (zh) | 用于能量测量的装置、服务器、系统和方法 | |
JP4266011B2 (ja) | 配電系統負荷想定方法、配電系統負荷想定装置 | |
JP4648482B1 (ja) | 分析装置及び計測管理システム | |
AU2011260098B2 (en) | Determining an indication of a background level of utility consumption | |
JP5534869B2 (ja) | 計測管理システム及び管理サーバ | |
US20170017215A1 (en) | Demand prediction system and program | |
US20170011304A1 (en) | Appliance inference device and program | |
JP6395083B2 (ja) | 電力使用状況推定装置、プログラム | |
US20160307458A1 (en) | Life style-services suggestion system | |
JP4531638B2 (ja) | 変圧器負荷想定方法、変圧器負荷想定装置 | |
JP2012138123A (ja) | 省エネ支援装置、省エネ支援システム | |
Costa et al. | Inferring daily routines from electricity meter data | |
US20170109467A1 (en) | Behavior prediction device and program | |
Wills et al. | Adaptation and validation of an existing bottom-up model for simulating temporal and inter-dwelling variations of residential appliance and lighting demands | |
JP6292515B2 (ja) | 需要予測装置、プログラム | |
JP2015042052A (ja) | 電力需給量予測装置、予測システムおよび予測方法 | |
JP5422612B2 (ja) | 節電情報提供装置、方法、システム及びプログラム | |
JP2015089163A (ja) | 行動評価装置、行動評価システム、行動評価方法、プログラム | |
JP6641235B2 (ja) | 負荷推定装置及び負荷推定方法 | |
EP2650831A1 (en) | A method for determining an electricity consumption profile of a facility and a system | |
Chin et al. | Household electricity load disaggregation based on low resolution smart meter data | |
Ibrahim et al. | Efficient planning of electrical distribution system for consumers in Sarawak, Malaysia | |
Chen et al. | A smart appliance management system with current clustering algorithm in home network |
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: 14870193 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015552292 Country of ref document: JP Kind code of ref document: A |
|
REEP | Request for entry into the european phase |
Ref document number: 2014870193 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15039182 Country of ref document: US Ref document number: 2014870193 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |