Effect prediction device, effect prediction method, and effect prediction program

Abstract

The effect prediction device (201) predicts the effect of DR control. The air conditioning data acquisition unit (402) acquires air conditioning data including an actual set temperature and actual power consumption. The temperature data acquisition unit (403) acquires temperature data including an actual temperature. The data zone division unit (404) divides the air conditioning data and the temperature data by zone. The model creation unit (405) creates a power consumption prediction model that predicts power consumption for each zone. The control effect prediction unit (407) predicts the effect of DR control using the power consumption prediction model for each zone.

Description

[Technical field]

[0001] The present disclosure relates to an effect prediction device, an effect prediction method, and an effect prediction program, and more particularly to an effect prediction device, an effect prediction method, and an effect prediction program that perform demand-response control for an air conditioner as a control target and predict effects related to the demand-response control. [Background technology]

[0002] Demand response control for maintaining the balance between power supply and demand is known. Demand response control is hereinafter referred to as DR control. DR control is a control for maintaining the balance between power supply and demand by suppressing or increasing the power consumption of consumers. An entity such as a power company or an aggregator is responsible for DR control. In DR control, the power company or aggregator controls the equipment of consumers to suppress or increase their power consumption. In addition, the power company or aggregator takes measures such as encouraging consumers to implement equipment control to suppress or increase their power consumption. Here, in order to determine the content of supply and demand control that can achieve the target power reduction amount, the power company or aggregator needs to predict the power consumption reduced during supply and demand control, that is, the effect of DR control. When there are many consumers subject to DR control, the effect of DR control needs to be estimated for each individual consumer. For this reason, it is desirable to have a small amount of calculation. There is a need for a small amount of calculation and a highly accurate prediction of the effect of DR control.

[0003] Patent Document 1 discloses a method for predicting power consumption in an air conditioner, in which power consumption is predicted by regression analysis using the indoor temperature or set temperature and the outdoor temperature as explanatory variables. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2013-120011 A Summary of the Invention [Problem to be solved by the invention]

[0005] By utilizing conventional technology, the effect of DR control on air conditioners can be predicted from the difference in predicted power consumption when DR control is implemented and when DR control is not implemented. However, the state of an air conditioner after DR control is different from the state before DR control. Therefore, there is an issue that the prediction error will be large when expressing power consumption with a single regression equation.

[0006] An object of the present disclosure is to improve the prediction accuracy of the effect of DR control when DR control is performed. [Means for solving the problem]

[0007] The effect prediction device according to the present disclosure is an effect prediction device that predicts an effect of demand-response control in an air-conditioning system installed in an electricity consumer, an air conditioning data acquisition unit that acquires air conditioning data including an actual set temperature indicating an actual set temperature and an actual power consumption indicating an actual power consumption in the consumer; A temperature data acquisition unit that acquires temperature data including a record temperature indicating a record of the temperature at the consumer; a data zone dividing unit that divides the air conditioning data and the temperature data into zones; a model creation unit that creates a power consumption prediction model that predicts power consumption for each of the zones using the air conditioning data and the temperature data divided for each of the zones; a control effect prediction unit that predicts an effect of the demand-response control by using the power consumption prediction model for each of the zones; Equipped with. Effect of the Invention

[0008] In the effect prediction device according to the present disclosure, a different regression equation is used to predict power consumption for each state, and a predicted value of the effect of DR control is calculated from the difference between the predicted power consumption when DR control is performed and when DR control is not performed. Therefore, the effect prediction device according to the present disclosure has an effect of reducing the prediction error of the power consumption in each state and improving the prediction accuracy of the effect of DR control. [Brief description of the drawings]

[0009] [Figure 1] 1 is a diagram showing an example of the overall configuration of an air conditioner management system 800 according to a first embodiment. [Diagram 2] FIG. 2 is a diagram showing division of a pre-DR control state and a post-DR control state into zones in the effect prediction system 200 according to the first embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of an effect prediction device 201 according to the first embodiment. [Figure 4] 2 is a diagram illustrating an example of a functional configuration of an effect prediction system 200 according to the first embodiment. FIG. [Diagram 5] FIG. 4 is a flow diagram showing a power consumption prediction model creation process according to the first embodiment. [Figure 6] FIG. 4 is a diagram showing an example of a consumer list 412 according to the first embodiment. [Figure 7] FIG. 11 is a diagram showing a detailed operation flow of step S506 according to the first embodiment. [Figure 8] FIG. 4 is a flow diagram showing a control effect prediction process according to the first embodiment. [Figure 9] FIG. 11 is a diagram showing a detailed operation flow of step S806 according to the first embodiment. [Figure 10] FIG. 13 is a diagram illustrating another example of the hardware configuration of the effect prediction device 201 according to a modified example of the first embodiment. [Figure 11] FIG. 11 is a diagram showing an example of the overall configuration of an air conditioner management system 800 according to a second embodiment. [Figure 12] FIG. 13 is a diagram showing a detailed operation flow of step S504 according to the fifth embodiment. [Figure 13]FIG. 13 is a diagram showing a detailed operation flow of step S804 according to the fifth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the present embodiment will be described with reference to the drawings. In each drawing, the same or corresponding parts are given the same reference numerals. In the description of the embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate. The arrows in the drawing mainly indicate the flow of data or the flow of processing. In addition, the relationship of the size of each component in the following drawings may differ from the actual one. In addition, in the description of the embodiment, directions or positions such as up, down, left, right, front, back, front, and back may be indicated. These notations are for convenience of explanation and do not limit the arrangement, direction, or orientation of devices, instruments, parts, etc.

[0011] Embodiment 1 ***Configuration Description*** FIG. 1 is a diagram showing an example of the overall configuration of an air conditioner management system 800 according to the present embodiment. An effect prediction system 200 according to this embodiment is installed in the air conditioner management system 800. The effect prediction system 200 is also called a DR control effect prediction system. The effect prediction system 200 is a system that predicts the effect of DR control with high accuracy and with a small amount of calculation. Also, 'kucho' is an abbreviation for 'air conditioning'.

[0012] The effect prediction system 200 is configured with at least one or more servers, and is configured as, for example, a cloud. The server in the effect prediction system 200 receives a command from a terminal device 210 via a communication network 220, and returns a result of effect prediction of DR control in response to the command from the terminal device 210. In the following, the server will be described as an effect prediction device 201 that predicts the effect of DR control.

[0013] The effect prediction device 201 is connected to each of a plurality of consumers 250 via a communication network 220 . The air conditioner system 255 is provided in an electric power consumer 250. The air conditioner system 255 includes, for example, an indoor unit 251, an outdoor unit 252, and a data acquisition device 253.

[0014] Moreover, the effect prediction device 201 acquires data from a temperature information DB (database) 231 provided in a temperature information collection / prediction system 230 via the communication network 220. Moreover, the effect prediction device 201 acquires data from an air conditioning information DB 241 provided in an air conditioning information collection system 240 via the communication network 220.

[0015] The temperature information collection / prediction system 230 collects and predicts various types of data relating to temperature. The air conditioning information collection system 240 collects various data such as temperature settings and power consumption from the consumers 250 via the communication network 220.

[0016] FIG. 2 is a diagram showing division of a pre-DR control state and a post-DR control state into zones in the effect prediction system 200 according to the present embodiment. The effect prediction system 200 according to this embodiment aims to improve the prediction accuracy of the effect of DR control when DR control is implemented. To achieve this aim, the effect prediction system 200 according to this embodiment divides the state before DR control and the state after DR control into zones as shown in Fig. 2. Then, the effect prediction system 200 predicts power consumption using a different regression equation for each state, and calculates the effect prediction value of DR control from the difference in predicted power consumption when DR control is implemented and when it is not implemented. As a result, in the effect prediction system 200 according to the present embodiment, the prediction error of the power consumption in each state is reduced, and the prediction accuracy of the effect of the DR control is improved.

[0017] FIG. 3 is a diagram showing an example of a hardware configuration of the effect prediction device 201 according to the present embodiment. The effect prediction device 201 is a computer. The effect prediction device 201 includes at least a processor 910, a memory 921, and an auxiliary storage device 922. The effect prediction device 201 also includes an input / output interface 930 and a communication interface 950 for communicating with other devices on the communication network 220. The communication network 220 is, for example, the Internet. An example of the hardware configuration will be described in detail later.

[0018] The terminal device 210 is managed by a user of the effect prediction system 200. The user transmits and receives data between the terminal device 210 and the effect prediction device 201 in the effect prediction system 200 via a communication network 220. The communication network 220 is, for example, the Internet. The data transmitted from the terminal device 210 is the DR control content and the date, time, and location of the target of the DR control. The data received by the terminal device 210 is the effect prediction value of the DR control.

[0019] At least one of the indoor unit 251 and the outdoor unit 252 of the air conditioner installed in each consumer 250 is connected to a data acquisition device 253 that acquires air conditioner data. The data acquisition device 253 transmits operation data of the air conditioner to an air conditioning information database (DB) 241 in the air conditioning information collection system 240 via the communication network 220. Here, the air conditioning information collection system 240 is configured as, for example, a cloud. The communication network 220 is, for example, the Internet. The transmitted operation data is, for example, power consumption and set temperature. Here, the data acquisition device 253 may be built into the indoor unit 251 or the outdoor unit 252.

[0020] The effect prediction device 201 in the effect prediction system 200 acquires data necessary for predicting the effect of DR control from a temperature information DB 231 in a temperature information collection / prediction system 230 or an air conditioning information DB 241 in an air conditioning information collection system 240 via a communication network 220. Here, the temperature information collection / prediction system 230 is configured as, for example, a cloud. The communication network 220 is, for example, the Internet. The data acquired by the effect prediction device 201 from the air conditioning information DB 241 is, for example, air conditioning data such as actual power consumption, actual set temperature, and time data. The data acquired by the effect prediction device 201 from the temperature information DB 231 is temperature data such as actual temperature, predicted temperature, and time data.

[0021] FIG. 4 is a diagram showing an example of a functional configuration of the effect prediction system 200 according to the present embodiment. The effect prediction system 200 is roughly divided into a consumer-specific effect prediction system 400 that predicts the effect of DR control for each consumer, and a system control unit 401 that controls the effect prediction system 200. The consumer-specific effect prediction system 400 is also called a consumer-specific DR control effect prediction system.

[0022] The consumer-specific effect prediction system 400 further includes an air conditioning data acquisition unit 402 , a temperature data acquisition unit 403 , a data area division unit 404 , a model creation unit 405 , a model storage unit 406 , and a control effect prediction unit 407 .

[0023] The air conditioning data acquisition unit 402 acquires actual and predicted temperature settings, actual power consumption, and time data for an arbitrary period from the air conditioning information DB 241. The temperature data acquisition unit 403 acquires the actual and predicted temperatures and time data from the temperature information DB 231 . The data division unit 404 divides the data acquired by the air conditioning data acquisition unit 402 and the temperature data acquisition unit 403 into regions for a pre-DR control state and a post-DR control state. The model creation unit 405 performs regression learning using the actual set temperature, actual power consumption, and actual air temperature data divided into zones by the data division unit 404, and creates a power consumption prediction model. The model storage unit 406 stores the power consumption prediction model created by the model creation unit 405 . The control effect prediction unit 407 predicts power consumption for each zone from the predicted set temperature, predicted air temperature data, and power consumption prediction model, and predicts the effect of DR control from the difference in predicted power consumption when DR control is implemented and when it is not implemented. The predicted set temperature and predicted air temperature data are zoned by the data zone division unit 404. The power consumption prediction model is obtained from the model storage unit 406.

[0024] ***Explanation of Operation*** Next, an operation of the effect prediction device 201 according to this embodiment will be described. The operation procedure of the effect prediction device 201 corresponds to an effect prediction method. Also, a program for realizing the operation of the effect prediction device 201 corresponds to an effect prediction program.

[0025] In this embodiment, the DR control method assumes, for example, changing the set temperature to increase in summer and decrease in winter. With this DR control method, it is possible to adjust the effect of DR control depending on the amount of change in the set temperature. With this DR control method, it is possible to predict the effect of DR control and change the set temperature so as to achieve a target amount of power consumption reduction.

[0026] <Power consumption prediction model creation process> An overview of the power consumption prediction model creation process will be described. The effect prediction device 201 predicts the effect of DR control in an air-conditioning system 255 installed in an electricity consumer 250. The air conditioning data acquisition unit 402 acquires air conditioning data including an actual set temperature indicating an actual set temperature in the consumer facility 250 and an actual power consumption indicating an actual power consumption. The temperature data acquisition unit 403 acquires temperature data including an actual temperature indicating the actual temperature at the consumer 250 . The data zone division unit 404 divides the air conditioning data and the temperature data into zones. The model creation unit 405 uses the air conditioning data and temperature data divided by zone to create a power consumption prediction model that predicts power consumption for each zone. Specifically, the model creation unit 405 uses the air conditioning data and temperature data divided by zone to perform regression learning using a regression equation corresponding to the power consumption of each zone to create a power consumption prediction model for each zone. The control effect prediction unit 407 predicts the effect of DR control by using a power consumption prediction model for each area.

[0027] FIG. 5 is a flow diagram showing the power consumption prediction model creation process according to the present embodiment. In step S501, the system control unit 401 receives location information for a target for which a power consumption prediction model is to be created from the user's terminal device 210 via the communication network 220. However, the system control unit 401 may automatically determine the location for which a power consumption prediction model is to be created without communicating with the terminal device 210.

[0028] FIG. 6 is a diagram showing an example of the consumer list 412 according to the present embodiment. In step S502, the system control unit 401 acquires the consumer list 412 in the location for which the power consumption prediction model is to be created. Here, the system control unit 401 may acquire the consumer list 412 from the air conditioning information DB 241 via the communication network 220. Alternatively, the system control unit 401 may acquire the consumer list 412 from another DB. Furthermore, as shown in FIG. 6, the consumer list 412 has at least information on consumer IDs and consumer locations. In the example of FIG. 6, City A is set as the location for the power consumption prediction model. However, instead of the consumer ID, information that can uniquely determine the consumer may be included, such as a MAC address or a consumer address.

[0029] If there is an unselected customer in the customer list 412, the process proceeds to step S503. If all the customers in the customer list 412 have been selected, the process ends.

[0030] In step S503, one customer to be processed is selected from the customer list 412. In step S504, the air conditioning data acquisition unit 402 acquires at least the actual set temperature, actual power consumption, and time data for an arbitrary period for the selected consumer from the air conditioning information DB 241 via the communication network 220. Here, the air conditioning data acquisition unit 402 acquires data including data after past DR control or after the consumer's set temperature was changed. This can be used for regression learning of the post-DR control state performed in a later step.

[0031] In step S505, the temperature data acquisition unit 403 acquires the actual temperature and time data corresponding to the location of the selected consumer or the location for which a model is to be created from the temperature information DB 231 via the communication network 220. Here, data for the same period as in step S504 is acquired.

[0032] In step S506, the data zoning unit 404 zonings the data acquired in steps S504 and S505. Here, the data zoning unit 404 zonings the data according to zoning conditions set by the system user. For example, the data is zoning into a pre-DR control state and a post-DR control state. In the post-DR control state, power consumption drops significantly because the operation of the air conditioning compressor stops. Predicting the power consumption in the pre-DR control state and the post-DR control state using separate regression equations improves prediction accuracy.

[0033] FIG. 7 is a diagram showing a detailed operational flow of step S506 according to the present embodiment. Step S506 is further divided into steps S701 to S703 in Fig. 7. Steps S701 to S703 of step S506 are executed by the data region dividing unit 404.

[0034] Here, an overview of the data division process will be described. The data zone division unit 404 creates a period prediction model by performing regression learning using a regression equation with the period of the post-DR state as a response variable based on the air conditioning data and the temperature data. More specifically, the data zone division unit 404 creates a period prediction model by performing regression learning using a regression equation with the period of the post-DR state as a response variable, using one or more parameters of the air conditioning data and the temperature data, including at least one of the set temperature, the set temperature change amount, the indoor temperature, and the temperature, as explanatory variables.

[0035] In step S701, the data division unit 404 divides the period ΔT DR The data division unit 404 calculates the period ΔT DR The state is divided into a pre-DR control state and a post-DR control state by this. In the post-DR control state, the operation of the air conditioning compressor is stopped and power consumption is reduced. A threshold value may be set for the actual power consumption, and the period of the post-DR control state may be the period from when DR control is implemented until the threshold is exceeded. Alternatively, the period of the post-DR control state may be determined based on compressor operation information. For example, the compressor operation information may be used to determine the period of the post-DR control state from when DR control is implemented until compressor operation is resumed.

[0036] In step S702, the data division unit 404 learns the period of the post-DR control state by a regression analysis using one or more parameters including at least one of the set temperature, the set temperature change amount, the indoor temperature, and the air temperature data as explanatory variables and the period of the post-DR control state as a response variable. The model after the regression learning is, for example, the following Equation 1. ΔT DR is the period of the post-DR control state, and X i are explanatory variables, j i are the regression coefficients and intercepts obtained by regression learning. (Number 1) ΔT DR =j1×X1+j2×X2+···+j n

[0037] In step S703, the period forecast model (j1 to j n) is registered in the model storage unit 406 in a state in which the consumer can be identified. For example, it is registered in association with the consumer ID.

[0038] If there is an unselected area, the process proceeds to step S507. If all the areas have been selected, the process returns to determining whether or not there are any unselected customers.

[0039] Steps S 507 to S 509 are performed by the model creation unit 405 . In step S507, the model creation unit 405 selects one area. In step S508, the model creation unit 405 performs regression learning on the data of the selected area. By performing regression learning for each area to create a power consumption prediction model, the accuracy is improved, and the accuracy of predicting the effect of DR control is also improved. Here, the power consumption prediction model is, for example, the following equation 2. E is the actual power consumption, T set is the actual set temperature, T out is the actual temperature, and k1, k2, and k3 are the regression coefficients and intercepts obtained by regression learning. (Equation 2) E = k1 × T set +k2×T out +k3

[0040] In step S509, the model creation unit 405 registers the power consumption prediction model (k1, k2, k3) obtained by the regression learning in step S508 in the model storage unit 406 in a state in which the consumer and the area can be specified. For example, the model is registered in association with the consumer ID and the area ID. After that, steps S507 to S509 are repeated until there are no unselected areas.

[0041] Finally, steps S503 to S509 are repeated until there are no more unselected consumers. By periodically creating the power consumption prediction model as described above, it is not necessary to perform regression learning for each command from the user, and the amount of calculations can be reduced. However, regression learning may be performed for each command from the user. If the frequency of commands from the user is low, the amount of calculations can be reduced by performing regression learning for each command.

[0042] <Control effect prediction processing> An overview of the control effect prediction process will be described. The air conditioning data acquisition unit 402 acquires a predicted set temperature indicating a prediction of the set temperature in the consumer facility 250. For example, the air conditioning data acquisition unit 402 acquires the most recent actual set temperature as the predicted set temperature. The temperature data acquisition unit 403 acquires a predicted temperature indicating a prediction of the temperature in the consumer 250 . The data division unit 404 divides the predicted set temperature and the predicted air temperature into zones. Specifically, the data division unit 404 divides the predicted set temperature and the predicted air temperature into zones according to a pre-DR control state and a post-DR control state using a period prediction model. The control effect prediction unit 407 predicts the power consumption for each zone using a power consumption prediction model for each zone, a predicted temperature setting, and a predicted air temperature. The control effect prediction unit 407 predicts the effect of DR control using a predicted value of power consumption for each zone. Specifically, the control effect prediction unit 407 predicts the effect of DR control from the difference between the predicted value of power consumption in the pre-DR control state and the predicted value of power consumption in the post-DR control state.

[0043] FIG. 8 is a flow diagram showing the control effect prediction process according to this embodiment. In step S801, the system control unit 401 receives the time and place for implementing DR control from the terminal device 210 via the communication network 220. In step S802, the system control unit 401 acquires the consumer list 412 within the location subject to DR control. Here, the system control unit 401 may acquire the consumer list 412 from the air conditioning information DB 241 via the communication network 220, or may acquire the consumer list 412 from another DB.

[0044] If there is an unselected customer in the customer list 412, the process proceeds to step S803. If all the customers in the customer list 412 have been selected, the process proceeds to step S811.

[0045] In step S803, one customer to be processed is selected from the customer list 412. In step S804, the air conditioning data acquisition unit 402 acquires at least the predicted set temperature at the DR control time for the selected consumer from the air conditioning information DB 241 via the communications network 220. Here, the most recent set temperature is taken as the predicted set temperature. In step S805, the temperature data acquisition unit 403 acquires, from the temperature information DB 231 via the communication network 220, the predicted temperature and time data corresponding to the location of the selected consumer or the location of the DR control target at the DR control time.

[0046] FIG. 9 is a diagram showing a detailed operational flow of step S806 according to the present embodiment. In step S806, the data acquired in steps S804 and S805 is divided into sections by the data section division unit 404. Step S806 is further divided into steps S901 and S902. Steps S901 and S902 of step S806 are executed by the data section division unit 404.

[0047] In step S901, the data division unit 404 selects a period prediction model (j1 to j n ) from the model storage unit 406. The data zone division unit 404 acquires it by using, for example, a consumer ID. In step S902, the data division unit 404 divides the period prediction model (j1 to j n ) and parameters (X^1~X^ (n-1) ) from the predicted DR control state period ΔT^ as shown in the following equation 3. DR Determine the period prediction model (j1~j n ) is the information acquired in step S901. (n-1) ) is a parameter corresponding to the explanatory variable when creating the model. The period of the determined predicted DR control state ΔT^ DRBased on this, data is divided into a pre-DR control state and a post-DR control state. (Number 3) ΔT^ DR =j1×X^1+j2×X^2+···+j n

[0048] If there are any unselected areas, the process proceeds to step S807. If all the areas have been selected, the process proceeds to step S810.

[0049] Steps S807 to S809 are performed by the control effect prediction unit 407 of the DR control. In step S807, the control effect prediction unit 407 selects one area. In step S808, the control effect prediction unit 407 calculates the power consumption prediction model (k1 to k n ) is obtained from the model storage unit 406. For example, it is obtained using the consumer ID and the area ID. In step S809, the control effect prediction unit 407 calculates the predicted power consumption for the selected area from the predicted temperature setting, the predicted air temperature, and the corresponding power consumption prediction model. For example, as shown in the following formula 4, the power consumption prediction model (k1 to k3) and the predicted set temperature T^ set , predicted temperature T^ out The predicted power consumption E^ is calculated from the above. By predicting the power consumption separately for the pre-DR control state and the post-DR control state, the accuracy of the power consumption prediction in each area is improved, and the accuracy of the prediction of the effect of DR control is also improved. Steps S807 to S809 are repeated until there are no unselected areas. (Number 4) E^=k1×T^ set +k2×T^ out +k3

[0050] In step S810, the control effect prediction unit 407 predicts the effect of DR control from the difference in predicted power consumption when DR control is performed and when DR is not performed. For example, the effect of DR control is predicted from the difference in predicted power consumption when the set temperature is changed and when it is not changed. Thereafter, steps S803 to S810 are repeated until there are no more unselected consumers.

[0051] Finally, in step S811, the system control unit 401 sums up the predicted DR control effects for all the selected consumers, and transmits the sum to the user terminal device 210 via the communication network 220. Note that the control effect prediction unit 407 may calculate an effect prediction for each of the multiple consumers, add up the effect predictions calculated for each of the multiple consumers, and output the sum as an effect prediction result.

[0052] ***Explanation of Hardware Configuration Example*** FIG. 3 shows an example of a hardware configuration of the effect prediction device 201 according to the present embodiment. The effect prediction device 201 is a computer. The effect prediction device 201 includes a processor 910 and other hardware such as a memory 921, an auxiliary storage device 922, an input / output interface 930, and a communication interface 950. The processor 910 is connected to the other hardware via a signal line 80 and controls the other hardware.

[0053] As described above, the effect prediction device 201 comprises, as functional elements, a system control unit 401, an air conditioning data acquisition unit 402, a temperature data acquisition unit 403, a data zone division unit 404, a model creation unit 405, and a control effect prediction unit 407. The functions of the system control unit 401, the air conditioning data acquisition unit 402, the temperature data acquisition unit 403, the data zone division unit 404, the model creation unit 405, and the control effect prediction unit 407 are realized by software. The model storage unit 406 is provided in the memory 921 or the auxiliary storage device 922. The functions of the system control unit 401, the air conditioning data acquisition unit 402, the temperature data acquisition unit 403, the data zone division unit 404, the model creation unit 405, and the control effect prediction unit 407 may be referred to as functions of the effect prediction device 201. In addition, the system control unit 401, the air conditioning data acquisition unit 402, the temperature data acquisition unit 403, the data zone division unit 404, the model creation unit 405, and the control effect prediction unit 407 may be referred to as each part of the effect prediction device 201.

[0054] The processor 910 is a device that executes an effect prediction program. The effect prediction program is a program that realizes the functions of the effect prediction device 201. The processor 910 is an IC that performs arithmetic processing. Specific examples of the processor 910 are a CPU, a DSP, and a GPU. IC is an abbreviation for Integrated Circuit. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

[0055] The memory 921 is a storage device that temporarily stores data. Specific examples of the memory 921 are SRAM and DRAM. SRAM is an abbreviation for Static Random Access Memory. DRAM is an abbreviation for Dynamic Random Access Memory. The auxiliary storage device 922 is a storage device that stores data. A specific example of the auxiliary storage device 922 is a HDD. The auxiliary storage device 922 may also be a portable storage medium such as an SD (registered trademark) memory card, CF, NAND flash, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, or a DVD. Note that HDD is an abbreviation for Hard Disk Drive. SD (registered trademark) is an abbreviation for Secure Digital. CF is an abbreviation for CompactFlash (registered trademark). DVD is an abbreviation for Digital Versatile Disk.

[0056] The input / output interface 930 is an interface for connecting an input / output device. Specific examples of the input / output interface 930 include a USB and an HDMI (registered trademark) port. USB is an abbreviation for Universal Serial Bus. HDMI (registered trademark) is an abbreviation for High-Definition Multimedia Interface.

[0057] The communication interface 950 is an interface for communicating with an external device. Specific examples of the communication interface 950 include an Ethernet (registered trademark) port, or a device for performing wireless communication.

[0058] The effect prediction program is executed in the effect prediction device 201. The effect prediction program is read into the processor 910 and executed by the processor 910. In addition to the effect prediction program, the OS is also stored in the memory 921. OS is an abbreviation for Operating System. The processor 910 executes the effect prediction program while executing the OS. The effect prediction program and the OS may be stored in the auxiliary storage device 922. The effect prediction program and the OS stored in the auxiliary storage device 922 are loaded into the memory 921 and executed by the processor 910. Note that a part or all of the effect prediction program may be incorporated into the OS.

[0059] The effect prediction device 201 may include a plurality of processors that replace the processor 910. These plurality of processors share the execution of the effect prediction program. Each of the processors is a device that executes the effect prediction program, like the processor 910.

[0060] Data, information, signal values ​​and variable values ​​used, processed or output by the effect prediction program are stored in the memory 921, the auxiliary storage device 922, or a register or cache memory in the processor 910.

[0061] The "part" of each part of the effect prediction device 201 may be read as a "circuit," "step," "procedure," "process," or "circuitry." The effect prediction program causes a computer to execute each process, with the "part" of each part of the effect prediction device 201 read as a "process." The "process" of each process of the effect prediction device 201 may be read as a "program," "program product," "computer-readable storage medium storing a program," or "computer-readable recording medium recording a program." The effect prediction method is a method performed by the effect prediction device 201 executing the effect prediction program. The effect prediction program may be provided by being stored in a computer-readable recording medium. Also, the effect prediction program may be provided as a program product.

[0062] ***Other configurations*** <Modification> In this embodiment, the functions of each unit of the effect prediction device 201 are realized by software. As a modification, the functions of each unit of the effect prediction device 201 may be realized by hardware. Specifically, the effect prediction device 201 includes an electronic circuit 909 instead of the processor 910 .

[0063] FIG. 10 is a diagram showing another example of the hardware configuration of the effect prediction device 201 according to the modified example of the present embodiment. The electronic circuit 909 is a dedicated electronic circuit that realizes the functions of each part of the effect prediction device 201. Specifically, the electronic circuit 909 is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array.

[0064] The functions of each unit of the effect prediction device 201 may be realized by one electronic circuit, or may be distributed and realized by multiple electronic circuits.

[0065] As another modified example, some of the functions of each unit of the effect prediction device 201 may be realized by electronic circuits and the remaining functions may be realized by software. Also, some or all of the functions of each unit of the effect prediction device 201 may be realized by firmware.

[0066] Each of the processor and the electronic circuit is also called a processing circuitry. In other words, the functions of each part of the effect prediction device 201 are realized by the processing circuitry.

[0067] ***Explanation of the Effects of the Present Embodiment*** As described above, the effect prediction device according to this embodiment divides the pre-DR control state and the post-DR control state into zones as shown in Fig. 2. The effect prediction device then predicts power consumption using a different regression equation for each state, and calculates the predicted DR control effect from the difference in predicted power consumption when DR control is implemented and when it is not implemented. Therefore, the effect prediction device according to this embodiment reduces the prediction error of power consumption in each state, and provides the effect of improving the prediction accuracy of the effect of DR control.

[0068] Embodiment 2 In this embodiment, differences from and additions to the first embodiment will be mainly described. In this embodiment, components having the same functions as those in the first embodiment are given the same reference numerals, and the description thereof will be omitted. The effect prediction device 201 is installed in an air-conditioning system 255 of a consumer 250 .

[0069] ***Configuration Description*** FIG. 11 is a diagram showing an example of the overall configuration of an air conditioner management system 800 according to this embodiment. In the first embodiment, the DR control effect prediction system 200 is constructed in the cloud. And, it has been explained that the effect prediction system 200 is connected to the air conditioning information DB 241 or the terminal device 210 via the communication network 220. In this embodiment, as shown in FIG. 11, a DR control effect prediction system 200 is formed by an effect prediction device 201 which is one or more local servers. The effect prediction system 200 is composed of at least one or more local servers, that is, an effect prediction device 201. A user operates the effect prediction device 201 in the control effect prediction system 200 directly or indirectly via a user interface to obtain the effect prediction result of DR control.

[0070] Each consumer 250 has at least one indoor unit 251 and one outdoor unit 252, and at least one of them is connected to a data acquisition device 253. The data acquisition device 253 transmits operation data of the air conditioner to the air conditioning information DB 241. For example, it transmits power consumption and set temperature data. Here, the data acquisition device 253 may be built into the indoor unit 251 or the outdoor unit 252. When predicting the effect of DR control, the effect prediction system 200 acquires air conditioning data from an air conditioning information DB 241. The effect prediction system 200 also acquires temperature data from a temperature information DB 231 in a temperature information collection / prediction system 230 via a communication network 220. Here, the temperature information collection / prediction system 230 is configured as, for example, a cloud, and the communication network 220 is the Internet.

[0071] ***Explanation of Operation*** The operation of the effect prediction device 201 according to this embodiment is similar to that described in the first embodiment.

[0072] ***Explanation of the Effects of the Present Embodiment*** As described above, in the effect prediction system according to the present embodiment, a building, factory, apartment, or other structure equipped with one or more indoor units and one or more outdoor units is regarded as one consumer, and the effect of DR control is predicted. By having the system locally, cloud costs can be reduced, and for consumers with many air conditioners, the total costs associated with introducing and maintaining the system can be reduced.

[0073] Embodiment 3 In this embodiment, differences from the first and second embodiments and additional features to the first and second embodiments will be mainly described. In this embodiment, components having the same functions as those in the first and second embodiments are given the same reference numerals, and the description thereof will be omitted.

[0074] ***Configuration Description*** The configuration of the effect prediction system 200 according to this embodiment is similar to that described in the first and second embodiments.

[0075] ***Explanation of Operation*** Regarding the operation of the effect prediction system 200 according to this embodiment, the points that differ from those described in the first and second embodiments will be described. In this embodiment, the data zone division unit 404 sets a threshold value for a parameter using at least one of the air conditioning data and air temperature data, the set temperature, the set temperature change amount, the indoor temperature, the air temperature, and the elapsed time after the demand-response control is implemented. The data zone division unit 404 defines the period from the implementation of DR control to the time when the threshold value is exceeded as the period of the post-DR control state.

[0076] In the first and second embodiments, an example has been described in which the data zone division unit 404 determines the predicted period of the post-DR state by regression analysis in step S506 or step S806. At this time, the data zone division unit 404 sets one or more parameters including at least one of the set temperature, the set temperature change amount, the indoor temperature, and the air temperature as explanatory variables, and sets the period of the post-DR state as a response variable. In this embodiment, a threshold is set for at least one of the parameters of the set temperature, the set temperature change amount, the indoor temperature, the air temperature, and the elapsed time after the DR control is implemented, and the period from the implementation of the DR control until the threshold is exceeded is defined as the period of the post-DR control state. For example, set and the indoor temperature T in Parameter T using set -T in If the threshold of is set to 0, after DR control is implemented, T set -T in The state after DR control is assumed to be until exceeds 0.

[0077] ***Explanation of the Effects of the Present Embodiment*** As described above, in the effect prediction system according to the present embodiment, the calculation cost of regression learning can be reduced by using a threshold value to determine the period of the post-DR control state.

[0078] Embodiment 4 In this embodiment, differences from the first to third embodiments and additional features to the first to third embodiments will be mainly described. In this embodiment, components having the same functions as those in the first to third embodiments are given the same reference numerals, and the description thereof will be omitted.

[0079] ***Configuration Description*** The configuration of the effect prediction system 200 according to this embodiment is similar to that described in the first to third embodiments.

[0080] ***Explanation of Operation*** Regarding the operation of the effect prediction system 200 according to this embodiment, the points different from those described in the first to third embodiments will be described. In the first to third embodiments, when the air conditioning data acquisition unit 402 acquires the predicted set temperature in step S804, the most recent actual set temperature is set as the predicted set temperature. In this embodiment, the average, mode, or median of the set temperature over a certain period is set as the predicted set temperature. For example, the most recent mode of the set temperature over the past two weeks is set as the predicted set temperature.

[0081] As described above, the set temperature before the DR control is executed may be the average, mode, or median of the set temperature in a certain period of time. Alternatively, the set temperature before the DR control is executed may be determined based on at least one of the time series data of the air temperature, humidity, and solar radiation.

[0082] ***Explanation of the Effects of the Present Embodiment*** As described above, in the effect prediction system according to the present embodiment, a more reliable predicted set temperature can be set by using a value such as the average value, the mode value, or the median value.

[0083] Embodiment 5. In this embodiment, differences from the first to third embodiments and additional features to the first to third embodiments will be mainly described. In this embodiment, components having the same functions as those in the first to third embodiments are given the same reference numerals, and the description thereof will be omitted.

[0084] ***Configuration Description*** The configuration of the effect prediction system 200 according to this embodiment is similar to that described in the first to third embodiments.

[0085] ***Explanation of Operation*** In the first to third embodiments, when the air conditioning data acquisition unit 402 acquires the predicted set temperature in step S804, the most recent actual set temperature is used as the predicted set temperature. In this embodiment, the predicted set temperature is calculated by regression learning using at least one of the air temperature, humidity, and solar radiation as an explanatory variable and the set temperature as a response variable. By predicting the set temperature in this manner, it is possible to calculate a predicted set temperature that takes into account the setting tendency of the consumer.

[0086] FIG. 12 is a diagram showing a detailed operational flow of step S504 according to the present embodiment. In this embodiment, step S504 is divided into steps S1101 to S1103 as shown in FIG.

[0087] In step S1101, the air conditioning data acquisition unit 402 acquires the actual set temperature, actual power consumption, and time data for the selected consumer from the air conditioning information DB 241 in the air conditioning information collection system 240 via the communications network 220. At the same time, at least one of the actual temperature, actual humidity, and actual solar radiation data is acquired. Here, the actual temperature, actual humidity, and actual solar radiation data may be acquired from the temperature information DB 231 in the temperature information collection / prediction system 230 via the communications network 220, or may be acquired via the temperature data acquisition unit 403. In step S1102, the air conditioning data acquisition unit 402 performs regression learning using at least one of the temperature, humidity, and solar radiation as an explanatory variable and the set temperature as a response variable. The model after regression learning is, for example, the following equation 5. X i are explanatory variables, l i represents the regression coefficient or intercept. (Number 5) T set =l1×X1+l2×X2+···+l n

[0088] In step S1103, the air conditioning data acquisition unit 402 acquires the predicted temperature setting model ( i ~l n ) is registered in the model storage unit 406. For example, it is registered in association with the consumer ID.

[0089] FIG. 13 is a diagram showing a detailed operational flow of step S804 according to the present embodiment. In this embodiment, step S804 is divided into steps S1201 to S1203 shown in FIG.

[0090] In step S1201, the air conditioning data acquisition unit 402 acquires at least one of the predicted temperature, predicted humidity, and predicted solar radiation data for the selected consumer, and time data. Here, the predicted temperature, predicted humidity, and predicted solar radiation data may be acquired from the temperature information DB 231 in the temperature information collection / prediction system 230 via the communication network 220, or may be acquired via the temperature data acquisition unit 403. In step S1202, the air conditioning data acquisition unit 402 acquires the predicted temperature setting models (l_1 to l_n) corresponding to the selected consumer from the model storage unit 406. For example, the acquisition is performed using the consumer ID. Next, in step S1203, the air conditioning data acquisition unit 402 acquires the predicted temperature setting model (l1 to l n ) and the parameters (X^1~X^ (n-1) ) and the predicted set temperature T^ is calculated as shown in the following equation 6. set Determine. (Number 6) T^ set =l1×X^1+l2×X^2+···+l n

[0091] ***Explanation of the Effects of the Present Embodiment*** As described above, in the effect prediction system according to the present embodiment, the predicted set temperature is calculated by regression learning using at least one of the temperature, humidity, and solar radiation as an explanatory variable and the set temperature as a response variable. By predicting the set temperature in this manner, it is possible to calculate a predicted set temperature that takes into account the setting tendency of the consumer.

[0092] In the effect prediction systems according to the above first to fifth embodiments, a method for predicting the amount of reduction in power consumption due to air conditioner control related to demand response for air conditioners, which is composed of the following elements, has been described. The amount of reduction in power consumption is calculated based on the power consumption before the execution of control related to the demand response and the power consumption after the execution of control related to the demand response. The calculation is performed using a prediction model for power consumption before the execution of control related to the demand response, and a prediction model for power consumption after the execution of control related to the demand response. The prediction model for power consumption before execution of control related to the demand response is trained based on air conditioner operation data or weather information before execution of control equivalent to demand response control, and the prediction model for power consumption after execution of control related to the demand response is trained based on air conditioner operation data or weather information after execution of control equivalent to demand response control. The amount of power consumption before the demand-response control is executed is predicted based on a prediction model corresponding to the amount of power consumption before the demand-response control is executed and air conditioner operation data or predicted weather information predicted at the time of the demand-response control. The amount of power consumption after the demand-response control is executed is predicted based on a prediction model corresponding to the amount of power consumption after the demand-response control is executed, and air conditioner operation data or predicted weather information predicted at the time of the demand-response control, and the demand-response control content.

[0093] In the above prediction method, the demand-response control of the air conditioner is a change in the set temperature of the air conditioner. The prediction model of the power consumption before the execution of control related to the demand response is learned from time-series data of the power consumption, the set temperature, and the air temperature before the set temperature of the air conditioner is changed. The prediction model of the power consumption after the execution of the control related to the demand response is learned from time-series data of the power consumption, the set temperature, and the air temperature after the set temperature of the air conditioner is changed.

[0094] In addition, in the above prediction method, the period after the execution of control related to the demand response is determined by learning from at least one of the time series data of the period of the state after the execution of control related to the demand response, the amount of change in the set temperature, the set temperature, the indoor temperature, and the air temperature before the change in the set temperature of the air conditioner, and the set temperature, the indoor temperature, and the air temperature after the change in the set temperature of the air conditioner.

[0095] In addition, in the above prediction method, a threshold is set for a parameter using at least one of the set temperature, indoor temperature, and air temperature before the set temperature of the air conditioner is changed, the set temperature, indoor temperature, and air temperature after the set temperature of the air conditioner is changed, and the elapsed time from the execution of the demand-response control, and the period until the parameter becomes equal to or greater than the threshold is defined as the period after the execution of the demand-response control.

[0096] In the above first to fifth embodiments, each part of the effect prediction system has been described as an independent functional block. However, the configuration of the effect prediction system does not have to be as in the above-mentioned embodiments. The functional blocks of the effect prediction system may have any configuration as long as they can realize the functions described in the above-mentioned embodiments. In addition, the effect prediction system may be a system composed of multiple devices, rather than a single device. In addition, it is possible to combine two or more parts of the first to fifth embodiments. Alternatively, it is possible to implement only one part of these embodiments. In addition, it is possible to implement any combination of these embodiments, either as a whole or in part. That is, in the first to fifth embodiments, any combination of the embodiments is possible, or any component of each embodiment may be modified, or any component of each embodiment may be omitted.

[0097] The above-described embodiment is essentially a preferred example, and is not intended to limit the scope of the present disclosure, the scope of application of the present disclosure, and the scope of use of the present disclosure. The above-described embodiment can be modified in various ways as necessary. For example, the procedure described using a flow chart or sequence chart may be modified as appropriate. [Explanation of symbols]

[0098] 80 signal line, 201 effect prediction device, 200 effect prediction system, 210 terminal device, 220 communication network, 230 temperature information collection / prediction system, 231 temperature information DB, 240 air conditioning information collection system, 241 air conditioning information DB, 250 consumer, 251 indoor unit, 252 outdoor unit, 253 data acquisition device, 255 air conditioning system, 400 effect prediction system for each consumer, 401 system control unit, 402 air conditioning data acquisition unit, 403 temperature data acquisition unit, 404 data area division unit, 405 model creation unit, 406 model storage unit, 407 control effect prediction unit, 412 consumer list, 800 air conditioning management system, 909 electronic circuit, 910 processor, 921 memory, 922 auxiliary storage device, 930 input / output interface, 950 communication interface, 950 communication device.

Claims

1. An effect prediction device for predicting an effect of demand response control in an air conditioning system installed at an electricity consumer, an air conditioning data acquisition unit that acquires air conditioning data including an actual set temperature indicating an actual set temperature and an actual power consumption indicating an actual power consumption in the consumer; A temperature data acquisition unit that acquires temperature data including a record temperature indicating a record of the temperature at the consumer; a data zone dividing unit that divides the air conditioning data and the temperature data into zones of a state before demand-response control and a state after demand-response control; a model creation unit that creates a power consumption prediction model that predicts power consumption for each of the zones using the air conditioning data and the temperature data divided for each of the zones; a control effect prediction unit that predicts an effect of the demand-response control by using the power consumption prediction model for each of the zones; An effect prediction device comprising:

2. The model creation unit is The effect prediction device of claim 1 , wherein the air conditioning data and the temperature data divided for each zone are used to perform regression learning using a regression equation corresponding to the power consumption of each zone, thereby creating the power consumption prediction model for each zone.

3. The data division unit includes:

3. The effect prediction device according to claim 1, wherein a period prediction model is created by performing regression learning using a regression equation having a period of the post-demand-response control state as a response variable, based on the air conditioning data and the temperature data.

4. The data division unit includes:

4. The effect prediction device according to claim 3, wherein regression learning is performed using a regression equation in which at least one of the set temperature, the set temperature change amount, the indoor temperature, and the air temperature among the air conditioning data and the air temperature data is used as an explanatory variable, and the period of the post-demand-response control state is used as a target variable.

5. The air conditioning data acquisition unit is Obtaining a predicted set temperature indicating a prediction of a set temperature in the consumer; The temperature data acquisition unit is Obtaining a predicted temperature indicating a prediction of the temperature at the consumer; The data division unit includes: The predicted set temperature and the predicted air temperature are divided into areas; The control effect prediction unit is The effect prediction device described in claim 3 predicts a predicted value of power consumption for each area using the power consumption prediction model for each area, the predicted set temperature, and the predicted air temperature, and predicts the effect of the demand-response control using the predicted value of power consumption for each area.

6. The data division unit includes: The effect prediction device according to claim 5 , wherein the period prediction model is used to zone the predicted set temperature and the predicted air temperature into a pre-demand-response control state and a post-demand-response control state.

7. The control effect prediction unit is The effect prediction device according to claim 5 , wherein the effect of the demand-response control is predicted from a difference between the predicted value of the power consumption in the pre-demand-response control state and the predicted value of the power consumption in the post-demand-response control state.

8. The data division unit includes:

3. The effect prediction device according to claim 1 or 2, wherein a threshold value is set for a parameter using at least one of the air conditioning data and the air temperature data, the set temperature, the amount of change in the set temperature, the indoor temperature, the air temperature, and the elapsed time after the demand-response control is implemented, and the period from the implementation of the demand-response control to the time when the threshold value is exceeded is defined as the period of the post-demand-response control state.

9. The air conditioning data acquisition unit is The effect prediction device according to claim 5 , wherein the most recent actual set temperature is acquired as the predicted set temperature.

10. The air conditioning data acquisition unit is The effect prediction device according to claim 5 , wherein an average value, a mode, or a median value of the set temperature for a certain period is obtained as the predicted set temperature.

11. The air conditioning data acquisition unit is 6. The effect prediction device according to claim 5, wherein the predicted set temperature is calculated by regression learning using at least one of air temperature, humidity, and solar radiation as an explanatory variable and the set temperature as a response variable.

12. The effect prediction device includes: The system is connected to each of a plurality of consumers via a communication network, The control effect prediction unit is The effect prediction device according to claim 1 or 2, wherein an effect prediction is calculated for each of the plurality of consumers, and the effect predictions calculated for each of the plurality of consumers are added together and output as an effect prediction result.

13. The effect prediction device includes: The effect prediction device according to claim 1 or 2, which is installed in the air-conditioning system of the customer.

14. 1. An effect prediction method for predicting an effect of demand response control in an air conditioning system installed at an electricity consumer, comprising: A computer acquires air conditioning data including an actual set temperature indicating an actual set temperature and an actual power consumption indicating an actual power consumption in the consumer, A computer acquires temperature data including a record temperature indicating a record of the temperature at the consumer's house, The computer divides the air conditioning data and the temperature data into zones of a pre-demand-response control state and a post-demand-response control state, a computer creates a power consumption prediction model that predicts power consumption for each of the zones using the air conditioning data and the temperature data divided for each of the zones; An effect prediction method in which a computer predicts the effect of the demand-response control using the power consumption prediction model for each area.

15. An effect prediction program for predicting the effect of demand response control in an air conditioning system installed at an electricity consumer, An air conditioning data acquisition process for acquiring air conditioning data including an actual set temperature indicating an actual set temperature and an actual power consumption indicating an actual power consumption in the consumer; A temperature data acquisition process for acquiring temperature data including a record temperature indicating a record of the temperature at the consumer; a data zone dividing unit that divides the air conditioning data and the temperature data into zones of a state before demand-response control and a state after demand-response control; a model creation process for creating a power consumption prediction model for predicting power consumption for each of the zones using the air conditioning data and the temperature data divided for each of the zones; a control effect prediction process for predicting an effect of the demand-response control by using the power consumption prediction model for each of the zones; An effect prediction program that causes a computer to execute the above.

Images