Control device

Abstract

To provide a control device that can easily improve an energy saving effect on an air conditioning device.SOLUTION: A control device includes: an indoor environment estimation unit for estimating information on an indoor environment for each predetermined time by inputting information on an air conditioner, information on an indoor environment, and information on an environment of ambient air to an indoor environment learning model; a number-of-persons-staying-in-a-room estimation unit for estimating the number of persons staying in a room for each predetermined time by inputting information on a date, and information on the number of persons staying in a room, and an environment of ambient air to a number-of-persons-staying-in-a- room learning model; and a consumed energy estimation unit for estimating a consumed energy amount for each predetermined time by inputting the information on the air conditioner, the information on the environment of ambient air, the information on the indoor environment, the consumed energy amount, information on the estimated indoor environment, and estimated number of persons staying in a room to a consumed energy amount learning model.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a control device.

Background Art

[0002] In the construction industry, there is an increasing interest in energy conservation (hereinafter also referred to as energy saving). Regarding air conditioning systems, they account for 40% of the energy consumption in buildings. Therefore, the impact of the energy-saving effect on air conditioning systems in large buildings such as office buildings is significant, and there are high expectations for the energy-saving effect of air conditioning systems.

[0003] In order to improve the energy-saving effect of air conditioning systems, various control methods have been proposed (for example, Patent Document 1). In Patent Document 1, control of an air conditioning system that improves the energy-saving effect during unoccupied time zones is proposed. The unoccupied time zone indicates that there is no one present in at least one room of a building.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When performing the control as described above, during the unoccupied time zone, control is performed to improve the energy-saving effect regarding the air conditioning system. However, during the occupied time zone, control to improve the energy-saving effect regarding the air conditioning system is not performed, and there is a problem that there is a limit to improving the energy-saving effect regarding the air conditioning system.

[0006] The present invention has been made to solve the above problems, and an object thereof is to provide a control device that easily improves the energy-saving effect regarding an air conditioning system.

Means for Solving the Problems

[0007] To achieve the above object, the present invention provides the following means. A control device for an air conditioner, comprising: an acquisition unit that acquires at least one or more of information related to the air conditioner, information related to the indoor environment, information related to the outside air environment, information related to the date, the number of occupants, and the amount of energy consumed by the air conditioner at predetermined time intervals; an indoor environment estimation unit that estimates information related to the indoor environment at the predetermined time intervals by inputting the information related to the air conditioner acquired this time by the acquisition unit, the information related to the indoor environment acquired last time, and the information related to the outside air environment acquired last time into a learned indoor environment learning model that performs machine learning for estimating the information related to the indoor environment; an occupant number estimation unit that estimates the number of occupants at the predetermined time intervals by inputting the information related to the date acquired this time by the acquisition unit, the number of occupants acquired last time, and the information related to the outside air environment acquired last time into a learned occupant number learning model that performs machine learning for estimating the number of occupants; and an energy consumption estimation unit that estimates the amount of energy consumed at the predetermined time intervals by inputting the information related to the air conditioner acquired this time by the acquisition unit, the information related to the outside air environment acquired last time, the information related to the indoor environment acquired last time, the amount of energy consumed acquired last time, the information related to the indoor environment estimated this time by the indoor environment estimation unit, and the number of occupants estimated this time by the occupant number estimation unit into a learned energy consumption learning model that performs machine learning for estimating the amount of energy consumed.

[0008] According to the control device according to the first aspect of the present invention, information related to the indoor environment is estimated by the indoor environment estimation unit. The number of occupants is estimated by the occupant number estimation unit. Using the estimated information related to the indoor environment and the number of occupants, the amount of energy consumed is further estimated by the energy consumption estimation unit.

[0009] By estimating the amount of consumed energy using information on the presumed indoor environment and the number of occupants, it is possible to estimate the amount of consumed energy with higher accuracy than when estimating the amount of consumed energy without using the number of occupants.

[0010] The information on the indoor environment includes information containing at least one or more of the indoor temperature, indoor humidity, and carbon dioxide concentration in the room. Note that information other than the above may also be included.

[0011] In the first aspect of the above invention, the set temperature of the air conditioner has a plurality of different values, and the indoor environment estimation unit, the number of occupants estimation unit, and the consumed energy estimation unit preferably estimate the information on the indoor environment, the number of occupants, and the consumed energy amount for each of the plurality of different set temperatures.

[0012] In this way, by estimating the information on the indoor environment, the number of occupants, and the consumed energy amount for each of the plurality of different set temperatures, it is possible to estimate the combination of the indoor temperature and the consumed energy amount for each of the plurality of different set temperatures. Based on the plurality of combinations, a prior risk assessment can be performed.

[0013] The prior risk assessment is to evaluate whether the estimated indoor temperature is included in a predetermined temperature range and to evaluate the magnitude of the estimated consumed energy amount.

[0014] In the first aspect of the above invention, it is preferable to further include a selection unit that obtains the value of the set temperature at which the indoor temperature included in the information on the indoor environment is included in the predetermined indoor temperature range and the consumed energy amount is the smallest.

[0015] In this way, by providing the selection unit, optimal control becomes easier. Optimal control is control that selects the best combination from a plurality of combinations. The best combination is a combination that satisfies both an improvement in human comfort and being the smallest among a plurality of estimated energy consumption amounts.

[0016] In the first aspect of the above invention, when the energy consumption amount corresponding to the estimated energy consumption amount is acquired by the acquisition unit, it is preferable to further include a comparison unit that compares the difference between the estimated energy consumption amount and the acquired energy consumption amount.

[0017] In this way, by providing the comparison unit, the difference between the estimated energy consumption amount and the corresponding acquired energy consumption amount is compared. By comparing the difference, the energy consumption amount can be easily quantitatively evaluated, and the energy-saving effect related to the air conditioner can be easily improved.

Effect of the Invention

[0018] According to the control device of the present invention, by using the estimated information on the indoor environment and the number of occupants and estimating the energy consumption amount, it is possible to easily perform control that improves the energy-saving effect related to the air conditioner.

Brief Description of the Drawings

[0019]

Figure 1

Figure 2

Figure 3

Figure 4

Mode for Carrying Out the Invention

[0020] 〔First Embodiment〕 The control device 100 according to the first embodiment of the present invention will be described with reference to FIGS. 1 to 4. The control device 100 of the present embodiment is a device that controls the air conditioner 900 and is a device that facilitates improving the energy-saving effect related to the air conditioner 900.

[0021] The air conditioner 900 has a configuration in which indoor air is inhaled, cooled and heated (hereinafter also referred to as cooling etc.), and the cooled air is supplied into the room. In the present embodiment, the air conditioner 900 will be described by taking an example in which cooled air is supplied into the indoor space of a building.

[0022] In the present embodiment, the air conditioner 900 is a device combined with one outdoor unit (not shown) and at least one or more indoor units (not shown), and it is sufficient if at least one set of such a combination is provided. In addition to the above combination, the air conditioner 900 may have a configuration in which a plurality of indoor units are combined with one outdoor unit.

[0023] The outdoor unit has a configuration for heat exchange between the refrigerant and the outside air or water. The outdoor unit is connected to the indoor unit through a pipe through which the refrigerant flows. In addition, the outdoor unit is provided with a compressor (not shown) for increasing the pressure of the refrigerant and an outdoor heat exchange unit (not shown) for cooling the inhaled air by heat exchange.

[0024] The indoor unit has a configuration for discharging the cooled air into the room. The indoor unit is connected to other indoor units and the outdoor unit respectively through pipes through which the refrigerant flows. In addition, the indoor unit is provided with an air-conditioning fan (not shown) for discharging the heat-exchanged air and an indoor heat exchange unit (not shown) for cooling the air discharged by heat exchange.

[0025] The control device 100 of the present embodiment is connected so as to enable information transmission to and from an air conditioner 900, a detection device 500 described later, and a communication device 501 described later via known information communication means, either wired or wireless. Further, the control device 100 is connected to the air conditioner 900, the detection device 500, and the communication device 501 so as to enable information transmission via a known wireless communication network or a combination of a wireless communication network and a wired communication network.

[0026] The control device 100 controls the air conditioner 900. The control device 100 is an information processing device such as a server having a CPU (Central Processing Unit), ROM, RAM, an input / output interface, and the like. As shown in FIG. 1, the programs stored in the storage devices such as the above-mentioned ROM cause the CPU, ROM, RAM, and input / output interface to cooperate, and function as at least an acquisition unit 101, a storage unit 102, an indoor environment estimation unit 103, an in-room occupant number estimation unit 104, an energy consumption amount estimation unit 105, a selection unit 106, a control unit 107, a comparison unit 108, an arithmetic unit 109, and a combination unit 110.

[0027] The acquisition unit 101 is connected to be able to communicate information with the air conditioner 900, the detection device 500, and the communication device 501, and is configured to acquire information related to the air conditioner 900, detected information, and communication information (hereinafter also referred to as various information) at predetermined time intervals. In the present embodiment, the predetermined time interval is described as 1 hour. Note that the predetermined time may be other than the above time interval.

[0028] The information related to the air conditioner 900 is information acquired from the air conditioner 900. In the present embodiment, the information related to the air conditioner 900 preferably includes the operating state and energy consumption amount of the air conditioner 900. The operating state of the air conditioner 900 preferably includes the start / stop state, operation setting, and set temperature of the air conditioner 900.

[0029] The detected information is the information acquired from the detection device 500. In the present embodiment, it is preferable that the detected information includes information regarding the indoor environment, information regarding the outside air environment, information regarding the date, and information regarding the occupants. Each piece of information will be described later.

[0030] The communication information is the information acquired from the communication device 501. In the present embodiment, it is preferable that the communication information includes prediction information regarding the outside air environment corresponding to the next time interval. Information regarding the outside air environment corresponding to the next time interval will be described later.

[0031] The storage unit 102 is an information storage medium and has a configuration for storing various information. It is preferable that the various information stored includes information regarding the air conditioner 900, the detected information, and the communication information. Note that the storage unit 102 may be a flash memory such as an SD memory card, or may be another type of recording medium.

[0032] The indoor environment estimation unit 103 has a configuration for estimating information regarding the next indoor environment at predetermined time intervals. In the present embodiment, the indoor environment estimation unit 103 has a configuration for inputting the information described below into the indoor environment learning model.

[0033] The information input into the indoor environment learning model is information regarding the air conditioner 900, information regarding the indoor environment acquired last time, and information regarding the outside air environment acquired last time. In addition to the above-mentioned information, information regarding the indoor environment acquired this time and information regarding the outside air environment acquired this time may also be included.

[0034] The indoor environment learning model is a model that has been learned by machine learning. A known learning method can be used as the machine learning. The machine learning is preferably ensemble learning. More preferably, the machine learning is gradient boosting regression tree (XGBOOST, eXtreme Gradient Boosting).

[0035] Information on the indoor environment is information indicating environmental information in the room. In the present embodiment, it is preferable that the information on the indoor environment includes the indoor temperature, the mean radiant temperature, and the indoor humidity.

[0036] Information on the outdoor environment is information indicating environmental information in the outside air. In the present embodiment, it is preferable that the information on the outdoor environment includes the outdoor temperature, the outdoor humidity, the weather, the precipitation probability, the cloud amount, the wind speed, and the solar radiation amount.

[0037] Next, the relationships among the current time, the previous time, and the next time will be described. The control device 100 performs arithmetic processing at predetermined time intervals. In the present embodiment, it is preferable that the predetermined time interval is one hour before.

[0038] The current time is the timing at which the control device 100 performs arithmetic processing. Hereinafter, the timing will also be described as the following point. The previous time is the timing at which the control device 100 is not performing arithmetic processing and is the timing before the current time point.

[0039] The next time is the timing at which the control device 100 is not performing arithmetic processing and is the timing after the current time point. The in-room occupant number estimation unit 104 is configured to estimate the number of in-room occupants at the next time at predetermined time intervals determined in advance. In the present embodiment, the in-room occupant number estimation unit 104 is configured to input the information described below into the in-room occupant mathematical learning model.

[0040] The information input into the in-room occupant mathematical learning model is information regarding the date corresponding to the next time, information regarding the outdoor environment corresponding to the next time, information regarding the date acquired this time, information regarding the in-room occupants acquired this time, information regarding the outdoor environment acquired this time, information regarding the date acquired the previous time, information regarding the in-room occupants acquired the previous time, and information regarding the outdoor environment acquired the previous time.

[0041] The information about the occupants is information including the number of occupants and the details of the occupants. The number of occupants is information indicating the number of people present in the room. The details of the occupants preferably include information about the group to which the occupants belong, the amount of clothing worn by the occupants, which is information about the clothing the occupants are wearing, and the amount of movement of the occupants.

[0042] The information about the date is information in which the schedule of the occupants is associated with the date. In this embodiment, the information about the date preferably includes information about the date, the day of the week, and holidays.

[0043] The occupant number learning model is a model that has been learned by machine learning. As the machine learning, known learning methods can be used. The machine learning is preferably ensemble learning. More preferably, the machine learning is gradient boosting regression tree (XGBOOST, eXtreme Gradient Boosting).

[0044] The power consumption estimation unit 105 is configured to estimate the next power consumption at predetermined time intervals. In this embodiment, the power consumption estimation unit 105 is configured to input the information described below into the power consumption learning model.

[0045] The information input into the power consumption learning model is information about the air conditioner 900 acquired this time, information about the indoor environment acquired last time, information about the outside air environment acquired last time, the power consumption acquired last time, the estimated information about the next indoor environment, and the estimated number of next occupants. In addition to the above-mentioned information, information about the indoor environment acquired this time, information about the outside air environment acquired this time, and the power consumption acquired this time may be included.

[0046] The power consumption learning model is a model that has been learned by machine learning. As the machine learning, known learning methods can be used. The machine learning is preferably a neural network.

[0047] The calculation unit 109 is configured to calculate the PMV value based on information regarding the indoor environment, information regarding the outside air environment, and information regarding the occupants. In the present embodiment, it is preferable that the calculation unit 109 estimates the amount of energy consumption for each room temperature included in the estimated information regarding the indoor environment.

[0048] The PMV value is a parameter calculated by a comfort equation using six variables: indoor temperature, indoor humidity, indoor radiant temperature, indoor wind speed, clothing quantity, and activity level. In the present embodiment, the PMV value is a parameter calculated by a comfort equation using as variables the indoor temperature, humidity, and radiant temperature included in the information regarding the indoor environment, the wind speed included in the information regarding the outside air environment, and the clothing quantity and activity level included in the information regarding the occupants.

[0049] Note that the PMV value ranges from -3 (cold) to +3 (hot). When the PMV value = 0, statistically about 95% of people feel comfortable, and when the PMV value is between +0.5 and -0.5, statistically about 90% of people feel comfortable. It is preferable to control the air conditioning so that the PMV value falls within a predetermined range.

[0050] The combination unit 110 is configured to combine at least one set of the amount of energy consumption estimated by the energy consumption estimation unit 105 and the PMV value calculated by the calculation unit 109. In the present embodiment, it is preferable that the combination unit 110 combines the amount of energy consumption and the PMV value estimated from the same room temperature.

[0051] The selection unit 106 is configured to select the best combination based on at least one set of combinations of the amount of energy consumption and the PMV value combined by the combination unit 110. The best combination is a combination that satisfies both an improvement in human comfort and being the minimum among a plurality of estimated energy consumption amounts. In other words, it is a combination that satisfies both being within the range of +0.5 to -0.5 for the PMV value and being the minimum among a plurality of estimated energy consumption amounts.

[0052] The control unit 107 is connected to the air conditioner 900 in an information - communicable manner and has a configuration capable of controlling the air conditioner 900. Note that the description of the control unit 107 controlling the air conditioner 900 will be described later.

[0053] The comparison unit 108 has a configuration for comparing the estimated energy consumption amount and the acquired energy consumption amount. In the present embodiment, the comparison unit 108 can output the difference between the estimated energy consumption amount and the acquired energy consumption amount as a graph.

[0054] The detection device 500 is a device connected to the control device 100 in an information - communicable manner and has a configuration for detecting information on the indoor environment, information on the outside - air environment, information on the date, and information on the occupants. In the present embodiment, it is preferable that one detection device 500 is provided for each room. Note that a plurality of detection devices 500 may be provided in one room, or they may not be provided at all.

[0055] The communication device 501 is a device connected to the control device 100 in an information - communicable manner and has a configuration for acquiring prediction information on the outside - air environment corresponding to the next time interval. In the present embodiment, the communication device 501 is a device capable of connecting to a network and includes a personal computer or the like.

[0056] The prediction information on the outside - air environment corresponding to the next time interval is preferably information on the next outside - air environment, and weather forecasts may be used. Note that it is preferable that the weather forecast includes predictions of the outside - air temperature, outside - air humidity, weather, precipitation probability, cloud amount, wind speed, and solar radiation amount.

[0057] Next, the operation of the control device 100 with the above configuration will be described. First, the air conditioning of the air conditioner 900 in the office will be described, second, the detection device 500 will be described, third, the control of the control device 100 will be described, and fourth, the learning method of the learning model will be described.

[0058] The mechanism by which the air conditioner 900 cools the room will be described. The air conditioner 900 sucks the indoor air into the interior of the indoor unit by rotating the air conditioning fan. The sucked air is cooled in the indoor heat exchange section. Specifically, the sucked air has its heat taken away by the refrigerant circulating between the indoor unit and the outdoor unit, and its temperature decreases. Also, the refrigerant that has taken away the heat releases the heat to the outside air in the outdoor heat exchange section. The refrigerant that has released the heat takes away the heat of the sucked air again in the heat exchange section. In other words, the sucked air is cooled by the refrigerant.

[0059] The cooled air is discharged into the room by the air conditioning fan. The air discharged into the room is warmed by the heat radiated from the occupants and electronic devices. The warmed air is sucked into the air conditioner 900 again.

[0060] Next, the detection device 500 will be described. When the detection device 500 is activated, it performs a process of detecting the information to be detected. Specifically, it performs a process of detecting information regarding the indoor environment, information regarding the outside air environment, information regarding the date, and information regarding the occupants. The detected information is communicated to the control device 100.

[0061] Next, the control of the control device 100 will be described with reference to FIG. 2. When the control in the control device 100 is started, the acquisition unit 101 performs a process of acquiring various information from the air conditioner 900, the detection device 500, and the communication device 501 at predetermined time intervals (S1). In the present embodiment, the predetermined time interval is preferably 1 hour.

[0062] When various information is stored, the indoor environment estimation unit 103 performs a process of estimating at least one piece of information regarding the next indoor environment based on the input data 1 (S2). The estimated information regarding the next indoor environment is stored in the storage unit 102.

[0063] The input data 1 is information regarding the air conditioner 900 acquired this time, information regarding the indoor environment acquired last time, and information regarding the outside air environment acquired last time. When the estimated information regarding the next indoor environment is stored, the in-room occupant number estimation unit 104 performs a process of estimating the next in-room occupant number based on the input data 2 (S3). The estimated next in-room occupant number is stored in the storage unit 102.

[0064] Note that the input data 2 is information regarding the date corresponding to the time next time, information regarding the outside air environment corresponding to the time next time, information regarding the date acquired this time, information regarding the in-room occupants acquired this time, information regarding the outside air environment acquired this time, information regarding the date acquired last time, information regarding the in-room occupants acquired last time, and information regarding the outside air environment acquired last time.

[0065] When the estimated information regarding the next in-room occupants is stored, the energy consumption estimation unit 105 performs a process of estimating the next energy consumption for each piece of information regarding the estimated next indoor environment based on the input data 3, the estimated information regarding the next indoor environment, and the estimated next in-room occupant number (S3). The information regarding the estimated next energy consumption is stored in the storage unit 102.

[0066] The input data 3 is information regarding the air conditioner 900 acquired this time, information regarding the indoor environment acquired last time, information regarding the outside air environment acquired last time, and the energy consumption acquired last time.

[0067] When the estimated next energy consumption amount is stored, the arithmetic unit 109 performs a process of calculating the PMV value for each of the estimated next indoor environmental information (S4). Specifically, based on the room temperature, humidity, radiant temperature, wind speed included in the temperature related to the outside air environment, clothing amount, and amount of movement included in the information related to the occupants, which are included in the information related to the estimated next indoor environment, a process of calculating the PMV value is performed. Note that a known method can be used as the method for the arithmetic process of obtaining the PMV value. The obtained PMV value is stored in the storage unit 102. The calculated PMV value is stored in the storage unit 102.

[0068] After the PMV value is stored, the combining unit 110 combines the estimated next energy consumption amount and the PMV value corresponding to the estimated next energy consumption amount for each of the information related to the estimated next indoor environment. In other words, the combining unit 110 combines at least one set of combinations of the energy consumption amount and the PMV value. The combination of the energy consumption amount and the PMV value is stored in the storage unit 102.

[0069] When the combination of the energy consumption amount and the PMV value is stored, the selection unit 106 performs a process of selecting the best combination from at least one set of combinations (S6). In the present embodiment, the best combination is a combination in which the power consumption amount is the minimum and the PMV value is within the range of +0.5 to -0.5.

[0070] Based on the best combination, the control unit 107 performs a process of controlling the air conditioner 900 (S7). In the present embodiment, it is preferable that the control unit 107 controls the start / stop of the air conditioner 900, the change of the operation setting, and the change of the set temperature.

[0071] Note that the processes of S1 to S7 described above can be described by rephrasing with reference to FIG. 3. Based on the input data 1, the indoor environment estimation unit 103 performs a process of estimating the information related to the next indoor environment in at least one or more respects (S11).

[0072] Next, based on the input data 2, the in-room number estimator 104 performs a process of estimating the next in-room number (S12). Based on the estimated information on the next indoor environment, the estimated next in-room number, and the input data 3, the energy consumption estimator 105 can estimate the next energy consumption for each piece of the estimated next indoor environment information (S13).

[0073] Also, when the process of S11 ends, the arithmetic unit 109 calculates the PMV value for each piece of the estimated next indoor environment information (S14). When the processes of S13 and S14 end, the combiner 110 performs a process of combining at least one combination of the energy consumption and the PMV value (S15).

[0074] The selector 106 performs a process of selecting the best combination from at least one combination. Based on at least one combination, the controller 107 performs a process of controlling the air conditioner 900 (S17).

[0075] Next, the process of the comparator 108 will be described. In the processes of S1 to S7, the comparator 108 performs a process of outputting, as a graph, the energy consumption (hereinafter also referred to as the control value) consumed in the air conditioner 900 by the control of the control device 100 and the energy consumption (hereinafter also referred to as the uncontrolled value) consumed by the control not by the control device 100. In the present embodiment, the output graph will be described as FIG. 4.

[0076] FIG. 4 is a graph showing the difference between the control value and the uncontrolled value in the air conditioner 900. The vertical axis of the graph in FIG. 4 indicates the power consumption, and the horizontal axis indicates the time. In FIG. 4, the control value is indicated by DA, and the uncontrolled value is indicated by DB. The range DC surrounded by the control value DA and the control value DB indicates the energy consumption reduced by the control in the control device 100.

[0077] Next, the machine learning of the indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model will be described. In the present embodiment, an example in which machine learning of the indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model is performed in an information processing apparatus different from the control device 100 will be described. The indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model for which machine learning has been performed are stored in the storage unit 102 before the control by the control device 100 is performed.

[0078] Further, after the control by the control device 100 is performed, the indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model for which further machine learning has been performed may be stored in the storage unit 102. In this case, the previously stored indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model are replaced with the indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model for which further machine learning has been performed.

[0079] Note that the machine learning of the indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model may be performed in a different information processing apparatus as described above, or may be performed in the control device 100. When machine learning is performed in the control device 100, a machine learning unit for performing machine learning is provided in the control device 100. Further, machine learning for one of the indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model may be performed in a different information processing apparatus, and machine learning for the other may be performed in the control device 100.

[0080] Regarding the specific machine learning in the indoor environment learning model, the occupant number learning model, and the energy consumption amount learning model, known supervised learning can be used, and the specific content of the arithmetic processing in the supervised learning is not limited.

[0081] In addition, regarding the method for creating the teacher data of the indoor environment learning model and the teacher data of the occupant number learning model, a known creation method can be used, and the specific creation method is not limited.

[0082] According to the control device 100 configured as described above, information regarding the indoor environment is estimated by the indoor environment estimation unit 103, and the number of occupants is estimated by the number-of-occupants estimation unit 104. By using the estimated information regarding the indoor environment and the number of occupants, the amount of consumed energy is further estimated by the consumed-energy estimation unit 105. Thus, compared with the case where the amount of consumed energy is estimated without using the number of occupants, it is easier to estimate the amount of consumed energy with high accuracy.

[0083] Furthermore, for each of a plurality of set temperatures with different values, information regarding the indoor environment, the number of occupants, and the amount of consumed energy are estimated, so that for each of the plurality of different set temperatures, a combination of the indoor temperature and the amount of consumed energy can be estimated. Therefore, a prior risk assessment can be performed based on the plurality of combinations.

[0084] Furthermore, by providing the selection unit 106, it becomes easier to perform optimal control. Optimal control means that it becomes easier to perform control for selecting the best combination from a plurality of combinations. Furthermore, by providing the comparison unit 108, the difference between the estimated amount of consumed energy and the obtained amount of consumed energy corresponding thereto is compared. By comparing the difference, it becomes easier to quantitatively evaluate the amount of consumed energy and easier to improve the energy-saving effect regarding the air conditioner 900.

[0085] Note that the technical scope of the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the spirit of the present invention. For example, the present invention is not limited to being applied to the above-described embodiments, and may be applied to embodiments in which these embodiments are appropriately combined, and is not particularly limited.

Description of Reference Numerals

[0086] 100... Control device, 101... Acquisition unit, 102... Memory unit, 103... Indoor environment estimation unit, 104... Occupant number estimation unit, 105... Energy consumption amount estimation unit, 106... Selection unit, 107... Control unit, 108... Comparison unit, 109... Calculation unit, 110... Combination unit, 500... Detection device, 501... Communication device, 900... Air conditioner.

Claims

1. A control device for an air conditioner, an acquisition unit that acquires at least one or more of information related to the air conditioner, information related to the indoor environment, information related to the outside air environment, information related to the date, the number of occupants, and the energy consumption of the air conditioner at predetermined time intervals; an indoor environment estimation unit that estimates the information related to the indoor environment at the predetermined time intervals by inputting the information related to the air conditioner acquired this time by the acquisition unit, the information related to the indoor environment acquired last time, and the information related to the outside air environment acquired last time into a learned indoor environment learning model that has performed machine learning for estimating the information related to the indoor environment; an occupant number estimation unit that estimates the number of occupants at the predetermined time intervals by inputting the information related to the date acquired this time by the acquisition unit, the number of occupants acquired last time, and the information related to the outside air environment acquired last time into a learned occupant number learning model that has performed machine learning for estimating the number of occupants; an energy consumption estimation unit that estimates the energy consumption at the predetermined time intervals by inputting the information related to the air conditioner acquired this time by the acquisition unit, the information related to the outside air environment acquired last time, the information related to the indoor environment acquired last time, the energy consumption acquired last time, the information related to the indoor environment estimated this time by the indoor environment estimation unit, and the number of occupants estimated this time by the occupant number estimation unit into a learned energy consumption learning model that has performed machine learning for estimating the energy consumption; characterized in that the control device is provided.

2. The set temperature of the air conditioner has a plurality of different values, The indoor environment estimation unit, the occupant number estimation unit, and the energy consumption estimation unit estimate the information related to the indoor environment, the number of occupants, and the energy consumption for each of the plurality of different set temperatures, respectively. The control device according to Claim 1.

3. The control device according to Claim 2, further comprising a selection unit that obtains a value of the set temperature at which the indoor temperature included in the information related to the indoor environment is included in a predetermined range of the indoor temperature and the energy consumption is the lowest.

4. When the energy consumption corresponding to the energy consumption estimated by the energy consumption estimation unit is acquired by the acquisition unit, The control device according to claim 1 or claim 2, further comprising a comparison unit that compares a difference between the estimated amount of consumed energy and the acquired amount of consumed energy.

Images