Air conditioner and air conditioning system

Abstract

An air conditioner (1) performs air conditioning of a room and comprises: an indoor unit (2) that is disposed inside the room, which is a space to be air-conditioned; an outdoor unit (3) that is disposed outside the room and is capable of communicating with the indoor unit (2); and an air conditioning control unit that controls the operation of the indoor unit (2) and the operation of the outdoor unit (3). The air conditioning control unit infers an operation parameter value of a component included in the outdoor unit (3) in a refrigeration cycle of the air conditioner (1) from environment information on the environment surrounding the outdoor unit (3) and information on the set temperature in the air conditioner (1) for the room, and controls the outdoor unit (3) by using the inferred operation parameter value.

Description

Air conditioners and air conditioning systems

[0001] The present disclosure relates to air conditioners and air conditioning systems that achieve energy efficiency.

[0002] Conventionally, when the indoor temperature is higher than the set temperature, air conditioners detect the indoor temperature in the indoor unit and control both the indoor and outdoor units to bring the indoor temperature closer to the set temperature. In today's world of increasingly smart devices, development is underway to incorporate digital technology into air conditioners to enable advanced information processing and advanced control.

[0003] For example, Patent Document 1 describes a process in which data on indoor and outdoor temperatures within a target space that is the subject of air conditioning control is accumulated, a model is used to predict the indoor temperature at each time, and an operating plan is generated to reach the target temperature at the target time.

[0004] Japanese Patent Application Laid-Open No. 2020-067270

[0005] However, the technology described in Patent Document 1 only provides feedback to the indoor temperature control based on information such as the outdoor temperature. As such, while energy conservation is becoming increasingly important due to environmental issues, conventional energy efficiency technologies for air conditioners have been developed that provide feedback on the operation of the indoor unit, but have not yet developed technology that provides feedback on the operation of the outdoor unit, which consumes a lot of power.

[0006] The present disclosure has been made in consideration of the above, and has an object to provide an air conditioner that can achieve energy efficiency of the entire air conditioner by improving the energy efficiency of the outdoor unit.

[0007] In order to solve the above-mentioned problems and achieve the object, the air conditioner according to the present disclosure is an air conditioner that conditions the air of a room, which is a space to be air-conditioned, and includes an indoor unit arranged inside the room, an outdoor unit arranged outside the room and capable of communicating with the indoor unit, and an air conditioning control unit that controls the operation of the indoor unit and the outdoor unit. The air conditioning control unit infers operating parameter values ​​of components included in the outdoor unit of the refrigeration cycle provided in the air conditioner from environmental information that is information about the environment surrounding the outdoor unit and information about the room's set temperature in the air conditioner, and controls the outdoor unit using the inferred operating parameter values.

[0008] According to the present disclosure, it is possible to achieve an effect of improving the energy efficiency of the entire air conditioner by improving the energy efficiency of the outdoor unit.

[0009] FIG. 1 is a diagram showing the configuration of an air conditioning system according to a first embodiment; FIG. 2 is a diagram showing a schematic configuration of an air conditioner included in the air conditioning system according to the first embodiment; FIG. 3 is a block diagram showing the functional configuration of an air conditioner included in the air conditioning system according to the first embodiment; FIG. 4 is a diagram showing the functional configuration of a remote controller included in the air conditioning system according to the first embodiment; FIG. 5 is a diagram showing the functional configuration of a server included in the air conditioning system according to the first embodiment; FIG. 6 is a diagram showing the functional configuration of an external terminal included in the air conditioning system according to the first embodiment;

[0010] An air conditioner and an air conditioning system according to an embodiment will be described in detail below with reference to the drawings.

[0011] Embodiment 1. Fig. 1 is a diagram showing the configuration of an air conditioning system 100 according to embodiment 1. The air conditioning system 100 according to embodiment 1 is configured to include an air conditioner 1, a server 110, and an external terminal 120. The air conditioner 1, the external terminal 120, and the server 110 are connected to the Internet 130, which is a global information and communications network, and are capable of sending and receiving information among them. In the air conditioning system 100, the operation of the air conditioner 1 can be remotely controlled by the external terminal 120.

[0012] Fig. 2 is a configuration diagram schematically showing the configuration of the air conditioner 1 provided in the air conditioning system 100 according to the first embodiment. Fig. 3 is a refrigerant circuit diagram of the air conditioner 1 provided in the air conditioning system 100 according to the first embodiment.

[0013] As shown in Fig. 2, the air conditioner 1 according to the first embodiment includes an indoor unit 2 installed inside a room which is a space to be air-conditioned, an outdoor unit 3 installed outside the room, a remote controller 5 that remotely controls the operation of the air conditioner 1, and a refrigerant pipe 4 for circulating a refrigerant between the indoor unit 2 and the outdoor unit 3. The outdoor unit 3 is capable of communicating with the indoor unit 2 via a communication line (not shown). Hereinafter, the remote controller may be referred to as a remote control.

[0014] 3 , the air conditioner 1 according to the first embodiment includes a compressor 40 for compressing a refrigerant, a four-way valve 41 for switching the direction of refrigerant flow, an outdoor unit heat exchanger 42 provided in the outdoor unit 3 for exchanging heat between outdoor air and the refrigerant flowing in the refrigerant circuit, an expansion valve 43 as an expansion device for regulating the flow rate of the refrigerant flowing in the refrigerant circuit, and an indoor unit heat exchanger 44 provided in the indoor unit 2 for exchanging heat between the air in the room where the indoor unit 2 is located and the refrigerant flowing in the refrigerant circuit, all of which are connected in sequence by refrigerant pipes 4. The four-way valve 41 switches the direction of refrigerant flow in the refrigeration cycle to switch between heating operation and cooling operation.

[0015] The indoor unit 2 is also provided with an indoor unit fan 45 that generates an airflow that passes through the indoor unit heat exchanger 44 and sends the conditioned air that has been heat exchanged in the indoor unit heat exchanger 44 from the indoor unit 2 into the room. The indoor unit fan 45 operates when an indoor unit propeller 451 is driven by an indoor unit fan motor 452. The outdoor unit 3 is also provided with an outdoor unit fan 46 that generates an airflow that passes through the outdoor unit heat exchanger 42. The outdoor unit fan 46 operates when an outdoor unit propeller 461 is driven by an outdoor unit fan motor 462.

[0016] 4 is a block diagram showing the functional configuration of the air conditioner 1 included in the air conditioning system 100 according to embodiment 1. The indoor unit 2 includes an indoor unit air conditioning unit 21, an indoor temperature sensor 22, an infrared sensor 23, an indoor unit communication unit 24, an indoor unit storage unit 25, and an indoor unit control unit 26. Information can be exchanged between the components of the indoor unit 2.

[0017] The indoor unit air conditioning section 21 is an air conditioning section in the air conditioner 1 that conditions the air in the room, and has the air conditioning function of a typical indoor unit of an air conditioner. The indoor unit air conditioning section 21 includes components such as an indoor unit heat exchanger 44, an indoor unit fan 45, and a wind direction adjustment section (not shown) that adjusts the direction in which conditioned air is sent out from the indoor unit 2 into the room. Note that the components included in the indoor unit 2 are not limited to these.

[0018] The indoor temperature sensor 22 is configured using, for example, a thermistor and detects the indoor temperature of the room, which is the space to be air-conditioned, at a predetermined cycle. The indoor temperature sensor 22 transmits the detected indoor temperature data to the indoor unit control unit 26.

[0019] The infrared sensor 23 detects the temperature of the occupants in the room where the indoor unit 2 is installed, i.e., the body temperatures of the occupants, under the control of the indoor unit control unit 26. The infrared sensor 23 can detect surface temperatures at a distance and can comprehensively detect the surface temperatures of the occupants. The infrared sensor 23 transmits the detected body temperature data of the occupants to the indoor unit control unit 26.

[0020] The indoor unit communication unit 24 communicates with the outdoor unit 3 and the remote control 5. The indoor unit communication unit 24 is capable of two-way communication of information with the outdoor unit 3 via a communication line. The indoor unit communication unit 24 also communicates with the external terminal 120 and the server 110 via the Internet 130. The indoor unit communication unit 24 transmits information obtained from devices external to the indoor unit 2 to the indoor unit control unit 26.

[0021] The indoor unit communication unit 24 acquires information about the current location of the external terminal 120, i.e., information about the current location of the user of the air conditioner 1 holding the external terminal 120, or information about the perceived temperature of the user of the air conditioner 1 holding the external terminal 120, from the external terminal 120 via the Internet 130. The indoor unit communication unit 24 acquires weather forecast information for the area in which the air conditioner 1 is installed from the server 110 via the Internet 130.

[0022] The indoor unit memory unit 25 is a memory unit that stores information such as various control setting values ​​and programs for controlling the operation of the air conditioner 1. The indoor unit memory unit 25 stores various information such as various information collected by the indoor unit 2 and control information generated by the indoor unit control unit 26. The various information collected by the indoor unit 2 includes information on the detection results of the indoor temperature sensor 22, information on the current location of the external terminal 120, information on the perceived temperature of the user of the air conditioner 1 holding the external terminal 120, and weather forecast information for the area where the air conditioner 1 is installed. The indoor unit memory unit 25 is a non-volatile memory unit and is composed of a semiconductor storage medium such as a flash memory.

[0023] The indoor unit control unit 26 controls the operation of the indoor unit 2 and the outdoor unit 3, including the operation of the air conditioning unit, and controls the operation of the entire air conditioning system 100. In other words, the indoor unit control unit 26 functions as an air conditioning control unit that controls the operation of the air conditioning unit. The indoor unit control unit 26 is a control unit that controls the indoor unit 2 and the outdoor unit 3 in response to control commands from the user received via the remote control 5, thereby controlling the air conditioning system 100.

[0024] The indoor unit control unit 26 includes an operation control unit 261 and a machine learning device 262. The components of the indoor unit control unit 26 described above can exchange information with each other.

[0025] The operation control unit 261 controls the operation of the air conditioner 1, including the operation of the air conditioning unit. The operation control unit 261 controls the operation of the indoor unit 2 and the outdoor unit 3, and controls, for example, each of the operation modes of cooling operation, dehumidification operation, fan operation, and heating operation of the air conditioner 1. The operation control unit 261 also controls the operation of the outdoor unit 3 using information on the operation parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1, which information is output from the machine learning device 262.

[0026] The machine learning device 262 learns the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1. Details of the machine learning device 262 will be described later.

[0027] The outdoor unit 3 includes an outdoor unit air conditioning unit 31, an outdoor air temperature sensor 32, an outdoor unit communication unit 33, an outdoor unit storage unit 34, and an outdoor unit control unit 35. Information can be exchanged between the above-described components of the outdoor unit 3.

[0028] The outdoor unit air conditioning section 31 is an air conditioning section that conditions the air indoors in the air conditioner 1, and has the functions of a general outdoor unit of an air conditioner. The indoor unit air conditioning section 21 of the indoor unit 2 and the outdoor unit air conditioning section 31 of the outdoor unit 3 constitute the air conditioning section of the air conditioner 1, which is a component that conditions the air indoors in the air conditioner 1.

[0029] The outdoor unit air conditioning section 31 is provided with a compressor 40, a four-way valve 41, an outdoor unit heat exchanger 42, an expansion valve 43, and an outdoor unit fan 46. Note that the configuration of the outdoor unit air conditioning section 31 is not limited to these.

[0030] The outdoor air temperature sensor 32 detects the outdoor air temperature, which is the temperature of the air outdoors. Information on the outdoor air temperature detected by the outdoor air temperature sensor 32 is sent to the indoor unit control unit 26.

[0031] The outdoor unit communication unit 33 communicates with the indoor unit communication unit 24 of the indoor unit 2. The outdoor unit communication unit 33 is capable of bidirectional communication of information with the indoor unit communication unit 24 of the indoor unit 2.

[0032] The outdoor unit storage unit 34 is a storage unit that stores information such as various control setting values ​​and programs for controlling the operation of the outdoor unit 3. The outdoor unit storage unit 34 is a non-volatile storage unit, and is configured with a semiconductor storage medium such as a flash memory.

[0033] The outdoor unit control unit 35 controls the operation of the outdoor unit 3 under the control of the indoor unit control unit 26 .

[0034] 5 is a diagram showing the functional configuration of the remote controller 5 provided in the air conditioning system 100 according to embodiment 1. The remote controller 5 communicates with the indoor unit 2 and transmits control information for remotely controlling the operation of the air conditioner 1 to the indoor unit 2. The remote controller 5 also communicates with the indoor unit 2 and receives and displays information related to the operation of the air conditioner 1.

[0035] The remote control 5 includes a remote controller operation unit 51, a remote controller display unit 52, a remote controller storage unit 53, a remote controller communication unit 54, and a remote controller control unit 55. Information can be exchanged between the above-described components of the remote control 5.

[0036] The remote control operation unit 51 accepts operations from the user. When the remote control operation unit 51 accepts an operation from the user, it transmits information corresponding to the user operation as an operation signal to the remote control control unit 55. The remote control operation unit 51 accepts operations to instruct an operation, such as an operation from the user to instruct cooling operation, an operation from the user to instruct dehumidification operation, an operation from the user to instruct fan operation, an operation from the user to instruct heating operation, and an operation from the user to instruct sleep operation.

[0037] The remote control display unit 52 is a display unit that displays various information. The remote control display unit 52 displays information and status required for air conditioning by the air conditioner 1, such as the set temperature and operation mode of the air conditioner 1, and switches and displays screens corresponding to operations on the remote control operation unit 51.

[0038] The remote control storage unit 53 stores various types of information necessary for air conditioning in the air conditioner 1. The remote control storage unit 53 temporarily or long-term stores the settings to be displayed on the remote control display unit 52 and image data related to the settings. The remote control storage unit 53 is a non-volatile storage unit, and is configured using a semiconductor storage medium such as a flash memory.

[0039] The remote control communication unit 54 is capable of bidirectional communication of information with the indoor unit communication unit 24 of the indoor unit 2. The connection between the indoor unit communication unit 24 of the indoor unit 2 and the remote control communication unit 54 may be either a wireless connection or a wired connection. In other words, the communication between the indoor unit communication unit 24 of the indoor unit 2 and the remote control communication unit 54 may be wireless communication, infrared communication, or wired communication.

[0040] The remote control control unit 55 controls the operation of the remote control 5. The remote control control unit 55 controls the remote control 5 based on an operation signal transmitted from the remote control operation unit 51. The remote control control unit 55 remotely controls the operation of the air conditioner 1. Based on the operation signal transmitted from the remote control operation unit 51, the remote control control unit 55 transmits control information for remotely controlling the operation of the air conditioner 1 to the indoor unit 2.

[0041] 6 is a diagram showing the functional configuration of the server 110 included in the air conditioning system 100 according to the first embodiment. The server 110 includes a server communication unit 111, a server storage unit 112, and a server control unit 113. Information can be exchanged between the components of the server 110.

[0042] The server communication unit 111 is connected to the Internet 130 and communicates with the indoor unit communication unit 24 of the indoor unit 2 of the air conditioner 1 .

[0043] The server storage unit 112 stores various information related to the processing of the server 110 .

[0044] The server control unit 113 is a control unit that controls the overall processing of the server 110. The server control unit 113 controls the acquisition of weather forecast information for the region in which the air conditioner 1 is installed from an external website or homepage managed by the server 110, controls the storage of weather forecast information for the region in which the air conditioner 1 is installed in the server storage unit 112, and controls the transmission of weather forecast information for the region in which the air conditioner 1 is installed to the indoor unit control unit 26 of the indoor unit 2 of the air conditioner 1.

[0045] 7 is a diagram showing the functional configuration of the external terminal 120 included in the air conditioning system 100 according to embodiment 1. The external terminal 120 includes a terminal operation unit 121, a position detection unit 122, a sensible temperature detection unit 123, a terminal display unit 124, a terminal storage unit 125, a terminal communication unit 126, and a terminal control unit 127. Information can be exchanged between the above-described components of the external terminal 120.

[0046] The terminal operation unit 121 is an input unit that accepts setting operations from the user. The terminal operation unit 121 accepts control instruction information for the air conditioner 1 that is input and set by the user, and transmits the control instruction information to the terminal storage unit 125 and the terminal control unit 127.

[0047] The position detection unit 122 detects information about the current position of the external terminal 120. The position detection unit 122 transmits the acquired information about the current position of the external terminal 120 to the terminal control unit 127. The information about the current position of the external terminal 120 can be said to be information about the current position of the user of the air conditioner 1 holding the external terminal 120, and can be said to be personal information of the user.

[0048] The sensible temperature detection unit 123 detects the sensible temperature of a user of the air conditioner 1 holding the external terminal 120. The sensible temperature detection unit 123 transmits the acquired information on the sensible temperature of the user to the terminal control unit 127. The sensible temperature of the user can be considered personal information of the user.

[0049] The terminal display unit 124 is a display unit that displays various information.

[0050] The terminal storage unit 125 is a storage unit that stores various types of information, including control instruction information for the air conditioner 1 .

[0051] The terminal communication unit 126 performs wireless communication with a public line, connects to the Internet 130 via the public line, and communicates with the server 110 .

[0052] The terminal control unit 127 is a control unit that controls the overall processing of the external terminal 120. The terminal control unit 127 transmits control instruction information for the air conditioner 1 sent from the terminal operation unit 121 to the air conditioner 1 via the terminal communication unit 126 and the Internet 130. This allows the user to control the operation of the air conditioner 1 using the external terminal 120.

[0053] In addition, the terminal control unit 127 transmits information about the current location of the external terminal 120 obtained from the location detection unit 122, i.e., information about the current location of the user of the air conditioner 1 holding the external terminal 120, to the indoor unit control unit 26 of the indoor unit 2 of the air conditioner 1 via the terminal communication unit 126 and the Internet 130.

[0054] In addition, the terminal control unit 127 transmits information about the user's perceived temperature obtained from the perceived temperature detection unit 123 to the indoor unit control unit 26 of the indoor unit 2 of the air conditioner 1 via the terminal communication unit 126 and the Internet 130.

[0055] Next, we will explain in detail the machine learning device 262 provided in the indoor unit control unit 26 of the indoor unit 2 of the air conditioner 1. Below, we will explain the case where the machine learning device 262 includes a learning device 27 and an inference device 28 and learns the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1.

[0056] The machine learning device 262 learns the operational parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1, based on input information including environmental information, which is information about the environment surrounding the outdoor unit 3, information about the room set temperature of the air conditioner 1, and operational parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1. In other words, the machine learning device 262 learns the operational parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1, which are appropriate for the combined state of the environmental information, which is information about the environment surrounding the outdoor unit 3, and the room set temperature of the air conditioner 1, based on input information including environmental information, which is information about the environment surrounding the outdoor unit 3, information about the room set temperature of the air conditioner 1, and operational parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1.

[0057] Hereinafter, the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle equipped in the air conditioner 1 may be simply referred to as operating parameter values. Furthermore, environmental information, which is information about the environment surrounding the outdoor unit 3, may be simply referred to as environmental information. Furthermore, the room setting temperature in the air conditioner 1 may be simply referred to as the room setting temperature.

[0058] <Learning Phase> Next, the configurations of the learning device 27 and the inference device 28 will be described. Fig. 8 is a diagram showing the configuration of the learning device 27 of the machine learning device 262 provided in the air conditioner 1 according to embodiment 1. The learning device 27 is a computer that learns the operational parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1 in an input state.

[0059] The learning device 27 includes a data acquisition unit 271 and a model generation unit 272 .

[0060] The data acquisition unit 271 acquires learning data including environmental information, which is information about the environment surrounding the outdoor unit 3, information about the room temperature setting of the air conditioner 1, and information about the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1. The data acquisition unit 271 is a first data acquisition unit in the machine learning device 262.

[0061] The operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1 are set parameter values ​​for controlling the operation of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1. The operating parameter value is, for example, at least one of the rotation speed of the compressor 40 included in the outdoor unit 3, the opening degree of the expansion valve 43 included in the outdoor unit 3, and the rotation speed of the outdoor unit fan 46 included in the outdoor unit 3. The data acquisition unit 271 acquires information on the operating parameter values ​​from the indoor unit control unit 26 or the outdoor unit control unit 35.

[0062] The environmental information, which is information about the environment surrounding the outdoor unit 3, is information about the environment surrounding the outdoor unit 3 installed outdoors, and is information about the outdoor environment. The environmental information is, for example, at least one of information about outdoor air temperature and information about the weather forecast for the area where the air conditioner 1 is installed. The data acquisition unit 271 acquires, from the indoor unit control unit 26, information about the outdoor air temperature that is detected by the outdoor air temperature sensor 32 and transmitted to the indoor unit control unit 26. The data acquisition unit 271 connects to the server 110 via the Internet 130 and the indoor unit communication unit 24, and acquires weather forecast information for the area where the air conditioner 1 is installed from an external website or homepage managed by the server 110 via the Internet 130.

[0063] The room set temperature in the air conditioner 1 is the set temperature for various operations of the air conditioner 1, which is set in the operation control unit 261 of the indoor unit control unit 26 from the remote control 5 or the external terminal 120. The data acquisition unit 271 acquires information about the room set temperature from the operation control unit 261.

[0064] The model generation unit 272 learns the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1 that are suitable for the combination of the environmental information, which is information about the environment surrounding the outdoor unit 3, and the room set temperature of the air conditioner 1, based on learning data including input information: environmental information, which is information about the environment surrounding the outdoor unit 3, information about the room set temperature of the air conditioner 1, and information about operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1. In other words, the model generation unit 272 generates a trained model 276 for inferring operating parameter values ​​corresponding to the state of the combination of the environmental information and the room set temperature, from the input information: environmental information and the room set temperature.

[0065] The operating parameter values ​​suitable for the combination of environmental information and room temperature setting are those that can reduce the power consumption of the outdoor unit 3 for the combination of environmental information and room temperature setting information.

[0066] Therefore, the trained model 276 can be said to be a trained model for inferring information on operating parameter values ​​that reduce the power consumption of the outdoor unit 3 from environmental information, which is information on the environment surrounding the outdoor unit 3, and information on the room set temperature in the air conditioner 1.

[0067] The learning algorithm used by the model generation unit 272 can be any known algorithm, such as supervised learning, unsupervised learning, or reinforcement learning. As an example, a case where reinforcement learning is applied will be described. In reinforcement learning, an agent (acting subject) in a certain environment observes the current state (environmental parameters) and determines the action to be taken. The environment changes dynamically depending on the agent's actions, and the agent is given a reward according to the environmental changes. The agent repeats this process and learns the course of action that will obtain the most reward through a series of actions. Q-learning and TD-learning are known as representative reinforcement learning methods. For example, in the case of Q-learning, the general update formula for the action value function Q(s, a) is expressed as the following formula (1):

[0068]

[0069] In formula (1), s t represents the environment at time t, and a t represents the action at time t. t Therefore, the state (environment) is s t+1 It changes to r t+1 represents the reward that can be obtained depending on the change in state, γ represents the discount rate, and α represents the learning coefficient. Note that γ is in the range of 0<γ≦1, and α is in the range of 0<α≦1. When the operation parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1 are t The environmental information, which is information about the environment surrounding the outdoor unit 3, and the information about the room temperature setting in the air conditioner 1 are in the state s t The learning device 27 calculates the state s t Best action in a t Learn.

[0070] The update formula expressed by equation (1) increases the action value Q if the action value Q of the action a with the highest Q value at time t+1 is greater than the action value Q of the action a executed at time t, and decreases the action value Q in the opposite case. In other words, the learning device 27 updates the action value function Q(s, a) so that the action value Q of the action a at time t approaches the best action value Q at time t+1. As a result, the best action value Q in a certain environment is propagated sequentially to the action value Q in the previous environment.

[0071] As described above, when the model generation unit 272 generates the trained model 276 by reinforcement learning, the model generation unit 272 has a reward calculation unit 273 and a function update unit 274.

[0072] The reward calculation unit 273 calculates a reward r for the applied operating parameter value, using a reduction in power consumption by the outdoor unit 3 as a reward criterion, based on input information such as environmental information, which is information about the environment surrounding the outdoor unit 3, information about the room temperature setting of the air conditioner 1, and information about operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle equipped in the air conditioner 1. For example, if the power consumption of the outdoor unit 3 decreases (reward increase criterion), the reward calculation unit 273 increases the reward r (for example, provides a reward of "1"), and on the other hand, if the power consumption of the outdoor unit 3 does not decrease (reward decrease criterion), the reward calculation unit 273 decreases the reward r (for example, provides a reward of "-1").

[0073] The reward calculation unit 273 stores a threshold value 2731, which is a reference value for determining whether to increase or decrease the reward for the applied operation parameter value.

[0074] The threshold 2731 is a reference value for determining whether to increase or decrease the reward for the applied operation parameter value by comparing the power consumption of the outdoor unit 3 in a state where environmental information, which is information about the environment surrounding the outdoor unit 3 and corresponds to the input information, is combined with information about the room set temperature of the air conditioner 1 and information about operation parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1. In other words, the threshold 2731 is a reference value for determining whether to increase or decrease the reward for the applied operation parameter value by comparing the power consumption of the outdoor unit 3 in a state where the outdoor unit 3 is controlled using the operation parameter value corresponding to the input information in a state where the environmental information corresponding to the input information is combined with information about the room set temperature. The threshold 2731 can be changed to any value by the user setting a value in the reward calculation unit 273.

[0075] The function update unit 274 updates the function for determining an action parameter value (action) based on the reward calculated by the reward calculation unit 273. The function update unit 274 updates the function for determining an action parameter value in accordance with the reward calculated by the reward calculation unit 273, and outputs the updated function to the learned model storage unit 275 as a learned model 276. For example, in the case of Q-learning, the function update unit 274 updates the action value function Q(s t , a t ) is used as a function for calculating the action parameter value. t , a t ) can be said to be an operation parameter value generation function for calculating the operation parameter values.

[0076] The learning device 27 repeatedly executes the above-described learning.

[0077] The learned model storage unit 275 stores the action value function Q(s t , a t ), i.e., the trained model 276.

[0078] Next, the processing procedure of the learning process performed by the learning device 27 will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the processing procedure of the learning process performed by the learning device 27 provided in the air conditioner 1 according to the first embodiment.

[0079] In step S110, the data acquisition unit 271 acquires the input information, which is environmental information that is information about the environment surrounding the outdoor unit 3, information about the room setting temperature in the air conditioner 1, and information about the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle equipped in the air conditioner 1, as learning data.

[0080] In step S120, the model generation unit 272 calculates a reward for the applied operation parameter value based on the environmental information, the room set temperature information, and the operation parameter value information. Specifically, the reward calculation unit 273 calculates and acquires the power consumption of the outdoor unit 3 based on the environmental information, the room set temperature information, and the operation parameter value information, and determines whether to increase or decrease the reward for the applied operation parameter value based on a threshold value 2731 that is a predetermined reward standard. Information for calculating the power consumption of the outdoor unit 3 based on the environmental information, the room set temperature information, and the operation parameter value information is stored in advance in the model generation unit 272.

[0081] The remuneration calculation unit 273 determines to increase the remuneration when the calculated power consumption of the outdoor unit 3 is less than the threshold value 2731. The remuneration calculation unit 273 determines to decrease the remuneration when the calculated power consumption of the outdoor unit 3 is equal to or greater than the threshold value 2731.

[0082] When the remuneration calculation unit 273 determines to increase the remuneration (step S120, remuneration increase criterion, power consumption of the outdoor unit 3<threshold 2731), it increases the remuneration in step S130. On the other hand, when the remuneration calculation unit 273 determines to decrease the remuneration (step S120, remuneration decrease criterion, power consumption of the outdoor unit 3≧threshold 2731), it decreases the remuneration in step S140.

[0083] In step S150, the function update unit 274 updates the action value function Q(s) represented by equation (1) stored in the trained model storage unit 275 based on the reward calculated by the reward calculation unit 273. t , a t ) to update.

[0084] The learning device 27 repeatedly executes the above steps S110 to S150 to generate the action value function Q(s t , a t ) is stored as a trained model 276 in the trained model storage unit 275.

[0085] In addition, the learning device 27 in embodiment 1 stores the learned model 276 in a learned model storage unit 275 provided outside the learning device 27, but the learned model storage unit 275 may also be located inside the learning device 27.

[0086] The learning device 27 configured as described above can learn the relationship between information on operating parameter values ​​of components included in the outdoor unit 3 of the refrigeration cycle equipped in the air conditioner 1, which can reduce the power consumption of the outdoor unit 3, environmental information which is information on the environment surrounding the outdoor unit 3, and information on the room set temperature in the air conditioner 1. In other words, the learning device 27 can learn operating parameter values ​​that can reduce the power consumption of the outdoor unit 3 for combinations of environmental information and room set temperature information.

[0087] 10 is a diagram showing the configuration of the inference device 28 of the machine learning device 262 provided in the air conditioner 1 according to embodiment 1. The inference device 28 includes a data acquisition unit 281 and an inference unit 282.

[0088] The data acquisition unit 281 acquires inference data, which is input information, including environmental information that is information about the environment surrounding the outdoor unit 3 and information about the room temperature setting of the air conditioner 1. The data acquisition unit 281 is a second data acquisition unit in the machine learning device 262.

[0089] The inference unit 282 uses the trained model 276 to infer operational parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1, and outputs the inferred operational parameter values ​​to the operation control unit 261 of the indoor unit control unit 26 as operational parameter inference results 283. That is, by inputting environmental information, which is information about the environment surrounding the outdoor unit 3 acquired by the data acquisition unit 281, and information about the room set temperature in the air conditioner 1, into the trained model 276, the inference unit 282 can infer operational parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1 that are suitable for the combination of the input environmental information and room set temperature information. Note that the inference device 28 can also be arranged outside the air conditioner 1.

[0090] In embodiment 1, the inference device 28 uses the learned model 276 learned by the model generation unit 272 to infer the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1. However, the inference device 28 may also acquire the learned model 276 from a learning device other than the learning device 27 and infer the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1 based on this learned model 276.

[0091] Next, the processing procedure of the process in which the inference device 28 infers the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1 will be described using Fig. 11. Fig. 11 is a flowchart showing the processing procedures of the inference process by the inference device 28 of the machine learning device 262 provided in the air conditioner 1 according to the first embodiment and the control process by the operation control unit 261 provided in the air conditioner 1 according to the first embodiment.

[0092] In step S210, the data acquisition unit 281 acquires environmental information, which is information about the environment surrounding the outdoor unit 3, and information about the room temperature setting of the air conditioner 1, as inference data.

[0093] In step S220, the inference unit 282 inputs the environmental information and the room set temperature information, which are data for inference, into the learned model 276 stored in the learned model memory unit 275, and obtains the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle equipped in the air conditioner 1.

[0094] In step S230, the inference unit 282 outputs information on the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle equipped in the air conditioner 1, which is the data obtained in step S220, to the operation control unit 261 of the indoor unit control unit 26 as operating parameter inference results 283. The operation control unit 261 transmits the operating parameter value information, which is the operating parameter inference result 283 obtained from the inference unit 282, to the outdoor unit control unit 35 of the outdoor unit 3 as control instruction information. The outdoor unit control unit 35 receives the operating parameter value information transmitted from the operation control unit 261.

[0095] In step S240, the outdoor unit control unit 35 uses the information on the operating parameter values ​​acquired from the operation control unit 261 to control the operation of the components included in the outdoor unit 3 of the refrigeration cycle equipped in the air conditioner 1, such as the compressor 40, expansion valve 43, and outdoor unit fan 46. This enables the air conditioner 1 to operate the outdoor unit 3 more efficiently and in an energy-saving manner with less power consumption.

[0096] In the first embodiment, a case where reinforcement learning is applied to the learning algorithm used by the inference unit 282 has been described, but the present invention is not limited to this. As for the learning algorithm, other than reinforcement learning, supervised learning, unsupervised learning, semi-supervised learning, or the like can also be applied.

[0097] Furthermore, the learning algorithm used in the model generation unit 272 can be deep learning, which learns to extract the features themselves, or the model generation unit 272 may perform machine learning according to other known methods, such as neural networks, genetic programming, functional logic programming, and support vector machines.

[0098] The learning device 27 and the inference device 28 may be devices separate from the indoor unit control unit 26 of the indoor unit 2, for example, connected to the indoor unit control unit 26 via a network. The learning device 27 and the inference device 28 may also be built into the indoor unit control unit 26. Furthermore, the learning device 27 and the inference device 28 may exist on a cloud server. That is, the machine learning device 262 may exist on the cloud server.

[0099] The model generation unit 272 may also use learning data acquired from multiple air conditioners 1 to learn the operating parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle of the air conditioner 1. The model generation unit 272 may acquire learning data from multiple air conditioners 1 used in the same area, or may learn the operating parameter values ​​using learning data collected from multiple air conditioners 1 operating independently in different areas. The learning device 27 may also add or remove air conditioners 1 from which learning data is collected as targets during the learning process. Furthermore, the learning device 27 that has learned the operating parameter values ​​for a certain air conditioner 1 may be applied to another air conditioner 1, and the learning device 27 may re-learn the operating parameter values ​​for the other air conditioner 1 to update the learned model 276.

[0100] In the above description, the data acquisition unit 271 acquires environmental information, information on the room temperature setting, and information on operation parameter values ​​as learning data. However, the data acquisition unit 271 may further acquire information on the user's current location, which is personal information about the user, as learning data. The data acquisition unit 271 acquires the information on the user's current location from the external terminal 120 via the Internet 130. The data acquisition unit 271 may acquire the information on the user's current location from the external terminal 120 via the server 110 and then via the Internet 130.

[0101] In this case, the learning device 27 learns operation parameter values ​​that can reduce the power consumption of the outdoor unit 3 for a combination of environmental information, information on the room set temperature, and information on the user's current location, and generates a learned model 276. Furthermore, the inference device 28 inputs inference data including the environmental information, information on the room set temperature, and information on the user's current location into the learned model 276, and infers operation parameter values ​​that can reduce the power consumption of the outdoor unit 3 for a combination of environmental information, information on the room set temperature, and information on the user's current location.

[0102] For example, the learning device 27 learns operational parameter values ​​that can predict the arrival time of a user in a room and reduce the power consumption of the outdoor unit 3 for a combination of environmental information, information on the room's set temperature, and information on the user's current location, and generates a trained model 276. When the operation of the air conditioner 1 is remotely controlled by the external terminal 120, the inference device 28 inputs the environmental information, information on the room's set temperature, and information on the user's current location into the trained model 276. Then, the inference device 28 predicts the arrival time of the user in the room and infers operational parameter values ​​that can reduce the power consumption of the outdoor unit 3.

[0103] That is, by inputting inference data including environmental information, information on the room's set temperature, and information on the user's current location, the trained model 276 predicts the user's arrival time in the room and infers operation parameter values ​​that can reduce unnecessary power consumption of the outdoor unit 3 before the arrival time, thereby reducing the power consumption of the outdoor unit 3. That is, the inference device 28 can obtain operation parameter values ​​that can reduce unnecessary power consumption of the outdoor unit 3 before the user's arrival time in the room, thereby reducing the power consumption of the outdoor unit 3. This allows the air conditioner 1 to reduce the power consumption of the outdoor unit 3.

[0104] The learning device 27 can then use information about the user's current location as learning data to learn operation parameter values ​​that are suitable for the environment in which the user is located, and generate a learned model 276.

[0105] Furthermore, the data acquisition unit 271 may further acquire information on the user's sensible temperature, which is personal information of the user, as learning data. The data acquisition unit 271 acquires the information on the user's sensible temperature from the external terminal 120. The data acquisition unit 271 may acquire the information on the user's sensible temperature from the external terminal 120 via the server 110 and the Internet 130.

[0106] In this case, the learning device 27 learns operation parameter values ​​that can reduce the power consumption of the outdoor unit 3 for a combination of environmental information, information on the room set temperature, and information on the user's perceived temperature, and generates a learned model 276. Furthermore, the inference device 28 inputs inference data including the environmental information, information on the room set temperature, and information on the user's perceived temperature into the learned model 276, and infers operation parameter values ​​that can reduce the power consumption of the outdoor unit 3 for a combination of environmental information, information on the room set temperature, and information on the user's perceived temperature.

[0107] For example, the learning device 27 learns the operation parameter values ​​using learning data of the operation control until the user feels the sensible temperature is reached based on the influence of the operation parameters on the user's sensible temperature. That is, the learning device 27 learns the operation parameter values ​​that can reduce the power consumption of the outdoor unit 3 for the state of combinations of the environmental information, the information on the room set temperature, and the information on the user's sensible temperature for the operation control until the user feels the sensible temperature is reached, and generates the learned model 276.

[0108] The inference device 28 inputs inference data including environmental information, information on the room set temperature, and information on the user's perceived temperature into the trained model 276, and infers operating parameter values ​​that will result in a perceived temperature that the user finds comfortable and that will reduce the power consumption of the outdoor unit 3, for a combination of the environmental information, information on the room set temperature, and information on the user's perceived temperature. This allows the air conditioner 1 to reduce the power consumption of the outdoor unit 3.

[0109] The learning device 27 can then use information about the user's perceived temperature as learning data to learn operational parameter values ​​that are appropriate for the current user's perceived temperature and generate a learned model 276.

[0110] According to the air conditioner of embodiment 1 configured as described above, an air conditioner that conditions the air of a room includes an indoor unit that is placed inside the room, which is the space to be air-conditioned, an outdoor unit that is placed outside the room and is capable of communicating with the indoor unit, and an air conditioning control unit that controls the operation of the indoor unit and the outdoor unit, and the air conditioning control unit infers operating parameter values ​​of the components included in the outdoor unit of the refrigeration cycle that the air conditioner has from environmental information that is information about the environment surrounding the outdoor unit and information about the room's set temperature in the air conditioner, and controls the outdoor unit using the inferred operating parameter values.

[0111] Furthermore, according to the air conditioning control unit configured as described above, an air conditioning control unit is realized that has a learning device that includes: a data acquisition unit that acquires learning data including environmental information, which is information about the environment surrounding the outdoor unit, information about the room set temperature in the air conditioner, and information about operating parameter values; and a model generation unit that uses the learning data to generate a trained model for inferring information about operating parameter values ​​from the environmental information, which is information about the environment surrounding the outdoor unit, and information about the room set temperature in the air conditioner.

[0112] Furthermore, according to the air conditioning control unit configured as described above, an air conditioning control unit is realized that has an inference device that includes: a data acquisition unit that acquires environmental information, which is information about the environment surrounding the outdoor unit, and information about the room set temperature in the air conditioner; and an inference unit that outputs operating parameter values ​​corresponding to the environmental information and the room set temperature information using a trained model for inferring information about operating parameter values ​​that reduce the power consumption of the outdoor unit from the environmental information, which is information about the environment surrounding the outdoor unit, and the room set temperature information in the air conditioner.

[0113] In the air conditioning system 100 according to the first embodiment described above, the learning device 27 learns operational parameter values ​​that can reduce the power consumption of the outdoor unit 3 for a combination of environmental information, which is information about the environment surrounding the outdoor unit 3, and information about the room set temperature of the air conditioner 1, to generate a trained model 276. Also, in the air conditioning system 100, the inference device 28 inputs inference data including environmental information, which is information about the environment surrounding the outdoor unit 3, and information about the room set temperature of the air conditioner 1, into the trained model 276, and infers operational parameter values ​​of the components included in the outdoor unit 3 of the refrigeration cycle provided in the air conditioner 1 that can reduce the power consumption of the outdoor unit 3 for a combination of the environmental information and the room set temperature information. The outdoor unit 3 is then controlled using the operational parameter values ​​inferred by the inference device 28.

[0114] The air conditioning system 100 configured in this manner can learn more efficient operating methods for the outdoor unit 3 and directly obtain, as output data, setting parameter values ​​for controlling the operation of the components included in the outdoor unit 3 of the refrigeration cycle equipped in the air conditioner 1.

[0115] Furthermore, the air conditioning system 100 can obtain operating parameter values ​​that can reduce the power consumption of the outdoor unit 3 for combinations of environmental information, which is information about the environment surrounding the outdoor unit 3, and information about the room set temperature in the air conditioner 1. Therefore, the air conditioning system 100 can operate in an energy-saving manner with less power consumption for combinations of environmental information and information about the room set temperature.

[0116] Furthermore, the air conditioning system 100 can directly use the operation parameter values, which are output data from the trained model 276, to control the components included in the outdoor unit 3 of the refrigeration cycle of the air conditioner 1, such as the compressor 40, the expansion valve 43, and the outdoor unit fan 46. In other words, the air conditioning system 100 does not need to convert the control instruction information output from the indoor unit control unit 26 to the outdoor unit control unit 35 into operation parameters. This simplifies the processing in the outdoor unit control unit 35 in the air conditioning system 100, and allows for a simpler configuration of the outdoor unit control unit 35. Furthermore, because the processing in the outdoor unit control unit 35 is simplified, it is possible to reduce the load on the computer that constitutes the outdoor unit control unit 35, making it possible to use a less expensive computer with lower specifications than before.

[0117] Furthermore, the air conditioning system 100 is configured to feed back easily available information to the control of the outdoor unit 3, such as environmental information, which is information about the environment surrounding the outdoor unit 3, information about the room temperature setting in the air conditioner 1, and the power consumption of the outdoor unit 3, so that high energy efficiency of the outdoor unit 3 can be achieved with a simple configuration.

[0118] Therefore, the air conditioning system 100 has the effect of learning a more efficient operating method for the outdoor unit 3, and by improving the energy efficiency of the outdoor unit 3, it is possible to achieve energy efficiency for the air conditioner 1 as a whole.

[0119] Next, the hardware configuration of each of the control units 80 according to the first embodiment will be described. The control unit 80 according to the first embodiment corresponds to each of the indoor unit control unit 26 in the indoor unit 2 of the air conditioner 1, the outdoor unit control unit 35 in the outdoor unit 3 of the air conditioner 1, the remote control unit 55 in the remote controller 5, the server control unit 113 in the server 110, and the terminal control unit 127 in the external terminal 120. Each function of the control unit 80 according to the first embodiment is realized by a processing circuit. The processing circuit may be dedicated hardware, or may be a processing unit that executes a program stored in a storage device.

[0120] When the processing circuit is dedicated hardware, the processing circuit may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an application specific integrated circuit, a field programmable gate array, or a combination thereof. Figure 12 is a diagram showing a configuration in which the functions of the control unit 80 according to the first embodiment are realized by hardware. The processing circuit 81 incorporates a logic circuit 81a that realizes the functions of the control unit 80.

[0121] When the processing circuit 81 is a processing device, the functions of the control unit 80 are realized by software, firmware, or a combination of software and firmware.

[0122] FIG. 13 is a diagram illustrating a configuration in which the functions of the control unit 80 according to the first embodiment are implemented by software. The processing circuit 81 includes a processor 811 that executes a program 81b, a random access memory 812 that the processor 811 uses as a work area, and a storage device 813 that stores the program 81b. The processor 811 deploys the program 81b stored in the storage device 813 on the random access memory 812 and executes it, thereby realizing the functions of the control unit 80. The software or firmware is written in a programming language and stored in the storage device 813. The processor 811 may be, but is not limited to, a central processing unit. The storage device 813 may be a semiconductor memory such as a random access memory (RAM), a read-only memory (ROM), a flash memory, an erasable programmable read-only memory (EPROM), or an electrically erasable programmable read-only memory (EEPROM). The semiconductor memory may be either a non-volatile memory or a volatile memory. In addition to semiconductor memory, a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc) can be used as the storage device 813. The processor 811 may output data such as calculation results to the storage device 813 for storage, or may store the data in an auxiliary storage device (not shown) via the random access memory 812. By integrating the processor 811, the random access memory 812, and the storage device 813 on a single chip, the functions of the control unit 80 can be realized by a microcomputer.

[0123] The processing circuitry 81 reads and executes the program 81b stored in the storage device 813 to realize the functions of the control unit 80. The program 81b can also be said to cause the computer to execute the procedures and methods for realizing the functions of the control unit 80.

[0124] The processing circuit 81 may be configured so that some of the functions of the control unit 80 are realized by dedicated hardware, and some of the functions of the control unit 80 are realized by software or firmware.

[0125] In this way, the processing circuitry 81 can realize each of the above-described functions by hardware, software, firmware, or a combination of these.

[0126] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, and parts of the configurations may be omitted or modified without departing from the spirit of the invention.

[0127] REFERENCE SIGNS LIST 1 Air conditioner, 2 Indoor unit, 3 Outdoor unit, 4 Refrigerant pipe, 5 Remote controller, 21 Indoor unit air conditioning unit, 22 Indoor temperature sensor, 23 Infrared sensor, 24 Indoor unit communication unit, 25 Indoor unit memory unit, 26 Indoor unit control unit, 27 Learning device, 28 Inference device, 31 Outdoor unit air conditioning unit, 32 Outdoor air temperature sensor, 33 Outdoor unit communication unit, 34 Outdoor unit memory unit, 35 Outdoor unit control unit, 40 Compressor, 41 Four-way valve, 42 Outdoor unit heat exchanger, 43 Expansion valve, 44 Indoor unit heat exchanger, 45 Indoor unit fan, 46 Outdoor unit fan, 51 Remote controller operation unit, 52 Remote controller display unit, 53 Remote controller memory unit, 54 Remote controller communication unit, 55 Remote controller control unit, 80 Control unit, 81 Processing circuit, 81a Logic circuit, 81b Program, 100 Air conditioning system, 110 Server, 111 Server communication unit, 112 Server storage unit, 113 Server control unit, 120 External terminal, 121 Terminal operation unit, 122 Position detection unit, 123 Sensible temperature detection unit, 124 Terminal display unit, 125 Terminal storage unit, 126 Terminal communication unit, 127 Terminal control unit, 130 Internet, 261 Operation control unit, 262 Machine learning device, 271, 281 Data acquisition unit, 272 Model generation unit, 273 Reward calculation unit, 274 Function update unit, 275 Learned model storage unit, 276 Learned model, 282 Inference unit, 283 Operation parameter inference result, 451 Indoor unit propeller, 452 Indoor unit fan motor, 461 Outdoor unit propeller, 462 Outdoor unit fan motor, 811 Processor, 812 Random access memory, 813 Storage device, 2731 threshold.

Claims

1. An air conditioner that conditions the air of a room, comprising: an indoor unit placed inside the room, which is the space to be air-conditioned; an outdoor unit placed outside the room and capable of communicating with the indoor unit; and an air conditioning control unit that controls the operation of the indoor unit and the outdoor unit, wherein the air conditioning control unit infers operating parameter values ​​of components included in the outdoor unit of the refrigeration cycle provided in the air conditioner from environmental information that is information about the environment surrounding the outdoor unit and information about the room's set temperature in the air conditioner, and controls the outdoor unit using the inferred operating parameter values.

2. The air conditioner according to claim 1, wherein the environmental information is at least one of an outside air temperature and a weather forecast for the area in which the air conditioner is installed.

3. The air conditioner according to claim 1 or 2, wherein the outdoor unit comprises, as components of the refrigeration cycle provided in the air conditioner, a compressor that compresses the refrigerant flowing through the refrigeration cycle, an outdoor unit heat exchanger that exchanges heat between outdoor air and the refrigerant, an expansion valve that adjusts the flow rate of the refrigerant flowing through the refrigeration cycle, and an outdoor unit fan that generates an airflow that passes through the outdoor unit heat exchanger, and the operating parameter value is at least one of the rotation speed of the compressor, the opening of the expansion valve, and the rotation speed of the outdoor unit fan.

4. An air conditioner as described in any one of claims 1 to 3, wherein the air conditioning control unit has a learning device comprising: a data acquisition unit that acquires learning data including the environmental information, information on the room set temperature, and information on the operating parameter values; and a model generation unit that uses the learning data to generate a trained model for inferring information on the operating parameter values ​​from the environmental information and information on the room set temperature.

5. The air conditioner of claim 4, wherein the model generation unit comprises: a reward calculation unit that calculates a reward for the operation parameter value based on the environmental information, the room set temperature information, and the operation parameter value information, using a reduction in power consumption by the outdoor unit as a reward standard; and a function update unit that updates a function for determining the operation parameter value based on the reward.

6. An air conditioner as described in any one of claims 1 to 5, wherein the air conditioning control unit has an inference device comprising: a data acquisition unit that acquires the environmental information and information on the room set temperature; and an inference unit that uses a trained model to infer information on the operating parameter value that reduces the power consumption of the outdoor unit from the environmental information and information on the room set temperature, and outputs the operating parameter value corresponding to the environmental information and information on the room set temperature.

7. An air conditioner as described in any one of claims 1 to 3, wherein the air conditioning control unit has a learning device comprising: a data acquisition unit that acquires learning data including the environmental information, information on the room set temperature, information on the current location of a user of the air conditioner, and information on the operating parameter values; and a model generation unit that uses the learning data to generate a trained model for inferring information on the operating parameter values ​​from the environmental information, information on the room set temperature, and information on the user's current location.

8. An air conditioner as described in any one of claims 1 to 3, wherein the air conditioning control unit has a learning device comprising: a data acquisition unit that acquires learning data including the environmental information, information on the room set temperature, information on the temperature perceived by the user of the air conditioner, and information on the operating parameter values; and a model generation unit that uses the learning data to generate a trained model for inferring information on the operating parameter values ​​from the environmental information, information on the room set temperature, and information on the temperature perceived by the user.

9. An air conditioning system comprising: an air conditioner according to any one of claims 1 to 3; and a server capable of communicating with the air conditioner and transmitting the environmental information to the air conditioning control unit.

Images