JP2024000742A - Simulation device, simulation method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce the calculation quantity of a coordination simulation that coordinates an air conditioning simulation with a space simulation.

SOLUTION: A control unit of a simulation device executes a coordination simulation that coordinates an air conditioning simulation which simulates the operation of an air conditioner with a space simulation which simulates the state of a space, and executes the air conditioning simulation or the space simulation through a learning model.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2024,JPO&INPIT

Description

The present disclosure relates to a simulation device, a simulation method, and a program.

In order to evaluate the control performance of air conditioners, air conditioning simulations that simulate the operation of air conditioners are used. In air conditioning simulation, the control performance that can be evaluated by itself is limited to control performance in a steady state. Therefore, air conditioning simulation and spatial simulation that simulates the state of the space are linked to evaluate the control performance of the air conditioner in an unsteady state.

For example, Non-Patent Document 1 discloses a simulator that couples an air conditioning equipment simulator that implements air conditioning control logic with computational fluid dynamics (CFD) analysis that analyzes indoor airflow distribution and temperature distribution. There is.

Yukako Saikazu, Kazuya Harayama, Mitsuhiro Honda, Hiroshi Murata, Nagao Aida, "Research on energy saving and comfort during local air conditioning control operation: (1st report) Unsteady formation simulator of air conditioning equipment and air conditioned space" "Development", Proceedings of the Society of Air Conditioning and Sanitary Engineers Conference, 2011.1(0), pp. 117-120, 2011

However, since conventional air conditioning simulations and spatial simulations require a large amount of calculation, a cooperative simulation that links these requires an enormous amount of calculation.

The present disclosure reduces the amount of calculation of a cooperative simulation that cooperates with an air conditioning simulation and a space simulation.

A simulation device according to a first aspect of the present disclosure is a simulation device having a control unit, wherein the control unit cooperates with an air conditioning simulation that simulates the operation of an air conditioner and a space simulation that simulates the state of the space. The air conditioning simulation or the space simulation is performed using a learning model.

According to the first aspect of the present disclosure, it is possible to reduce the amount of calculation of a cooperative simulation in which an air conditioning simulation and a space simulation are cooperated.

A second aspect of the present disclosure is the simulation device according to the first aspect, wherein the control unit performs the air conditioning simulation using the learning model, and the air conditioning simulation outputs an internal state of the air conditioner. do.

A third aspect of the present disclosure is a simulation device according to the second aspect, in which the internal state includes refrigerant temperature, pressure, or control state inside the air conditioner.

A fourth aspect of the present disclosure is a simulation apparatus according to the second aspect or the third aspect, in which the air conditioning simulation uses the set temperature of the air conditioner and the indoor temperature of the space as input, and The outlet temperature, outlet air volume, internal state, and power consumption of the conditioner are output.

A fifth aspect of the present disclosure is a simulation device according to any one of the first to fourth aspects, wherein the control unit performs the spatial simulation using the learning model, and the spatial simulation The amount of load on the space is used as input, and the indoor temperature of the space is used as output.

A sixth aspect of the present disclosure is the simulation device according to the fifth aspect, wherein the load amount includes a blowout temperature and a blowout air volume of the air conditioner, an intrusion heat load from the outside of the space, and an internal load. including.

A seventh aspect of the present disclosure is a simulation device according to any one of the first to sixth aspects, wherein the space simulation includes a temperature of the air outlet of the air conditioner and a blowout temperature of the air conditioner outputted by the air conditioning simulation. The air flow rate is input, and the air conditioning simulation uses the indoor temperature of the space outputted by the space simulation as input.

An eighth aspect of the present disclosure is a simulation device according to any one of the first to seventh aspects, wherein the cooperative simulation inputs a load amount to the space and a set temperature of the air conditioner. shall be.

A ninth aspect of the present disclosure is a simulation apparatus according to the eighth aspect, in which the cooperative simulation outputs the operating efficiency of the air conditioner.

A tenth aspect of the present disclosure is the simulation apparatus according to the ninth aspect, wherein the cooperative simulation includes the refrigerant temperature inside the air conditioner, the control state, power consumption, the blowout temperature, and the blowout air volume. Either the indoor temperature of the space or the indoor airflow is further output.

An eleventh aspect of the present disclosure is a simulation device according to any one of the second to tenth aspects, wherein the control unit executes the air conditioning simulation of the physical model, and configures the air conditioner. Temperature and the indoor temperature of the space are used as input data, and learning data is generated that uses the air conditioner's outlet temperature, outlet air volume, internal state, and power consumption as output data, and the learning data is used to perform the air conditioning simulation. Learn the learning model.

A twelfth aspect of the present disclosure is a simulation device according to any one of the fifth to eleventh aspects, wherein the control unit executes a three-dimensional thermal fluid analysis, and determines the amount of load on the space; Learning data is generated in which the air temperature and air volume of the air conditioner are used as input data, and the indoor temperature of the space is used as output data, and the learning model of the space simulation is learned using the learning data.

A simulation method according to a thirteenth aspect of the present disclosure includes a procedure in which a control unit included in a simulation device performs a cooperative simulation in which an air conditioning simulation that simulates the operation of an air conditioner and a spatial simulation that simulates the state of the space are linked. The air conditioning simulation or the space simulation is performed using a learning model.

A program according to a fourteenth aspect of the present disclosure causes a control unit included in a simulation device to execute a procedure for performing a cooperative simulation in which an air conditioning simulation that simulates the operation of an air conditioner and a spatial simulation that simulates the state of the space are linked. The air conditioning simulation or the space simulation is performed using a learning model.

FIG. 2 is a block diagram showing an example of the overall configuration of a cooperative simulation. FIG. 2 is a block diagram showing an example of a hardware configuration of a simulation device. 3 is a flowchart illustrating an example of a processing procedure of a simulation method.

Each embodiment will be described below with reference to the accompanying drawings. Note that, in this specification and the drawings, components having substantially the same functional configuration are designated by the same reference numerals, thereby omitting redundant explanation.

[Embodiment]
An embodiment of the present disclosure is a simulation device that performs a cooperative simulation that combines an air conditioning simulation and a space simulation. Air conditioning simulation simulates the operation of an air conditioner. The space simulation simulates the state of a space where air conditioning is performed by an air conditioner.

The air conditioner targeted for air conditioning simulation is, for example, a room air conditioner or a multi-air conditioner. However, the type of air conditioner is not limited, and any type of air conditioning device may be used.

The space targeted for spatial simulation is, for example, a house, a living room, an office, or the like. However, the type of space is not limited, and any space may be used as long as the air is conditioned by an air conditioner.

In the cooperative simulation, the simulation results output from the air conditioning simulation are input into the spatial simulation, and the simulation results output from the spatial simulation are input into the air conditioning simulation. By performing the cooperative simulation, it is possible to simultaneously simulate the influence that the operation of the air conditioner has on the state of the space and the influence that the state of the space has on the operation of the air conditioner.

In particular, by linking the air conditioning simulation and the space simulation, it is possible to simulate the operation of the air conditioner not only in a steady state but also in unsteady states such as startup, start/stop, and transient states. As a result, highly accurate simulation results can be obtained.

The simulation device in this embodiment performs space simulation or air conditioning simulation using a learning model. Conventional air conditioning simulations are performed using, for example, physical models. Conventional spatial simulation is performed, for example, by three-dimensional thermal fluid analysis. Air conditioning simulations using physical models and spatial simulations using three-dimensional thermal fluid analysis require a large amount of calculation and require high-spec information processing equipment.

When performing an air conditioning simulation using a learning model, the relationship between input data and output data obtained in a conventional spatial simulation is used as learning data, and a learning model is generated by supervised learning. Although collecting learning data requires calculation costs, the amount of calculation required to predict simulation results using a trained learning model can be significantly reduced compared to conventional air conditioning simulations. Similarly, when performing spatial simulation using a learning model, the amount of calculation can be significantly reduced compared to conventional spatial simulation.

Therefore, according to the simulation device in this embodiment, it is possible to reduce the amount of calculation of a cooperative simulation in which an air conditioning simulation and a space simulation are coordinated.

<Overall configuration>
FIG. 1 is a block diagram showing an example of the overall configuration of cooperative simulation in this embodiment.

As shown in FIG. 1, the cooperative simulation 1 in this embodiment is composed of an air conditioning simulation 2 and a space simulation 3. Air conditioning simulation 2 performs air conditioning simulation using air conditioning learning model 4, which is a trained learning model. The spatial simulation 3 performs a spatial simulation using the spatial learning model 5, which is a trained learning model.

Note that at least one of the air conditioning learning model 4 and the space learning model 5 may be used. In other words, only the air conditioning learning model 4 may be used, only the spatial learning model 5 may be used, or both the air conditioning learning model 4 and the spatial learning model 5 may be used.

The cooperative simulation 1 inputs simulation conditions and outputs simulation results. The simulation conditions in this embodiment are the set temperature of the air conditioner and the amount of load on the space. The amount of load on the space is the intrusion heat load from the outside of the space and the internal load. The simulation result in this embodiment is the operating efficiency of the air conditioner. The operating efficiency of the air conditioner is calculated based on the internal state and power consumption of the air conditioner output from the air conditioning simulation 2.

The operating efficiency of an air conditioner is, for example, the coefficient of performance (COP). The coefficient of performance is a value representing the work (heat amount) given to the indoor space with respect to the electric power used to operate the air conditioner. Specifically, the coefficient of performance is a value obtained by dividing the cooling/heating capacity by the consumed energy.

The cooling/heating capacity can be calculated by, for example, the CC (Compressor Curve) method. The CC method is a method of estimating the capacity from the refrigerant circulation amount and the enthalpy difference between the indoor unit inlet and outlet. The refrigerant circulation amount is determined from a predetermined compressor characteristic equation using the evaporation temperature and condensation temperature of the refrigerant. The consumed energy is the sum of the consumed energy calculated from the rotation speed of the compressor and the rotation speed of the outdoor unit fan.

The set temperature of the air conditioner input into the cooperative simulation 1 is input into the air conditioning simulation 2. The amount of load on the space input into the cooperative simulation 1 is input into the space simulation 3.

Air conditioning simulation 2 inputs the set temperature of the air conditioner and the indoor temperature of the space, and outputs the air outlet temperature, outlet air volume, internal state, and power consumption of the air conditioner. The indoor temperature of the space is output from the space simulation 3.

An example of the internal state of the air conditioner is the refrigerant temperature, pressure, or control state inside the air conditioner. The control state of the air conditioner is a control amount of a control device included in the air conditioner. An example of the control state is the rotation speed of a compressor or a fan included in the indoor unit and the outdoor unit.

Space simulation 3 inputs the amount of load on the space and outputs the indoor temperature and indoor airflow of the space. Examples of the amount of load on the space are the blowout temperature and blowout air volume of an air conditioner, as well as the intrusion heat load from the outside of the space and the internal load. The blowout temperature and blowout air volume of the air conditioner are output from air conditioning simulation 2.

The blowout temperature and blowout air volume of the air conditioner output by the air conditioning simulation 2 are input to the space simulation 3 as the amount of load on the space. The indoor temperature of the space output by the space simulation 3 is input to the air conditioning simulation 2.

The simulation results may include any of the refrigerant temperature inside the air conditioner, control state, power consumption, blowout temperature and blowout air volume, and the indoor temperature and indoor airflow of the space. The simulation results are not limited to these, and may include any information as long as it is information obtained from the outputs of the air conditioning simulation 2 and the space simulation 3.

The air conditioning learning model 4 is a machine learning model generated by supervised learning using input data and output data obtained in a conventional air conditioning simulation as learning data. An example of a machine learning model is a decision tree. Another example of a machine learning model is a neural network.

An example of a conventional air conditioning simulation is an air conditioning simulation using a physical model. By running an air conditioning simulation using a physical model, we obtain input data including the set temperature of the air conditioner and the indoor temperature of the space, and output data including the air conditioner's outlet temperature, outlet air volume, internal state, and power consumption. be able to. The air conditioning learning model 4 can be generated by executing a learning algorithm according to the machine learning model using learning data that is a combination of these input data and output data.

The spatial learning model 5 is a machine learning model generated by supervised learning using input data and output data obtained by conventional spatial simulation as learning data. The machine learning model may be similar to the air conditioning learning model 4.

An example of conventional spatial simulation is spatial simulation using three-dimensional thermal fluid analysis. By executing a spatial simulation using three-dimensional thermal fluid analysis, we can obtain input data including the load on the space, air conditioner outlet temperature and outlet air volume, and output data including the indoor temperature and indoor airflow of the space. I can do it. The spatial learning model 5 can be generated by executing a learning algorithm according to the machine learning model using learning data that is a combination of these input data and output data.

The learning data for generating the air conditioning learning model 4 and the space learning model 5 do not have to be obtained by simulation. The learning data may be obtained by accumulating various types of information measured in an actual driving environment. Furthermore, learning data obtained through simulation and learning data obtained in an actual driving environment may be used together.

<Hardware configuration>
FIG. 2 is a block diagram showing an example of the hardware configuration of the simulation device 10 in this embodiment. As shown in FIG. 2, the simulation device 10 includes a processor 101, a memory 102, an auxiliary storage device 103, an operating device 104, a display device 105, a communication device 106, and a drive device 107. Each piece of hardware in the simulation device 10 is interconnected via a bus 108.

The processor 101 includes various calculation devices such as a CPU (Central Processing Unit). The processor 101 reads various programs installed in the auxiliary storage device 103 onto the memory 102 and executes them.

The memory 102 includes main storage devices such as ROM (Read Only Memory) and RAM (Random Access Memory). The processor 101 and the memory 102 form a so-called computer (hereinafter also referred to as a "control unit"), and when the processor 101 executes various programs read onto the memory 102, the computer realizes various functions. .

The auxiliary storage device 103 (hereinafter also referred to as “storage unit”) stores various programs and various data used when the various programs are executed by the processor 101.

The operating device 104 is an operating device for the user of the simulation device 10 to perform various operations. The display device 105 is a display device that displays the results of various processes executed by the simulation device 10.

The communication device 106 is a communication device for communicating with an external device via a network (not shown).

The drive device 107 is a device for setting the storage medium 109. The storage medium 109 here includes a medium that stores information optically, electrically, or magnetically, such as a CD-ROM, a flexible disk, or a magneto-optical disk. Further, the storage medium 109 may include a semiconductor memory that electrically stores information, such as a ROM or a flash memory.

The various programs installed in the auxiliary storage device 103 are installed by, for example, setting the distributed storage medium 109 in the drive device 107 and reading out the various programs stored in the storage medium 109 by the drive device 107. Ru. Alternatively, various programs installed in the auxiliary storage device 103 may be installed by being downloaded from a network via the communication device 106.

<Processing procedure>
FIG. 3 is a flowchart illustrating an example of a processing procedure of a simulation method executed by the simulation apparatus 10 in this embodiment.

In step S1, the control unit of the simulation device 10 generates learning data for generating the air conditioning learning model 4. The learning data is generated by air conditioning simulation using a physical model.

Specifically, the control unit of the simulation device 10 generates a plurality of input data for the air conditioning learning model 4. The input data includes, for example, the set temperature of the air conditioner and the indoor temperature of the space. Next, the control unit of the simulation device 10 performs an air conditioning simulation using the physical model for each input data. As a result, output data corresponding to each input data is obtained. The output data includes, for example, the air temperature, air volume, internal state, and power consumption of the air conditioner.

The control unit of the simulation device 10 generates learning data for the air conditioning learning model 4 by combining each input data and the output data obtained for the input data. The number of learning data may be any amount sufficient to generate the air conditioning learning model 4. The amount sufficient to generate the air conditioning learning model 4 varies depending on the type of machine learning model and learning algorithm.

In step S2, the control unit of the simulation device 10 generates the air conditioning learning model 4 using the learning data of the air conditioning learning model 4 generated in step S1. The air conditioning learning model 4 is generated using a learning algorithm according to the type of machine learning model that implements the air conditioning learning model 4. The control unit of the simulation device 10 stores the trained air conditioning learning model 4 in the storage unit.

Note that if the air conditioning simulation is not performed using the learning model (in other words, when only the spatial simulation is performed using the learning model), steps S1 and S2 may not be performed.

In step S3, the control unit of the simulation device 10 generates learning data for generating the spatial learning model 5. The learning data is generated by spatial simulation using three-dimensional thermal fluid analysis.

Specifically, the control unit of the simulation device 10 generates a plurality of input data for the spatial learning model 5. The input data includes, for example, the amount of load on the space, the outlet temperature of the air conditioner, and the outlet air volume. Next, the control unit of the simulation device 10 performs a spatial simulation using three-dimensional thermal fluid analysis for each input data. As a result, output data corresponding to each input data is obtained. The output data includes, for example, the indoor temperature and indoor airflow of the space.

The control unit of the simulation device 10 generates learning data for the spatial learning model 5 by combining each input data and the output data obtained for the input data. The number of learning data may be any amount sufficient to generate the spatial learning model 5. The amount sufficient to generate the spatial learning model 5 varies depending on the type of machine learning model and learning algorithm.

In step S4, the control unit of the simulation device 10 generates the spatial learning model 5 using the learning data of the spatial learning model 5 generated in step S3. The spatial learning model 5 is generated using a learning algorithm according to the type of machine learning model implementing the spatial learning model 5. The control unit of the simulation device 10 stores the learned spatial learning model 5 in the storage unit.

Note that if the space simulation is not performed using the learning model (in other words, when only the air conditioning simulation is performed using the learning model), steps S3 and S4 may not be performed.

In step S5, the control unit of the simulation device 10 receives input of simulation conditions. The simulation conditions include, for example, the set temperature of the air conditioner and the amount of load on the space. The amount of load on the space includes, for example, an intrusion heat load from the outside of the space and an internal load.

In step S6, the control unit of the simulation device 10 obtains the set temperature of the air conditioner from the simulation conditions input in step S5, and inputs it to the air conditioning simulation 2. Next, the control unit of the simulation device 10 obtains the amount of load on the space from the simulation conditions input in step S5, and inputs it to the space simulation 3. Subsequently, the control unit of the simulation device 10 executes the cooperative simulation 1.

In step S6-1, the control unit of the simulation device 10 reads out the trained air conditioning learning model 4 stored in the storage unit. Next, the control unit of the simulation device 10 executes the air conditioning simulation 2 using the read air conditioning learning model 4.

Air conditioning simulation 2 inputs the set temperature of the air conditioner and the indoor temperature of the space, and outputs the air outlet temperature, outlet air volume, internal state, and power consumption of the air conditioner. The control unit of the simulation device 10 inputs the air temperature and air volume of the air conditioner outputted from the air conditioning simulation 2 into the space simulation 3.

Note that when the air conditioning simulation is not performed using the learning model (in other words, when only the spatial simulation is performed using the learning model), the control unit of the simulation device 10 performs the air conditioning simulation using the physical model.

In step S6-2, the control unit of the simulation device 10 reads out the trained spatial learning model 5 stored in the storage unit. Next, the control unit of the simulation device 10 executes the spatial simulation 3 using the read spatial learning model 5.

Space simulation 3 inputs the amount of load on the space and outputs the indoor temperature and indoor airflow of the space. The amount of load on the space includes the intrusion heat load from the outside of the space and the internal load that were input to the cooperative simulation 1, and the air temperature and air volume of the air conditioner that were output from the air conditioning simulation 2. The control unit of the simulation device 10 inputs the indoor temperature of the space output from the space simulation 3 to the air conditioning simulation 2.

Note that when the spatial simulation is not performed using the learning model (in other words, when only the air conditioning simulation is performed using the learning model), the control unit of the simulation device 10 performs the spatial simulation using three-dimensional thermal fluid analysis.

In step S7, the control unit of the simulation device 10 calculates the operating efficiency of the air conditioner based on the internal state and power consumption of the air conditioner output from the air conditioning simulation 2. Next, the control unit of the simulation device 10 outputs simulation results including the operating efficiency of the air conditioner.

The control unit of the simulation device 10 may include in the simulation results any of the refrigerant temperature, control state, power consumption, blowout temperature and blowout air volume of the air conditioner, and the indoor temperature and indoor airflow of the space. The control unit of the simulation device 10 may include other information obtained from the outputs of the air conditioning simulation 2 and the space simulation 3 in the simulation results.

The control unit of the simulation device 10 repeatedly executes steps S6-1, S6-2, and S7. The control unit of the simulation device 10 repeatedly executes steps S6-1, S6-2, and S7 until the user performs a stop operation or until a predetermined termination condition is satisfied. The predetermined termination condition is, for example, that the output of the air conditioning simulation 2 or the space simulation 3 converges.

<Summary>
As described above, according to each embodiment of the present disclosure, it is possible to reduce the amount of calculation of a cooperative simulation in which an air conditioning simulation and a space simulation are cooperated. The simulation device 10 in the embodiment performs air conditioning simulation or space simulation using a learning model. The simulation device 10 in the embodiment may perform air conditioning simulation and space simulation using a learning model. By performing an air conditioning simulation or a space simulation using a trained learning model, the amount of calculation can be significantly reduced. Therefore, according to the simulation device 10 in the embodiment, it is possible to reduce the amount of calculation of a cooperative simulation in which an air conditioning simulation and a space simulation are cooperated.

In particular, the simulation device 10 in the embodiment performs an air conditioning simulation that can output the internal state of the air conditioner. In conventional cooperative simulations, the internal state of the air conditioner is not simulated. When the air conditioning simulation outputs the internal state of the air conditioner, for example, the operating efficiency of the air conditioner can be obtained as a simulation result. Therefore, according to the simulation device 10 in the embodiment, it is possible to evaluate the control performance of the air conditioner in an unsteady state in more detail than in the conventional cooperative simulation.

According to each embodiment of the present disclosure, the control performance of the air conditioner in an unsteady state can be evaluated in detail, so it is possible to support the control design of the air conditioner in consideration of control in the actual operating environment. . Furthermore, it can be used to select or propose the most suitable equipment for the air conditioning environment in which the air conditioner is installed.

Although the embodiments have been described above, it will be understood that various changes in form and details can be made without departing from the spirit and scope of the claims.

1 Cooperative simulation 2 Air conditioning simulation 3 Space simulation 4 Air conditioning learning model 5 Space learning model 10 Simulation device

Claims (14)

A simulation device having a control section,
The control unit includes:
We perform a collaborative simulation that combines an air conditioning simulation that simulates the operation of an air conditioner and a spatial simulation that simulates the state of the space.
performing the air conditioning simulation or the space simulation using a learning model;
simulation equipment. The control unit performs the air conditioning simulation using the learning model,
The air conditioning simulation outputs an internal state of the air conditioner.
The simulation device according to claim 1. The internal state includes refrigerant temperature, pressure, or control state inside the air conditioner.
The simulation device according to claim 2. The air conditioning simulation uses the set temperature of the air conditioner and the indoor temperature of the space as input, and outputs the air outlet temperature, outlet air volume, internal state, and power consumption of the air conditioner.
The simulation device according to claim 2. The control unit performs the spatial simulation using the learning model,
The space simulation uses the amount of load on the space as input and the indoor temperature of the space as output.
The simulation device according to claim 1. The load amount includes the blowout temperature and blowout air volume of the air conditioner, as well as the intrusion heat load from the outside of the space and the internal load.
The simulation device according to claim 5. The space simulation takes as input the outlet temperature and outlet air volume of the air conditioner output by the air conditioning simulation,
The air conditioning simulation takes as input the indoor temperature of the space output by the space simulation,
The simulation device according to claim 1. The cooperative simulation inputs the amount of load on the space and the set temperature of the air conditioner.
The simulation device according to claim 1. The cooperative simulation outputs the operating efficiency of the air conditioner.
The simulation device according to claim 8. The cooperative simulation is
further outputting any of the refrigerant temperature, control state, power consumption, outlet temperature and outlet air volume of the air conditioner, and the indoor temperature and indoor airflow of the space;
The simulation device according to claim 9. The control unit includes:
performing the air conditioning simulation of the physical model;
Generating learning data using the set temperature of the air conditioner and the indoor temperature of the space as input data, and using the outlet temperature, outlet air volume, internal state, and power consumption of the air conditioner as output data,
generating the learning model for the air conditioning simulation using the learning data;
The simulation device according to claim 2. The control unit includes:
Perform 3D thermal fluid analysis,
Generating learning data in which the amount of load on the space, the outlet temperature and the outlet air volume of the air conditioner are used as input data, and the indoor temperature of the space is used as output data;
generating the learning model for the spatial simulation using the learning data;
The simulation device according to claim 5. The control unit included in the simulation device is
Execute the steps to perform a cooperative simulation that links an air conditioning simulation that simulates the operation of an air conditioner and a spatial simulation that simulates the state of the space,
performing the air conditioning simulation or the space simulation using a learning model;
Simulation method. In the control section of the simulation device,
Execute a procedure to perform a cooperative simulation that links an air conditioning simulation that simulates the operation of an air conditioner and a spatial simulation that simulates the state of the space,
performing the air conditioning simulation or the space simulation using a learning model;
program.

Images