Control method and control program

Abstract

We provide air conditioning for the target space in accordance with policies regarding user comfort and energy conservation. [Solution] A control method for an air conditioning system that provides air conditioning for a target space, wherein the method accepts a user setting of a target value for the temperature distribution of the target space at a predetermined set time, sets the parameters for the air conditioning settings of the air conditioning system by performing an air conditioning control simulation of the target space, calculates the predicted value of the temperature distribution of the target space and the power consumption of the air conditioning system when the air conditioning system provides air conditioning for the target space based on the set air conditioning settings parameters, and when the user specifies the temperature difference and power consumption, which represent the difference between the calculated predicted value and the target value, the method causes the air conditioning system to provide air conditioning for the target space based on the air conditioning settings parameters set in the air conditioning control simulation.

Description

Technical Field

[0001] The present disclosure relates to a control method and a control program. Background Art

[0002] Patent Document 1 discloses a control device that controls a control target device to be controlled such that a controlled variable, which is a measured value aimed at a target value, reaches the target value at a target time. According to this control device, it is possible to prevent energy loss caused by the controlled variable reaching the target value earlier than the target time. Prior Art Documents Patent Documents

[0003] Patent Document 1 Japanese Patent No. 7446546 Summary of the Invention Problems to be Solved by the Invention

[0004] Conventionally, the operation management of an air conditioning system that performs air conditioning for a target space such as a facility may be uniformly performed for a plurality of target spaces based on, for example, general-purpose comfort indicators and the like. Such uniform operation management can, for example, facilitate the operation of the air conditioning system suitable for energy saving. On the other hand, for example, policies for energy saving may differ between regions with cold climates and regions with warm climates, and even at the same temperature, people's perception of heat / cold may differ depending on the region. Therefore, with the uniform operation management of the air conditioning system as described above, it is difficult to achieve both ensuring comfort and energy saving in each of the plurality of target spaces.

[0005] The present disclosure has been devised in view of the above-described conventional situation, and an object thereof is to perform air conditioning of a target space in line with a user's policies for comfort and energy saving. Means for Solving the Problems

[0006] This disclosure provides a control method for an air conditioning system that provides air conditioning for a target space, comprising: receiving a user setting of a target value for the temperature distribution of the target space at a predetermined set time; setting parameters for the air conditioning settings of the air conditioning system by performing an air conditioning control simulation of the target space; calculating a predicted value for the temperature distribution of the target space and the power consumption of the air conditioning system when the air conditioning system provides air conditioning for the target space based on the set parameters for the air conditioning settings; and, upon receiving the user's specification for the temperature difference showing the difference between the calculated predicted value and the target value and the power consumption, causing the air conditioning system to provide air conditioning for the target space based on the parameters for the air conditioning settings set in the air conditioning control simulation.

[0007] Furthermore, this disclosure provides a control program for causing a computing device to control an air conditioning device that provides air conditioning for a target space, the program causing the computing device to perform the following actions: accept a user setting of a target value for the temperature distribution of the target space at a predetermined set time; set parameters for the air conditioning settings of the air conditioning device by performing an air conditioning control simulation of the target space; calculate a predicted value for the temperature distribution of the target space at the predetermined set time and the power consumption of the air conditioning device when the air conditioning device provides air conditioning for the target space based on the set parameters for the air conditioning settings; and, upon receiving the user's specification for the temperature difference showing the difference between the calculated predicted value and the target value and the power consumption, cause the air conditioning device to provide air conditioning for the target space based on the parameters for the air conditioning settings set in the air conditioning control simulation.

[0008] Furthermore, any combination of the above components, as well as any conversion of the expressions of this disclosure between methods, apparatus, systems, storage media, computer programs, etc., are also valid as aspects of this disclosure. [Effects of the Invention]

[0009] According to this disclosure, it is possible to provide air conditioning for the target space in accordance with the user's comfort and energy conservation policies. [Brief explanation of the drawing]

[0010] [Figure 1] Conceptual diagram illustrating the control flow of the air conditioning system according to this embodiment. [Figure 2] Table diagram illustrating various information related to this embodiment [Figure 3] Block diagram showing an example configuration of the control system according to this embodiment. [Figure 4] A flowchart showing a first example of the control processing of an air conditioning system by the computing device according to this embodiment. [Figure 5] A flowchart showing a second example of the control processing of an air conditioning system by the computing device according to this embodiment. [Figure 6] A flowchart showing a first example of the processing of an air conditioning control simulation by the computing device according to this embodiment. [Figure 7] A schematic diagram illustrating the search for air conditioning setting parameters in the air conditioning control simulation according to this embodiment. [Figure 8] A flowchart showing a second example of the processing of an air conditioning control simulation by the computing device according to this embodiment. [Figure 9] Schematic diagram illustrating the automatic control of an air conditioning system by the computing device according to this embodiment. [Modes for carrying out the invention]

[0011] The following description will detail embodiments specifically disclosing the control method and control program according to this disclosure, with appropriate reference to the drawings. However, unnecessarily detailed explanations may be omitted. For example, detailed explanations of already well-known matters and redundant explanations of substantially identical configurations may be omitted. This is to avoid the following explanation becoming unnecessarily verbose and to facilitate understanding by those skilled in the art. The accompanying drawings and the following description are provided to enable those skilled in the art to fully understand this disclosure and are not intended to limit the subject matter of the claims. Furthermore, in this specification, terms such as "first" and "second" are used merely to distinguish components for the sake of explanation and are not intended to be interpreted as limiting to specific components. Therefore, these expressions should be understood to be appropriately reinterpreted depending on the configuration to which the invention of this disclosure applies.

[0012] (Embodiment) [Overview] First, the overall outline of this embodiment will be described with reference to Figure 1. Figure 1 is a conceptual diagram illustrating the control flow of the air conditioning device 210 (see Figure 3) according to this embodiment. The air conditioning device 210 is installed in the target space 200 (see Figure 3) and performs air conditioning of the target space 200. Hereinafter, air conditioning may be referred to as "air conditioning". In this embodiment, the computing device 100 (see Figure 3) causes the air conditioning device 210 to perform air conditioning of the target space 200.

[0013] First, the computing device 100 acquires the measured temperature at the locations where the temperature sensors 220 are installed in the target space 200, which are measured by the temperature sensors 220 installed in the target space 200. The computing device 100 may acquire the measured temperature in real time. In other words, the computing device 100 can acquire the measured temperature at the current time. In the example in Figure 1, this measured temperature is the measured temperature at time t.

[0014] Arithmetic device 100 calculates a temperature distribution D0 of target space 200 based on the acquired measured temperatures. Here, the arithmetic device 100 may calculate the temperature distribution from the measured temperatures using a known simulation technique or a known Artificial Intelligence (hereinafter referred to as "AI") technique. The temperature distribution D0 is the so-called current value of the temperature distribution, which is calculated from the measured temperatures at time t that is the current time.

[0015] The arithmetic device 100 presents the calculated temperature distribution D0 and reference information described later with reference to Figure 2 to user U1. In the present embodiment, it is assumed that the user U1 is an administrator of the target space 200. For example, the target space 200 may be a store such as a convenience store. The user U1 may be the store manager of the relevant store, or an administrator who manages a plurality of stores including the relevant store. The reference information includes various types of information for the user U1 to refer to, in order to set a target value for the temperature distribution of the target space 200. The arithmetic device 100 may present the temperature distribution D0 and the reference information to the user U1 by displaying them on a display device 105 (see Figure 3).

[0016] The user U1 refers to the temperature distribution D0 and the reference information, and sets a temperature distribution D1 in the arithmetic device 100. The temperature distribution D1 is a desired temperature distribution of the user U1 at a predetermined set time of the target space 200, and is the so-called target value of the temperature distribution.

[0017] After the user U1 sets the temperature distribution D1, the arithmetic device 100 executes a series of processes for air conditioning control simulation. First, the arithmetic device 100 searches for and sets parameters for air conditioning settings. The air conditioning settings are settings for the air conditioner 210 to perform air conditioning, and include parameters that respectively determine air volume, temperature, and air direction as data. The arithmetic device 100 may use a known simulation technique to search for the parameters of the air conditioning settings. A specific example will be described later with reference to FIG. 7. Alternatively, the arithmetic device 100 may use a learned inverse estimation AI model M2, which will be described later, to search for the parameters of the air conditioning settings. The inverse estimation AI model M2 is trained to be capable of calculating the parameters of the air conditioning settings. Hereinafter, the inverse estimation AI model may be referred to as the second AI model in some cases.

[0018] In the example of FIG. 1, the arithmetic device 100 searches for and sets a plurality of parameters for air conditioning settings. That is, the arithmetic device 100 searches for and sets a plurality of patterns of combinations of air volume, temperature, and air direction when the air conditioner 210 performs air conditioning. In the example of FIG. 1, the arithmetic device 100 is assumed to set each of air conditioning setting α, air conditioning setting β, and air conditioning setting γ.

[0019] The arithmetic device 100 inputs the temperature distribution D0 and the set parameters of the air conditioning settings into the learned forward estimation AI model M1. The forward estimation AI model M1 is trained to be capable of calculating the temperature distribution at a predetermined set time when the air conditioner 210 performs air conditioning on the target space 200 based on the input parameters of the air conditioning settings. Here, the predetermined set time is a time that is a predetermined time after the temperature distribution at the input predetermined time. For example, the forward estimation AI model M1 may be trained to be capable of calculating the temperature distribution one hour after the time corresponding to the input temperature distribution (time t in the case of the temperature distribution D0). Hereinafter, the forward estimation AI model may be referred to as the first AI model in some cases.

[0020] Furthermore, when user U1 sets a target value for the temperature distribution at a predetermined time, it is desirable to take into account the time corresponding to the temperature distribution calculated by the forward estimation AI model M1. For example, if the forward estimation AI model M1 calculates the temperature distribution one hour after the time corresponding to the input temperature distribution (in the case of temperature distribution D0, time t), it is desirable for user U1 to set a target value for the temperature distribution one hour after time t. This makes it possible to compare the temperature distribution calculated by the forward estimation AI model M1 with the temperature distribution set by user U1 at the same time.

[0021] The forward estimation AI model M1 calculates the temperature distribution Dα based on the input parameters of temperature distribution D0 and air conditioning setting α. The forward estimation AI model M1 also calculates the temperature distribution Dβ based on the input parameters of temperature distribution D0 and air conditioning setting β. Furthermore, the forward estimation AI model M1 calculates the temperature distribution Dγ based on the input parameters of temperature distribution D0 and air conditioning setting γ. Temperature distribution Dα is a predicted value of the temperature distribution in the target space 200 at a predetermined set time, assuming that the air conditioning system 210 performs air conditioning on the target space 200 based on the parameters of air conditioning setting α. The explanations for temperature distribution Dβ and temperature distribution Dγ are the same as for temperature distribution Dα and are therefore omitted.

[0022] Furthermore, the calculation unit 100 calculates the power consumption of the air conditioning unit 210 when it performs air conditioning on the target space 200, based on the respective parameters of air conditioning setting α, air conditioning setting β, and air conditioning setting γ.

[0023] The calculation unit 100 presents the user U1 with multiple combinations of the calculated temperature distribution and power consumption. The calculation unit 100 may also display these multiple combinations of temperature distribution and power consumption on the display device 105 (see Figure 3).

[0024] User U1 reviews the multiple combinations of temperature distribution and power consumption presented and specifies the desired combination. In other words, User U1 specifies the air conditioning setting corresponding to the desired combination of temperature distribution and power consumption. User U1 may specify the air conditioning setting via the input device 104 (see Figure 3). For example, User U1 may determine that among temperature distributions Dα, Dβ, and Dγ, temperature distribution Dα is the closest to the target temperature distribution D1 and specify air conditioning setting α. Here, the calculation device 100 may calculate the difference between the predicted value and the target value of the temperature distribution to support User U1's decision and present the temperature difference showing this difference to User U1. This makes it easy for User U1 to determine the air conditioning setting to specify.

[0025] The computing unit 100 controls the air conditioning unit 210 based on the air conditioning settings specified by user U1. As a result, the air conditioning unit 210 provides air conditioning to the target space 200 based on the air conditioning settings specified by user U1. The air conditioning settings used by the air conditioning unit 210 may be included in the reference information as air conditioning control information (see Figure 2).

[0026] The calculation unit acquires the measured temperature at time t+Δt. Then, the series of processes described above is repeated. In this way, the air conditioning of the target space 200 is performed in accordance with user U1's policies regarding comfort and energy saving. User U1's policies regarding comfort may include user U1's preferences regarding the appropriate room temperature, etc., of the target space 200. User U1's policies regarding energy saving may include user U1's preferences regarding the permissible upper limit of power consumption in the target space 200 or of the air conditioning system 210, etc.

[0027] Next, with reference to Figure 2, various types of information, such as the reference information mentioned above, will be explained. Figure 2 is a table diagram for explaining the various types of information related to this embodiment. The various types of information shown in Figure 2 may be stored and held in the memory 102 of the arithmetic unit 100 (see Figure 3), or they may be stored and held in an external server (not shown) capable of data communication with the arithmetic unit 100.

[0028] The reference information presented to user U1 includes indicator information and environmental information. The indicator information includes, as data, the temperature distribution of the target space 200 and the power consumption of the air conditioning unit 210. The power consumption data included in the indicator information may include the total power consumption of the target space 200. This is because the target space 200 may have other power-consuming equipment besides the air conditioning unit 210, and user U1 may want to check the total power consumption of each piece of equipment installed in the target space 200.

[0029] The indicator information includes past temperature distributions and past power consumption. For example, the indicator information may include the temperature distribution at any given time yesterday, the power consumption on this day last year, the power consumption up to the present day, and the temperature distribution at any given time up to the present day.

[0030] Environmental information includes data such as outside temperature, solar radiation, the number of people in the target space 200, and their staffing arrangement. Similar to indicator information, environmental information may also include historical data. For example, environmental information may include the outside temperature up to the current time today, yesterday's solar radiation, and the number of people in the target space 200 at any given time yesterday.

[0031] User U1 can set a target value for the temperature distribution by referring to the reference information, which includes the aforementioned indicator information and environmental information, as well as the current temperature distribution value.

[0032] The reference information may also include air conditioning control information. The air conditioning control information includes, as data, the parameters for the air conditioning settings of the air conditioning unit 210. In other words, the air conditioning control information includes the parameters that determine the airflow rate, temperature, and airflow direction when the air conditioning unit 210 has performed air conditioning in the past. Whether or not the reference information includes air conditioning control information may be set in advance by, for example, user U1. If the reference information includes air conditioning control information, user U1 can refer to the air conditioning control information when setting the target value for the temperature distribution.

[0033] Indicator information and environmental information may be updated at predetermined time intervals set by, for example, user U1. Air conditioning control information may be updated when the air conditioning system 210 changes the air conditioning settings, that is, when air conditioning is performed with predetermined air conditioning settings.

[0034] Furthermore, indicator information, environmental information, and air conditioning control information are treated collectively as related information. This related information is recorded in the related information database DB1 (see Figure 9). The related information database DB1 may be stored and maintained, for example, in the memory 102 of the computing unit 100, or in an external server (not shown) capable of data communication with the computing unit 100. The related information database DB1 will be described later with reference to Figure 9.

[0035] [System Configuration] Figure 3 is a block diagram showing an example configuration of the control system 50 according to this embodiment. The control system 50 includes an air conditioner 210, a temperature sensor 220, and a computing device 100. The air conditioner 210 and the temperature sensor 220 are installed in the target space 200 and are connected to the computing device 100 via a network 108 for data communication. The computing device 100 may be installed outside the target space 200 as in the example in Figure 3, or it may be installed in the target space 200.

[0036] The arithmetic unit 100 is operated by user U1. The arithmetic unit 100 may be a general-purpose computer device such as a Personal Computer (hereinafter referred to as "PC") or a server computer, or it may be a mobile device such as a tablet terminal or a smartphone.

[0037] The arithmetic unit 100 comprises a processor 101, memory 102, communication device 103, input device 104, display device 105, and external interface device 106. Each component is configured to communicate via an internal interface device 107.

[0038] The processor 101 may be configured using, for example, a Central Processing Unit (hereinafter referred to as "CPU"), a Graphical Processing Unit (hereinafter referred to as "GPU"), a Micro Processing Unit (hereinafter referred to as "MPU"), a Digital Signal Processor (hereinafter referred to as "DSP"), or a Field Programmable Gate Array (hereinafter referred to as "FPGA"). The processor 101 realizes various functions by reading and executing various data and programs held in the memory 102.

[0039] Memory 102 is a storage unit for storing various data and programs. Memory 102 may consist of volatile / non-volatile storage devices such as Random Access Memory (hereinafter referred to as "RAM"), Read Only Memory (hereinafter referred to as "ROM"), Hard Disk Drive (hereinafter referred to as "HDD"), and Solid State Drive (hereinafter referred to as "SSD").

[0040] The communication device 103 is an interface for communicating with external devices, etc., via the network 108. The communication standards that the communication device 103 can support are not particularly limited and may support either wired or wireless communication standards. Furthermore, the communication device 103 may support multiple communication standards. Therefore, the network 108 used by the communication device 103 may be configured by combining networks using multiple communication standards.

[0041] The input device 104 accepts, for example, operations and instructions from user U1. The input device 104 may consist of a mouse, keyboard, touch panel display, etc.

[0042] The display device 105 displays various user interfaces to the user U1. The display device 105 may consist of a liquid crystal display, a touch panel display, or the like.

[0043] The external interface device 106 is an interface for sending and receiving data with an external device (not shown).

[0044] [Processing flow] Figure 4 is a flowchart showing a first example of the control process of the air conditioning system 210 by the arithmetic unit 100 according to this embodiment. At the start of the flowchart shown in Figure 4, the arithmetic unit 100 is assumed to be calculating the current value of the temperature distribution of the target space 200 based on the measured temperature obtained from the temperature sensor 220. Furthermore, each process in the flowchart shown in Figure 4 is performed by the processor 101 of the arithmetic unit 100.

[0045] The processor 101 presents the current temperature distribution and reference information of the target space 200 to the user U1 (step St1000). The processor 101 may also present the current temperature distribution and reference information to the user U1 by, for example, displaying it on the display device 105.

[0046] User U1 can use the presented current temperature distribution values ​​and reference information as a reference for setting target values ​​for the temperature distribution.

[0047] The processor 101 accepts a setting by user U1 for a target value of the temperature distribution of the target space 200 at a set time (step St1010). This set time may be, for example, the time of the current temperature distribution, in other words, one hour after the current time.

[0048] The processor 101 calculates multiple parameters for the air conditioning settings through air conditioning control simulation, and based on each of the calculated parameters, it calculates the temperature distribution of the target space 200 and the power consumption of the air conditioning unit 210 at the set time for each of the calculated parameters (step St1020). Details of the processing in step St1020 and step St1020A of the flowchart shown in Figure 5 will be described later with reference to Figures 6, 7, and 8.

[0049] By processing in step St1020, the processor 101 can calculate, for each setting of the air conditioning settings parameters, the predicted temperature distribution of the target space 200 at a predetermined set time, and the power consumption of the air conditioning unit 210, based on the set air conditioning setting parameters.

[0050] Processor 101 presents to user U1 the multiple parameters of the air conditioning settings calculated and set in step St1020, as well as the predicted temperature distribution and power consumption calculated for each setting of the air conditioning setting parameters (step St1030). Here, processor 101 may also calculate the difference between the predicted temperature distribution and the target temperature distribution received in step St1010, and present the temperature difference representing this difference to user U1.

[0051] This allows user U1 to specify one of several combinations of temperature difference (showing the difference between the predicted value and the target value) and power consumption for each of the predicted values ​​of multiple temperature distributions. In other words, user U1 can specify the air conditioning setting parameters corresponding to one of the combinations of temperature difference (showing the difference between the predicted value and the target value) and power consumption for each of the calculated predicted values ​​of multiple temperature distributions.

[0052] The processor 101 accepts user U1's specification for one of the multiple parameters of the air conditioning settings calculated and set in step St1020 (step St1040). User U1 may specify the parameters of the air conditioning settings via the input device 104.

[0053] The processor 101 controls the air conditioning unit 210 based on the air conditioning setting parameters specified by user U1 in step St1040 (step St1050).

[0054] As a result, the air conditioning unit 210 performs air conditioning on the target space 200 based on the air conditioning setting parameters specified by user U1 in step St1040.

[0055] The processor 101 records relevant information in the relevant information database DB1 (step St1060). More specifically, the processor 101 records in the relevant information database DB1 the current value of the temperature distribution calculated at the start of this flowchart, the parameters of the air conditioning settings when the air conditioning unit 210 was made to air condition the target space 200 in step St1050, and the power consumption of the air conditioning unit 210. This updates the indicator information and air conditioning control information recorded in the relevant information database DB1. In other words, new data is added to the indicator information and air conditioning control information recorded in the relevant information database DB1. The processor 101 may further acquire various data included in the environmental information, namely the outside temperature, solar radiation, the number and location of people in the target space 200, and record them in the relevant information database DB1. This updates the environmental information recorded in the relevant information database DB1. In other words, new data is added to the environmental information recorded in the relevant information database DB1.

[0056] The processor 101 determines whether or not to terminate the control processing of the air conditioning system 210 (step St1070). The processor 101 may determine whether or not to terminate the control processing of the air conditioning system 210 based, for example, on the operation of user U1.

[0057] If the processor 101 determines that it does not want to terminate the control process of the air conditioning system 210 (step St1070: NO), it returns to step St1000 and repeats the process.

[0058] If the processor 101 determines that it has finished the control processing of the air conditioning system 210 (step St1070: YES), it terminates this processing flow.

[0059] This allows user U1 to specify parameters from among multiple air conditioning setting parameters calculated by the computing device 100 through air conditioning control simulation that can achieve the desired temperature distribution, power consumption, or both. Then, the computing device 100 can have the air conditioning system 210 perform air conditioning of the target space 200 based on the air conditioning setting parameters specified by user U1.

[0060] In the examples shown in Figures 1 and 4, the computing device 100 presents the user U1 with parameters for multiple air conditioning settings, and the temperature distribution and power consumption calculated for each of the parameters for the multiple air conditioning settings. However, the computing device 100 may also present the user U1 with parameters for a single air conditioning setting, and the temperature distribution and power consumption calculated based on those parameters. Details will be explained with reference to Figure 5. Figure 5 is a flowchart showing a second example of the control process of the air conditioning system 210 by the computing device 100 according to this embodiment. Note that in the explanation of the flowchart shown in Figure 5, parts that overlap with the explanation of the flowchart shown in Figure 4 may be omitted or simplified.

[0061] The processes in steps St1000 and St1010 have been described with reference to Figure 4, so they will be omitted here, and the process will begin with step St1020A. The processor 101 calculates the parameters for a single air conditioning setting through air conditioning control simulation, and based on the calculated single parameters, calculates the temperature distribution of the target space 200 and the power consumption of the air conditioning unit 210 at the set time (step St1020A). Details of the processes in step St1020A and step St1020 in the flowchart shown in Figure 4 above will be described later with reference to Figures 6, 7, and 8.

[0062] By processing in step St1020, the processor 101 can calculate the predicted temperature distribution of the target space 200 at a predetermined set time, and the power consumption of the air conditioner 210, based on the parameters of a single set air conditioning setting.

[0063] The processor 101 presents to user U1 several parameters of the air conditioning settings calculated and set in step St1020A, as well as the predicted temperature distribution and power consumption calculated based on the parameters of the air conditioning settings (step St1030A). Here, the processor 101 may calculate the difference between the predicted temperature distribution and the target temperature distribution received in step St1010, and present the temperature difference showing this difference to user U1.

[0064] This allows user U1 to check the temperature difference and power consumption, which represent the difference between the predicted and target values ​​of the calculated temperature distribution, and specify them if they are satisfied with the results. In other words, user U1 can specify the air conditioning setting parameters corresponding to the temperature difference and power consumption, which represent the difference between the predicted and target values ​​of the calculated temperature distribution.

[0065] The processor 101 determines whether or not it has received a specification from user U1 regarding the air conditioning setting parameters calculated and set in step St1020A (step St1040A). The processor 101 may receive a specification from user U1 regarding the air conditioning setting parameters via the input device 104. The processor 101 may determine that it has not received a specification from user U1 regarding the air conditioning setting parameters if it has not received a specification from user U1 for a predetermined period of time, or it may determine that it has not received a specification from user U1 regarding the air conditioning setting parameters if it has received a predetermined user operation that has been defined in advance.

[0066] If the processor 101 determines that it has not accepted user U1's specification for the air conditioning setting parameters (step St1040A: NO), it returns to step St1010 and repeats the process. This allows user U1 to have the arithmetic unit 100 repeat a series of processes until it can calculate and set the air conditioning setting parameters that can achieve the desired temperature distribution, power consumption, or both, through the air conditioning control simulation.

[0067] If the processor 101 determines that it has received user U1's specification for the air conditioning setting parameters (step St1040A: YES), it proceeds to the next step, St1050. The processing in steps St1050, St1060, and St1070 has been described with reference to Figure 4 and is therefore omitted here.

[0068] Next, referring to Figures 6, 7, and 8, the processing of step St1020 in the flowchart shown in Figure 4 and step St1020A in the flowchart shown in Figure 5 will be explained in detail. Figure 6 is a flowchart showing a first example of the processing of the air conditioning control simulation by the arithmetic unit 100 according to this embodiment.

[0069] Processor 101 searches for parameters for the air conditioning settings and sets them as input parameters for the forward estimation AI model M1 (step St1021). Note that parameter search can be read as parameter calculation. A specific example of searching for parameters for the air conditioning settings will be explained with reference to Figure 7.

[0070] Figure 7 is a schematic diagram illustrating the search for air conditioning setting parameters in the air conditioning control simulation according to this embodiment.

[0071] Figure 7 shows an example of processor 101 searching for air conditioning setting parameters through simulation. Note that the method for searching for air conditioning setting parameters is not limited to the example described with reference to Figure 7; any method may be used.

[0072] The processor 101 searches for the parameters of the air conditioning settings that minimize the power consumption of the air conditioner 210 during the control period described below, through simulation. The control period may be, for example, the period from the time corresponding to the current value of the temperature distribution, i.e., the current time, to the time corresponding to the target value of the temperature distribution set by the user U1, i.e., the set time. Furthermore, the constraints of the simulation may include that the temperature of the target space 200 after controlling the air conditioner 210 based on the temperature of the target space 200 at predetermined time intervals during the control period is within an acceptable range. In the example in Figure 7, the upper and lower limits of the acceptable temperature range are the upper temperature Tu and the lower temperature Tl, respectively. For example, in the simulation, the air conditioner 210 may be controlled so that the temperature after control approaches the target temperature Tc, which is the temperature midway between the upper temperature Tu and the lower temperature Tl.

[0073] In the simulation, the control of the air conditioning system 210 means that the parameters for the air conditioning settings are set. Furthermore, in the simulation, the parameters for the air conditioning settings may be set at least at predetermined time intervals, and control points may be set at predetermined time intervals. For illustrative purposes, in the example in Figure 7, the control points (for example, control point P1, control point P2, control point P3, control point P4, control point P5, control point P6 and control point P7) are represented as points indicating the temperature of the target space 200.

[0074] At the control point, for example, the parameters for the air conditioning settings may be set based on the difference between the temperature of the target space 200 and the target temperature Tc.

[0075] The method for setting the parameters of the air conditioning settings in the simulation, in other words, the method for controlling the air conditioning system 210, may be either a one-stage control or a two-stage control method. In the case of one-stage control, the parameters of the air conditioning settings remain constant between a certain control point and the next control point. For example, the parameters of the air conditioning settings set at control point P1 remain unchanged until the parameters of the air conditioning settings are set at control point P2.

[0076] For the sake of explanation, let's assume that there are five setting patterns for each of the airflow, air direction, and temperature settings in the air conditioning system. In this case, in one-stage control, there are a total of 125 control patterns for the air conditioning unit 210 from one control point to the next. The processor 101 selects one control pattern from these 125 patterns. In other words, the processor 101 sets the parameters of the air conditioning settings. At this time, the processor 101 may select the control pattern that consumes the least power or brings the temperature of the target space 200 closest to the target temperature Tc when the air conditioning unit 210 is controlled using each of the 125 patterns. In other words, the processor 101 may perform a full search of all 125 patterns. Using this one-stage control, the processor 101 may repeatedly set the parameters of the air conditioning settings during the control period.

[0077] Next, two-stage control will be explained. In the case of two-stage control, the control pattern of the air conditioner 210 may be changed once between a given control point and the next control point. As with the explanation of one-stage control above, it is assumed that there are five setting patterns each for airflow, air direction, and temperature among the air conditioning settings. In this case, in two-stage control, there are a total of 15,625 control patterns for the air conditioner 210 from one control point to the next control point. In the explanation of one-stage control above, an example was given in which the processor 101 exhaustively searches all control patterns, but the processor 101 may perform a random search depending on the number of control patterns. The processor 101 may select a control pattern from the 15,625 control patterns by random search. Using such two-stage control, the processor 101 may repeatedly set the parameters of the air conditioning settings during the control period.

[0078] Through one-stage or two-stage control, the parameters of the air conditioning settings are set at least at predetermined time intervals during the control period. In this embodiment, the parameters of the air conditioning settings set at each control point during the control period are collectively referred to as "parameters of a single air conditioning setting." This is because when the air conditioning system 210 is controlled based on the parameters of the air conditioning settings set at each control point during the control period, the temperature of the target space 200 exhibits a single change characteristic (for example, change characteristic C1 shown in Figure 7). In this way, the processor 101 may calculate the "parameters of a single air conditioning setting" by simulation. On the other hand, calculating "parameters of multiple air conditioning settings," as in the example described with reference to Figure 1 or Figure 4, is equivalent to calculating multiple "parameters of a single air conditioning setting" as described above.

[0079] Returning to the explanation of Figure 6, in step St1021, the processor 101 sets the parameters of the single air conditioning setting that it searched for as parameters to be input to the forward estimation AI model M1. Then, the processor 101 inputs the first input data, described later, to the forward estimation AI model M1 and calculates a predicted value of the temperature distribution of the target space 200 after air conditioning control based on the air conditioning setting parameters set in step St1021 (step St1022).

[0080] The first input data includes at least the temperature distribution of the target space 200 at a predetermined time and the parameters of the air conditioning settings of the air conditioning unit 210 set in step St1021. Here, the temperature distribution included in the first input data may be the current value of the temperature distribution. The first input data may further include the outside temperature at the current time, the amount of solar radiation, and the number and arrangement of people in the target space 200.

[0081] The forward estimation AI model M1 is trained to calculate the temperature distribution of the target space 200 at a predetermined set time, in response to the input of the first input data. The learning algorithm for generating the forward estimation AI model M1, the inverse estimation AI model M2 (described later), and the automatic control AI model M3 (see Figure 9) (described later) is not particularly limited, but machine learning including neural network technologies such as Convolutional Neural Network (hereinafter referred to as "CNN") and U-Net, and deep learning technologies may be used.

[0082] For example, the forward estimation AI model M1 may be trained to calculate the temperature distribution one hour later from the input temperature distribution of the target space 200, or it may be trained to calculate the temperature distribution two hours later. Here, it is assumed that the set time corresponding to the target value of the temperature distribution set by user U1 in step St1010 and the time corresponding to the predicted value of the temperature distribution calculated by the forward estimation AI model M1 are the same time.

[0083] After step St1022, the processor 101 calculates the power consumption of the air conditioning unit 210 when the air conditioning is conditioned based on the air conditioning setting parameters set in step St1021 (step St1023). When calculating the power consumption of the air conditioning unit 210, the processor 101 may use known simulation techniques.

[0084] The processor 101 saves the air conditioning setting parameters set in step St1021, the predicted temperature distribution after air conditioning control calculated in step St1022, and the power consumption calculated in step St1023 (step St1024). The processor 101 may also save the air conditioning setting parameters, the predicted temperature distribution, and the power consumption in, for example, memory 102.

[0085] The processor 101 determines whether to terminate the search for the air conditioning setting parameters (step St1025). In other words, the processor 101 determines whether to re-execute the processes from step St1021 to step St1024. For example, the number of times the processes from step St1021 to step St1024 are executed, or the processing time, may be predetermined by user U1, etc. Then, the processor 101 may make the determination in step St1025 based on the number of executions or processing time.

[0086] If processor 101 determines that it has not finished searching for the air conditioning setting parameters (step St1025: NO), it returns to step St1021 and repeats the process.

[0087] For example, if processor 101 proceeds to step St1030 of the flowchart shown in Figure 4 after completing this processing flow, processor 101 repeats the processing from step St1021 to step St1024 multiple times. This is because it is necessary to calculate multiple air conditioning setting parameters. In step St1030, processor 101 presents user U1 with the multiple air conditioning setting parameters saved in step St1024, as well as the predicted temperature distribution values ​​and power consumption calculated for each of the multiple air conditioning setting parameters.

[0088] If the processor 101 determines that it has finished searching for the parameters of the air conditioning settings (step St1025: YES), it terminates this processing flow. If the processor 101 proceeds to step St1030A of the flowchart shown in Figure 5 after terminating this processing flow, and if the processing from step St1021 to step St1024 has been repeated multiple times, the processor 101 performs the following processing: In step St1024, the processor 101 determines, from among the multiple air conditioning setting parameters saved and the predicted temperature distribution values ​​and power consumption calculated for each of the multiple air conditioning setting parameters, the single air conditioning setting parameter to be presented to the user U1 in step St1030A, and the predicted temperature distribution values ​​and power consumption calculated based on that single air conditioning setting parameter. In this case, for example, the system may be configured to present user U1 with the predicted value that has the smallest difference from the target value, along with the parameters and power consumption associated with that predicted value, or it may be configured to present user U1 with the smallest power consumption, along with the parameters and predicted value associated with that power consumption.

[0089] Next, with reference to Figure 8, a second example of the processing of the air conditioning control simulation by the arithmetic unit 100 will be described. Figure 8 is a flowchart showing a second example of the processing of the air conditioning control simulation by the arithmetic unit 100 according to this embodiment.

[0090] Processor 101 calculates multiple parameters for the air conditioning settings by inputting the second input data, described later, into the inverse estimation AI model M2 (step St1026).

[0091] The second input data includes at least the temperature distribution of the target space 200 at a predetermined time and the temperature distribution of the target space 200 at a predetermined set time after the predetermined time. Here, the temperature distribution of the target space 200 at a predetermined time and the temperature distribution of the target space 200 at a predetermined set time after the predetermined time may be the current value of the temperature distribution and the target value of the temperature distribution, respectively. The second input data includes at least the current value of the temperature distribution of the target space 200 and the target value of the temperature distribution of the target space 200. The second input data may further include the outside temperature at the current time, the amount of solar radiation, and the number and arrangement of people in the target space 200.

[0092] The inverse estimation AI model M2 is trained to calculate the parameters of the air conditioning settings of the air conditioning unit 210 in response to the input of the second input data. The inverse estimation AI model M2 may be trained to calculate multiple parameters for the air conditioning settings, or it may be trained to calculate the parameters of a single air conditioning setting. Here, it is assumed that the inverse estimation AI model M2 is trained to calculate multiple parameters for the air conditioning settings.

[0093] The processor 101 sets the parameters of the air conditioning settings for the air conditioning unit 210, calculated by the inverse estimation AI model M2, as parameters of the air conditioning settings for the air conditioning unit 210 to be input to the forward estimation AI model M1.

[0094] In step St1026, for each of the multiple air conditioning setting parameters calculated by the inverse estimation AI model M2, the processor 101 uses the forward estimation AI model M1 to calculate a predicted value of the temperature distribution after air conditioning control based on the air conditioning setting parameters (step St1027).

[0095] The processor 101 calculates the power consumption when the air conditioning unit 210 performs air conditioning control based on the parameters of the air conditioning settings, for each of the multiple air conditioning setting parameters calculated in step St1026 (step St1028).

[0096] The processor 101 saves the air conditioning setting parameters, the predicted temperature distribution calculated in step St1027, and the power consumption calculated in step St1028 for each of the multiple air conditioning setting parameters calculated in step St1026 (step St1029). The processor 101 may save the air conditioning setting parameters, the predicted temperature distribution, and the power consumption to, for example, memory 102. Then, the processor 101 terminates this processing flow.

[0097] If processor 101 proceeds to step St1030A of the flowchart shown in Figure 5 after completing this processing flow, processor 101 performs the following processing: Specifically, from the multiple air conditioning setting parameters saved in step St1029 and the predicted temperature distribution values ​​and power consumption calculated for each of the multiple air conditioning setting parameters, processor 101 determines the parameters of a single air conditioning setting to be presented to user U1 in step St1030A, and the predicted temperature distribution values ​​and power consumption calculated based on the parameters of that single air conditioning setting.

[0098] [Automatic control] Figure 9 is a schematic diagram illustrating the automatic control of the air conditioning system 210 by the computing device 100 according to this embodiment.

[0099] As each process in the flowchart shown in Figure 4 or Figure 5 is repeated, related information is accumulated in the related information database DB1. The processor 101 of the arithmetic unit 100 generates a trained automatic control AI model M3 based on the related information database DB1. Hereinafter, the automatic control AI model M3 may be referred to as the third AI model.

[0100] The automatic control AI model M3 is trained to calculate the parameters for the air conditioning settings of the air conditioning unit 210 in response to the input of the third input data described later. Relevant information may be used as training data for training the automatic control AI model M3.

[0101] The third input data includes the temperature distribution of the target space 200, the power consumption of the air conditioning unit 210 over a predetermined period, the outside temperature, and the amount of solar radiation. The third input data may further include the number and arrangement of people in the target space 200.

[0102] For example, the automatic control AI model M3 can calculate the parameters for the air conditioning settings that the air conditioner 210 should use when air conditioning the target space 200, based on inputs such as the current temperature distribution of the target space 200, the power consumption of the air conditioner 210 so far today, and the outside temperature and solar radiation at the current time. When the air conditioner 210 performs air conditioning based on the calculated parameters, the air conditioning will be in line with user U1's policies regarding comfort and energy saving. This is because the automatic control AI model M3 is generated based on air conditioning control information that indicates the content of the air conditioning based on user U1's intentions.

[0103] The processor 101 of the arithmetic unit 100 may cause the automatic control AI model M3 to calculate the parameters for the air conditioning settings, and then cause the air conditioning unit 210 to perform air conditioning of the target space 200 based on the calculated parameters, at predetermined time intervals. This ensures that the air conditioning of the target space 200 is performed in accordance with user U1's policies regarding comfort and energy saving, without any operation from user U1.

[0104] (Summary of the embodiments) The above description of embodiments discloses at least the following technologies. Note that the components etc. in the embodiments are examples of those described in parentheses, but are not limited to these.

[0105] (Technology 1) A control method for an air conditioning system (e.g., air conditioning system 210) that provides air conditioning to a target space (e.g., target space 200) involves receiving a user's (e.g., user U1) setting of a target value for the temperature distribution of the target space at a predetermined set time, setting the parameters for the air conditioning system's settings through an air conditioning control simulation of the target space, calculating the predicted value of the temperature distribution of the target space and the power consumption of the air conditioning system at a predetermined set time based on the set air conditioning system parameters, and, upon receiving the user's specification for the temperature difference and power consumption, which represent the difference between the calculated predicted value and the target value, causing the air conditioning system to provide air conditioning to the target space based on the air conditioning system parameters set in the air conditioning control simulation.

[0106] This allows the control method to set air conditioning parameters through air conditioning control simulation, and to calculate the temperature distribution of the target space and the power consumption of the air conditioning system when air conditioning is performed based on the set parameters. Furthermore, the user can compare their set target temperature distribution with the calculated predicted temperature distribution. The user can also check the power consumption when air conditioning is performed based on those parameters. Moreover, if the user is satisfied with the calculation results, the control method can instruct the air conditioning system to perform air conditioning based on those parameters. This ensures that the air conditioning of the target space is performed in accordance with the user's comfort and energy-saving policies.

[0107] (Technology 2) The control method described in Technology 1 involves setting multiple parameters for the air conditioning settings of an air conditioning system, calculating the predicted temperature distribution of the target space at a predetermined set time and the power consumption of the air conditioning system for each parameter setting, based on the set parameters. The control method then causes the air conditioning system to perform air conditioning of the target space based on the parameter corresponding to the combination of temperature difference (showing the difference between the calculated predicted value and the target value) and power consumption specified by the user from among the multiple parameters of the set air conditioning settings.

[0108] This allows users to configure the air conditioning system based on the parameters among multiple air conditioning settings that achieve the desired temperature distribution and power consumption.

[0109] (Technology 3) The control method described in Technology 1 repeatedly executes the following processes, from accepting the setting of a target value for the temperature distribution at a predetermined time in the target space to calculating the predicted value of the temperature distribution at that predetermined time in the target space and the power consumption of the air conditioner, until it receives user specifications for the temperature difference and power consumption, which represent the difference between the calculated single predicted value and the target value.

[0110] This allows users to repeatedly explore air conditioning settings parameters that align with their preferences, in other words, parameters that achieve the desired temperature distribution and power consumption.

[0111] (Technology 4) The control method described in any one of the technologies 1 to 3 involves obtaining the current value of the temperature distribution of a target space and, in an air conditioning control simulation, inputting the current value of the temperature distribution of the target space and the set air conditioning setting parameters into a first AI model (e.g., forward estimation AI model M1) that calculates the temperature distribution of the target space at a predetermined set time after the predetermined time in response to input of first input data including the temperature distribution of the target space at a predetermined time and the air conditioning setting parameters of the air conditioning system, thereby calculating a predicted value of the temperature distribution of the target space at a predetermined set time.

[0112] This allows the control method to use a trained AI model to calculate the temperature distribution of the target space when the air conditioning is applied based on the set air conditioning parameters. As a result, the control method can predict the temperature distribution of the target space quickly and easily.

[0113] (Technology 5) The control method described in Technology 4 calculates the parameters for the air conditioning settings of an air conditioning system by inputting the current value and target value of the temperature distribution of the target space into a second AI model (for example, an inverse estimation AI model M2) that calculates the parameters for the air conditioning settings of an air conditioning system in response to input of second input data including the temperature distribution of the target space at a predetermined time and the temperature distribution of the target space at a predetermined set time after the predetermined time in an air conditioning control simulation. The parameters for the air conditioning settings of an air conditioning system calculated by the second AI model are then set as the parameters for the air conditioning settings of an air conditioning system to be input into the first AI model.

[0114] This allows the control method to use a trained AI model to calculate the parameters for the air conditioning settings of the air conditioning system in order to bring the temperature distribution of the target space closer to the target value from the current value. As a result, the control method can calculate the air conditioning setting parameters quickly and easily.

[0115] (Technology 6) The control method described in Technology 4 or 5 acquires the measured temperature at the locations where the temperature sensors in the target space are installed, measured by a plurality of temperature sensors (for example, temperature sensor 220) installed in the target space, and calculates the current value of the temperature distribution in the target space based on the measured temperature.

[0116] This allows the control method to calculate the current temperature distribution of the target space based on the temperatures measured by multiple temperature sensors installed in the target space.

[0117] (Technology 7) The control method described in any one of the technologies 1 to 6 presents the user with the current temperature distribution of the target space, past temperature distribution of the target space, past power consumption of the air conditioning system, outside temperature, and solar radiation, and then accepts the user's setting of a target value for the temperature distribution of the target space.

[0118] This allows the control method to present the user with the current temperature distribution of the target space, along with reference information including the past temperature distribution of the target space, the past power consumption of the air conditioning system, the outside temperature, and solar radiation, before accepting the user's setting of the target temperature distribution value for the target space. This allows the user to set the target temperature distribution value by referring to the current temperature distribution value and the reference information.

[0119] (Technology 8) The control method described in any one of technologies 1 to 7 generates a third AI model (e.g., automatic control AI model M3) that records indicator information including the temperature distribution of the target space and the power consumption of the air conditioner, environmental information including the outside temperature and solar radiation, and air conditioning control information including the parameters of the air conditioning settings of the air conditioner in a database (e.g., related information database DB1) that records the parameters of the air conditioning settings when the air conditioner is made to air condition the target space, the power consumption of the air conditioner, the current value of the temperature distribution of the target space, the outside temperature, and the solar radiation, and based on the database, calculates the parameters of the air conditioning settings of the air conditioner in response to the input of third input data including the temperature distribution of the target space, the power consumption of the air conditioner over a predetermined period, the outside temperature, and the solar radiation.

[0120] This allows the control method to record parameters of the air conditioning settings in a database when the air conditioning system is performing air conditioning. Furthermore, the control method can generate a third AI model for automatically performing air conditioning in accordance with user comfort and energy conservation policies for the target space.

[0121] (Technology 9) The control method described in Technology 8 involves inputting the current temperature distribution of the target space, the power consumption of the air conditioner over a predetermined period, the outside temperature, and the amount of solar radiation into the third AI model, and then having the air conditioner perform air conditioning of the target space at predetermined time intervals based on the parameters of the air conditioning settings of the air conditioner calculated from these parameters.

[0122] This allows the control method to automatically adjust the air conditioning in accordance with user comfort and energy-saving policies, without requiring any user intervention.

[0123] (Technology 10) The control program that causes the computing unit to control an air conditioning unit that provides air conditioning for a target space includes: receiving a user setting for a target value of the temperature distribution in the target space at a predetermined set time; setting the parameters of the air conditioning unit's settings through an air conditioning control simulation of the target space; calculating the predicted value of the temperature distribution in the target space and the power consumption of the air conditioning unit when the air conditioning unit provides air conditioning for the target space based on the set air conditioning settings parameters; and, upon receiving the user's specification for the temperature difference and power consumption, which represent the difference between the calculated predicted value and the target value, causing the air conditioning unit to provide air conditioning for the target space based on the air conditioning settings parameters set in the air conditioning control simulation.

[0124] As a result, the control program can achieve the same effect as in Technique 1.

[0125] The functions of the above-described embodiment can also be realized by supplying programs and applications for realizing the functions of the above-described embodiment to a system or device using a network or storage medium, and by having one or more processors in the computer of that system or device read and execute the programs.

[0126] Furthermore, the functions of the above-described embodiments may be implemented by a circuit that implements one or more functions, such as an Application Specific Integrated Circuit (hereinafter referred to as "ASIC") or an FPGA.

[0127] While embodiments relating to this disclosure have been described above with reference to the drawings, this disclosure is not limited to such examples. It is clear to those skilled in the art that various modifications, alterations, substitutions, additions, deletions, and equivalents can be conceived within the scope of the claims, and these are also understood to fall within the technical scope of this disclosure. Furthermore, the components of the embodiments described above can be combined in any way without departing from the spirit of the invention. [Industrial applicability]

[0128] This disclosure is useful as a control method and control program. [Explanation of Symbols]

[0129] 50 Control Systems 100 Computing equipment 101 Processors 102 memory 103 Communication equipment 104 Input device 105 Display device 106 External Interface Device 107 Internal Interface Device 108 Network 200 Target Space 210 Air conditioning system 220 Temperature Sensor D0, D1, Dα, Dβ, Dγ temperature distribution U1 User M1 Forward Estimation AI Model M2 Inverse Estimation AI Model M3 Automatic Control AI Model

Claims

1. A control method for an air conditioning system that provides air conditioning for a target space, The system accepts the user's setting of a target value for the temperature distribution in the target space at a predetermined set time. Based on the air conditioning control simulation of the aforementioned target space, Set the parameters for the air conditioning settings of the aforementioned air conditioning system. Based on the parameters of the set air conditioning settings, the predicted temperature distribution of the target space at the predetermined set time and the power consumption of the air conditioning system are calculated. When the user specifies the temperature difference, which represents the difference between the calculated predicted value and the target value, and the power consumption, the air conditioning system is instructed to perform air conditioning of the target space based on the air conditioning setting parameters set in the air conditioning control simulation. Control method.

2. Multiple parameters for the air conditioning settings of the aforementioned air conditioning system are set, Based on the set parameters of the air conditioning settings, the predicted temperature distribution of the target space at the predetermined set time, and the power consumption of the air conditioning system are calculated for each setting of the parameters of the air conditioning settings. Based on the parameters corresponding to the combination of the temperature difference (showing the difference between the calculated multiple predicted values ​​and the target value) and the power consumption, among the multiple parameters of the set air conditioning settings, the air conditioning system is instructed to conditioned the air in the target space. The control method according to claim 1.

3. Until the user specifies the temperature difference and power consumption, which represent the difference between the single calculated predicted value and the target value, The process from receiving the setting of a target value for the temperature distribution of the target space at a predetermined time to calculating the predicted value of the temperature distribution of the target space at that predetermined time and the power consumption of the air conditioning system are repeatedly executed. The control method according to claim 1.

4. The current value of the temperature distribution in the aforementioned target space is obtained. In the aforementioned air conditioning control simulation, A first AI model calculates the temperature distribution of the target space at a predetermined set time after the predetermined time, based on input of first input data including the temperature distribution of the target space at a predetermined time and the parameters of the air conditioning settings of the air conditioning system. By inputting the current value of the temperature distribution of the target space and the set parameters of the air conditioning settings, the AI ​​model calculates a predicted value of the temperature distribution of the target space at the predetermined set time. The control method according to claim 1.

5. In the aforementioned air conditioning control simulation, The parameters for the air conditioning settings of the air conditioning system are calculated by inputting the current value and the target value of the temperature distribution of the target space into a second AI model that calculates the parameters for the air conditioning settings of the air conditioning system in response to input of second input data including the temperature distribution of the target space at a predetermined time and the temperature distribution of the target space at a predetermined set time after the predetermined time. The parameters for the air conditioning settings of the air conditioner calculated by the second AI model are set as parameters for the air conditioning settings of the air conditioner for input into the first AI model. The control method according to claim 4.

6. The measured temperature at the location where the temperature sensors are installed in the target space is obtained by the temperature sensors installed in the target space, which are measured by a plurality of temperature sensors provided in the target space. Based on the measured temperature, the current value of the temperature distribution in the target space is calculated. The control method according to claim 4.

7. After presenting the user with the current temperature distribution of the target space, past temperature distribution of the target space, past power consumption of the air conditioning system, outside temperature, and solar radiation, the system accepts the user's setting of a target value for the temperature distribution of the target space. The control method according to claim 1.

8. A database that records index information including the temperature distribution of the target space and the power consumption of the air conditioner, environmental information including the outside temperature and solar radiation, and air conditioning control information including the parameters of the air conditioning settings of the air conditioner, records the parameters of the air conditioning settings when the air conditioner is used to conditioned the target space, the power consumption of the air conditioner, the current value of the temperature distribution of the target space, the outside temperature, and the solar radiation. Based on the aforementioned database, a third AI model is generated that calculates the parameters for the air conditioning settings of the air conditioning system in response to the input of third input data, which includes the temperature distribution of the target space, the power consumption of the air conditioning system over a predetermined period, the outside temperature, and the amount of solar radiation. The control method according to claim 1.

9. Based on the parameters of the air conditioning settings of the air conditioning system calculated by inputting the current temperature distribution of the target space, the power consumption of the air conditioning system over a predetermined period, the outside temperature, and the amount of solar radiation into the third AI model, the air conditioning system is instructed to perform air conditioning of the target space at predetermined time intervals. The control method according to claim 8.

10. A control program for causing a computing device to control an air conditioning system that provides air conditioning for a target space, The system accepts user settings for target values ​​of the temperature distribution in the aforementioned target space at a predetermined set time, Based on the air conditioning control simulation of the aforementioned target space, Setting the parameters for the air conditioning settings of the aforementioned air conditioning system, Calculate the predicted temperature distribution of the target space at the predetermined set time and the power consumption of the air conditioning system when the air conditioning system performs air conditioning of the target space based on the set air conditioning settings parameters, When the user specifies the temperature difference and power consumption, which represent the difference between the calculated predicted value and the target value, the calculation device is instructed to perform air conditioning on the air conditioning system in the target space based on the air conditioning setting parameters set in the air conditioning control simulation. Control program.

Images