Air conditioning system

The air conditioning system uses machine learning to estimate and manage heat generation loads, reducing ICT equipment failures and improving energy efficiency by accurately transferring loads between zones.

JP2025142997APending Publication Date: 2025-10-01NTT FACILITIES INC
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2024042660
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-03-18
Publication Date
2025-10-01

AI Technical Summary

Technical Problem

Existing methods for transferring heat generation load in case of air conditioning unit failure are prone to errors due to inaccuracies in calculating heat generation load, which can lead to ICT equipment failures and increased energy consumption.

Method used

An air conditioning system that utilizes machine learning models to estimate outdoor and indoor temperatures, calculates allowable loads, and compares heat generation loads to reduce the risk of ICT equipment failures and improve energy efficiency by transferring loads between zones.

Benefits of technology

Accurately estimates and manages heat generation loads to minimize ICT equipment failures and enhance energy-saving effects by optimizing load distribution across zones.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025142997000001_ABST
    Figure 2025142997000001_ABST
Patent Text Reader

Abstract

To provide an air conditioning system capable of estimating indoor temperature easy to improve an energy-saving effect and reduce a risk of failure of an ICT device, and comparing the estimated indoor temperature and allowable temperature.SOLUTION: The system comprises: an acquisition part 101 for acquiring a heat generation load, information relating to indoor temperature, information relating to ambient air, and information relating to an air conditioner 900; an allowable calculation part 106 capable of calculating allowable temperature and an allowable repairing time which is an elapsed time until it is increased to the allowable temperature and is predetermined based on the heat generation load; a first estimation part 103 for estimating ambient temperature; a second estimation part 104 for estimating the indoor temperature; a temperature calculation part 107 for calculating estimated temperature which is the indoor temperature after a power supply time elapses; a load calculation part 108 for estimating an allowable load which is the heat generation load allowed to keep the indoor temperature after the allowable repairing time elapses to not more than the allowable temperature; and a comparison part 109 for comparing a comparison load and the allowable load.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present invention relates to an air conditioning system. [Background technology]

[0002] ICT equipment (hereafter referred to as heat-generating equipment) installed in server rooms generates heat during operation. As the ICT equipment generates heat, the temperature inside the server room rises. If the temperature inside the server room becomes too high, the risk of ICT equipment malfunctioning increases. For this reason, air conditioning units are installed in server rooms to prevent the temperature inside the server room from becoming too high.

[0003] A breakdown in an air conditioning unit increases the risk of ICT equipment failure. For this reason, it is common for server rooms to take precautions against air conditioning unit failure. For example, Patent Document 1 proposes a method of transferring the load of an ICT device to another ICT device. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-002148 Summary of the Invention [Problem to be solved by the invention]

[0005] Specifically, in Patent Document 1, when an air conditioning unit fails, the heat generation load of the ICT device corresponding to the failed air conditioning unit is calculated, and based on the calculated heat generation load, the heat generation load of the ICT device is transferred to another ICT device corresponding to the failed air conditioning unit.

[0006] However, the above-mentioned method has a problem in that errors are likely to occur in the calculation accuracy of the heat generation load depending on the building environment, etc. The present invention has been made to solve the above-mentioned problems, and aims to provide an air conditioning system that can estimate the heat generation load of a heat generation device when an air conditioning device breaks down, and compare the heat generation load before the heat generation load is transferred with the heat generation load after the heat generation load is transferred. [Means for solving the problem]

[0007] In order to achieve the above object, the present invention provides the following means. An air conditioning system according to one aspect of the present invention is an air conditioning system in which a heat-generating device and an air conditioning device that cools the heat-generating device and is supplied with power from at least a power storage unit are arranged in a target space, the air conditioning system including an acquisition unit that acquires at least one of a heat load generated by the heat-generating device, information on an indoor temperature, information on outdoor air, and information on the air conditioning device at predetermined time intervals; an allowable temperature calculation unit that calculates a predetermined allowable temperature based on the heat-generating device and an allowable repair time that is a time elapsed from when the operating air conditioning device stops until the indoor temperature of the target space rises to the predetermined allowable temperature, the allowable repair time being predetermined based on the heat load; a first estimation unit that estimates the outdoor air temperature at the predetermined time intervals by inputting the currently acquired information on the outdoor air environment into a trained first learning model that has undergone machine learning to estimate the outdoor air temperature; a second estimation unit that estimates the indoor temperature at the predetermined time intervals by inputting the currently acquired heat generation load, information about the currently acquired indoor temperature, and the estimated outside air temperature into a trained second learning model that has undergone machine learning to determine the indoor temperature; a temperature calculation unit that calculates an estimated temperature that is the indoor temperature after the power supply time has elapsed based on the heat generation load of the heat generation device, the estimated indoor temperature, an air conditioning device capacity that is the capacity of the air conditioning device, a power supply time by the power storage unit, and the estimated outside air temperature; a load calculation unit that calculates an allowable load that is the heat generation load that is allowable for keeping the indoor temperature at or below the allowable temperature after the allowable repair time has elapsed based on at least the heat generation load, the allowable temperature, the estimated temperature, and the allowable repair time; and a comparison unit that compares the allowable load with a comparison load calculated based on the estimated temperature.

[0008] According to the air conditioning system according to the first aspect of the present invention, the outdoor air temperature is estimated by the first estimator. The second estimator estimates the indoor temperature based on at least the estimated outdoor air temperature. The estimated temperature is estimated based on at least the estimated outdoor air temperature and the indoor temperature.

[0009] The allowable load or comparative load is estimated based on at least the estimated temperature. The calculated comparative load is compared with the acquired heat generation load by a comparison unit. Based on the comparison result, the administrator can easily select control that is less likely to cause the heat generation device to fail.

[0010] The information about the outdoor environment preferably includes at least one of the outdoor temperature and weather forecast information, but may also include information other than the above information. The information relating to the indoor temperature preferably includes at least one of the heat generation load, the indoor temperature, and the outdoor air temperature, but may also include information other than the above information.

[0011] The information about the air conditioner preferably includes at least one of the capacity of the air conditioner, the settings of the air conditioner, and the amount of energy consumed by the air conditioner. However, information other than the above information may also be included.

[0012] The allowable temperature is the threshold for the room temperature in a server room at which heat-generating devices are less likely to malfunction. Specifically, if the allowable temperature is exceeded, heat-generating devices are more likely to malfunction. If the temperature is below the allowable temperature, heat-generating devices are less likely to malfunction.

[0013] The allowable repair time is the time it takes for the indoor temperature in the server room to reach an allowable temperature after a failure occurs in at least one air conditioning unit. In other words, it is the target time within which the air conditioning unit must be repaired.

[0014] The allowable load is a heat load that does not cause the indoor temperature to exceed the allowable temperature within the allowable repair time. A detailed explanation of the allowable load will be given later. The comparative load is a load calculated based on the allowable load. The comparative load will be described in detail later.

[0015] The estimated temperature is the room temperature when the power supply from the power storage unit is stopped. Specifically, after the power supply from the commercial power source to the air conditioner is stopped due to a power outage or other reason, the power supply to the air conditioner is switched from the commercial power source to the power storage unit. As the power storage unit continues to supply power, its storage capacity is consumed and the power supply to the air conditioner is stopped. The room temperature when the power supply is stopped is the estimated temperature.

[0016] In a first aspect of the above invention, the target space is divided into a plurality of zones, the temperature calculation unit estimates the estimated temperature for each zone, the load calculation unit estimates the allowable load for each zone, and the comparison unit compares the comparison load with the allowable load for each zone.

[0017] In this way, by comparing the comparative load and the allowable load for each zone, the administrator can determine which zones are less likely to cause ICT equipment breakdowns due to the heat generation load of the ICT equipment and are more likely to achieve high energy-saving effects.

[0018] In addition, when there are zones where air conditioning equipment is broken and zones where it is not broken, the load of the ICT equipment installed in the broken zone can be transferred to the ICT equipment installed in the non-broken zone, making it easier to reduce ICT equipment failures.

[0019] In a first aspect of the above invention, the air conditioning system is characterized by further comprising a control unit that, when there is a space in which the comparative load exceeds the allowable load, transfers the load of a heat generating device located in the exceeding space to a heat generating device located in a space other than the exceeding space in which the comparative load is less than the allowable load.

[0020] In this way, by providing a control unit, if an excess space exists, the heat generation load of the air conditioner installed in the excess space can be transferred to an air conditioner installed outside the excess space, which makes it easier to reduce the risk of failure. (Effects of the Invention) According to the air conditioning system of the present invention, it is possible to calculate a control method that is likely to reduce the risk of ICT equipment failures and compare it with the current control method. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a block diagram illustrating the configuration of an air conditioning system according to a first embodiment of the present invention. [Figure 2] 1 is a graph showing allowable temperatures and allowable repair times. [Figure 3] 4 is a flowchart illustrating processing by a control device according to the first embodiment of the present invention. [Figure 4] FIG. 5 is a block diagram illustrating the configuration of an air conditioning system according to a second embodiment of the present invention. [Figure 5] 10 is a flowchart illustrating processing by a control device according to a second embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0022] [First embodiment] An air conditioning system 10 according to a first embodiment of the present invention will be described with reference to Figures 1 to 3. The air conditioning system 10 of this embodiment is a system that controls an air conditioning device 900, and is a system that makes it easier to improve the energy-saving effect of the air conditioning device 900 and reduce the risk of ICT device failure.

[0023] 1, the air conditioning system 10 of this embodiment is configured with an air conditioning device 900, a power storage unit 901, a heat generating device 500, and a control device 100. Note that the air conditioning system 10 may have a configuration other than that described above.

[0024] The air conditioner 900 is configured to take in indoor air, cool it, and supply the cooled air to the room. The air conditioner 900 is preferably configured with at least an indoor unit (not shown), an outdoor unit (not shown), and a power storage unit 901. In addition, regarding the number of indoor units and outdoor units of the air conditioner 900 of this embodiment, an example will be described in which at least two combinations of one outdoor unit and one indoor unit are provided. Note that the combinations of indoor units and outdoor units may be combinations other than those described above. For example, the air conditioner 900 may be configured with at least one combination of one outdoor unit and at least two indoor units (not shown).

[0025] The outdoor unit is configured to exchange heat between a refrigerant and outside air or water. The outdoor unit is connected to the indoor unit through piping through which the refrigerant flows. The outdoor unit is also equipped with a compressor (not shown) that increases the pressure of the refrigerant and an outdoor heat exchanger (not shown) that cools the drawn-in air through heat exchange.

[0026] The indoor unit is configured to discharge cooled air into the room. The indoor unit is connected to the other indoor units and the outdoor unit via pipes through which a refrigerant flows. The indoor unit is also provided with an air conditioning fan (not shown) that discharges the air that has undergone heat exchange, and an indoor heat exchanger (not shown) that cools the discharged air through heat exchange.

[0027] The power storage unit 901 is configured to store power supplied from a commercial power source (not shown). In this embodiment, the power storage unit 901 supplies the stored power to the air conditioner 900 when power is not supplied from the commercial power source (hereinafter also referred to as during a power outage). Note that the capacity of the air conditioner 900 operating on the power stored in the power storage unit 901 may be lower than the capacity of the air conditioner 900 operating on power supplied from the commercial power source.

[0028] The heat-generating device 500 is an information processing device having a CPU (central processing unit), ROM, RAM, an input / output interface, etc. In this embodiment, the heat-generating device 500 is also referred to as a server device or an ICT device. It is preferable that at least two or more heat-generating devices 500 are provided.

[0029] The control device 100 of this embodiment is connected to the air conditioning device 900 and the heat generating device 500 so as to be able to transmit information via known wired or wireless information communication means. The control device 100 is also connected between the air conditioning device 900 and the heat generating device 500 so as to be able to transmit information via a known wireless communication network or a combination of a wireless communication network and a wired communication network.

[0030] Control device 100 is a device that compares the heat generation load of heat-generating device 500 with a comparison load, which will be described later. Control device 100 is an information processing device, such as a server device, that has a CPU (Central Processing Unit), ROM, RAM, an input / output interface, etc. As shown in FIG. 1 , a program stored in the storage device, such as the ROM, causes at least an acquisition unit 101, a memory unit 102, a first estimation unit 103, a second estimation unit 104, a third estimation unit 105, an allowable calculation unit 106, a temperature calculation unit 107, a load calculation unit 108, and a comparison unit 109 to function by cooperating with the CPU, ROM, RAM, and input / output interface.

[0031] The acquisition unit 101 is connected to the air conditioning device 900 and the heat generating device 500 so that information can be communicated, and is configured to acquire information about the outside air, information about the indoor temperature, information about the air conditioning device 900, and information about the heat generating device 500 (hereinafter also referred to as various types of information) at predetermined time intervals.

[0032] The information about the outside air is information indicating environmental information about the outside air. In this embodiment, the information about the outside air preferably includes at least one of information about the outside air temperature and information about a weather forecast. Note that the weather forecast information may be obtained from a communication device (not shown).

[0033] The information about the indoor temperature is information about the room in the building in which the air conditioner 900 is installed, and is information that indicates indoor environmental information including the indoor temperature. In this embodiment, an example will be described in which the room is a server room. Furthermore, the information about the indoor temperature may include a heat generation load and an outside air temperature in addition to the indoor temperature.

[0034] The information related to the air conditioner 900 is information acquired from the air conditioner 900. In this embodiment, the information related to the air conditioner 900 preferably includes the number of operating air conditioners 900, their operating states, the amount of energy consumed by the air conditioner 900, and the time for which stored power is supplied. The information related to the air conditioner 900 may also include the indoor temperature and the outdoor temperature.

[0035] The amount of energy consumed by the air conditioner 900 refers to the amount of energy consumed by the operation of the air conditioner 900. In this embodiment, the amount of energy consumed by the air conditioner 900 that is currently operating will be described.

[0036] The stored power supply time is the time during which power can be supplied from the power storage unit 901 to at least one air conditioner 900 in the event of a power outage. The information relating to the heat generating device 500 is information acquired from the heat generating device 500. In this embodiment, the information relating to the heat generating device 500 preferably includes at least the heat load generated by the heat generating device 500.

[0037] The storage unit 102 is an information storage medium configured to store various types of information. The storage unit 102 may be a flash memory such as an SD memory card, or may be a recording medium of another type.

[0038] The first estimation unit 103 is configured to estimate the next outside air temperature at predetermined time intervals. In this embodiment, the first estimation unit 103 is configured to input the following information to the first learning model.

[0039] The information input to the first learning model is the information about the outdoor air that has been acquired this time. The first learning model is a model that has been trained by machine learning. A known learning method can be used as the machine learning method.

[0040] Next, the relationship between the current time and the next time will be explained. The control device 100 performs calculation processing at predetermined time intervals. The present time refers to the timing at which the control device 100 performs the calculation process.

[0041] The next time is a time when the control device 100 is not performing calculation processing, and is a time after the current first point. The second estimation unit 104 is configured to estimate the next indoor temperature at predetermined time intervals. In this embodiment, the second estimation unit 104 is configured to input the following information to the second learning model.

[0042] The information input to the second learning model is information related to the currently acquired indoor temperature and the next outdoor temperature. In other words, the outdoor temperature estimated by the first estimation unit 103 is input to the second learning model. Note that the information input to the second learning model may include the currently acquired outdoor temperature instead of the next outdoor temperature. The second learning model is a model that has been trained by machine learning. A known learning method can be used for machine learning.

[0043] The third estimation unit 105 is configured to estimate information about the air conditioner 900 that takes into account the next indoor temperature and the next outdoor temperature at predetermined time intervals (hereinafter also referred to as information about the next air conditioner 900). In other words, the information about the next air conditioner 900 is information about the air conditioner 900 that is calculated based on the next indoor temperature and the next outdoor temperature, rather than the acquired indoor temperature and the acquired outdoor temperature. In this embodiment, the third estimation unit 105 is configured to input the information described below into the third learning model.

[0044] The information input to the third learning model includes the next outdoor temperature, the next indoor temperature, and information related to the current air conditioner 900. The third learning model is a model that has been trained by machine learning. A known learning method can be used as the machine learning.

[0045] The tolerance calculation unit 106 is configured to calculate the tolerance repair time based on at least the next outdoor temperature, the next indoor temperature, the next information about the air conditioner 900, and the tolerance temperature. A specific method for calculating the tolerance repair time will be described later.

[0046] The allowable temperature is a threshold value of the room temperature in the server room at which the heat-generating device 500 is unlikely to malfunction. Specifically, if the allowable temperature is exceeded, the heat-generating device 500 is likely to malfunction. If the temperature is equal to or lower than the allowable temperature, the heat-generating device 500 is unlikely to malfunction.

[0047] The allowable repair time is the time from when a failure occurs in at least one air conditioner 900 until the indoor temperature in the server room reaches an allowable temperature. In other words, it is the target time within which the air conditioner 900 must be repaired.

[0048] The relationship between the allowable repair time and the allowable temperature will be explained with reference to FIG. 2. In FIG. 2, the vertical axis represents the indoor temperature, and the horizontal axis represents time. In FIG. 2, the change in indoor temperature is shown by lines DA and DB, the allowable temperature is shown by line DC, and the allowable repair time is shown by line DD. Line DA is the indoor temperature when no failure occurs in the air conditioner 900. Line DB is the indoor temperature when a failure occurs in at least one air conditioner 900. Line DD is the change in time from when a failure occurs in the air conditioner 900 until the indoor temperature reaches the allowable temperature.

[0049] Point P is the timing when a failure occurs in at least one or more air conditioners 900. Point Q is the timing when the room temperature reaches the allowable temperature. The temperature calculation unit 107 is configured to calculate an estimated temperature based on at least the next outdoor temperature, the next indoor temperature, the allowable temperature, the allowable repair time, information about the air conditioner 900, and the stored power supply time. A specific method for calculating the estimated temperature will be described later.

[0050] The estimated temperature is the room temperature when the power supply from the power storage unit 901 is stopped. Specifically, after the power supply from the commercial power source to the air conditioner 900 is stopped due to a power outage or the like, the power supply to the air conditioner 900 is switched from the commercial power source to the power storage unit 901. As the power storage unit 901 continues to supply power, its storage capacity is consumed and the power supply to the air conditioner 900 is stopped. The room temperature when the power supply is stopped is the estimated temperature.

[0051] The load calculation unit 108 is configured to calculate the allowable load based on the heat generation load, allowable temperature, estimated temperature, and allowable repair time. Furthermore, the load calculation unit 108 calculates a comparative load by adding a predetermined margin to the estimated allowable load. The allowable load is a heat generation load that does not cause the indoor temperature to exceed the allowable temperature within the allowable repair time.

[0052] The comparison unit 109 is configured to compare the acquired heat generation load with a comparison load. In this embodiment, the comparison result (hereinafter also referred to as the comparison result) is stored in the storage unit 102. It is preferable that the comparison result be transmitted to the administrator of the ICT device.

[0053] Next, the operation of the control device 100 configured as described above will be described. First, the air conditioner 900 will be described, second, the heat generating device 500 will be described, third, the control of the control device 100 will be described, and fourth, the learning method of the learning model will be described.

[0054] The mechanism by which the air conditioner 900 cools a room will now be described. The air conditioner 900 rotates the air conditioning fan to draw indoor air into the indoor unit. The drawn-in air is cooled in the indoor heat exchanger. Specifically, the temperature of the drawn-in air is lowered as heat is absorbed by the refrigerant circulating between the indoor unit and the outdoor unit. The refrigerant that absorbed the heat then releases the heat to the outside air in the outdoor heat exchanger. The refrigerant that released the heat then absorbs heat from the drawn-in air again in the heat exchanger. In other words, the drawn-in air is cooled by the refrigerant.

[0055] The cooled air is discharged into the room by the air conditioning fan. The air discharged into the room is warmed by the heat of the people and electronic devices in the room. The warmed air is then drawn into the air conditioner 900 again.

[0056] Secondly, the heat generating device 500 will be described. In this embodiment, an example in which the heat generating device 500 is provided in a server room will be described. The heat generating device 500 performs information processing work and thereby emits heat into the server room. The heat emission increases the indoor temperature of the server room. The increase in the indoor temperature makes the heat generating device 500 more susceptible to failure.

[0057] Thirdly, the control of the control device 100 will be described with reference to Fig. 3. When control in the control device 100 is started, the acquisition unit 101 performs a process of acquiring various pieces of information from the air conditioner 900 and the heat generating device 500 at predetermined time intervals (S1). The acquired various pieces of information are stored in the storage unit 102.

[0058] After the various pieces of information are stored, the first estimation unit 103 performs a process of estimating the next outside air temperature based on at least the acquired information about the outside air (S2). The estimated next outside air temperature is stored in the storage unit 102.

[0059] Once the estimated next outdoor temperature is stored, the second estimation unit 104 performs a process of estimating the next indoor temperature based on at least the acquired information on the indoor temperature and the estimated next outdoor temperature (S3). The estimated next indoor temperature is stored in the memory unit 102.

[0060] Once the next indoor temperature is stored, the third estimation unit 105 performs a process of estimating information about the next air conditioner 900 based on at least the acquired information about the air conditioner 900, the next outdoor temperature, and the next indoor temperature (S4). The estimated information about the next air conditioner 900 is stored in the storage unit 102.

[0061] Once the estimated next outdoor temperature, next indoor temperature, and information related to the next air conditioner 900 are stored, the allowable repair time calculation unit 106 performs a process to calculate the allowable repair time (S5). Specifically, the allowable repair time can be calculated by inputting the next outdoor temperature, next indoor temperature, and information related to the next air conditioner 900 into Equation 1.

[0062]

number

[0063] (Equation 1) is an equation that shows the thermal balance in a room. Θr is a variable that indicates the indoor temperature. Θr / d T is a variable that indicates the change in indoor temperature over time.

[0064] Ws is a variable related to the exterior wall load. In other words, it is a variable that indicates the amount of heat that changes due to the wall that separates the inside and outside of a building. Θs is a variable that indicates the equivalent outdoor temperature, which is the outdoor temperature calculated by taking into account the amount of solar radiation.

[0065] Wn is a variable that indicates the wall load, in other words, the amount of heat that is transferred by the walls of a building. Θn is a variable that indicates the indoor temperature.

[0066] Wv is a variable that indicates the ventilation load, or in other words, the amount of heat that changes due to ventilation. Θo is a variable indicating the outside air temperature.

[0067] Nc is a variable indicating the number of air conditioners 900 in operation or the required number. H BA is a variable indicating the rated capacity of the air conditioner 900. C r is the coefficient of variation of the capacity of the air conditioner 900 depending on the room temperature.

[0068] Θ Br is the coefficient of variation of the air conditioning capacity of the air conditioner 900 depending on the room temperature. C O is a variable indicating the capacity of the air conditioner 900. Θ BO is the coefficient of variation of air conditioning capacity due to outside temperature.

[0069] The calculated allowable repair time is stored in the storage unit 102. Once the allowable repair time is stored, the temperature calculation unit 107 performs a process of calculating an estimated temperature (S6). The calculated estimated temperature is stored in the storage unit 102.

[0070] Specifically, the estimated temperature can be calculated by inputting the next outdoor temperature, the next indoor temperature, the next air conditioner 900, the allowable repair time, and the allowable temperature into Equation 1. Once the estimated temperature is stored, the load calculation unit 108 calculates a comparative load based on at least the heat load, the allowable temperature, the allowable repair time, and the estimated temperature (S7). The estimated comparative load is stored in the storage unit 102.

[0071] Once the comparison load is stored, the comparison unit 109 performs a process of comparing the current heat generation load with the comparison load (S8). The comparison result is stored in the storage unit 102. The comparison result may be communicated to an ICT terminal or the like used by the administrator.

[0072] Fourth, we will explain the machine learning of the first learning model, the second learning model, and the third learning model. In this embodiment, the present invention will be described as being applied to an example in which machine learning of a first learning model, a second learning model, and a third learning model is performed in an information processing device different from the control device 100. The first learning model, the second learning model, and the third learning model that have undergone machine learning are stored in the memory unit 102 before being controlled by the control device 100.

[0073] Furthermore, after control by the control device 100 is performed, the first learning model, the second learning model, and the third learning model that have been further subjected to machine learning may be stored in the storage unit 102. In this case, the previously stored first learning model, the second learning model, and the third learning model are replaced with the first learning model, the second learning model, and the third learning model that have been further subjected to machine learning.

[0074] Note that machine learning of the first learning model, the second learning model, and the third learning model may be performed in different information processing devices as described above, or may be performed in the control device 100. When machine learning is performed in the control device 100, a machine learning unit that performs machine learning is provided in the control device 100. Furthermore, machine learning for one of the first learning model, the second learning model, and the third learning model may be performed in a different information processing device, and machine learning for the other may be performed in the control device 100.

[0075] The specific machine learning in the first learning model, the second learning model, and the third learning model can use well-known supervised learning, and the specific content of the calculation processing in supervised learning is not limited.

[0076] Furthermore, the method for creating the teacher data for the first learning model, the second learning model, and the third learning model can be any known method, and there are no specific limitations on the creation method.

[0077] According to the air conditioning system 10 configured as described above, a comparative load can be calculated. The calculated comparative load and the acquired heat generation load are compared by the comparison unit 109. Based on the comparison result, the administrator can easily select control that is less likely to cause breakdowns in the heat generation device 500. Furthermore, the administrator can easily select control that is likely to improve energy-saving effects within a range that does not cause breakdowns in the heat generation device 500.

[0078] Furthermore, by providing the first estimation unit 103, the second estimation unit 104, and the third estimation unit 105, it is possible to estimate the indoor temperature based on the estimated outdoor air temperature. Information about the air conditioner 900 can be estimated based on the estimated indoor temperature. Furthermore, since the comparison result is calculated based on the estimated outdoor air temperature, the estimated indoor temperature, and the estimated information about the air conditioner 900, it is easier to calculate an accurate comparison result than when it is based on various acquired information.

[0079] Second Embodiment Next, a second embodiment of the present invention will be described with reference to FIGS. The air conditioning system 10A of this embodiment is similar to that of the first embodiment, but differs from the first embodiment in the configuration of the control device 100A. Another difference is that the target space is divided into zones. Therefore, in this embodiment, only the differences from the first embodiment will be described, and other descriptions will be omitted.

[0080] The air conditioning system 10A is preferably installed in a room divided into multiple zones. In this embodiment, an example in which the room is divided into two zones will be described. It is preferable that at least one heat generating device 500 is installed in each of the two zones.

[0081] As shown in Fig. 4, the control device 100A is a device that compares the heat generation load of the heat generation device 500 with a comparison load, which will be described later. The control device 100A is an information processing device, such as a server device, that has a CPU (central processing unit), ROM, RAM, an input / output interface, etc. As shown in Fig. 1, the programs stored in the storage device, such as the ROM, cause the CPU, ROM, RAM, and input / output interface to cooperate with each other to function at least an acquisition unit 101, a storage unit 102, a first estimation unit 103, a second estimation unit 104A, a third estimation unit 105, an allowance calculation unit 106A, a temperature calculation unit 107A, a load calculation unit 108A, a comparison unit 109A, a determination unit 110A, and a control unit 111A.

[0082] The second estimating unit 104A is basically the same as that in the first embodiment, but differs in that it can estimate the room temperature for each zone. The third estimation unit 105A is basically the same as that in the first embodiment, but differs in that it can estimate information about air conditioners for each zone.

[0083] The allowable calculation unit 106A is basically the same as that in the first embodiment, but differs in that it can calculate the allowable repair time for each zone. The temperature calculation unit 107A is basically the same as that in the first embodiment, but differs in that it can estimate the room temperature for each zone.

[0084] The load calculation unit 108A is basically the same as that in the first embodiment, but differs in that it can estimate the allowable load for each zone. The comparison unit 109A is basically the same as that in the first embodiment, but differs in that it can estimate the heat generation load and allowable load for each zone.

[0085] The determination unit 110A is configured to determine whether the heat generation load of the heat generation device 500 exceeds the allowable load. In this embodiment, the determination unit 110A determines whether the heat generation load of the heat generation device 500 exceeds the allowable load for each zone.

[0086] The control unit 111A has a configuration for transferring the heat generation load of one heat generation device 500 to the other heat generation device 500. Specifically, the control unit 111A reduces or stops the processing of one heat generation device 500. Thereafter, the other heat generation device 500 performs the processing that has been reduced or stopped in the one heat generation device 500. In other words, the control unit 111A can cause the other heat generation device 500 to perform the processing that has been performed in one heat generation device 500.

[0087] In this embodiment, an example will be described in which, when there is a zone in which the allowable load is exceeded, the control unit 111A moves the heat generation load of the heat generation device 500 installed in the zone in which the allowable load is exceeded to a heat generation device 500 installed in a zone in which the allowable load is not exceeded.

[0088] Next, the operation of the air conditioning system 10A configured as described above will be described with reference to Fig. 5. The explanation of the air conditioning device 900, the power storage unit 901, the heat generating device 500, the processing of Fig. 3, and the learning method of the learning model are the same as those in the first embodiment, and therefore will not be repeated. Fig. 5 is a diagram showing the processing after the processing of S8 in Fig. 3.

[0089] The results of the comparison in the process of S8 are stored in the memory unit 102. Based on the stored comparison results, the determination unit 110A determines whether the heat generation load exceeds the allowable load for each zone (S11). Furthermore, the determination unit 110A determines whether there is a zone where the heat generation load exceeds the allowable load and whether there is a zone where the heat generation load does not exceed the allowable load (hereinafter, the heat generation load can be moved) (S12).

[0090] If the heat generating load can be moved (YES), the control unit 111A performs a process to move the load of the heat generating device 500 installed in the zone where the allowable load is exceeded to a heat generating device 500 installed in a zone where the allowable load is not exceeded (S13).

[0091] If the heat generating load cannot be moved (NO), the control unit 111A performs processing to maintain the current state (S14). According to the air conditioning system 10A having the above configuration, the room is divided into zones, and therefore the comparison load and the acquired heat generation load can be compared for each zone. By comparing the heat generation load of the heat generation device 500 for each zone, the administrator can identify zones where the ICT device is less likely to break down and where energy saving effects are more likely to be high compared to the first embodiment.

[0092] Furthermore, by providing determination unit 110A and control unit 111A, if there is a zone where the comparison load is exceeded, the heat generation load of heat generation device 500 provided in the exceeding zone can be transferred to heat generation device 500 provided in a zone other than the exceeding zone, which makes it easier to reduce the risk of failure.

[0093] The technical scope of the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the spirit of the present invention. For example, the present invention is not limited to applications of the above-described embodiments, and may be applied to embodiments in which these embodiments are appropriately combined, and is not particularly limited. [Explanation of symbols]

[0094] 10, 10A...air conditioning system, 100, 100A...control device, 101...acquisition unit, 102...memory unit, 103...first estimation unit, 104, 104A...second estimation unit, 105...third estimation unit, 106, 106A...tolerance calculation unit, 107, 107A...temperature calculation unit, 108, 108A...load calculation unit, 109, 109A...comparison unit, 110A...determination unit, 111A...control unit, 500...heat generation device, 900...air conditioning device, 901...power storage unit.

Claims

1. An air conditioning system in which a heat generating device and an air conditioning device that cools the heat generating device and is supplied with power from at least a power storage unit are arranged in a target space, an acquisition unit that acquires at least one of information regarding a heat load generated by the heat generating device, information regarding an indoor temperature, information regarding outside air, and information regarding the air conditioning device at predetermined time intervals; a tolerance calculation unit that calculates a predetermined tolerance temperature based on the heat-generating device and a tolerance repair time that is a time elapsed from when the operating air conditioning device stops until the indoor temperature of the target space rises to the predetermined tolerance temperature, the tolerance calculation unit being a predetermined tolerance repair time based on the heat-generating load; a first estimation unit that estimates the outside air temperature at the predetermined time intervals by inputting the currently acquired information about the outside air environment into a trained first learning model that has undergone machine learning to estimate the outside air temperature; a second estimation unit that estimates the indoor temperature at the predetermined time intervals by inputting the currently acquired heat generation load, information related to the currently acquired indoor temperature, and the estimated outdoor air temperature into a trained second learning model that has undergone machine learning to estimate the indoor temperature; a temperature calculation unit that calculates an estimated temperature, which is the indoor temperature after the power supply time has elapsed, based on the heat generation load, the estimated indoor temperature, information about the air conditioner, a power supply time by the power storage unit, and the estimated outside air temperature; and a load calculation unit that calculates an allowable load, which is the heat generation load that is allowable for maintaining the indoor temperature at a target temperature after the allowable repair time has elapsed, based on at least the heat generation load, the allowable temperature, the estimated temperature, and the allowable repair time; a comparison unit that compares a comparative load calculated based on the estimated temperature with the allowable load; An air conditioning system comprising:

2. The target space is divided into a plurality of zones; the temperature calculation unit estimates the estimated temperature for each of the zones; the load calculation unit estimates the allowable load for each of the zones, 2. The air conditioning system according to claim 1, wherein the comparison unit compares the comparative load with the allowable load for each zone.

3. The air conditioning system of claim 1, further comprising a control unit that, when there is a space in which the comparative load exceeds the allowable load, transfers the load of the heat generating device located in the exceeding space to a heat generating device located in a space other than the exceeding space in which the comparative load is less than the allowable load.

Citation Information

Patent Citations

  • Method of controlling linkage of air conditioning facility and ICT equipment

    JP2010002148A