Air-conditioning control device, air-conditioning control method, and air-conditioning control program

Abstract

An air-conditioning control device (200) calculates one or more estimated values for an air-conditioning area (109) on the basis of area environment data and operation state data, generates one or more candidates of a set value pair on the basis of current setting data, calculates, for each candidate, a predicted energy consumption amount and a predicted comfort as a predicted balance on the basis of the one or more estimated values, and controls the air-conditioning area (109). On the basis of the predicted balance of each candidate, a set value pair to be set to the air conditioner pair (101) is determined.

Description

Technical Field

[0001] The present disclosure relates to control of air conditioning systems. Background Art

[0002] As an air conditioning system with excellent energy saving and comfort, central air conditioners are used in large buildings, and multi-split air conditioners are used in small and medium-sized buildings.

[0003] In recent years, in order to improve energy saving in large-scale buildings, an air conditioning system combining an outdoor air conditioner of a central air conditioner and an internal air conditioner of a building multi-split air conditioner is sometimes used.

[0004] The external machine and the internal machine handle heat differently in capacity and characteristics. Therefore, load coordination control is performed to control the external machine and the internal machine in coordination.

[0005] In load coordination control, at least one of the set values ​​of the external control unit and the internal control unit is controlled so that the indoor temperature or indoor humidity approaches the specified value, and the sum of the power consumption of the central air conditioner and the power consumption of the multi-split air conditioner for the building becomes smaller.

[0006] Prior art literature

[0007] Patent Literature

[0008] Patent Document 1: Japanese Patent No. 6414354 Summary of the invention

[0009] Problem that the invention aims to solve

[0010] The technology of Patent Document 1 brings the temperature or humidity close to a predetermined set value, but cannot set a better set value in consideration of the balance between power consumption and comfort.

[0011] An object of the present disclosure is to determine a setting value of an air-conditioning system in consideration of a balance between energy consumption and comfort.

[0012] Means used to solve problems

[0013] The air conditioning control device disclosed in the present invention comprises: a state estimation unit, wherein regional environmental data represents measured values ​​of each of more than one state of an air-conditioning area using an air-conditioning pair, the air-conditioning pair being composed of two types of air-conditioners, and the operating state data represents state values ​​of each of more than one state for each of the air-conditioners, and the state estimation unit calculates estimated values ​​of each of more than one state of the air-conditioning area different from the one or more states of the regional environmental data based on the regional environmental data and the operating state data; a candidate generation unit, which generates one or more candidates for the setting value pair set for the air-conditioning pair based on current setting data representing the setting value pair set in the air-conditioning pair; a balance prediction unit, which calculates predicted energy consumption and predicted comfort as predicted balance for a case where the setting value pair is set in the air-conditioning pair based on the calculated one or more estimated values ​​for each generated candidate; and a setting determination unit, which determines any of the candidates as the setting value pair set to the air-conditioning pair based on the predicted balance of each candidate.

[0014] Effects of the Invention

[0015] According to the present disclosure, it is possible to determine the set value of the air-conditioning system in consideration of the balance between energy consumption and comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a configuration diagram of the air conditioning system 100 in Embodiment 1.

[0017] Figure 2 This is a configuration diagram of the air-conditioning control device 200 in the first embodiment.

[0018] Figure 3 1 is a functional configuration diagram of the air-conditioning control device 200 in the first embodiment.

[0019] Figure 4 This is a flowchart of the air conditioning control method in the first embodiment.

[0020] Figure 5 This is a diagram showing the generation of setting value pair candidates in the first embodiment (first time).

[0021] Figure 6 This is a diagram showing the generation of setting value pair candidates in the first embodiment (second and subsequent times).

[0022] Figure 7 This is a diagram showing the Pareto goodness method in the first embodiment.

[0023] Figure 8 This is a diagram showing the Pareto goodness method in the first embodiment.

[0024] Fig. 9This is a graph showing the relationship among the set value, energy consumption, and indoor temperature in the first embodiment.

[0025] Fig.10 This is a diagram showing the selection of candidates for setting value pair in the first embodiment.

[0026] Fig.11 It is a configuration diagram of the air conditioning system 100 in the second embodiment.

[0027] Fig.12 1 is a functional configuration diagram of the air-conditioning control device 200 in the third embodiment.

[0028] Fig.13 This is a flowchart of the air conditioning control method in the third embodiment.

[0029] Fig.14 1 is a functional configuration diagram of the air-conditioning control device 200 in the fourth embodiment.

[0030] Fig.15 This is a flowchart of the model learning process in Implementation Example 4.

[0031] Fig.16 This is a flowchart of the air conditioning control method in the fourth embodiment.

[0032] Fig.17 1 is a functional configuration diagram of the air-conditioning control device 200 in the fifth embodiment.

[0033] Fig.18 This is a flowchart of the air conditioning control method in the fifth embodiment.

[0034] Fig.19 1 is a functional configuration diagram of the air-conditioning control device 200 in the sixth embodiment.

[0035] Fig. 20 This is a flowchart of the air conditioning control method in the sixth embodiment.

[0036] Fig.21 2 is a functional configuration diagram of the air-conditioning control device 200 in the seventh embodiment.

[0037] Fig. 22 This is a flowchart of the air conditioning control method in the seventh embodiment.

[0038] Fig.23 This is a diagram showing the selection of candidates for setting value pair in the seventh embodiment.

[0039] Fig.24 This is a flowchart of the air conditioning control method in the eighth embodiment.

[0040] Fig.25 This is a diagram showing the upper limit value of the temperature setting in the eighth embodiment.

[0041] Fig.26 It is a configuration diagram of an air conditioning system 100 in Embodiment 9.

[0042] Fig. 27 This is a flowchart of the air-conditioning method in the ninth embodiment.

[0043] Fig.28 This is a diagram showing the selection of candidates for setting value pair in the ninth embodiment.

[0044] Fig.29 2 is a hardware configuration diagram of the air-conditioning control device 200 in the embodiment. DETAILED DESCRIPTION

[0045] In the embodiments and the drawings, the same or corresponding elements are marked with the same reference numerals. The description of the elements marked with the same reference numerals as the elements in the description is appropriately omitted or simplified. The arrows in the figures mainly show the flow of data or the process flow.

[0046] Implementation method 1.

[0047] based on Figures 1 to 10 The air conditioning system 100 will be described.

[0048] ***Structure description***

[0049] based on Figure 1 , the structure of the air conditioning system 100 is described.

[0050] The air conditioning system 100 is a system that conditions the air in the air conditioning area 109 .

[0051] The air-conditioning area 109 is an area to be air-conditioned. Specifically, the air-conditioning area 109 is a specific indoor area.

[0052] The air conditioning system 100 includes an air conditioning unit pair 101 used for air conditioning of an air conditioning area 109 .

[0053] The air conditioner pair 101 includes two types of air conditioners.

[0054] Specific examples of the two types of air conditioners are the central air conditioner 110 and the multi-type air conditioner 120 .

[0055] The central air conditioner 110 includes a heat source unit 111 and an external unit 112. The external unit 112 is also simply referred to as an air conditioner.

[0056] The heat source machine 111 produces cold water and hot water.

[0057] The external conditioning unit 112 uses cold water and hot water to condition the outside air and supplies air to the air-conditioning area 109 .

[0058] The multi-split air conditioner 120 is a multi-split air conditioner for buildings.

[0059] The multi-type air conditioner 120 includes an outdoor unit 121 and an indoor unit 122. The outdoor unit 121 is connected to the air-conditioned area 109 via a refrigerant pipe. The indoor unit 122 is also called an indoor unit.

[0060] The outdoor unit 121 includes a compressor, and compresses the refrigerant and sends it out.

[0061] The indoor unit 122 sucks in air from the air-conditioned area 109 , conditions the sucked air, and supplies air to the air-conditioned area 109 .

[0062] The air conditioning control device 200 includes a sensor group 130 .

[0063] The sensor group 130 includes one or more types of sensors, and each sensor is disposed in the air-conditioning area 109 , the central air conditioner 110 , or the multi-split air conditioner 120 .

[0064] The sensor group 130 measures the states of each of the air-conditioning area 109 , the central air conditioner 110 , and the multi-type air conditioner 120 .

[0065] The air conditioning control device 200 controls the central air conditioner 110 and the multi-type air conditioner 120 based on the measurement data obtained by the sensor group 130 .

[0066] based on Figure 2 , the structure of the air conditioning control device 200 is described.

[0067] The air conditioning control device 200 is a computer including hardware such as a processor 201, a memory 202, an auxiliary storage device 203, a communication device 204, and an input / output interface 205. These hardware are connected to each other via a signal line.

[0068] The processor 201 is an IC that performs calculation processing and controls other hardware. For example, the processor 201 is a CPU.

[0069] IC is the abbreviation of Integrated Circuit.

[0070] CPU is the abbreviation of Central Processing Unit.

[0071] The memory 202 is a volatile or nonvolatile storage device. The memory 202 is also called a main storage device or a main memory. For example, the memory 202 is a RAM. The data stored in the memory 202 is stored in the auxiliary storage device 203 as needed.

[0072] RAM is the abbreviation of Random Access Memory.

[0073] The auxiliary storage device 203 is a nonvolatile storage device. For example, the auxiliary storage device 203 is a ROM, an HDD, a flash memory, or a combination thereof. The data stored in the auxiliary storage device 203 is loaded into the memory 202 as needed.

[0074] ROM is the abbreviation of Read Only Memory.

[0075] HDD is the abbreviation of Hard Disk Drive.

[0076] The communication device 204 is a receiver and a transmitter. For example, the communication device 204 is a communication chip or a NIC. The communication of the air conditioning control device 200 is performed using the communication device 204.

[0077] NIC is the abbreviation of Network Interface Card.

[0078] The input / output interface 205 is a port connected to an input device and an output device. For example, the input / output interface 205 is a USB terminal, the input device is a keyboard and a mouse, and the output device is a display. The input / output of the air conditioning control device 200 is performed using the input / output interface 205 .

[0079] USB is the abbreviation of Universal Serial Bus.

[0080] The air conditioning control device 200 is connected to the central air conditioner 110 , the multi-type air conditioner 120 , and the sensor group 130 via the communication device 204 .

[0081] However, the air conditioning control device 200 may be connected to the central air conditioner 110 , the multi-type air conditioner 120 , and the sensor group 130 via the input / output interface 205 .

[0082] The air conditioning control device 200 includes elements such as a data acquisition unit 211, a state estimation unit 212, a candidate generation unit 213, a balance prediction unit 214, a setting determination unit 215, and a setting output unit 216. These elements are realized by software.

[0083] The auxiliary storage device 203 stores an air conditioning control program for causing the computer to function as a data acquisition unit 211, a state estimation unit 212, a candidate generation unit 213, a balance prediction unit 214, a setting determination unit 215, and a setting output unit 216. The air conditioning control program is loaded into the memory 202 and executed by the processor 201.

[0084] The auxiliary storage device 203 also stores an OS. At least a part of the OS is loaded into the memory 202 and executed by the processor 201 .

[0085] The processor 201 executes the air-conditioning control program while executing the OS.

[0086] OS is the abbreviation of Operating System.

[0087] The input and output data of the air-conditioning control program are stored in the storage unit 290 .

[0088] The memory 202 functions as the storage unit 290 . However, a storage device such as the auxiliary storage device 203 , a register in the processor 201 , or a cache memory in the processor 201 may function as the storage unit 290 instead of or together with the memory 202 .

[0089] The air-conditioning control device 200 may include a plurality of processors instead of the processor 201 .

[0090] The air conditioning control program can be recorded (stored) in a computer-readable form on a non-volatile recording medium such as an optical disk or a flash memory.

[0091] Figure 3 The functional structure of the air-conditioning control device 200 is shown.

[0092] The region estimation model 291 and the equilibrium prediction model 292 are stored in the storage unit 290. These models will be described later.

[0093] ***Action description***

[0094] The operation process of the air conditioning control device 200 corresponds to the air conditioning control method. In addition, the operation process of the air conditioning control device 200 corresponds to the process performed by the air conditioning control program.

[0095] based on Figure 4 The air conditioning control method is described.

[0096] In step S110 , the data acquisition unit 211 acquires the regional environment data and the operating status data from the sensor group 130 .

[0097] The area environment data indicates measured values ​​of each of one or more states of the air-conditioning area 109 .

[0098] The measured value is a value (state value) indicating a measured state. Specifically, the measured value indicates a physical quantity related to the thermal environment.

[0099] Specific examples of the state of the air-conditioning area 109 are temperature, humidity, and wind speed.

[0100] The operating state data indicates state values ​​of each of one or more states for each air conditioner.

[0101] In the central air conditioner 110, specific examples of the state of the heat source machine 111 are the inlet and outlet temperatures of hot and cold water, the compressor frequency, and the cooling fan speed. In addition, specific examples of the state of the external machine 112 are the inlet and outlet temperatures of the hot and cold water coils, the flow rate of the hot and cold water coils, the opening of the hot and cold water coil valves, the supply air temperature, the supply air humidity, the fan speed, the fan air volume, the opening of the external air damper, and the filter differential pressure.

[0102] In the multi-connected air conditioner 120, specific examples of the state of the outdoor unit 121 are refrigerant condensing temperature, compressor frequency, compressor power consumption, blower fan speed, air supply volume, suction temperature, blowout temperature, outside air temperature, and outside air humidity. In addition, specific examples of the state of the indoor unit 122 are suction temperature, blowout temperature, refrigerant evaporation temperature, refrigerant pressure, blower fan speed, and air supply volume.

[0103] Furthermore, the data acquisition unit 211 acquires current setting data from the air conditioner pair 101 .

[0104] The current setting data indicates a pair of setting value groups set in the pair of air conditioners 101. That is, the current setting data indicates a setting value group set in the central air conditioner 110 and a setting value group set in the multi-type air conditioner 120. A setting value group is one or more setting values.

[0105] In the central air conditioner 110, a specific example of the setting of the heat source device 111 is the cold and hot water outlet temperature. In addition, a specific example of the setting of the external air conditioner 112 is the supply air temperature, supply air humidity, fan speed, and external air damper opening.

[0106] In the multi-type air conditioner 120, a specific example of the setting of the outdoor unit 121 is the refrigerant evaporation temperature. In addition, a specific example of the setting of the indoor unit 122 is the suction temperature and the rotation speed.

[0107] In step S120 , the state estimation unit 212 calculates estimated values ​​of each of one or more states of the air-conditioning area 109 based on the area environment data and the operating state data.

[0108] An estimated value is an estimated state value. Specifically, an estimated value represents a physical quantity that is difficult to measure directly.

[0109] The estimated state is a state that cannot be measured by the sensor group 130 and is different from the state of the regional environmental data. Specifically, the estimated state is a state that changes according to building-specific parameters and time periods, such as internal heat load, wall insulation, and sunlight.

[0110] The estimated values ​​are calculated using the region estimation model 291 .

[0111] The area estimation model 291 is an air conditioner model. The air conditioner model is a model for simulating the operation of each air conditioner.

[0112] The state estimation unit 212 uses the area environment data and the operation state data as inputs to calculate the area estimation model 291 . In this way, area estimation data is obtained. The area estimation data indicates the estimated value of each of one or more states of the air-conditioning area 109 .

[0113] Each estimated value may be calculated based on the indoor-outdoor enthalpy difference, the amount of outside air introduced, and the amount of heat handled by each air conditioner. For example, each estimated value may be calculated using a state estimator such as a state observer or a Kalman filter.

[0114] In step S130 , the candidate generating unit 213 generates one or more candidates for the setting value pair for the air conditioner pair 101 based on the current setting data.

[0115] In the first step S130 , the candidate generating unit 213 generates candidates by changing the setting value pair indicated by the current setting data.

[0116] based on Figure 5 , the generation of the first candidate is explained. Figure 5 The current setting value (solid line) and the candidate setting value (dashed line) are shown for the temperature. The setting value is shown in time series.

[0117] (1) The candidate generation unit 213 randomly determines a time period (change time period) for changing a setting value within a predetermined period. The predetermined period is determined in advance.

[0118] (2) The candidate generation unit 213 randomly determines the change width of the setting value of the change time period within a setting range. The setting range is determined in advance.

[0119] (3) The candidate generation unit 213 changes the setting value of the change time period in the current setting value time series by the change width. The changed time series becomes the setting value candidate.

[0120] In step S130 for the second and subsequent times, the candidate generating unit 213 changes the previous candidates and generates new candidates.

[0121] based on Figure 6, the generation of candidates after the second time is explained. Figure 6 Two existing candidate setting values ​​(solid line (a), dotted line (b)) and two new candidate setting values ​​(solid line (A), dotted line (B)) are shown for temperature. The setting values ​​are shown in time series.

[0122] (0) The candidate generator 213 deletes the candidate whose prediction balance is worse than that of other candidates among the candidates before the last time, thereby leaving good candidates.

[0123] For example, the candidate generation unit 213 retains good candidates using a method called Pareto goodness. The method of retaining good candidates will be described later.

[0124] (1) The candidate generation unit 213 randomly selects two candidates (reference candidates) from the remaining candidates.

[0125] (2) The candidate generation unit 213 randomly determines the change time period.

[0126] (3) The candidate generator 213 adopts the setting value of another reference candidate as the change value for each reference candidate in the change time period. Alternatively, the candidate generator 213 may calculate the average of the setting values ​​of two reference candidates as the change value for each reference candidate.

[0127] (4) The candidate generator 213 changes the setting value of the change time period to the change value for each reference candidate. The time series after the change of each reference candidate becomes the setting value of the new candidate.

[0128] based on Figure 7 and Figure 8 The Pareto goodness method is explained.

[0129] First, the candidate generating unit 213 compares each candidate A with other candidates B using the objective function for energy consumption and the objective function for comfort.

[0130] Next, the candidate generating unit 213 determines, for each candidate A, whether or not there is a candidate B that is superior to the candidate A in both energy consumption and comfort.

[0131] Then, if there is a candidate B that is superior to the candidate A in both energy consumption and comfort, the candidate generation unit 213 deletes the candidate A. Figure 7 There is a candidate B that is better than candidate A, so candidate A is deleted.

[0132] In addition, if there is no candidate B that is superior to candidate A in both energy consumption and comfort, the candidate generation unit 213 retains candidate A. Figure 8 There is no candidate B that is better than candidate A, so candidate A is retained.

[0133] As described above, it is determined whether or not there is an excellent candidate for all the candidates. When there are no other excellent candidates and only candidates in a trade-off relationship are left, only the candidate with a black circle remains.

[0134] However, the candidate generating unit 213 may retain good candidates using a method other than the Pareto goodness.

[0135] In addition, the candidate generation unit 213 may also use the congestion distance of NSGA-II to determine the candidates in a trade-off relationship ( Figure 7 and Figure 8 The good candidates are retained based on the determined good and bad candidates.

[0136] NSGA is the abbreviation of Non-dominated Sorting Genetic Algorithm.

[0137] Step S130 is supplemented.

[0138] To generate candidates, generally known multi-objective optimization methods may also be used.

[0139] Specific examples of the multi-objective optimization method are NSGA-II, NSGA-III, MOPSO, and MOEA / D. A specific example of NSGA-II is SBX.

[0140] MOPSO is the abbreviation of Multi-objective Particle Swarm Optimization.

[0141] MOEA / D is the abbreviation of A Multiobjective Evolutional Algorithm based on Decomposition.

[0142] SBX is the abbreviation of Simulated Binary Crossover.

[0143] Return to Figure 4 , the description continues from step S140.

[0144] In step S140 , the balance prediction unit 214 calculates a predicted balance for a case where the setting value pair is set in the air conditioner pair 101 based on the calculated one or more estimated values ​​for each of the generated candidates.

[0145] The predicted balance is the predicted energy consumption and the predicted comfort. For example, comfort is represented by temperature and humidity. In addition, comfort can also be represented by a comfort index value such as PMV or SET*.

[0146] PMV is the abbreviation of Predicted Mean Vote.

[0147] SET* is the abbreviation of Standard New Effective Temperature.

[0148] In step S140 of the nth time, the balance prediction unit 214 calculates the predicted balance based on the estimated state data obtained in step S120 and the set value pair obtained in step S130 of the nth time.

[0149] The predicted balance is calculated using the balance prediction model 292 .

[0150] The balance prediction model 292 is an air conditioner model.

[0151] The balance prediction unit 214 uses the region estimation data and the set value pair as input to calculate the balance prediction model 292. Thus, a predicted balance is obtained.

[0152] Fig. 9 An example of energy consumption and comfort (indoor temperature) calculated from the time-series temperature setting value and the balance prediction model is shown.

[0153] The predicted balance is calculated using the values ​​of a predetermined period in the calculated time series (energy consumption, comfort). For example, the predicted balance is calculated by calculating the cumulative value of the predetermined period for energy consumption and the average value of the predetermined period for comfort.

[0154] Return to Figure 4 , the description continues from step S150.

[0155] In step S150, the setting determination unit 215 determines whether the termination conditions of step S130 and step S140 are satisfied. The termination conditions are determined in advance.

[0156] For example, the termination condition is repetition of a predetermined number of times or repetition of a predetermined time. The termination condition may also be a condition that energy consumption, comfort, or predicted balance satisfies a predetermined condition.

[0157] When the end condition is satisfied, the process proceeds to step S160.

[0158] If the end condition is not satisfied, the process proceeds to step S130.

[0159] In step S160 , the setting determination unit 215 determines an arbitrary candidate as a setting value pair to be set in the air conditioner pair 101 based on the predicted balance of each candidate.

[0160] Specifically, the setting determination unit 215 determines a candidate for a predicted balance that is closest to an ideal balance as a setting value pair to be set in the air conditioner pair 101 .

[0161] Fig.10 The relationship between the predicted balance and the ideal balance of each candidate is shown. The candidate point (black circle, black quadrilateral) represents the predicted balance of each candidate. The ideal point (black triangle) represents the ideal balance. The candidate point (black quadrilateral) is the shortest distance from the ideal point. Therefore, the candidate point (black quadrilateral) is selected as the set value pair to be set for the air conditioner pair 101.

[0162] However, the set value pair is selected from candidates that satisfy the conditions that must be satisfied for energy consumption and comfort.

[0163] Return to Figure 4 , step S170 is explained.

[0164] In step S170 , the setting output unit 216 outputs the determined setting value group pair to the air conditioner pair 101 . Specifically, the setting output unit 216 outputs the setting value group for the central air conditioner 110 to the central air conditioner 110 and outputs the setting value group for the multi-type air conditioner 120 to the multi-type air conditioner 120 .

[0165] Thus, the set value group pair is set in the air conditioner pair 101. The central air conditioner 110 and the multi-type air conditioner 120 each receive the set value group and set the set value group.

[0166] **Effects of Implementation Method 1**

[0167] In the prior art, load distribution that minimizes power consumption is determined under the condition that temperature or humidity is brought close to a desired value, and a set value is set according to the determined load distribution.

[0168] In the first embodiment, various setting value candidates such as setting values ​​that can achieve energy saving even if the temperature and humidity are not close to the desired values ​​are searched through multi-objective optimization. Then, a setting value that has a good balance between energy consumption and comfort is selected from the various setting value candidates. That is, the first embodiment can set a better setting value.

[0169] In the first embodiment, the room state that is usually difficult to measure is estimated based on the current measured value, the current operating state, and the air conditioner model, and the optimal setting value is calculated by considering the transition of the state during the specified period. Therefore, compared with the prior art that only uses the current measured value, the first embodiment can more appropriately determine the setting value of the air conditioner. In addition, the first embodiment can determine the setting value by considering not only the instantaneous energy consumption state after the change, but also the transient energy consumption increase involved in the change together with the change in comfort.

[0170] Embodiment 1 has a means for automatically extracting one of the generated setting value candidates. Therefore, Embodiment 1 can automatically select an ideal setting value that is usually determined by a human under desired conditions. Thus, continuous control of the air conditioner can be achieved.

[0171] Implementation method 2.

[0172] Regarding the multi-split air conditioner 120 having a plurality of indoor units 122, based on Fig.11 The differences from Implementation Example 1 will be mainly described.

[0173] ***Structure description***

[0174] based on Fig.11 , the structure of the air conditioning system 100 is described.

[0175] In the air conditioning system 100, the multi-type air conditioner 120 includes a plurality of indoor units 122. That is, the multi-type air conditioner 120 includes two indoor units 122 or three or more indoor units 122.

[0176] The plurality of indoor units 122 are arranged in the same air-conditioning area 109, and each of the indoor units 122 is operated or stopped.

[0177] ***Action description***

[0178] The process of the air conditioning control method is the same as that in the first embodiment.

[0179] However, in step S110 and step S130, the setting value group of the multi-type air conditioner 120 in the setting value group pair includes a setting value indicating the number of operating indoor units. The number of operating indoor units is the number of indoor units 122 in operation.

[0180] **Effects of Implementation Method 2**

[0181] Embodiment 2 can optimize the change in the number of operating units. When a plurality of indoor units of a multi-type air conditioner for a building are arranged in the same air-conditioning area, Embodiment 2 changes the state (operation, stop) of each indoor unit to the optimum state.

[0182] For example, when the same indoor thermal environment can be maintained and energy consumption can be further reduced by changing the number of operating units (for example, when the load is low), Embodiment 2 can change the number of operating units to achieve energy consumption reduction.

[0183] Implementation method 3.

[0184] Regarding the method of using the information of the air-conditioning area 109, based on Fig.12 and Fig.13 The differences from Implementation Example 1 will be mainly described.

[0185] ***Structure description***

[0186] based on Fig.12 , the structure of the air conditioning control device 200 is described.

[0187] The air conditioning control device 200 further includes an element called a data acquisition unit 221 .

[0188] The air-conditioning control program also causes the computer to function as the data acquisition unit 221 .

[0189] ***Action description***

[0190] based on Fig.13 , the air conditioning control method is explained.

[0191] In step S310 , the data acquisition unit 211 acquires the regional environment data and the operating status data from the sensor group 130 .

[0192] Furthermore, the data acquisition unit 211 acquires current setting data from the air conditioner pair 101 .

[0193] Furthermore, the data acquisition unit 221 acquires the area information data.

[0194] The area information data indicates at least one of the number of people in the air-conditioning area 109 and the thermal information of the air-conditioning area 109 .

[0195] The number of people information indicates the number of people present in the air-conditioned area 109. For example, the number of people information is obtained from the room entry and exit management system. The number of people information can also be obtained based on an image showing the air-conditioned area 109. For example, a visible light camera is set on (the top surface of) the air-conditioned area 109, captures the air-conditioned area 109 and outputs an image. The data acquisition unit 211 acquires the image and calculates the number of people by processing the image.

[0196] The thermal information indicates the heat generation in the air-conditioning area 109 and the wall surface temperature of the air-conditioning area 109. For example, a thermal camera is installed in the air-conditioning area 109 to measure the heat generation and the wall surface temperature. The data acquisition unit 211 acquires the thermal information from the thermal camera.

[0197] In step S320 , the state estimation unit 212 calculates one or more estimation values ​​based on the regional environment data, the operating state data, and the regional information data.

[0198] After step S320, the process proceeds to step S140.

[0199] The processing after step S140 is the same as that described in the first embodiment.

[0200] **Effects of Implementation Method 3**

[0201] Implementation 3 uses the number of people in the room. For example, the number of people in the room counted from the room entry and exit management system, the number of people in the room counted by processing the image from the visible light camera installed on the ceiling, the indoor heat generation measured by the thermal camera or the wall temperature, etc. Then, Implementation 3 estimates the state of the air-conditioned area (room state).

[0202] Therefore, the third embodiment can improve the estimation accuracy of the room state.

[0203] Implementation method 4.

[0204] Regarding the method of using the alternative model 293 instead of the equilibrium prediction model 292, based on Figures 14 to 16 The differences from Implementation Example 1 will be mainly described.

[0205] ***Structure description***

[0206] based on Fig.14 , the structure of the air conditioning control device 200 is described.

[0207] The air conditioning control device 200 further includes an element called a model learning unit 222 .

[0208] The air-conditioning control program also causes the computer to function as the model learning unit 222 .

[0209] The substitute model 293 is a model that replaces the equilibrium prediction model 292. For example, the substitute model 293 is a learned model obtained by machine learning.

[0210] ***Action description***

[0211] based on Fig.15 , the model learning unit processing is explained. The model learning processing is a processing for generating a substitute model 293 and is executed by the model learning unit 222.

[0212] In step S401 , the model learning unit 222 generates training environment data, training status data, and training setting data based on the learning conditions.

[0213] The training environment data is data equivalent to the regional environment data.

[0214] The training status data is data equivalent to the operating status data.

[0215] The training setting data is data equivalent to the current setting data.

[0216] Specific examples of the learning conditions include a range of set values, a range of state values, the number of samples, a sample interval, weather data, and a learning target day.

[0217] In step S402, the model learning unit 222 calculates estimated values ​​of each of one or more states of the air-conditioned area 109 based on the training environment data and the training state data. The calculation method is the same as the method in step S120 of the first embodiment.

[0218] Data indicating one or more calculated estimated values ​​is referred to as training estimation data. The training estimation data corresponds to the region estimation data.

[0219] In step S403, the model learning unit 222 generates one or more candidates for the setting value pair for the air conditioner pair 101 based on the training setting data. The generation method is the same as the method in step S130 of Embodiment 1. However, the generated candidates satisfy the learning conditions.

[0220] The generated candidates are called training candidates.

[0221] In step S404, the model learning unit 222 calculates the predicted balance for the case where the setting value pair is set in the air conditioner pair 101 based on the calculated one or more estimated values ​​for each generated candidate. The calculation method is the same as the method in step S140 of the first embodiment.

[0222] The calculated predicted balance is called the training balance.

[0223] In step S405 , the model learning unit 222 stores the training candidates, the training estimation data, and the training balance as training data.

[0224] In step S406 , the model learning unit 222 determines whether the end condition for acquiring the training data is satisfied.

[0225] When the end condition is satisfied, the process proceeds to step S407.

[0226] If the end condition is not satisfied, the process proceeds to step S403.

[0227] In step S407 , the model learning unit 222 generates the substitute model 293 by learning the training data.

[0228] based on Fig.16 , the air conditioning control method is explained.

[0229] Steps S110 to S130 are the same as those described in the first embodiment.

[0230] After step S130, the process proceeds to step S440.

[0231] In step S440 , the balance prediction unit 214 calculates a predicted balance for a case where the setting value pair is set in the air conditioner pair 101 based on the calculated one or more estimated values ​​for each of the generated candidates.

[0232] Specifically, the balance prediction unit 214 uses the region estimation data and the set value pair as input to calculate the substitute model 293. Thus, a predicted balance is obtained.

[0233] After step S440, the process proceeds to step S150.

[0234] Steps S150 to S170 are the same as those described in the first embodiment.

[0235] **Effects of Implementation Method 4**

[0236] Embodiment 4 uses a substitute model to speed up prediction calculation. Embodiment 4 uses a machine learning model or the like to learn the input-output relationship of the air conditioner model in the operation of the air conditioner, and uses the learning result for prediction of energy consumption and comfort.

[0237] Thus, the fourth embodiment can speed up the prediction which takes a long time when using the air conditioner model.

[0238] Implementation method 5.

[0239] Regarding the method of considering the air quality of the air-conditioning area 109, based on Fig.17 and Fig.18 The differences from Implementation Example 1 will be mainly described.

[0240] ***Structure description***

[0241] The configuration of the air conditioning system 100 is the same as that of Embodiment 1. However, the sensor group 130 includes an air quality sensor disposed in the air conditioning area 109 .

[0242] The air quality sensor is a sensor that measures air quality. Specific examples of air quality are carbon dioxide concentration and particle count. The particle count is the number of particles such as PM10 or PM2.5.

[0243] based on Fig.17The configuration of the air conditioning control device 200 will be described.

[0244] The air conditioning control device 200 further includes a data acquisition unit 223 .

[0245] The air-conditioning control program also causes the computer to function as the data acquisition unit 223 .

[0246] ***Action description***

[0247] based on Fig.18 , the air conditioning control method is explained.

[0248] In step S510 , the data acquisition unit 211 acquires the regional environment data and the operating status data from the sensor group 130 .

[0249] Furthermore, the data acquisition unit 211 acquires current setting data from the air conditioner pair 101 .

[0250] Furthermore, the data acquisition unit 223 acquires the air quality data from the sensor group 130 .

[0251] The air quality data indicates the air quality of the air-conditioning area 109 .

[0252] After step S510, the process proceeds to step S120.

[0253] In step S120 , the state estimation unit 212 calculates one or more estimation values ​​based on the regional environment data and the operating state data.

[0254] In step S130 , the candidate generating unit 213 generates one or more candidates for the setting value pair based on the current setting data.

[0255] After step S130, the process proceeds to step S540.

[0256] In step S540 , the balance prediction unit 214 calculates a predicted balance for each generated candidate based on one or more estimated values ​​and the air quality data.

[0257] Specifically, the balance prediction unit 214 uses the area estimation data, the air quality data, and the set value pair as inputs to calculate the balance prediction model 292. Thus, a predicted balance is obtained.

[0258] The predicted balance is the predicted energy consumption, predicted comfort, and predicted air quality.

[0259] After step S540, the process proceeds to step S150.

[0260] Steps S150 and thereafter are the same as those described in the first embodiment.

[0261] **Effects of Implementation 5**

[0262] Implementation 5 optimizes air quality. Implementation 5 searches for set values ​​by optimizing three objectives: energy consumption, indoor thermal environment, and air quality environment. CO2 concentration, PM10 particle count, PM2.5 particle count, etc. are measured to be used as air quality.

[0263] Thus, in Embodiment 5, it is possible to derive setting values ​​such that both the thermal environment and the air quality environment become good.

[0264] Implementation method 6.

[0265] The method for considering the required ventilation volume is based on Fig.19 and Fig. 20 The differences from Implementation 5 will be mainly described.

[0266] ***Structure description***

[0267] based on Fig.19 , the structure of the air conditioning control device 200 is described.

[0268] The air conditioning control device 200 further includes an element called a ventilation volume calculation unit 224 .

[0269] The air-conditioning control program also causes the computer to function as the ventilation volume calculation unit 224 .

[0270] ***Action description***

[0271] based on Fig.24 , the air conditioning control method is explained.

[0272] In step S510 , the data acquisition unit 211 acquires regional environmental data and operating status data.

[0273] Furthermore, the data acquisition unit 211 acquires current setting data.

[0274] Furthermore, the data acquisition unit 223 acquires air quality data.

[0275] After step S510, the process proceeds to step S610.

[0276] In step S610, the ventilation volume calculation unit 224 calculates the required ventilation volume based on the air quality data.

[0277] The required ventilation volume is the ventilation volume required to make the air quality environment of the air-conditioning area 109 an ideal environment.

[0278] After step S610, the process proceeds to step S120.

[0279] In step S120 , the state estimation unit 212 calculates one or more estimation values ​​based on the regional environment data and the operating state data.

[0280] After step S120, the process proceeds to step S630.

[0281] In step S630 , the candidate generating unit 213 generates one or more candidates based on the current setting data on the condition that a ventilation volume equal to or greater than a required ventilation volume is ensured in the air-conditioning area 109 when each candidate is set in an air conditioner pair.

[0282] For example, in each candidate, the ventilation volume calculated based on the set value related to the ventilation volume is greater than the required ventilation volume.

[0283] After step S630, the process proceeds to step S540.

[0284] Steps S540 and thereafter are the same as those described in Implementation 5.

[0285] **Effects of Implementation Method 6**

[0286] Embodiment 6 calculates required ventilation volume. Embodiment 6 calculates the required ventilation volume for the measured air quality, and obtains setting values ​​that provide a good energy consumption amount and indoor thermal environment within a range where the required ventilation volume is sufficient.

[0287] Thus, the sixth embodiment can achieve the minimum conditions for satisfying good air quality and realize energy-saving and comfortable air-conditioning operation.

[0288] Implementation method 7.

[0289] The way to consider the questionnaire results related to comfort is based on Figure 21 to Figure 23 The differences from Implementation Example 1 will be mainly described.

[0290] ***Structure description***

[0291] based on Fig.21 , the structure of the air conditioning control device 200 is described.

[0292] The air conditioning control device 200 further includes an element called a questionnaire result acquisition unit 225 .

[0293] The air conditioning control program also causes the computer to function as the questionnaire result acquisition unit 225 .

[0294] ***Action description***

[0295] based on Fig. 22 , the air conditioning control method is explained.

[0296] In step S710 , the data acquisition unit 211 acquires the regional environment data and the operating status data from the sensor group 130 .

[0297] Furthermore, the data acquisition unit 211 acquires current setting data from the air conditioner pair 101 .

[0298] Then, the questionnaire result acquisition unit 225 acquires the questionnaire result data. For example, the questionnaire result data is input to the air conditioning control device 200, and then the questionnaire result acquisition unit 225 receives the input questionnaire result data.

[0299] The questionnaire result data indicates the questionnaire result related to comfort. The questionnaire result is obtained from the occupants of the rooms in the air-conditioning area 109, for example.

[0300] After step S710, the process proceeds to step S120.

[0301] Steps S120 to S150 are the same as those described in the first embodiment.

[0302] After step S150, the process proceeds to step S760.

[0303] In step S760 , the setting determination unit 215 determines an arbitrary candidate as a setting value pair to be set in the air conditioner pair 101 based on the questionnaire result data and the predicted balance of each candidate.

[0304] Specifically, the setting determination unit 215 determines the ideal balance based on the questionnaire result data. Then, the setting determination unit 215 selects an arbitrary candidate as a setting value pair by the same method as the method in step S160 of the first embodiment.

[0305] Fig.23 The figure shows a case where the ideal balance (ideal point) is changed based on the questionnaire survey results.

[0306] For example, suppose that a candidate for an indoor environment that is neither too warm nor too cold when cooling is selected. As a result of a questionnaire survey of residents, it is determined that the occupants are comfortable when the room temperature is not too low and not too cold. In this case, the ideal point is usually changed so as to move to the side where comfort decreases (the warmer side). When the ideal point is changed, the selected candidate changes.

[0307] **Effects of Implementation Method 7**

[0308] Embodiment 7 reflects the questionnaire results. That is, embodiment 7 reflects the questionnaire results of the indoor occupants to extract the setting value. In order to extract the setting value, embodiment 7 changes the set ideal balance based on the questionnaire results. For example, embodiment 7 moves the ideal point to the side that is considered comfortable in the questionnaire results.

[0309] Thus, the seventh embodiment can extract good setting values ​​by further considering the actual comfort of the occupants.

[0310] Implementation method 8.

[0311] Regarding the method of considering the characteristics of each air conditioner, based on Fig.24 and Fig.25 The differences from Implementation Example 1 will be mainly described.

[0312] ***Structure description***

[0313] The configuration of the air conditioning system 100 is the same as that in the first embodiment.

[0314] ***Action description***

[0315] based on Fig.24 , the air conditioning control method is explained.

[0316] Step S110 and step S120 are the same as those described in the first embodiment.

[0317] After step S120, the process proceeds to step S830.

[0318] In step S830, the candidate generator 213 determines the restriction ranges of the setting values ​​of the central air conditioner 110 and the multi-split air conditioner 120 according to the characteristics of the central air conditioner 110 and the multi-split air conditioner 120. The restriction range is the range of values ​​that the setting value can take.

[0319] Then, the candidate generating unit 213 generates one or more candidates for each air conditioner based on the current setting data and the restriction range. In each candidate, each setting value is a value included in the restriction range.

[0320] For example, it is assumed that if sensible heat is processed in a multi-split air conditioner for a building, the overall energy consumption can be reduced. In addition, it is assumed that if latent heat is processed in a central air conditioner, the overall energy consumption can be reduced. In this case, in the multi-split air conditioner for a building, the set value of the evaporation temperature is limited to a higher range in order to process sensible heat. In addition, in the central air conditioner, the set value of the heat source outlet temperature is limited to a lower range in order to process latent heat. Then, candidates for each set value are generated within the limited range.

[0321] Fig.25 Shows the upper limit value of the temperature setting. The upper limit value is a value obtained in consideration of efficiency, and indicates the upper limit of the temperature setting limit range. The temperature setting value is lower than the upper limit value.

[0322] ***Effects of Implementation 8***

[0323] Embodiment 8 takes the characteristics of each air conditioner into consideration. Embodiment 8 limits the range of the set value according to the characteristics of the air conditioner, and optimizes the set value within the limited range.

[0324] Thus, the eighth embodiment makes the search for more appropriate setting values ​​more efficient and can shorten the time required for optimization.

[0325] Implementation method 9.

[0326] Regarding the method of conditioning the air in each of the plurality of air-conditioning areas 109, based on Figure 26 to Figure 28 The differences from Implementation Example 1 will be mainly described.

[0327] ***Structure description***

[0328] based on Fig.26 , the structure of the air conditioning system 100 is described.

[0329] The air conditioning system 100 is a system that conditions air in each of a plurality of air conditioning areas 109 .

[0330] In the air-conditioning system 100 , the multi-type air conditioner 120 includes a plurality of indoor units 122 .

[0331] The plurality of indoor units 122 are used for air conditioning of different air-conditioning areas 109 .

[0332] ***Action description***

[0333] based on Fig. 27 , the air conditioning control method is explained.

[0334] In step S910 , the data acquisition unit 211 acquires the area environment data and the operation status data from the sensor group 130 . In addition, the data acquisition unit 211 acquires the current setting data from the air conditioner pair 101 .

[0335] Here, the area environment data is acquired for each air-conditioning area 109 .

[0336] In step S920 , the state estimation unit 212 calculates estimated values ​​of each of one or more states of the air-conditioning area 109 based on the area environment data and the operating state data.

[0337] However, one or more estimated values ​​are calculated for each air-conditioning area 109 .

[0338] In step S930 , the candidate generating unit 213 generates one or more candidates for the setting value pair for the air conditioner pair 101 based on the current setting data.

[0339] Among them, one or more candidates are generated under the condition that power consumption is low and the comfort level of all air-conditioned areas 109 is good.

[0340] In step S940 , the balance prediction unit 214 calculates a predicted balance for a case where a set value pair is set in the air conditioner pair 101 based on one or more estimated values ​​of each air conditioning area 109 for each generated candidate.

[0341] The comfort level of each air-conditioning zone 109 is included in the predicted balance.

[0342] After step S940, the process proceeds to step S150.

[0343] Steps S150 and thereafter are the same as those described in the first embodiment.

[0344] Fig.28 The relationship between the predicted balance and the ideal balance of each candidate is shown for a case where there are two air-conditioning areas 109 .

[0345] When the first air-conditioning area 109 and the second air-conditioning area 109 exist, a candidate point closest to the ideal balance (ideal point) is selected from the three-dimensionally arranged candidates.

[0346] **Effects of Implementation Method 9**

[0347] In the ninth embodiment, it is possible to cope with a plurality of air-conditioning areas. In the case where there are two air-conditioning areas, in the ninth embodiment, (a) the energy consumption of the entire air conditioner, (b) the indoor environment of the first air-conditioning area, and (c) the indoor environment of the second air-conditioning area are predicted. Then, in the ninth embodiment, the setting values ​​are searched so that all of (a) to (c) are good.

[0348] Thus, in a system that supplies air to a plurality of air-conditioning areas, it is possible to calculate setting values ​​that optimize the overall energy consumption of a plurality of air conditioners and the indoor environment of each air conditioner.

[0349] **Supplementary information on implementation methods**

[0350] based on Fig.29 , the hardware structure of the air conditioning control device 200 is described.

[0351] The air conditioning control device 200 includes a processing circuit 209 .

[0352] The processing circuit 209 is hardware that realizes a data acquisition unit 211, a state estimation unit 212, a candidate generation unit 213, a balance prediction unit 214, a setting determination unit 215, and a setting output unit 216. In addition, the processing circuit 209 realizes a data acquisition unit 221, a model learning unit 222, a data acquisition unit 223, a ventilation volume calculation unit 224, and a questionnaire result acquisition unit 225.

[0353] The processing circuit 209 may be dedicated hardware, or may be the processor 201 that executes a program stored in the memory 202 .

[0354] In the case where the processing circuit 209 is dedicated hardware, the processing circuit 209 is, for example, a single circuit, a complex circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

[0355] ASIC is the abbreviation of Application Specific Integrated Circuit.

[0356] FPGA is the abbreviation of Field Programmable Gate Array.

[0357] The air-conditioning control device 200 may include a plurality of processing circuits instead of the processing circuit 209 .

[0358] In the processing circuit 209 , part of the functions may be implemented by dedicated hardware, and the remaining functions may be implemented by software or firmware.

[0359] In this way, the functions of the air conditioning control device 200 can be implemented by hardware, software, firmware or a combination thereof.

[0360] Each embodiment is an example of a preferred method and is not intended to limit the technical scope of the present disclosure. Each embodiment can be implemented partially or in combination with other methods. The process described using flowcharts and the like can also be appropriately changed.

[0361] The “unit” of each element of the air-conditioning control device 200 may be rewritten as “processing”, “step”, “circuit” or “line”.

[0362] Description of Reference Numerals

[0363] 100 air conditioning system, 101 air conditioning unit pair, 109 air conditioning area, 110 central air conditioner, 111 heat source unit, 112 external air conditioner, 120 multi-split air conditioner, 121 outdoor unit, 122 indoor unit, 130 sensor group, 200 air conditioning control device, 201 processor, 202 memory, 203 auxiliary storage device, 204 communication device, 205 input and output interface, 209 processing circuit, 211 data acquisition unit, 212 state estimation unit, 213 candidate generation unit, 214 balance prediction unit, 215 setting determination unit, 216 setting output unit, 221 data acquisition unit, 222 model learning unit, 223 data acquisition unit, 224 ventilation volume calculation unit, 225 questionnaire result acquisition unit, 290 storage unit, 291 area estimation model, 292 balance prediction model, 293 alternative model.

Claims

1. An air conditioning control device, comprising: a state estimation unit, wherein the regional environment data represents measured values ​​of each of one or more states of an air-conditioning area using an air-conditioning pair, the air-conditioning pair being composed of two types of air-conditioners, and the operating state data represents state values ​​of each of the one or more states for each of the air-conditioners, and the state estimation unit calculates estimated values ​​of each of one or more states of the air-conditioning area different from the one or more states of the regional environment data based on the regional environment data and the operating state data; a candidate generating unit for generating one or more candidates for the setting value pair for the air conditioner pair based on current setting data indicating the setting value pair set in the air conditioner pair; a balance prediction unit that calculates, for each of the generated candidates, a predicted energy consumption and a predicted comfort level as a predicted balance for a case where the set value pair is set in the air conditioner pair based on the calculated one or more estimated values; as well as A setting determination unit determines, based on the predicted balance of each candidate, any of the candidates as a setting value pair to be set in the pair of air conditioners.

2. The air conditioning control device according to claim 1, in, One of the pair of air conditioners is a multi-type air conditioner having a plurality of indoor units. The setting value group for the multi-type air conditioner in the setting value group pair includes a setting value indicating the number of operating indoor units.

3. The air conditioning control device according to claim 1 or 2, in, The state estimation unit calculates the one or more estimated values ​​based on the area information data, the area environment data, and the operation state data. The area information data indicates at least one of the number of people in the air-conditioning area and the thermal information of the air-conditioning area.

4. The air conditioning control device according to any one of claims 1 to 3, in, The air conditioning control device includes a model learning unit. The model learning unit includes a model learning unit, which generates educational environment data equivalent to the regional environment data and educational status data equivalent to the operating status data, calculates training estimation data equivalent to the one or more estimated values ​​based on the educational environment data and the educational status data, generates training setting data equivalent to the current setting data, generates one or more training candidates equivalent to the one or more candidates based on the training setting data, calculates a training balance equivalent to the predicted balance for each of the training candidates based on the training estimation data for the case where the training candidate is set in the air conditioner pair, learns the training candidate, the training estimation data and the training balance according to each of the training candidates, and generates a replacement model, The balance prediction unit calculates the predicted balance by computing the alternative model using the one or more estimated values ​​and the candidate as inputs for each of the candidates.

5. The air conditioning control device according to any one of claims 1 to 4, in, The balance prediction unit calculates predicted air quality, predicted energy consumption, and predicted comfort as the predicted balance based on air quality data indicating air quality of the air-conditioning area and the one or more estimated values.

6. The air conditioning control device according to claim 5, in, The air conditioning control device includes a ventilation volume calculation unit. The ventilation volume calculation unit calculates the required ventilation volume based on the air quality data. The candidate generating unit generates the one or more candidates based on the current setting data on the condition that a ventilation volume equal to or greater than the required ventilation volume is ensured in the air-conditioning area when each candidate is set in the air-conditioning pair.

7. The air conditioning control device according to any one of claims 1 to 6, in, The setting determination unit determines an ideal balance based on questionnaire result data indicating a questionnaire result related to comfort, and determines the set value pair based on the ideal balance and the predicted balance of each candidate.

8. The air conditioning control device according to any one of claims 1 to 7, in, The candidate generating unit generates, for each of the air conditioners, candidates for setting values ​​of the air conditioners within a restriction range determined based on characteristics of the air conditioners.

9. The air conditioning control device according to any one of claims 1 to 8, in, There are a plurality of said air-conditioned areas, The state estimation unit calculates the one or more estimation values ​​for each of the air-conditioning areas. The balance prediction unit calculates the predicted energy consumption and the predicted comfort level of each air-conditioning area as the predicted balance based on the one or more estimated values ​​of each air-conditioning area.

10. An air conditioning control method, in, The regional environment data represents measured values ​​of one or more states of an air-conditioning area using an air-conditioning pair, the air-conditioning pair being composed of two air-conditioning machines, the operating state data represents state values ​​of one or more states for each of the air-conditioning machines, and based on the regional environment data and the operating state data, estimated values ​​of one or more states of the air-conditioning area different from the one or more states of the regional environment data are calculated. generating one or more candidates for the set value pair for the air conditioner pair based on current setting data indicating the set value pair set in the air conditioner pair, For each of the generated candidates, based on the calculated one or more estimated values, a predicted energy consumption and a predicted comfort level are calculated as a predicted balance for a case where the set value pair is set in the air conditioner pair. Based on the predicted balance of each candidate, any of the candidates is determined as a set value pair to be set for the pair of air conditioners.

11. An air conditioning control program, in, The air conditioning control program is used to enable the computer to execute: State estimation processing, wherein the regional environment data represents measured values ​​of one or more states of an air-conditioning area using an air-conditioning pair, the air-conditioning pair being composed of two air-conditioning units, the operating state data represents state values ​​of one or more states for each of the air-conditioning units, and based on the regional environment data and the operating state data, the estimated values ​​of one or more states of the air-conditioning area different from the one or more states of the regional environment data are calculated; A candidate generation process of generating one or more candidates of a setting value pair for the air conditioner pair based on current setting data indicating a setting value pair set in the air conditioner pair; A balance prediction process of calculating, for each of the generated candidates, a predicted energy consumption and a predicted comfort level as a predicted balance for a case where the set value pair is set in the air conditioner pair based on the calculated one or more estimated values; as well as The setting determination process determines, based on the predicted balance of each candidate, any of the candidates as a setting value pair to be set in the pair of air conditioners.

Images