JP6893262B2 - Smart window control device, smart window control method and smart window control program - Google Patents

Description

The present invention relates to a smart window control device, a smart window control method, and a smart window control program.

Conventionally, smart window control that adjusts the amount of sunlight and the amount of heat incident on a building by applying glass whose optical characteristics (for example, transmittance) can be controlled as a smart window to the window of a building such as an office building. The system is known.

According to the smart window control system, for example, in the summer, the amount of sunlight and heat incident on the building is reduced, and in the winter, the amount of sunlight incident on the building and the amount of heat are increased to control the temperature inside the building. Can assist the air conditioning system. As a result, the load on the air conditioning system can be reduced.

Japanese Patent Application Laid-Open No. 2015-534127

Here, in the case of the smart window control system, there is a large time lag from when the transmittance is controlled and the amount of sunlight and heat incident on the building are adjusted until the temperature inside the building actually changes.

Therefore, in order to reduce the load on the air conditioning system, it is necessary to consider the above time lag when controlling the transmittance.

On one side, it aims to reduce the load on the air conditioning system.

According to one aspect, the smart window controller
A smart window control device that controls the transmittance of a smart window provided in a window in a space where the temperature is controlled according to a set temperature by an air conditioning system.
An acquisition unit that acquires a predicted value of environmental information outside the space in the section between the first time and the second time after a predetermined time from the first time.
A calculation unit that calculates the temperature transition of the space in the section based on the predicted value of the external environmental information in the section.
It has a transmittance control unit that controls the transmittance of the smart window so that the temperature of the space in the section changes based on the calculated temperature transition.

The load on the air conditioning system can be reduced.

It is a figure which shows the appearance composition of the building which installed the smart window. It is a figure which shows an example of the network system configured in a building. It is a figure which shows the configuration example of a smart window control system. It is a figure which shows the configuration example of an air conditioning system. It is a figure which shows an example of the hardware configuration of a smart window control device. It is a figure which shows an example of the functional structure of the generation part of a smart window control device. It is a flowchart which shows the flow of the model generation process by the generation part of a smart window control device. FIG. 1 is a first diagram showing an example of a functional configuration of a control unit of a smart window control device. It is a figure which shows an example of the mode transition of the control part of the smart window control device. It is a figure which shows the specific example of the predicted value of the environmental information in the prediction mode section. It is a figure which shows an example of the temperature transition prediction data in a prediction mode section. It is a 1st flowchart which shows the flow of the transmittance control processing in a prediction mode. FIG. 2 is a second diagram showing an example of a functional configuration of a control unit of a smart window control device. It is a figure which shows the specific example of the measured room temperature in a prediction mode section. It is a 2nd flowchart which shows the flow of the transmittance control processing in a prediction mode. It is the first figure which shows an example of the temperature transition prediction data in a normal mode section. It is a 1st flowchart which shows the flow of the transmittance control processing in a normal mode section. It is a figure which shows the predicted value of the environmental information. FIG. 3 is a third diagram showing an example of the functional configuration of the control unit of the smart window control device. It is a 2nd figure which shows an example of the temperature transition prediction data in a normal mode section. It is a 2nd flowchart which shows the flow of the transmittance control processing in a normal mode section.

Hereinafter, each embodiment will be described with reference to the accompanying drawings. In the present specification and the drawings, components having substantially the same functional configuration are designated by the same reference numerals to omit duplicate explanations.

[First Embodiment]
<Exterior composition of the building>
First, the exterior configuration of the building where the smart window is installed will be described. FIG. 1 is a diagram showing an external configuration of a building in which a smart window is installed. As shown in FIG. 1, a window group 120 is provided on a predetermined surface of a building 110 (for example, an office building). In the present embodiment, it is assumed that the smart windows 120_1 to 120_15 are installed on the floor indicated by the dotted line 130.

A smart window is a window portion to which glass whose transmittance can be controlled is applied. In the present embodiment, the control method of the transmittance of the glass applied to the smart window is an electrochromic method, a PDLC (Polymer dispersed LCs) method, or a gas chromic method. May be good.

The cross-sectional structure of the smart window 120_15 is as shown on the right side of FIG. 1, and includes a plurality of layers of glass. In the smart window 120_15, the transmittance of the glass 140 applied to one of the layers is controlled. As shown on the right side of FIG. 1, the transmittance of the glass 140 is controlled in the range indicated by the arrow 150 (for example, in the range of 10% to 90%). Thereby, the amount of sunlight and the amount of heat incident on the floor space indicated by the dotted line 130 of the building 110 can be adjusted.

<Network system configuration>
Next, the network system configured in the building 110 will be described. FIG. 2 is a diagram showing an example of a network system configured in a building. As shown in FIG. 2, the network system 200 includes a building management system 210, a smart window control system 220, and an air conditioning system 230. In the network system 200, each system is communicably connected via a LAN (Local Area Network) 240.

The building management system 210 is a system that manages the security in the building 110. In the present embodiment, the building management system 210 monitors, for example, whether or not the entrance / exit of each space on each floor is locked, and determines the usage status of each space on each floor.

The method of determining the usage status of each space on each floor by the building management system 210 is not limited to this. For example, another sensor (such as a motion sensor) capable of directly or indirectly detecting the presence or absence of a person may be used to determine the usage status of each space on each floor. However, in the following, for the sake of simplification of the explanation, it is assumed that the usage status of each space on each floor is determined by monitoring whether or not the doorway is locked.

For example, when the entrance / exit of the target space on the target floor is locked, the building management system 210 determines that no one is using the space on the floor (it is not being used). Further, the building management system 210 determines, for example, that when the entrance / exit of the target space on the target floor is unlocked, there is a person (in use) using the space on the floor. The usage status of each floor determined by the building management system 210 (information indicating that it is not being used / information indicating that it is being used) is transmitted to the smart window control system 220.

The smart window control system 220 controls the transmittance of the smart windows 120_1 to 120_15. In the smart window control system 220, when it is determined that the usage status of the target space on the floor shown by the dotted line 130 in FIG. 1 is being used by the building management system 210, and the corresponding air conditioning system is in operation. Operates in normal mode.

On the other hand, in the smart window control system 220, it is determined that the usage status of the target space on the floor shown by the dotted line 130 in FIG. 1 is not being used by the building management system 210, and the corresponding air conditioning system is stopped. If so, it operates in predictive mode.

When operating in the prediction mode, the smart window control system 220 acquires ON / OFF information, measured indoor solar radiation amount, measured outdoor solar radiation amount, measured indoor temperature, measured outdoor temperature, and indoor temperature setting from the air conditioning system 230. Further, when operating in the prediction mode, the smart window control system 220 acquires predicted values (predicted temperature transition information, predicted solar radiation amount transition information) of environmental information from the external network 250.

The ON / OFF information is information indicating whether the air conditioning system 230 is operating or stopped (the OFF information further includes information indicating the timing when the air conditioning system 230 is restarted). ). The measured indoor insolation amount is an output value of an indoor insolation amount sensor that measures the amount of insolation in the room. The measured outdoor solar radiation amount is an output value of an outdoor solar radiation amount sensor that measures the outdoor solar radiation amount. The measured indoor temperature is an output value of an indoor temperature sensor that measures the indoor temperature. The measured outdoor temperature is an output value of an outdoor temperature sensor that measures the outdoor temperature. The indoor set temperature is a set temperature of a space whose temperature is controlled by the air conditioning system 230.

In addition, the predicted value of the environmental information includes the predicted temperature transition information and the predicted solar radiation amount transition information. The predicted temperature transition information is, for example, a predicted value that predicts the transition of the outdoor temperature during the stop section of the air conditioning system 230. The predicted solar radiation amount transition information is, for example, a predicted value that predicts the transition of the outdoor solar radiation amount during the stop section of the air conditioning system 230.

When the inside of the floor shown by the dotted line 130 in FIG. 1 is formed by one space, the smart window control system 220 is also composed of one system. On the other hand, when the floor indicated by the dotted line 130 in FIG. 1 is formed by a plurality of spaces and the temperature is controlled by different air conditioning systems in each space, the smart window control system 220 is also a separate system. It is composed.

<Configuration example of smart window control system>
Next, a configuration example of the smart window control system 220 formed on the floor shown by the dotted line 130 in FIG. 1 will be described. FIG. 3 is a diagram showing a configuration example of a smart window control system.

The example of FIG. 3 shows that the floor shown by the dotted line 130 is formed by three spaces (spaces A, B, and shared space). The smart window control system 220_1 is a system formed in the space A, and includes a smart window control device 310, a smart window 120_11, and a smart window 120_1.

On the other hand, the smart window control system 220_2 is a system formed in the space B, and has a smart window control device 320, a smart window 120_13, a smart window 120_14, and a smart window 120_15.

Both the smart window control devices 310 and 320 function as the generation unit 330 and the control unit 340 by executing the smart window control program. The generation unit 330 generates a model (temperature transition prediction model) that reproduces the temperature characteristics of the space A (or space B). The control unit 340 controls the transmittance of the smart window with a predetermined transmittance pattern based on the predicted value of the environmental information in the stop section based on the generated temperature transition prediction model, and the space A (or space). B) Predict the temperature transition. Further, the control unit 340 extracts and extracts the temperature transition in which the temperature of the space A (or the space B) at the timing when the air conditioning system 230 is restarted is the closest to the indoor set temperature among the predicted temperature transitions. Control the transmittance of the smart window so as to realize the temperature transition.

<Example of air conditioning system configuration>
Next, the air conditioning system 230 formed on the floor shown by the dotted line 130 in FIG. 1 will be described. FIG. 4 is a diagram showing a configuration example of an air conditioning system.

The air conditioning system 230_1 is a system formed in the space A. As shown in FIG. 4, the air conditioner system 230_1 includes an air conditioner 410, an indoor temperature sensor 411_1, 411_2, an outdoor solar radiation sensor 412, an indoor solar radiation sensor 413, an outdoor temperature sensor 414, and an outlet 415_1 to 415___. And have.

On the other hand, the air conditioning system 230_2 is a system formed in the space B. As shown in FIG. 4, the air conditioning system 230_2 includes an air conditioner 420, an indoor temperature sensor 421, an outdoor solar radiation sensor 422, an indoor solar radiation sensor 423, an outdoor temperature sensor 424, and outlets 425_1 and 425_2. Have.

<Smart window control device>
Next, the hardware configurations of the smart window control devices 310 and 320 will be described. FIG. 5 is a diagram showing an example of the hardware configuration of the smart window control device. As shown in FIG. 5, the smart window control devices 310 and 320 include a CPU (Central Processing Unit) 501, a ROM (Read Only Memory) 502, and a RAM (Random Access Memory) 503. The CPU 501, ROM 502, and RAM 503 form a so-called computer. Further, the smart window control devices 310 and 320 include an auxiliary storage unit 504, a display unit 505, an input unit 506, a network I / F (Interface) unit 507, and a connection unit 508. The hardware of the smart window control devices 310 and 320 are connected to each other via the bus 509.

The CPU 501 is a device that executes various programs (for example, a smart window control program, etc.) installed in the auxiliary storage unit 504. ROM 502 is a non-volatile memory. The ROM 502 functions as a main storage device that stores various programs, data, and the like necessary for the CPU 501 to execute various programs installed in the auxiliary storage unit 504. Specifically, the ROM 502 stores boot programs such as BIOS (Basic Input / Output System) and EFI (Extensible Firmware Interface).

The RAM 503 is a volatile memory such as a DRAM (Dynamic Random Access Memory) or a SRAM (Static Random Access Memory). The RAM 503 functions as a main storage device that provides a work area that is expanded when various programs installed in the auxiliary storage unit 504 are executed by the CPU 501.

The auxiliary storage unit 504 is an auxiliary storage device that stores various programs and information used when various programs are executed.

The display unit 505 is a display device that displays the internal state of the smart window control devices 310 and 320. The input unit 506 is an input device for the administrator of the smart window control devices 310 and 320 to input various instructions to the smart window control devices 310 and 320.

The network I / F unit 507 is a communication device that connects to the external network 250. The connection unit 508 is a connection device that connects to the LAN 240.

<Functional configuration of smart window control device>
Next, the functional configuration of the smart window control device will be described. Since the smart window control device 310 and the smart window control device 320 have the same configuration, the smart window control device 310 will be described below for the sake of simplification of the description.

(1) Functional configuration of the generation unit of the smart window control device First, the functional configuration of the generation unit 330 of the smart window control device 310 will be described. FIG. 6 is a diagram showing an example of the functional configuration of the generation unit of the smart window control device.

As shown in FIG. 6, the generation unit 330 of the smart window control device 310 includes an actual measurement outdoor temperature acquisition unit 601, an actual measurement outdoor solar radiation amount acquisition unit 602, an actual transmittance acquisition unit 603, a model generation unit 604, and an actual measurement indoor temperature acquisition unit. It has 607.

The actual measurement outdoor temperature acquisition unit 601 acquires transition data for each predetermined time range (for example, 24 hours) of the past actual measurement outdoor temperature measured by the outdoor temperature sensor 414 and inputs it to the model generation unit 604.

The actual measurement outdoor solar radiation amount acquisition unit 602 acquires the transition data for each predetermined time range of the past actual measurement outdoor temperature measured by the outdoor solar radiation amount sensor 412, and inputs it to the model generation unit 604.

The actual transmittance acquisition unit 603 acquires transition data for each predetermined time range of the past control result (transmittance) by the control unit 340 and inputs it to the model generation unit 604.

The model generation unit 604 is an example of the generation unit, and has a temperature transition prediction model 605 and a model evaluation unit 606. The temperature transition prediction model 605 is a machine learning model, and the model generation unit 604 inputs transition data in a predetermined time range of the measured outdoor temperature, the measured outdoor solar radiation amount, and the control result (transmittance), so that the predetermined time Output the temperature transition data in the range. Further, the temperature transition prediction model 605 receives a model parameter change instruction from the model evaluation unit 606 in response to the output of the temperature transition data in a predetermined time range, and performs machine learning by changing the model parameter. ..

The model evaluation unit 606 has an error between the temperature transition data in the predetermined time range output by the temperature transition prediction model 605 and the transition data in the predetermined time range of the past measured indoor temperature notified by the measured indoor temperature acquisition unit 607. Is calculated. Further, the model evaluation unit 606 outputs a change instruction for changing the model parameters to the temperature transition prediction model 605 based on the calculated error.

The actual measurement indoor temperature acquisition unit 607 acquires the transition data of the past actual measurement indoor temperature within a predetermined time range measured by the indoor temperature sensors 411_1 and 411_2, and notifies the model evaluation unit 606 of the transition data.

(2) Flow of model generation processing by the generation unit of the smart window control device Next, the flow of model generation processing by the generation unit 330 of the smart window control device 310 will be described. FIG. 7 is a flowchart showing the flow of the model generation process by the generation unit of the smart window control device.

In step S701, the actually measured outdoor temperature acquisition unit 601 acquires transition data in a predetermined time range of the past actually measured outdoor temperature.

In step S702, the measured outdoor solar radiation amount acquisition unit 602 acquires transition data of the past measured outdoor solar radiation amount in a predetermined time range.

In step S703, the actual transmittance acquisition unit 603 acquires transition data in a predetermined time range of the past control result.

In step S704, the measured indoor temperature acquisition unit 607 acquires transition data of the past measured indoor temperature in a predetermined time range.

In step S705, the model generation unit 604
・ Transition data of past measured outdoor temperature in a predetermined time range and
・ Transition data of past measured outdoor solar radiation in a predetermined time range,
-Transition data in a predetermined time range of past control results is input to the temperature transition prediction model 605. As a result, the temperature transition prediction model 605 outputs the temperature transition data in a predetermined time range.

In step S706, the model evaluation unit 606 calculates an error between the output temperature transition data in the predetermined time range and the acquired past measured indoor temperature transition data in the predetermined time range. Further, the model evaluation unit 606 changes the model parameters of the temperature transition prediction model 605 based on the calculated error. As a result, the model generation unit 604 can perform machine learning on the temperature transition prediction model 605 by using the transition data in the predetermined time range of the past measured room temperature as the correct answer data.

In step S707, the model generation unit 604 determines whether or not machine learning has been performed on the temperature transition prediction model 605 using all the transition data acquired in steps S701 to S704.

If it is determined in step S707 that there is transition data that is not used for machine learning (if No in step S707), the process returns to step S701.

On the other hand, if it is determined in step S707 that machine learning has been performed on the temperature transition prediction model 605 using all the transition data (in the case of Yes in step S707), the process proceeds to step S708.

In step S708, the model generation unit 604 extracts the trained temperature transition prediction model 605 for which machine learning has been completed and sets it in the control unit 340 to end the model generation process.

(3) Functional Configuration of Control Unit of Smart Window Control Device Next, the functional configuration of the control unit 340 included in the smart window control device 310 will be described. FIG. 8 is a first diagram showing an example of the functional configuration of the control unit of the smart window control device.

As shown in FIG. 8, the control unit 340 of the smart window control device 310 includes an air conditioning system operation status acquisition unit 801, a usage status acquisition unit 802, a predicted temperature acquisition unit 803, a predicted solar radiation amount acquisition unit 804, and a transmittance pattern input unit. It has 805. Further, the control unit 340 of the smart window control device 310 includes a model execution unit 806, a set temperature acquisition unit 807, a determination unit 808, a transmittance pattern extraction unit 809, and a transmittance control unit 810.

The air conditioning system operation status acquisition unit 801 acquires ON / OFF information from the air conditioning system 230_1. The usage status acquisition unit 802 acquires the usage status of the space A from the building management system 210.

When the air-conditioning system operation status acquisition unit 801 acquires OFF information indicating that the system is stopped, and the usage status acquisition unit 802 acquires information indicating that the system is not in use, the control unit 340 shifts to the prediction mode. To do.

On the other hand, when the air conditioning system operation status acquisition unit 801 acquires ON information indicating that the air conditioning system is in operation, the control unit 340 shifts to the normal mode.

The predicted temperature acquisition unit 803 is an example of an acquisition unit, and when the control unit 340 shifts to the prediction mode, the predicted temperature transition information in the prediction mode section is acquired from the external network 250. The prediction mode section is a section specified based on the time when the control unit 340 shifts to the prediction mode and the time when the control unit 340 shifts to the normal mode next. In the present embodiment, the prediction mode section is equal to the stop section of the air conditioning system 230_1. Therefore, in the following, the timing at which the air conditioning system 230_1 restarts will be referred to as "prediction mode section break".

The predicted solar radiation amount acquisition unit 804 is an example of the acquisition unit, and when the control unit 340 shifts to the prediction mode, the predicted solar radiation amount transition information in the prediction mode section is acquired from the external network 250.

The transmittance pattern input unit 805 has a plurality of transmittance transition patterns in a predetermined time range, and by combining the transition patterns, the transmittance transition pattern in the prediction mode section (referred to as “transmittance pattern”). To generate multiple.

The model execution unit 806 is an example of a calculation unit, and a plurality of transmittance patterns are sequentially input to the trained temperature transition prediction model 605 together with the predicted temperature transition information and the predicted solar radiation amount transition information in the prediction mode section. The trained temperature transition prediction model 605 is executed. As a result, the trained temperature transition prediction model 605 sequentially outputs the temperature transition prediction data in the prediction mode section.

The set temperature acquisition unit 807 acquires the indoor set temperature set in the air conditioning system 230_1 from the air conditioning system 230_1 as the temperature setting value of the space A after the prediction mode section.

The determination unit 808 extracts the temperature at the end of the prediction mode section from the plurality of temperature transition prediction data sequentially output from the trained temperature transition prediction model 605, and sets the temperature with the indoor set temperature acquired by the set temperature acquisition unit 807. Calculate the error. Further, the determination unit 808 notifies the transmittance pattern extraction unit 809 of the calculated error.

The transmittance pattern extraction unit 809 is an example of the extraction unit, and extracts the transmittance pattern that minimizes the error notified by the determination unit 808 and notifies the transmittance control unit 810.

When the control unit 340 shifts to the prediction mode, the transmittance control unit 810 waits until the transmittance pattern extraction unit 809 notifies the transmittance pattern. Further, when the transmittance pattern is notified from the transmittance pattern extraction unit 809, the transmittance control unit 810 controls the transmittance of the smart windows 120_11 and 120_12 according to the transmittance pattern. The transmittance control unit 810 continues the control based on the transmittance pattern during the prediction mode section.

<Explanation of mode transition>
Next, the mode transition of the control unit 340 of the smart window control device 310 will be described. FIG. 9 is a diagram showing an example of mode transition of the control unit of the smart window control device.

As shown in FIG. 9, in a state where the building management system 210 notifies the information indicating that the space A is in use and the air conditioning system 230_1 notifies the ON information, the control unit 340 is normally used. Operates in mode. The example of FIG. 9 shows that the control unit 340 operated in the normal mode until "XX month XX day XX hour XX minute".

In the case of the present embodiment, the air conditioning system 230_1 is configured to stop when the last user of the space A leaves and the space A is locked on the day before the holiday.

On the other hand, in the case of the present embodiment, the date and time when the air conditioning system 230_1 is restarted after the holiday is determined in advance (regardless of whether or not the user of the space A unlocks the lock). The example of FIG. 9 shows that the date and time when the air conditioning system 230_1 is restarted is determined to be "YY month YY day YY hour YY minute".

As described above, the OFF information acquired by the air conditioning system operation status acquisition unit 801 also includes the timing when the air conditioning system 230_1 restarts. Therefore, in the control unit 340, based on the OFF information, "YY month YY day YY hour YY minute" (second time) after a predetermined time from "XX month XX day XX hour XX minute" (first time). The section up to can be specified as a prediction mode section operating in the prediction mode.

<Specific example of operation in the prediction mode section>
Next, a specific example of the operation of the control unit 340 in the prediction mode section will be described.

(1) Predicted value of environmental information in the predicted mode section First, a specific example of the predicted temperature transition information in the predicted mode section acquired by the predicted temperature acquisition unit 803 of the control unit 340, and the predicted solar radiation amount acquisition unit of the control unit 340. A specific example of the predicted solar radiation amount transition information in the predicted mode section acquired by 804 will be described.

FIG. 10 is a diagram showing a specific example of the predicted value of the environmental information in the prediction mode section. The example of FIG. 10 shows the case where "XX month XX day XX hour XX minute" is Friday night and "YY month YY day YY hour YY minute" is Monday morning. That is, the case where the section including the two days of Saturday and Sunday, which are holidays, is the prediction mode section is shown.

Of these, FIG. 10A shows a specific example of the predicted temperature transition information in the prediction mode section. According to the example of FIG. 10A, it is predicted that the temperature will decrease until Saturday morning and increase during the daytime on Saturday after "XX month XX day XX hours XX minutes" after the transition to the prediction mode. .. Further, according to the example of FIG. 10A, it is predicted that the temperature will decrease from Saturday evening to Sunday morning and will rise again during the daytime on Sunday. In addition, temperatures are expected to drop from Sunday evening to Monday morning.

According to the example of FIG. 10A, it is predicted that the minimum temperature is lower but the maximum temperature is higher on Saturday than on Sunday.

FIG. 10B shows a specific example of the predicted solar radiation amount transition information in the prediction mode section. According to the example of FIG. 10B, the amount of solar radiation is zero from "XX month XX day XX hour XX minute" after the transition to the prediction mode until Saturday morning, and the solar radiation is sunny during the daytime on Saturday. The amount is expected to be high. Further, according to the example of FIG. 10B, since it is cloudy during the daytime on Sunday, it is predicted that the amount of solar radiation will be lower than that during the daytime on Saturday.

(2) Temperature Transition Prediction in Prediction Mode Section Next, the temperature transition prediction data of the space A in the prediction mode section calculated by the model execution unit 806 of the control unit 340 executing the trained temperature transition prediction model 605. A specific example will be described. FIG. 11 is a diagram showing an example of temperature transition prediction data in the prediction mode section. As described above, the model execution unit 806 has learned by sequentially inputting the predicted temperature transition information, the predicted solar radiation amount transition information, and a plurality of transmittance patterns in the prediction mode section into the trained temperature transition prediction model 605. The temperature transition prediction model 605 is executed. As a result, the trained temperature transition prediction model 605 sequentially outputs the temperature transition prediction data of the space A in the prediction mode section.

In FIG. 11, the dotted line 1110 shows the temperature transition prediction data of the space A when the transmittance pattern that transitions in the state where the temperature of the space A is the highest is input. Further, the dotted line 1120 shows the temperature transition prediction data of the space A when the transmittance pattern that transitions in the state where the temperature of the space A is the lowest is input.

As described above, the temperature of the space A in the "YY month YY day YY hour YY minute" varies depending on the transmittance pattern used in the prediction mode section. Here, in the example of FIG. 11, it is assumed that the temperature indicated by the broken line is set in the air conditioning system 230_1 as the indoor set temperature of the space A at the end of the prediction mode section (“YY month YY day YY hour YY minute”). To do.

Therefore, in the transmittance pattern extraction unit 809 of the control unit 340, the temperature transition prediction in which the temperature of the space A at the end of the prediction mode section (“YY month YY day YY hour YY minute”) is closest to the set temperature indicated by the broken line. The transmittance pattern corresponding to the data (solid line 1130) is extracted.

By controlling the transmittance of the smart windows 120_11 and 120_12 using such a transmittance pattern, the temperature of the space A at the end of the prediction mode section ("YY month YY day YY hour YY minute") is made to match the indoor set temperature. It becomes possible. As a result, the load on the air conditioning system 230_1 when the air conditioning system 230_1 is restarted can be reduced.

<Transmittance control processing in prediction mode>
Next, the flow of the transmittance control process in the prediction mode will be described. FIG. 12 is a first flowchart showing the flow of the transmittance control process in the prediction mode.

In step S1201, the air conditioning system operation status acquisition unit 801 monitors the ON / OFF information notified by the air conditioning system 230_1, and the usage status acquisition unit 802 monitors the usage status of the space A notified by the building management system 210. To do. As a result, the control unit 340 determines whether to operate in the normal mode or the prediction mode. On the other hand, the predicted temperature acquisition unit 803, the predicted solar radiation amount acquisition unit 804, and the transmittance control unit 810 monitor the mode transition of the control unit 340 and determine whether or not the control unit 340 has shifted from the normal mode to the prediction mode. To do.

If it is determined in step S1201 that the mode has not changed from the normal mode to the prediction mode (if No in step S1201), it waits until it is determined that the mode has changed from the normal mode to the prediction mode.

On the other hand, if it is determined in step S1201 that the mode has shifted from the normal mode to the prediction mode (yes in step S1201), the process proceeds to step S1202.

In step S1202, the predicted temperature acquisition unit 803 acquires the predicted temperature transition information in the predicted mode section from the external network 250. Further, the predicted solar radiation amount acquisition unit 804 acquires the predicted temperature transition information in the predicted mode section from the external network 250.

In step S1203, the set temperature acquisition unit 807 acquires the indoor set temperature set in the air conditioning system 230 as the indoor set temperature of the space A after the prediction mode section.

In step S1204, the transmittance pattern input unit 805 selects one of the plurality of transmittance patterns and notifies the model execution unit 806.

In step S1205, the predicted temperature acquisition unit 803 notifies the model execution unit 806 of the acquired predicted temperature transition information. Further, the predicted solar radiation amount acquisition unit 804 notifies the model execution unit 806 of the acquired predicted solar radiation amount transition information. Further, the model execution unit 806 executes the temperature transition prediction model 605 by inputting the predicted temperature transition information, the predicted solar radiation amount transition information, and the transmittance pattern into the temperature transition prediction model 605, and calculates the temperature transition prediction data. ..

In step S1206, the determination unit 808 sets the temperature of the temperature transition prediction data calculated by the model execution unit 806 after the prediction mode section and the indoor set temperature of the space A after the prediction mode section acquired by the set temperature acquisition unit 807. Calculate the error with.

In step S1207, the transmittance pattern input unit 805 determines whether or not the temperature transition prediction data has been calculated for all the transmittance patterns. If it is determined in step S1207 that there is a transmittance pattern for which the temperature transition prediction data has not been calculated (if No in step S1207), the process returns to step S1204.

On the other hand, if it is determined in step S1207 that the temperature transition prediction data has been calculated for all the transmittance patterns, the process proceeds to step S1208.

In step S1208, the transmittance pattern extraction unit 809 extracts the transmittance pattern that minimizes the error and notifies the transmittance control unit 810.

In step S1209, the transmittance control unit 810 starts controlling the transmittance of the smart window by using the transmittance pattern notified by the transmittance pattern extraction unit 809.

In step S1210, the transmittance control unit 810 determines whether or not the prediction mode is continuing. If it is determined in step S1210 that the prediction mode is continuing (yes in step S1210), the process returns to step S1209.

On the other hand, if it is determined in step S1210 that the mode has changed from the prediction mode to the normal mode (No in step S1210), the transmittance control process in the prediction mode is terminated.

<Summary>
As is clear from the above description, the smart window control device according to the first embodiment is
-Controls the transmittance of the smart window provided in the window of the space where the temperature is controlled according to the indoor set temperature by the air conditioning system.
-The stop section from the stop to the restart of the air conditioning system is set as the prediction mode section, and the predicted temperature transition information and the predicted solar radiation amount transition information in the section are acquired from the external network.
-Generate a temperature transition prediction model that predicts the temperature transition in space within a predetermined time range based on the past measured outdoor temperature, the past measured outdoor solar radiation amount, and the past actual transmittance.
-By sequentially inputting a plurality of transmittance patterns together with the predicted temperature transition information and the predicted solar radiation amount transition information into the generated temperature transition prediction model, a plurality of temperature transition prediction data in the prediction mode section are calculated.
-Of the plurality of calculated temperature transition prediction data, the transmittance pattern in which the temperature after the prediction mode section is closest to the indoor set temperature after the prediction mode section is extracted, and the transmittance pattern is used in the prediction mode section. Control the transparency of smart windows.

As described above, in the smart window control device according to the first embodiment, the temperature of the space in the prediction mode section is predicted so that the temperature after the prediction mode section approaches the indoor set temperature after the prediction mode section. The transition is based on the temperature transition. As a result, according to the smart window control device according to the first embodiment, it is possible to reduce the influence of the time lag from the control of the transmittance to the actual change in the temperature inside the building.

As a result, according to the smart window control device according to the first embodiment, it is possible to reduce the load on the air conditioning system when the air conditioning system is restarted after the prediction mode section.

[Second Embodiment]
In the first embodiment, a transmittance pattern is extracted based on the temperature transition prediction data calculated by the temperature transition prediction model 605, and the transparency of the smart window in the prediction mode section is based on the extracted transmittance pattern. The configuration is such that the rate is controlled.

On the other hand, in the second embodiment, the transmittance of the smart window is controlled so that the temperature of the space in the prediction mode section changes according to the temperature transition prediction data calculated by the temperature transition prediction model 605. Hereinafter, the second embodiment will be described focusing on the differences from the first embodiment.

<Functional configuration of the control unit of the smart window control device>
First, the functional configuration of the control unit 340 of the smart window control device 310 will be described. FIG. 13 is a second diagram showing an example of the functional configuration of the control unit of the smart window control device. The difference from FIG. 8 is that, in the case of FIG. 13, it has a temperature transition pattern extraction unit 1301, an actually measured indoor temperature acquisition unit 1302, and a transmittance control unit 1303.

The temperature transition pattern extraction unit 1301 is an example of the extraction unit, and the error between each temperature transition prediction data calculated by inputting a plurality of transmittance patterns into the temperature transition prediction model 605 and the indoor set temperature. Is obtained from the determination unit 808.

Further, the temperature transition pattern extraction unit 1301 extracts the temperature transition prediction data that minimizes the acquired error, and notifies the transmittance control unit 1303 as the temperature transition pattern.

The actual measurement room temperature acquisition unit 1302 acquires the actual measurement room temperature at the current time from the air conditioner 410 and notifies the transmittance control unit 1303.

When the control unit 340 shifts to the prediction mode, the transmittance control unit 1303 waits until the temperature transition pattern extraction unit 1301 notifies the temperature transition pattern. Further, when the temperature transition pattern is notified from the temperature transition pattern extraction unit 1301, the transmittance control unit 1303 controls the transmittance of the smart windows 120_11 and 120_12 according to the temperature transition pattern. Specifically, the transmission rate control unit 1303 compares the measured indoor temperature at the current time with the temperature at the current time in the temperature transition pattern, and the measured indoor temperature at the current time is the current time in the temperature transition pattern. If the temperature is higher than the temperature, the permeability is controlled to be lowered. Further, the transmittance control unit 1303 controls to increase the transmittance when the measured indoor temperature at the current time is lower than the temperature at the current time in the temperature transition pattern.

<Specific example of operation in the prediction mode section>
Next, a specific example of the operation of the control unit 340 in the prediction mode section will be described. FIG. 14 is a diagram showing a specific example of the measured room temperature in the prediction mode section. In FIG. 14, the period from "XX month XX day XX hour XX minute" to "YY month YY day YY hour YY minute" is a prediction mode section. Further, in FIG. 14, the solid line 1130 is a temperature transition pattern notified by the temperature transition pattern extraction unit 1301 (the temperature 1100 after the prediction mode section is a temperature transition pattern that matches the indoor set temperature after the prediction mode section. is there).

On the other hand, the thick solid line 1400 is the measured room temperature from the transition to the prediction mode to the current time. Further, reference numeral 1401 indicates the measured indoor temperature at the current time, and reference numeral 1411 indicates the temperature at the current time in the temperature transition pattern (solid line 1130). In the example of FIG. 14, since the measured indoor temperature (reference numeral 1401) at the current time is lower than the temperature at the current time (reference numeral 1411) in the temperature transition pattern (solid line 1130), the transmittance control unit 1303 increases the transmittance. To control.

As a result, the transmittance control unit 1303 can change the temperature of the space A in the prediction mode section according to the temperature transition pattern (solid line 1130). Then, the temperature at the end of the prediction mode section can be matched with the indoor set temperature at the end of the prediction mode section.

As a result, the load on the air conditioning system when the air conditioning system is restarted after the prediction interval can be reduced.

<Transmittance control processing in prediction mode>
Next, the flow of the transmittance control process in the prediction mode will be described. FIG. 15 is a second flowchart showing the flow of the transmittance control process in the prediction mode. The difference from the flowchart shown in FIG. 12 is steps S1501 to S1505.

In step S1501, the temperature transition pattern extraction unit 1301 extracts the temperature transition pattern that minimizes the error and notifies the transmittance control unit 1303.

In step S1502, the transmittance control unit 1303 starts controlling the transmittance of the smart window with the default transmittance.

In step S1503, the transmittance control unit 1303 determines whether or not a predetermined control cycle has elapsed. If it is determined in step S1503 that the predetermined control cycle has not elapsed (No in step S1503), the process waits until the predetermined control cycle elapses.

On the other hand, if it is determined in step S1503 that the predetermined control cycle has elapsed (yes in step S1503), the process proceeds to step S1504.

In step S1504, the transmittance control unit 1303 compares the measured room temperature at the current time acquired by the measured room temperature acquisition unit 1302 with the temperature at the current time in the temperature transition pattern, and changes the transmittance according to the comparison result. To do.

In step S1505, the transmittance control unit 1303 determines whether or not the prediction mode is continuing. If it is determined in step S1505 that the prediction mode is continuing (yes in step S1505), the process returns to step S1503.

On the other hand, if it is determined in step S1505 that the mode has changed from the prediction mode to the normal mode (No in step S1505), the transmittance control process in the prediction mode is terminated.

<Summary>
As is clear from the above description, the smart window control device according to the second embodiment is
-Controls the transmittance of the smart window provided in the window of the space where the temperature is controlled according to the indoor set temperature by the air conditioning system.
-The stop section from the stop to the restart of the air conditioning system is set as the prediction mode section, and the predicted temperature transition information and the predicted solar radiation amount transition information in the section are acquired from the external network.
-Generate a temperature transition prediction model that predicts the temperature transition in space within a predetermined time range based on the past measured outdoor temperature, the past measured indoor solar radiation amount, and the past actual transmittance.
-By sequentially inputting a plurality of transmittance patterns together with the predicted temperature transition information and the predicted solar radiation amount transition information into the generated temperature transition prediction model, a plurality of temperature transition prediction data in the prediction mode section are calculated.
-Of the plurality of calculated temperature transition prediction data, the temperature transition prediction data in which the temperature after the prediction mode section is closest to the indoor set temperature after the prediction mode section is extracted as the temperature transition pattern. In addition, the transmittance of the smart window in the prediction mode section is controlled by using the temperature transition pattern and the measured room temperature.

As described above, in the smart window control device according to the second embodiment, the temperature of the space in the prediction mode section is changed so that the temperature after the prediction mode section approaches the indoor set temperature after the prediction mode section. Make a transition based on the pattern. As a result, according to the smart window control device according to the second embodiment, it is possible to reduce the influence of the time lag from the control of the transmittance to the actual change in the temperature inside the building.

As a result, according to the smart window control device according to the second embodiment, it is possible to reduce the load on the air conditioning system when the air conditioning system is restarted after the prediction mode section.

[Third Embodiment]
In the first and second embodiments described above, the case where the smart window control device operates in the prediction mode has been described. On the other hand, in the third embodiment, the case where the smart window control device operates in the normal mode will be described. Hereinafter, the third embodiment will be described focusing on the differences from the first and second embodiments.

<Specific example of operation in the normal mode section>
First, a specific example of the operation of the control unit 340 in the normal mode section will be described. FIG. 16 is a first diagram showing an example of temperature transition prediction data in the normal mode section. In the example of FIG. 16, the normal mode section is from "AA month AA day AA hour AA minute" (first time) to "BB month BB day BB hour BB minute" (second time) after a predetermined time. ..

In the third embodiment, the model execution unit 806 sequentially inputs the predicted temperature transition information, the predicted solar radiation amount transition information, and a plurality of transmittance patterns in the normal mode section into the trained temperature transition prediction model 605. The trained temperature transition prediction model 605 is executed. As a result, the trained temperature transition prediction model 605 sequentially outputs the temperature transition prediction data of the space A in the normal mode section.

In FIG. 16, the dotted line 1110 shows the temperature transition prediction data of the space A when the transmittance pattern that transitions in the state where the temperature of the space A is the highest is input. Further, the dotted line 1120 shows the temperature prediction data of the space A when the transmittance pattern that transitions in the state where the temperature of the space A is the lowest is input.

As described above, the temperature transition of the space A in the normal mode section varies depending on the transmittance pattern used in the normal mode section. The transmittance pattern extraction unit 809 of the control unit 340 corresponds to the temperature transition prediction data (solid line 1600) in which the cumulative value of the difference from the indoor set temperature (for example, the area of the gray area in FIG. 16) is the minimum. Extract the transmittance pattern. This is because when the cumulative value of the difference from the indoor set temperature is the minimum, the load in the operating section of the air conditioning system 230_1 can be minimized.

<Transmittance control processing in normal mode>
Next, the flow of the transmittance control process in the normal mode will be described. FIG. 17 is a first flowchart showing the flow of the transmittance control process in the normal mode. The difference from the transmittance control process in the prediction mode shown in FIG. 12 is steps S1701 to S1703, S1704, and S1705.

In step S1701, the air conditioning system operation status acquisition unit 801 monitors the ON / OFF information notified by the air conditioning system 230_1, and the usage status acquisition unit 802 monitors the usage status of the space A notified by the building management system 210. To do. As a result, the control unit 340 determines whether to operate in the normal mode or the prediction mode. On the other hand, the predicted temperature acquisition unit 803, the predicted solar radiation amount acquisition unit 804, and the transmittance control unit 810 monitor the mode transition of the control unit 340, and determine whether or not the control unit 340 has shifted from the prediction mode to the normal mode. To do.

If it is determined in step S1701 that the prediction mode has not shifted to the normal mode (if No in step S1701), it waits until it is determined that the prediction mode has shifted to the normal mode.

On the other hand, if it is determined in step S1701 that the mode has changed from the prediction mode to the normal mode (yes in step S1701), the process proceeds to step S1702.

In step S1702, the predicted temperature acquisition unit 803 acquires the predicted temperature transition information in the normal mode section from the external network 250. Further, the predicted solar radiation amount acquisition unit 804 acquires the predicted temperature transition information in the normal mode section from the external network 250.

In step S1703, the set temperature acquisition unit 807 acquires the indoor set temperature set in the air conditioning system 230 as the indoor set temperature of the space A in the normal mode section.

In step S1704, the determination unit 808 determines the temperature in the normal mode section of the temperature transition prediction data calculated by the model execution unit 806 and the indoor set temperature of the space A in the normal mode section acquired by the set temperature acquisition unit 807. Calculate the cumulative value of the error.

In step S1705, the transmittance pattern extraction unit 809 extracts the transmittance pattern that minimizes the cumulative value of the error and notifies the transmittance control unit 810.

<Summary>
As is clear from the above description, the smart window control device according to the third embodiment is
-Controls the transmittance of the smart window provided in the window of the space where the temperature is controlled according to the indoor set temperature by the air conditioning system.
-The section in which the air conditioning system is operating is set as the normal mode section, and the predicted temperature transition information and the predicted solar radiation amount transition information in the section are acquired from the external network.
-Generate a temperature transition prediction model that predicts the temperature transition in space within a predetermined time range based on the past measured outdoor temperature, the past measured outdoor solar radiation amount, and the past actual transmittance.
-By sequentially inputting a plurality of transmittance patterns together with the predicted temperature transition information and the predicted solar radiation amount transition information into the generated temperature prediction model, a plurality of temperature transition prediction data in the normal mode section is calculated.
-Of the plurality of calculated temperature transition prediction data, the transmittance pattern in which the cumulative value of the difference between the temperature in the normal mode section and the indoor set temperature in the normal mode section is the minimum is extracted, and the transmittance pattern is used. Therefore, the transmittance of the smart window in the normal mode section is controlled.

As described above, in the smart window control device according to the third embodiment, the temperature of the space in the normal mode section is predicted so that the temperature in the normal mode section approaches the indoor set temperature in the normal mode section. The transition is based on the temperature transition. As a result, according to the smart window control device according to the third embodiment, it is possible to reduce the influence of the time lag from the control of the transmittance to the actual change in the temperature inside the building.

As a result, according to the smart window control device according to the third embodiment, the load on the operating section of the air conditioning system can be minimized.

[Fourth Embodiment]
In the third embodiment, it has been described that the indoor set temperature set in the air conditioning system 230 is used as the indoor set temperature of the space A in the normal mode section. However, as the indoor set temperature of the space A in the normal mode section, the modified indoor set temperature obtained by modifying the indoor set temperature set in the air conditioning system 230 may be used.

For example, if it is known in advance that a large number of people will flow in at a predetermined date and time to raise the temperature of the space A, the indoor set temperature at the predetermined date and time is corrected to be lowered. You may control the transparency of the smart window.

That is, if it is known in advance that a change in the internal environment information that affects the temperature in the space will occur at a predetermined date and time, the result can be obtained by correcting the indoor set temperature at the predetermined date and time. The temperature of the room A is kept constant. As a result, the load on the operating section of the air conditioning system can be reduced regardless of changes in the internal environmental information. Hereinafter, the fourth embodiment will be described focusing on the differences from the first to third embodiments.

<Explanation of predicted values of environmental information>
First, the predicted values of environmental information will be explained. In the first to third embodiments, the predicted temperature transition information and the predicted solar radiation amount transition information are exemplified as the predicted values of the environmental information affecting the temperature in the space A. However, the predicted value of the environmental information that affects the temperature in the space A is not limited to the predicted value of the external environmental information, but also includes the predicted value of the internal environmental information.

The predicted value of the internal environmental information affects the temperature of the space A during the normal mode section, such as the inflow of a person into the space A, the inflow of the outside air into the space A, and the outflow of the inside air from the space A. It is a predicted value that predicts an event in the given space A.

FIG. 18 is a diagram showing predicted values of environmental information. As shown in FIG. 18, in the fourth embodiment, the predicted values of the environmental information (predicted temperature transition information, predicted solar radiation amount transition information) in the first to third embodiments are "predicted values of external environmental information". It corresponds to.

On the other hand, the predicted value that predicts the events in the spaces A and B that affect the temperature of the spaces A and B during the normal mode section is referred to as the predicted value of the internal environment information.

<Functional configuration of smart window control device>
Next, the functional configuration of the smart window control device will be described. FIG. 19 is a second diagram showing an example of the functional configuration of the control unit of the smart window control device.

The difference from the functional configuration shown in FIG. 8 is that, in the case of FIG. 19, the function of the set temperature acquisition unit 1901 is different from the function of the set temperature acquisition unit 807 of FIG.

The set temperature acquisition unit 1901 is an example of a correction unit. The set temperature acquisition unit 1901 acquires the indoor set temperature set in the air conditioning system 230_1 from the air conditioning system 230_1 as the indoor set temperature of the space A in the normal mode section. Further, the set temperature acquisition unit 1901 acquires the predicted value of the internal environment information of the space A in the normal mode section from the external network 250. Further, the set temperature acquisition unit 1901 corrects the acquired indoor set temperature based on the predicted value of the acquired internal environment information, and notifies the determination unit 808 of the corrected indoor set temperature.

<Temperature transition prediction in normal mode section>
Next, a specific example of the temperature transition prediction data of the space A in the normal mode section, which is calculated by executing the trained temperature transition prediction model 605 by the model execution unit 806 of the control unit 340, will be described. FIG. 20 is a second diagram showing an example of temperature transition prediction data in the normal mode section.

Of these, FIG. 20A is an example of the predicted value of the internal environment information in the normal mode section, and here shows the number of people flowing into the space A during the normal mode section. As shown in the example of FIG. 20A, from "AA month AA day AA hour AA minute" (first time) to "CC month CC day CC hour CC minute" (second time) after a predetermined time. It is predicted that the maximum value of the number of people flowing into the space A during the period is constant (see reference numerals 2001 to 2003).

On the other hand, it is predicted that the maximum value of the number of people flowing into the space A will change significantly between "CC month CC day CC hour CC minute" and "DD month DD day DD hour DD minute" (code). See 2004).

FIG. 20B shows a predicted value of the fluctuation range of the temperature of the space A, which fluctuates due to the change of the internal environment information in the normal mode section. According to the example of FIG. 20B, when the maximum value of the number of people flowing into the space A is the value shown by reference numerals 2001 to 2003, the fluctuation range of the temperature of the space A due to the inflow of people is zero or It is predicted to be very small.

On the other hand, when the maximum value of the number of people flowing into the space A is the value shown in reference numeral 2004, it is predicted that the temperature of the space A will rise with the inflow of people (see reference numeral 2011).

FIG. 20C shows an example of the corrected indoor set temperature in the normal mode section and the temperature transition prediction data in the normal mode section. As shown in FIG. 20 (c), the temperature from "AA month AA day AA hour AA minute" to "CC month CC day CC hour CC minute" fluctuates due to changes in internal environmental information. The predicted value of the fluctuation range of the temperature in space A is zero or minute. Therefore, the set temperature acquisition unit 1901 notifies the determination unit 808 of the indoor set temperature set in the air conditioning system 230_1 as it is.

On the other hand, between "CC month CC day CC hour CC minute" and "DD month DD day DD hour DD minute", it is predicted that the temperature of space A will rise due to the change in internal environmental information. Has been done. Therefore, the set temperature acquisition unit 1901 corrects the indoor set temperature set in the air conditioning system 230_1 according to the temperature increase range, and notifies the determination unit 808 of the corrected indoor set temperature (see reference numeral 2021). ).

Further, in FIG. 20 (c), the dotted line 1110 is the temperature transition prediction data of the space A when the transmittance pattern that transitions in the state where the temperature of the space A is the highest is input in response to the change of the external environment information. Shown. Further, the dotted line 1120 shows the temperature prediction data of the space A when the transmittance pattern that transitions in the state where the temperature of the space A is the lowest is input in response to the change of the external environment information.

As described above, the temperature transition of the space A in the normal mode section varies depending on the transmittance pattern used in the normal mode section. The transmittance pattern extraction unit 809 of the control unit 340 corresponds to the temperature transition prediction data (solid line 2020) in which the cumulative value of the difference from the corrected indoor set temperature (for example, the area of the gray area in FIG. 20) is minimized. Extract the transmittance pattern. This is because when the cumulative value of the difference from the corrected indoor set temperature is the minimum, the load in the operating section of the air conditioning system 230_1 can be minimized.

<Transmittance control processing in normal mode>
Next, the flow of the transmittance control process in the normal mode will be described. FIG. 21 is a second flowchart showing the flow of the transmittance control process in the normal mode. The difference from the flowchart shown in FIG. 17 is steps S2101 to S2103.

In step S2101, the set temperature acquisition unit 1901 acquires the predicted value of the internal environment information of the space A in the normal mode section from the external network 250.

In step S2102, the set temperature acquisition unit 1901 determines whether or not the temperature of the space A fluctuates due to the change in the internal environment information in the normal mode section. When it is determined in step S2102 that the temperature does not fluctuate (No in step S2102), the set temperature acquisition unit 1901 notifies the determination unit 808 of the indoor set temperature set in the air conditioning system 230_1 as it is, and proceeds to step S1204. ..

On the other hand, if it is determined in step S2102 that the fluctuation occurs (in the case of Yes in step S2102), the process proceeds to step S2103.

In step S2103, the set temperature acquisition unit 1901 corrects the indoor set temperature set in the air conditioning system 230_1 according to the fluctuation range of the temperature of the space A which fluctuates due to the change of the internal environment information. Notify the determination unit 808 of the corrected indoor set temperature.

<Summary>
As is clear from the above description, the smart window control device according to the fourth embodiment is
-Controls the transmittance of the smart window provided in the window of the space where the temperature is controlled according to the indoor set temperature by the air conditioning system.
-The section in which the air conditioning system is operating is set as the normal mode section, and the predicted temperature transition information and the predicted solar radiation amount transition information in the section are acquired from the external network.
-Generate a temperature transition prediction model that predicts the temperature transition in space within a predetermined time range based on the past measured outdoor temperature, the past measured outdoor solar radiation amount, and the past actual transmittance.
-By sequentially inputting a plurality of transmittance patterns together with the predicted temperature transition information and the predicted solar radiation amount transition information into the generated temperature prediction model, a plurality of temperature transition prediction data in the normal mode section is calculated.
-Acquire the change of the internal environment information in the normal mode section from the external network, and predict the fluctuation range of the temperature of the space, which fluctuates due to the change of the internal environment information. In addition, the indoor set temperature in the normal mode section is corrected according to the predicted temperature fluctuation range.
-Of the plurality of calculated temperature transition prediction data, the transmittance pattern in which the cumulative value of the difference between the temperature in the normal mode section and the corrected indoor set temperature in the normal mode section is minimized is extracted. In addition, the transmittance of the smart window in the normal mode section is controlled by using the extracted transmittance pattern.

As described above, in the smart window control device according to the fourth embodiment, the temperature of the space in the normal mode section is set so that the temperature in the normal mode section approaches the corrected indoor set temperature in the normal mode section. , Make a transition based on the predicted temperature transition. As a result, according to the smart window control device according to the fourth embodiment, it is possible to reduce the influence of the time lag from the control of the transmittance to the actual change in the temperature inside the building.

As a result, according to the smart window control device according to the fourth embodiment, the load in the operating section of the air conditioning system can be minimized regardless of the change in the internal environmental information.

[Other Embodiments]
In the first embodiment, the temperature transition prediction model 605 has been described as a machine learning model, but the temperature transition prediction model 605 is not limited to the machine learning model. Any model may be used as long as it is a model showing the correspondence between the measured outdoor temperature, the measured outdoor solar radiation amount, the actual transmittance, and the measured indoor temperature in a predetermined time range.

Further, in the first embodiment, a predetermined transmittance pattern is prepared in advance in the transmittance pattern input unit, and the transmittance pattern extraction unit prepares the transmittance control process from the prepared transmittance patterns in advance. It has been described as extracting the transmittance pattern of 1 used in. However, the method for extracting the transmittance pattern used in the transmittance control process is not limited to this. For example, the transmittance pattern may be extracted by performing an inverse problem analysis based on the error calculated by the determination unit 808.

Further, in the first and second embodiments, it has been described that the smart window control device controls a plurality of smart windows with the same transmittance. However, the control method of the smart window is not limited to this, and for example, each smart window may be configured to be controlled with a different transmittance.

Further, in the third and fourth embodiments, it has been described that the transmittance patterns for a plurality of days in the normal mode section are input to the trained temperature transition prediction model 605. Specifically, in the third embodiment, "AA month AA day AA hour AA minute" is set as the first time, and "BB month BB day BB hour BB minute" is set as the second time. Further, in the fourth embodiment, "AA month AA day AA hour AA minute" is set as the first time, "CC month CC day CC hour CC minute" is set as the second time, or "CC month CC day". "CC hours CC minutes" was set as the first time, and "DD month DD day DD hours DD minutes" was set as the second time. Then, it has been described that each transmittance pattern corresponding to the interval between the first time and the second time is input to the trained temperature transition prediction model 605.

However, the transmittance pattern is not limited to a plurality of days, and may be one day. Alternatively, it may be for a predetermined time.

The present invention is not limited to the configurations shown here, such as combinations with other elements in the configurations and the like described in the above embodiments. These points can be changed without departing from the spirit of the present invention, and can be appropriately determined according to the application form thereof.

120_11-1120_15: Smart window 200: Network system 210: Building management system 220: Smart window control system 230: Air conditioning system 310, 320: Smart window control device 330: Generation unit 340: Control unit 410: Air conditioning device 411_1, 411_2: Indoor Temperature sensor 412: Outdoor solar radiation amount sensor 413: Indoor solar radiation amount sensor 414: Outdoor temperature sensor 601: Actual measurement outdoor temperature acquisition unit 602: Actual measurement outdoor solar radiation amount acquisition unit 603: Actual transmission rate acquisition unit 604: Model generation unit 605: Temperature transition Prediction model 606: Model evaluation unit 607: Actual measurement room temperature acquisition unit 801: Air conditioning system operation status acquisition unit 802: Usage status acquisition unit 803: Prediction temperature acquisition unit 804: Predicted solar radiation amount acquisition unit 805: Transmission pattern input unit 806: Model execution unit 807: Set temperature acquisition unit 808: Judgment unit 809: Permeability pattern extraction unit 810: Permeability control unit 1301: Temperature transition pattern extraction unit 1302: Actually measured indoor temperature acquisition unit 1303: Permeability control unit 1901: Set temperature Acquisition department

Claims (13)

A smart window control device that controls the transmittance of a smart window provided in a window in a space where the temperature is controlled according to a set temperature by an air conditioning system.
An acquisition unit that acquires a predicted value of environmental information outside the space in the section between the first time and the second time after a predetermined time from the first time.
A calculation unit that calculates the temperature transition of the space in the section based on the predicted value of the external environmental information in the section.
A smart window control device including a transmittance control unit that controls the transmittance of the smart window so that the temperature of the space in the section changes based on the calculated temperature transition. The acquisition unit
The predicted value of the external environmental information in the stop section from the first time when the air conditioning system is stopped to the second time when the air conditioning system is restarted is acquired.
The calculation unit
Predicting the temperature transition of the space in the stop section to bring the temperature of the space closer to the set temperature at the second time when the air conditioning system is restarted, and predicting the external environmental information in the stop section. Calculated based on the value
The transmittance control unit is
The smart window control device according to claim 1, wherein the transmittance of the smart window is controlled so that the temperature of the space in the stop section changes based on the calculated temperature transition. It further has a generator that generates a model showing the correspondence between the control results of the outdoor temperature, the amount of outdoor solar radiation, and the transmittance of the smart window in the past predetermined time range and the indoor temperature of the space in the predetermined time range. ,
Based on the correspondence, the calculation unit calculates the temperature transition of the space in the stop section from the predicted value of the external environmental information in the stop section and the pattern of the plurality of transmittances in the stop section. Item 2. The smart window control device according to item 2. When the generation unit inputs the control result of the outdoor temperature, the amount of outdoor solar radiation, and the transmittance of the smart window in the past predetermined time range into the model, the output is the indoor temperature in the past predetermined time range. The smart window control device according to claim 3, wherein the model is generated by learning the model so as to approach the model. Claim 2 or 3 that the predicted value of the external environmental information in the stopped section includes a predicted value of the outdoor temperature transition in the stopped section and a predicted value of the indoor solar radiation amount transition in the stopped section. The smart window control device described in. Of the temperature transitions of the space in the stop section calculated for each of the plurality of transmittance patterns by the calculation unit, the temperature of the space at the second time when the air conditioning system is restarted. Further, it has an extraction unit for extracting a pattern of transmittance that minimizes an error from the set temperature.
The smart window control device according to claim 3, wherein the transmittance control unit controls the transmittance of the smart window in the stop section based on the extracted transmittance pattern. Of the temperature transitions of the space in the stop section calculated for each of the plurality of transmittance patterns by the calculation unit, the temperature of the space at the second time when the air conditioning system is restarted. Further, it has an extraction unit for extracting a temperature transition pattern that minimizes an error from the set temperature.
The smart window control device according to claim 3, wherein the transmittance control unit controls the transmittance of the smart window in the stop section based on the extracted temperature transition pattern. The smart window according to claim 2, wherein the stop section is specified by acquiring information indicating that the air conditioning system has been stopped and a predetermined time when the air conditioning system is restarted next. Control device. The acquisition unit
Acquire the predicted value of the external environmental information in the section where the air conditioning system is operating, and obtain the predicted value.
The calculation unit
Predicted value of the external environmental information in the operating section for the temperature transition of the space in the operating section in order to bring the temperature of the space in the section in which the air conditioning system is operating closer to the set temperature. Calculated based on
The transmittance control unit is
The smart window control device according to claim 1, wherein the transmittance of the smart window is controlled so that the temperature of the space in the operating section changes based on the calculated temperature transition. The ninth aspect of claim 9, further comprising a correction unit that acquires a predicted value of environmental information inside the space in a section in which the air conditioning system is operating and corrects the set temperature of the space in the operating section. Smart window control device. The calculation unit
The temperature transition of the space in the operating section for bringing the temperature of the space in the section in which the air conditioning system is operating closer to the set temperature corrected by the correction unit is changed to the temperature transition in the operating section. The smart window control device according to claim 10, which is calculated based on a predicted value of external environmental information. It is a smart window control method that controls the transmittance of a smart window provided in a window in a space where the temperature is controlled according to a set temperature by an air conditioning system.
An acquisition step of acquiring a predicted value of environmental information outside the space in a section between the first time and a second time after a predetermined time from the first time.
A calculation step of calculating the temperature transition of the space in the section based on the predicted value of the external environmental information in the section, and
A smart window control method including a transmittance control step of controlling the transmittance of the smart window so that the temperature of the space in the section changes based on the calculated temperature transition. For the computer of the smart window control device that controls the transmittance of the smart window provided in the window in the space where the temperature is controlled according to the set temperature by the air conditioning system.
An acquisition step of acquiring a predicted value of environmental information outside the space in a section between the first time and a second time after a predetermined time from the first time.
A calculation step of calculating the temperature transition of the space in the section based on the predicted value of the external environmental information in the section, and
A smart window control program for executing a transmittance control step for controlling the transmittance of the smart window so that the temperature of the space in the section changes based on the calculated temperature transition.

Images