CN113396267B

CN113396267B - Smart window control device, smart window control method, and smart window control program

Info

Publication number: CN113396267B
Application number: CN202080012572.5A
Authority: CN
Inventors: 渡边健太; 小笠原晶子; 岸敦史
Original assignee: Nitto Denko Corp
Current assignee: Nitto Denko Corp
Priority date: 2019-02-08
Filing date: 2020-02-05
Publication date: 2023-08-25
Anticipated expiration: 2040-02-05
Also published as: CN113396267A; JP6893262B2; JP2020128686A

Abstract

The load of the air conditioning system is reduced. A smart window control apparatus for controlling transmittance of a smart window provided in a window portion of a space where temperature control based on a set temperature is performed by an air conditioning system, the smart window control apparatus having: an acquisition unit that acquires a predicted value of environmental information outside the space in a section between a 1 st time and a 2 nd time after a predetermined time from the 1 st time; a calculation unit configured to calculate a temperature change of the space in the section based on a predicted value of the external environmental information in the section; and 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 change.

Description

Smart window control device, smart window control method, and smart window control program

Technical Field

The invention relates to an intelligent window control device, an intelligent window control method and an intelligent window control program.

Background

A smart window control system is known in the past, which is capable of adjusting the amount of sunlight and heat entering a building by applying glass capable of controlling optical characteristics (for example, transmittance) to a window portion of the building such as an office building as a smart window.

According to the smart window control system, for example, the amount of sunlight and heat incident into a building can be reduced in summer and the amount of sunlight and heat incident into a building can be increased in winter, thereby assisting an air conditioning system that performs temperature control in a building. Therefore, the load of the air conditioning system can be reduced.

[ citation document ]

[ patent document ]

[ patent document 1] (Japanese patent application) publication No. 2015-534127

Disclosure of Invention

[ problem to be solved ]

Here, in the case of the smart window control system, a time lag from when the transmittance is controlled to adjust the amount of sunlight and the amount of heat incident into the building to when the temperature in the building is actually changed is large.

For this reason, in order to reduce the load on the air conditioning system, the time lag described above when the transmittance is controlled needs to be considered in advance.

An aspect of the present invention is directed to reducing the load of an air conditioning system.

Technical scheme

According to one aspect, there is provided a smart window control apparatus for controlling transmittance of a smart window provided in a window section of a space in which temperature control based on a set temperature is performed by an air conditioning system, the smart window control apparatus having:

An acquisition unit that acquires a predicted value of environmental information outside the space in a section between a 1 st time and a 2 nd time after a predetermined time from the 1 st time;

a calculation unit configured to calculate a temperature change of the space in the section based on a predicted value of the external environmental information in the section; and

And 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 change.

[ advantageous effects ]

The load of the air conditioning system can be reduced.

Drawings

Fig. 1 is a schematic view of an external appearance structure of a building provided with a smart window.

Fig. 2 is a schematic diagram of an example of a network system configured in a building.

Fig. 3 is a schematic diagram of a configuration example of a smart window control system.

Fig. 4 is a schematic diagram of an exemplary configuration of an air conditioning system.

Fig. 5 is a schematic diagram showing an example of the hardware configuration of the smart window control device.

Fig. 6 is a schematic diagram showing an example of the functional configuration of the generating unit of the smart window control apparatus.

Fig. 7 is a flowchart showing a flow of model generation processing performed by the generation unit of the smart window control apparatus.

Fig. 8 is a view showing an example of a functional configuration of a control unit of the smart window control device.

Fig. 9 is a schematic diagram showing an example of mode transition of the control unit of the smart window control device.

Fig. 10 is a schematic diagram of a specific example of a predicted value of the environmental information within a prediction mode (prediction mode) section.

Fig. 11 is a schematic diagram showing an example of prediction data of a temperature change (also referred to as a temperature transition (temperature transition)) in a prediction mode section.

Fig. 12 is a 1 st flowchart showing a flow of transmittance control processing in the prediction mode.

Fig. 13 is a view showing an example of a functional configuration of a control unit of the smart window control device.

Fig. 14 is a schematic diagram of a specific example of the measured indoor temperature in the prediction mode interval.

Fig. 15 is a 2 nd flowchart showing a flow of transmittance control processing in the prediction mode.

Fig. 16 is a view 1 showing an example of temperature change prediction data in a normal mode (normal mode) interval.

Fig. 17 is a 1 st flowchart showing a flow of the transmittance control processing in the normal mode section.

Fig. 18 is a schematic diagram of predicted values of environmental information.

Fig. 19 is a view of fig. 3 showing an example of a functional configuration of a control unit of the smart window control device.

Fig. 20 is a view of fig. 2 showing an example of temperature change prediction data in the normal mode section.

Fig. 21 is a 2 nd flowchart showing a flow of the transmittance control processing in the normal mode section.

Detailed Description

The embodiments are described below with reference to the drawings. In the present specification and the drawings, constituent elements having substantially the same functional constitution are denoted by the same reference numerals, and repetitive description thereof will be omitted.

[ embodiment 1 ]

< appearance structure of building >)

First, an external appearance structure of a building provided with a smart window will be described. Fig. 1 is a schematic view of an external appearance structure of a building provided with a smart window. As shown in fig. 1, a predetermined surface of a building 110 (e.g., an office building) is provided with a window group 120. In the present embodiment, it is assumed that smart windows 120_11 to 120_15 are provided in floors indicated by broken lines 130.

Smart windows refer to window sections to which glass capable of controlling transmittance is applied. In the present embodiment, the transmittance of glass applied to a smart window may be controlled by electrochromic, PDLC (Polymer dispersed LCs), or gas chrome.

The cross-sectional structure of smart window 120_15 is shown on the right side of fig. 1 and includes multiple layers of glass. In smart window 120-15, the transmittance of glass 140 applied to one of the layers may be controlled. As shown on the right side of fig. 1, the transmittance of the glass 140 can be controlled in the range shown by arrow 150 (e.g., in the range of 10% to 90%). Accordingly, the amount of sunlight and the amount of heat that enter the space of the floor indicated by the broken line 130 of the building 110 can be adjusted.

< construction of network System >, and method for controlling the same

Next, a network system configured in the building 110 will be described. Fig. 2 is a schematic diagram of an example of a network system configured in a building. As shown in fig. 2, the network system 200 has a building management system 210, a smart window control system 220, and an air conditioning system 230. In the network system 200, the respective systems may be connected to each other via LAN (Local Area Network) and 240 so as to be able to communicate with each other.

Building management system 210 is a system that manages security within building 110. In the present embodiment, the building management system 210 can monitor whether or not the entrance of each space of each floor is locked, for example, and can determine the use status of each space of each floor.

The method for determining the use status of each space on each floor by the building management system 210 is not limited to this. For example, the use condition of each space on each floor may be determined by using another sensor (a human sensor or the like) capable of directly or indirectly detecting the presence or absence of a person. In the following, for the sake of simplicity of explanation, it is assumed that the use condition of each space of each floor is determined by monitoring whether or not the doorway is locked, and the explanation is made on this basis.

For example, when the entrance/exit of the target space of the target floor is locked, the building management system 210 may determine that there is no person using the space of the floor (in an unused state (shown as "unused")). For example, when the entrance of the target space of the target floor is not locked, the building management system 210 may determine that a person using the space of the floor exists (a use state (shown as "in use"). It should be noted that the usage status (information indicating the unused state/usage state) of each floor determined by the building management system 210 may be sent to the smart window control system 220.

Smart window control system 220 can control the transmittance of smart windows 120_11-120_15. In the case where the use condition of the target space of the floor indicated by the broken line 130 in fig. 1 is judged to be in the use state by the building management system 210, and the corresponding air conditioning system is operating (shown as "in operation" in the figure), the smart window control system 220 operates in the normal mode.

On the other hand, in the case where the use condition of the target space of the floor indicated by the broken line 130 in fig. 1 is judged to be in an unused state by the building management system 210, and the corresponding air conditioning system is in a stopped state (shown as "stopped" in the figure), the smart window control system 220 operates in accordance with the prediction mode.

The smart window control system 220 may acquire ON/OFF information, measured indoor solar radiation amount, measured outdoor solar radiation amount, measured indoor temperature, measured outdoor temperature, and indoor set temperature from the air conditioning system 230 when operating according to the prediction mode. In addition, the smart window control system 220 may also obtain predicted values of environmental information (predicted temperature change information and predicted solar radiation amount change information) from the external network 250 when operating in a predicted mode.

The ON/OFF information is information indicating whether the air conditioning system 230 is operating or in a stopped state (it should be noted that the OFF information also includes information indicating the time at which the air conditioning system 230 is re-operating (i.e., resumes operation). The measured indoor solar radiation amount is an output value of an indoor solar radiation amount sensor for measuring an indoor solar radiation amount. The actually measured outdoor solar radiation amount means an output value of an outdoor solar radiation amount sensor for measuring an outdoor solar radiation amount. The measured indoor temperature is an output value of an indoor temperature sensor that measures an indoor temperature. The measured outdoor temperature is an output value of an outdoor temperature sensor for measuring the outdoor temperature. The indoor set temperature refers to a set temperature of a space in which the air conditioning system 230 performs temperature control.

Further, the predicted value of the environmental information includes predicted temperature change information and predicted solar radiation amount change information. The predicted temperature change information is, for example, a predicted value obtained by predicting a change in the outdoor temperature in the stop zone of the air conditioning system 230. The predicted solar radiation amount change information is, for example, a predicted value obtained by predicting a change in the outdoor solar radiation amount in the stop zone of the air conditioning system 230.

It should be noted that, in the case where the floor shown by the dotted line 130 in fig. 1 is formed of one space, the smart window control system 220 may be constituted of one system. On the other hand, in the case where the floor shown by the broken line 130 in fig. 1 is formed of a plurality of spaces and each space performs temperature control based on a different air conditioning system, the smart window control system 220 may also be constituted of a respectively different system.

Constituent example of Smart Window control System

Next, a configuration example of the smart window control system 220 formed in the floor shown by the broken line 130 in fig. 1 will be described. Fig. 3 is a schematic diagram of a configuration example of a smart window control system.

Fig. 3 shows an example in which the floor shown by the broken line 130 is formed of three spaces (space A, B and shared space). Smart window control system 220_1 is a system formed in space A therein and has smart window control device 310, smart window 120_11, and smart window 120_12.

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

The smart window control devices 310 and 320 may each function as the generating unit 330 and the control unit 340 by executing a smart window control program. The generating unit 330 may generate a model (temperature change prediction model) for reproducing the temperature characteristics of the space a (or the space B). The control unit 340 may predict the temperature change of the space a (or the space B) in the case of controlling the transmittance of the smart window in accordance with a predetermined transmittance pattern (pattern) based on the generated temperature change prediction model and the predicted value of the environmental information in the stop section. The control unit 340 may extract a temperature change in which the temperature of the space a (or the space B) at which the air conditioning system 230 resumes operation among the predicted temperature changes is closest to the indoor set temperature, and may control the transmittance of the smart window to realize the extracted temperature change.

Constituent example of air Conditioning System

Next, an air conditioning system 230 formed in the floor shown by the broken line 130 in fig. 1 will be described. Fig. 4 is a schematic diagram of an exemplary configuration of an air conditioning system.

Air conditioning system 230_1 is a system formed in space a therein. As shown in fig. 4, air conditioning system 230_1 includes air conditioning device 410, indoor temperature sensors 411_1 and 411_2, outdoor solar radiation sensor 412, indoor solar radiation sensor 413, outdoor temperature sensor 414, and outlets 415_1 to 415_3.

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

< Smart Window control device >)

Next, the hardware configuration of the smart window control devices 310 and 320 will be described. Fig. 5 is a schematic diagram showing an example of the hardware configuration of the smart window control device. As shown in fig. 5, the smart window control device 310, 320 has CPU (Central Processing Unit), ROM (Read Only Memory), 502, RAM (Random Access Memory), 503. The CPU501, ROM502, and RAM503 may form a so-called computer. The smart window control devices 310 and 320 further 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 respective hardware of the smart window control devices 310 and 320 are connected to each other via a bus 509.

The CPU501 is a device for executing various programs (for example, a smart window control program) installed in the auxiliary storage unit 504. ROM502 is a non-volatile memory. The ROM502 can function as a main storage device that stores various programs, data, and the like necessary for the CPU501 to execute the various programs installed in the auxiliary storage unit 504. Specifically, the ROM502 may store a boot program or the like of BIOS (Basic Input/Output System), EFI (Extensible Firmware Interface), or the like.

RAM503 is a volatile memory such as DRAM (Dynamic Random Access Memory) and SRAM (Static Random Access Memory). The RAM503 can function as a main storage device for providing a work area expanded when various programs installed in the auxiliary storage section 504 are executed by the CPU 501.

The auxiliary storage unit 504 is an auxiliary storage device for storing various programs and information used when the various programs are executed.

The display unit 505 is a display device capable of displaying the internal states of the smart window control devices 310 and 320. The input unit 506 is an input device for allowing an administrator of the smart window control device 310, 320 to input various instructions to the smart window control device 310, 320.

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

Functional constitution of intelligent window control device

Next, the functional configuration of the smart window control device will be described. Since the smart window control apparatus 310 and the smart window control apparatus 320 have the same configuration, only the smart window control apparatus 310 will be described below for simplicity of description.

(1) Functional configuration of generating unit of intelligent window control device

First, the functional configuration of the generating unit 330 of the smart window control apparatus 310 will be described. Fig. 6 is a schematic diagram showing an example of the functional configuration of the generating unit of the smart window control apparatus.

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

The measured outdoor temperature acquisition unit 601 may acquire change data for each predetermined time range (for example, 24 hours) of the past measured outdoor temperature measured by the outdoor temperature sensor 414, and may input the change data to the model generation unit 604.

The measured outdoor solar radiation amount acquisition section 602 may acquire change data for each predetermined time range of the past measured outdoor temperature measured by the outdoor solar radiation amount sensor 412, and may input it to the model generation section 604.

The actual-result transmittance obtaining section 603 may obtain the change data for each predetermined time range of the past control result (transmittance) performed by the control section 340, and may input it to the model generating section 604.

The model generating unit 604 is an example of a generating unit, and includes a temperature change prediction model 605 and a model evaluating unit 606. The temperature change prediction model 605 is a machine learning model, and the model generating unit 604 inputs change data of a predetermined time range of the measured outdoor temperature, the measured outdoor solar radiation amount, and the control result (transmittance), thereby outputting temperature change data of the predetermined time range. The temperature change prediction model 605 may perform machine learning by receiving an instruction to change the model parameters from the model evaluation unit 606 based on the output of the temperature change data in the predetermined time range, and changing the model parameters.

The model evaluation unit 606 can calculate an error between the temperature change data in the predetermined time range outputted from the temperature change prediction model 605 and the change data in the predetermined time range of the past measured indoor temperature notified from the measured indoor temperature acquisition unit 607. The model evaluation unit 606 may output a change instruction for changing the model parameter to the temperature change prediction model 605 based on the calculated error.

The measured indoor temperature acquisition unit 607 may acquire change data of a predetermined time range of past measured indoor temperatures measured by the indoor temperature sensors 411_1 and 411_2, and may notify the model evaluation unit 606 of the change data.

(2) Flow of model generation processing performed by generation unit of smart window control device

Next, a flow of the model generation process performed by the generation unit 330 of the smart window control apparatus 310 will be described. Fig. 7 is a flowchart showing a flow of model generation processing performed by the generation unit of the smart window control apparatus.

In step S701, the measured outdoor temperature acquiring unit 601 acquires change data within a predetermined time range of the past measured outdoor temperature.

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

In step S703, the actual-result transmittance acquiring unit 603 acquires change data within a predetermined time range of the past control result.

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

In step S705, the model generation unit 604 generates a model

Change data over a predetermined time frame of the measured outdoor temperature,

Data of the variation of the measured outdoor solar radiation quantity over a predetermined time range, and

change data within a predetermined time range of past control results

A temperature change prediction model 605 is input. Accordingly, the temperature change prediction model 605 may output temperature change data within a predetermined time range.

In step S706, the model evaluation unit 606 calculates an error between the output temperature change data within the predetermined time range and the acquired change data of the predetermined time range of the past measured indoor temperature. Further, the model evaluation unit 606 changes the model parameters of the temperature change prediction model 605 based on the calculated error. Accordingly, the model generating unit 604 can perform machine learning (also referred to as training) on the temperature change prediction model 605, using the change data of the past measured indoor temperature within a predetermined time range as forward solution data (correct answer data).

In step S707, the model generating unit 604 determines whether or not all the change data acquired in steps S701 to S704 are used to machine-learn the temperature change prediction model 605.

In step S707, when it is determined that there is No change data for machine learning (No in step S707), the flow returns to step S701.

On the other hand, in step S707, when it is determined that the temperature change prediction model 605 has been machine-learned using all the change data (Yes in step S707), the flow proceeds to step S708.

In step S708, the model generation unit 604 extracts the temperature change prediction model 605 after completion of the learning of the machine learning (also referred to as training), and sets the model to the control unit 340, thereby ending the model generation process.

(3) Functional constitution of control part of intelligent 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 view showing an example of a functional configuration of a control unit of the smart window control device.

As shown in fig. 8, the control unit 340 of the smart window control apparatus 310 includes an air conditioning system operation state acquisition unit 801, a use state acquisition unit 802, a predicted temperature acquisition unit 803, a predicted solar radiation amount acquisition unit 804, and a transmittance pattern input unit 805. 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 state acquisition unit 801 can acquire ON/OFF information from the air conditioning system 230_1. The usage acquiring section 802 may acquire the usage of the space a from the building management system 210.

When the air conditioning system operation condition acquiring unit 801 acquires OFF information indicating that the air conditioning system is in a stopped state and the use condition acquiring unit 802 acquires information indicating that the air conditioning system is in an unused state, the control unit 340 enters a prediction mode.

ON the other hand, when the air conditioning system operation condition acquisition unit 801 acquires ON information indicating that the operation is underway, the control unit 340 enters the normal mode.

The predicted temperature acquiring unit 803 is an example of an acquiring unit, and the control unit 340 enters the prediction mode to acquire the predicted temperature change information in the prediction mode section from the external network 250. The prediction mode section is a section determined by the time when the control unit 340 enters the prediction mode and the time when the control unit enters the normal mode next time. In the present embodiment, the prediction mode interval is equal to the stop interval of the air conditioning system 230_1. For this reason, the time at which the air conditioning system 230_1 resumes operation is also referred to as "at the end of the prediction mode section" hereinafter.

The predicted solar radiation amount obtaining unit 804 is an example of an obtaining unit, and the control unit 340 enters the prediction mode to obtain the predicted solar radiation amount change information in the prediction mode section from the external network 250.

The transmittance pattern input unit 805 has a plurality of variation patterns of transmittance within a predetermined time range, and by combining the variation patterns, a plurality of variation patterns of transmittance (also referred to as "transmittance patterns") within a prediction mode section can be generated.

The model execution unit 806 is an example of a calculation unit, and allows the learned temperature change prediction model 605 to be executed by sequentially inputting the plurality of transmittance modes, together with the predicted temperature change information and the predicted solar radiation amount change information in the prediction mode section, into the learned temperature change prediction model 605. Accordingly, the learned temperature change prediction model 605 may sequentially output the temperature change prediction data within the prediction mode interval.

The set temperature acquiring unit 807 can acquire the indoor set temperature set in the air conditioning system 230_1 as the temperature set value of the space a at the end of the prediction mode section from the air conditioning system 230_1.

The determination unit 808 may extract the temperature at the end of the prediction mode section from the plurality of temperature change prediction data sequentially output from the temperature change prediction model 605 after learning, and may calculate an error with the indoor set temperature acquired by the set temperature acquisition unit 807. The determination unit 808 may also notify the transmittance pattern extraction unit 809 of the calculated error.

The transmittance pattern extraction unit 809 is an example of an extraction unit, and can extract the transmittance pattern in which the error notified by the determination unit 808 is minimum, and can notify the transmittance control unit 810 of the extracted pattern.

After the control unit 340 enters the prediction mode, the transmittance control unit 810 is in a standby (waiting) state until the transmittance mode is notified from the transmittance mode extracting unit 809. Further, after the transmittance pattern is notified from the transmittance pattern extraction section 809, the transmittance control section 810 can control the transmittance of the smart windows 120_11, 120_12 according to the transmittance pattern. The transmittance control section 810 continuously performs control based on the transmittance mode in the prediction mode interval.

Description of mode transition >

Next, mode transition of the control unit 340 of the smart window control apparatus 310 will be described. Fig. 9 is a schematic diagram showing an example of mode transition of the control unit of the smart window control device.

As shown in fig. 9, the control section 340 operates in the normal mode in a state in which the information indicating that the space a is in use is being notified from the building management system 210 and ON information is being notified from the air conditioning system 230_1. Fig. 9 shows an example in which the control unit 340 operates in the normal mode until "XX month XX day XX time XX minute".

In the case of the present embodiment, it is assumed that the air conditioning system 230_1 is configured to stop operation by the last user of the space a exiting the space a on the day before the rest day and locking the space a.

On the other hand, in the case of the present embodiment, the date and time at which the air conditioning system 230_1 resumes operation after the end of the rest day is preset (irrespective of whether the user of the space a locks (locks the door). Fig. 9 shows an example in which the date and time at which the air conditioning system 230_1 resumes operation is set to "YY month YY day YY time YY score".

As described above, the OFF information acquired by the air conditioning system operation condition acquisition unit 801 also includes the time when the air conditioning system 230_1 is restarted. For this reason, the control unit 340 may determine, based on the OFF information, a section from "XX month XX day XX time XX minute" (time 1) to "YY month YY day YY time YY minute" (time 2) after a predetermined time as a prediction mode section in which the operation is performed in accordance with the prediction mode.

Specific example of actions within prediction mode interval

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

(1) Predictive value of environmental information in prediction mode section

First, a specific example of the predicted temperature change information in the prediction mode section acquired by the predicted temperature acquiring section 803 of the control section 340 and a specific example of the predicted solar radiation amount change information in the prediction mode section acquired by the predicted solar radiation amount acquiring section 804 of the control section 340 will be described.

Fig. 10 is a schematic diagram of a specific example of a predicted value of environmental information within a prediction mode interval. The example of fig. 10 shows the case where "XX month XX day XX time XX score" is the night of friday (friday) and "YY month YY day YY time YY score" is the morning of monday (monday). That is, a case is shown in which the section including the two-day period of the rest day, that is, the Saturday (Saturday) and the sunday (Sunday), is the prediction mode section.

Here, 10a of fig. 10 shows a specific example of the predicted temperature change information within the prediction mode section. As can be seen from the example of 10a of fig. 10, it is predicted that the "XX month XX day XX hour XX minute" after entering the prediction mode decreases the morning air temperature on wednesday and increases the daytime air temperature on wednesday. Further, as is clear from the example of 10a in fig. 10, it is predicted that the morning air temperature decreases from dusk to sunday on Saturday and the daytime air temperature increases again on sunday. In addition, it is also predicted that the air temperature decreases from dusk on the sunday to morning on the sunday.

As is clear from the example of 10a in fig. 10, the minimum air temperature is lower in wednesday than in sunday, but the maximum air temperature is higher.

Fig. 10b shows a specific example of predicted solar radiation amount change information within the prediction mode interval. As can be seen from the example of 10b of fig. 10, it is predicted that the solar radiation amount becomes zero in the morning from "XX month XX day XX time XX minute" to wednesday after entering the prediction mode, and the daytime in wednesday becomes a sunny day, and the solar radiation amount becomes high. Further, as is clear from the example of 10b of fig. 10, it is also predicted that the daytime on the sunday is overcast, so the solar radiation amount becomes lower than the daytime on the Saturday.

(2) Prediction of temperature change within prediction mode interval

Next, a specific example of the temperature change prediction data of the space a in the prediction mode section calculated by the model execution unit 806 of the control unit 340 by executing the learned temperature change prediction model 605 will be described. Fig. 11 is a schematic diagram showing an example of temperature change prediction data in a prediction mode section. As described above, the model execution unit 806 sequentially inputs the predicted temperature change information, the predicted solar radiation amount change information, and the plurality of transmittance modes in the prediction mode section into the learned temperature change prediction model 605, and causes the learned temperature change prediction model 605 to execute. Accordingly, the learned temperature change prediction model 605 can sequentially output the temperature change prediction data of the space a within the prediction mode section.

In fig. 11, a broken line 1110 shows temperature change prediction data of the space a in the case where a transmittance pattern that changes in a state where the temperature of the space a is the highest is input. Further, a broken line 1120 shows temperature change prediction data of the space a in the case where the transmittance pattern that changes in a state where the temperature of the space a is the lowest is input.

In this way, the temperature of the space a at the "YY month YY day YY time YY minute" varies as indicated by the arrow by the transmittance pattern used in the prediction pattern section. Here, in the example of fig. 11, it is assumed that the air conditioning system 230_1 is set to a temperature indicated by a broken line as an indoor set temperature of the space a at the end of the prediction mode section ("YY month YY day YY time YY score").

For this reason, the transmittance pattern extraction unit 809 of the control unit 340 can extract the transmittance pattern corresponding to the temperature change prediction data (solid line 1130) in which the temperature of the space a at the end of the prediction pattern section ("YY month YY day YY minute") is closest to the set temperature shown by the broken line.

By controlling the transmittance of the smart windows 120_11, 120_12 using this transmittance pattern, the temperature of the space a at the end of the prediction mode section ("YY month YY day YY score") can be made to coincide with the indoor set temperature. Therefore, the load of air conditioning system 230_1 when air conditioning system 230_1 is restarted can be reduced.

< transmittance control processing in prediction mode >)

Next, a flow of the transmittance control processing in the prediction mode will be described. Fig. 12 is a 1 st flowchart showing a flow of transmittance control processing in the prediction mode.

In step S1201, the air conditioning system operation condition acquiring unit 801 monitors ON/OFF information notified from the air conditioning system 230_1, and the use condition acquiring unit 802 monitors the use condition of the space a notified from the building management system 210. Accordingly, the control unit 340 determines whether to operate in the normal mode or in the prediction mode. On the other hand, the predicted temperature acquiring section 803, the predicted solar radiation amount acquiring section 804, and the transmittance controlling section 810 monitor the mode transition of the control section 340, and determine whether the control section 340 has transitioned from the normal mode to the predicted mode.

In step S1201, when it is determined that the normal mode has not been shifted to the prediction mode (in the case of No in step S1201), the standby is performed until it is determined that the normal mode has been shifted to the prediction mode.

On the other hand, in step S1201, when it is determined that the normal mode has been shifted to the prediction mode (in the case of Yes in step S1201), the flow advances to step S1202.

In step S1202, the predicted temperature acquiring unit 803 acquires the predicted temperature change information in the prediction mode section from the external network 250. Further, the predicted solar radiation amount obtaining unit 804 obtains the predicted temperature change information in the prediction mode section from the external network 250.

In step S1203, the set temperature acquiring unit 807 acquires the indoor set temperature set in the air conditioning system 230 as the indoor set temperature of the space a at the end of the prediction mode interval.

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

In step S1205, the predicted temperature acquiring unit 803 notifies the model executing unit 806 of the acquired predicted temperature change information. Further, the predicted solar radiation amount acquisition unit 804 notifies the model execution unit 806 of the acquired predicted solar radiation amount change information. The model execution unit 806 inputs the predicted temperature change information, the predicted solar radiation amount change information, and the transmittance pattern into the temperature change prediction model 605, and causes the temperature change prediction model 605 to execute, thereby calculating temperature change prediction data.

In step S1206, the determination unit 808 calculates an error between the temperature at the end of the prediction mode section of the temperature change prediction data calculated by the model execution unit 806 and the indoor set temperature of the space a at the end of the prediction mode section acquired by the set temperature acquisition unit 807.

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

On the other hand, in step S1207, when it is determined that the temperature change prediction data is calculated for all the transmittance modes, the flow advances to step S1208.

In step S1208, the transmittance pattern extraction section 809 extracts a transmittance pattern having the smallest error, and notifies the transmittance control section 810 of the extracted transmittance pattern.

In step S1209, the transmittance control unit 810 starts the control of 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 current (current) mode (here, the prediction mode) is to be maintained. In step S1210, when it is determined that the current prediction mode is to be continuously maintained (Yes in step S1210), the routine returns to step S1209.

On the other hand, in step S1210, when it is determined that the mode has shifted from the prediction mode to the normal mode (in the case of No in step S1210), the transmittance control processing in the prediction mode is ended.

< summary >

As is clear from the above description, the smart window control device according to embodiment 1

Control of transmittance of a smart window provided in a window unit in a space where temperature control is performed by an air conditioning system based on an indoor set temperature;

taking a stop section from the stop operation of the air conditioning system to the restart operation as a prediction mode section, and acquiring predicted temperature change information and predicted solar radiation amount change information in the section from an external network;

generating a temperature change prediction model for predicting a temperature change of the 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;

calculating a plurality of temperature change prediction data in a prediction mode section by sequentially inputting a plurality of transmittance modes together with the predicted temperature change information and the predicted solar radiation amount change information into the generated temperature change prediction model; and

And extracting a transmittance pattern of the calculated plurality of temperature change prediction data, the transmittance pattern having a temperature closest to the indoor set temperature at the end of the prediction mode section, and controlling the transmittance of the smart window in the prediction mode section using the transmittance pattern.

As described above, in the smart window control apparatus according to embodiment 1, the temperature of the space in the prediction mode section is changed in accordance with the predicted temperature change so that the temperature at the end of the prediction mode section approaches the indoor set temperature at the end of the prediction mode section. Accordingly, according to the smart window control apparatus of embodiment 1, the influence of the time lag from the start of the control of the transmittance to the actual change of the temperature in the building can be reduced.

Therefore, according to the smart window control apparatus of embodiment 1, the load of the air conditioning system when the air conditioning system is restarted at the end of the prediction mode interval can be reduced.

[ embodiment 2 ]

In embodiment 1, the transmittance pattern is extracted based on the temperature change prediction data calculated by the temperature change prediction model 605, and the transmittance of the smart window in the prediction mode section is controlled based on the extracted transmittance pattern.

In contrast, in embodiment 2, the transmittance of the smart window is controlled so that the temperature of the space in the prediction mode section changes based on the temperature change prediction data calculated by the temperature change prediction model 605. Embodiment 2 will be described below focusing on differences from embodiment 1.

Functional constitution of control part of intelligent window control device

First, the functional configuration of the control unit 340 of the smart window control apparatus 310 will be described. Fig. 13 is a view showing an example of a functional configuration of a control unit of the smart window control device. The difference from fig. 8 is that the temperature change pattern extraction unit 1301, the measured indoor temperature acquisition unit 1302, and the transmittance control unit 1303 are provided in the case of fig. 13.

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

The temperature change pattern extraction unit 1301 extracts temperature change prediction data in which the acquired error is minimum, and notifies the transmittance control unit 1303 of the temperature change prediction data as a temperature change pattern.

The measured indoor temperature acquiring unit 1302 acquires the measured indoor temperature at the current time from the air conditioner 410, and notifies the transmittance controlling unit 1303 of the acquired indoor temperature.

When the control unit 340 transitions to the prediction mode, the transmittance control unit 1303 waits until the temperature change mode is notified from the temperature change mode extraction unit 1301. After the temperature change pattern is notified from the temperature change 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 change pattern. Specifically, the transmittance control unit 1303 compares the measured indoor temperature at the current time with the temperature at the current time in the temperature change mode, and performs control to reduce the transmittance when the measured indoor temperature at the current time is higher than the temperature at the current time in the temperature change mode. When the measured indoor temperature at the current time is lower than the temperature at the current time in the temperature change mode, the transmittance control unit 1303 performs control to increase the transmittance.

Specific example of actions within prediction mode interval

Next, a specific example of the operation of the control unit 340 in the prediction mode section will be described. Fig. 14 is a schematic diagram of a specific example of the measured indoor temperature in the prediction mode interval. In fig. 14, the period from "XX month XX day XX time XX minute" to "YY month YY day YY time YY minute" is a prediction mode interval. In fig. 14, a solid line 1130 is a temperature change pattern (a temperature change pattern in which the temperature 1100 at the end of the prediction mode section coincides with the indoor set temperature at the end of the prediction mode section) notified from the temperature change pattern extraction unit 1301.

On the other hand, the thick solid line 1400 is the measured indoor temperature from the transition to the prediction mode to the current time. Note that reference numeral 1401 denotes an actual indoor temperature at the current time, and reference numeral 1411 denotes a temperature at the current time in the temperature change pattern (solid line 1130). In the example of fig. 14, since the measured indoor temperature at the current time (symbol 1401) is lower than the temperature at the current time (symbol 1411) of the temperature change pattern (solid line 1130), the transmittance control unit 1303 performs control to increase the transmittance.

Accordingly, the transmittance control unit 1303 can change the temperature of the space a in the prediction mode section based on the temperature change mode (solid line 1130). In addition, the temperature at the end of the prediction mode section may be matched with the indoor set temperature at the end of the prediction mode section.

Therefore, the load of the air conditioning system when the air conditioning system is restarted at the end of the prediction interval can be reduced.

< transmittance control processing in prediction mode >)

Next, a flow of the transmittance control processing in the prediction mode will be described. Fig. 15 is a 2 nd flowchart showing a flow of transmittance control processing in the prediction mode. The difference from the flowchart shown in fig. 12 is in steps S1501 to S1505.

In step S1501, the temperature change pattern extraction unit 1301 extracts a temperature change pattern having the smallest error, and notifies the transmittance control unit 1303 of the temperature change pattern.

In step S1502, the transmittance control unit 1303 starts control of the transmittance of the smart window by using the default transmittance.

In step S1503, the transmittance control unit 1303 determines whether or not a predetermined control period has elapsed. In step S1503, when it is determined that the predetermined control period has not elapsed (in the case of No in step S1503), the standby is performed until the predetermined control period has elapsed.

On the other hand, in step S1503, when it is determined that the predetermined control period has elapsed (in the case of Yes in step S1503), the routine proceeds to step S1504.

In step S1504, the transmittance control unit 1303 compares the measured indoor temperature at the current time acquired by the measured indoor temperature acquisition unit 1302 with the temperature at the current time of the temperature change pattern, and changes the transmittance according to the comparison result.

In step S1505, the transmittance control unit 1303 determines whether or not to continue maintaining the prediction mode. In step S1505, when it is determined that the prediction mode is to be continuously maintained (in the case of Yes in step S1505), the routine returns to step S1503.

On the other hand, in step S1505, when it is determined that the mode has been shifted from the prediction mode to the normal mode (in the case of No in step S1505), the transmittance control processing in the prediction mode is ended.

< summary >

As is clear from the above description, the smart window control device according to embodiment 2

Generating a temperature change prediction model for predicting a temperature change of the 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;

sequentially inputting the plurality of transmittance modes together with the predicted temperature change information and the predicted solar radiation amount change information into the generated temperature change prediction model, and calculating a plurality of temperature change prediction data in a prediction mode section; and

And extracting temperature change prediction data of an indoor set temperature at which a temperature at the end of the prediction mode section is closest to the end of the prediction mode section from the calculated plurality of temperature change prediction data, and using the temperature change pattern and the measured indoor temperature as a temperature change pattern, and controlling transmittance of the smart window in the prediction mode section.

As described above, in the smart window control apparatus according to embodiment 2, the temperature of the space in the prediction mode section is changed based on the temperature change pattern so that the temperature at the end of the prediction mode section approaches the indoor set temperature at the end of the prediction mode section. Accordingly, according to the smart window control apparatus of embodiment 2, the influence of time lag from the start of control of transmittance to the actual change of temperature in the building can be reduced.

Therefore, according to the smart window control apparatus of embodiment 2, the load of the air conditioning system when the air conditioning system is restarted at the end of the prediction mode interval can be reduced.

[ embodiment 3 ]

In the above embodiments 1 and 2, description is made of the case where the smart window control apparatus operates in the prediction mode. In contrast, in embodiment 3, a case where the smart window control device operates in the normal mode will be described. Embodiment 3 will be described below focusing on differences from embodiments 1 and 2.

Specific example of actions within the Normal mode Interval

First, a specific example of the operation of the control unit 340 in the normal mode section will be described. Fig. 16 is a view of fig. 1 showing an example of temperature change prediction data in the normal mode section. In the example of fig. 16, the period from "AA month AA day AA score" (time 1) to "BB month BB day BB score" (time 2) after a predetermined time is the normal mode section.

In embodiment 3, the model execution unit 806 sequentially inputs the predicted temperature change information, the predicted solar radiation amount change information, and the plurality of transmittance modes in the normal mode section into the learned temperature change prediction model 605, and causes the learned temperature change prediction model 605 to execute. Accordingly, the learned temperature change prediction model 605 can sequentially output the temperature change prediction data of the space a in the normal mode section.

In fig. 16, a broken line 1110 shows temperature change prediction data of the space a in the case where a transmittance pattern that changes in a state where the temperature of the space a is the highest is input. Further, a broken line 1120 shows temperature prediction data of the space a in the case where the transmittance pattern that changes in a state where the temperature of the space a is the lowest is input.

In this way, by the transmittance mode used in the normal mode section, a deviation occurs in the temperature change of the space a in the normal mode section. The transmittance pattern extraction unit 809 of the control unit 340 extracts a transmittance pattern corresponding to temperature change prediction data (solid line 1600) in which the integrated value of the difference (difference) between the indoor set temperatures (for example, the area of the gray region in fig. 16) is the smallest. This is because, when the integrated value of the difference from the indoor set temperature is the smallest, the load in the section where the air conditioning system 230_1 operates can be minimized.

< transmittance control Process in Normal mode >)

Next, a flow of the transmittance control processing in the normal mode will be described. Fig. 17 is a 1 st flowchart showing a flow of the transmittance control processing in the normal mode. The difference from the transmittance control processing in the prediction mode shown in fig. 12 is in steps S1701 to S1703, S1704, and S1705.

In step S1701, the air conditioning system operation status acquisition unit 801 monitors ON/OFF information notified by the air conditioning system 230_1, and the use status acquisition unit 802 monitors the use status of the space a notified by the building management system 210. Accordingly, the control part 340 can determine whether to operate in the normal mode or the prediction mode. On the other hand, the predicted temperature acquiring section 803, the predicted solar radiation amount acquiring section 804, and the transmittance controlling section 810 monitor the mode transition of the control section 340, and determine whether the control section 340 has transitioned from the predicted mode to the normal mode.

In step S1701, when it is determined that the mode has not been changed from the prediction mode to the normal mode (in the case of No in step S1701), the standby is performed until it is determined that the mode has been changed from the prediction mode to the normal mode.

On the other hand, in step S1701, when it is determined that the mode has been shifted from the prediction mode to the normal mode (in the case of Yes in step S1701), the flow advances to step S1702.

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

In step S1703, the set temperature acquiring 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 calculates an integrated value of the error between the temperature in the normal mode section of the temperature change 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.

In step S1705, the transmittance pattern extraction unit 809 extracts a transmittance pattern in which the cumulative value of the errors is minimum, and notifies the transmittance control unit 810 of the extracted transmittance pattern.

< summary >

As is clear from the above description, the smart window control device according to embodiment 3

Transmittance of a smart window provided in a window portion in a space where temperature control is performed by an air conditioning system based on an indoor set temperature;

taking the section where the air conditioning system works as a normal mode section, and acquiring predicted temperature change information and predicted solar radiation amount change information in the section from an external network;

Sequentially inputting the plurality of transmittance modes together with the predicted temperature change information and the predicted solar radiation amount change information into the generated temperature prediction model, and calculating a plurality of temperature change prediction data in a normal mode section; and

And extracting a 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 smallest from the calculated plurality of temperature change prediction data, and controlling the transmittance of the smart window in the normal mode section using the transmittance pattern.

In this way, in the smart window control apparatus according to embodiment 3, the temperature of the space in the normal mode zone is changed based on the predicted temperature change so that the temperature in the normal mode zone approaches the indoor set temperature in the normal mode zone. Accordingly, according to the smart window control apparatus of embodiment 3, the influence of the time lag from the start of the control of the transmittance to the actual change of the temperature in the building can be reduced.

Therefore, according to the smart window control apparatus of embodiment 3, the load in the section where the air conditioning system operates can be reduced.

[ embodiment 4 ]

In embodiment 3, a case is described in which 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 zone. However, the indoor set temperature that has been set in the air conditioning system 230, which is the indoor set temperature of the space a in the normal mode section, may be corrected, and then the corrected indoor set temperature may be used.

For example, if it is known in advance that a large number of persons will enter the space a at a predetermined date and time, the transmittance of the smart window can be controlled by correcting the indoor set temperature at the predetermined date and time in a decreasing direction.

That is, when it is known in advance that a change in the internal environment information that affects the temperature in the space is to occur at a predetermined date and time, the temperature of the room a can be kept constant by correcting the indoor set temperature at the predetermined date and time. Accordingly, the load in the operation section of the air conditioning system can be reduced regardless of the change in the internal environment information. Embodiment 4 will be described below focusing on differences from embodiments 1 to 3.

Description of the predicted value of Environment information

First, a predicted value of environmental information will be described. In embodiments 1 to 3, as predicted values of environmental information that can affect the temperature in the space a, predicted temperature change information and predicted solar radiation amount change information are exemplified. However, the predicted value of the environmental information that can affect the temperature in the space a is not limited to the predicted value of the external environmental information, and includes the predicted value of the internal environmental information.

The predicted value of the internal environment information is, for example, a predicted value obtained by predicting a phenomenon in the space a that can affect the temperature of the space a in a normal mode section, such as a person entering the space a, outside air entering the space a, and inside air exiting the space a.

Fig. 18 is a schematic diagram of predicted values of environmental information. As shown in fig. 18, in embodiment 4, the predicted values of the environmental information (predicted temperature change information and predicted solar radiation amount change information) in embodiments 1 to 3 correspond to "predicted values of the external environmental information".

On the other hand, a predicted value obtained by predicting a phenomenon in the space A, B that can affect the temperatures of the space a and the space B in the normal mode section is referred to as a predicted value of the internal environment information.

Functional constitution of intelligent window control device

Next, the functional configuration of the smart window control device will be described. Fig. 19 is a view showing an example of a functional configuration of a control unit of the smart window control device.

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

The set temperature acquisition unit 1901 is an example of a correction unit. The set temperature acquisition unit 1901 can acquire, from the air conditioning system 230_1, an indoor set temperature that has been set in the air conditioning system 230_1 as an indoor set temperature of the space a in the normal mode section. Further, the set temperature acquisition unit 1901 may acquire a predicted value of the internal environment information of the space a in the normal mode section from the external network 250. The setting temperature acquiring unit 1901 may correct the acquired indoor setting temperature based on the predicted value of the acquired internal environment information, and notify the judging unit 808 of the corrected indoor setting temperature.

< prediction of temperature Change within Normal mode Interval >)

Next, a specific example of the temperature change prediction data of the space a in the normal mode section calculated by the model execution unit 806 of the control unit 340 by executing the learned temperature change prediction model 605 will be described. Fig. 20 is a view of fig. 2 showing an example of temperature change prediction data in the normal mode section.

Here, 20a of fig. 20 is an example of a predicted value of the internal environment information in the normal mode section, and here, the number of people entering the space a in the normal mode section is shown. As shown in the example of 20a of fig. 20, it is predicted that the maximum number of people who enter the space a is constant in the period from "AA month AA day AA score" (time 1) to "CC month CC day CC time CC score" (time 2) after a predetermined time (see reference numerals 2001 to 2003).

On the other hand, it is predicted that the maximum number of people who enter the space a varies greatly from the "CC month CC day CC hour CC minute" to the "DD month DD day DD minute" (see symbol 2004).

Fig. 20b shows a predicted value of the range of the temperature fluctuation 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 20b of fig. 20, it is predicted that when the maximum value of the number of persons entering the space a is the value indicated by symbols 2001 to 2003, the range of variation in the temperature of the space a accompanying the entrance of the person is zero or small.

On the other hand, it is predicted that when the maximum value of the number of persons entering the space a is a value indicated by a symbol 2004, the temperature of the space a increases with the entry of the persons (see a symbol 2011).

Fig. 20c shows an example of the corrected indoor set temperature in the normal mode section and the temperature change prediction data in the normal mode section. As shown in 20c of fig. 20, the predicted value of the temperature fluctuation range of the space a, which fluctuates due to the change of the internal environment information, is zero or small in the period from "AA month AA time AA score" to "CC month CC time CC score". For this reason, the set temperature acquiring unit 1901 may notify the determining unit 808 of the indoor set temperature set in the air conditioning system 230_1 as it is.

On the other hand, it is predicted that the temperature of the space a increases due to a change in the internal environment information in a period from the start of the CC-month CC-day CC-hour CC division to the DD-month DD-day DD division. For this purpose, the setting temperature acquiring unit 1901 may correct the indoor setting temperature set in the air conditioning system 230_1 according to the temperature rise, and then notify the determination unit 808 of the corrected indoor setting temperature (see reference numeral 2021).

In fig. 20c, a broken line 1110 shows temperature change prediction data of the space a when the transmittance pattern that changes in a state where the temperature of the space a is the highest is inputted with respect to the change of the external environment information. The broken line 1120 shows temperature prediction data of the space a in the case where the transmittance pattern that changes in a state where the temperature of the space a is the lowest is input with respect to the change in the external environment information.

In this way, the temperature change of the space a in the normal mode section is biased by the transmittance mode used in the normal mode section. The transmittance pattern extraction unit 809 of the control unit 340 extracts a transmittance pattern corresponding to temperature change prediction data (solid line 2020) in which the cumulative value of the difference between the corrected indoor set temperatures (for example, the area of the gray area in fig. 20) is the smallest. This is because, when the integrated value of the difference from the corrected indoor set temperature is the smallest, the load in the operation section of the air conditioning system 230_1 can be minimized.

< transmittance control Process in Normal mode >)

Next, a flow of the transmittance control processing in the normal mode will be described. Fig. 21 is a 2 nd flowchart showing a flow of the transmittance control processing in the normal mode. The difference from the flowchart shown in fig. 17 is in steps S2101 to S2103.

In step S2101, the set temperature acquiring unit 1901 acquires a 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 acquiring unit 1901 determines whether or not the temperature of the space a in the normal mode section fluctuates due to a change in the internal environment information. When it is determined in step S2102 that No fluctuation occurs (in the case of 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 the flow proceeds to step S1204.

On the other hand, when it is determined in step S2102 that a change is to be made (in the case of Yes in step S2102), the flow advances to step S2103.

In step S2103, the set temperature acquiring unit 1901 corrects the indoor set temperature set in the air conditioning system 230_1 based on the range of temperature fluctuation of the space a to be varied due to the change of the internal environment information, and then notifies 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 embodiment 4

taking a section in which the air conditioning system is operated as a normal mode section, and acquiring predicted temperature change information and predicted solar radiation amount change information in the section from an external network;

sequentially inputting the plurality of transmittance modes together with the predicted temperature change information and the predicted solar radiation amount change information into the generated temperature prediction model, and calculating a plurality of temperature change prediction data in a normal mode section;

Acquiring a change in internal environment information in a normal mode section from an external network, predicting a fluctuation range of a temperature of a space that fluctuates due to the change in the internal environment information, and correcting an indoor set temperature in the normal mode section based on the predicted fluctuation range of the temperature; and

And extracting a 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 the minimum from the calculated plurality of temperature change prediction data, and then controlling the transmittance of the smart window in the normal mode section using the extracted transmittance pattern.

In this way, in the smart window control apparatus according to embodiment 4, the temperature of the space in the normal mode zone is changed based on the predicted temperature change so that the temperature in the normal mode zone approaches the corrected indoor set temperature in the normal mode zone. Accordingly, according to the smart window control apparatus of embodiment 4, the influence of the time lag from the start of the control of the transmittance to the actual change of the temperature in the building can be reduced.

Therefore, according to the smart window control apparatus of embodiment 4, the load in the operation section of the air conditioning system can be reduced regardless of the change in the internal environment information.

Other embodiments

In embodiment 1, the case where the temperature change prediction model 605 is a machine learning model has been described, but the temperature change prediction model 605 is not limited to the machine learning model. Any model may be used as long as it can represent the correspondence relationship between the measured outdoor temperature, the measured outdoor solar radiation amount, and the actual transmittance and the measured indoor temperature within a predetermined time range.

In embodiment 1, a case where a predetermined transmittance pattern is prepared in advance in the transmittance pattern input unit, and the transmittance pattern extraction unit extracts one transmittance pattern used in the transmittance control process from among the transmittance patterns prepared in advance is described. However, the extraction method of the transmittance pattern used in the transmittance control processing is not limited thereto. For example, the transmittance pattern may be extracted by performing inverse problem analysis based on the error calculated by the determination unit 808.

In embodiments 1 and 2, a case where the smart window control device is a plurality of smart windows and controls the smart windows using the same transmittance will be described. However, the control method of the smart window is not limited to this, and for example, the control may be performed by using different transmittances for each smart window.

In embodiments 3 and 4, a case where a transmittance pattern of several days (days) in the normal mode interval is input to the learned temperature change prediction model 605 is described. Specifically, in embodiment 3, the "AA month AA day AA time AA score" is set as time 1, and the "BB month BB day BB time BB score" is set as time 2. In embodiment 4, the "AA month AA day AA time AA score" is defined as time 1, the "CC month CC day CC time CC score" is defined as time 2, or the "CC month CC day CC time CC score" is defined as time 1, and the "DD month DD day DD score" is defined as time 2. Next, a case will be described in which the transmittance patterns corresponding to the sections between the 1 st time and the 2 nd time are input into the learned temperature change prediction model 605.

However, the transmittance mode is not limited to the transmittance mode within several days, and may be the transmittance mode within one day. Alternatively, the transmittance pattern may be predetermined for several or one hour.

The present invention is not limited to the configurations and the like described in the above embodiments, but is not limited to the configurations shown here, which can be combined with other elements and the like. In this regard, the determination may be appropriately made according to the application form thereof within a range not departing from the gist of the present invention.

The present application claims priority based on the application of Japanese patent application No. 2019-021863 and Japanese patent application No. 2020-013263 of the application of month 2 and 30 of the year 2020, and the contents of both Japanese patent applications are incorporated by reference in their entirety.

[ description of reference numerals ]

120_11 to 120_15: intelligent window

200: network system

210: building management system

220: intelligent window control system

230: air conditioning system

310. 320: intelligent window control device

330: generating part

340: control unit

410: air conditioner

411_1, 411_2: indoor temperature sensor

412: outdoor solar radiation sensor

413: indoor solar radiation sensor

414: outdoor temperature sensor

601: actually measured outdoor temperature acquisition unit

602: actually measured outdoor solar radiation quantity acquisition part

603: actual result transmittance obtaining unit

604: model generating unit

605: temperature change prediction model

606: model evaluation unit

607: actually measured indoor temperature acquisition unit

801: air conditioning system operation condition acquisition unit

802: service condition acquisition unit

803: predicted temperature acquiring unit

804: predicted solar radiation amount acquisition unit

805: transmittance mode input unit

806: model execution unit

807: set temperature acquisition unit

808: determination unit

809: transmittance pattern extraction unit

810: transmittance control unit

1301: temperature change pattern extraction unit

1302: actually measured indoor temperature acquisition unit

1303: transmittance control unit

1901: set temperature acquisition unit

Claims

1. A smart window control apparatus for controlling transmittance of a smart window provided in a window portion of a space where temperature control based on a set temperature is performed by an air conditioning system, the smart window control apparatus having:

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 change,

wherein the acquiring unit acquires a predicted value of external environmental information in a stop section from the 1 st time when the air conditioning system is stopped to the 2 nd time when the air conditioning system is restarted,

The predicted value of the external environmental information in the stop zone includes a predicted value of a temperature change of the outside of the room in the stop zone and a predicted value of a solar radiation amount change of the inside of the room in the stop zone,

the smart window control device further has:

a generation unit configured to generate a model indicating a correspondence relationship between an outdoor temperature, an outdoor solar radiation amount, and a transmittance control result of the smart window in a predetermined time range in the past and an indoor temperature of the space in the predetermined time range,

wherein the calculation unit calculates the temperature change of the space in the stop section based on the predicted value of the external environmental information in the stop section and the pattern of the plurality of transmittances in the stop section, according to the correspondence relation.

2. The smart window control device of claim 1, wherein,

the generation unit generates the model by training the model so that an output when a control result of an outdoor temperature, an outdoor solar radiation amount, and a transmittance of the smart window in the predetermined time range in the past is input to the model approaches an indoor temperature in the predetermined time range in the past.

3. The smart window control device of claim 1, further comprising:

an extracting unit configured to extract a transmittance pattern in which an error between the temperature of the space at the 2 nd time point at which the air conditioning system is restarted and the set temperature is minimized among the temperature changes of the space in the stop section calculated by the calculating unit for each of the plurality of transmittance patterns,

wherein the transmittance control unit controls the transmittance of the smart window in the stop section according to the extracted transmittance pattern.

4. The smart window control device of claim 1, further comprising:

an extracting unit configured to extract a pattern of temperature change in which an error between the temperature of the space at the 2 nd time point at which the air conditioning system is restarted and the set temperature is minimized among the temperature changes of the space in the stop section calculated by the calculating unit for the plurality of patterns of transmittance,

wherein the transmittance control unit controls the transmittance of the smart window in the stop section according to the extracted pattern of temperature change.

5. The smart window control device of claim 1, wherein,

The stop section is determined by acquiring information indicating that the air conditioning system has stopped and a preset time at which the air conditioning system is next re-operated.

6. The smart window control device of claim 1, wherein,

the acquiring section acquires a predicted value of the external environmental information in an interval in which the air conditioning system operates,

the calculation unit calculates a temperature change of the space in the operating section for bringing the temperature of the space in the operating section to the set temperature based on a predicted value of the external environmental information in the operating section of the air conditioning system,

the transmittance control unit controls the transmittance of the smart window so that the temperature of the space in the operating section changes based on the calculated temperature change.

7. The smart window control device of claim 6, further comprising:

and a correction unit that acquires a predicted value of environmental information in the space in a section in which the air conditioning system is operated, and corrects the set temperature of the space in the section in which the air conditioning system is operated.

8. The smart window control device of claim 7, wherein,

The calculation unit calculates a temperature change of the space in the operating section for making the temperature of the space in the operating section close to the set temperature corrected by the correction unit, based on a predicted value of the external environmental information in the operating section of the air conditioning system.

9. A smart window control method for controlling transmittance of a smart window provided in a window portion of a space where temperature control based on a set temperature is performed by an air conditioning system, the smart window control method comprising:

an acquisition step of acquiring a predicted value of environmental information outside the space in a section between a 1 st time and a 2 nd time after a predetermined time from the 1 st time;

a calculation step of calculating a temperature change of the space in the section according to a predicted value of the external environmental information in the section; and

A transmittance control step of controlling transmittance of the smart window so that a temperature of the space within the section changes based on the calculated temperature change,

wherein in the acquiring step, a predicted value of the external environment information in a stop section from the 1 st time when the air conditioning system is stopped to the 2 nd time when the air conditioning system is restarted is acquired,

the smart window control method further has:

a generation step of generating a model showing a correspondence relationship between an outdoor temperature, an outdoor solar radiation amount, and a result of control of transmittance of the smart window in a predetermined time range in the past and an indoor temperature of the space in the predetermined time range,

wherein in the calculating step, a temperature change of the space in the stop section is calculated based on a predicted value of the external environmental information in the stop section and a pattern of a plurality of transmittances in the stop section, according to the correspondence relation.

10. A smart window control program causes a computer of a smart window control device, which controls transmittance of a smart window provided in a window section of a space where temperature control based on a set temperature is performed by an air conditioning system, to execute:

the smart window control program further causes the computer to perform: