JP5635220B1 - Heat storage amount prediction device, heat storage amount prediction method and program - Google Patents

Abstract

An object of the present invention is to accurately predict the amount of heat stored in a building. A heat storage amount prediction device 10 stores an actual value of heat storage amount in a database 131, an actual value of outside air temperature and humidity for every hour, and a value related to the number of visitors, and an external air temperature in a prediction model storage unit 134. A prediction model is stored in which values relating to temperature, humidity, and the number of visitors according to are used as explanatory variables, and the amount of stored heat is used as an objective variable. The prediction model estimation unit 115 estimates the regression coefficient of the explanatory variable and the constant of the prediction model based on the actual value of the heat storage amount, the actual value of the outside air temperature, the actual value of the humidity, the value related to the number of visitors, and the prediction model, The predicted temperature acquisition unit 116 acquires the predicted value of the outside air temperature, the predicted humidity acquisition unit 117 acquires the predicted value of the humidity, and the heat storage amount prediction unit 118 uses the regression coefficient, the constant, the predicted value of the outside temperature and the humidity, the visitor The predicted value of the heat storage amount is calculated by applying the predicted value of the number related value to the prediction model.

Description

  The present invention relates to a heat storage amount prediction device, a heat storage amount prediction method, and a program.

  In order to efficiently operate store cooling, it is necessary to accurately predict the amount of heat stored in the store. For example, in Patent Document 1, the heat load is predicted using the amount of solar radiation, the outside air temperature, and the room temperature.

Japanese Patent Publication No. 60-24889

  However, in Patent Document 1, it is necessary to acquire data on the amount of solar radiation, but the data on the amount of solar radiation cannot be easily acquired for both the actual value and the predicted value.

  This invention is made | formed in view of such a background, and it aims at providing the heat storage amount prediction apparatus, the heat storage amount prediction method, and program which can estimate the heat storage amount of a building accurately.

  The main invention of the present invention for solving the above problems is an apparatus for predicting the amount of heat stored in a building, wherein the amount of stored heat per unit time, the humidity of outside air per unit time, and the outside air temperature per unit time. And a database for storing actual values of values related to the number of visitors to the building per unit time, the outside air temperature per unit time, the humidity per unit time, and the visitor per unit time A prediction model storage unit that stores a prediction model that includes a value related to the number as an explanatory variable, and that uses the heat storage amount per unit time as a target variable, and the actual value of the heat storage amount per unit time, for each unit time Based on the actual value of the outside air temperature, the actual value of the humidity per unit time, the actual value of the value related to the number of visitors per unit time, and the prediction model, the explanatory variable. And a prediction unit for estimating a regression coefficient of the prediction model and a constant of the prediction model, and a predicted value of each of the values related to the outside air temperature per unit time, the humidity per unit time, and the number of guests per unit time A predicted value acquisition unit, the regression coefficient, the constant, a predicted value of the outside air temperature per unit time, a predicted value of the humidity per unit time, and a predicted value of a value related to the number of customers per unit time And a heat storage amount prediction unit that calculates the predicted value of the heat storage amount per unit time by applying the above to the prediction model.

  In the heat storage amount prediction apparatus of the present invention, the value related to the number of visitors may include a dummy variable representing a day of the week and a dummy variable representing a time per unit time.

  In the heat storage amount prediction apparatus of the present invention, the value related to the number of visitors may further include the presence or absence of an event that is performed in an area to which the building belongs.

  In the heat storage amount prediction device of the present invention, the value related to the number of visitors may be the number of visitors to the building.

  In the heat storage amount prediction apparatus of the present invention, the explanatory variable of the outside air temperature included in the prediction model may be a temperature obtained by subtracting a set temperature of air conditioning in the building from the outside air temperature.

  Moreover, in the heat storage amount prediction device of the present invention, the database further stores an actual value of the ventilation heat amount, which is the amount of heat exhausted from or taken into the building by ventilation of the building, and the prediction model further includes , Including the temperature according to the ventilation heat amount as an explanatory variable, the estimation unit includes the actual value of the heat storage amount, the actual value of the outside air temperature, the actual value of the humidity, the actual value of the value related to the number of visitors, the ventilation Based on the actual value of heat quantity and the prediction model, the regression coefficient of the explanatory variable and the constant of the prediction model are estimated, the prediction value acquisition unit further acquires the prediction value of the ventilation heat amount, and the heat storage amount prediction unit Applies the regression coefficient, the constant, the predicted value of the outside air temperature, the predicted value of the humidity, the predicted value of the value related to the number of visitors, and the predicted value of the ventilation heat quantity to the predicted model. It may be calculated predicted value of the heat storage amount.

  Another aspect of the present invention is a method for predicting the amount of heat stored in a building, wherein the amount of stored heat per unit time, the humidity of outside air per unit time, the outside air temperature per unit time, and the unit time. A database storing each actual value of the value related to the number of visitors to each building, and the outside temperature per unit time, the humidity per unit time, and the value related to the number of visitors per unit time A computer including a prediction model storage unit that stores a prediction model that includes the heat storage amount per unit time as an objective variable, and includes the actual value of the heat storage amount per unit time, the unit time Based on the actual value of the outside air temperature, the actual value of the humidity per unit time, the actual value of the value related to the number of visitors per unit time, and the prediction model, the description A step of estimating a regression coefficient of a number and a constant of the prediction model, and obtaining respective predicted values of the outside air temperature per unit time, the humidity per unit time, and the number of guests per unit time Predicting the regression coefficient, the constant, the predicted value of the outside air temperature per unit time, the predicted value of the humidity per unit time, and the predicted value of the number of visitors per unit time And applying a model to calculate a predicted value of the heat storage amount per unit time.

  Another aspect of the present invention is a program for predicting the amount of heat stored in a building, the amount of stored heat per unit time, the humidity of outside air per unit time, the outside air temperature per unit time, and the A database that stores actual values of values related to the number of visitors to the building per unit time, the outside air temperature per unit time, the humidity per unit time, and the number of visitors per unit time A computer that includes a prediction model storage unit that stores a prediction model that includes a value as an explanatory variable and uses the heat storage amount per unit time as a target variable, the actual value of the heat storage amount per unit time, Based on the actual value of the outside air temperature, the actual value of the humidity per unit time, the actual value of the value related to the number of visitors per unit time, and the prediction model Estimating a regression coefficient of the explanatory variable and a constant of the prediction model, and predicting each of the values related to the outside air temperature per unit time, the humidity per unit time, and the number of visitors per unit time A step of obtaining a value, the regression coefficient, the constant, the predicted value of the outside air temperature per unit time, the predicted value of the humidity per unit time, and the predicted value of the value related to the number of visitors per unit time And calculating the predicted value of the heat storage amount per unit time by applying to the prediction model.

  Other problems and solutions to be disclosed by the present application will be made clear by the embodiments of the present invention and the drawings.

  According to the present invention, the amount of heat stored in a building can be predicted with high accuracy.

It is a figure which shows the hardware structural example of the thermal storage amount prediction apparatus. It is a figure which shows the software structural example of the thermal storage amount prediction apparatus. It is a figure which shows the structural example of the database 131. FIG. It is a figure which shows the structural example of the ventilation schedule memory | storage part. 6 is a diagram illustrating a configuration example of an event schedule storage unit 133. FIG. It is the graph showing the predicted value 21 of the thermal storage amount by the thermal storage amount prediction part 118 using a prediction model, and the measured value 22 of the thermal storage amount. It is a figure which shows the software structural example of the thermal storage amount prediction apparatus 10 in the case of using the number of visitors. It is a figure which shows the structural example of the visitor number memory | storage part 135. FIG.

  Hereinafter, the heat storage amount prediction apparatus 10 according to an embodiment of the present invention will be described. The heat storage amount prediction device 10 of the present embodiment predicts the amount of heat of a building to be removed during the business hours of the store, that is, the amount of heat storage of the building. By predicting the amount of stored heat, air conditioning can be operated according to the amount of stored heat so that the store has a comfortable temperature.

== Hardware configuration ==
FIG. 1 is a diagram illustrating a hardware configuration example of the heat storage amount prediction device 10. The heat storage amount prediction device 10 includes a CPU 101, a memory 102, a storage device 103, an interface 104, an input device 105, and an output device 106. The storage device 103 stores various data and programs, for example, a hard disk drive, a solid state drive, a flash memory, or the like. The CPU 101 implements various functions by reading a program stored in the storage device 103 into the memory 102 and executing it.

  The interface 104 is an interface for connecting to the sensor 5, for example, connecting a serial cable or a communication cable. In the present embodiment, it is assumed that the sensor 5 is a sensor that measures the outside air temperature. The heat storage amount prediction device 10 can acquire the measured value of the outside air temperature from the sensor 5 via the interface 104. Moreover, it connects with an air conditioning equipment via the interface 104, and you may make it the heat storage amount prediction apparatus 10 control an air conditioning equipment.

  The input device 105 is, for example, a keyboard, a mouse, a trackball, a touch panel, or a microphone that accepts data input. The output device 106 outputs data, for example, a display, a printer, a speaker, or the like.

== Software configuration ==
FIG. 2 is a diagram illustrating a software configuration example of the heat storage amount prediction device 10. The heat storage amount prediction device 10 includes a heat storage amount actual value acquisition unit 111, a temperature actual value acquisition unit 112, a humidity actual value acquisition unit 113, a ventilation heat amount calculation unit 114, a prediction model estimation unit 115, a predicted temperature acquisition unit 116, and a predicted humidity acquisition. Unit 117, heat storage amount prediction unit 118, predicted heat storage amount output unit 119, database 131, ventilation schedule storage unit 132, event schedule storage unit 133, and prediction model storage unit 134.

  In addition, the heat storage amount actual value acquisition unit 111, the temperature actual value acquisition unit 112, the humidity actual value acquisition unit 113, the ventilation heat amount calculation unit 114, the predicted model estimation unit 115, the predicted temperature acquisition unit 116, the predicted humidity acquisition unit 117, the heat storage amount The prediction unit 118 and the predicted heat storage amount output unit 119 are realized by the CPU 101 included in the heat storage amount prediction device 10 reading out the program stored in the storage device 103 to the memory 102 and executing it, and the database 131 and the ventilation schedule storage unit 132. The event schedule storage unit 133 and the prediction model storage unit 134 are realized as part of a storage area provided by the memory 102 and the storage device 103.

  The database 131 stores data necessary for predicting the heat storage amount, including the actual value of the outside air temperature. FIG. 3 is a diagram illustrating a configuration example of the database 131. The database 131 associates the date and time with the actual value of the outside air temperature, the actual value of the air temperature in the store (hereinafter referred to as the internal air temperature), the humidity outside the store (hereinafter, The actual value of the outside humidity, the actual value of the humidity in the store (hereinafter referred to as internal humidity), the actual value of the housing temperature, the actual value of the ventilation heat amount, and the actual value of the heat storage amount are stored.

The ventilation schedule storage unit 132 stores a ventilation schedule of the store. FIG. 4 is a diagram illustrating a configuration example of the ventilation schedule storage unit 132. Ventilation schedule storage unit 132 in association with the time indicating the date and time zone t, and stores the ventilation Q _t. In addition, ventilation of a store shall be performed along the ventilation schedule memory | storage part 132. FIG. That is, the ventilation volume corresponding to the past date and time stored in the ventilation schedule storage unit 132 is the actual value of the ventilation volume, and the ventilation volume corresponding to the future date and time is the predicted value of the ventilation volume. And

  The event schedule storage unit 133 stores events to be held. In the present embodiment, the event schedule storage unit 133 stores events that have been held in the past or are scheduled to be held in the future in the store's trade area. FIG. 5 is a diagram illustrating a configuration example of the event schedule storage unit 133. The event schedule storage unit 133 stores the contents of the event in association with the date. It can be determined that an event has occurred on the date when the event content is registered in the event schedule storage unit 133. In the event schedule storage unit 133, an event corresponding to a past date indicates that an event has been held, and an event corresponding to a future date indicates that an event is scheduled to be held. is there.

  The heat storage amount actual value acquisition unit 111 acquires the actual value of the heat storage amount of the store for each predetermined unit time (in this embodiment, 1 hour; the same applies hereinafter). The heat storage amount actual value acquisition unit 111 can receive an input of the heat storage amount actual value from the input device 105, for example. Further, for example, the sensor 5 measures the temperature of the store housing and the room temperature in the store, and the heat storage amount actual value acquisition unit 111 calculates the heat storage amount from the temperature of the housing measured by the sensor 5 and the room temperature in the store. It may be. Moreover, you may make it the heat storage amount performance value acquisition part 111 acquire from the air conditioner the cold energy amount required in order to lower room temperature to a predetermined value for every time slot | zone as a heat storage amount.

  The temperature actual value acquisition unit 112 acquires an outside temperature and an inside temperature for each predetermined unit time. In the present embodiment, the actual temperature value acquisition unit 112 acquires the outside air temperature and the inside air temperature measured by the sensor 5. However, for example, the input of the outside air temperature and the inside air temperature may be received from the user. The actual temperature value acquisition unit 112 acquires, for example, the outside temperature and the inside temperature at every hour on the hour, and the outside temperature and the inside temperature at the hour may be set as the outside temperature and the inside temperature in the time zone from the hour to the next hour. The average values of the outside temperature and the inside temperature at the hour and the next hour may be used as the outside temperature and the inside temperature in the time zone from the hour to the next hour. Moreover, the temperature actual value acquisition part 112 measures outside temperature and inside temperature for every short time, such as 5 minutes or 10 minutes, for example, and averages the outside temperature and inside temperature measured during the time zone. It is good also as outside temperature and inside temperature. The actual temperature value acquisition unit 112 registers the acquired actual values of the outside temperature and the inside temperature in the database 131 in association with the current date and the current hour.

  The actual humidity value acquisition unit 113 acquires the internal humidity and the external humidity for each time period. In the present embodiment, the sensor 5 that measures the internal humidity and the sensor 5 that measures the external humidity are installed, and the humidity actual value acquisition unit 113 acquires the internal humidity and the external humidity from the sensor 5. The input of internal humidity and external humidity may be received. The actual humidity value acquisition unit 113 registers the acquired internal humidity and external humidity in the database 131 in association with the current date and the current hour of the current time.

  The ventilation heat quantity calculation unit 114 calculates the amount of heat (hereinafter referred to as ventilation heat quantity) changed by ventilating the store in the time zone t.

The ventilation heat quantity _Dt is obtained by the following equation (D1).

Here, D _t ^IN is the amount of heat taken from outside in the time zone t. D _t ^IN is _expressed by the following equation (D2), where h _t ^OUT is the specific enthalpy (kJ / kg) of outdoor air, ρ ^{OUT is} the air density (kg / m ³ ) of outdoor air, and Q _t is the ventilation rate (m ³ ). ).

D _t ^OUT is the amount of heat discharged from the indoor to the outdoor in the time zone t. D _t ^OUT is _expressed by the following formula (D3), where the specific enthalpy (kJ / kg) of indoor air is h _t ^IN , the air density (kg / m ³ ) of indoor air is ρ ^IN , and the ventilation volume (m ³ ) is Q _t. ).

  The specific enthalpy can be calculated from temperature and humidity. The air density can be calculated from the temperature and atmospheric pressure.

Specifically, the ventilation heat calculator 114 calculates the specific enthalpy h _t ^OUT buildings outside air from the actual value temp _t and outer humidity m _t of the outside air temperature for each time zone is stored in the database 131, time The specific enthalpy h _t ^IN of the air in the building is calculated from the actual value temp _t ^IN and the internal humidity m _t ^IN of the inner temperature for each band. Ventilation heat calculator 114 obtains the ventilation Q _t time zone made ventilated from the ventilation schedule storage unit 132, the ventilation Q _t of the time zone in which ventilation is not registered in the ventilation schedule storage unit 132 0. The ventilation heat quantity calculation unit 114 calculates the air densities ρ ^OUT and ρ ^IN from a predetermined atmospheric pressure, the outside air temperature temp ^t, and the inside air temperature temp _t ^IN . The ventilation heat quantity calculation unit 114 calculates the amount of heat W _t ^IN taken from the outdoors by applying the specific enthalpy h _t ^{OUT of} the outdoor air, the air density ρ ^OUT of the outdoor air, and the ventilation quantity Q _t to the above formula (D2). Then, by applying the specific enthalpy h _t ^IN of indoor air, the air density ρ ^{IN of} indoor air, and the ventilation amount Q _t to the above formula (D3), the amount of heat W _t ^OUT discharged to the outdoors is calculated. The ventilation heat quantity _Dt is calculated by D1). The ventilation heat quantity calculation unit 114 registers the ventilation heat quantity D _t in the database 131 in association with the time zone t.

The prediction model storage unit 134 stores a prediction model for predicting the heat storage amount. The prediction model is expressed by the following equation (1).

Here, Y _t is the amount of heat stored in the store in the time zone t, and t is a numerical value representing the time zone in units of one hour. n is the number of days of the week. For example, if Monday is a reference day, n = 6 on Tuesdays, Wednesdays, Thursdays, Fridays, Saturdays, and holidays. m is the number of hours on the hour from the opening time to the closing time. For example, if the reference time is 9 o'clock, the business hours are from 9 o'clock to 22 o'clock except for 9 o'clock, and m = 12. .

a is a constant, and b _i , c _i , d, e, and f are regression coefficients. X _{i, t} is a dummy variable representing the day of the week. By the way, when a holiday occurs on a holiday such as a holiday or the year-end and New Year holidays on Tuesday, a dummy variable indicating a holiday is used for X _{i, t} . W _{i, t} is a dummy variable representing the time of the time zone t. m _t is the humidity of the outside air in the time zone t. T _t is a value corresponding to the outside air temperature in the time zone t, and is obtained by the following equation (2).

Here, temp _t is an outside air temperature in the time zone t, and α is a set temperature of air conditioning indoors (in the present embodiment, it is a constant). V _t is a dummy variable indicating the presence or absence of an event in the time zone t. In the present embodiment, the presence / absence of an event is managed in the event schedule storage unit 133 by date. D _t is the amount of ventilation heat.

The prediction model estimation unit 115 estimates the regression coefficient and constant of the prediction model. The prediction model estimation unit 115 creates a dummy variable X _{i, t} for the day of the week and a dummy variable W _{i, t} for the time for each record in the database 131, and calculates T _{t according} to equation (2). Furthermore, the prediction model estimation unit 115 refers to the event schedule storage unit 133, determines whether the event corresponding to the date of record, creating a dummy variable V _t. The prediction model estimation unit 115 calculates the constant a and the regression coefficients b _i , c _i , d, e, based on the record, the dummy variables X _{i, t} , W _{i, t,} V _t , T _t, and equation (1). Estimate f. The estimation process is performed by a general regression analysis method, and the description is omitted here. The prediction model estimation unit 115 applies a statistical model (hereinafter referred to as a prediction formula) in which the estimated constant α and the estimated regression coefficients b _i , c _i , d, e, and f are applied to the formula (1), as a prediction model storage unit. 134.

  The predicted temperature acquisition unit 116 acquires predicted values of the outside temperature and the inside temperature for each time zone. The predicted temperature acquisition unit 116 may predict the outside temperature and the inside temperature based on the actual values of the outside temperature and the inside temperature stored in the database 131, for example, or the weather provided by a weather company or the like The outside air temperature as a forecast value may be acquired, and the inside air temperature may be predicted based on the outside air temperature. Moreover, you may make it the estimated temperature acquisition part 116 receive the input of the predicted value of external temperature and internal temperature from a user.

  The predicted humidity acquisition unit 117 acquires predicted values of the external humidity and the internal humidity for each time zone. The predicted humidity acquisition unit 117 may predict the external humidity and the internal humidity, for example, based on the actual values of the external humidity and the internal humidity stored in the database 131, or the external temperature acquired by the predicted temperature acquisition unit 116 and The outside humidity and the inside humidity may be predicted based on the inside temperature. Further, the predicted humidity acquisition unit 117 may acquire the external humidity as a weather forecast value provided by a weather company or the like, and may predict the internal humidity based on the external humidity. The predicted humidity acquisition unit 117 may accept input of external humidity and internal humidity from the user.

The heat storage amount prediction unit 118 calculates a predicted value of the heat storage amount. The heat storage amount prediction unit 118 calls the ventilation heat amount calculation unit 114, and uses the outside air temperature, the inside air temperature, the outside humidity, and the inside humidity acquired by the prediction temperature acquisition unit 116 and the prediction humidity acquisition unit 117 to calculate the prediction value of the ventilation heat amount. Let it be calculated. The heat storage amount prediction unit 118 sets the dummy variables X _{i, t} and W _{i, t} of the prediction model based on the day of the prediction target day and the time of the prediction target time zone. Heat storage amount estimation unit 118, an event corresponding to the predicted target day is determined whether the event by whether or not it is registered in the event schedule storage unit 133, sets a dummy variable V _t based on this. The heat storage amount prediction unit 118 calculates the T _t by giving the outside air temperature to the equation (2), calculates the T _t , the dummy variables X _{i, t} , _{Wi, t,} and V _t , the outside air temperature and the outside air the predicted value of the humidity, and the predicted value of the ventilation heat given to the prediction equation to calculate the predicted value Y _t of the heat storage amount.

  The predicted heat storage amount output unit 119 outputs the predicted value of the heat storage amount calculated by the heat storage amount prediction unit 118. The predicted heat storage amount output unit 119 may output the predicted value of the heat storage amount to the output device 106, for example, or may set the predicted value of the heat storage amount in an e-mail and send it to a predetermined address. Good.

  FIG. 6 is a graph showing the predicted value 21 of the heat storage amount by the heat storage amount prediction unit 118 using the prediction model and the actual measurement value 22 of the heat storage amount. From the graph of FIG. 6, it can be seen that the predicted value 21 and the actually measured value 22 according to the prediction model of the present embodiment are closely approximated.

== Effect ==
As described above, according to the heat storage amount prediction device 10 of the present embodiment, the heat storage amount can be predicted by a prediction formula obtained by estimating a prediction model including a temperature according to the outside air temperature as an explanatory variable. Since it is assumed that the amount of heat stored in the building is affected by the outside air temperature, the accuracy of predicting the amount of stored heat can be improved by adding the temperature according to the outside air temperature as an explanatory variable. Moreover, since the predicted value of the outside air temperature that is easily available is used, it is possible to easily predict the heat storage amount. In addition, when the humidity is high, the specific enthalpy increases and the amount of heat of the air increases. Therefore, by adding the humidity as an explanatory variable, it is expected that the prediction accuracy of the heat storage amount is improved.

Further, in the heat storage amount prediction device 10 of the present embodiment, the difference between the outside air temperature temp _t and the set temperature α of the air conditioning is used as an explanatory variable. Not all the energy of the outside air temperature is stored in the building, but only the temperature of the outside air temperature temp _t , excluding that which is cooled by air conditioning, is considered to contribute to the heat storage in the store. By using it, the prediction accuracy of the heat storage amount can be improved.

  Moreover, in the heat storage amount prediction apparatus 10 of this embodiment, the day and time dummy variables are added to the explanatory variables. As the number of visitors to the store increases, the amount of heat storage increases, and it is known that the number of visitors varies depending on the day of the week and the time zone in stores such as retail stores and restaurants. In addition, when an event is held in the store's trade area, the number of visitors is different from the normal number, and a dummy variable indicating the presence or absence of the event is also added to the explanatory variable. As described above, it is expected that the accuracy of the predicted value of the heat storage amount is improved by considering the day of the week, the time zone, and the presence or absence of an event.

Further, the heat storage amount prediction device 10 of the present embodiment, in addition to ventilation heat D _t as explanatory variables. Since the amount of heat enters or is discharged from the building by ventilation, the prediction accuracy of the heat storage amount that is the objective variable can be improved by adding the amount of ventilation heat to the explanatory variable.

== Modification ==
In the present embodiment, dummy variables such as day of the week, time, and the presence / absence of an event are included as explanatory variables in the prediction model (1). However, these affect the number of customers to the store. The value associated with can be an explanatory variable. For example, you may make it include the number of visitors itself as an explanatory variable as a value regarding the number of visitors. In this case, the expression (1) is changed to the following expression (1-1).

Here, g is a regression coefficient, and P _t is the number of visitors in the time zone t.

  In this case, as shown in FIG. 7, the heat storage amount prediction device 10 further includes a visitor number storage unit 135 and a visitor number prediction unit 120 that store the number of visitors for each time zone. FIG. 8 is a diagram illustrating a configuration example of the visitor number storage unit 135. As shown in FIG. 8, the visitor number storage unit 135 stores the number of visitors in the time zone in association with the time indicating the date and time of the day.

  The prediction model estimation unit 115 includes the actual values of the outside air temperature, humidity, and heat storage amount stored in the database 131 for each time period, the actual value of the number of visitors stored in the visitor number storage unit 135, and the prediction model. The constant a and the regression coefficients d, e, and g are estimated using the equation (1-1). The prediction model estimation unit 115 registers a value obtained by applying the estimated constant a and regression coefficients d, e, and g to the equation (1-1) in the prediction model storage unit 134 as a prediction equation.

  The visitor number predicting unit 120 predicts the number of store visitors for each time zone. A general prediction method can be used for predicting the number of customers visiting the store. For example, the visitor number prediction unit 120 can calculate the predicted value of the visitor number based on the actual number of visitors stored in the visitor number storage unit 135. Moreover, you may make it receive the input of the predicted value of a visitor number from a user, for example from a user.

The heat storage amount prediction unit 118 calculates the calculated T _t , the dummy variables X _{i, t} , W _{i, t} and V _t , the predicted values of the outside air temperature and the outside humidity, the predicted value of the ventilation heat amount, and the number of visitors The predicted value Y _t is calculated by giving the predicted value to the prediction formula.

When air-conditioning a store, the influence of the amount of heat generated by customers visiting the building can be considered. Therefore, the heat storage amount to be removed from the store can be predicted more accurately by adding the number of customers _Pt to the explanatory variable.

== Other variations ==
In the present embodiment, the heat storage amount prediction device 10 is a single computer, but is not limited thereto, and may be configured by a plurality of computers. For example, the database 131, the ventilation schedule storage unit 132, the event schedule storage unit 133, and the prediction model storage unit 134 may be managed by an external database server, and the heat storage amount prediction device 10 may access them. Further, the heat storage amount prediction device 10 may be connected to a communication network and the heat storage amount may be predicted according to a request from another computer on the communication network. Moreover, you may make it perform the estimation process of a prediction model, and the prediction process of heat storage amount with a different apparatus.

Further, in the present embodiment, the explanatory variable _{T t} has been from ambient temperature temp _t and minus the set temperature α of the air conditioning may be ambient temperature temp _t itself _(T t = temp t). Further, in the example, if you have a humidifying or dehumidifying air conditioning, as (air-conditioning set humidity of the β indoor) Similarly M _{t =} m _t -β also humidity m _t, e · prediction models (1) e · M _t may be used instead of m _t .

In the case of using a model (1-1) employing the customer traffic itself P _t as the value associated with the number of visitors may be added to engage employees in the store to the number of visitors.

Further, the outside humidity and the inside humidity may be evaluated stepwise such as high humidity, medium humidity, and low humidity, and these may be used as explanatory variables. In addition, when using the store visitor number P _t , the customer number may be evaluated in stages such as many, medium, small, and none, and this may be used as an explanatory variable.

  Moreover, you may make it the estimated heat storage amount output part 119 control an air-conditioning installation according to the predicted value of heat storage amount. In this case, for example, the predicted heat storage amount output unit 119 receives the input of the target heat storage amount for each time period, calculates the removal heat amount that is the difference between the target heat storage amount and the predicted value Z of the heat storage amount, and responds to the removal heat amount. The air conditioning equipment can be operated. For example, the predicted heat storage output unit 119 calculates the operating time of the air conditioning equipment by dividing the removed heat storage amount by the amount of cold energy per unit time according to the rating of the air conditioning equipment, and controls the air conditioning equipment to move only for the calculated operating time. can do. In this case, the indoor temperature during the opening hours can be held comfortably.

In this embodiment, an event is managed in association with a date. However, an event may be managed in association with a date and a time zone. In this case, since the increase / decrease in the number of visitors due to the event can be analyzed in more detail, the prediction accuracy of the heat storage amount can be improved. In consideration of the time lag from the event to the visitor, the number of visitors P _{t + j} shifted by j from the time zone t including the event occurrence time may be calculated as Pt. This makes it possible to more accurately analyze changes in the amount of stored heat according to changes in the number of visitors due to events, and is expected to improve prediction accuracy.

  Although the present embodiment has been described above, the above embodiment is intended to facilitate understanding of the present invention and is not intended to limit the present invention. The present invention can be changed and improved without departing from the gist thereof, and the present invention includes equivalents thereof.

DESCRIPTION OF SYMBOLS 10 Thermal storage amount prediction apparatus 111 Thermal storage amount actual value acquisition part 112 Temperature actual value acquisition part 113 Humidity actual value acquisition part 114 Ventilation calorie calculation part 115 Prediction model estimation part 116 Predicted temperature acquisition part 117 Predictive humidity acquisition part 118 Thermal storage amount prediction part 119 Predicted heat storage output unit 120 Visitor number prediction unit 131 Database 132 Ventilation schedule storage unit 133 Event schedule storage unit 134 Prediction model storage unit 135 Visitor number storage unit

Claims (8)

A device that predicts the amount of heat stored in a building,
A database that stores the actual storage values of the heat storage amount per unit time, the humidity of the outside air per unit time, the outside air temperature per unit time, and the value related to the number of visitors to the building per unit time;
A prediction model including, as explanatory variables, values related to the outside air temperature per unit time, the humidity per unit time, and the number of visitors per unit time, and the heat storage amount per unit time as an objective variable A prediction model storage unit for storing;
The actual value of the heat storage amount per unit time, the actual value of the outside air temperature per unit time, the actual value of the humidity per unit time, the actual value of the value related to the number of visitors per unit time, and the An estimation unit for estimating a regression coefficient of the explanatory variable and a constant of the prediction model based on a prediction model;
A predicted value acquisition unit that acquires respective predicted values of the outside air temperature per unit time, the humidity per unit time, and the value related to the number of visitors per unit time;
The regression coefficient, the constant, the predicted value of the outside air temperature per unit time, the predicted value of the humidity per unit time, and the predicted value of the value related to the number of visitors per unit time are applied to the prediction model. A heat storage amount prediction unit that calculates a predicted value of the heat storage amount per unit time,
A heat storage amount prediction apparatus comprising: The heat storage amount prediction device according to claim 1,
The value related to the number of visitors includes a dummy variable representing a day of the week and a dummy variable representing a time per unit time,
A heat storage amount prediction apparatus comprising: The heat storage amount prediction device according to claim 2, wherein the value related to the number of visitors further includes presence or absence of an event to be performed in an area to which the building belongs,
A heat storage amount prediction device characterized by The heat storage amount prediction apparatus according to any one of claims 1 to 3,
The value related to the number of visitors is the number of visitors to the building;
A heat storage amount prediction device characterized by The heat storage amount prediction device according to any one of claims 1 to 4,
The explanatory variable of the outside air temperature included in the prediction model is a temperature obtained by subtracting a set temperature of air conditioning in the building from the outside air temperature,
A heat storage amount prediction device characterized by The heat storage amount prediction apparatus according to any one of claims 1 to 5,
The database further stores the actual value of ventilation heat, which is the amount of heat discharged from or taken into the building by ventilation of the building;
The prediction model further includes a temperature according to the ventilation heat quantity as an explanatory variable,
The estimation unit is based on the actual value of the heat storage amount, the actual value of the outside air temperature, the actual value of the humidity, the actual value of the value related to the number of visitors, the actual value of the ventilation heat amount, and the prediction model. Estimate the regression coefficient of the variable and the constant of the prediction model,
The predicted value acquisition unit further acquires a predicted value of the ventilation heat quantity,
The heat storage amount prediction unit applies the regression coefficient, the constant, the predicted value of the outside air temperature, the predicted value of the humidity, the predicted value of the value related to the number of visitors, and the predicted value of the ventilation heat amount to the prediction model. Calculating a predicted value of the heat storage amount,
A heat storage amount prediction device characterized by A method for predicting the amount of heat stored in a building,
A database for storing each actual value of the amount of heat stored per unit time, the humidity of the outside air per unit time, the outside air temperature per unit time and the number of visitors to the building per unit time; and Stores a prediction model including, as explanatory variables, values related to the outside air temperature per unit time, the humidity per unit time, and the number of visitors per unit time, and the heat storage amount per unit time as an objective variable A computer comprising a prediction model storage unit for
The actual value of the heat storage amount per unit time, the actual value of the outside air temperature per unit time, the actual value of the humidity per unit time, the actual value of the value related to the number of visitors per unit time, and the Estimating a regression coefficient of the explanatory variable and a constant of the prediction model based on a prediction model;
Obtaining each predicted value of the outside air temperature per unit time, the humidity per unit time and the number of customers per unit time;
The regression coefficient, the constant, the predicted value of the outside air temperature per unit time, the predicted value of the humidity per unit time, and the predicted value of the value related to the number of visitors per unit time are applied to the prediction model. Calculating a predicted value of the heat storage amount per unit time,
The heat storage amount prediction method characterized by performing this. A program for predicting the amount of heat stored in a building,
A database for storing each actual value of the amount of heat stored per unit time, the humidity of the outside air per unit time, the outside air temperature per unit time and the number of visitors to the building per unit time; and Stores a prediction model including, as explanatory variables, values related to the outside air temperature per unit time, the humidity per unit time, and the number of visitors per unit time, and the heat storage amount per unit time as an objective variable A computer having a prediction model storage unit for
The actual value of the heat storage amount per unit time, the actual value of the outside air temperature per unit time, the actual value of the humidity per unit time, the actual value of the value related to the number of visitors per unit time, and the Estimating a regression coefficient of the explanatory variable and a constant of the prediction model based on a prediction model;
Obtaining each predicted value of the outside air temperature per unit time, the humidity per unit time and the number of customers per unit time;
The regression coefficient, the constant, the predicted value of the outside air temperature per unit time, the predicted value of the humidity per unit time, and the predicted value of the value related to the number of visitors per unit time are applied to the prediction model. Calculating a predicted value of the heat storage amount per unit time,
A program for running