JP2019203652A - Shop air-conditioning system - Google Patents

Abstract

To provide a shop air-conditioning system that can reduce power an air conditioner and a freezer consume, while air-conditioning a shop comfortably by the air conditioner.SOLUTION: A shop air-conditioning system comprises: a prediction model creating unit 38 that performs machine learning based on a database 37 constructed by accumulating an outside air temperature, an air-conditioning setting temperature, a power consumption and a discomfort index for a predetermined period, and creates a model for predicting a power consumption and a discomfort index after a predetermined time from the latest data; a prediction unit 42 that predicts a plurality of power consumptions and discomfort indexes after the predetermined time by applying a plurality of air-conditioning setting temperatures to a prediction model; and an optimal value calculation unit 44 that calculates the optimal value of the air-conditioning setting temperature at which the discomfort index after the predetermined time is acceptable and the power consumption is minimized.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a store air conditioning system that performs air conditioning of a store in which a refrigeration apparatus such as a showcase is installed.

  Conventionally, stores such as convenience stores and supermarkets have been provided with a plurality of refrigeration apparatuses such as refrigeration / frozen showcases. In recent years, in order to perform energy-saving operation on the showcases installed in these stores, a system that predicts the future outside air temperature and controls the showcase has been developed (see, for example, Patent Document 1).

Japanese Patent No. 6284173

  Here, the inside of the store where the refrigeration apparatus including the showcase described above is installed is air-conditioned by the air conditioner based on a predetermined air conditioning set temperature, but the temperature and humidity in the store are changed by changing the air conditioning set temperature. Will change the operation of the refrigeration system installed in the store.

  However, in the past, the air conditioning set temperature of the air conditioner was set at a fixed value for each season, and the store clerk made a fine adjustment of the air conditioning set temperature so as to eliminate customer discomfort. There is a problem in that the power consumption of the entire store including the air conditioner is remarkably increased by adversely affecting the operation.

  The present invention is made in order to solve the conventional technical problem, and in a store where a refrigeration apparatus including a showcase is installed, the air conditioner It is an object of the present invention to provide an air conditioning system that can reduce the power consumed by the refrigeration apparatus.

  The store air-conditioning system of the present invention air-conditions a store where a refrigeration apparatus including a showcase is installed, and controls the operation of the air-conditioner that air-conditions the store based on a predetermined air-conditioning set temperature. Consumed by the device control unit, the outside air temperature detecting unit for detecting the outside air temperature, the in-store temperature detecting unit for detecting the temperature in the store, the in-store humidity detecting unit for detecting the humidity in the store, the air conditioner and the freezing device A power consumption detection unit that detects power consumption, a discomfort index calculation unit that calculates a discomfort index in the store from the temperature and humidity in the store, and at least predetermined outside air temperature, air conditioning set temperature, power consumption, and discomfort index A database constructed by accumulating data for a period of time and machine learning based on this database, and at least the most recent outside temperature, air conditioning set temperature, power consumption, and discomfort index A prediction model creation unit that creates a prediction model for predicting the power and discomfort index, and by applying a plurality of air conditioning set temperatures to the prediction model created by the prediction model creation unit, the power consumption and discomfort index after a predetermined time Air-conditioning that consumes the least amount of power after a predetermined time in a range in which the discomfort index after a predetermined time can be tolerated from a plurality of power consumption and discomfort index after a predetermined time predicted by the prediction unit. An optimum value calculation unit that calculates an optimum value of the set temperature is provided, and the air conditioner control unit controls the operation of the air conditioner using the optimum value calculated by the optimum value calculation unit as the air conditioning set temperature.

  The store air-conditioning system according to the invention of claim 2 is characterized in that, in the above invention, the prediction model creating unit periodically creates and updates a prediction model.

  According to a third aspect of the present invention, in the above-described invention, the prediction model creation unit performs machine learning by any one of linear regression analysis and nonlinear regression analysis, or a combination thereof, and obtains a prediction model. It is characterized by creating.

  According to a fourth aspect of the present invention, in the above-described invention, the predicting unit periodically predicts a plurality of power consumption and discomfort index after a predetermined time, and the optimum value calculating unit predicts the optimum value every time the predicting unit predicts. Is calculated.

  In the store air conditioning system of the invention of claim 5, in each of the above inventions, the database is additionally provided with data relating to the operating factor of the air conditioner and / or the refrigeration apparatus that affects the power consumption and the discomfort index, and is predicted. The model creation unit creates a prediction model that predicts the power consumption and discomfort index after a predetermined time by adding the added operation factor, and the prediction unit adds the operation factor added to the prediction model in addition to the air conditioning set temperature. A plurality of power consumption and discomfort index after a predetermined time are predicted, and the optimal value calculation unit calculates the discomfort index after a predetermined time from the plurality of power consumption and discomfort index after a predetermined time predicted by the prediction unit. Calculates the optimum value of the added operation factor that minimizes the power consumption after a predetermined time within an allowable range, and controls the air conditioner controller and / or the refrigeration system Refrigeration apparatus controller for controlling the operation, the air conditioning apparatus as the operating factors optimum value calculating unit is added to the optimum value calculated, and / or, and controls the operation of the refrigeration system.

  In the store air-conditioning system according to the invention of claim 6, the operating factors added in the above invention are the operation mode of the air conditioner, the temperature in the showcase, the air volume of the circulation fan in the showcase, the target low pressure of the refrigeration system One of the high pressure of the refrigeration apparatus, the rotation speed of the compressor of the refrigeration apparatus, the minimum valve opening of the expansion valve of the refrigeration apparatus, the operating state of the total heat exchanger that constitutes a part of the air conditioner, or It is characterized by being a combination thereof or all of them.

  According to the store air conditioning system of the present invention, a database is constructed by accumulating at least the outside air temperature, the air conditioning set temperature, the power consumption, and the discomfort index for a predetermined period, and the prediction model creation unit performs machine learning based on this database. And creating a prediction model for predicting the power consumption and discomfort index after a predetermined time from at least the latest outside air temperature, air conditioning set temperature, power consumption, and discomfort index. By applying the air conditioning set temperature, a plurality of power consumption and discomfort index after a predetermined time are predicted, and the optimum value calculation unit calculates the discomfort index after a predetermined time from the predicted power consumption and discomfort index after a plurality of predetermined times. Within the allowable range, the optimum value of the air conditioning set temperature that minimizes the power consumption after a predetermined time is calculated, and the air conditioner controller calculates the optimum value. The optimal value calculated by is used as the air conditioning set temperature, and the operation of the air conditioner that air-conditions the store is controlled, so that the power consumed by the air conditioner and the refrigeration device is the most within the acceptable range of the discomfort index in the store. The air conditioning set temperature can be automatically adjusted to an optimum value that can be reduced, and the operation of the air conditioner can be controlled.

  Thereby, the power consumption of the air conditioner and the refrigeration apparatus can be reduced while ensuring the comfort in the store.

  In this case, if the prediction model creation unit periodically creates and updates the prediction model as in the invention of claim 2, the optimum value of the air conditioning set temperature is accurately determined according to the change in the environment surrounding the store. It becomes possible to calculate.

  The machine learning in the prediction model creation unit may be either linear regression analysis or nonlinear regression analysis, or a combination thereof.

  Further, as in the invention of claim 4, the prediction unit periodically predicts a plurality of power consumption and discomfort index after a predetermined time, and the optimum value calculation unit calculates the optimum value every time the prediction unit predicts. For example, the optimum value of the air conditioning set temperature can be calculated with high accuracy in response to a change in the situation in the store.

  Further, as in the invention of claim 5, data relating to the operating factor of the air conditioner and / or the refrigeration apparatus that affect the power consumption and the discomfort index is additionally provided in the database, and a prediction model creation unit has been added. Create a prediction model that predicts power consumption and discomfort index after a predetermined time by adding an operation factor, and the prediction unit applies a plurality of operation factors added to the prediction model in addition to the air conditioning set temperature. After a predetermined time, the optimal value calculation unit predicts the power consumption and discomfort index after a predetermined time from the power consumption and discomfort index after a plurality of predetermined times predicted by the prediction unit. Calculating an optimum value of the added operation factor that minimizes the power consumption of the air conditioner, and / or a refrigeration system controller that controls the operation of the refrigeration system, If the operation of the air conditioner and / or refrigeration system is controlled using the optimal value calculated by the appropriate value calculation unit as an added operating factor, it will affect the power consumption and discomfort index other than the outside air temperature and air conditioning set temperature. It is possible to control the driving factor that gives the vehicle with the optimum value, and to further improve the comfort and reduce the power consumption.

  In this case, the added operation factors include the operation mode of the air conditioner, the temperature in the showcase, the air flow rate of the circulation fan in the showcase, and the target low pressure of the refrigeration system. The high pressure of the refrigeration apparatus, the rotation speed of the compressor of the refrigeration apparatus, the minimum valve opening of the expansion valve of the refrigeration apparatus, and the operating state of the total heat exchanger that constitutes a part of the air conditioner can be considered.

It is a schematic plan view of the store of one Example to which the store air-conditioning system of the present invention is applied. It is a block diagram of one Example of the store air conditioning system of this invention. It is a block diagram of the optimization controller in FIG. It is a flowchart explaining operation | movement of the optimization controller of FIG. It is another flowchart explaining operation | movement of the optimization controller of FIG. It is a figure which shows the structure of the database which the optimization controller of FIG. 3 builds. It is a figure explaining the data used for the machine learning by the optimization controller of FIG. FIG. 8 is a diagram in which values to be predicted by the optimization controller of FIG. 3 and the data of FIG. 7 for the past day are arranged side by side. It is a figure explaining determination of the optimal value of air-conditioning preset temperature. It is a figure explaining the prediction model of the power consumption by decision tree analysis. It is a figure explaining the prediction model of the discomfort index by decision tree analysis. It is a block diagram of the other Example of the store air-conditioning system of this invention when producing a prediction model by the server side of a management company.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
(1) Store 1
FIG. 1 is a schematic plan view of a general convenience store as an example of the store 1. Inside the sales floor 2 of the store 1, an open type showcase 4 (refrigerated refrigeration, multiple units) and product shelves 6 to 8 are installed from the back as viewed from the front entrance 3. A reach-in type showcase 11 (refrigerated and frozen, with multiple units) is installed, a toilet 12 is disposed in front of it, and a cash register space 13, a cooking chamber 14, and an office 16 are disposed on the right side. And the indoor unit 17 of the air conditioner 19 (FIG. 2) for air-conditioning the inside of the shop 1 is provided in the ceiling of the sales floor 2, the cooking chamber 14, and the office 16, respectively.

  In the figure, 18 is a fryer (fried food cooker) provided in the cooking chamber 14. In the present application, the inside of the thick line frame shown in FIG. 1 is the inside of the store and the outside thereof is the outside of the store. Outside the store, a refrigerator 15 for circulating the refrigerant in the showcases 4 and 11 and an outdoor unit 20 of the air conditioner 19 are installed, and the showcases 4 and 11 and the refrigerator 15 (compressors constituting the refrigerant circuit) are installed. The refrigeration apparatus 21 (FIG. 2) is configured by the expansion valve and the circulation fans in the showcases 4 and 11), and the air conditioner 19 is configured by the indoor unit 17 and the outdoor unit 20. Further, the store 1 is provided with a total heat exchanger 22 for exchanging heat between the outside air supplied to the store and the air discharged outside the store, and this also constitutes a part of the air conditioner 19 in the present application. It shall be.

(2) Store air conditioning system 24
Next, FIG. 2 shows an example of the configuration of the store air conditioning system 24 of the present invention provided in the store 1 of FIG. The store air-conditioning system 24 of this embodiment includes a power consumption detection unit 26 including the air conditioner 19 and the refrigerating device 21 described above, and a power meter that detects the total power consumption P of the air conditioner 19 and the refrigerating device 21 combined. An outside air temperature detection unit 27 that includes a temperature sensor that detects the outside air temperature T of the store 1, an in-store temperature detection unit 28 that includes a temperature sensor that detects the temperature in the store 1, and a humidity sensor that detects humidity in the store 1 The in-store humidity detection unit 29 is composed of an optimization controller 31, an air conditioner control unit 32, and a refrigeration unit control unit 33, each of which includes a microcomputer including a microprocessor.

(3) Air conditioner control unit 32 and refrigeration unit control unit 33
The air conditioner control unit 32 is provided in the air conditioner 19 and includes the outdoor unit 20 and the indoor unit 17 described above so that the temperature in the store 1 becomes the air condition set temperature A based on the air condition set temperature A described later. 19 operations are controlled. The refrigeration apparatus control unit 33 is provided in the refrigeration apparatus 21 and includes the above-described refrigerator 15 and the showcases 4 and 11 so that the inside temperature of each showcase 4 and 11 becomes a predetermined set temperature. To control the operation.

(4) Configuration of the Optimization Controller 31 The optimization controller 31 includes an overall power consumption P that is a combination of the air conditioner 19 and the refrigeration apparatus 21 output from the power consumption detection unit 26, and the outside air that the outside air temperature detection unit 27 detects. The temperature T, the temperature in the store 1 detected by the store temperature detection unit 28, and the humidity in the store 1 detected by the store humidity detection unit 29 are input. The optimization controller 31 transmits and receives data between the air conditioner control unit 32 of the air conditioner 19 and the refrigeration apparatus control unit 33 of the refrigeration apparatus 21, and optimizes these operations as will be described later. Control.

  Next, the detailed configuration of the optimization controller 31 will be described with reference to FIG. The optimization controller 31 of the embodiment includes a data receiving unit 34, a discomfort index calculation unit 36, a database 37, a prediction model creation unit 38, an optimization control unit 41, and a data transmission unit 46, and is optimized. The control unit 41 includes a prediction unit 42 and an optimum value calculation unit 44.

  The data receiving unit 34 of the optimization controller 31 performs an operation of receiving data from the air conditioner control unit 32 and the refrigeration unit control unit 33, and also includes the power consumption P from the power consumption detection unit 26 and the outside temperature detection described above. Data relating to the outside air temperature T from the unit 27, the temperature in the store 1 from the store temperature detection unit 28, and the humidity in the store 1 from the store humidity detection unit 29 are received. In addition, the data transmission unit 46 performs an operation of transmitting data to the air conditioner control unit 32 and the refrigeration unit control unit 33.

(5) Operation of the Optimization Controller 31 With the above configuration, the optimization control by the optimization controller 11 will be described with reference to FIGS.
(5-1) Construction of Database 37 The data receiving unit 34 of the optimization controller 31 in FIG. 3 receives the power consumption P from the power consumption detection unit 26 and the outside air from the outside air temperature detection unit 27 in step S1 in FIG. Data on the temperature T, the temperature in the store 1 from the in-store temperature detection unit 28, and the humidity in the store 1 from the in-store humidity detection unit 29 are received. Further, the air conditioner control unit 32 receives data related to the air conditioning set temperature A.

  At this time, the data regarding the temperature and humidity in the store 1 is sent to the discomfort index calculation unit 36. The discomfort index calculating unit 36 calculates the discomfort index D in the store 1 from the temperature and humidity in the store 1 received from the data receiving unit 34, and returns it to the data receiving unit 34. Then, the data receiving unit 34 accumulates the received data of the outside air temperature T, the air conditioning set temperature A, the power consumption P, and the discomfort index D for a predetermined period (one year in the embodiment), and the contents as shown in FIG. The database 37 is constructed. In FIG. 6, the air conditioning set temperature is expressed as air conditioning setting, and the power consumption is expressed as electric power.

  In this case, in the embodiment, the data receiving unit 21 periodically stores data on the outside air temperature T, the air conditioning set temperature A, the power consumption P, and the discomfort index D (in the embodiment, every 30 minutes as shown in FIG. 6). It is recorded in 37 and updated sequentially from the one year passed. In FIG. 6, the value of each outdoor air temperature T for every 30 years is indicated by t1 to t17520, the value of each air conditioning set temperature A is indicated by a1 to a17520, and the value of each power consumption P is indicated by p1 to p17520. The values of each discomfort index D are indicated by d1 to d17520.

(5-2) Creation of prediction model (1)
Next, in step S2 of FIG. 4, the prediction model creation unit 38 of the optimization controller 31 includes the latest outside air temperatures T to T48 in the database 37 (for the past one day in the embodiment), the air conditioning set temperatures A to Based on the data of A48, power consumption P to P48, and discomfort index D to D48, a prediction model for predicting the power consumption TGT1 after a predetermined time (in the embodiment, after 1 hour) by machine learning, and also after a predetermined time ( Similarly, a prediction model for predicting the discomfort index TGT2 after 1 hour in the embodiment is created.

  FIG. 7 shows data used for this machine learning, and FIG. 8 shows an actual value TGT1real of the power consumption TGT1 one hour later (predetermined time) and an uncomfortable one hour later (predetermined time) to be predicted by the prediction model. The actual value TGT2real of the index TGT2 is shown in each row side by side with the data of FIG. 7 for one day. In FIGS. 7 and 8, the air conditioning set temperature is expressed as air conditioning setting, and the power consumption is expressed as electric power.

The prediction model of this example is a calculation formula for multiple regression analysis, which is one of linear regression analyzes represented by the following formulas (I) and (II).
TGT1 = b0 + b1 × T + b2 × T1 +... + B196 × D48 (I)
TGT2 = c0 + c1 × T + c2 × T1 +... + C196 × D48 (II)
Equation (I) is a prediction model for predicting power consumption TGT1 after 1 hour, and Equation (II) is a prediction model for predicting discomfort index TGT2 after 1 hour.

  In the machine learning in step S2, the prediction model creation unit 38 calculates the power consumption TGT1 after 1 hour calculated in all rows when the data of each row in FIG. 8 is applied to the equations (I) and (II). The common coefficients b0 to b196 and c0 to c196 are determined so that the difference between the actual value TGT1real and the difference between the discomfort index TGT2 after one hour and the actual value TGT2real are minimized.

  Then, the prediction model creation unit 38 creates a prediction model (formula (I)) for predicting the power consumption TGT1 after 1 hour and a prediction model (formula (formula (I)) for predicting the discomfort index TGT2 after 1 hour. II)) is output in step S3 of FIG. 4 (indicated by reference numeral 39 in FIG. 3). The prediction model creation unit 38 creates and updates such a prediction model periodically (once a day in the embodiment).

(5-3) Optimization Control Next, the prediction unit 27 included in the optimization control unit 26 of the optimization controller 31 is the latest outside air temperature (for the past one day in the embodiment) in step S4 of FIG. Data of T, air conditioning setting A, power P, and discomfort index D is acquired from the database 37 and applied to each prediction model shown in the above formulas (I) and (II) in step S5, and 1 in steps S6 and S7. The power consumption TGT1 and the discomfort index TGT2 after time are predicted and output (shown as a prediction result 43 in FIG. 3). Note that the prediction unit 27 predicts and outputs the power consumption TGT1 and the discomfort index TGT2 after one hour regularly (once every hour in the embodiment).

  Here, in step S5, the prediction unit 42 changes the current air conditioning set temperature A in FIG. 7 to a plurality of values, for example, 21 ° C., 22 ° C., 23 ° C., 24 ° C. The power consumption TGT1 and the discomfort index TGT2 are predicted. If the predicted result is as shown in FIG. 9, for example, the power consumption TGT1 after 1 hour when the air conditioning set temperature A is 21 ° C. is “5 kW”, and the discomfort index TGT2 after 1 hour is “Uncomfortable”, power consumption TGT1 after 1 hour when air conditioning set temperature A is 22 ° C. is “4 kW”, discomfort index TGT2 after 1 hour is “comfort”, and air conditioning set temperature A is 23 ° C. The power consumption TGT1 after 1 hour is “3 kW”, the discomfort index TGT2 after 1 hour is “comfortable”, and the power consumption TGT1 after 1 hour when the air conditioning set temperature A is 24 ° C. is “4 kW”, after 1 hour If the discomfort index TGT2 is “comfortable”, the optimum value calculation unit 44 selects 23 ° C. in step S8 of FIG. 5 and calculates it as the optimum value Aopt of the air conditioning set temperature A (“Result” in FIG. 9). : Select ”).

  The optimum value Aopt, 23 ° C., is the air conditioning set temperature A at which the power consumption TGT1 after 1 hour is the smallest in the range (comfort) in which the discomfort index TGT2 after 1 hour is acceptable. Next, the data transmission unit 46 transmits the optimum value Aopt of the air conditioning set temperature A to the air conditioner control unit 32 in step S9 of FIG. 5 to change the air conditioning set temperature. The air conditioner control unit 32 controls the operation of the air conditioner 19 using the received optimum value Aopt as the air conditioning set temperature A. The optimum value calculation unit 44 calculates the optimum value Aopt every time the prediction unit 42 predicts, that is, periodically.

(5-4) Creation of prediction model (2)
Next, using FIG. 10 and FIG. 11, the prediction model for predicting the power consumption TGT1 after 1 hour and the prediction for predicting the discomfort index TGT2 after 1 hour by decision tree analysis which is one of nonlinear regression analysis. An embodiment in which a model is created and optimization control is performed will be described.

  In this case, the prediction model creation unit 38 of the optimization controller 31 of FIG. 3 has the latest outside air temperatures T to T48, the air conditioning set temperatures A to A48, and the power consumption P to Based on the data of P48 and the discomfort index D to D48, the prediction model of the decision tree analysis for predicting the power consumption TGT1 after a predetermined time (also after 1 hour) by machine learning, and also after the predetermined time (after 1 hour) The prediction model of the decision tree analysis for predicting the discomfort index TGT2 is created.

  The prediction model creation unit 38 calculates the difference between the power consumption TGT1 after 1 hour and its actual value TGT1real predicted in all the rows of FIG. 8, and the difference between the discomfort index TGT2 after 1 hour and its actual value TGT2real. A decision tree that minimizes is created as shown in FIGS. FIG. 10 shows a prediction model of power consumption P for predicting the power consumption TGT11 after one hour by decision tree analysis, and FIG. 11 shows a prediction model for the discomfort index D for predicting the discomfort index TGT2 after one hour by decision tree analysis.

(5-5) Optimization Control in the Cases of FIGS. 10 and 11 Next, the prediction unit 42 of the optimization control unit 41 of the optimization controller 31 applies a plurality of air conditioning set temperatures A to the prediction model of FIG. Thus, a plurality of power consumption TGT1 after one hour is predicted, and a plurality of air conditioning set temperatures A are also applied to the prediction model of FIG. 11 to predict a plurality of discomfort indices TGT2 after one hour.

  In this example, assuming that the air conditioning set temperature A is 21 ° C., 22 ° C., 23 ° C., and 24 ° C., the air conditioning set temperature A is 22 ° C., 23 ° C., and 24 ° C. in the prediction model of FIG. The discomfort index TGT2 after 1 hour becomes comfortable, and in the prediction model of FIG. 10, when the air conditioning set temperature is 23 ° C., the power consumption TGT1 after 1 hour is the smallest 3 kW. Therefore, also in this embodiment, the optimum value calculation unit 44 calculates 23 ° C. as the optimum value Aopt of the air conditioning set temperature A, and the data transmission unit 46 transmits to the air conditioning device control unit 32.

  As described in detail above, the store air conditioning system 24 of the present invention builds the database 37 by accumulating the outside air temperature T, the air conditioning set temperature A, the power consumption P, and the discomfort index D for a predetermined period (one year), The prediction model creation unit 38 performs machine learning based on the database 37, and from the latest outside air temperature T, air conditioning set temperature A, power consumption P, and discomfort index D for a predetermined time (1 hour). A prediction model for predicting the subsequent power consumption TGT1 and the discomfort index TGT2 is created, and the prediction unit 42 applies a plurality of air conditioning set temperatures A to the prediction model, whereby the power consumption TGT1 after a predetermined time (1 hour). And an unpleasantness index TGT2 are predicted, and the optimum value calculation unit 44 calculates a predetermined time (1 hour) from the predicted power consumption TGT1 and unpleasantness index TGT2 after the predetermined time (1 hour). ) In the range in which the later discomfort index TGT2 can be tolerated, the optimum value Aopt of the air conditioning set temperature A at which the power consumption TGT1 after the predetermined time (one hour) becomes the smallest is calculated, and the air conditioner control unit 32 calculates the optimum value. Since the optimum value Aopt calculated by the unit 44 is set as the air conditioning set temperature and the operation of the air conditioner 19 that air-conditions the interior of the store 1 is controlled, the air conditioner 19 and the air conditioner 19 are within the allowable range of the discomfort index D in the store 1. The air conditioning set temperature A is automatically adjusted to the optimum value Aopt that can minimize the electric power P consumed by the refrigeration apparatus 21, and the operation of the air conditioning apparatus 19 can be controlled.

  Thereby, the power consumption P of the air conditioner 19 and the refrigeration apparatus 21 can be reduced while ensuring the comfort in the store 1. In this case, in the embodiment, since the prediction model creating unit 38 periodically creates and updates the prediction model, the optimum value Aopt of the air conditioning set temperature A is accurately determined according to the change in the environment surrounding the store 1. Can be calculated.

  Further, in the embodiment, the prediction unit 42 periodically predicts a plurality of power consumption TGT1 and discomfort index TGT2 after a predetermined time (one hour), and the optimum value calculation unit 44 optimizes the optimum value Aopt every time the prediction unit 42 predicts. Therefore, the optimum value Aopt of the air conditioning set temperature A can be calculated accurately in response to a change in the situation in the store 1 quickly.

(6) Other examples of optimization controller Next, FIG. 12 has shown the other example of a structure of the optimization controller 31 which comprises the shop air conditioning system 24 of this invention. In the embodiment of FIG. 3, all functions of the optimization controller 31 are provided on the store 1 side. However, in this embodiment, the prediction model creation unit 38 of FIG. On the side.

  That is, in the store air conditioning system 24 in this case, the optimization controller 31A on the store 1 side does not create a prediction model, and transmits the database 37 constructed on the optimization controller 31A side to the server 47. Then, the prediction model creation unit 38 of the server 47 creates a prediction model (reference numeral 39) and transmits it to the optimization control unit 41 of the optimization controller 31A.

  The prediction unit 42 of the optimization controller 31A predicts the power consumption TGT1 and the discomfort index TGT2 after 1 hour using this prediction model, calculates the optimum value Aopt of the air conditioning set temperature A, and the data transmission unit 46 performs air conditioning. The data is transmitted to the device control unit 32. Thus, if the prediction model is created on the server 47 side, there is an advantage that the control on the store 1 side is simplified.

(7) Other Configurations In the above-described embodiment, multiple regression analysis is adopted as linear regression analysis performed by machine learning. However, not limited to this, generalized linear regression analysis can also be used. Also, the above-described nonlinear regression analysis is not limited to the decision tree analysis shown in the other embodiments, and random forest analysis, neural network analysis, SVM analysis, and the like can be used.

  In the embodiment, the power consumption TGT1 and the discomfort index TGT2 after 1 hour are predicted by multiple regression analysis, or the power consumption TGT1 and the discomfort index TGT2 after 1 hour are predicted by decision tree analysis. However, the power consumption TGT1 may be predicted by linear regression analysis, and the discomfort index TGT2 may be predicted by nonlinear regression analysis, or vice versa.

  Furthermore, in the embodiment described above, the database 37 is constructed by accumulating the outside air temperature T, the air conditioning set temperature A, the power consumption P, and the discomfort index D for a predetermined period (one year). In addition, data regarding the operating factors of the air conditioner 19 and the refrigeration apparatus 21 that affect the power consumption P and the discomfort index D may be additionally provided in the database 37.

  The operating factors to be added in this case include the operation mode of the air conditioner 19 (cooling, heating, dry, etc.), the internal temperature of the showcases 4 and 11, the air volume of the internal circulation fan in the showcases 4 and 11, the refrigeration system The target low pressure 21, the high pressure of the refrigeration apparatus 21, the rotation speed of the compressor of the refrigeration apparatus 21 (inverter control), the minimum valve opening of the expansion valve of the refrigeration apparatus 21, and the operating state of the total heat exchanger 22 can be considered.

  In that case, the prediction model creation unit 38 creates a prediction model for predicting the power consumption TGT1 and the discomfort index TGT2 after a predetermined time (one hour) by adding the added driving factor, and the prediction unit 42 By applying a plurality of operation factors added to the prediction model in addition to the air conditioning set temperature A, a plurality of power consumption TGT1 and discomfort index TGT2 after a predetermined time (1 hour) are predicted.

  The optimum value calculation unit 44 is determined within a range in which the discomfort index TGT2 after a predetermined time (1 hour) is allowable from the power consumption TGT1 and the discomfort index TGT2 after a plurality of predetermined times (1 hour) predicted by the prediction unit 42. The optimum value of the added operation factor that minimizes the power consumption TGT1 after time (1 hour) is calculated.

  If the air conditioner control unit 32 and the refrigerating device control unit 33 control the operation of the air conditioner 19 and the refrigerating device 21 using the optimum value calculated by the optimum value calculating unit 44 as an added operation factor, the outside air temperature T In addition, the operating factor that affects the power consumption P and the discomfort index D other than the air conditioning set temperature A can also be controlled with the optimum value, and it is possible to further improve the comfort and reduce the power consumption.

  Further, for example, assuming that a showcase is installed in the store 1 of the embodiment in addition to the showcases 4 and 11, for example, as the above-described operation factor related to the showcase and the refrigeration apparatus, the data of similar devices is averaged. It can be considered that the values, maximum values, minimum values, and standard deviation are combined into one. By doing so, even when the configuration of the showcase of the store 1 is subsequently changed, the database 37 can be constructed without any trouble, and the power consumption TGT1 and the discomfort index TGT2 can be predicted and the optimum values can be calculated. It becomes possible.

DESCRIPTION OF SYMBOLS 1 Store 4, 11 Showcase 15 Refrigerator 17 Indoor unit 19 Air conditioner 20 Outdoor unit 21 Refrigerator 22 Total heat exchanger 24 Store air-conditioning system 26 Power consumption detection part 27 Outside air temperature detection part 28 In-store temperature detection part 29 In-store humidity detection part DESCRIPTION OF SYMBOLS 31 Optimization controller 32 Air conditioning apparatus control part 33 Refrigeration apparatus control part 34 Data receiving part 36 Discomfort index calculation part 37 Database 38 Prediction model creation part 42 Prediction part 44 Optimal value calculation part

Claims (6)

In the store air conditioning system that air-conditions the store where the refrigeration system including the showcase is installed,
An air conditioner control unit for controlling the operation of the air conditioner for air conditioning the store based on a predetermined air conditioning set temperature;
An outside temperature detector for detecting the outside temperature;
An in-store temperature detector that detects the temperature in the store;
An in-store humidity detector that detects humidity in the store;
A power consumption detector that detects power consumed by the air conditioner and the refrigeration apparatus;
A discomfort index calculating unit for calculating a discomfort index in the store from the temperature and humidity in the store;
A database constructed by accumulating at least the outside temperature, the air conditioning set temperature, the power consumption, and the discomfort index for a predetermined period;
A prediction model for performing machine learning based on the database and predicting the power consumption and the discomfort index after a predetermined time from at least the latest outside air temperature, the air conditioning set temperature, the power consumption, and the discomfort index A prediction model creation unit for creating
A prediction unit that predicts a plurality of the power consumption and discomfort index after a predetermined time by applying a plurality of air conditioning set temperatures to the prediction model created by the prediction model creation unit;
The optimum air conditioning set temperature at which the power consumption after a predetermined time is minimized within the allowable range of the discomfort index after a predetermined time from the power consumption and the discomfort index after a plurality of predetermined times predicted by the prediction unit An optimal value calculation unit for calculating a value,
The air conditioner control unit controls the operation of the air conditioner using the optimum value calculated by the optimum value calculation unit as the air conditioning set temperature.   The store air conditioning system according to claim 1, wherein the prediction model creation unit periodically creates and updates the prediction model.   The prediction model creation unit performs machine learning by any one of linear regression analysis and non-linear regression analysis, or a combination thereof, and creates the prediction model. The store air conditioning system described in 1.   The prediction unit periodically predicts a plurality of the power consumption and discomfort index after a predetermined time, and the optimal value calculation unit calculates the optimal value every time the prediction unit predicts. The store air conditioning system according to any one of claims 1 to 3. In the database, the air conditioner that influences the power consumption and the discomfort index, and / or data regarding the operating factor of the refrigeration apparatus are additionally provided,
The prediction model creating unit creates a prediction model for predicting the power consumption and discomfort index after a predetermined time by adding the added driving factor,
The prediction unit predicts a plurality of the power consumption and discomfort index after a predetermined time by applying a plurality of the added operation factors in addition to the air conditioning set temperature to the prediction model,
The optimum value calculation unit has the smallest power consumption after a predetermined time in a range in which the discomfort index after a predetermined time can be tolerated from the power consumption and the discomfort index after a plurality of predetermined times predicted by the prediction unit. Calculating the optimum value of the added operating factor,
The air conditioning device control unit and / or the refrigeration device control unit that controls the operation of the refrigeration device, the air conditioning device, and / or the optimum value calculated by the optimum value calculation unit as the added operating factor The store air conditioning system according to any one of claims 1 to 4, wherein operation of the refrigeration apparatus is controlled.   The added operation factor includes the operation mode of the air conditioner, the temperature in the showcase, the air volume of the circulation fan in the showcase, the target low pressure of the refrigeration apparatus, the high pressure of the refrigeration apparatus, One of the number of rotations of the compressor of the refrigeration apparatus, the minimum valve opening of the expansion valve of the refrigeration apparatus, the operating state of the total heat exchanger constituting a part of the air conditioner, or a combination thereof, or The store air conditioning system according to claim 5, which is all of them.

Images