JP2009204195A - Air conditioning system and power consumption estimating device for building air-conditioning equipment - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an air conditioning system and a power consumption estimating device for air conditioning equipment capable of estimating power consumption per month. <P>SOLUTION: This air conditioning system comprises a database 31 storing actual operation data such as power consumption of the building air conditioning equipment, an outside air temperature, a room temperature and set temperatures of air conditioners respectively installed in the building, corresponding to date, a data designating section 32 designating the plurality of actual operation data used in estimating the power consumption of an estimation day, a data extracting section 33 extracting the plurality of actual operation data designated by the data designating section 32 from the database 31, and a statistics estimating section 34 estimating the power consumption of the estimation day by using a statistical method. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to, for example, an air conditioning system that centrally manages a plurality of air conditioners provided in a building and a power consumption prediction device for building air conditioning equipment used in the air conditioning system.

Conventionally, an air conditioning system that centrally manages the operation of a plurality of air conditioners installed in a building is known. For example, in Patent Documents 1 and 2, a host computer and an air conditioning control monitoring device are connected via a building management communication network, and an air conditioning control monitoring device and a plurality of air conditioners are connected via an air conditioning control network. An air conditioning system in which an air conditioning control monitoring device controls each air conditioner based on an operation control command from a host computer is disclosed.
JP 2005-291610 A JP-A-2005-308278

  By the way, in buildings where many air conditioners are installed, the amount of power consumed by the air conditioning equipment accounts for most of the power consumed by the entire building. For this reason, for example, it is important to predict the power consumption of the entire month during the month.

  This invention is made | formed in view of such a situation, and it aims at providing the power consumption prediction apparatus of the air conditioning system and air conditioning equipment which can estimate the power consumption per month.

In order to solve the above problems, the present invention employs the following means.
The present invention relates to storage means for storing actual operation data including power consumption of building air conditioning equipment, outside air temperature, room temperature, and set temperature of each air conditioner installed in the building in association with the date. Data specifying means for specifying a plurality of actual operation data used for prediction of power consumption on the prediction target day, and a data extraction means for extracting a plurality of actual operation data specified by the data specifying means from the storage means A power consumption prediction apparatus for building air conditioning equipment, comprising statistical prediction means for predicting power consumption on the prediction target day using a statistical method based on the actual operation data extracted by the data extraction means I will provide a.

  According to such a configuration, the plurality of actual operation data used for the power consumption amount prediction for the prediction target day is specified by the data specifying unit, and the specified actual operation data is extracted from the storage unit by the data extraction unit. Then, using the extracted actual operation data, the power consumption on the prediction target day is predicted by the statistical prediction means. And by changing the said prediction object day sequentially, the power consumption in each prediction object day will be estimated sequentially. Thus, by repeatedly predicting the power consumption amount on each prediction target day, for example, it is possible to predict the power consumption amount on each day from the middle of the month to the end of the month. As a result, the actual power consumption is used for the date when the actual operation data is stored in the storage means, and the future date when the actual operation data is not stored in the storage means is predicted by the statistical prediction means. By using the amount of consumed power, it becomes possible to predict the total amount of power consumed by the air conditioning equipment per month.

  In the power consumption prediction apparatus for the building air-conditioning equipment, the data specifying means may specify actual operation data whose air-conditioning usage status is similar to the prediction target date.

  According to such a configuration, the power consumption of the air conditioning use state is predicted using the actual operation data similar to the prediction target day, so that the prediction accuracy can be improved.

  In the power consumption prediction apparatus for building air conditioning equipment, the data designating unit may designate actual operation data for a predetermined past period on the same day of the week as the prediction target date.

  As described above, the actual operation data in the past predetermined period on the same day of the week as the prediction target day is specified, so that it is possible to easily specify and extract the actual operation data having a similar air condition utilization status to the prediction target day. .

  In the power consumption prediction apparatus for building air conditioning equipment, the data specifying means may include input means that can be input by a user.

  According to such a configuration, it is possible for the user to specify actual operation data used for prediction of power consumption.

  In the power consumption prediction apparatus for building air conditioning equipment, the statistical prediction means includes, for each of the actual operation data extracted by the data extraction means, a total power consumption for one day relating to the air conditioning equipment, The average outside air temperature, the weighted average suction temperature based on the time for one day and the capacity of the indoor unit, and the weighted average set temperature based on the time for the day and the capacity of the indoor unit are calculated, respectively. It is good also as estimating for every said actual operation data, and estimating the power consumption of the said prediction object day from the autoregressive model which is a linear combination of this state vector.

  According to such a configuration, the past power consumption, the average outside air temperature, the weighted average suction temperature (average room temperature), and the weighted average set temperature, which are important parameters for grasping the operation status of the air conditioning, are used. It becomes possible to increase the reliability of the prediction of the power consumption on the target day.

  The building air-conditioning equipment power consumption prediction apparatus uses the power consumption predicted by the statistical prediction means to calculate a monthly predicted power consumption calculation means for calculating a monthly predicted power consumption for the air-conditioning equipment of the entire building; And an output means for outputting the monthly predicted power consumption.

  According to such a configuration, since the monthly predicted power consumption calculated by the monthly predicted power consumption calculation means is output by the output means, the user can easily grasp the monthly predicted power consumption. .

  In the above-mentioned building air-conditioning equipment power consumption prediction device, when the monthly predicted power consumption exceeds a preset target power consumption, the statistical prediction means uses the actual power consumption predicted. Data correction means for correcting a set temperature of the operation data by a predetermined amount, and the statistical prediction means predicts the power consumption amount related to each prediction target day again using the actual operation data corrected by the data correction means. The monthly power consumption calculating means may calculate the monthly predicted power consumption again using the predicted power consumption again.

  According to such a configuration, when the monthly predicted power consumption exceeds the target power consumption, the set temperature is corrected by a predetermined amount in the actual operation data. Then, the prediction of the power consumption amount for the prediction target day using the corrected actual operation data is performed again, and the predicted power consumption amount for the month is calculated again using the recalculated power consumption amount. As a result, when the set temperature is corrected, it is possible to present to the user how much the power consumption is reduced.

  In the power consumption prediction apparatus for a building air conditioner, the data correction unit may repeatedly correct the set temperature of the actual operation data until the monthly predicted power consumption is within the target power consumption. Good.

  According to such a configuration, it is possible to present to the user a set temperature for ensuring that the monthly predicted power consumption is within the target power consumption.

  This invention provides an air-conditioning system provided with the power consumption amount prediction apparatus of one of the said building air-conditioning equipment.

  The present invention relates to storage means for storing actual operation data including power consumption of building air conditioning equipment, outside air temperature, room temperature, and set temperature of each air conditioner installed in the building in association with the date. The process of designating a plurality of actual operation data used for the prediction of the power consumption amount on the prediction target day, the process of extracting a plurality of designated actual operation data from the storage means, and based on the extracted actual operation data And a method for predicting the power consumption amount of a building air-conditioning facility, comprising a step of predicting the power consumption amount of the prediction target day using a statistical method.

  The present invention relates to storage means for storing actual operation data including power consumption of building air conditioning equipment, outside air temperature, room temperature, and set temperature of each air conditioner installed in the building in association with the date. Based on the extracted actual operating data, the process of specifying a plurality of actual operating data for use in the prediction of the power consumption amount for the prediction target day, the process of extracting the specified plurality of actual operating data from the storage means, The present invention provides a power consumption prediction program for building air conditioning equipment that causes a computer to execute a process of predicting the power consumption of the prediction target day using a statistical method.

  According to the present invention, it is possible to predict the power consumption per month.

Hereinafter, an air-conditioning system and a power consumption prediction device for air-conditioning equipment according to each embodiment of the present invention will be described with reference to the drawings.
[First Embodiment]
FIG. 1 is a block diagram showing the overall configuration of the air conditioning system according to the first embodiment of the present invention. As shown in FIG. 1, an air conditioning system according to this embodiment includes a host computer 1, an air conditioning control monitoring device 3 connected to the host computer 1 via a building management communication network 2, an air conditioning control monitoring device 3, and an air conditioning system. A plurality of air conditioners 5 connected via a control network 4, a host computer 1, an air conditioning control monitoring device 3, and a power consumption prediction device 10 connected via a building management communication network 2 are provided.

The host computer 1 is, for example, a CPU (Central Processing Unit), ROM (Read Only)
Memory), RAM (Random Access)
A computer for building management including a memory, an input device, a display device, and the like, and performs operation management of facilities provided in the building.

  The building management communication network 2 is a network using a communication protocol (for example, TCP / IP) standardized for building management, and is, for example, a LAN (Local Area Network), an intranet, the Internet, or the like.

The air-conditioning control monitoring device 3 is a device for performing operation control and operation management of the air conditioner 5 provided in each room in the building, and monitors the operation state of each air conditioner 5 and is the monitoring result. The operating state information is provided to the host computer 1 and the power consumption prediction device 10.
The operation state information includes, for example, information on the operation type such as cooling operation, heating operation, and operation stop, as well as set temperature, room temperature (intake air temperature of the indoor unit), outside air temperature, operation time, and the like. .
The air conditioning control network 4 is a network that uses a standardized communication protocol for controlling and monitoring the air conditioner 5.

The power consumption amount prediction device 10 is a device that can predict, for example, the power consumption amount consumed by all the air conditioners 5 arranged in a building on a monthly basis.
FIG. 2 is a block diagram showing a schematic configuration of the power consumption prediction apparatus 10 according to the present embodiment of the present invention.
As shown in FIG. 2, the power consumption prediction apparatus 10 according to the present embodiment includes a computer system (computer system), and includes a CPU (central processing unit) 21, a RAM (Random Access).
Main storage device 22 such as Memory, ROM (Read Only Memory), HDD (Hard Disk)
An auxiliary storage device 23 such as a drive), an input device 24 such as a keyboard and a mouse, and an output device 25 such as a display device and a printer.
Various programs are stored in the auxiliary storage device 23, and the CPU 21 reads out the programs from the auxiliary storage device 23 to the main storage device 22 such as a RAM, and executes them to implement various processes.

  FIG. 3 is a functional block diagram in which the functions of the power consumption prediction apparatus 10 are expanded. As shown in FIG. 3, the power consumption prediction apparatus 10 includes a database (storage unit) 31, a data designation unit (data designation unit) 32, a data extraction unit (data extraction unit) 33, a statistical prediction unit (statistic prediction unit). ) 34 and a monthly predicted power consumption calculation unit (monthly predicted power consumption calculation means) 35.

  In the database 31, actual operation data including the power consumption of the building air conditioning equipment, the outside air temperature, the room temperature, and the set temperature of each air conditioner installed in the building are stored in association with the date. . The actual operation data includes, for example, operating state information supplied from the air conditioning control monitoring device 3 and a building supplied from a power monitoring device (not shown) that monitors the power consumption of the entire air conditioning equipment arranged in the building. It is created from the power consumption information related to the air conditioning equipment. In the following description, it is assumed that “actual operation data” is composed of a plurality of data groups such as the power consumption, the outside air temperature, the room temperature, and the set temperature collected every day.

The data specifying unit 32 specifies a plurality of actual operation data used for power consumption amount prediction on the prediction target day. For example, the data designating unit 32 designates N pieces of actual operation data whose air conditioning usage status is similar to the prediction target date. In other words, a plurality of dates used for power consumption prediction are designated.
For example, when an air conditioning operation pattern in which one week is one cycle is set in advance, the similarity between the air conditioning operation pattern of the prediction target day and the air conditioning operation pattern of each day is calculated, and the similarity is a predetermined value. The actual operation data as described above may be designated. Alternatively, actual operation data on the same day of the week as the prediction target day may be designated for the purpose of simplifying the process. Moreover, it is good also as a structure which a user can examine the past air-conditioning operation pattern etc., and a user can designate the thing close | similar to the air-conditioning use condition of a prediction object day from the said input device (refer FIG. 2).
In the present embodiment, it is assumed that N pieces of actual operation data on the same day of the week as the prediction target date are specified from the newest date.
The data extraction unit 33 extracts a plurality of actual operation data designated by the data designation unit 32 from the database 31.

  The statistical prediction unit 34 predicts the power consumption amount on the prediction target day using a statistical method based on the N actual operation data extracted by the data extraction unit 33. For example, the statistical prediction unit 34 uses the N pieces of actual operation data extracted by the data extraction unit 33, the power consumption of the air conditioning equipment for the entire building for one day, the average outside air temperature for one day, one day The weighted average suction temperature based on the minutes and indoor unit capacity, and the weighted average set temperature based on the time and indoor unit capacity for one day are calculated for each actual operation data, and a state vector having these as elements is calculated for each actual operation data. And the power consumption amount of the prediction target day is predicted from an autoregressive model that is a linear combination of the state vectors. As a result, N state vectors are generated from the N actual operation data.

Specifically, the statistical prediction unit 34 calculates the autoregressive model (Auto
Regressive model) is generated using N state vectors, and this autoregressive model is solved by using a known method such as a minimum AIC (Akaike Information Criterion) method, thereby predicting power consumption on the prediction target day. To do.

  In the above equation (1), A (i) (i = 1, 2,..., N) is an N number of 4 × 4 coefficient matrix, which is called an autoregressive model. System identification is performed online using the AIC method. The order of this coefficient matrix is determined according to the number of elements of the state vector. That is, in this embodiment, the power consumption of the air conditioning equipment for the entire building for one day, the average outside air temperature for one day, the time for one day, the weighted average suction temperature by the indoor unit capacity, and the time for one day Since the state vector is created using four elements consisting of the weighted average set temperature based on the indoor unit capacity, the coefficient matrix has 4 rows and 4 columns.

  U (k) is the k-th white noise error. Wh (k) is the accumulated power consumption in the air conditioner for the entire building for the day for the kth actual operation data, and To (k) is the average daily outside air for the kth actual operation data. The temperature, Ta (k) is the weighted average suction temperature (room temperature) based on the operation time and the indoor unit capacity for one day for the kth actual operation data, and Ts (k) is one for the kth actual operation data. This is the weighted average set temperature based on the daily operation time and indoor unit capacity.

About the said suction temperature (room temperature), since an operation time and power consumption differ with each air conditioner, it considers an operation time and an indoor unit capacity | capacitance, and it is trying to take out an average value.
Similarly, for the set temperature, the degree of contribution to the power consumption varies depending on the operating time and the size of the indoor unit capacity for each air conditioner. I try to put out a value.
The statistical prediction unit 34 obtains a matrix A (i) that minimizes U (k) in the above equation (1), and predicts power consumption on the prediction target day using this matrix A (i). As described above, the minimum AIC method or the like may be used for obtaining the matrix A (i) that minimizes U (k). Further, “N”, which means the number of actual operation data, is also determined by solving the autoregressive model. For example, once the autoregressive model is solved, the optimum number N of actual operational data is obtained, and after N is determined, the above calculation is performed again using the determined N actual operational data, thereby predicting The prediction accuracy of power consumption on the target day can be increased.

  The monthly predicted power consumption calculation unit 35 calculates the monthly predicted power consumption related to the air conditioning equipment of the entire building using the power consumption predicted by the statistical prediction unit 34 and the actual operation data stored in the database 31. The calculation result is output to, for example, the output device 25 (see FIG. 2).

  Next, processing contents executed in each unit included in the air conditioning system having the above configuration, particularly, the power consumption amount prediction apparatus 10 will be described with reference to FIGS. 1 to 3. Note that various processes described later realized by the units illustrated in FIG. 3 are executed by the CPU 21 illustrated in FIG. 2 reading out the power consumption amount prediction program stored in the auxiliary storage device 23 to the main storage device 22. Is realized.

First, the air conditioner control and monitoring device 3 controls the operation of the air conditioner 5 installed in the building based on a control command from the host computer 1 or the like, so that the operation state information of each air conditioner 5 becomes the air conditioner control and monitor device. 3, this operation state information is transmitted from the air conditioning control monitoring device 3 to the power consumption prediction device 10 via the building management communication network 2. Further, the amount of power consumed by the air conditioner 5 in the building is monitored by a power monitoring device (not shown), and information related to the power consumption is transmitted from the power monitoring device to the power consumption prediction device 10.
As a result, in the database 31 in the power consumption prediction device 10, the actual operation data including the power consumption of the building air conditioning equipment for one day, the outside air temperature, the room temperature, and the set temperature based on these pieces of information are dated. Correspondingly, they are stored sequentially.

Next, at a predetermined time every day (for example, midnight), the power consumption prediction apparatus 10 uses the actual operation data accumulated in the database 31 until the previous day to reduce the power consumption after today. Forecast on a daily basis.
For example, if the current time is 0:00 on October 20, 2007, the power consumption prediction device 10 predicts the power consumption after October 20 on a daily basis.

First, a prediction target date is set to October 20, and N (for example, five) actual operation data used for prediction of power consumption on October 20 are designated by the data designation unit 32. Specifically, since October 20, 2007 is a Saturday, October 13 which is Saturday one week ago, October 6 which is Saturday two weeks ago, similarly, September 29, The actual operation data on September 22 and September 15 is designated by the data designation unit 32.
The data extraction unit 33 extracts the Saturday actual operation data for five weeks designated by the data designation unit 32 from the database 31 and outputs the extracted five actual operation data to the statistical prediction unit 34.

  The statistical prediction unit 34 uses the five actual operation data extracted by the data extraction unit 33 for each actual operation data, in other words, for every day, the power consumption Wh of the air conditioning equipment for the entire building for one day. Calculate the average outside air temperature To for one day, the weighted average suction temperature Ta based on the time for one day and the indoor unit capacity, and the weighted average set temperature Ts based on the time for one day and the indoor unit capacity, respectively. An autoregressive model using the state vector is generated based on (1) above. Then, by solving these autoregressive models, the power consumption amount Wh (k) on October 20, which is the prediction target day, is predicted. In this way, when the prediction of the power consumption amount on October 20 is completed, October 21 is set as the next prediction target day, and the power consumption amount is predicted in the same procedure. Then, by sequentially changing the prediction target date, the power consumption amount until October 31, which is the last day of October, is predicted.

  When the prediction of the power consumption from October 20 to the end of October is completed by the statistical prediction unit 34, the monthly predicted power consumption calculation unit 35 stores the power consumption up to October 19 in the database 31. The stored monthly power consumption is used, and for the power consumption after 20th, the power consumption predicted by the statistical prediction unit 34 is used. Calculate power consumption. The monthly predicted power consumption calculation unit 35 outputs the calculation result and information on each power consumption used for the calculation to the output device 25 (see FIG. 2). As a result, the monthly predicted power consumption for October is displayed on the output device 25, for example, the monitor of the display device, etc., so that it is possible to notify the user of this information.

Note that the display mode of the display device is not particularly limited. For example, the monthly predicted power consumption may be displayed only as a numerical value, or may be displayed as a graph, for example, as shown in FIG.
FIG. 4 is a diagram illustrating a display example displayed on the display device. In the graph shown in FIG. 4, the power consumption for each date is shown as a bar graph, and the integrated power consumption is shown as a line graph. In addition, the bar graph and line graph up to October 19 in which the actual operation data exist are black, while the bar graph and line graph after October 20 in which the actual operation data does not exist are predicted. It is represented in white.
In this way, the user can easily determine whether or not the data is predicted data by changing the display mode between when actual operation data exists and when prediction is performed.

As described above, according to the air conditioning system and the power consumption prediction device according to the present embodiment, it is possible to predict the power consumption per month. As a result, even during the month, the user can grasp the approximate amount of power consumption for one month of the month. It is possible to adjust the temperature setting of the air conditioner inside.
Furthermore, since the power consumption of the prediction target day is predicted using actual operation data whose air condition usage status is similar to the prediction target date, for example, actual operation data on the same day of the week, the prediction accuracy can be improved. .

[Second Embodiment]
Next, an air conditioning system and a power consumption prediction device according to a second embodiment of the present invention will be described with reference to FIG.
In the air conditioning system according to the present embodiment, the configuration of the power consumption prediction device is different from that of the first embodiment described above.
Hereinafter, regarding the power consumption prediction apparatus of the present embodiment, description of points that are common to the first embodiment will be omitted, and different points will be mainly described.

FIG. 5 is a functional block diagram of the power consumption prediction apparatus according to the present embodiment. As shown in FIG. 5, the power consumption amount prediction apparatus 10 ′ according to the present embodiment is configured to further include a data correction unit (data correction unit) 36.
In the data correction unit 36, when the monthly predicted power consumption calculated by the monthly predicted power consumption calculation unit 35 exceeds a preset target power consumption, the statistical prediction unit 34 predicts the power consumption. The set temperature of the actual operation data used for the correction is corrected by a predetermined amount.
For example, the data correction unit 36 corrects the set temperature of the actual operation data as shown in the following equation (2).

  Ts ′ (k−i) = Ts (k−i) + ΔTs (2)

  In the above equation (2), Ts ′ (ki) is the set temperature after correction in the kth actual operation data, and Ts (ki) is the setting before correction in the kth actual operation data. The temperature and ΔTs are correction amounts. For example, ΔTs = + 0.5 ° C. is set for cooling operation, and ΔTs = −0.5 ° C. is set for heating operation. This correction amount is a value that can be arbitrarily set. For example, the correction amount may be configured to be arbitrarily input by the user from the input device 24 (see FIG. 2).

As described above, the corrected set temperature Ts ′ (k−i) is calculated by the data correction unit 36, and when this is given to the statistical prediction unit 34, the statistical prediction unit 34 corrects the set temperature Ts ′ (k after correction). -I) is used to generate an autoregressive model based on (1) above, and by solving this, the power consumption on the prediction target date is predicted.
Specifically, the power consumption amount for the prediction target day is calculated again based on the following equation (3).

When the statistical prediction unit 34 performs the prediction of the power consumption amount from October 20 to the end of October again using the corrected set temperature, the predicted power consumption amount is supplied to the monthly predicted power consumption calculation unit 35. Output.
The monthly predicted power consumption calculating unit 35 uses the actual power consumption stored in the database 31 for the date on which the actual operation data exists, and for the future date on which the actual operation data does not exist. By using the power consumption predicted by the statistical prediction unit 34, the monthly predicted power consumption related to the air conditioning equipment is calculated and output to the output device 25 (see FIG. 2).

As described above, according to the air conditioning system and the power consumption prediction device according to the present embodiment, when the set temperature is corrected by displaying the corrected monthly predicted power consumption on a display monitor or the like. In addition, it is possible to present to the user how much the power consumption is reduced.
In the present embodiment, when the corrected monthly predicted power consumption exceeds the target power consumption, the data correction unit 36 may further correct the set temperature. In other words, until the monthly predicted power consumption after correction falls within the target power consumption, calculation of monthly predicted power consumption, correction of actual operation data, and statistical prediction using the corrected actual operation data are repeated. Also good. Accordingly, the user can be notified of the set temperature for keeping the monthly predicted power consumption within the target power consumption, and the monthly predicted power consumption can be surely set within the target power consumption.

  Further, in the present embodiment, the data correction unit 36 corrects the set temperature so as to predict the power consumption again, but instead, for example, the rotation speed of the compressor is set to the autoregressive model. When included in the element, the rotational speed of the compressor may be corrected.

  As mentioned above, although embodiment of this invention was explained in full detail with reference to drawings, the specific structure is not restricted to this embodiment, The design change etc. of the range which does not deviate from the summary of this invention are included.

It is a figure showing the whole air-conditioning system composition concerning a 1st embodiment of the present invention. It is the figure which showed the hardware constitutions of the power consumption prediction apparatus which concerns on the 1st Embodiment of this invention. It is the functional block diagram which expanded and showed the function with which the power consumption prediction apparatus which concerns on the 1st Embodiment of this invention is provided. It is the figure which showed the example of 1 output displayed on a display monitor. It is the functional block diagram which expanded and showed the function with which the power consumption amount prediction apparatus which concerns on the 2nd Embodiment of this invention is provided.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Host computer 2 Building management communication network 3 Air-conditioning control monitoring apparatus 4 Air-conditioning control network 5 Air conditioner 10 Power consumption prediction apparatus 21 CPU
22 main storage device 23 auxiliary storage device 24 input device 25 output device 31 database 32 data designation unit 33 data extraction unit 34 statistical prediction unit 35 monthly predicted power consumption calculation unit 36 data correction unit

Claims (11)

Storage means in which actual operation data including power consumption of building air conditioning equipment, outside air temperature, room temperature, and set temperature of each air conditioner installed in the building is stored in association with the date;
A data specifying means for specifying a plurality of actual operation data used for prediction of power consumption on the prediction target day;
Data extraction means for extracting a plurality of actual operation data designated by the data designation means from the storage means;
A power consumption prediction apparatus for building air conditioning equipment, comprising: statistical prediction means for predicting power consumption on the prediction target day using a statistical method based on the actual operation data extracted by the data extraction means.   The said data designation | designated means is the power consumption amount prediction apparatus of the building air-conditioning equipment of Claim 1 which designates the actual operation data with the utilization condition of an air conditioning similar to the said prediction object day.   The said data designation | designated means is the power consumption amount prediction apparatus of the building air-conditioning equipment of Claim 1 or Claim 2 which designates the actual operation data in the past predetermined period of the same day of the week as the said prediction object day.   The said data designation | designated means is a power consumption amount prediction apparatus of the building air-conditioning equipment of Claim 1 provided with the input means which can be input-operated by the user. The statistical prediction means includes
In each of the actual operation data extracted by the data extraction means, the weighted average suction based on the total power consumption for one day, the average outside air temperature for one day, the time for one day, and the indoor unit capacity related to the air conditioning equipment Calculating the temperature, the weighted average set temperature by the time of one day and the capacity of the indoor unit, and obtaining a state vector having these as elements for each of the actual operation data,
The power consumption amount prediction apparatus for a building air conditioning facility according to any one of claims 1 to 4, wherein the power consumption amount of the prediction target day is predicted from an autoregressive model that is a linear combination of the state vectors. Using the power consumption predicted by the statistical prediction means, a monthly predicted power consumption calculating means for calculating a monthly predicted power consumption related to the air conditioning equipment of the entire building;
The power consumption prediction apparatus of the building air-conditioning equipment according to any one of claims 1 to 5, further comprising: an output unit that outputs the monthly predicted power consumption. Data correction that corrects the set temperature of the actual operation data used by the statistical prediction means for prediction of power consumption by a predetermined amount when the monthly predicted power consumption exceeds a preset target power consumption With means,
The statistical prediction means predicts again the power consumption related to each prediction target day using the actual operation data corrected by the data correction means,
The said monthly power consumption calculation means is the power consumption prediction apparatus of the building air-conditioning equipment of Claim 6 which calculates the said monthly predicted power consumption again using the said predicted power consumption.   The said power correction means is a power consumption amount prediction apparatus of the building air-conditioning equipment of Claim 7 which repeats correction | amendment of the setting temperature of the said actual operation data until the said monthly estimated power consumption amount is less than the said target power consumption amount. .   An air conditioning system provided with the power consumption prediction apparatus for building air conditioning equipment according to any one of claims 1 to 8. Predicted date from the storage means in which actual operation data including energy consumption of building air conditioning equipment, outside air temperature, room temperature, and set temperature of each air conditioner installed in the building is stored in association with the date Specifying multiple production data to be used for power consumption prediction
Extracting a plurality of designated operational data from the storage means;
A method for predicting the power consumption amount of a building air-conditioning facility, comprising: a step of predicting the power consumption amount of the prediction target day using a statistical method based on the extracted actual operation data. Predicted date from the storage means in which actual operation data including energy consumption of building air conditioning equipment, outside air temperature, room temperature, and set temperature of each air conditioner installed in the building is stored in association with the date A process for specifying a plurality of actual operation data used for power consumption prediction of
A process of extracting a plurality of designated actual operation data from the storage means;
A building air-conditioning equipment power consumption prediction program that causes a computer to execute a process of predicting the power consumption of the prediction target day using a statistical method based on the extracted actual operation data.

Images