JP2021002311A - Analyzer - Google Patents

Abstract

To provide a technique that can accurately analyze power consumption by purpose.SOLUTION: An analyzer 100 analyzing the power consumption state of a building comprises an acquisition unit 10, a determination unit 14, and an estimation unit 15. The acquisition unit 10 acquires electric energy data 12 that indicates the power consumption of the building measured for every time zone in an analysis target period. The determination unit 14 extracts, from the electric energy data 12, data of the lower predetermined number of days of the maximum power consumption of the power consumption measured for every time zone in a day as training data. The determination unit 14 determines, for each day included in the analysis target period, whether the day is an operating day or a non-operating day based on comparison of the training data with determination target data that is data of the day of the electric energy data 12. The estimation unit 15 estimates the power consumption by purpose of the building in a target time zone in a target day included in the analysis target period based on non-operating day data that is data of a non-operating day of the electric energy data 12.SELECTED DRAWING: Figure 3

Description

The present disclosure relates to a technique for analyzing the power consumption state of a building.

Conventionally, a technique for analyzing the power consumption of a building for each purpose has been developed based on the power consumption of the building. For example, Japanese Patent Application Laid-Open No. 2008-298375 (Patent Document 1) discloses an air-conditioning load calculation system that calculates an air-conditioning load of a building from the actual energy usage in the building. The air-conditioning load calculation system selects the second predetermined period with the least energy consumption in the first predetermined period based on the data related to the energy consumption for each time in the first predetermined period. The second predetermined period is, for example, one week. The air conditioning load calculation system calculates the energy-based usage amount in the first predetermined period based on the energy consumption amount in the second predetermined period. The energy-based usage is calculated as the energy usage excluding the air conditioning load. The air conditioning load calculation system calculates the amount of energy used for air conditioning based on the amount of energy used.

Japanese Unexamined Patent Publication No. 2008-298375

In the technique described in Patent Document 1, the energy-based usage amount is calculated based on the energy usage amount in the second predetermined period. Since the second predetermined period is as short as one week, for example, the accuracy of the energy-based usage is low. As a result, the accuracy of calculating the amount of energy used for air conditioning also decreases.

The present invention has been made in view of the above problems, and an object of the present invention is to provide a technique capable of accurately analyzing power consumption for each application.

According to a certain aspect, the analyzer for analyzing the power consumption state of the building includes an acquisition unit, a determination unit, and an estimation unit. The acquisition unit acquires power consumption data indicating the power consumption measured for each time zone of the building during the analysis target period. The determination unit determines whether each day included in the analysis target period is an air conditioner operating day or a non-operating day. The estimation unit estimates the power consumption of each building in the target time zone of the target day included in the analysis target period based on the non-working day data, which is the non-working day data of the electric energy data. The determination unit extracts from the electric energy data the data of the day in which the maximum electric energy consumption is the lower predetermined number of days among the electric energy consumption measured for each time zone in one day as training data. For each day included in the analysis target period, the judgment unit determines whether the day is a working day or a non-working day based on the comparison result between the training data and the power amount data, which is the data of the day. Determine if.

In the above analyzer, the judgment unit creates test data which is time-series data obtained by combining the training data and the judgment target data, and calculates the change point score at each time point in the test data using the change point detection algorithm. You may. The judgment unit determines by a test whether or not the first change point score at the time corresponding to the training data in the test data and the second change point score at the time corresponding to the judgment target data in the test data are equivalent. , When the first change point score and the second change point score are equivalent, it is determined that the day corresponding to the judgment target data is a non-working day, and the first change point score and the second change point score are set. If they are not equivalent, it may be determined that the day corresponding to the determination target data is a working day. The test is, for example, a t-test.

In the above analyzer, when the target day is determined to be a non-working day, the estimation unit may estimate the air-conditioning power consumption for air conditioning in the target time zone of the target day to be zero. Furthermore, when the target day is determined to be a working day, the estimation unit calculates the target time zone on the non-working day from the target power consumption measured in the target time zone on the target day from the non-working day data. The amount obtained by subtracting the representative value of the power consumption of the above may be estimated as the power consumption of the air conditioning component in the target time zone of the target day.

In the above-mentioned analyzer, the acquisition unit may further acquire outside air temperature data indicating the outside air temperature for each time zone in the area including the building during the analysis target period. The estimation unit may extract the minimum power consumption for each outside air temperature zone by using the electric energy data and the outside air temperature data. The estimation unit further calculates a regression equation with the outside temperature as the explanatory variable and the extracted minimum power consumption as the objective variable, and based on the regression equation and the outside temperature in the target time zone of the target day, the target day The base power consumption in the target time zone may be estimated.

In the above analyzer, the estimation unit determines the representative value of the base power consumption in the target time zone on the non-working day from the representative value of the power consumption in the target time zone on the non-working day calculated from the non-working day data. The amount obtained by subtracting the above may be estimated as the power consumption for the activity due to the human activity in the target time zone.

When there is a difference between the target power consumption and the total of the air conditioning power consumption, the base power consumption, and the activity power consumption, the above analyzer makes the target power consumption and the total match. , A correction unit for correcting at least one of the air conditioning power consumption and the activity power consumption may be further provided.

In the above-mentioned analyzer, an activity time zone, which is a time zone in which human activity is scheduled to be performed in the building, may be predetermined. Then, the correction unit may increase the air-conditioning power consumption by the difference when the target time zone is included in the activity time zone and the target power consumption is larger than the total. When the target time zone is included in the activity time zone, the target power consumption is smaller than the total, and the difference is less than or equal to the air conditioning component power consumption, the correction unit sets the air conditioning component power consumption by the difference. You may reduce it. The correction unit is used when the target time zone is included in the activity time zone, the target power consumption is smaller than the total, and the difference exceeds the air conditioning power consumption by an excess amount. May be reduced to 0, and the power consumption for the activity may be reduced by the excess amount. When the target time zone is not included in the activity time zone and the target power consumption is smaller than the total, the correction unit may increase the activity power consumption by the difference. When the target time zone is not included in the activity time zone, the target power consumption is smaller than the total, and the difference is less than or equal to the air conditioning component power consumption, the correction unit sets the air conditioning component power consumption only by the difference. You may reduce it. The correction unit is used when the target time zone is not included in the activity time zone, the target power consumption is smaller than the total, and the difference exceeds the air conditioning power consumption by an excess amount. May be reduced to 0, and the power consumption for the activity may be reduced by the excess amount.

According to the other aspects, the estimation method for estimating the power consumption state of the building includes the first to third steps. The first step is a step of acquiring electric energy data indicating the electric energy consumption measured for each time zone of the building in the analysis target period. The second step is a step of determining whether each day included in the analysis target period is an air conditioning working day or a non-working day. The third step is to estimate the power consumption of each building in the target time zone of the target day included in the analysis target period based on the non-working day data, which is the non-working day data of the power amount data. It is a step. The determination step is a step of extracting as training data the data of the day in which the maximum power consumption of the power consumption measured for each time zone in one day is the lower predetermined number of days from the power amount data and analysis. For each day included in the target period, it is determined whether the day is a working day or a non-working day based on the comparison result between the training data and the power consumption data, which is the data of the day, and the judgment target data. Including steps to do.

In another aspect, the program causes the computer to perform each step of the above analytical method.

According to the technology of the present disclosure, it is possible to analyze the power consumption for each application with high accuracy.

It is a figure which shows the outline of the system including the analyzer according to this embodiment. It is a figure which shows the hardware configuration of an analyzer. It is a figure which shows the functional structure of an analyzer. It is a flowchart which shows an example of the flow of analysis processing in an analyzer. It is a figure explaining the method of estimating the base power consumption. It is a figure which shows the verification result of the estimation accuracy of the base power consumption estimated by the estimation part. It is a figure which shows the application example of ChangeFinder to the test data. It is a figure which shows the verification result of the estimation accuracy of the activity component power consumption estimated by the estimation unit. It is a figure explaining the method of estimating the air-conditioning power consumption. It is a figure which shows the verification result of the estimation accuracy of the air-conditioning power consumption estimated by the estimation unit. It is a figure which shows the verification result of the decomposition accuracy of power consumption into three uses. It is a figure which shows the average value of the error of each estimated value of base power consumption, activity power consumption, and air-conditioning power consumption, and the measured value.

Hereinafter, embodiments according to the present invention will be described with reference to the drawings. In the following description, the same parts and components are designated by the same reference numerals, and duplicate description will not be repeated. In addition, the embodiment and each modification described below may be selectively combined as appropriate.

<A. System configuration>
The configuration of the system including the analyzer according to the present embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an outline of a system including an analyzer according to the present embodiment. As shown in FIG. 1, the system SYS includes an analyzer 100, a building 200, and a server device 300.

The building 200 is, for example, a small-to-medium-sized business building such as a store or an office. A smart meter 210 is installed in the building 200. The smart meter 210 measures and records the total power consumption (hereinafter, simply referred to as “power consumption”) for each time zone used by various devices 220 in the building 200. Specifically, the power consumption is measured for each time zone in which 0 o'clock to 24:00 is divided by a predetermined time length (for example, 30 minutes or 15 minutes).

The smart meter 210 communicates with the server device 300 and transmits the electric energy data indicating the measured power consumption to the server device 300.

The server device 300 stores the electric energy data received from the smart meter 210 of the building 200.

The analyzer 100 is connected to the network, and acquires the electric energy data of the building 200 from the server device 300 via the network. The analyzer 100 analyzes the power consumption state of the building 200 based on the power data. The analyzer 100 may use the analysis results to generate proposal information regarding energy saving of the building 200. The generated proposal information is appropriately distributed to the manager who manages the building 200. By confirming the proposal information, the manager can take appropriate actions for energy saving of the building 200.

<B. Analytical device hardware configuration>
FIG. 2 is a diagram showing a hardware configuration of the analyzer. As shown in FIG. 2, the analyzer 100 is generated by executing a program by a processor 101 that executes a program, a ROM (Read Only Memory) 102 that stores data in a non-volatile manner, and a processor 101 as main components. A RAM (Random Access Memory) 103 that volatilely stores the input data or data input via an input device, a hard disk (HDD) 104 that stores the data non-volatilely, and a communication IF (Interface) 105. , The operation key 106, the power supply circuit 107, and the display 108. The components are connected to each other by a data bus. The communication IF 105 is an interface for communicating with other devices.

The processing in the analyzer 100 is realized by the program 110 executed by each hardware and the processor 101. Such a program 110 is stored in the HDD 104 in advance. However, the program 110 may be stored in another storage medium and distributed as a program product. Alternatively, the program 110 may be provided as a program product that can be downloaded by an information provider connected to the so-called Internet. Such a program 110 is stored in the HDD 104 after being read from the storage medium by a reading device or downloaded via a communication IF 105 or the like. The processor 101 reads the program 110 from the HDD 104 and executes the program 110.

<C. Functional configuration of analyzer>
FIG. 3 is a diagram showing a functional configuration of the analyzer. As shown in FIG. 3, the analyzer 100 includes an acquisition unit 10, a storage unit 11, a determination unit 14, an estimation unit 15, a correction unit 16, and a proposal information generation unit 17. The acquisition unit 10, the determination unit 14, the estimation unit 15, the correction unit 16, and the proposal information generation unit 17 are realized by the processor 101 executing the program 110. The storage unit 11 is realized by the ROM 102 and the RAM 103.

The acquisition unit 10 acquires the electric energy data 12 in the analysis target period for the building 200 to be analyzed from the server device 300 via the network. The analysis target period is, for example, one year. However, holidays (for example, Saturdays, Sundays, and holidays) of the building 200 to be analyzed are excluded from the analysis period. The acquisition unit 10 stores the acquired electric energy data 12 in the storage unit 11.

Further, the acquisition unit 10 acquires the outside air temperature data 13 indicating the outside air temperature for each time zone in the analysis target period in the area including the building 200 to be analyzed via the network. The outside air temperature data is distributed from a predetermined organization (for example, the Japan Meteorological Agency). The acquisition unit 10 stores the acquired outside air temperature data 13 in the storage unit 11.

The determination unit 14 uses the electric energy data 12 to determine whether each day included in the analysis target period is a working day or a non-working day of the air conditioner (air conditioner).

The estimation unit 15 estimates the power consumption of the building 200 for each purpose in the target time zone of the target day included in the analysis target period. In the present embodiment, the estimation unit 15 estimates the power consumption for the three uses. The power consumption of the three applications is the base power consumption, the activity power consumption, and the air conditioning power consumption.

Base power consumption is the power consumption of applications that are not caused by human activity. The base power consumption includes the power consumed by communication equipment, the power consumed by cooling equipment that is used all year round (for example, the refrigerator in the server room, the refrigerating and freezing case of the food supermarket), and the power outlet of the lamp. The amount of standby power is included.

The power consumption for activities is the power consumption for applications caused by human activities. The amount of power consumed for activities includes the amount of power consumed by ventilation power, the amount of power consumed by electric light outlets (excluding standby power), the amount of power consumed by elevators, and the power for EV (Electric Vehicle) charging. Includes the amount, the amount of electricity consumed by the electric hot water supply facility, and the amount of electricity consumed by other power sources.

The air-conditioning component power consumption is the power consumption of an application (hereinafter, referred to as "air-conditioning application") for adjusting temperature and / or humidity for the purpose of improving human comfort. The air-conditioning power consumption includes the amount of power consumed by the heat source equipment and the amount of power consumed by the air transport power of the air conditioner. Since ventilation is simply the adjustment of airflow, the amount of power consumed by ventilation power is not included in the amount of power consumed by air conditioning. The power consumption of the cooling equipment that is used all the time throughout the year is included in the base power consumption as described above, and is not included in the air conditioning power consumption.

The correction unit 16 consumes the target power when there is a difference between the target power consumption measured in the target time zone of the target day and the total of the base power consumption, the activity power consumption, and the air conditioning power consumption. Correct at least one of the activity power consumption and the air conditioning power consumption so that the amount and the sum match. The target power consumption is the power consumption indicated by the data corresponding to the target time zone of the target day in the power consumption data.

The proposal information generation unit 17 generates proposal information to the manager of the building 200 based on the base power consumption, the activity power consumption, and the air conditioning power consumption.

<D. Analysis process flow>
FIG. 4 is a flowchart showing an example of the flow of analysis processing in the analyzer. As shown in FIG. 4, first, the acquisition unit 10 of the analyzer 100 acquires the electric energy data 12 and the outside air temperature data 13 of the analysis target period for the building 200 to be analyzed (step S1). The acquired electric energy data 12 and the outside air temperature data 13 are stored in the storage unit 11.

Next, the estimation unit 15 estimates the base power consumption in the target time zone of the target day by using the power amount data 12 and the outside air temperature data 13 (step S2).

Next, the determination unit 14 uses the electric energy data 12 to determine whether each day included in the analysis target period is a working day or a non-working day of the air conditioner (step S3).

Next, the estimation unit 15 is based on the data of the day determined as the non-working day by the determination unit 14 (hereinafter referred to as “non-working day data”) in the electric energy data 12 and the base power consumption. Then, the power consumption for the activity in the target time zone of the target day is estimated (step S4).

Next, the estimation unit 15 estimates the air-conditioning power consumption in the target time zone of the target day based on the non-working day data (step S5).

Next, the correction unit 16 corrects at least one of the air-conditioning power consumption and the activity power consumption, if necessary (step S6).

Next, the proposal information generation unit 17 generates proposal information to the manager of the building 200 based on the base power consumption, the activity power consumption, and the air conditioning power consumption (step S7).

The processing order of steps S1 to S6 is not limited to the order shown in FIG. For example, step S3 may be executed before step S2. Further, step S5 may be executed before step S4.

<E. Estimating method of base power consumption>
The method of estimating the base power consumption executed in step S2 will be described with reference to FIG. FIG. 5 is a diagram illustrating a method of estimating base power consumption.

The estimation unit 15 uses the electric energy data 12 and the outside air temperature data 13 to generate unit data in which the electric energy consumption in each time zone included in the analysis target period and the outside air temperature in the time zone are associated with each other. Generate. For example, when the number of days included in the analysis target period is 300 and each day is divided into 96 time zones every 15 minutes, the estimation unit 15 generates 300 × 96 = 28800 unit data. The upper part of FIG. 5 shows the results of plotting a plurality of unit data 30 generated on a graph in which the horizontal axis is the outside air temperature (° C.) and the vertical axis is the power consumption (kWh / 15 min).

Base power consumption is power consumption for applications that are not caused by human activity, and is likely to correspond to the minimum power consumption at each outside temperature. Therefore, the estimation unit 15 estimates the base power consumption in the target time zone of the target day according to the following procedures (1) to (4).

Procedure (1): The estimation unit 15 divides the set outside air temperature range into a plurality of outside air temperature zones. The outside air temperature range may be set in advance, or may be set according to the distribution of the outside air temperature data 13. For example, the range occupied by 95% of the distribution of the outside air temperature shown in the outside air temperature data 13 is defined as the outside air temperature range. The width of the outside air temperature zone is predetermined, for example, 1 ° C. The divided outside air temperature zone is shown in the middle of FIG. In the example shown in FIG. 5, the estimation unit 15 divides the outside air temperature range of 0 to 40 ° C. into 40 outside air temperature zones having a width of 1 ° C.

Step (2): The estimation unit 15 extracts the minimum power consumption for each outside air temperature zone. An enlarged view of the graph shown in the upper part of FIG. 5 at 5 to 9 ° C. is shown in the middle part of FIG. In the example shown in FIG. 5, the estimation unit 15 extracts the unit data 31 having the minimum power consumption from the unit data 30 belonging to the outside air temperature zone for each of the 40 outside air temperature zones. The estimation unit 15 determines the power consumption indicated by the unit data 31 extracted for each of the 40 outside air temperature zones as the minimum power consumption of the outside air temperature zone.

Procedure (3): The estimation unit 15 calculates a regression equation with the outside air temperature as the explanatory variable and the minimum power consumption extracted in the procedure (2) as the objective variable. In the example shown in FIG. 5, the estimation unit 15 uses the outside air temperature indicated by the unit data 31 extracted for each of the 40 outside air temperature zones as an explanatory variable, and the power consumption (minimum power consumption) indicated by the unit data 31. Calculate a regression equation with quantity) as the objective variable. The regression equation shows, for example, an nth-order curve and is calculated using the method of least squares.

The regression curve 33 represented by the regression equation is shown in the middle and lower rows of FIG. In the example shown in FIG. 5, the regression curve 33 is correlated with the outside air temperature when the outside air temperature is high. This is because the amount of electric power consumed by the cooling equipment for communication equipment increases as the outside air temperature rises.

It should be noted that the outside air temperature zone in which the number of unit data 30 is small may not include unit data 30 indicating only the power consumption of the application not caused by human activity. Therefore, the estimation unit 15 uses the minimum power consumption of the outside air temperature zone in which the number of unit data 30 is less than the threshold, which is the closest to the outside air temperature zone, and the number of unit data 30 is equal to or more than the threshold. It is preferable to calculate the regression equation. The estimation unit 15 may calculate the regression equation for the outside air temperature zone in which the number of unit data 30 is less than the threshold value, using the intermediate temperature of the outside air temperature zone as the outside air temperature.

In the example shown in FIG. 5, since the number of unit data 30 belonging to the outside air temperature zone of 5 ° C. or lower is less than the threshold value, the estimation unit 15 has 5 to 6 as the minimum power consumption of the outside air temperature zone of 5 ° C. or lower. The regression equation is calculated using the minimum power consumption in the outside air temperature range of ° C. Further, since the number of unit data 30 belonging to the outside air temperature zone of 30 ° C. or higher is less than the threshold value, the estimation unit 15 sets the minimum power consumption of the outside air temperature zone of 30 ° C. or higher as the outside air temperature zone of 29 to 30 ° C. Use the minimum power consumption of.

Step (4): The estimation unit 15 estimates the base power consumption in the target time zone of the target day based on the regression equation and the outside air temperature in the target time zone of the target day. That is, the estimation unit 15 calculates the base power consumption in the target time zone of the target day by substituting the outside air temperature in the target time zone of the target day into the regression equation.

FIG. 6 is a diagram showing a verification result of the estimation accuracy of the base power consumption estimated by the estimation unit. FIG. 6A shows the verification result of the estimation accuracy of the base power consumption estimated for the winter season (January) as the target day. FIG. 6B shows the verification result of the estimation accuracy of the base power consumption estimated for the summer (September) as the target day.

The verification was carried out by measuring the power consumption of each of the various facilities installed in the building 200. FIG. 6 shows the time change of the power consumption of each facility. FIG. 6 shows an example of the building 200 including only the cooling equipment for communication equipment (cooling machine in the server room) as the cooling equipment used throughout the year. In FIG. 6, the electric energy indicated by the “communication equipment system” includes the electric energy consumed by the communication equipment and the electric energy consumed by the cooling equipment for the communication equipment.

As shown in FIG. 6, the line 34 showing the waveform of the base power consumption estimated by the estimation unit 15 is larger than the valley part of the waveform showing the sum of the power amount of the communication device system and the power amount of the lamp outlet. It shows a slight change in the amount of electricity. The electric energy of the lamp outlet includes the standby electric energy of the lamp outlet and the electric energy when the lamp outlet is used. In the waveform showing the time change of the electric energy of the lamp outlet, the valley part shows the standby electric energy amount, and the mountain part shows the electric energy amount at the time of use. In this way, the base power consumption estimated by the estimation unit 15 is the power consumption of applications not caused by human activities (power consumption of communication equipment, power consumption of cooling equipment for communication equipment). , The amount of standby power consumption of the lamp outlet) is accurately represented.

As shown in FIG. 6, the base power consumption estimated in winter (and in the middle (spring and autumn)) is substantially constant, while the base power consumption estimated in summer fluctuates slightly. This is because the amount of power consumed by the cooling equipment for communication equipment increases as the outside temperature rises in the summer when the outside temperature is high.

<F. How to determine working / non-working days of air conditioners>
Next, a method of determining the working day / non-working day of the air conditioner executed in step S3 will be described. The determination unit 14 determines whether each day included in the analysis target period is a working day or a non-working day of the air conditioner according to the following procedures (a) and (b).

Procedure (a): The determination unit 14 extracts the data of the day in which the maximum power consumption of the power consumption measured for each time zone in one day is the lower predetermined number of days from the power amount data as training data. To do.

Specifically, the determination unit 14 specifies the maximum power consumption of the power consumption for each time zone on each day included in the analysis target period. The determination unit 14 sorts the specified maximum power consumption in ascending order, and defines the days of the lower predetermined number of days as the non-operating days of the air conditioner. The predetermined number of days is, for example, 20 days. The determination unit 14 extracts the data of the days of the lower predetermined number of days from the electric energy data, and generates training data by concatenating the extracted data.

Procedure (b): For each day included in the analysis target period, the judgment unit 14 sets the air conditioner on that day based on the comparison result between the training data and the judgment target data which is the data of the day among the electric energy data. Determine whether it is a working day or a non-working day. The procedure (b) includes, for example, the following procedures (b-1) to (b-4).

Procedure (b-1): The determination unit 14 creates test data which is time-series data in which determination target data is combined after training data.

Procedure (b-2): The determination unit 14 calculates the change point score at each time point in the test data by using the change point detection algorithm. As a change point detection algorithm, for example, ChangeFinder (“J. Takeuchi and K. Yamanishi: A Unifying Framework for Detecting Outliers and Change Points from Time Series, IEEE Tran.on Knowledge and Data Engineering, Vol.18, No.4 (April-) 2006), p.482-492 ”and“ Kiyoyuki Kaido, Kosuke Kazumi: Early Anomaly Detection of Social Infrastructure Facilities Based on Statistical Change Point Detection (Anomaly Detection and Change Point Detection), Institute of Electrical and Electronics Engineers REAJ, Vol. .37 (Vol. 223) (2015), p.116-125 ") can be used. ChangeFinder employs two-step learning of a time-series model, and calculates the change point score after distinguishing the change of time-series data from outliers. Specifically, outliers are detected using the model learned in the first stage, and change points are detected using the model learned in the second stage.

FIG. 7 is a diagram showing an application example of ChangeFinder to test data. FIG. 7 shows the time change of the test data in which the judgment target data is combined after the training data for 20 days.

The determination unit 14 performs the first stage of learning. Determination unit 14 uses the AR model (Auto Regressive Model) as a probabilistic model of the test data, learns the AR model SDAR (Sequentially Discounting Auto Regressive) algorithm, the probability density function _{p t (x) (t =} 1 , 2, ...) Is calculated. Using the probability density function _pt (x) obtained by learning, the determination unit 14 calculates the logarithmic loss represented by the following equation (1) as an outlier score of the data x _t at each time point t.
Score1 (x _t ) = −lnp _t-1 (x _t ) ・ ・ ・ Equation (1)
In equation (1), Score1 (x _t ) is an outlier score.

The determination unit 14 smoothes the outlier score. The determination unit 14 provides a window having a width of T, which is a positive integer, and calculates the average value of the outlier scores at the time points included in the window. By sliding the window, the determination unit 14 calculates the time-series moving average score y _t (t = 1, 2, ...) Expressed by the following equation (2).

Next, the determination unit 14 performs the second stage learning. The determination unit 14 uses the AR model as the probability model of the new time series data y _t (t = 1, 2, ...) Obtained by the equation (2), and learns the AR model by the SDAR algorithm. , The probability density function q _t (y) (t = 1, 2, ...) Is calculated. Further, the determination unit 14 uses the logarithmic loss −lnq _t-1 (y _t ) at each time point t and T ′ which is a positive integer, and according to the following equation (3), the change point score at each time point t. To calculate. In equation (3), Score2 (y _t ) is the change point score.

It can be determined that the larger the Score2 (y _t ), the larger the change in the test data, which is the time series data, at the time t.

Procedure (b-3): The determination unit 14 sets the change point score for each time point in the test data into the first data group at the time point corresponding to the training data and the second data group at the time point corresponding to the judgment target data. To divide. In the test data, the change point score becomes extremely large due to the small amount of training data from the beginning to the elapse of a predetermined time. Therefore, the change point score from the beginning to the elapse of a predetermined time (in the example shown in FIG. 7, 5 days from the beginning) is not included in the first data group.

Procedure (b-4): The determination unit 14 has a change point score (first change point score) indicated by the first data group and a change point score (second change point score) shown by the second data group. Whether it is equivalent or not is judged by a test. The determination unit 14 uses, for example, Welch's t-test. As a result of the t-test, for example, when the p value falls below the significance level of 5%, the determination unit 14 has a significant difference between the average value of the first change point score and the average value of the second change point score ( Not equivalent). The determination unit 14 determines that the day corresponding to the determination target data is the operating day of the air conditioner when there is a significant difference between the average value of the first change point score and the average value of the second change point score. To do. The determination unit 14 determines that the day corresponding to the determination target data is the non-operating day of the air conditioner when there is no significant difference between the average value of the first change point score and the average value of the second change point score. judge.

The determination accuracy of working days / non-working days determined in this way was verified. Specifically, when the determination unit 14 determines the working days / non-working days of the air conditioner using the electric energy data of the building in which the actual number of working days of the air conditioner is 208 days in one year. 204 days was determined as a working day. That is, the determination accuracy was 97.1%. As described above, it was confirmed that the determination accuracy by the determination unit 14 was sufficiently high.

<G. Method of estimating power consumption for activities>
The power consumption when the air conditioner is not operating is the sum of the base power consumption and the activity power consumption. Power consumption for activities fluctuates over time. However, in the case of small and medium-sized business buildings, the power consumption for activities during a certain period of time does not fluctuate significantly throughout the year. Therefore, the estimation unit 15 estimates the activity power consumption in the target time zone on the assumption that the activity power consumption in each time zone is constant throughout the year.

The estimation unit 15 calculates a first representative value (for example, an average value, an intermediate value, etc.) of the power consumption in the target time zone on the non-working day based on the non-working day data in the electric energy data 12. Further, the estimation unit 15 estimates the base power consumption of the target time zone on each non-working day according to the above-mentioned method of estimating the base power consumption, and the second representative value (for example, an average value) of the estimated base power consumption. , Intermediate value, etc.) The estimation unit 15 estimates the amount obtained by subtracting the second representative value from the first representative value as the activity power consumption in the target time zone.

FIG. 8 is a diagram showing a verification result of the estimation accuracy of the active power consumption estimated by the estimation unit. The verification was carried out by measuring the power consumption of each of the various facilities installed in the building 200, as in FIG. FIG. 8 shows the verification results of the estimation accuracy of the activity power consumption in each time zone estimated from November 7th to 11th as the target day. As described above, since the activity power consumption in each time zone is constant throughout the year, the activity power consumption estimated for the same time zone in the five target days is the same. Note that FIG. 8 also shows the base power consumption estimated from November 7th to 11th as the target date.

As shown in FIG. 8, the activity portion electric energy estimated by the estimation unit 15 is the electric energy consumed by the ventilation equipment, the electric energy consumed by the electric light outlet (excluding the standby electric energy), and the electric energy consumed by the elevator. It is almost the same as the total measured value of the electric energy to be generated, the electric energy for EV charging, the electric energy consumed by the electric hot water supply facility, and the electric energy consumed by other electric power. As described above, the activity power consumption estimated by the estimation unit 15 accurately represents the total power consumption of the applications caused by human activities.

<H. Estimating method of air conditioning power consumption>
With reference to FIG. 9, the method for estimating the air-conditioning power consumption executed in step S5 will be described. FIG. 9 is a diagram illustrating a method of estimating the power consumption for air conditioning. The power consumption for air conditioning corresponds to the power consumption that exceeds the power consumption when the air conditioner is not operating. Therefore, the estimation unit 15 estimates the air-conditioning power consumption in the target time zone of the target day as follows.

FIG. 9 shows the distribution of power consumption in the target time zone from 14:00 to 14:15 during the analysis target period. In FIG. 9, the circle mark indicates the data of the day determined as the working day of the air conditioner by the determination unit 14, and the cross mark indicates the data of the day determined as the non-operating day of the air conditioner by the determination unit 14. ..

The estimation unit 15 is described in <G. Similar to the method for estimating the power consumption for activity>, the first representative value (for example, average value, median) of the power consumption in the target time zone on the non-working day is based on the non-working day data in the power data 12. Value etc.) is calculated. In FIG. 9, line 35 shows the average value of power consumption in the target time zone on non-working days.

The estimation unit 15 subtracts the first representative value from the power consumption indicated by the data 36 corresponding to the target time zone of the target day (hereinafter referred to as “target power consumption”) in the power amount data. , Estimated as the air-conditioning power consumption in the target time zone of the target day.

When the target day is determined by the determination unit 14 to be a non-working day, the estimation unit 15 estimates the air-conditioning power consumption in the target time zone of the target day to be 0.

FIG. 10 is a diagram showing a verification result of the estimation accuracy of the air-conditioning power consumption estimated by the estimation unit. The verification was carried out by measuring the amount of electric power consumed by the air transport power of the heat source equipment and the air conditioner installed in the building 200. FIG. 10 shows the verification result of the estimation accuracy of the air-conditioning power consumption estimated from February 1st to 9th as the target date. As shown in FIG. 10, the air-conditioning power consumption estimated by the estimation unit 15 substantially matches the measured value. As described above, the air-conditioning power consumption estimated by the estimation unit 15 accurately represents the power consumption of the air transport power of the heat source equipment and the air conditioner.

<I. Correction method>
Next, the correction method executed in step S6 will be described. As described above, the base power consumption is estimated based on the regression equation and the outside air temperature in the target time zone of the target day. The activity power consumption in the target time zone is estimated using non-working day data and takes a constant value throughout the year. Therefore, the sum of the target power consumption indicated by the data corresponding to the target time zone of the target day in the power amount data, the base power consumption, the activity power consumption, and the air conditioning power consumption (hereinafter, "estimated value"). There may be a difference between the sum and the sum of the two. Therefore, the correction unit 16 corrects the activity power consumption and the air conditioning power consumption as follows.

In the analyzer 100, an activity time zone, which is a time zone in which human activity is scheduled to be performed in the building 200, is predetermined. Specifically, the activity time zone for each building (for example, 8:00 to 20:00) is registered in advance in the analyzer 100 using the operation key 106 (see FIG. 2).

Excessive operation of the air conditioner is considered to be the main reason why the target power consumption becomes larger than the sum of the estimated values during the active hours. Therefore, when the target time zone is included in the activity time zone and the target power consumption is larger than the sum of the estimated values, the correction unit 16 air-conditions only the difference between the target power consumption and the sum of the estimated values. Increase power consumption.

The reason why the target power consumption becomes smaller than the sum of the estimated values during the activity time is firstly considered to be the implementation of energy saving action for the air conditioner, and secondly to the implementation of the energy saving action for other equipment. Therefore, in the correction unit 16, the target time zone is included in the activity time zone, the target power consumption is smaller than the sum of the estimated values, and the difference between the target power consumption and the sum of the estimated values is the air conditioning component. When it is less than or equal to the power consumption, the power consumption for air conditioning is reduced by the difference. On the other hand, in the correction unit 16, the target time zone is included in the activity time zone, the target power consumption is smaller than the total of the estimated values, and the difference between the target power consumption and the total of the estimated values is the air conditioning component. When the excess amount exceeds the power consumption, the air conditioning power consumption is reduced to 0 and the activity power consumption is reduced by the excess amount.

The main reason why the target power consumption becomes larger than the sum of the estimated values in the time zone other than the activity time zone is considered to be the increase in human activity. Therefore, when the target time zone is not included in the activity time zone and the target power consumption is larger than the sum of the estimated values, the correction unit 16 increases the activity by the difference between the target power consumption and the sum of the estimated values. Increase power consumption.

The reason why the target power consumption becomes smaller than the sum of the estimated values during the time other than the activity time is considered to be that the power consumption for air conditioning is overestimated, and secondly, other equipment. It is conceivable to implement energy-saving actions against. Therefore, in the correction unit 16, the target time zone is not included in the activity time zone, the target power consumption is smaller than the sum of the estimated values, and the difference between the target power consumption and the sum of the estimated values is the air conditioning component. When it is less than or equal to the power consumption, the power consumption for air conditioning is reduced by the difference. On the other hand, in the correction unit 16, the target time zone is not included in the activity time zone, the target power consumption is smaller than the total of the estimated values, and the difference between the target power consumption and the total of the estimated values is the air conditioning component. When the excess amount exceeds the power consumption, the air conditioning power consumption is reduced to 0 and the activity power consumption is reduced by the excess amount.

By the correction of the correction unit 16, the actually measured power consumption can be matched with the total of the base power consumption, the activity power consumption, and the air conditioning power consumption.

<J. Verification result of decomposition accuracy of power consumption ＞
Three uses of power consumption by comparing the base power consumption, activity power consumption, air-conditioning power consumption, and measured values estimated and corrected by the analyzer 100 for five different buildings A to E. The decomposition accuracy was verified.

FIG. 11 is a diagram showing verification results of decomposition accuracy of power consumption into three uses. In FIG. 11, (a) to (e) show the comparison result between the estimated value and the measured value of the base power consumption, the activity power consumption, and the air conditioning power consumption in the buildings A to E, respectively. In FIGS. 11 (a) to 11 (e), the upper row shows the comparison result between the estimated value of the base power consumption and the measured value, and the middle row shows the estimated value and the measured value of the active power consumption. The comparison result with the above is shown, and the comparison result between the estimated value of the air-conditioning power consumption and the measured value is shown in the lower part. The estimated values of the base power consumption, the activity power consumption, and the air conditioning power consumption are appropriately corrected by the correction unit 16.

FIG. 12 is a diagram showing an average value of errors between each estimated value of base power consumption, activity power consumption, and air conditioning power consumption and an actually measured value.

As shown in FIGS. 11 and 12, the error between the estimated values of the base power consumption, the activity power consumption, and the air conditioning power consumption and the measured values is 15% or less. For this reason, the decomposition of power consumption into three uses is performed with high accuracy.

<K. Proposal information generation process>
The proposal information generation unit 17 generates, for example, the following first to third proposal information.

The first proposal information indicates the amount of energy saving that can be expected when the air conditioner operating at an outside air temperature that does not require the operation of the air conditioner is stopped (hereinafter, referred to as "first energy saving amount").

The second proposal information indicates the amount of energy saving (hereinafter referred to as "second energy saving amount") that can be expected when the air conditioner that is excessively operated with respect to the outside air temperature is changed to the optimum operation.

The third proposal information indicates the amount of energy saving that can be expected when preventing forgetting to turn off the lamp outlet at night (hereinafter, referred to as "third energy saving amount").

(K-1. Method of generating first proposal information)
The proposal information generation unit 17 extracts the outside air temperature in the time zone included in the determined day of the non-operating day of the air conditioner from 9:00 to 17:00 from the outside air temperature data. The proposal information generation unit 17 determines the lower 25% outside air temperature in the plurality of outside air temperatures indicated by the extracted outside air temperature data as the heating start outside air temperature, and cools the top 25% outside air temperature in the plurality of outside air temperatures. Determined as the starting outside temperature. The proposal information generation unit 17 determines the outside air temperature zone from the heating start outside air temperature to the cooling start outside air temperature as an air conditioning-free temperature zone in which the operation of the air conditioner is unnecessary.

The proposal information generation unit 17 specifies the day determined to be the operating day of the air conditioner in the analysis target period as the target day, and further, on the target day, the time zone in which the outside air temperature belongs to the air conditioning unnecessary temperature zone is the target time. Identify as a band. The proposal information generation unit 17 calculates the total value of the air-conditioning power consumption estimated by the estimation unit 15 for the target time zone of these target days as the first energy saving amount. Then, the proposal information generation unit 17 generates the first proposal information indicating the calculated first energy saving amount.

(K-2. Method of generating second proposal information)
The proposal information generation unit 17 determines the heating start outside air temperature and the cooling start outside air temperature by the same method as described above. The proposal information generation unit 17 extracts the data of the air-conditioning power consumption estimated as the target time zone in the time zone corresponding to the outside air temperature below the heating start outside air temperature as the heating outside air temperature zone data. The proposal information generation unit 17 extracts the data of the air-conditioning power consumption estimated as the target time zone in the time zone corresponding to the outside air temperature above the cooling start outside air temperature as the cooling outside air temperature zone data.

The proposal information generation unit 17 applies robust regression to the heating outside air temperature zone data. Robust regression is a method of adding outlier tests to linear regression. By applying robust regression, it is possible to automatically set a threshold value for determining outliers based on data variations. The proposal information generation unit 17 classifies the heating outside air temperature zone data into normal data and abnormal data using the set threshold value. The proposal information generation unit 17 calculates the total difference between the abnormal data and the threshold value as the second energy saving amount during the heating operation.

Similarly, the proposal information generation unit 17 applies robust regression to the cooling outside air temperature zone data. The proposal information generation unit 17 classifies the cooling outside temperature zone data into normal data and abnormal data by using the threshold value set by robust regression. The proposal information generation unit 17 calculates the total difference between the abnormal data and the threshold value as the second energy saving amount during the cooling operation.

The proposal information generation unit 17 generates the second proposal information indicating the calculated second energy saving amount during the heating operation and the cooling operation.

(K-3. Method of generating third proposal information)
The proposal information generation unit 17 extracts the data of the power consumption for the activity estimated by setting the time zone other than the activity time zone as the target time zone as the night activity data. The proposal information generation unit 17 applies robust regression to the nighttime activity data by the same method as (K-2. Second proposal information generation method). The proposal information generation unit 17 classifies nighttime activity data into normal data and abnormal data using the threshold value set by robust regression. The proposal information generation unit 17 calculates the total difference between the abnormal data and the threshold value as the third energy saving amount. The proposal information generation unit 17 generates the third proposal information indicating the calculated third energy saving amount.

<L. Modification example>
In the above description, it is assumed that the analyzer 100 is provided with the proposal information generation unit 17. However, the proposed information generation unit 17 may be provided in an information processing device that is communicably connected to the analyzer 100. In this case, the information processing apparatus acquires the base power consumption, the activity power consumption, and the air conditioning power consumption for each time period within the analysis target period from the analysis device 100, and uses the acquired data to propose information. Should be generated.

When the proposal information generation unit 17 generates at least one of the first proposal information and the second proposal information described above, the estimation unit 15 performs air conditioning among the base power consumption, the activity power consumption, and the air conditioning power consumption. Only the power consumption may be estimated. When the proposal information generation unit 17 generates only the above-mentioned third proposal information, the estimation unit 15 consumes the base power consumption and the activity power consumption out of the base power consumption, the activity power consumption, and the air conditioning power consumption. Only the quantity may be estimated.

In the example shown in FIG. 1, the smart meter 210, the server device 300, and the analyzer 100 are assumed to exchange data with each other via a network. However, the method of exchanging data between the smart meter 210, the server device 300, and the analyzer 100 is not limited to the example shown in FIG. For example, the server device 300 may directly acquire the electric energy data from the smart meter 210 without going through the network. Further, the analyzer 100 may be connected to the server device 300 without going through the network, and the electric energy data of the building 200 may be directly acquired from the server device 300.

<M. Summary>
As described above, the analyzer 100 that analyzes the power consumption state of the building 200 includes an acquisition unit 10, a determination unit 14, and an estimation unit 15. The acquisition unit 10 acquires the electric energy data 12 indicating the electric energy consumption measured for each time zone of the building 200 in the analysis target period. The determination unit 14 determines whether each day included in the analysis target period is a working day or a non-working day of the air conditioner. The estimation unit 15 estimates the power consumption for each purpose of the building in the target time zone of the target day included in the analysis target period based on the non-working day data which is the data of the non-working day in the power amount data 12. .. The determination unit 14 extracts from the electric energy data 12 the data of the day in which the maximum electric energy consumption is the lower predetermined number of days among the electric energy consumption measured for each time zone in one day as training data. For each day included in the analysis target period, the judgment unit 14 sets the day as a working day and a non-working day based on the comparison result between the training data and the judgment target data which is the data of the day among the electric energy data 12. Determine which one is.

According to the above configuration, the training data is the data of the day in which the maximum power consumption of the power consumption measured for each time zone in one day is the lower predetermined number of days. Therefore, the training data corresponds to the data of the day when the air conditioner is likely to be inactive. Therefore, based on the comparison result between the training data and the determination target data, each day included in the analysis target period can be accurately determined as either a working day or a non-operating day of the air conditioner. As a result, as much data as possible and accurately corresponding to the non-operating days of the air conditioner can be extracted from the electric energy data 12. As a result, the power consumption of the air conditioner on non-operating days can be accurately specified, and the power consumption of the building 200 for each application can be accurately analyzed using the specified power consumption.

It should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is shown not by the above description but by the scope of claims, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

10 Acquisition unit, 11 Storage unit, 12 Power supply data, 13 Outside temperature data, 14 Judgment unit, 15 Estimator unit, 16 Correction unit, 17 Proposal information generation unit, 30, 31 unit data, 33 Regression curve, 100 Analyzer, 101 processor, 102 ROM, 103 RAM, 104 HDD, 105 communication IF, 106 operation key, 107 power supply circuit, 108 display, 110 program, 200 building, 210 smart meter, 220 equipment, 300 server device, SYSTEM.

Claims (10)

An analyzer that analyzes the power consumption of a building
An acquisition unit that acquires power consumption data indicating the power consumption measured for each time zone of the building during the analysis target period, and an acquisition unit.
A determination unit that determines whether each day included in the analysis target period is a working day or a non-working day of the air conditioner.
An estimation unit that estimates the power consumption of the building for each purpose in the target time zone of the target day included in the analysis target period based on the non-working day data which is the non-working day data of the power amount data. With and
The determination unit
From the electric energy data, the data of the day in which the maximum electric energy consumption of the electric energy consumption measured for each time zone in one day is the lower predetermined number of days is extracted as training data.
For each day included in the analysis target period, the day is the working day and the non-working day based on the comparison result between the training data and the determination target data which is the data of the day among the electric energy data. An analyzer that determines which is. The determination unit
Test data, which is time-series data obtained by combining the determination target data after the training data, is created.
Using the change point detection algorithm, the change point score at each time point in the test data is calculated.
Whether or not the first change point score at the time corresponding to the training data in the test data and the second change point score at the time corresponding to the determination target data in the test data are equivalent is determined by a test. When the first change point score and the second change point score are equivalent, it is determined that the day corresponding to the determination target data is a non-working day, and the first change point score and the second change point score are determined. The analyzer according to claim 1, wherein the date corresponding to the determination target data is determined to be a working day when the change point score is not equivalent. The analyzer according to claim 2, wherein the test is a t-test. The estimation unit
When the target day is determined to be the non-working day, the air-conditioning power consumption for the air-conditioning application in the target time zone of the target day is estimated to be 0.
When the target day is determined to be the working day, the target time on the non-working day is calculated from the non-working day data from the target power consumption measured in the target time zone on the target day. The analyzer according to any one of claims 1 to 3, wherein the amount obtained by subtracting the representative value of the power consumption of the band is estimated as the power consumption of the air conditioning component in the target time zone of the target day. The acquisition unit further acquires outside air temperature data indicating the outside air temperature for each time zone in the area including the building during the analysis target period.
The estimation unit
Using the electric energy data and the outside air temperature data, the minimum electric energy consumption for each outside air temperature zone is extracted.
Calculate a regression equation with the outside air temperature as the explanatory variable and the extracted minimum power consumption as the objective variable.
The analyzer according to claim 4, wherein the base power consumption in the target time zone of the target day is estimated based on the regression equation and the outside air temperature in the target time zone of the target day. The estimation unit
Amount obtained by subtracting the representative value of the base power consumption in the target time zone on the non-working day from the representative value of the power consumption in the target time zone on the non-working day calculated from the non-working day data. The analyzer according to claim 5, wherein is estimated as the activity power consumption for the purpose caused by human activity in the target time zone. When there is a difference between the target power consumption and the sum of the air conditioning power consumption, the base power consumption, and the activity power consumption, the target power consumption and the total are matched. The analyzer according to claim 6, further comprising a correction unit for correcting at least one of the air conditioning power consumption and the activity power consumption. The activity time zone, which is the time zone in which human activity is scheduled to take place in the building, is predetermined.
The correction unit
When the target time zone is included in the activity time zone and the target power consumption is larger than the total, the air conditioning component power consumption is increased by the difference.
The air-conditioned power consumption when the target time zone is included in the activity time zone, the target power consumption is smaller than the total, and the difference is equal to or less than the air-conditioned power consumption. Is reduced by the above difference,
When the target time zone is included in the activity time zone, the target power consumption is smaller than the total, and the difference exceeds the air conditioning power consumption by an excess amount, the air conditioning component While reducing the power consumption to 0, the power consumption for the activity is reduced by the excess amount.
When the target time zone is not included in the activity time zone and the target power consumption is larger than the total, the activity power consumption is increased by the difference.
When the target time zone is not included in the activity time zone, the target power consumption is smaller than the total, and the difference is equal to or less than the air conditioning component power consumption, the air conditioning component power consumption Is reduced by the above difference,
When the target time zone is not included in the activity time zone, the target power consumption is smaller than the total, and the difference exceeds the air conditioning power consumption by an excess amount, the air conditioning portion The analyzer according to claim 7, wherein the power consumption is reduced to 0 and the power consumption for the activity is reduced by the excess amount. It is an estimation method that estimates the power consumption state of a building.
A step of acquiring electric energy data indicating the electric energy consumption measured for each time zone of the building in the analysis target period, and
A step of determining whether each day included in the analysis target period is an air conditioning working day or a non-working day, and
A step of estimating the power consumption of the building for each purpose in the target time zone of the target day included in the analysis target period based on the non-working day data which is the non-working day data of the power amount data. With
The determination step is
From the electric energy data, a step of extracting the data of the day in which the maximum electric energy consumption of the electric energy consumption measured for each time zone in one day is the lower predetermined number of days is extracted as training data.
For each day included in the analysis target period, the day is the working day and the non-working day based on the comparison result between the training data and the determination target data which is the data of the day among the electric energy data. An estimation method that includes a step to determine which is. A program that causes a computer to execute an estimation method that estimates the power consumption of a building.
The estimation method is
A step of acquiring electric energy data indicating the electric energy consumption measured for each time zone of the building in the analysis target period, and
A step of determining whether each day included in the analysis target period is an air conditioning working day or a non-working day, and
A step of estimating the power consumption of the building for each purpose in the target time zone of the target day included in the analysis target period based on the non-working day data which is the non-working day data of the power amount data. With
The determination step is
From the electric energy data, a step of extracting the data of the day in which the maximum electric energy consumption of the electric energy consumption measured for each time zone in one day is the lower predetermined number of days is extracted as training data.
For each day included in the analysis target period, the day is the working day and the non-working day based on the comparison result between the training data and the determination target data which is the data of the day among the electric energy data. A program that includes steps to determine which one.