JP7003597B2 - Demand forecasting device, demand forecasting method - Google Patents

Description

The present invention relates to a demand amount prediction device and a demand amount prediction method.

For example, as described in Patent Document 1, a device for predicting an electric power demand is known. The apparatus described in Patent Document 1 calculates the future demand amount based on the deviation between the average demand amount and the demand amount calculated based on the predicted temperature and the predicted value of the temperature. Here, regarding the predicted value of the air temperature, the temperature difference from the temperature at which the cooling equipment will be used or the temperature at which the heating equipment will be used so as to consider the insensitive zone to the temperature of the electric power demand. The amount of demand is calculated using the temperature difference as one of the explanatory variables of the regression equation.

Japanese Unexamined Patent Publication No. 2009-251742

However, in the device described in Patent Document 1, multiple regression analysis is performed by using the temperature difference between the temperature at which the cooling device is used and the temperature at which the heating device is used, the day of the day, the weather, etc. as explanatory variables. Although the amount of demand is calculated using it, it only considers the temperature related to the on / off of heating and cooling, and does not accurately reflect the dead zone where the amount of demand is not easily affected by changes in temperature. That is, in the apparatus described in Patent Document 1, since the outside of the dead zone is not appropriately reflected in the calculation of the demand amount, there is a possibility that the demand amount cannot be predicted accurately.

The present invention, which mainly solves the above-mentioned problems, has an information acquisition unit for acquiring air temperature information indicating the air temperature and demand information indicating the electric power demand amount of the consumer corresponding to the air temperature, and the air temperature and the electric power demand. In relation to the amount, the reference temperature setting unit that sets the first reference temperature and the second reference temperature higher than the first reference temperature in the dead zone where the power demand is not easily affected even if the temperature fluctuates. , The demand amount information in the past predetermined time, the first variable information indicating a predetermined value determined by the relationship between the first reference temperature information indicating the first reference temperature and the temperature information, and the second reference. A regression equation creation unit that creates a regression equation based on a second reference temperature information indicating the temperature and a second variable information indicating a predetermined value determined by the relationship between the temperature information, and a predetermined time in the past. , The regression equation, the first reference temperature information, the second reference temperature information, and the temperature information at a predetermined time in the future, and the power demand of the consumer at the predetermined time in the future is calculated. It is equipped with a demand forecasting unit.
Other features of the invention will become apparent with reference to the accompanying drawings and the description herein.

According to the present invention, it is possible to accurately predict the electric power demand by appropriately considering the dead zone of the electric power demand with respect to the temperature based on the past tendency.

It is a figure which shows an example of the outline of the demand amount forecasting apparatus which concerns on 1st Embodiment. It is a demand temperature graph which shows the process of setting the 1st reference temperature which concerns on 1st Embodiment. It is a demand temperature graph which shows the process of setting the 2nd reference temperature which concerns on 1st Embodiment. It is a schematic diagram which shows an example of the past time. It is a conceptual diagram which shows an example for calculating explanatory variables of multiple regression analysis. It is a figure which shows an example of the past information table. It is a figure which shows an example of a reference information table. It is a figure which shows an example of the processing flow of the demand quantity forecasting apparatus which concerns on 1st Embodiment. It is a figure which shows an example of the processing flow of the reference temperature setting part which concerns on 1st Embodiment. It is a figure which shows an example of the outline of the demand amount forecasting apparatus which concerns on 2nd Embodiment. It is a demand temperature graph which shows the process of setting the 1st reference temperature which concerns on 2nd Embodiment. It is a demand temperature graph which shows the process of setting the 2nd reference temperature which concerns on 2nd Embodiment. It is a figure which shows an example of the processing flow of the reference temperature setting part which concerns on 2nd Embodiment. It is a figure which shows an example of the outline of the demand amount forecasting apparatus which concerns on 3rd Embodiment. It is a demand temperature graph which shows the process of setting the 1st reference temperature which concerns on 3rd Embodiment. It is a demand temperature graph which shows the process of setting the 2nd reference temperature which concerns on 3rd Embodiment. It is a figure which shows an example of the processing flow of the reference temperature setting part which concerns on 3rd Embodiment. It is a conceptual diagram which shows an example for predicting the demand amount which concerns on other embodiment.

The description of this specification and the accompanying drawings will clarify at least the following matters. In the following description, the parts with the same reference numerals represent the same elements, and their basic configurations and operations are the same.

=== Demand amount forecasting device 10 according to the first embodiment ===
The demand amount forecasting apparatus 10 according to the first embodiment will be described as follows with reference to FIG. 1. FIG. 1 is a diagram showing an example of an outline of the demand amount forecasting device 10 according to the present embodiment.

The demand amount prediction device 10 is a device that predicts a future electric power demand amount by using, for example, a regression equation, based on temperature information indicating the past air temperature. The demand amount prediction device 10 has a function of specifying a range of air temperature (hereinafter, referred to as "dead zone") in which the electric power demand amount is not easily affected by a change in air temperature. Here, the dead zone is set by its lower limit temperature (hereinafter referred to as "first reference temperature") and upper limit temperature (hereinafter referred to as "second reference temperature"). The method for setting the first reference temperature and the second reference temperature will be described in detail later. By setting the first reference temperature and the second reference temperature, the demand amount forecasting device 10 can accurately predict the future electric power demand amount in consideration of the dead zone which is unlikely to affect the electric power demand amount. ..

As shown in FIG. 1, the demand amount prediction device 10 having such a function has an arithmetic processing unit 11, a storage unit 12, an input unit 13, an output unit 14, and a memory 15. .. The arithmetic processing unit 11, the storage unit 12, the input unit 13, the output unit 14, and the memory 15 are connected to each other so as to be communicable.

The arithmetic processing unit 11 is composed of, for example, a CPU or an MPU, and realizes various functions by reading a program stored in the memory 15. Further, the arithmetic processing unit 11 has an information acquisition unit 11a, a reference temperature setting unit 11b, a regression equation creation unit 11c, and a demand amount prediction unit 11d. Each component of the arithmetic processing unit 11 will be described in detail later.

The storage unit 12 is a device for storing programs and various information. The storage unit 12 is composed of, for example, a ROM, a RAM, a flash memory, or the like. Various tables stored in the storage unit 12 will be described in detail later.

The input unit 13 is a network interface to which various information is input via the communication network 120. The output unit 14 is a network interface that outputs various information to the communication network 120. The memory 15 is a device for storing a program for processing by the arithmetic processing unit 11. The memory 15 is composed of, for example, a hard disk drive, an SSD, an optical storage device, or the like.

The demand amount forecasting device 10 acquires information on the weather such as temperature and weather from the Japan Meteorological Agency database (not shown) via the input unit 13, and also obtains information on the weather such as temperature and weather from the external demand amount providing device (not shown). Get past electricity demand.

== Arithmetic processing unit 11 ==
As shown in FIG. 1, the arithmetic processing unit 11 refers to various tables of the storage unit 12, and includes an information acquisition unit 11a, a reference temperature setting unit 11b, a regression equation creation unit 11c, and a demand amount prediction unit 11d. Demonstrate the function of. Each component will be described below.

<< Information acquisition unit 11a >>
The information acquisition unit 11a has a function of acquiring various information via the input unit 13. The information acquisition unit 11a acquires at least the air temperature information indicating the air temperature from the database of the Japan Meteorological Agency and the demand amount information indicating the past electric power demand amount from the device of the demand amount providing device. The temperature information includes, for example, at least the average temperature information indicating the average temperature, the time temperature information indicating the temperature at each time, the maximum temperature information indicating the maximum temperature, and the minimum temperature information during a predetermined period (for example, one day). It includes the minimum temperature information indicating the temperature and the weather information indicating the weather. The information acquisition unit 11a stores the acquired temperature information and the demand amount information in the storage unit 12. The demand amount prediction device 10 may not be provided with the information acquisition unit 11a and the storage unit 12, but may be configured to be accessible to an external storage device that stores the temperature information and the demand amount information.

<< Reference temperature setting unit 11b >>
The reference temperature setting unit 11b will be described as follows with reference to FIGS. 2 and 3. FIG. 2 is a demand temperature graph showing a process of setting the first reference temperature according to the first embodiment. FIG. 3 is a demand temperature graph showing a process of setting a second reference temperature according to the first embodiment.

The reference temperature setting unit 11b has a function of setting the first reference temperature and the second reference temperature. The first reference temperature and the second reference temperature are, for example, the upper limit and the lower limit of the dead zone in which the demand amount is not easily affected by the change in temperature. The reference temperature setting unit 11b has a function of plotting the relationship between the temperature information acquired from the past information table 12a and the demand information in a Cartesian coordinate system in order to set the first reference temperature and the second reference temperature. The temperature information here is, for example, information indicating the temperature at the time.

In the reference temperature setting unit 11b, the central temperature, which is a value near the center of the dead zone, is set, the first reference temperature is set on the negative side of the temperature from the central temperature, and the second reference is set on the positive side of the temperature from the central temperature. Set the temperature. The central temperature may be input by the operator, or the apex of the approximate curve formula calculated by the reference temperature setting unit 11b in the third embodiment described later may be automatically set as the central temperature.

Further, there are two methods for setting the first reference temperature and the second reference temperature in the first embodiment, and each of them will be described as follows.

(1) First Method In the first method, the relationship between the temperature information and the demand amount information is shown by an approximate linear formula, and it is determined and set whether or not the approximate linear formula has a predetermined inclination. Here, the predetermined inclination includes, for example, a negative inclination and a positive inclination predetermined by the operator, for example, an inclination empirically determined by the operator based on past achievements, and artificial intelligence (artificial intelligence). The slope is determined by using a neural network, etc.).

More specifically, as shown in FIG. 2, first, the reference temperature setting unit 11b is arbitrarily set to a predetermined temperature (for example, 20% of the central temperature) rather than the central temperature; the following "predetermined temperature". The same applies to ""), and a lower temperature (hereinafter referred to as "11th temperature") is set. The relationship between the temperature information and the demand amount information at a temperature lower than the eleventh temperature is represented by an approximate straight line (hereinafter referred to as "the eleventh approximate straight line") (one-point chain line in FIG. 2). The reference temperature setting unit 11b compares a predetermined negative slope (not shown) with the slope of the eleventh approximate straight line (hereinafter referred to as “11th slope”). Next, a temperature (hereinafter referred to as "12th temperature") lower than the 11th temperature by a predetermined temperature is set. The relationship between the air temperature information and the demand amount information at a temperature lower than the twelfth temperature is represented by an approximate straight line (hereinafter referred to as "the twelfth approximate straight line") (two-point chain line in FIG. 2). The reference temperature setting unit 11b compares a predetermined negative slope (not shown) with the slope of the twelfth approximate straight line (hereinafter referred to as “12th slope”). Similarly, the procedure is repeated to represent an approximate linear equation (hereinafter referred to as "13th approximate straight line") (three-dot chain line in FIG. 2), and the thirteenth slope thereof is compared with a predetermined negative slope.

Then, from the comparison result between the slope of the approximate straight line and the predetermined negative slope, the approximate straight line whose slope of the approximate straight line is closest to the predetermined negative slope is selected. The temperature corresponding to the selected approximate straight line is set as the first reference temperature. For example, when the twelfth approximate straight line is selected, the twelfth temperature is set as the first reference temperature. In the above, it was decided to obtain the 11th approximate straight line to the 13th approximate straight line, but the number of approximate straight lines to be obtained includes "the number of plot points" and "predetermined temperature" indicating the relationship between the temperature information and the demand amount information. It shall be changed as appropriate according to ".

Next, as shown in FIG. 3, the reference temperature setting unit 11b sets a temperature (hereinafter, referred to as “21st temperature”) higher than the central temperature by a predetermined temperature. The relationship between the temperature information and the demand amount information at a temperature higher than the 21st temperature is represented by an approximate straight line (hereinafter referred to as "21st approximate straight line") (one-point chain line in FIG. 3). The reference temperature setting unit 11b compares a predetermined positive inclination (not shown) with the inclination of the 21st approximate straight line (hereinafter, referred to as “21st inclination”). Next, a temperature higher than the 21st temperature by a predetermined temperature (hereinafter referred to as "22nd temperature") is set. The relationship between the temperature information and the demand amount information at a temperature higher than the 22nd temperature is represented by an approximate linear formula (hereinafter referred to as "22nd approximate straight line") (two-point chain line in FIG. 3). The reference temperature setting unit 11b compares a predetermined positive inclination with the inclination of the 22nd approximate straight line (hereinafter, referred to as “22nd inclination”). Similarly, the procedure is repeated to represent an approximate straight line equation (hereinafter referred to as "23rd approximate straight line") (dashed-dotted line in FIG. 3), and the 23rd slope thereof is compared with a predetermined positive slope.

Then, from the comparison result between the slope of the approximate straight line and the predetermined positive slope, the approximate straight line whose slope of the approximate straight line is closest to the predetermined positive slope is selected. The temperature corresponding to the selected approximate straight line is set as the second reference temperature. For example, when the 22nd approximate straight line is selected, the 22nd temperature is set as the second reference temperature. In the above, it was decided to obtain the 21st approximate straight line to the 23rd approximate straight line, but the number of approximate straight lines to be obtained is "the number of plot points" or "predetermined temperature" indicating the relationship between the temperature information and the demand amount information. It shall be changed as appropriate according to ".

By this process, in actual operation, the first reference temperature and the second reference temperature are set to be close to the minimum and maximum temperatures in the dead zone.

(2) Second Method In the second method, it is determined whether or not the rate of change between the eleventh slope and the thirteenth slope calculated by the first method is included in the predetermined price range. , Set. Here, the rate of change is, for example, a value obtained by dividing the twelfth slope by the eleventh slope as a percentage, or the thirteenth slope divided by the twelfth slope when the first reference temperature is set. It is a value that indicates the value obtained as a percentage. Further, the predetermined price range is a price range predetermined by the operator.

More specifically, first, the reference temperature setting unit 11b calculates the rate of change (hereinafter referred to as "the eleventh rate of change") by indicating the value obtained by dividing the twelfth slope by the eleventh slope as a percentage. .. Next, the reference temperature setting unit 11b calculates the rate of change (hereinafter referred to as "the twelfth rate of change") by indicating the value obtained by dividing the thirteenth slope by the twelfth slope as a percentage. Repeat the procedure in the same way to calculate the rate of change between each approximate straight line.

Then, the calculated plurality of change rates are compared with a predetermined change rate having a predetermined predetermined price range, and the change rate that first matches the predetermined change rate is selected. The temperature corresponding to the selected rate of change is set as the first reference temperature. More specifically, for example, when the selected rate of change is the twelfth rate of change, the twelfth approximation line having the twelfth slope is selected, and the twelfth temperature corresponding to the twelfth approximation line is the first reference. Set to temperature.

Next, the reference temperature setting unit 11b calculates the rate of change (hereinafter referred to as "the 21st rate of change") by indicating the value obtained by dividing the 22nd slope by the 21st slope as a percentage. Next, the reference temperature setting unit 11b calculates the rate of change (hereinafter referred to as "the 22nd rate of change") by indicating the value obtained by dividing the 23rd slope by the 22nd slope as a percentage. Repeat the procedure in the same way to calculate the rate of change between each approximate straight line.

Then, the calculated rate of change is compared with the predetermined rate of change having a predetermined predetermined price range, and the rate of change that first matches the predetermined rate of change is selected. The temperature corresponding to the selected rate of change is set as the second reference temperature.

Thereby, the second process is set so that the first reference temperature and the second reference temperature are closer to the minimum temperature and the maximum temperature of the dead zone as compared with the first process.

<< Regression formula creation unit 11c >>
The regression equation creating unit 11c will be described in detail as follows with reference to FIGS. 4 and 5.

The regression equation creating unit 11c has a function of generating a regression equation based on various information. The regression equation creating unit 11c has a plurality of power demands measured at predetermined times in the past (hereinafter referred to as “past time”), and the first reference temperature and the first reference temperature set by the reference temperature setting unit 11b. 2 Generate a regression equation based on the reference temperature and the temperature measured in the past time. The term "time" includes the meaning of a predetermined time for convenience of explanation. Specifically, for example, a case of indicating a time such as 12 o'clock, a time from 12 o'clock to a time of 13:00, etc. It may indicate the time of.

Here, as shown in FIG. 4, the past time means, for example, the latest 15 days until the current day, 15 days before and after the day one year before the current day, and two years before the current day. The same predetermined time for each day, 15 days before and after the day and 15 days before and after the day three years before the current day. However, the above is only an example, and it is sufficient if various information of a predetermined time can be obtained in a season in which the temperature conditions are similar to those of the current day.

Further, as the explanatory variables for generating the regression equation, information indicating weekdays and holidays and information on the weather (cloudy, sunny, snow, etc.) may be included, and the items of the explanatory variables are limited. It's not a thing. In the following, as an example, information on the first reference temperature and the second reference temperature, information on the temperature, and information on the day of the week will be described as explanatory variables.

As an example, the regression equation creating unit 11c sets the power demand as the "objective variable", the variable related to the first reference temperature, the variable related to the second reference temperature, the maximum temperature, the minimum temperature, and the previous day. Perform multiple regression analysis with variables indicating the maximum temperature, the minimum temperature of the previous day, and the day of the day as "explanatory variables". The least squares method, Bayesian inference method, or the like may be used instead of the multiple regression analysis.

（但し、Ｇは目的変数（電力需要量）、Ａは回帰定数、Ｂ１，Ｂ２、Ｃ１～Ｃ４、Ｄ１，Ｄ２は偏回帰係数、Ｘ１は第１基準気温に関する変数（第１変数情報）、Ｘ２は第２基準気温に関する変数（第２変数情報）、Ｙ１は最高気温、Ｙ２は最低気温、Ｙ３は前日最高気温、Ｙ４は前日最低気温、Ｚ１は平日を示す変数、Ｚ２は休日を示す変数を表す。）

(However, G is the objective variable (power demand), A is the regression constant, B1, B2, C1 to C4, D1 and D2 are the partial regression coefficients, X1 is the variable related to the first reference temperature (first variable information), and X2. Is a variable related to the second reference temperature (second variable information), Y1 is the maximum temperature, Y2 is the minimum temperature, Y3 is the previous day's maximum temperature, Y4 is the previous day's minimum temperature, Z1 is a variable indicating a weekday, and Z2 is a variable indicating a holiday. show.)

Here, the variable (X1) (first variable information) relating to the first reference temperature includes, for example, a temperature (T1) in which the temperature in the past time is smaller than the first reference temperature (a1), as shown in FIG. In the case, the value calculated by "T1-a1" is set, and when the temperature (T2, T3) in the past time is equal to or higher than the first reference temperature (a1), "0" is set. As a result, future demand can be predicted in consideration of changes in demand at temperatures lower than the lower limit of the dead zone.

Further, as shown in FIG. 5, the variable (X2) (second variable information) relating to the second reference temperature includes, for example, a temperature (T1, T2) in which the temperature in the past time is smaller than the second reference temperature (a2). In the case of, "0" is set, and when the temperature (T3) in the past time is larger than the second reference temperature (a2), the value calculated by "T3-a2" is set. As a result, future demand can be predicted in consideration of changes in demand at temperatures higher than the upper limit of the dead zone.

Further, the variables (Z1 and Z2) indicating weekdays and holidays are set to "1" when the predicted day is applicable, and "0" is set when the predicted day is not applicable. This makes it possible to predict future demand by considering the demand that changes depending on weekdays and holidays.

As a result, the arithmetic processing unit 11 can calculate the regression constant and the partial regression coefficient in the past time, and obtain the regression equation for predicting the power demand amount in the predetermined time.

<< Demand Forecasting Unit 11d >>
The demand forecasting unit 11d has a function of calculating the amount of power demand for a predetermined time in the future (hereinafter referred to as "future time") by using the regression equation in the past time obtained by the regression equation creating unit 11c. ..

Specifically, the demand forecasting unit 11d acquires various information (information corresponding to each variable) in the future time from the forecast information table 12b, and sets the same time as the future time obtained by the regression equation creating unit 11c. By inputting the various information into the regression equation in the past time shown, the power demand amount in the future time is calculated.

== Storage unit 12 ==
The storage unit 12 has a function of storing various data for the arithmetic processing unit 11 to execute processing. The storage unit 12 stores the past information table 12a and the prediction information table 12b.

<< Past information table 12a >>
The past information table 12a will be described as follows with reference to FIG. FIG. 6 is a diagram showing an example of the past information table 12a.

The past information table 12a is a table in which various information necessary for generating a multiple regression equation is stored. In the past information table 12a, at least, a "date and time" item indicating the past time (time), a "demand amount" item indicating the amount of power demand in the past time, and a "time temperature" item indicating the temperature of the time are displayed. The "maximum temperature" item indicating the maximum temperature, the "minimum temperature" item indicating the minimum temperature, and the "day" item indicating the day of day are stored in association with each other.

<< Criteria information table 12b >>
The reference information table 12b will be described as follows with reference to FIG. 7. FIG. 7 is a diagram showing an example of the reference information table 12b.

The reference information table is a table in which the first reference temperature, the second reference temperature, and the regression equation for the future time to be predicted are stored. In the reference information table, for example, a "date and time" item indicating the future time (time), a "first reference temperature" item indicating the first reference temperature in the future time, and a "second reference temperature" indicating the second reference temperature are displayed. The "reference temperature" item and the "regression formula" item indicating the regression equation are stored in association with each other.

The storage formats of the past information table 12a and the reference information table 12b are shown as an example, and may be any database format that can be referred to by the arithmetic processing unit 11. Further, the items stored in the past information table 12a and the reference information table 12d are not limited, and the items are necessary for the demand amount prediction device 10 to generate a regression equation for predicting the demand amount. Items should be included.

== Processing flow ==
The processing flow of the demand amount forecasting apparatus 10 according to the first embodiment will be described as follows with reference to FIGS. 8 and 9. FIG. 8 is a diagram showing an example of a processing flow of the demand amount prediction device 10 according to the first embodiment. FIG. 9 is a diagram showing an example of the processing flow of the reference temperature setting unit 11b according to the first embodiment.

First, the information acquisition unit 11a acquires the demand amount information of the past time from an external device and outputs the demand amount information to the storage unit 12 (S100). Then, the information acquisition unit 11a acquires the temperature information of the past time from an external device (Japan Meteorological Agency database) and outputs the temperature information to the storage unit 12 (S200). As a result, information for predicting the amount of electric power demand in the future time is stored in the storage unit 12.

Next, the reference temperature setting unit 11b sets the first reference temperature and the second reference temperature based on the relationship between the demand amount information and the temperature information in the past time (S300). The set first reference temperature and the second reference temperature are stored in the storage unit 12. Hereinafter, the method for setting the first reference temperature and the second reference temperature will be described in detail with reference to FIG. 9.

First, the reference temperature setting unit 11b determines the past time for setting the first reference temperature and the second reference temperature (S1301). Next, the reference temperature setting unit 11b reads the demand amount information and the temperature information from the past information table 12a, and plots these relationships in, for example, an orthogonal coordinate system (S1302). Then, for example, the temperature at the apex of the approximate curve of the plot point is set to the central temperature of the dead zone (S1303). However, the operator may empirically set the central temperature in the dead zone.

Next, the reference temperature setting unit 11b calculates the k-th temperature, which is lower than the central temperature by a predetermined temperature, in order to set the first reference temperature (S1304). The reference temperature setting unit 11b calculates the k-th approximate straight line of the plot points of the temperature information and the demand amount information at the temperature lower than the k-th temperature (S1305). Then, the k-th inclination of the k-th approximate straight line is specified (S1306). For example, the processing of S1304 to S1306 is repeated until the number of plot points indicating a temperature lower than the central temperature becomes equal to or less than the number of predetermined plot points (S1307).

Similarly, the reference temperature setting unit 11b calculates the k-th temperature, which is higher than the central temperature by a predetermined temperature, in order to set the second reference temperature (S1304). The reference temperature setting unit 11b calculates the k-th approximate straight line of the plot points of the temperature information and the demand amount information at the temperature higher than the k-th temperature (S1305). Then, the k-th inclination of the k-th approximate straight line is specified (S1306). The above processes of S1304 to S1306 are repeated (1 to n) (S1307) until the number of plot points indicating a temperature higher than the central temperature becomes equal to or less than the number of predetermined plot points.

The reference temperature setting unit 11b compares whether the first to n slopes of the plurality of first to n approximate straight lines calculated in the above process are equal to the predetermined slope or the predetermined rate of change. , Determine approximate straight lines equal to them (S1308). Since this comparison method is as described in << Reference temperature setting unit 11b >>, the description thereof will be omitted.

The reference temperature setting unit 11b sets the low side air temperature corresponding to the determined approximate straight line as the first reference temperature, and sets the high side air temperature as the second reference temperature (S1309).

Next, the regression equation creating unit 11c creates a multiple regression equation based on the first and second reference temperatures, the temperature information, and the day of the week information (S400). Since the method for creating the multiple regression equation is as described in << Regression equation creation unit 11c >>, the description thereof will be omitted.

Next, the demand forecasting unit 11d substitutes the temperature information and the day of the week information of the future time acquired by the information acquisition unit 11a into the multiple regression equation to calculate the power demand amount of the future time (S500, S600). The demand forecasting unit 11d stores the calculated demand amount information in the storage unit 12. End the process.

=== Demand amount forecasting device 20 according to the second embodiment ===
The demand amount forecasting apparatus 20 according to the second embodiment will be described in detail as follows with reference to FIGS. 10, 11, and 12. FIG. 10 is a diagram showing an example of an outline of the demand amount forecasting device 20 according to the second embodiment. FIG. 11 is a demand temperature graph showing a process of setting the first reference temperature according to the second embodiment. FIG. 12 is a demand temperature graph showing a process of setting the second reference temperature according to the second embodiment.

As shown in FIG. 10, the demand amount prediction device 20 according to the second embodiment is obtained by changing the reference temperature setting unit 11b in the demand amount prediction device 10 according to the first embodiment to the reference temperature setting unit 21b. .. Therefore, the components other than the reference temperature setting unit 21b are the same components as the demand amount prediction device 10 according to the first embodiment, and the description thereof will be omitted. Further, only the differences between the reference temperature setting unit 21b according to the second embodiment and the reference temperature setting unit 11b according to the first embodiment will be described below. As in the first embodiment, the apex of the approximate curve may be set to the central temperature by using the method calculated by the reference temperature setting unit 31b in the third embodiment described later.

In the second embodiment, the relationship between the temperature information and the demand amount information is shown by an approximate straight line, and the distance between the approximate straight line and the plot point showing the relationship between the temperature information and the demand amount information is calculated. Set the reference temperature and the second reference temperature.

Specifically, as shown in FIG. 11, first, the reference temperature setting unit 21b sets a temperature (hereinafter, referred to as “31st temperature”) lower than the central temperature by a predetermined temperature (arbitrarily set). calculate. The relationship between the temperature information and the demand amount information at a temperature lower than the 31st temperature is represented by an approximate linear formula (hereinafter, referred to as “31st approximate straight line”) (one-point chain line in FIG. 11). A value obtained by dividing the sum of the distances between the 31st approximate straight line and a plurality of plot points by the number of plot points (hereinafter referred to as "31st total distance") is calculated. Subsequently, a temperature lower than the 31st temperature by a predetermined temperature (hereinafter referred to as "32nd temperature") is calculated, and at a temperature lower than the 32nd temperature, the relationship between the temperature information and the demand amount information is determined. It is represented by an approximate linear formula (hereinafter referred to as “the 32nd approximate straight line”) (two-point chain line in FIG. 11). A value obtained by dividing the sum of the distances between the 32nd approximate straight line and a plurality of plot points by the number of plot points (hereinafter referred to as "32nd total distance") is calculated. For example, the 32nd total distance is the sum of the perpendicular distances (d11 to d19) from the plot points (P11 to P19) in the temperature range lower than the 32nd temperature to the 32nd approximate straight line, as shown in FIG. Is divided by the number of plot points. Similarly, the process is repeated.

Then, among the plurality of values calculated by dividing the sum of the distances between the approximate straight line and the plurality of plot points by the number of plot points, each value does not change, or the change in the value is a predetermined rate of change. Select the first value that is as follows. The temperature corresponding to the selected value is set as the first reference temperature. For example, the 32nd total distance of all the calculated values does not change in relation to the 33rd total distance calculated after the 32nd total distance, or the change in the value is less than or equal to the predetermined rate of change. In the case of the first value, the 32nd temperature is set as the 1st reference temperature.

Next, as shown in FIG. 12, the reference temperature setting unit 21b calculates a temperature (hereinafter, referred to as “41st temperature”) that is higher than the central temperature by a predetermined temperature. The relationship between the temperature information and the demand amount information at a temperature higher than the 41st temperature is represented by an approximate linear formula (hereinafter referred to as "41st approximate straight line") (one-point chain line in FIG. 8). A value obtained by dividing the sum of the distances between the 41st approximate straight line and a plurality of plot points by the number of plot points (hereinafter referred to as "41st total distance") is calculated. Subsequently, a temperature higher than the 41st temperature by a predetermined temperature (hereinafter referred to as "42nd temperature") is calculated, and at a temperature higher than the 42nd temperature, the relationship between the temperature information and the demand amount information is determined. It is represented by an approximate linear formula (hereinafter, referred to as “42nd approximate straight line”) (two-point chain line in FIG. 12). A value obtained by dividing the sum of the distances between the 42nd approximate straight line and a plurality of plot points by the number of plot points (hereinafter referred to as "42nd total distance") is calculated. For example, the 42nd total distance is the sum of the perpendicular distances (d21 to d29) from the plot points (P21 to P29) in the temperature range higher than the 42nd air temperature to the 42nd approximate straight line, as shown in FIG. Is divided by the number of plot points. Similarly, the process is repeated.

Then, among the plurality of values calculated by dividing the sum of the distances between the approximate straight line and the plurality of plot points by the number of plot points, each value does not change, or the change in the value is a predetermined rate of change. Select the first value that is as follows. The temperature corresponding to the selected value is set as the second reference temperature. For example, the 42nd total distance of all the calculated values does not change in relation to the 43rd total distance calculated after the 42nd total distance, or the change in the value is less than or equal to the predetermined rate of change. In the case of the first value, the 42nd temperature is set to the 2nd reference temperature.

By this process, the first reference temperature and the second reference temperature can be automatically set to be close to the minimum and maximum temperatures in the dead zone. Furthermore, as compared with the reference temperature setting unit 11b according to the first embodiment, the work of predetermining a predetermined inclination can be omitted, so that the work efficiency can be improved.

== Processing flow ==
With reference to FIG. 13, the processing flow of the reference temperature setting unit 21b according to the second embodiment will be described in detail as follows. FIG. 13 is a diagram showing an example of the processing flow of the reference temperature setting unit 21b according to the second embodiment.

Since the demand amount prediction device 20 according to the second embodiment performs the same processing as the S100, S200, S400, S500, S600 in the demand amount prediction device 10 according to the first embodiment, the description thereof will be omitted. .. Further, since steps 2301 to 2305 are the same as steps 1301 to 1305 in the demand amount prediction device 10 according to the first embodiment, the description thereof will be omitted, and steps 2306 to 2309 will be described below.

The reference temperature setting unit 21b calculates the distance between the calculated k-nearest neighbor straight line and each plot point in order to set the first and second reference temperatures, and the sum of the calculated distances is the sum of the calculated distances of the plot points. The k-th total distance indicating the value divided by the number is calculated (S2306). The process of S2304 to S2306 is repeated until the number of plot points indicating a temperature lower than the central temperature becomes less than or equal to the number of predetermined plot points in order to set the first reference temperature, and similarly, for example, the second reference temperature is set. The process of S2304 to S2306 is repeated until the number of plot points indicating a temperature higher than the central temperature is equal to or less than the predetermined number of plot points (S2307).

In the reference temperature setting unit 21b, among the plurality of first to n total distances calculated by the above processing, the value does not change or the value does not change due to the relationship between the kth total distance and the k + 1 total total distance. The first value that is less than or equal to the predetermined rate of change is specified (S2308).

The reference temperature setting unit 21b sets the temperature on the lower side corresponding to the specified value as the first reference temperature, and sets the temperature on the higher side as the second reference temperature (S2309).

=== Demand amount forecasting device 30 according to the third embodiment ===
The demand amount forecasting apparatus 30 according to the third embodiment will be described in detail as follows with reference to FIGS. 14, 15, and 16. FIG. 14 is a diagram showing an example of an outline of the demand amount forecasting device 30 according to the third embodiment. FIG. 15 is a demand temperature graph showing a process of setting the first reference temperature according to the third embodiment. FIG. 16 is a demand temperature graph showing a process of setting the second reference temperature according to the third embodiment.

As shown in FIG. 14, the demand amount prediction device 30 according to the third embodiment is obtained by changing the reference temperature setting unit 11b in the demand amount prediction device 10 according to the first embodiment to the reference temperature setting unit 31b. .. Therefore, the components other than the reference temperature setting unit 31b are the same components as the demand amount prediction device 10 according to the first embodiment, and the description thereof will be omitted. Further, only the differences between the reference temperature setting unit 31b according to the third embodiment and the reference temperature setting unit 11b according to the first embodiment will be described below.

In the third embodiment, the relationship between the temperature information and the demand amount information is shown by an approximate curve, the apex thereof is set to the central temperature, and the plot points showing the relationship between the temperature information and the demand amount information and a predetermined inclination are set. The distance between the straight line and the straight line is calculated, and the first reference temperature and the second reference temperature are set.

More specifically, as shown in FIG. 15, first, the reference temperature setting unit 31b shows the relationship between the temperature information and the demand amount information by an approximate curve (hereinafter, referred to as a “first approximate curve”). The apex of the first approximation curve is set as the central temperature. A straight line passing through the apex and parallel to the axis indicating the temperature (hereinafter referred to as "minimum demand line") is created. As shown in FIG. 15, a temperature (hereinafter referred to as “51st temperature”) lower than the central temperature by a predetermined temperature (arbitrarily set) is calculated. A straight line having a predetermined negative slope (hereinafter referred to as "11th straight line") passing through the intersection of the straight line indicating the 51st temperature and the lowest demand line, and a plot point (P31) at a temperature lower than the 51st temperature. ~ P37) and are added up for each area separated by the 11th straight line, and the absolute value of the difference between the total values for each area (hereinafter referred to as “51st total distance”) is calculated.

At this time, as shown in FIG. 15, the sum of the distances (d35 to d37) between the 11th straight line and the plot points in the positive region separated by the 11th straight line (the sum of the first positive regions) and the 11th straight line are separated. The absolute value (51st total distance) of the difference between the sum of the distances (d31 to d34) between the 11th straight line and the plot points in the negative region (first negative region sum) is calculated.

Subsequently, a temperature (hereinafter referred to as "52 temperature") lower than the 51st temperature by a predetermined temperature (arbitrarily set) is calculated. A straight line having a predetermined negative slope (hereinafter referred to as "12th straight line") passing through the intersection of the straight line indicating the 52nd temperature and the lowest demand line, and plot points at a temperature lower than the 52nd temperature. Is added up for each area divided by the twelfth straight line, and the absolute value of the difference between the total values for each area (hereinafter, referred to as "52nd total distance") is calculated.

Then, among the calculated absolute values, the absolute value indicating the minimum value is selected. The temperature corresponding to the absolute value indicating the selected minimum value is set as the first reference temperature. For example, when the 51st total distance is the smallest among all the calculated absolute values, the 51st temperature is set as the first reference temperature.

Next, as shown in FIG. 16, the reference temperature setting unit 31b calculates a temperature (hereinafter, referred to as “61st temperature”) that is higher than the central temperature by a predetermined temperature (arbitrarily set). A straight line having a predetermined positive slope (hereinafter referred to as "21st straight line") passing through the intersection of the straight line indicating the 61st temperature and the lowest demand line, and a plot point (P41) at a temperature higher than the 61st temperature. ~ P47) and the distances are summed for each region separated by the 21st straight line, and the absolute value of the difference between the summed values for each region (hereinafter referred to as “61st summed distance”) is calculated.

At this time, as shown in FIG. 16, the sum of the distances (d45 to d47) between the 21st straight line and the plot points (d45 to d47) in the negative region separated by the 21st straight line and the sum of the second negative regions are separated by the 21st straight line. The absolute value (61st total distance) of the difference between the sum of the distances (d41 to d44) between the 21st straight line and the plot points in the positive region (second positive region sum) is calculated.

Subsequently, a temperature (hereinafter referred to as "62 temperature") higher than the 61st temperature by a predetermined temperature (arbitrarily set) is calculated. A straight line having a predetermined positive slope (hereinafter referred to as "22nd straight line") passing through the intersection of the straight line indicating the 62nd temperature and the lowest demand line, and plot points at a temperature higher than the 62nd temperature. Is added up for each area separated by the 22nd straight line, and the absolute value of the difference between the total values for each area (hereinafter referred to as "62nd total distance") is calculated.

Then, among the calculated absolute values, the absolute value indicating the minimum value is selected. The temperature corresponding to the absolute value indicating the selected minimum value is set as the second reference temperature. For example, when the 61st total distance is the smallest among all the calculated absolute values, the 61st temperature is set as the second reference temperature.

As a result, the central temperature of the dead zone can be set accurately, so that the first reference temperature and the second reference temperature can be automatically set to be close to the minimum and maximum temperatures of the dead zone based on the central temperature. .. Furthermore, as compared with the reference temperature setting unit 31b according to the first embodiment, the work of predetermining a predetermined rate of change can be omitted, so that the work efficiency can be improved.

== Processing flow ==
The processing flow of the demand amount forecasting apparatus 30 according to the third embodiment will be described in detail with reference to FIG. 17 as follows. FIG. 17 is a diagram showing an example of a processing flow of the reference temperature setting unit 31b according to the third embodiment.

Since the demand amount prediction device 30 according to the third embodiment performs the same processing as the S100, S200, S400, S500, S600 in the demand amount prediction device 10 according to the first embodiment, the description thereof will be omitted. .. Further, since S3301 to S3304 are the same as S1301 to S1304 in the demand amount prediction device 10 according to the first embodiment, the description thereof will be omitted, and S3305 to S3309 will be described below.

The reference temperature setting unit 31b creates a k-th straight line having a predetermined negative slope in order to set the first reference temperature (S3305). Absolute difference between the sum of the distances between the k-line and the plot points in the positive region separated by the k-th straight line and the sum of the distances between the k-line and the plot points in the negative region separated by the k-th straight line. The value (kth total distance) is calculated (S3306).

Then, the reference temperature setting unit 31b repeats the processes of S3304 to S3306 until the number of plot points indicating the temperature lower than the central temperature becomes less than or equal to the number of predetermined plot points in order to set the first reference temperature, and similarly. , The process of S3304 to S3306 is repeated until the number of plot points indicating a temperature higher than the central temperature becomes less than or equal to the number of predetermined plot points in order to set the second reference temperature (S3307).

The reference temperature setting unit 31b specifies the minimum total distance among the plurality of first to nth total distances calculated in the above process (S3308).

The reference temperature setting unit 31b sets the low side temperature corresponding to the specified total distance as the first reference temperature, and sets the high side temperature as the second reference temperature (S3309).

=== Other embodiments ===
A demand amount forecasting device (not shown) according to another embodiment will be described below with reference to FIG. 18. FIG. 18 is a conceptual diagram showing an example for predicting a demand amount according to another embodiment.

In the above, it has been described that a multiple regression equation is created for the relationship between the demand amount and the temperature showing the bathtub curve as shown in FIG. 5, but the present invention is not limited to this.

For example, it has a dead zone having a low temperature as shown in FIG. 18 (hereinafter referred to as "first dead zone") and a dead zone having a high temperature (hereinafter referred to as "second dead zone"). By creating a multiple regression equation for the relationship between the demand amount and the temperature, the demand amount in the future time may be predicted. In the first dead zone, the lower reference temperature is the 11th reference temperature (a11), and the higher reference temperature is the 12th reference temperature (a12). Further, in the second dead zone, the lower reference temperature is the 21st reference temperature (a13), and the higher reference temperature is the 22nd reference temperature (a14). The 11th reference temperature, the 12th reference temperature, the 21st reference temperature, and the 22nd reference temperature are set in advance by the operator via the reference temperature setting unit.

In this case, as an example, the regression equation creation unit (not shown) sets the power demand as the "objective variable", the variable related to the eleventh reference temperature (a11), and the twelfth reference temperature (not shown). Variables related to a12), the function related to the 21st reference temperature (a13), the function related to the 22nd reference temperature (a14), the maximum temperature, the minimum temperature, the previous day's maximum temperature, the previous day's minimum temperature, and the variables indicating the day of the day are used as "explanatory variables". Perform regression analysis. The least squares method, Bayesian inference method, or the like may be used instead of the multiple regression analysis.

（但し、Ｇは目的変数（電力需要量）、Ａは回帰定数、Ｂ１～Ｂ３、Ｃ１～Ｃ４、Ｄ１，Ｄ２は偏回帰係数、Ｘ１は第１１基準気温に関する変数、Ｘ２は第１２基準気温と第２１基準気温に関する変数、Ｘ３は第２２基準気温に関する変数、Ｙ１は最高気温、Ｙ２は最低気温、Ｙ３は前日最高気温、Ｙ４は前日最低気温、Ｚ１は平日を示す変数、Ｚ２は休日を示す変数を表す。）

(However, G is the objective variable (power demand), A is the regression constant, B1 to B3, C1 to C4, D1 and D2 are the partial regression coefficients, X1 is the variable related to the 11th reference temperature, and X2 is the 12th reference temperature. Variables related to the 21st reference temperature, X3 is a variable related to the 22nd reference temperature, Y1 is the highest temperature, Y2 is the lowest temperature, Y3 is the highest temperature the day before, Y4 is the lowest temperature the day before, Z1 is a variable indicating a weekday, and Z2 is a holiday. Represents a variable.)

Here, as shown in FIG. 18, the variable (X1) relating to the 11th reference temperature includes, for example, "T11-a11" when the temperature in the past time is smaller than the 11th reference temperature (a11) (T11). The value calculated in "" is set, and "0" is set when the temperature in the past time is equal to or higher than the eleventh reference temperature (a11). As a result, future demand can be predicted in consideration of changes in demand at temperatures lower than the lower limit of the dead zone.

Further, as shown in FIG. 18, in the variables (X2) relating to the 12th reference temperature and the 21st reference temperature, for example, the temperature in the past time is larger than the 12th reference temperature (a12) and the 21st reference temperature (a13). In the case of a lower temperature (T13), the value calculated by "T13-a12" is set. Further, for example, when the temperature in the past time is larger than the 21st reference temperature (a13) and smaller than the 22nd reference temperature (a14) (T14), the value calculated by "a13-a12" is set. .. As a result, the future demand amount can be predicted in consideration of the change in the demand amount in the temperature from the first dead zone to the second dead zone.

Further, as shown in FIG. 18, the variable (X3) relating to the 22nd reference temperature is set to "0", for example, when the temperature in the past time is smaller than the 22nd reference temperature (a14) (T11 to T14). Then, when the air temperature in the past time is larger than the second reference air temperature (a14) (T15), the value calculated by "T15-a14" is set. As a result, the future demand amount can be predicted in consideration of the change in the demand amount at the temperature larger than the upper limit value of the second dead zone.

=== Summary ===
As described above, the demand amount prediction devices 10, 20, and 30 according to the present embodiment acquire the air temperature information indicating the air temperature and the demand amount information corresponding to the air temperature information and indicating the electric power demand amount of the consumer. Based on the relationship between the information acquisition units 11a, 21a, 31a, the temperature, and the demand amount, the first criterion for identifying the dead zone in which the electricity demand amount of the consumer is not easily affected even if the temperature fluctuates. The reference temperature setting units 11b, 21b, 31b that set the air temperature and the second reference temperature higher than the first reference temperature, the demand amount information in the past predetermined time, and the first reference temperature indicating the first reference temperature. The first variable information indicating a predetermined value determined by the relationship between the reference temperature information and the temperature information, and the second variable information indicating the predetermined value determined by the relationship between the second reference temperature information indicating the second reference temperature and the temperature information. The regression equation creation units 11c, 21c, 31c that create the regression equation based on the above, the regression equation, the first reference temperature information and the second reference temperature information in the past predetermined time, and the future predetermined time. It is provided with a demand prediction unit 11d, 21d, 31d for calculating a consumer's electric power demand amount at a predetermined time in the future based on the temperature information in the above. According to the present embodiment, it is possible to accurately predict the demand amount in the future time in consideration of the dead zone for the demand amount of the temperature.

Further, the reference temperature setting unit 11b of the demand amount prediction device 10 according to the present embodiment sets a plurality of temperatures lower than the temperature lower than the predetermined temperature (central temperature) (any of the 11th to 13th temperatures). Approximate linear formula (any of the 11th to 13th approximate straight lines) that approximates the relationship between the 1st air temperature information shown and the 1st air temperature information corresponding to the 1st air temperature information and indicating the power demand of the consumer. When the inclination of (any of the eleventh to thirteenth inclinations) indicates a predetermined inclination, the first temperature (any of the eleventh to thirteenth temperatures) is set as the first reference temperature, and the predetermined temperature (center). The second temperature information indicating multiple temperatures higher than the temperature higher than the air temperature (any of the 21st to 23rd temperatures) and the second temperature information corresponding to the second temperature information and indicating the power demand of the consumer. The second temperature when the slope (any of the 21st to 23rd slopes) of the approximate linear formula (any of the 21st to 23rd approximate straight lines) that approximates the relationship with the demand amount information shows a predetermined slope. (Any of the 21st to 23rd temperatures) is set as the second reference temperature. According to the present embodiment, since the first reference temperature and the second reference temperature can be set accurately based on the actual results of the air temperature and the demand amount, the demand amount in the future time can be predicted more accurately.

Further, the reference temperature setting unit 11b of the demand amount prediction device 10 according to the present embodiment has a slope (any of the eleventh to thirteenth slopes) of the approximate straight line formula (any of the eleventh to thirteenth approximate straight lines). Corresponds to the third temperature information indicating multiple temperatures and the third temperature information, which are lower than the temperature (any of the eleventh to thirteenth temperatures) and lower than the temperature (one of the twelfth and thirteenth temperatures). The slope (either the twelfth or the thirteenth slope) of the approximate straight line formula (either the twelfth or the thirteenth approximate straight line) that approximates the relationship with the third demand amount information indicating the power demand amount of the consumer. The temperature (any of the 11th to 13th temperatures) when the rate of change of is set to a predetermined value is set as the first reference temperature, and the slope of the approximate linear formula (any of the 21st to 23rd approximate straight lines) (any of the 21st to 23rd approximate straight lines) is set. A fourth indicating a plurality of temperatures that are higher than the temperature (any of the 22nd and 23rd temperatures) higher than the temperature (any of the 21st to 23rd slopes) and the temperature (any of the 21st to 23rd slopes). The slope of the approximate linear formula (either the 22nd or the 23rd approximate straight line) that approximates the relationship between the temperature information and the 4th demand information that corresponds to the 4th temperature information and indicates the power demand of the consumer. The temperature (any of the 21st to 23rd temperatures) when the rate of change of (either the 22nd or the 23rd slope) shows a predetermined value is set as the second reference temperature. According to the present embodiment, it is determined that the rate of change of the slope of the approximate linear formula indicates a predetermined price range predetermined as the most appropriate value for setting the first reference temperature and the second reference temperature. Thereby, the first reference temperature and the second reference temperature can be set accurately.

Further, the reference temperature setting unit 21b of the demand amount prediction device 20 according to the present embodiment sets a plurality of temperatures lower than the temperature lower than the predetermined temperature (central temperature) (any of the 31st to 33rd temperatures). Approximate linear equation (31st to 33rd) that approximates the 1st plot point showing the relationship between the 5th air temperature information shown and the 5th air temperature information corresponding to the 5th air temperature information and showing the power demand of the consumer. A value obtained by dividing the sum of the shortest distances (d11 to d19) between (one of the approximate straight lines), the relationship between the fifth temperature information and the fifth demand amount information, by the number of first plot points is a predetermined condition. The temperature (any of the 31st to 33rd temperatures) when the condition is satisfied (the temperature does not change or the change in the value is less than the predetermined rate of change) is set as the first reference temperature, and is higher than the predetermined temperature in the dead zone. The sixth temperature information indicating a plurality of temperatures higher than the air temperature (any of the 41st to 43rd temperatures), the sixth temperature information corresponding to the sixth temperature information, and the sixth demand information indicating the power demand of the consumer. The shortest distance (d21 to d29) between the approximate linear equation (any of the 41st to 43rd approximate straight lines) that approximates the second plot point showing the relationship between the 6th temperature information and the 6th demand amount information. ) Is divided by the number of second plot points, and the temperature (41st to 43rd temperature) when the predetermined condition is satisfied (the value does not change or the change in the value is less than the predetermined rate of change). Either) is set to the second reference temperature. According to the present embodiment, since the relationship between the air temperature and the demand amount and the relationship between the approximate linear formula specifies the optimum temperature range, the first reference temperature and the second reference temperature can be set accurately.

Further, the reference temperature setting units 11b and 21b of the demand amount prediction devices 10 and 20 according to the present embodiment are approximate curve equations that approximate the relationship between the plurality of temperature information and the demand amount information corresponding to the plurality of temperature information. The temperature corresponding to the peak of is set to a predetermined temperature (central temperature) in the dead zone. According to this embodiment, the central air temperature can be set automatically, so that the work efficiency can be improved.

Further, the reference temperature setting unit 31b of the demand amount prediction device 30 according to the present embodiment shows the relationship between the plurality of temperature information and the demand amount information corresponding to the plurality of temperature information by an approximate curve formula. In a range indicating a temperature lower than the central temperature indicating the temperature corresponding to the apex of, a linear formula (either the 11th or 12th straight line) having a predetermined negative slope and a positive region separated by the linear formula. In, the 7th temperature information indicating a plurality of temperatures lower than the temperature lower than the central temperature (either the 51st or the 52nd temperature) and the 7th temperature information corresponding to the customer's electric power demand are shown. The first positive region sum, which indicates the sum of the shortest distances and the relationship between the seventh demand amount information, is calculated, and a linear formula (either the eleventh or the twelfth straight line) having a predetermined negative slope and the said. In the negative region separated by a straight line, it corresponds to the 7th temperature information indicating multiple temperatures and the 7th temperature information, which are lower than the temperature lower than the central temperature (either the 51st or the 52nd temperature). The first negative region sum, which indicates the sum of the shortest distances and the relationship between the seventh demand amount information indicating the power demand amount of the consumer, is calculated, and the first positive region sum and the first negative region sum are calculated. The seventh temperature when the absolute value of the difference shows the smallest value is set as the first reference temperature, and the linear formula (21st, 22nd) having a predetermined positive slope in the range showing a temperature higher than the central temperature. 8th temperature information indicating a plurality of temperatures higher than the central temperature (either 61st or 62nd temperature) in the positive region separated by the straight line) and the 8th temperature information. Corresponding to the 8th temperature information, the relationship between the 8th demand amount information indicating the electric power demand amount of the consumer and the 2nd positive region sum indicating the sum of the shortest distances is calculated and has a predetermined positive slope. In the negative region separated by the linear type (either the 21st or 22nd straight line) and the linear type (either the 21st or 22nd straight line), the temperature higher than the central temperature (61st and 62nd temperature) The sum of the shortest distances between the relationship between the 8th temperature information indicating a plurality of temperatures higher than any) and the 8th temperature information corresponding to the 8th temperature information and indicating the electric power demand of the consumer. The second negative region sum is calculated, and the eighth temperature when the absolute value of the difference between the second positive region sum and the second negative region sum shows the smallest value is set as the second reference temperature. According to this embodiment, since the central temperature can be set automatically, the work efficiency can be improved, and further, the relationship between the temperature and the demand and the relationship between the approximate linear formula specifies the optimum temperature range. Therefore, the first reference temperature and the second reference temperature can be set accurately.

It should be noted that the above embodiment is for facilitating the understanding of the present invention, and is not for limiting the interpretation of the present invention. The present invention can be modified and improved without departing from the spirit thereof, and the present invention also includes an equivalent thereof.

10, 20, 30 Demand forecasting device 11 Arithmetic processing unit 11a, 21a, 31a Information acquisition unit 11b, 21b, 31b Reference temperature setting unit 11c, 21c, 31c Regression formula creation unit 11d, 21d, 31d Demand forecasting unit

Claims (6)

An information acquisition unit that acquires temperature information indicating the air temperature and demand amount information indicating the electric power demand amount of the consumer corresponding to the temperature.
In the relationship between the air temperature and the electric power demand, the first reference temperature and the second reference temperature higher than the first reference temperature are used to identify a dead zone in which the electric power demand is not easily affected even if the temperature fluctuates. And, the standard temperature setting part to set, and
The demand amount information in the past predetermined time, the first variable information indicating a predetermined value determined by the relationship between the first reference temperature information indicating the first reference temperature and the temperature information, and the second reference temperature. A regression equation creation unit that creates a regression equation based on the second variable information indicating a predetermined value determined by the relationship between the second reference temperature information indicating the temperature information and the temperature information.
A consumer at a predetermined time in the future based on the regression equation, the first reference temperature information and the second reference temperature information at a predetermined time in the past, and the temperature information at a predetermined time in the future. Equipped with a demand forecasting unit that calculates the amount of electricity demand in
The reference temperature setting unit is
Relationship between the first temperature information indicating a plurality of temperatures lower than the first temperature lower than the predetermined temperature and the first demand amount information corresponding to the first temperature information and indicating the electric power demand of the consumer. When the first slope of the first approximate linear formula that approximates the above indicates a predetermined slope, the first temperature is set to the first reference temperature.
The second temperature information indicating a plurality of temperatures higher than the second temperature higher than the predetermined temperature, and the second demand information indicating the power demand of the consumer corresponding to the second temperature information. A demand amount prediction device that sets the second temperature when the second slope of the second approximate linear formula that approximates the relationship shows a predetermined slope to the second reference temperature. The reference temperature setting unit is
The first slope of the first approximate linear equation and
The third temperature information indicating a plurality of temperatures lower than the first temperature and lower than the third temperature, and the third demand information corresponding to the third temperature information and indicating the electric power demand of the consumer. The third slope of the third approximate linear formula that approximates the relationship, and
The first temperature when the rate of change of the above indicates a predetermined value is set to the first reference temperature, and the temperature is set to the first reference temperature.
The second slope of the second approximate linear equation and
The fourth temperature information indicating a plurality of temperatures higher than the fourth temperature higher than the second temperature, and the fourth demand information corresponding to the fourth temperature information and indicating the electric power demand of the consumer. The 4th inclination of the 4th approximate linear formula that approximates the relationship, and
The demand amount forecasting apparatus according to claim 1, wherein the second temperature when the rate of change of is set to a predetermined value is set to the second reference temperature. An information acquisition unit that acquires temperature information indicating the air temperature and demand amount information indicating the electric power demand amount of the consumer corresponding to the temperature.
In the relationship between the air temperature and the electric power demand, the first reference temperature and the second reference temperature higher than the first reference temperature are used to identify a dead zone in which the electric power demand is not easily affected even if the temperature fluctuates. And, the standard temperature setting part to set, and
The demand amount information in the past predetermined time, the first variable information indicating a predetermined value determined by the relationship between the first reference temperature information indicating the first reference temperature and the temperature information, and the second reference temperature. A regression equation creation unit that creates a regression equation based on the second variable information indicating a predetermined value determined by the relationship between the second reference temperature information indicating the temperature information and the temperature information.
A consumer at a predetermined time in the future based on the regression equation, the first reference temperature information and the second reference temperature information at a predetermined time in the past, and the temperature information at a predetermined time in the future. Equipped with a demand forecasting unit that calculates the amount of electricity demand in
The reference temperature setting unit is
Relationship between the 5th temperature information indicating a plurality of temperatures lower than the 5th temperature lower than the predetermined temperature and the 5th demand amount information corresponding to the 5th temperature information and indicating the electric power demand of the consumer. Set the 5th approximate linear equation that approximates the 1st plot point showing
The value obtained by dividing the sum of the shortest distances of the first plot points with respect to the fifth approximate linear equation by the number of the first plot points satisfies the predetermined condition, and the fifth temperature is used as the first reference temperature. Set,
The sixth temperature information indicating a plurality of temperatures higher than the sixth temperature higher than the predetermined temperature, and the sixth demand information indicating the power demand of the consumer corresponding to the sixth temperature information. Set the 6th approximate linear formula that approximates the 2nd plot point showing the relationship,
The value obtained by dividing the sum of the shortest distances of the second plot points with respect to the sixth approximate linear equation by the number of the second plot points makes the sixth temperature when a predetermined condition is satisfied to the second reference temperature. A demand forecaster characterized by being set. The reference temperature setting unit is
A claim characterized in that the temperature corresponding to the apex of the approximate curve equation that approximates the relationship between the plurality of the temperature information and the demand amount information corresponding to the plurality of temperature information is set to the predetermined temperature. Item 1 or the demand amount forecasting apparatus according to claim 3. An information acquisition unit that acquires temperature information indicating the air temperature and demand amount information indicating the electric power demand amount of the consumer corresponding to the temperature.
In the relationship between the air temperature and the electric power demand, the first reference temperature and the second reference temperature higher than the first reference temperature are used to identify a dead zone in which the electric power demand is not easily affected even if the temperature fluctuates. And, the standard temperature setting part to set, and
The demand amount information in the past predetermined time, the first variable information indicating a predetermined value determined by the relationship between the first reference temperature information indicating the first reference temperature and the temperature information, and the second reference temperature. A regression equation creation unit that creates a regression equation based on the second variable information indicating a predetermined value determined by the relationship between the second reference temperature information indicating the temperature information and the temperature information.
A consumer at a predetermined time in the future based on the regression equation, the first reference temperature information and the second reference temperature information at a predetermined time in the past, and the temperature information at a predetermined time in the future. Equipped with a demand forecasting unit that calculates the amount of electricity demand in
The reference temperature setting unit is
The relationship between the plurality of the temperature information and the demand amount information corresponding to the plurality of temperature information is shown by an approximate curve formula.
In the range indicating a temperature lower than the central temperature indicating the temperature corresponding to the apex of the approximate curve equation, the power demand corresponding to the apex and the seventh temperature lower than the central temperature are used as coordinates. Set the first linear equation with a predetermined negative slope,
In the positive region separated by the first linear formula, the seventh temperature information indicating a plurality of temperatures lower than the seventh temperature and the seventh temperature information corresponding to the seventh temperature information and indicating the electric power demand of the consumer are shown. 7 Set the third plot point showing the relationship with the demand information,
The first positive domain sum showing the sum of the shortest distances between the first linear equation and the third plot point was calculated.
In the negative region separated by the first linear formula, a fourth plot point showing the relationship between the seventh temperature information and the seventh demand amount information is set.
The first negative region sum showing the sum of the shortest distances between the first linear equation and the fourth plot point was calculated.
The seventh air temperature when the absolute value of the difference between the first positive region sum and the first negative region sum shows the smallest value is set as the first reference temperature.
A second linear equation having a predetermined positive slope, passing through a point whose coordinates are the power demand corresponding to the apex and the eighth temperature higher than the central temperature in the range indicating a temperature higher than the central temperature. And set
In the positive region separated by the second linear formula, the eighth temperature information indicating a plurality of temperatures higher than the eighth temperature and the eighth temperature information corresponding to the eighth temperature information and indicating the electric power demand of the consumer are shown. 8 Set the 5th plot point showing the relationship with the demand information,
The second positive domain sum, which indicates the sum of the shortest distances between the second linear equation and the fifth plot point, is calculated.
In the negative region separated by the second linear equation, a sixth plot point showing the relationship between the eighth temperature information and the eighth demand amount information is set.
The second negative region sum, which indicates the sum of the shortest distances between the second linear equation and the sixth plot point, is calculated.
Demand forecast, characterized in that the eighth temperature when the absolute value of the difference between the second positive region sum and the second negative region sum shows the smallest value is set as the second reference temperature. Device. It is a method of predicting the demand for electric power to be executed by the device.
The device is
The temperature information indicating the air temperature and the demand amount information indicating the electric power demand amount of the consumer corresponding to the above temperature are acquired.
In the relationship between the air temperature and the electric power demand, the first reference temperature and the second higher than the first reference temperature are used to identify a dead zone in which the electric power demand is unlikely to fluctuate even if the temperature fluctuates. Set the standard temperature and
The demand amount information in the past predetermined time, the first variable information indicating a predetermined value determined by the relationship between the first reference temperature information indicating the first reference temperature and the temperature information, and the second reference temperature. A regression equation is created based on the second reference temperature information indicating the above and the second variable information indicating a predetermined value determined by the relationship between the temperature information.
A consumer at a predetermined time in the future based on the regression equation, the first reference temperature information and the second reference temperature information at a predetermined time in the past, and the temperature information at a predetermined time in the future. Calculate the power demand of
Relationship between the first temperature information indicating a plurality of temperatures lower than the first temperature lower than the predetermined temperature and the first demand amount information corresponding to the first temperature information and indicating the electric power demand of the consumer. When the first slope of the first approximate linear formula that approximates the above indicates a predetermined slope, the first temperature is set to the first reference temperature.
The second temperature information indicating a plurality of temperatures higher than the second temperature higher than the predetermined temperature, and the second demand information indicating the power demand of the consumer corresponding to the second temperature information. A demand amount prediction method, characterized in that the second temperature when the second slope of the second approximate linear formula that approximates the relationship shows a predetermined slope is set to the second reference temperature.

Images