JP2021182791A - Power demand predicting device, control method for power demand predicting device, and program - Google Patents

Abstract

To predict a near-future power demand more accurately.SOLUTION: A power demand predicting device for obtaining a prediction value of a power demand, includes a result value storage unit that stores a result value of a power demand, a calculation expression storage unit that stores a calculation expression for calculating a power demand at a reference time point by using the result value of the power demand predetermined time before the reference time point, a change amount calculating unit that calculates a power demand at the present time point and a power demand at a prediction target time point by using the result value of the power demand and the calculation expression, and obtains a change amount of the power demand from the present time point to the prediction target time point on the basis of the difference between the calculated values, and a predication value calculating unit that obtains a prediction value of the power demand at the prediction target time point by adding the change amount to the result value of the power demand at the present time point.SELECTED DRAWING: Figure 5

Description

The present invention relates to a power demand forecasting device, a control method and a program of the power demand forecasting device.

Based on the power generation plan decided based on the power demand forecast created up to the previous day, the electric power company combines multiple power demand forecasts from tens of minutes to several hours ahead every day, and the deadline for changing the plan on the day (gate close). ) Is being reviewed.

Japanese Unexamined Patent Publication No. 2013-062953

However, in recent years, power generation facilities using natural energy such as solar power and wind power have rapidly become widespread, making it difficult to forecast the demand for electric power.

Therefore, there is a demand for a technique for more accurately predicting the amount of electric power demand in a short time of several tens of minutes to several hours.

The present invention has been made in view of the above problems, and is a power demand prediction device and a power demand prediction device capable of more accurately predicting the power demand in a short time of several tens of minutes to several hours. It is an object of the present invention to provide a control method and a program of.

The electric power demand forecasting device that solves the above problems is a power demand forecasting device that obtains a predicted value of the electric power demand, and has an actual value storage unit that stores the actual value of the electric power demand and a predetermined time before the reference time. A calculation formula storage unit that stores a calculation formula for calculating the power demand amount at the reference time point using the actual value of the power demand amount of the above, and the current value and the calculation formula of the power demand amount are used at the present time and. The change amount calculation unit that calculates the power demand amount at the time of the forecast target and obtains the change amount of the power demand amount from the current time to the forecast target time point from the difference of each calculated value, and the change amount is the current power demand amount. It is provided with a predicted value calculation unit for obtaining a predicted value of the electric power demand at the time of the prediction target by adding it to the actual value of.

In addition, the problems disclosed in the present application and the solutions thereof will be clarified by the description in the column of the mode for carrying out the invention, the description in the drawings, and the like.

It will be possible to more accurately predict the amount of electricity demand in a short period of time.

It is a hardware block diagram of the power demand forecasting apparatus. It is a figure which shows the storage device of the electric power demand forecasting apparatus. It is a figure which shows the electric power demand actual value management table. It is a functional block diagram of the electric power demand forecasting apparatus. It is a figure which shows the state which obtains the predicted value of the electric power demand. It is a figure which shows the state of finding the insensitive zone of temperature. It is a figure which shows the state of finding the insensitive zone of temperature. It is a figure which shows an example of the past time. It is a figure which shows the dead zone of the temperature. It is a figure which shows an example of the daytime time zone. It is a flowchart which shows the flow of the electric power demand amount prediction processing. It is a figure which shows the state which obtains the predicted value of the electric power demand. It is a figure which shows the state which obtains the predicted value of the electric power demand. It is a flowchart which shows the flow of the electric power demand amount prediction processing. It is a figure which shows the state which obtains the predicted value of the electric power demand. It is a figure which shows the state which obtains the predicted value of the electric power demand. It is a flowchart which shows the flow of the electric power demand amount prediction processing.

The description of this specification and the accompanying drawings will clarify at least the following matters. Hereinafter, the present invention will be described according to the embodiment with reference to the accompanying drawings.

== Power demand forecaster ==
The electric power demand forecasting device 100 according to the embodiment of the present invention is an apparatus for obtaining a predicted value of the electric power demand for a short time of several tens of minutes to several hours ahead.

Although the details will be described later, the power demand prediction device 100 according to the present embodiment uses the calculation formula 310 for calculating the power demand amount prepared in advance by using a method such as multiple regression analysis. Calculate the current power demand and the power demand at the forecast target time point (for example, 3 hours after the current time), and use the difference between these calculated values to estimate the change in power demand from the current time to the forecast target time point. Then, by adding this change amount to the actual value of the current power demand amount, the predicted value of the power demand amount at the time of the prediction target is calculated.

The electric power demand amount calculated by using the calculation formula 310 is appropriate because it is calculated based on the data such as the temperature which is related to the electric power demand amount and the calculation formula 310 which formulates the relation. However, the value of the power demand calculated by the above formula 310 may deviate from the actual value due to some factor such as a temporary change in the weather condition. In such a case, this divergence may continue for a short period of time, such as tens of minutes to several hours.

Like the power demand forecasting device 100 according to the present embodiment, the change amount of the power demand amount from the present time to the prediction target time point is obtained, and the change amount is added to the actual value of the current power demand amount for prediction. By calculating the predicted value of the power demand at the target time point, the influence of the divergence can be reduced even if the above divergence occurs, and the predicted value of the power demand can be accurately calculated. It becomes possible to calculate. In this way, according to the electric power demand amount predicting device 100 according to the present embodiment, it is possible to more accurately predict the electric power demand amount in a short time of about several tens of minutes to several hours.

Data such as various actual values, observed values, and predicted values related to the amount of power demand can be adopted as the explanatory variables of the above calculation formula 310. For example, in the present embodiment, the power demand before a predetermined time is used. The actual value of the quantity is included in the explanatory variables. In addition, various data such as temperature, amount of solar radiation, amount of precipitation, day of the week, and weather may be included as explanatory variables. Details will be described later.

<Hardware configuration>
FIG. 1 shows a hardware configuration diagram of the power demand forecasting device 100. The power demand prediction device 100 is, for example, a computer having a CPU (Central Processing Unit) 110, a memory 120, a storage device 130, a recording medium reading device 140, a communication device 150, an input device 160, and an output device 170, and various information processing devices. It is composed of electronic devices such as.

The storage device 130 includes a power demand prediction device control program 700 executed or processed by the power demand prediction device 100, a power demand actual value management table 300 described later, a calculation formula 310, a reference temperature 320, and a reference precipitation 330. Stores various data such as. FIG. 2 shows how the power demand forecasting device control program 700 and the above data are stored in the storage device 130.

The power demand forecasting device control program 700 and various data stored in the storage device 130 are read into the memory 120 and executed or processed by the CPU 110 to realize various functions of the power demand forecasting device 100. NS. Here, the storage device 130 is a non-volatile storage device such as a hard disk drive, an SSD (Solid State Drive), or a flash memory.

The power demand prediction device control program 700 is a general term for programs for realizing the functions of the power demand prediction device 100, and for example, an application program or an OS (Operating System) that operates on the power demand prediction device 100. ), Various libraries, etc. are included.

FIG. 3 shows an example of the electric power demand actual value management table 300. In the electric power demand amount actual value management table 300, the actual value of the electric power demand amount is stored in association with the date and time information. In the example shown in FIG. 3, y (t) indicates the actual value of the current power demand, and y (t-τ) is the power demand predetermined time before the current time (1 hour in the example shown in FIG. 3). Shows the actual value of the quantity. For convenience, FIG. 3 shows the actual value of the electric power demand amount at predetermined time intervals (every hour), but the electric power demand amount actual value management table 300 shows the actual value other than the actual value shown in FIG. At any time, for example, the actual value of the electric power demand every minute is stored. The electric power demand forecasting device 100 acquires the actual value of the electric power demand from another computer (not shown) connected so as to be communicable via the Internet at any time, and records the actual value of the electric power demand in the electric power demand actual value management table 300. To go.

Returning to FIG. 1, the recording medium reading device 140 reads a program or data recorded on a recording medium 800 such as a CD-ROM or a DVD, and stores the program or data in the storage device 130.

The communication device 150 exchanges data and programs with another computer (not shown) via a communication network such as the Internet or a LAN (Local Area Network). For example, the power demand forecaster control program 700 described above may be stored in another computer so that the power demand forecaster 100 downloads the power demand forecaster control program 700 from this computer and executes it. can.

Alternatively, the communication device 150 periodically obtains various weather information such as the actual value of the electric power demand, the temperature, the amount of precipitation, and the amount of solar radiation from the computer that distributes the actual value of the electric power demand and the computer that distributes the meteorological information. It may be received in.

The input device 160 is an input interface such as various buttons, switches, a keyboard, and a microphone that receive commands and data input by the user.

The output device 170 is, for example, a display device such as a display, or an output user interface such as a speaker.

<Functional configuration>
FIG. 4 shows a functional block diagram of the electric power demand amount prediction device 100 according to the present embodiment. The power demand prediction device 100 includes each function of an actual value storage unit 101, a calculation formula storage unit 102, a change amount calculation unit 103, a predicted value calculation unit 104, a reference temperature storage unit 105, and a reference precipitation storage unit 106. These functions are realized by executing or processing the power demand forecasting device control program 700 and various data according to the present embodiment by the hardware shown in FIG. 1.

[Actual value storage unit]
The actual value storage unit 101 stores the actual value of the electric power demand amount. In the present embodiment, the actual value storage unit 101 is embodied as the power demand actual value management table 300 or the storage device 130 described above. FIG. 2 shows how the power demand actual value management table 300 is stored in the storage device 130.

[Calculation formula storage unit]
The calculation formula storage unit 102 stores the calculation formula 310 for calculating the power demand amount at the reference time using the actual value of the power demand amount before the predetermined time from the reference time. In the present embodiment, the calculation formula storage unit 102 is embodied as a storage device 130. FIG. 2 shows how the calculation formula 310 is stored in the storage device 130.

The calculation formula 310 is a regression equation in which the power demand amount at the reference time is used as an objective variable and the actual value of the power demand amount before a predetermined time (for example, 1 hour or 10 minutes before) from the reference time is included as an explanatory variable. ..

The reference time point is the time point for which the power demand is calculated using the calculation formula 310. Therefore, for example, when calculating the power demand amount one hour after the current time (calculation target time point), the actual value of the current power demand amount one hour before the calculation target time point is substituted into the calculation formula 310. Alternatively, when calculating the current power demand amount, the actual value of the power demand amount one hour before the current time (calculation target time point) is substituted into the calculation formula 310.

The calculation formula 310 is expressed as, for example, (Equation 1). G is the amount of power demand at the reference time, A and B are constants, and X1 is the actual value of the amount of power demand before a predetermined time (for example, one hour) from the reference time.

G = A + (B × X1)… (Equation 1)
Further, in the calculation formula 310, as in (Equation 2), in addition to the actual value X1 of the electric power demand amount before a predetermined time (for example, one hour before the reference time) from the reference time point, the calculation formula 310 is further before (for example, 2 from the reference time point). The actual value of the power demand amount (time before) may be included in the explanatory variable. C is a constant, and X2 is the actual value of power demand 2 hours before the reference time.

G = A + (B × X1) + (C × X2)… (Equation 2)
In addition to (Equation 1) and (Equation 2), the calculation formula 310 also includes temperature and amount of solar radiation (for example, total amount of solar radiation on a horizontal plane) as shown in the following (Equation 3) to (Equation 5). Precipitation may be included as an explanatory variable.

G = A + (B × X1) + (C × X2) + (D × X3) + (E × X4) + (F × X5)… (Equation 3)
G = A + (B × X1) + (C × X2) + (D × X3) + (F × X5)… (Equation 4)
G = A + (B × X1) + (C × X2) + (E × X4) + (F × X5)… (Equation 5)
Here, D, E, and F are constants, X3 is the observed or predicted value of solar radiation at the reference time, X4 is the observed or predicted value of precipitation at the reference time, and X5 is the observed or predicted value of temperature at the reference time. It is a predicted value.

Here, the electric power demand G includes fluctuations in the electric power demand due to solar power generation and fluctuations in the electric power demand due to an increase in lighting demand on a rainy day. Therefore, by adding the amount of solar radiation and precipitation to the explanatory variables, it becomes possible to consider the influence of the amount of solar radiation and precipitation on the amount of electricity demand.

Here, both the amount of solar radiation and the amount of precipitation affect the power demand G in the daytime. Therefore, when calculating the amount of power demand during the daytime, the calculation formulas 310 (first calculation formula and third calculation formula) of the above (formula 3) to (formula 5) are used, while the power at night. When calculating the demand amount, it is possible to use the calculation formula 310 (second calculation formula, fourth calculation formula) that does not include the amount of solar radiation and the amount of precipitation in the explanatory variables, as in (Equation 6). .. With such an aspect, it becomes possible to calculate the electric power demand more accurately.

G = A + (B × X1) + (C × X2) + (F × X5)… (Equation 6)
The daytime and the nighttime can be distinguished by the time, and for example, the time zone from 7:00 to 18:00 may be set as the daytime. Further, as shown in FIG. 10, the time zone of daytime or nighttime may be changed in consideration of the season, the month, the latitude, longitude, altitude, and the like of the predicted point of the electric power demand. In this way, by switching between the calculation formula 310 used in the daytime time zone and the calculation formula 310 used in the nighttime time zone, it is possible to calculate the power demand more accurately.

Furthermore, regarding the amount of precipitation, the amount of electricity demand (in this case, the demand for lighting) tends to increase because the number of consumers who turn on the lights becomes dim even in the daytime when it rains, but when the amount of precipitation exceeds a certain level, Further increases in precipitation do not necessarily mean that lighting demand will increase further.

Therefore, the reference precipitation 330, which is the value of precipitation that makes it difficult for the power demand to fluctuate even if the precipitation increases further, is set in advance, and the value of the explanatory variable X4 is the upper limit of the reference precipitation 330. If it is set to a value, it becomes possible to calculate the power demand more accurately.

In this case, the explanatory variable X4 is the smaller value of the precipitation at the reference time point and the reference precipitation 330 (hereinafter, also referred to as the precipitation index). The value of the reference precipitation 330 may be set to, for example, 2 mm.

Regarding the temperature, depending on the season and time zone, the amount of electricity demand tends to increase when the number of people who feel hot or cold increases. There is a temperature range that has little effect on the increase or decrease in electricity demand so that it is sandwiched. By considering such a dead zone, which is a range of temperature in which the power demand is unlikely to fluctuate even if the temperature fluctuates, it becomes possible to calculate the power demand more accurately.

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 first reference temperature and the second reference temperature (hereinafter collectively referred to as the reference temperature 320) may be set manually by the operator, or the power demand prediction device 100 may set the past power demand and temperature. The reference temperature 320 may be calculated based on the data of. The method for calculating the reference temperature 320 by the power demand prediction device 100 will be described later, but the power demand prediction device 100 affects the power demand by setting the first reference temperature and the second reference temperature. It is possible to accurately predict the amount of electricity demand in consideration of the dead zone, which is difficult to come to.

The calculation formula 310 when the dead zone is taken into consideration is represented by, for example, the following (formula 7).

G = A + (B × X1) + (C × X2) + (D × X3) + (E × X4) + (H × X6) + (I × X7)… (Equation 7)
Here, H and I are constants, X6 is the first temperature index, and X7 is the second temperature index. The first temperature index becomes 0 when the temperature at the reference time is equal to or higher than the first reference temperature, and becomes a value corresponding to the difference between the first reference temperature and the temperature when the temperature is lower than the first reference temperature. The second temperature index is 0 when the temperature at the reference time is equal to or lower than the second reference temperature, and becomes a value corresponding to the difference between the second reference temperature and the temperature when the temperature is higher than the second reference temperature.

Specifically, the first temperature index is calculated by "T1-a1" because, for example, when the temperature at the reference time is T1, it is lower than the first reference temperature (a1). When the temperature at the reference time is T2 or T3, it becomes "0" because it is equal to or higher than the first reference temperature (a1). As a result, the power demand can be predicted in consideration of the change in the demand at the temperature lower than the lower limit of the dead zone.

Further, for example, when the temperature at the reference time is T1 or T2, the second temperature index is "0" because it is equal to or less than the second reference temperature (a2), and when the temperature at the reference time is T3, the second temperature index is set. Since it is larger than the second reference temperature (a2), it is a value calculated by "T2-a2". As a result, the power demand can be predicted in consideration of the change in the demand at the temperature higher than the upper limit of the dead zone.

Next, with reference to FIGS. 6 and 7, a method for setting the first reference temperature and the second reference temperature by the power demand prediction device 100 will be described. FIG. 6 is a demand temperature graph showing a process of setting the first reference temperature. FIG. 7 is a demand temperature graph showing the process of setting the second reference temperature.

The first reference temperature and the second reference temperature are the lower limit value and the upper limit value of the dead zone in which the electric power demand is not easily affected by the change in temperature.

The electric power demand forecasting device 100 acquires data of the past air temperature and the electric power demand in order to set the first reference temperature and the second reference temperature.

Then, the electric power demand prediction device 100 sets the central temperature, which is a value near the center of the dead zone that appears when these temperatures and the electric power demand are plotted on the Cartesian coordinate system, and is the second from the central temperature on the minus side of the air temperature. 1 Set the reference temperature, and set the second reference temperature on the plus side of the temperature from the central temperature. The central temperature may be set by the operator, or the power demand prediction device 100 obtains a curve that approximates each point obtained by plotting the relationship between the temperature and the power demand, and the apex of the curve is centered. It may be set as the temperature.

Then, the electric power demand prediction device 100 shows the relationship between the air temperature and the electric power demand by an approximate straight line on each of the low temperature side and the high temperature side of the central temperature, and determines whether or not the approximate straight line has a predetermined inclination. Then, the first reference temperature and the second reference temperature are set. Here, the predetermined slope includes, for example, a negative slope and a positive slope predetermined by the operator, for example, a slope empirically determined by the operator based on past achievements, and artificial intelligence (neural network). Etc.).

More specifically, as shown in FIG. 6, first, the electric power demand forecasting device 100 is arbitrarily set to a predetermined temperature (for example, 20% of the central temperature) rather than the central temperature. The same applies to ""), and a lower temperature (hereinafter referred to as "11th temperature") is set. The power demand prediction device 100 represents the relationship between the air temperature and the power demand at a temperature lower than the eleventh temperature by an approximate straight line (hereinafter, referred to as "11th approximate straight line") (one-point chain line in FIG. 6). ).

The electric power demand prediction device 100 compares a predetermined negative slope (not shown) with the slope of the eleventh approximate straight line (hereinafter referred to as “11th slope”). Next, the electric power demand prediction device 100 sets a temperature (hereinafter, referred to as "12th air temperature") which is lower than the 11th air temperature by a predetermined temperature. The power demand prediction device 100 represents the relationship between the air temperature and the power demand at a temperature lower than the twelfth temperature by an approximate straight line (hereinafter referred to as "the twelfth approximate straight line") (two points in FIG. 6). Chain line).

The electric power demand prediction device 100 compares a predetermined negative slope (not shown) with the slope of the twelfth approximate straight line (hereinafter referred to as “twelfth slope”). By repeating the same procedure, the power demand prediction device 100 represents an approximate straight line (hereinafter referred to as "13th approximate straight line") (three-dot chain line in FIG. 6), its thirteenth inclination, and a predetermined negative. Compare the tilts of.

Then, the power demand prediction device 100 selects the approximate straight line whose inclination of the approximate straight line is closest to the predetermined negative slope from the comparison result between the slope of the approximate straight line and the predetermined negative slope. The electric power demand forecasting device 100 sets the temperature corresponding to the selected approximate straight line as the first reference temperature. For example, when the twelfth approximate straight line is selected, the power demand prediction device 100 sets the twelfth temperature to the first reference temperature. In the above example, three approximate straight lines from the 11th approximate straight line to the 13th approximate straight line are obtained, but the number of the approximate straight lines to be obtained is "the number of plot points" indicating the relationship between the temperature and the power demand. Or "predetermined temperature" shall be changed as appropriate.

Next, as shown in FIG. 7, the electric power demand prediction device 100 sets a temperature (hereinafter, referred to as “21st temperature”) higher than the central temperature by a predetermined temperature. The power demand prediction device 100 represents the relationship between the air temperature and the power demand at a temperature higher than the 21st temperature by an approximate straight line (hereinafter referred to as "21st approximate straight line") (one-point chain line in FIG. 7). ).

The electric power demand prediction device 100 compares a predetermined positive slope (not shown) with the slope of the 21st approximate straight line (hereinafter referred to as “21st slope”). Next, the electric power demand forecasting device 100 sets a temperature (hereinafter, referred to as “22nd temperature”) higher than the 21st temperature by a predetermined temperature. The power demand prediction device 100 represents the relationship between the air temperature and the power demand at a temperature higher than the 22nd temperature by an approximate straight line (hereinafter referred to as "22nd approximate straight line") (two points in FIG. 7). Chain line).

The electric power demand prediction device 100 compares a predetermined positive slope with the slope of the 22nd approximate straight line (hereinafter, referred to as “22nd slope”). By repeating the procedure in the same manner, the power demand prediction device 100 represents an approximate straight line (hereinafter referred to as "the 23rd approximate straight line") (the three-dot chain line in FIG. 7), the 23rd inclination thereof, and a predetermined positive value. Compare the tilts of.

Then, the power demand prediction device 100 selects an approximate straight line whose inclination of the approximate straight line is closest to the predetermined positive inclination from the comparison result between the inclination of the approximate straight line and the predetermined positive inclination, and selects the approximation. The temperature corresponding to the straight line is set as the second reference temperature. For example, when the 22nd approximate straight line is selected, the power demand prediction device 100 sets the 22nd temperature to the second reference temperature. In the above example, it was decided to obtain three approximate straight lines from 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" indicating the relationship between the temperature and the power demand. It shall be changed as appropriate depending on "" and "predetermined temperature".

By the above process, the electric power demand prediction device 100 can set the first reference temperature and the second reference temperature so as to be close to the lower limit value and the upper limit value of the dead zone.

Although some examples of the calculation formula 310 have been described above, various variables other than those described above can be used as the explanatory variables used in the calculation formula 310. For example, the maximum and minimum temperature of the day, the maximum and minimum temperature of the previous day, the PV equipment amount corresponding to the total power generation capacity of the photovoltaic power generation equipment, the humidity, the day, the flag indicating a holiday, the special day, the solar radiation amount and the PV equipment. Information on the product with quantity, the demand one year ago, the demand two years ago, and the weather (cloudy, sunny, snow, etc.) can be used as explanatory variables.

Such a calculation formula 310 is generated based on a plurality of objective variables and each explanatory variable measured at a predetermined time in the past (hereinafter, referred to as "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. 8, 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.

[Reference temperature storage unit]
The reference temperature storage unit 105 sets the reference temperature 320, that is, the first reference temperature representing the lower limit of the dead zone, which is the range of the temperature in which the power demand does not easily fluctuate even if the temperature fluctuates, and the upper limit of the dead zone. The second reference temperature to be represented is stored. In the present embodiment, the reference temperature storage unit 105 is embodied as a storage device 130. FIG. 2 shows how the reference temperature 320 is stored in the storage device 130.

[Reference Precipitation Memory]
The reference precipitation storage unit 106 stores the reference precipitation 330, which is the value of the precipitation so that the power demand is less likely to fluctuate even if the precipitation increases further. In the present embodiment, the reference precipitation storage unit 106 is embodied as a storage device 130. FIG. 2 shows how the reference precipitation 330 is stored in the storage device 130.

[Change amount calculation unit, predicted value calculation unit]
The change amount calculation unit 103 obtains the calculated value of the current power demand amount and the calculated value of the power demand amount at the time of the prediction target by using the actual value of the power demand amount and the calculation formula 310, and each of these is obtained. From the difference between the calculated values, the estimated value of the change in power demand from the current time to the forecast target time is obtained.

For example, to explain with reference to FIG. 5, the change amount calculation unit 103 first uses the calculation formula 310 and the actual value of the power demand amount, and the current power demand amount y _{fore shown in FIG. 5 (3). (t) and the power demand y fore} (t + sτ) at the time of the prediction target (sτ time after the present time) shown in (4) in FIG. 5 are calculated. Then, the change amount calculation unit 103 _{obtains the difference d between y fore} (t) and y _fore (t + sτ) as the change amount of the power demand amount from the present time to the prediction target time point.

The calculation formula 310 used in the example shown in FIG. 5 includes the power demand amount at the reference time as the objective variable and the actual value of the power demand amount sτ time before the reference time as the explanatory variable. Further, this calculation formula 310 can include various explanatory variables such as temperature, solar radiation, and precipitation as described above, and _{when calculating y fore} (t) and y _fore (t + sτ). The change amount calculation unit 103 appropriately uses the data corresponding to these explanatory variables.

For example, when the explanatory variables of the above-mentioned calculation formula 310 include the first temperature index and the second temperature index, the change amount calculation unit 103 determines the actual value of the electric power demand, the first temperature index, and the like. Using the second temperature index and the formula 310, the calculated value y _fore (t) of the current power demand and the calculated value y _fore (t + sτ) of the power demand at the time of the prediction target are obtained, and each From the difference between the calculated values, the amount of change d in the amount of power demand from the present time to the time to be predicted is obtained.

Alternatively, when the explanatory variable of the calculation formula 310 includes the amount of solar radiation, the change amount calculation unit 103 uses the actual value of the electric power demand amount, the amount of solar radiation, and the calculation formula 310 to generate the current electric power. The calculated value y _fore (t) of the demand amount and the calculated value y _fore (t + sτ) of the power demand amount at the time of the forecast target are obtained, and the difference of each calculated value is used to determine the power demand amount from the present time to the forecast target time. Find the amount of change d.

Further, when the calculation formula 310 used in the daytime time zone and the calculation formula 310 used in the nighttime time zone are used properly with respect to the amount of solar radiation, the change amount calculation unit 103 includes the reference time in the daytime time zone. _{In this case, the calculated value y fore} (t) of the current power demand and the power demand at the time of the forecast target are calculated using the actual value of the power demand, the amount of solar radiation, and the calculation formula 310 for the daytime. Find the value y _fore (t + sτ), and if the reference time is included in the night time zone, use the actual value of the power demand and the calculation formula 310 for the night to use the current power demand. The calculated value y _{fore (t) and the calculated value y fore} (t + sτ) of the power demand at the time of the prediction target are obtained.

Further, when the explanatory variable of the above-mentioned calculation formula 310 includes the precipitation index, the change amount calculation unit 103 uses the actual value of the electric power demand, the precipitation index, and the calculation formula 310. Then, the calculated value y _fore (t) of the current power demand and the calculated value y _fore (t + sτ) of the power demand at the time of the prediction target are obtained, and from the difference between the calculated values, from the current time to the prediction target time. The change amount d of the electric power demand amount of is obtained.

As in the case of the amount of solar radiation, when the calculation formula 310 used in the daytime time zone and the calculation formula 310 used in the nighttime time zone are used properly for the precipitation amount, the change amount calculation unit 103 has a reference time point. _{If it is included in the daytime time zone, it is predicted to be the current calculated value of power demand y fore} (t) using the actual value of power demand, the precipitation index, and the calculation formula 310 for daytime. _{Obtain the calculated value y fore} (t + sτ) of the power demand at the target time, and if the reference time is included in the night time zone, the actual value of the power demand and the calculation formula 310 for the night are used. The calculated value y _{fore (t) of the current power demand and the calculated value y fore} (t + sτ) of the power demand at the time of the prediction target are obtained by using.

When the change amount d of the electric power demand amount from the present time to the forecast target time point is calculated in this way, the predicted value calculation unit 104 adds the change amount d to the actual value of the electric power demand amount at the present time. Obtain the forecast value of the power demand at the time of the forecast target.

In the example shown in FIG. 5, the predicted value calculation unit 104 acquires the actual value y (t) of the current power demand shown in FIG. 5 (1) from the power demand actual value management table 300, and this current time. By adding the change amount d of the electric power demand to the actual value y (t) of, the predicted value y ^new _fore (t + sτ) of the electric power demand after sτ time from the present time shown in FIG. 5 (2). ).

According to such an aspect, even when the value of the electric power demand amount calculated by the calculation formula 310 deviates from the actual value, the predicted value of the electric power demand amount can be accurately calculated. Therefore, according to the power demand prediction device 100 according to the present embodiment, it is possible to more accurately predict the power demand in a short time of about several tens of minutes to several hours.

== Processing flow ==
Next, a control method of the electric power demand amount prediction device 100 according to the present embodiment will be described with reference to FIG. FIG. 11 is a flowchart showing the procedure, and these steps are realized by the CPU 110 executing the power demand amount prediction device control program 700 stored in the storage device 130 of the power demand amount prediction device 100.

First, the electric power demand forecasting device 100 obtains the calculated value of the current electric power demand and the calculated value of the electric power demand at the time of the prediction target by using the actual value of the electric power demand and the calculation formula 310 (S1000). ).

Then, the electric power demand forecasting device 100 obtains the amount of change in the electric power demand from the present time to the forecast target time point from the difference between these calculated values (S1010).

Then, the electric power demand forecasting device 100 obtains a predicted value of the electric power demand at the time of the forecast target by adding this change amount to the actual value of the electric power demand at the present time (S1020).

With such an aspect, even when the value of the power demand amount calculated by the calculation formula 310 deviates from the actual value, it becomes possible to accurately calculate the predicted value of the power demand amount, and the number. It is possible to more accurately predict the amount of electricity demand in a short period of time, from ten minutes to several hours.

== Other embodiments ==
As described above, the calculation formula 310 calculates the power demand at the forecast target time using the actual value of the power demand before the forecast target time, and the time from the current time to the forecast target time is this. If it is longer than the predetermined time, the actual value of the power demand before the predetermined time before the forecast target time does not exist yet.

The power demand prediction device 100 according to the present embodiment can calculate the predicted value of the power demand at the time of the prediction target even in such a case.

In this case, the change amount calculation unit 103 first finds the difference between the calculated value of the power demand amount of the first timing at the present time and the calculated value of the power demand amount of the second timing after a predetermined time from the present time. The amount of change in the amount of power demand from the first timing to the second timing is obtained.

Then, the predicted value calculation unit 104 obtains the predicted value of the power demand amount of the second timing by adding this change amount to the actual value of the power demand amount of the first timing.

The change amount calculation unit 103 regards the predicted value of the power demand amount of the second timing as the actual value (A) of the power demand amount, and regards the second timing as the new first timing, and regards the new first timing. A new amount of change in the amount of power demand from the timing to the new second timing after a predetermined time is obtained by using the calculation formula 310.

The predicted value calculation unit 104 adds this new change in the power demand to the actual value of the power demand in the new first timing (A above) to obtain the power demand in the new second timing. Calculate the predicted value.

The change amount calculation unit 103 and the predicted value calculation unit 104 repeat the above processing until the new second timing reaches the initial prediction target time point, so that the predicted value of the power demand amount at the prediction target time point is reached. Is calculated.

Explaining this situation with reference to FIGS. 12 and 13, the change amount calculation unit 103 uses the calculation formula 310 to show the current power demand amount at the first timing shown in FIG. 12 (5) and FIG. The power demand amount at the second timing shown in (6) in 12 is calculated, and the difference d1 between them is first obtained.

Then, the predicted value calculation unit 104 adds this difference d1 to the actual value of the power demand amount of the first timing shown in FIG. 12 (1), so that the power demand of the second timing shown in FIG. Find the predicted value of the quantity.

Then, the change amount calculation unit 103 regards the predicted value of the power demand amount as the actual value, and regards the second timing as the new first timing, and regards the power of the new second timing shown in FIG. 12 (7). The calculated value of the demand amount is obtained, and the calculated value of the new first timing power demand amount shown in FIG. 12 (6) and the calculated value of the new second timing power demand amount shown in FIG. 12 (7). The difference d2 from is obtained.

Then, the predicted value calculation unit 104 adds this difference d2 to the actual value (considered as the actual value) of the new power demand amount at the first timing shown in FIG. 12 (2), thereby (in FIG. 12). Obtain the predicted value of the new power demand at the second timing shown in 3).

The change amount calculation unit 103 and the predicted value calculation unit 104 calculate the predicted value of the power demand amount at the time of the prediction target point shown in FIG. 12 (4) by repeating the same processing thereafter.

By doing so, even if the time from the present time to the prediction target time point is longer than the predetermined time, the power demand amount prediction device 100 can calculate the predicted value of the power demand amount at the prediction target time point.

The flow of the above processing will be described with reference to the flowchart shown in FIG.

First, the power demand forecasting device 100 sets the current time as the first timing (S2000).

Then, the electric power demand predicted value 100 calculates the calculated value of the electric power demand amount of the first timing and the calculated value of the electric power demand amount of the second timing after a predetermined time from the present time (S2010). Next, the power demand prediction device 100 obtains the difference between these calculated values as the amount of change in the power demand from the first timing to the second timing (S2020).

Then, the electric power demand forecasting device 100 obtains the predicted value of the electric power demand amount of the second timing by adding this change amount to the actual value of the electric power demand amount of the first timing (S2030).

Subsequently, the power demand forecasting device 100 determines whether or not the second timing has reached the prediction target time point (S2040), and if so, determines the predicted value of the power demand of the second timing. The process ends as the predicted value of the power demand at the time of the prediction target.

On the other hand, when the second timing has not reached the prediction target time point, the power demand prediction device 100 considers the predicted value of the power demand amount of the second timing as the actual value of the power demand amount (S2050). Considering this second timing as the new first timing (S2060), returning to S2010, the calculation formula is used to calculate the new change in power demand from the new first timing to the new second timing after a predetermined time. Obtained using 310 (S2010, S2020).

The power demand forecasting device 100 calculates the predicted value of the power demand at the forecasting target time by repeating the same processing until the new second timing reaches the initial forecasting target time.

According to such an aspect, even when the time from the present time to the prediction target time point is longer than a predetermined time, the power demand amount prediction device 100 can calculate the predicted value of the power demand amount at the prediction target time point.

Further, in addition to the above-described embodiment, the change amount calculation unit 103 and the predicted value calculation unit 104 can also have the following modes.

When the time from the current time to the forecast target time is longer than the predetermined time, the change amount calculation unit 103 first determines the calculated value of the power demand amount at the first timing at the present time and the power at the second timing after the predetermined time from the current time. Obtain the calculated value of the demand amount. Then, the change amount calculation unit 103 regards the calculated value of the power demand amount of the second timing as the actual value of the power demand amount of the new first timing, and uses the calculation formula 310 to use the new first timing. The calculated value of the new second timing power demand after a predetermined time is obtained from.

In this way, the change amount calculation unit 103 sequentially obtains the calculated value of the new second timing power demand amount that arrives at predetermined time intervals. Then, when the new second timing reaches the prediction target time point, the change amount calculation unit 103 sets the difference between the current power demand calculated value and the latest second timing power demand calculated value at the present time. It is calculated as the amount of change in the amount of power demand from to the time of the forecast target.

Explaining this situation with reference to FIGS. 15 and 16, the change amount calculation unit 103 uses the calculation formula 310 to show the current power demand amount at the first timing shown in FIG. 15 (3) and FIG. The power demand amount of the second timing shown in (4) in 15 is calculated.

Then, the change amount calculation unit 103 regards the calculated value of the power demand amount of the second timing as the actual value of the power demand amount of the new first timing, and uses the calculation formula 310 to use the new first timing. After a predetermined time from the above, the calculated value of the new power demand amount at the second timing shown in FIG. 15 (5) is obtained.

Then, as shown in FIG. 15 (6), the change amount calculation unit 103 calculates the current power demand amount shown in FIG. 15 (3) when the new second timing reaches the prediction target time point. And the difference d from the latest calculated value of the power demand amount of the second timing shown in FIG. 15 (6) is obtained as the change amount d of the power demand amount from the present time to the forecast target time point.

Then, the predicted value calculation unit 104 adds this change amount d to the actual value of the current power demand amount shown in FIG. 15 (1), so that the power demand amount at the time of the prediction target point shown in FIG. Predicted value of.

Even in such an aspect, even if the time from the present time to the prediction target time point is longer than a predetermined time, the power demand amount prediction device 100 can calculate the predicted value of the power demand amount at the prediction target time point. ..

The flow of the above processing will be described with reference to the flowchart shown in FIG.

First, the power demand forecasting device 100 sets the current time as the first timing (S3000).

Then, the electric power demand predicted value 100 is obtained by using the calculation formula 310 to obtain the calculated value of the electric power demand amount of the first timing (S3010), and further, the calculated value of the electric power demand amount of the second timing after a predetermined time from the present time. (S3015).

Subsequently, the power demand forecasting device 100 determines whether or not the second timing has reached the prediction target time point (S3020), and if not, the calculated value of the power demand of the second timing is actually obtained. It is regarded as a value (S3030), the second timing is regarded as a new first timing (S3040), the process returns to S3015, and the calculation formula 310 is used again after a predetermined time from the new first timing. Obtain the calculated value of the new second timing power demand (S3015).

In S3020, when the new second timing reaches the prediction target time point (S3020), the power demand forecasting device 100 uses the calculated value of the current power demand and the latest power demand of the second timing. The difference from the calculated value is calculated as the amount of change in power demand from the current time to the forecast target time (S3050).

Then, the electric power demand forecasting device 100 obtains a predicted value of the electric power demand at the time of the forecast target by adding this change amount to the actual value of the electric power demand at the present time (S3060).

According to such an aspect, even when the time from the present time to the prediction target time point is longer than a predetermined time, the power demand amount prediction device 100 can calculate the predicted value of the power demand amount at the prediction target time point.

The control method and program of the power demand prediction device 100 and the power demand prediction device according to the present embodiment have been described above. According to the program, it is possible to more accurately predict the amount of power demand in a short time of several tens of minutes to several hours.

It should be noted that the above-described 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.

100 Power demand prediction device 101 Actual value storage unit 102 Calculation formula storage unit 103 Change amount calculation unit 104 Predicted value calculation unit 105 Reference temperature storage unit 106 Reference precipitation storage unit 110 CPU
120 Memory 130 Storage device 140 Recording medium reader 150 Communication device 160 Input device 170 Output device 300 Power demand actual value management table 310 Calculation formula 320 Standard temperature 330 Standard precipitation 700 Power demand forecaster Control program 800 Recording medium

Claims (10)

It is a power demand forecasting device that obtains a predicted value of power demand.
An actual value storage unit that stores the actual value of power demand,
A calculation formula storage unit that stores a calculation formula for calculating the power demand at the reference time using the actual value of the power demand before a predetermined time from the reference time.
Using the actual value of the power demand amount and the calculation formula, the power demand amount at the present time and the forecast target time point is calculated respectively, and the change amount of the power demand amount from the present time to the forecast target time point from the difference between the calculated values. Change amount calculation unit to find
A forecast value calculation unit that obtains a forecast value of the power demand at the time of the forecast target by adding the change amount to the actual value of the power demand at the present time.
A power demand forecasting device equipped with. The power demand forecasting device according to claim 1.
When the time from the current time to the prediction target time is longer than the predetermined time, the change amount calculation unit determines the calculated value of the power demand amount at the first timing at the present time and the second timing after the predetermined time from the present time. From the difference between the calculated value of the power demand amount and the calculated value, the change amount of the power demand amount from the first timing to the second timing is obtained.
The predicted value calculation unit obtains a predicted value of the power demand amount of the second timing by adding the change amount to the actual value of the power demand amount of the first timing.
Each time the predicted value of the power demand amount of the second timing is calculated, the change amount calculation unit regards the predicted value as the actual value of the power demand amount, and sets the second timing as the new first timing. Assuming that, a new amount of change in the amount of power demand from the new first timing to the new second timing is obtained.
The predicted value calculation unit adds the new change amount of the power demand amount to the actual value of the power demand amount of the new first timing until the new second timing reaches the prediction target time point. , A power demand forecasting device that calculates a predicted value of the power demand of the new second timing. The power demand forecasting device according to claim 1.
When the time from the current time to the prediction target time is longer than the predetermined time, the change amount calculation unit determines the calculated value of the power demand amount at the first timing at the present time and the second timing after the predetermined time from the present time. The calculated value of the electric power demand amount is obtained, and the calculated value of the electric power demand amount of the second timing is regarded as an actual value, and the second timing is regarded as a new first timing, and the new second timing is used. Sequentially obtains a new calculated value of the power demand amount at the second timing until the power demand reaches the forecast target time point, and calculates the difference between the current power demand amount calculation value and the power demand amount calculation value at the forecast target time point. , A power demand forecasting device that obtains the amount of change in power demand from the current time to the forecast target time. The power demand forecasting device according to any one of claims 1 to 3.
A reference temperature that stores a first reference temperature that represents the lower limit of the dead zone, which is a range of temperatures in which the power demand does not easily fluctuate even if the temperature fluctuates, and a second reference temperature that represents the upper limit of the dead zone. Memory and
With further preparation
The calculation formula is 0 when the temperature at the reference time is equal to or higher than the first reference temperature and is lower than the first reference temperature, in addition to the actual value of the electric power demand amount before the predetermined time from the reference time. Is the first temperature index, which is a value corresponding to the difference between the first reference temperature and the air temperature, and 0 when the temperature at the reference time is equal to or less than the second reference temperature, and is larger than the second reference temperature. Is to calculate the amount of electric power demand at the time of the reference by using the second temperature index, which is a value corresponding to the difference between the second reference temperature and the air temperature.
The change amount calculation unit uses the actual value of the electric power demand amount, the first temperature index, the second temperature index, and the calculation formula to calculate the current electric power demand amount and the time to be predicted. A power demand prediction device that obtains the calculated value of the power demand amount of the above and obtains the change amount of the power demand amount from the present time to the prediction target time point from the difference between the calculated values. The power demand forecasting device according to any one of claims 1 to 3.
The calculation formula calculates the power demand amount at the reference time by using the solar radiation amount at the reference time in addition to the actual value of the power demand amount before the predetermined time from the reference time.
The change amount calculation unit uses the actual value of the electric power demand amount, the solar radiation amount, and the calculation formula to obtain the calculated value of the current electric power demand amount and the calculated value of the electric power demand amount at the time of the prediction target. A power demand prediction device that obtains and obtains the amount of change in power demand from the current time to the time to be predicted from the difference between the calculated values. The power demand forecasting device according to claim 5.
The calculation formula includes a first calculation formula for calculating the power demand amount at the reference time using the actual value of the power demand amount before the predetermined time from the reference time point and the solar radiation amount at the reference time point. Includes a second calculation formula for calculating the power demand at the reference time using the actual value of the power demand before the predetermined time from the reference time.
When the reference time is included in the daytime time zone, the change amount calculation unit uses the actual value of the power demand amount, the solar radiation amount, and the first calculation formula to generate the current power demand. The calculated value of the amount and the calculated value of the electric power demand at the time to be predicted are obtained, and when the reference time is included in the night time zone, the actual value of the electric power demand and the second calculation formula are used. A power demand forecasting device that obtains the calculated value of the current power demand and the calculated value of the power demand at the time of the prediction target. The power demand forecasting device according to any one of claims 1 to 3.
A reference precipitation storage unit that stores the reference precipitation, which is the value of the precipitation so that the power demand is less likely to fluctuate even if the precipitation increases further.
With further preparation
In the calculation formula, in addition to the actual value of the electric power demand amount before the predetermined time from the reference time point, the precipitation index which is the smaller value of the precipitation amount at the reference time point and the reference precipitation amount is used. It calculates the amount of power demand at the reference time point.
The change amount calculation unit uses the actual value of the electric power demand, the precipitation index, and the calculation formula to obtain the calculated value of the current electric power demand and the calculated value of the electric power demand at the time of the prediction target. Is obtained, and the amount of change in the amount of power demand from the present time to the time to be predicted is obtained from the difference between the calculated values. The power demand forecasting device according to claim 7.
The calculation formula is a third calculation formula for calculating the power demand amount at the reference time using the actual value of the power demand amount before the predetermined time from the reference time point and the precipitation index at the reference time point. And a fourth calculation formula for calculating the power demand amount at the reference time using the actual value of the power demand amount before the predetermined time from the reference time point.
When the reference time is included in the daytime time zone, the change amount calculation unit uses the actual value of the power demand, the precipitation index, and the third calculation formula to generate the current power. The calculated value of the demand amount and the calculated value of the power demand amount at the time to be predicted are obtained, and when the reference time point is included in the night time zone, the actual value of the power demand amount and the fourth calculation formula are used. A power demand forecasting device that obtains the calculated value of the current power demand and the calculated value of the power demand at the time of the prediction target using. It is a control method of the power demand forecasting device that obtains the predicted value of the power demand.
The power demand forecasting device
Using the actual value of the electric power demand amount before a predetermined time from the reference time point, the calculation formula for calculating the electric power demand amount at the reference time point is stored.
Using the actual value of the power demand amount and the calculation formula, the power demand amount at the present time and the forecast target time point is calculated respectively, and the change amount of the power demand amount from the present time to the forecast target time point from the difference between the calculated values. Seeking,
By adding the change amount to the actual value of the current power demand amount, the predicted value of the power demand amount at the time of the prediction target is obtained.
A control method for the power demand forecaster. For computers that obtain predicted values of power demand,
A function to store a calculation formula for calculating the power demand at the reference time using the actual value of the power demand before a predetermined time from the reference time.
Using the actual value of the power demand amount and the calculation formula, the power demand amount at the present time and the forecast target time point is calculated respectively, and the change amount of the power demand amount from the present time to the forecast target time point from the difference between the calculated values. And the function to ask for
A function to obtain the predicted value of the power demand at the time of the forecast target by adding the change amount to the actual value of the current power demand.
A program to realize.

Images