JP7835198B2 - Adjustment force setting device, adjustment force setting method, and adjustment force setting program - Google Patents

Description

This disclosure relates to an adjustment force setting device, an adjustment force setting method, and an adjustment force setting program.

Patent Document 1 discloses an internal combustion power generation device, a renewable energy power generation device, a power storage device, and a power supply and demand control device that controls the supply and demand of power in a grid to which a load is connected.

Patent Document 2 discloses a supply-demand balance control device for formulating a supply plan for a predetermined period.

Japanese Patent Publication No. 2016-093049 Japanese Patent Publication No. 2012-060789

Retail electricity providers or registered specified transmission and distribution operators must comply with the planned simultaneous supply and demand system to avoid disrupting the regional power supply and demand. Under the planned simultaneous supply and demand system, they are required to submit an equipment operation plan for their service area to the OCCTO, or to the representative contractor if they are part of a balancing group. "OCCTO" is an abbreviation for Organization for Cross-regional Coordination of Transmission Operators. The equipment operation plan is created by (i) forecasting electricity demand and solar power generation, and (ii) creating an equipment operation plan that can cover the power shortfall in (i) while minimizing costs.

In equipment operation planning, it is necessary to ensure adjustment capacity that can absorb the prediction errors that occur in (i).

The purpose of this disclosure is to define the necessary adjustment capacity for absorbing forecast errors during the planning period.

The adjustment force setting device relating to this disclosure is
The control unit includes a first forecasting model used to forecast electricity demand over multiple time periods, which obtains the standard deviation of the forecasted electricity demand for each time period as the first standard deviation; a second forecasting model used to forecast the amount of electricity generated over multiple time periods, which obtains the standard deviation of the forecasted amount of electricity generated for each time period as the second standard deviation; a control unit that sets the adjustment capacity using the first and second standard deviations for time periods in which electricity is generated, and a control unit that sets the adjustment capacity using the first standard deviation for time periods in which electricity is not generated, and outputs the set value of the adjustment capacity for each time period.

The method for setting the adjustment power related to this disclosure is as follows:
For the first forecasting model used to predict electricity demand across multiple time periods, the control unit acquires the standard deviation of the predicted electricity demand values for each time period as the first standard deviation.
Regarding the second prediction model used to predict the amount of power generation in the aforementioned multiple time periods, the control unit acquires the standard deviation of the predicted power generation values for each time period as the second standard deviation.
Of the aforementioned multiple time periods, for the time periods during which power generation occurs, the control unit sets the adjustment force using the first standard deviation and the second standard deviation.
Of the aforementioned multiple time periods, for the time periods when no power is generated, the control unit sets the adjustment force using the first standard deviation.
This includes outputting setting values for adjustment force for each time period using the control unit.

The adjustment force setting program related to this disclosure is
For the first forecasting model used to predict electricity demand across multiple time zones, the standard deviation of the predicted electricity demand values for each time zone is obtained as the first standard deviation,
Regarding the second prediction model used to predict power generation amounts for the aforementioned multiple time periods, the standard deviation of the predicted power generation amounts for each time period is obtained as the second standard deviation,
Among the aforementioned multiple time periods, the adjustment capacity is set using the first standard deviation and the second standard deviation for the time period during which power generation occurs.
Among the aforementioned multiple time periods, the adjustment capacity is set using the first standard deviation for the time periods when no power is generated,
The computer is instructed to perform an operation that includes outputting the set values for adjustment power for each time period.

According to this disclosure, it is possible to set the necessary adjustment force for absorbing prediction errors during the planning period.

This is a block diagram showing the configuration of an adjustment force setting device according to an embodiment of the present disclosure. This graph shows an example of the adjustment capacity required to absorb prediction errors during the planning period. This is a flowchart showing the operation of the adjustment force setting device according to the embodiment of this disclosure.

An embodiment of this disclosure will be described below with reference to the figures.

In each figure, identical or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of identical or corresponding parts will be omitted or simplified as appropriate.

The outline of this embodiment will be described with reference to Figures 1 and 2.

The adjustment power setting device 10 is a general-purpose computer such as a PC, a server computer such as a cloud server, or a dedicated computer used or operated by an electricity business operator such as a retail electricity business operator or a registered specified transmission and distribution business operator. "PC" is an abbreviation for personal computer.

The adjustment power setting device 10 acquires the standard deviation of the predicted electricity demand values for each time period as the first standard deviation for the first prediction model used to predict electricity demand in multiple time periods P. The adjustment power setting device 10 also acquires the standard deviation of the predicted power generation values for each time period as the second standard deviation for the second prediction model used to predict power generation in multiple time periods P. The multiple time periods P correspond to the planning period. The length of the planning period is, for example, 24 hours or 72 hours. Each time period Ti included in the multiple time periods P corresponds to each segment of the planning period. The length of one segment is, for example, 30 minutes.

The adjustment capacity setting device 10 sets the adjustment capacity Ax using the first and second standard deviations for the time period Tx in which power generation occurs, among the multiple time periods P. "Adjustment capacity" refers to the capacity of power generation facilities (including pumped-storage hydroelectric facilities), power storage devices, DRs, and other systems that control power supply and demand, and other similar equipment (excluding distribution facilities), necessary for frequency control, supply and demand balance adjustment, and other grid stabilization operations in the supply area. "DR" is an abbreviation for demand response. The adjustment capacity setting device 10 sets the adjustment capacity Ay using the first standard deviation for the time period Ty in which power generation does not occur, among the multiple time periods P. The adjustment capacity setting device 10 outputs the set value of the adjustment capacity Ai for each time period. The set value of the adjustment capacity Ai for each time period includes the set value of adjustment capacity Ax for the time period Tx in which power generation occurs, and includes the set value of adjustment capacity Ay for the time period Ty in which power generation does not occur.

According to this embodiment, the necessary adjustment force 20 for absorbing forecast errors during the planning period can be set, as shown in Figure 2. The necessary adjustment force 20 for absorbing forecast errors during the planning period includes the necessary adjustment force 21 for absorbing demand forecast errors and the necessary adjustment force 22 for absorbing power generation forecast errors. The unit is kW.

In this embodiment, the second prediction model is a statistical model used to predict the amount of electricity generated by solar panels. Specifically, the second prediction model is used to predict the amount of solar power generated in multiple time periods P. Therefore, the sunshine period corresponds to the time period Tx where power is generated, and the non-sunshine period corresponds to the time period Ty where power is not generated. That is, the adjustment force setting device 10 sets the adjustment force Ax for the sunshine period among the multiple time periods P using the first and second standard deviations, and sets the adjustment force Ay for the non-sunshine period among the multiple time periods P using the first standard deviation.

In the example shown in Figure 2, the planning period is 24 hours, from 0:00 to 24:00. Therefore, each time frame within the time range R1 (from sunrise to sunset) corresponds to the time period Tx when power generation occurs, while each time frame within the time range R2 (from 0:00 to sunrise and from sunset to 24:00) corresponds to the time period Ty when no power generation occurs. The adjustment force setting device 10 assumes a power generation prediction error of 0 for the time range R2 where no power generation occurs, and calculates the adjustment force using the standard deviation calculated from the prediction by the statistical model.

As a variation of this embodiment, the second prediction model may be a statistical model used to predict the amount of power generated by other types of power generation equipment, similar to solar panels, where the presence or absence of power generation depends on the time of day.

Referring to Figure 1, the configuration of the adjustment force setting device 10 according to this embodiment will be described.

The adjustment force setting device 10 comprises a control unit 11, a storage unit 12, a communication unit 13, an input unit 14, and an output unit 15.

The control unit 11 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for specific processing. "CPU" is an abbreviation for central processing unit. "GPU" is an abbreviation for graphics processing unit. The programmable circuit is, for example, an FPGA. "FPGA" is an abbreviation for field-programmable gate array. The dedicated circuit is, for example, an ASIC. "ASIC" is an abbreviation for application specific integrated circuit. The control unit 11 controls each part of the adjustment force setting device 10 and executes processing related to the operation of the adjustment force setting device 10.

The storage unit 12 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, RAM, ROM, or flash memory. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read-only memory. RAM is, for example, SRAM or DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. ROM is, for example, EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read-only memory. Flash memory is, for example, SSD. "SSD" is an abbreviation for solid-state drive. Magnetic memory is, for example, HDD. "HDD" is an abbreviation for hard disk drive. The storage unit 12 functions, for example, as main memory, auxiliary memory, or cache memory. The memory unit 12 stores information used for the operation of the adjustment force setting device 10, and information obtained through the operation of the adjustment force setting device 10.

The communication unit 13 includes at least one communication module. The communication module is, for example, a module compatible with a wired LAN communication standard such as Ethernet®, or a wireless LAN communication standard such as IEEE 802.11. "LAN" is an abbreviation for local area network. "IEEE" is an abbreviation for Institute of Electrical and Electronics Engineers. The communication unit 13 receives information used in the operation of the adjustment force setting device 10 and transmits information obtained through the operation of the adjustment force setting device 10.

The input unit 14 is, for example, a physical key, a capacitive key, a pointing device, a touchscreen integrated with a display, a camera, or a microphone. The input unit 14 accepts operations to input information used for the operation of the adjustment force setting device 10. Instead of being integrated into the adjustment force setting device 10, the input unit 14 may be connected to the adjustment force setting device 10 as an external input device. As a connection interface, an interface compatible with standards such as USB, HDMI®, or Bluetooth® can be used. "USB" is an abbreviation for Universal Serial Bus. "HDMI®" is an abbreviation for High-Definition Multimedia Interface.

The output unit 15 is, for example, a display, speaker, or printer. The display is, for example, an LCD or an organic EL display. "LCD" is an abbreviation for liquid crystal display. "EL" is an abbreviation for electroluminescent. The output unit 15 outputs information obtained by the operation of the adjustment force setting device 10. Instead of being provided in the adjustment force setting device 10, the output unit 15 may be connected to the adjustment force setting device 10 as an external output device. As a connection interface, an interface compatible with standards such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used.

The function of the adjustment force setting device 10 is realized by executing the adjustment force setting program according to this embodiment on the processor acting as the control unit 11. In other words, the function of the adjustment force setting device 10 is realized by software. The adjustment force setting program causes the computer to perform the operations of the adjustment force setting device 10, thereby causing the computer to function as the adjustment force setting device 10. That is, the computer functions as the adjustment force setting device 10 by performing the operations of the adjustment force setting device 10 according to the adjustment force setting program.

The program can be stored on a non-temporary computer-readable medium. Examples of non-temporary computer-readable mediums include flash memory, magnetic recording devices, optical discs, magneto-optical recording media, or ROM. The program can be distributed, for example, by selling, transferring, or lending portable media such as SD cards, DVDs, or CD-ROMs containing the program. "SD" is an abbreviation for Secure Digital. "DVD" is an abbreviation for digital versatile disc. "CD-ROM" is an abbreviation for compact disc read-only memory. The program may also be distributed by storing it in server storage and transferring it from the server to other computers. The program may also be provided as a program product.

A computer, for example, stores programs stored on portable media or transferred from a server in its main memory. Then, the computer reads the program stored in main memory using its processor and executes the processing according to the program. Alternatively, the computer may directly read the program from the portable media and execute the processing according to the program. The computer may also execute the processing according to the program received sequentially each time a program is transferred from a server. Furthermore, processing may be performed using a so-called ASP-type service, which does not transfer programs from the server to the computer, but only provides execution instructions and retrieves results. "ASP" is an abbreviation for application service provider. A program includes information used for processing by an electronic computer that is equivalent to a program. For example, data that is not a direct instruction to the computer but has the nature of defining the computer's processing falls under the category of "equivalent to a program."

Some or all of the functions of the adjustment force setting device 10 may be implemented by a programmable circuit or dedicated circuit as the control unit 11. In other words, some or all of the functions of the adjustment force setting device 10 may be implemented by hardware.

Referring to Figure 3, the operation of the adjustment force setting device 10 according to this embodiment will be explained. The operation shown in Figure 3 corresponds to the adjustment force setting method according to this embodiment.

The processes from Step S1 to Step S5 are executed for each time slot within the planning period, i.e., for each time slot Ti included in the multiple time slots P.

In step S1, the control unit 11 acquires the standard deviation of the predicted power demand value for time period Ti as the first standard deviation for the first prediction model. For example, the control unit 11 receives information regarding the first standard deviation from the administrator's terminal device or an external server device via the communication unit 13. Alternatively, the control unit 11 may directly receive information regarding the first standard deviation from the administrator via the input unit 14.

The first prediction model is a machine learning model that takes operator input values, calendar data, weather forecast data, measured data, pedestrian flow data, or any combination thereof as input and outputs a predicted value of electricity demand. Calendar data includes days of the week, working day flags to consider holidays, or any combination thereof. Weather forecast data includes temperature forecasts to predict air conditioning demand, humidity forecasts to consider whether it is sunny or rainy, solar radiation forecasts to predict air conditioning demand, or any combination thereof. Measured data includes actual demand, actual temperature to predict air conditioning demand, actual humidity to consider whether it is sunny or rainy, actual solar radiation to predict air conditioning demand, or any combination thereof. Pedestrian flow data includes predictions of urban population distribution, predictions of individual behavior, or any combination thereof. Wind speed, wind direction, or any combination thereof may be further input to consider perceived temperature or to predict air conditioning demand. Dates may be further input to consider pedestrian flow or logistics events. For example, the first forecasting model may be constructed to predict changes in demand due to increased tourism during long holidays, increased logistics during Christmas, or changes in factory operating modes depending on the season.

In step S2, the control unit 11 determines whether power generation occurs during time zone Ti. In the example shown in Figure 2, the control unit 11 determines whether the time frame corresponding to time zone Ti falls within time range R1 or time range R2.

If the time frame corresponding to time zone Ti is included in time range R1, i.e., if there is power generation during time zone Ti, the process in step S3 is executed. If the time frame corresponding to time zone Ti is included in time range R2, i.e., if there is no power generation during time zone Ti, the process in step S5 is executed.

In step S3, the control unit 11 obtains the standard deviation of the predicted power generation value for time period Ti as the second standard deviation for the second prediction model. For example, the control unit 11 receives information regarding the second standard deviation from the administrator's terminal device or an external server device via the communication unit 13. Alternatively, the control unit 11 may directly receive information regarding the second standard deviation from the administrator via the input unit 14. After step S3, the processing in step S4 is executed.

The second prediction model is a machine learning model that takes operator input values, weather forecast data, measured data, or any combination thereof as input and outputs a predicted value of PV power generation. "PV" is an abbreviation for photovoltaic. Weather forecast data includes predictions of solar radiation to consider reduction rates due to clouds or atmosphere, predictions of aerosol amounts to consider solar transmittance, predictions of cloud cover to consider solar shading rates, or any combination thereof. Measured data includes actual cloud cover to improve the accuracy of cloud cover predictions, actual PV power generation to improve the accuracy of aerosol or cloud cover predictions, panel conversion efficiency, days elapsed since installation to consider efficiency degradation due to aging, panel surface temperature to consider efficiency degradation due to surface temperature, power conditioner conversion efficiency, or any combination thereof. Geometric solar radiation to consider celestial positional relationships or PV panel installation angles, reduction rates due to building shadows, reduction rates due to panel installation orientation and angle, or any combination thereof may be further input.

In step S4, the control unit 11 sets the adjustment force Ai for time zone Ti using the first standard deviation obtained in step S1 and the second standard deviation obtained in step S3. For example, when σdemand is the first standard deviation, σPV is the second standard deviation, and α and β are coefficients, the control unit 11 calculates the required adjustment force as α × σdemand + β × σPV. The units of σdemand and σPV are kW. α and β are adjusted as appropriate.

In step S5, the control unit 11 sets the adjustment force Ai for time zone Ti using only the first standard deviation obtained in step S1. For example, the control unit 11 calculates the required adjustment force as α × σdemand. σdemand, α, and β are the same as in step S4. σPV can also be considered as 0.

When steps S1 to S5 are executed for multiple time zones P, in step S6, the control unit 11 outputs the set values of the adjustment force Ai for each time zone. For example, the control unit 11 transmits the set values of the adjustment force Ai for each time zone to the administrator's terminal device or an external server device via the communication unit 13. Alternatively, the control unit 11 may directly output the set values of the adjustment force Ai for each time zone to the administrator via the output unit 15. After step S6, the operation shown in Figure 3 is completed.

In this embodiment, during periods when no PV power generation occurs, the predicted PV power generation value is 0, thus the prediction error for PV power generation is set to 0. Furthermore, since prediction is performed using a statistical model, the standard deviation can be calculated. Therefore, by considering reducing the adjustment force in confident intervals, the necessary adjustment force 20 for absorbing prediction errors during the planning period can be calculated as precisely as possible.

This disclosure is not limited to the embodiments described above. For example, two or more blocks shown in the block diagram may be combined, or one block may be divided. Instead of executing two or more steps shown in the flowchart in chronological order as described, they may be executed in parallel or in a different order, depending on the processing capacity of the device performing each step, or as necessary. Other modifications are possible without departing from the spirit of this disclosure.

10 Adjustment force setting device 11 Control unit 12 Storage unit 13 Communication unit 14 Input unit 15 Output unit 20, 21, 22 Required adjustment force

Claims (3)

The first prediction model is a machine learning model that takes data for predicting air conditioning demand as input and outputs predicted values of electricity demand for multiple time periods. The standard deviation of the prediction error for electricity demand by time period is obtained as the first standard deviation σdemand .
The second prediction model, which is a machine learning model that takes data for predicting at least solar radiation, aerosol amount, or cloud cover as input and outputs predicted values of solar power generation for the aforementioned multiple time periods, has its standard deviation, which indicates the variability of the prediction error of solar power generation for each time period, obtained as the second standard deviation σPV .
With α and β as non-zero coefficients, for each time period included in the time range from sunrise to sunset among the multiple time periods, α × σdemand + β × σPV is calculated as the set value for the adjustment force.
For each of the aforementioned time periods, within the time ranges from 0:00 to sunrise and from sunset to 24:00 , α × σdemand is calculated as the set value for the adjustment force.
An adjustment force setting device equipped with a control unit that outputs set values for adjustment force for different time periods. The control unit acquires the standard deviation, which represents the variability of the prediction error of electricity demand by time of day, as the first standard deviation σdemand, from the first prediction model, which is a machine learning model that takes data for predicting air conditioning demand as input and outputs predicted values of electricity demand for multiple time periods.
The control unit acquires the second standard deviation σPV, which represents the variability of the prediction error of solar power generation for each time period, from the second prediction model, which is a machine learning model that takes data for predicting at least solar radiation, aerosol amount, or cloud cover as input and outputs predicted values of solar power generation for the multiple time periods,
With α and β as non-zero coefficients, the control unit calculates α × σdemand + β × σPV as the set value for the adjustment force for each time period included in the time range from sunrise to sunset among the multiple time periods,
Of the aforementioned multiple time periods, for each time period included in the time range from 0:00 to sunrise and from sunset to 24:00 , the control unit calculates α × σdemand as the set value for the adjustment force.
A method for setting adjustment force, which includes outputting setting values for adjustment force for different time periods using the control unit. The first prediction model is a machine learning model that takes data for predicting air conditioning demand as input and outputs predicted values of electricity demand for multiple time periods. The first standard deviation, σdemand , represents the standard deviation showing the variability of the prediction error of electricity demand for each time period.
The second prediction model is a machine learning model that takes data for predicting at least solar radiation, aerosol amount, or cloud cover as input and outputs predicted values of solar power generation for the aforementioned multiple time periods. The standard deviation of the second prediction model, which shows the variability of the prediction error of solar power generation for each time period, is obtained as the second standard deviation σPV .
With α and β as non-zero coefficients, for each time period included in the time range from sunrise to sunset among the aforementioned multiple time periods, α × σdemand + β × σPV is calculated as the set value for the adjustment force,
Of the aforementioned multiple time periods, for each time period included in the time range from 0:00 to sunrise and from sunset to 24:00 , α × σdemand is calculated as the set value for the adjustment force.
A control force setting program that causes a computer to perform actions including outputting the set values for the control force for different time periods.