JP6794141B2 - Information processing equipment, information processing systems, and information processing programs - Google Patents

Description

Embodiments of the present invention relate to information processing devices, information processing systems, and information processing programs.

In recent years, the introduction of storage batteries has made it possible to cut the peak of received power. Peak cut means that the peak power consumption can be reduced by charging the storage battery during the time when the power consumption is low and discharging the storage battery during the time when the power usage peaks. .. In addition, since the storage battery is charged during the time of the low midnight electricity charge and discharged in the daytime when the electricity charge is high, the total electricity charge can be reduced.

In the storage battery control, the power demand is predicted every day, the peak cut line is calculated based on the result, and the charge / discharge control of the storage battery is performed. However, if the power demand forecast is incorrect, appropriate charge / discharge control cannot be performed.

For example, when the predicted value of the electric power demand is predicted to be lower than the actual value, the electric power is not sufficiently discharged even though there is a residual electric power at the peak of the electric power, and the electric power received becomes large. On the contrary,
If it is predicted to be higher than the actual value, the storage battery will be discharged ahead of schedule, and the required peak cut will not be possible.

In order to avoid the above problems, the power demand forecast is corrected to reflect the actual value of the day. However, when the actual value to be reflected in the correction is used for all time zones up to the current time of the day, it is not possible to follow sudden fluctuations in power demand. In addition, when using only the data of the latest actual value of the day, the predicted value is updated more frequently than necessary even for a slight fluctuation in power demand, so the correction amount becomes excessive or too small, and the charge / discharge plan There is a problem that cannot be followed.

Japanese Unexamined Patent Publication No. 2016-19450

An object to be solved by the embodiment of the present invention is to provide an information processing apparatus capable of appropriately correcting the electric power demand forecast in order to improve the problem of the conventional electric power demand forecasting method.

In order to solve the above problems, the information processing apparatus of the embodiment includes a prediction unit, a determination unit, a calculation unit, and a correction unit. The forecasting unit predicts the power demand forecast value, which is the future power demand value. The determination unit determines whether or not the time when the correction of the power demand forecast value is to be determined is in the preset deviation monitoring time zone , and if the time is not in the deviation monitoring time zone , the determination unit determines. When it is decided not to correct the power demand forecast value and the time is in the deviation monitoring time zone, the deviation between the actual power demand value , which is the actual actual power demand value, and the power demand forecast value. Based on the above, it is determined whether or not to correct the power demand forecast value. The calculation unit calculates the correction amount of the power demand forecast value when it is determined by the determination unit to make corrections. The correction unit corrects the power demand forecast value based on the correction amount.

It is a block diagram of the information processing apparatus which concerns on embodiment of this invention. It is a flowchart which shows the operation of the information processing apparatus which concerns on embodiment of this invention. It is a flowchart which shows the method of correcting the electric power demand forecast of the information processing apparatus which concerns on embodiment of this invention. It is a graph which shows an example of the method of correcting the electric power demand forecast of the information processing apparatus which concerns on embodiment of this invention. It is a graph which shows the example which is different by the season, etc. in the method of correcting the electric power demand forecast of the information processing apparatus which concerns on embodiment of this invention. It is a graph which shows the example of the method of correcting the electric power demand forecast of the information processing apparatus which concerns on embodiment of this invention, and how to take the correction determination retroactive period. It is a graph which shows the example of the method of correcting the electric power demand forecast of the information processing apparatus which concerns on embodiment of this invention, and how to calculate the correction amount. It is a graph which shows the example which corrects the electric power demand forecast of the terminal time of the correction target time zone by the method of correcting the electric power demand forecast of the information processing apparatus which concerns on embodiment of this invention.

Hereinafter, embodiments for carrying out the invention will be described with reference to the drawings.

(Embodiment)
(Constitution)
FIG. 1 shows an information processing device according to an embodiment. The information processing device 1 includes an acquisition unit 11, a storage unit 12, an output unit 13, a prediction unit 14, a determination unit 15, a calculation unit 16, a correction unit 17, and a creation unit 18.

The acquisition unit 11 acquires information that affects the amount of power demand. The storage unit 12 stores the pattern of the time change of the past electric power demand and the past data which is the weather information of the past day.

The prediction unit 14 provides weather information on the day when the power demand forecast acquired by the acquisition unit 11 is performed, and the storage unit 1
Predict the time change of future power demand based on the past data stored in 2.

The determination unit 15 determines whether or not to correct the power demand forecast, which is a time change of the predicted future power demand, based on the actual value of the day.

Specifically, it is determined whether the time for determining the correction of the power demand forecast is the deviation monitoring time zone, which is a time zone suitable for correcting the power demand forecast. In addition, it is determined whether the error rate of the actual power demand with respect to the power demand forecast is larger than the preset error rate threshold value. The error rate here is the ratio of the difference between the total values (integral values) of the power demand forecast and the power demand actual results.

However, when deciding whether or not to correct the power demand forecast, it is judged by the divergence between the power demand forecast and the actual power demand, so even if the judgment standard is not the error rate [%], the divergent electric energy [kWh].
] May be. The calculation unit 16 calculates the error rate of the actual power demand value with respect to the predicted power demand value in the predetermined correction determination retroactive period. When correcting the power demand forecast, the correction amount is calculated. The correction amount is an amount for correcting the power demand forecast in a predetermined time zone. The correction unit 17 corrects the power demand forecast based on the correction amount calculated by the calculation unit 16.

The creation unit 18 creates a charge / discharge plan based on the time change of the electric power demand predicted by the prediction unit 14. The charge / discharge plan is a time and amount of charging or discharging of the storage battery planned in advance.

The output unit 13 outputs the power demand forecast predicted by the prediction unit 14, the power demand forecast corrected by the correction unit 17, the charge / discharge plan created or corrected by the preparation unit 18, and the like.

(Action)
FIG. 2 shows a sequence diagram relating to the operation of the information processing apparatus 1 according to the embodiment. First, the prediction unit 14 of the information processing device 1 predicts the time change of the electric power demand on the current day or the next day (S1).
1). At that time, the weather information of the day when the power demand forecast is performed and the storage unit 1 acquired by the acquisition unit 11
Predict based on the past data stored in 2.

Next, the creation unit 18 creates a charge / discharge plan based on the time change of the power demand amount predicted by the prediction unit 14 (S12). The charge / discharge plan is a plan in which the time and amount of charging or discharging the storage battery are set in advance.

Then, the determination unit 15 determines whether or not to correct the power demand forecast, which is a time change of the predicted future power demand, based on the actual value of the day (S13). The detailed steps for determining the determination will be described with reference to the flowchart of FIG.

When the power demand forecast is not corrected (NO in S13), the storage battery is charged / discharged according to the charge / discharge plan created in S12.

On the other hand, when correcting the power demand forecast (YES in S13), the correction unit 17 corrects the power demand forecast (S14). A detailed method of correction will be described with reference to the flowchart of FIG. Then, the creation unit 18 corrects the charge / discharge plan of the storage battery based on the corrected power demand forecast (
S15).

After that, the output unit 13 outputs the power demand forecast corrected by the correction unit 17 or the charge / discharge plan created by the creation unit 18 (S16). The output power demand forecast may be the power demand forecast predicted by the prediction unit 14. The output method may be displayed on a display unit (not shown), or may be output to a control unit (not shown) for control.

FIG. 3 shows a flowchart of a step of determining whether or not to correct the power demand forecast and a method of correcting the power demand forecast.

First, the determination unit 15 determines whether the time for determining the correction of the power demand forecast is the deviation monitoring time zone (S21). The divergence monitoring time zone is a preset time zone for monitoring the divergence between the power demand forecast and the actual power demand. In other words, during this divergence monitoring time zone, it is monitored whether the power demand forecast and the power demand actual are divergent.

This is because the monitoring time zone is limited to the set time zone, so that unnecessary correction of the power demand forecast can be avoided. Further, the start time of the deviation monitoring time zone is set in the time zone after the time when the load (actual power demand value) starts to rise in order to monitor the deviation for the purpose of correcting the power demand forecast. For the purpose of correcting the power demand forecast, for example, the time zone suitable for the deviation monitoring time zone is the time zone in which the storage battery was charged / discharged in the past, or the amount of power in the past actual power demand value is relatively high. It is a time zone related to making a charge / discharge plan for a storage battery.

When the time for determining the correction of the power demand forecast is not in the deviation monitoring time zone (NO in S21),
The flow chart ends and the power demand forecast is not corrected.

On the other hand, when the time for determining the correction of the power demand forecast is the deviation monitoring time zone (Y in S21).
ES), the calculation unit 16 calculates the error rate of the actual power demand value with respect to the predicted power demand value during the period retroactive to the correction determination (S22). The correction judgment retroactive period is the data required to determine whether or not to correct the power demand forecast value when monitoring the discrepancy between the actual power demand and the power demand forecast, for the past hours or minutes from the present. It is a period to decide whether to use for a minute. This period is preset.

The actual power demand and the actual power demand forecast for the period retroactive to the correction judgment set are accumulated, and the error rate of the actual power demand with respect to the electric power demand forecast, that is, the ratio of the difference between the total values of the electric power demand forecast and the actual power demand forecast calculate.

The purpose of setting the correction determination retroactive period is to prevent excessive correction of the power demand forecast due to a large error rate during a time period when the power demand is low.

If the correction judgment retroactive period is too short, the power demand forecast will be frequently corrected due to slight fluctuations in the actual power demand from the calculation of the error rate and the judgment of the threshold value, so it is preferable to set it in the medium period. The medium period is calculated based on, for example, past actual power demand values, and the time from the time when the power demand rises to 70% to 90% of the peak power demand is appropriate.
In concrete terms, it is, for example, 2 to 4 hours. However, the period for tracing back the correction judgment is not limited to 2 hours to 4 hours.

After that, the determination unit 15 determines whether the error rate is larger than the error rate threshold value (S23). The error rate is a ratio indicating how much the deviation from the accumulated total power demand value is ± what percentage when the total integrated power demand forecast value in the corresponding time zone is set to "1" (100%). Is. The error rate threshold value is an error rate threshold value for determining whether or not to correct the power demand forecast. The error rate threshold may be changed depending on the season, date, and day of the week.

The time zone to be integrated when calculating the integrated total of the estimated power demand value and the actual power demand value is based on the current time, and the time of the period retroactive to the correction judgment is adopted. The correction judgment retroactive period is set in advance with a setting suitable for the consumer. For example, the correction judgment retroactive period is 2
In the case of time, the total of the estimated power demand value and the actual power demand value is accumulated in the time zone from 2 hours ago to the present.

A specific method for calculating the error rate will be described. First, the total integrated power demand forecast is the formula (
In 1), the integrated total of the actual power demand values can be calculated by the formula (2).

Total integrated power demand forecast value = Σ correction judgment Forecast value for the retroactive period ... (1)
Cumulative total of actual power demand values = Σ correction judgment Actual values for the retroactive period ... (2)

Then, as the deviation value, the difference between the integrated total of the predicted power demand value and the integrated total of the actual power demand value is calculated. As shown in the equation (3), the difference is obtained by giving an absolute value.
Deviation value = | "Total total of actual power demand values"-"Total total of predicted power demand values" | ... (3)
)

Finally, when the error rate is calculated as a percentage (%), it is the equation (4).
Error rate = (deviation value ÷ "total total of power demand forecast values") x 100 (%) ... (4)

When the calculated error rate is smaller than the preset error rate threshold (NO in S23)
), The flowchart ends and the power demand forecast is not corrected. That is, in the case of equation (5)
The electricity demand forecast is not corrected.
Error rate> Error rate threshold ... (5)

On the other hand, when the error rate is larger than the error rate threshold value (YES in S23), the calculation unit 16 calculates the correction amount in order to correct the power demand forecast (S24). The correction amount is an amount for correcting the power demand forecast value in a predetermined correction target time zone.

The correction target time zone is the time for correcting the power demand forecast, which is determined appropriately for each consumer. This is because if the forecast is corrected at the same rate in both the time zone with high power demand and the time zone with low power demand, it may be overcorrected in the time zone with low power demand. Set. For example, the time to start the correction is from the current time, but the end time of the correction is set to 19:30 or the like in consideration of the power demand.

The case where the error rate is larger than the error rate threshold value is expressed by the equation (6). The formula for calculating the correction amount is shown in formula (7). That is, in the case of equation (6), in order to correct the power demand forecast, the calculation unit 1
6 calculates the correction amount as in the equation (7).

In the formula (7), the predicted value of the correction determination retroactive period is a preset power demand forecast value of the correction determination retroactive period. For example, assuming that the correction determination retroactive period is 2 hours, it means the power demand forecast value from 2 hours ago to the current time.

Explaining the meaning of equation (7), the difference rate is calculated from the actual power demand value and the predicted power demand value (
"Integrated total of actual power demand value" / "Integrated total of estimated power demand value") -1) is obtained, multiplied by the estimated power demand value before correction, and integrated in the correction target time zone, and the correction target time zone Divide by number.

The number of correction target time zones is the number when the correction target time zone is divided into certain time zones. For example, when the correction target time zone is 2 hours and is divided every 30 minutes, the number of correction target time zones is 4.
Error rate <Error rate threshold ... (6)
Correction amount = (Σ (power demand forecast value for correction target time zone) x ((" power demand actual value "/" power demand forecast value ") -1)) / number of correction target time zones ... (7)

For the actual power demand value and the predicted power demand value here, the integrated total value of each was used.
An instantaneous value at a certain time may be used.

Finally, the correction unit 17 corrects the power demand forecast (S25). Specifically, the power demand forecast value is corrected by adding the correction amount calculated by the calculation unit 16 to the original power demand forecast value before the correction. Expressed as an equation, it is the equation (8).
Correction forecast value = power demand forecast value before correction + correction amount ... (8)

The target uncorrected power demand forecast value is the power demand forecast value in the correction target time zone. For example, if the correction target time zone is 19:30 from the current time and 11:30 at present, it is 1 from 11:30.
The power demand forecast value up to 9:30 is the uncorrected power demand forecast value. That is, from 11:30 to 1
The power demand forecast until 9:30 is corrected.

However, when the correction amount is a negative value and the calculation result of the equation (8) is 0 or less, the correction prediction value is set to 0.

FIG. 4 shows an image diagram of a method for correcting the predicted power demand value. The horizontal axis is time and the vertical axis is demand, which represents the time change of daily electricity demand of a certain consumer. The solid line is the actual power demand value, the dotted line is the power demand forecast value before correction, and the broken line is the power demand forecast value after correction. The period (a) indicates the deviation monitoring time zone, the period (b) indicates the correction determination retroactive period, and the period (c) indicates the correction target time zone. The correction amount of (d) is the correction amount of the power demand forecast obtained by the equation (8). FIG. 4 shows that when the time when the electric energy of the actual power demand value rises is 8 o'clock and the current time is 12 o'clock, the power demand forecast value for the period (c) correction target time zone is corrected from the current time. ..

In FIG. 4, since (b) the correction determination retroactive period is set to 2 hours, the correction determination retroactive period is from 10:00 to 12:00. In addition, (a) the deviation monitoring time zone is from 10:00 to 15:00, (
c) The correction target time zone is set to 15:00. However, FIG. 4 is only an example, and the correction judgment retroactive period, the deviation monitoring time zone, and the correction target time zone are changed to times more suitable for the customer.

The corrected power demand forecast value shown by the broken line is (b) the error rate, which is the ratio of the integrated value of the deviation between the actual power demand value and the power demand forecast value to the power demand forecast value during the period retroactive to the correction judgment. (C) The correction amount is calculated as constant on the assumption that it will continue for the period of the correction target time zone.

Regarding the correction method, (d) the correction amount is calculated based on the formula (7), and (c) the power demand forecast value for the period of the correction target time zone is a uniform amount as in the formula (8). (D) The correction amount is added to obtain the value.

(effect)
By establishing a standard for correcting the power demand forecast and changing the standard to a value appropriate for the consumer, it is possible to prevent overcorrection and correct the power demand forecast at a more appropriate timing and correction amount. it can. As a result, an appropriate charge / discharge plan can be created.

Correcting at a more appropriate timing of correction means that the difference between the power demand forecast and the actual power demand, which is the standard for deciding whether to correct the power demand forecast, is set for all time zones up to the current time of the day. Instead, by using the data after the rise time of the actual power demand, it is not necessary to make corrections unnecessarily, and the necessary corrections are made during the time period related to the creation of the charge / discharge plan of the storage battery. ..

A more appropriate correction amount is a period for performing a preset correction based on the ratio of the deviation between the power demand actual and the power demand forecast after the rise time of the power amount of the actual power demand used at the timing of the correction. By calculating the correction amount assuming that the deviation occurs at a certain rate within the (correction target time zone), more accurate correction can be performed in the time zone related to the creation of the charge / discharge plan of the storage battery.

In addition, by changing parameters such as deviation monitoring time zone, correction target time zone, correction judgment retroactive period, error rate threshold value, etc. according to the pattern of power demand amount that differs for each power consumer, more power consumers Expected to expand its application to.

In addition, the deviation monitoring time zone, the correction target time zone, the correction judgment retroactive period, and the error rate threshold value described as the values preset in the present embodiment should be adjusted so as to be suitable for each electric power consumer. Therefore, the effect of this embodiment can be realized. In addition, the deviation monitoring time zone, the correction target time zone, the correction judgment retroactive period, and the error rate threshold value can be changed at any time.

Further, regarding the rise time of the actual power demand value, which is the start time of the correction determination retroactive period (b) shown in FIG. 4, the determination of the rise time is based on the gradient which is the time change of the electric energy of the actual power demand. The time of rise may be detected, or the time may be determined in advance with reference to past actual power demand. Further, when determining the time, the rising time may be changed depending on the season, the day of the week, or the like. Along with this, (a) divergence monitoring time zone and (b)
) The start time of the correction judgment retroactive period may be advanced. For example, in summer, the actual power demand value is 1.
When starting up earlier, as shown in FIG. 5, the setting may be advanced by one hour, the start time of the correction determination retroactive period may be set to 7 o'clock, and the start time of the deviation monitoring time zone may be set to 9 o'clock.

Further, (b) the correction determination retroactive period does not necessarily have to be a fixed time. That is, only the start time of the correction determination retroactive period may be set, and the time may be set to the current time. For example, in FIG. 4, if the start time of the correction determination retroactive period is set as the rising time of the actual power demand value, the correction determination retroactive period is from 8:00 to 12:00 as shown in FIG.

Further, in the present embodiment, it is described that the power demand forecast is corrected evenly in the correction target time zone, but the correction amount may be changed depending on the time zone. That is, the magnitude of the correction amount may be changed depending on the time zone. For example, in addition to (d) the correction amount being constantly distributed with respect to time as shown in FIG. 4, the correction amount of the power demand forecast value is (d) the ratio of the power demand forecast value as shown in FIG. It can also be distributed with.

Further, although the power demand forecast value at the end time of the correction target time zone in FIG. 4 (c) is discontinuous, the power demand forecast value may be corrected so as to be continuous as shown in FIG.

Further, in the present embodiment, when determining whether to correct the power demand forecast value, the error rate is used and the formula (
As shown in 4), the ratio of the deviation value to the integrated total of the power demand forecast values was calculated, but the formula (9)
As described above, the ratio of the deviation value to the integrated total of the actual power demand values may be calculated. Further, when determining whether to correct the electric power demand forecast value, it may be determined by the amount of electric power instead of the error rate. That is, it is also possible to set a threshold for the amount of electric power at which the predicted electric power demand value and the actual electric power demand value deviate in advance, and to correct the predicted electric power demand value when the amount of electric power deviates beyond the threshold value.
Error rate = (deviation value ÷ "total total of actual power demand values") x 100 (%) ... (9)

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

1 Information processing device 11 Acquisition unit 12 Storage unit 13 Output unit 14 Prediction unit 15 Judgment unit 16 Calculation unit 17 Correction unit 18 Creation unit

Claims (12)

A forecasting unit that predicts the power demand forecast value, which is the future power demand value,
It is determined whether or not the time for which the correction of the power demand forecast value is to be determined is the preset deviation monitoring time zone , and if the time is not the deviation monitoring time zone, the power demand forecast When it is decided not to correct the value and the time is in the deviation monitoring time zone, the deviation between the actual power demand value , which is the actual actual power demand value, and the expected power demand forecast value is used. A judgment unit that determines whether or not to correct the power demand forecast value,
A calculation unit that calculates the correction amount of the power demand forecast value when it is determined by the determination unit to make corrections.
A correction unit that corrects the power demand forecast value based on the correction amount,
Information processing device equipped with. The divergence monitoring time zone is
It is a time zone after the time when the actual power demand value starts to rise, and is set based on the past actual power demand value.
The information processing device according to claim 1. As a deviation between the actual power demand value and the predicted power demand value, the determination unit sets the power demand amount to a predetermined ratio of the peak of the power demand amount from the time when the actual power demand amount rises in the past. The power demand when the ratio of the difference between the integrated values in the correction judgment retroactive period preset in the middle period to the power demand forecast value in the correction judgment retroactive period is larger than the preset threshold value. The information processing apparatus according to claim 1 or 2, which is determined to correct the predicted value. The information processing apparatus according to any one of claims 1 to 3 , wherein the correction unit corrects the power demand forecast value based on the correction amount in a correction target time zone which is a period for performing a preset correction. .. The calculation unit is the correction determination retroactive period set in advance in the middle period from the time when the actual power demand rises in the past until the power demand reaches a predetermined ratio of the peak of the power demand. The information processing apparatus according to claim 4 , wherein the correction amount is calculated to be constant in the correction target time zone based on the ratio of the actual power demand value to the predicted power demand value. The calculation unit is the correction determination retroactive period set in advance in the middle period from the time when the actual power demand rises in the past until the power demand reaches a predetermined ratio of the peak of the power demand. The information processing apparatus according to claim 4 , wherein the correction amount in the correction target time zone is calculated to be the ratio of the power amount of the power demand forecast value based on the ratio of the power demand actual value to the power demand forecast value. A creation unit that creates a charge / discharge plan that plans the time and amount of charging or discharging the storage battery based on the power demand forecast value.
The information processing apparatus according to any one of claims 1 to 6 . An output unit that outputs the power demand forecast value or charge / discharge plan, and
The information processing apparatus according to any one of claims 1 to 7 . A forecasting unit that predicts the power demand forecast value, which is the future power demand value,
The actual power demand value in the correction judgment retroactive period preset in the middle period from the time when the actual power demand rises in the past until the power demand reaches a predetermined ratio of the peak of the power demand. Based on the discrepancy between the actual power demand value and the predicted power demand value, which is the actual result of the above, a judgment unit for determining whether or not to correct the predicted power demand value, and
A calculation unit that calculates the correction amount of the power demand forecast value when it is determined by the determination unit to make corrections.
A correction unit that corrects the power demand forecast value based on the correction amount,
Information processing system equipped with. The judgment unit
It is determined whether or not the time for which the correction of the power demand forecast value is to be determined is in the preset deviation monitoring time zone, and if the time is not in the deviation monitoring time zone, the power demand forecast It is determined not to correct the value, and when the time is in the deviation monitoring time zone, it is determined whether or not to correct the power demand forecast value.
The information processing system according to claim 9. Information processing device,
Predicting means for predicting future power demand forecast value, which is the future power demand value,
The actual power demand value in the correction judgment retroactive period preset in the middle period from the time when the actual power demand rises in the past until the power demand reaches a predetermined ratio of the peak of the power demand. Based on the discrepancy between the actual power demand value and the predicted power demand value, which is the actual result of the above, a judgment means for determining whether or not to correct the predicted power demand value, and
When it is determined to be corrected by the determination means, the calculation means for calculating the correction amount of the power demand forecast value and the calculation means.
A correction means for correcting the power demand forecast value based on the correction amount, and
An information processing program to make it work. The judgment means is
It is determined whether or not the time for which the correction of the power demand forecast value is to be determined is in the preset deviation monitoring time zone , and if the time is not in the deviation monitoring time zone, the power demand forecast is performed. It is determined not to correct the value, and when the time is in the deviation monitoring time zone, it is determined whether or not to correct the power demand forecast value.
The information processing program according to claim 11.

Images