KR102338524B1 - System and method for determining the optimum bid of power generation - Google Patents

Abstract

The present invention relates to a system for determining an optimal power generation bid price. More specifically, the system for determining an optimal power generation bid price includes: a predicted value receiving unit which receives a predicted value for renewable power generation from a power generation prediction system; a conditional distribution estimating unit which estimates an actual value probability distribution for the received predicted value from previously collected past power generation data including a predicted value and an actual value for renewable power generation; and a bid price determining unit that calculates a bid price that maximizes expected revenue by using a predetermined revenue settlement standard and the estimated actual value probability distribution based on power market operation rules of the Korea Power Exchange, and determines the calculated bid price as a final bid price.

Description

SYSTEM AND METHOD FOR DETERMINING THE OPTIMUM BID OF POWER GENERATION

The present invention relates to a system for determining the optimal power generation bid value, and more particularly, by identifying the relationship between the predicted value and the actual value from the past generation record, estimating the probability distribution of the actual value for a given predicted value, and the estimated actual value probability It relates to an optimal power generation bid value determination system that can determine the bid value with the maximum expected revenue as the optimal bid value using distribution and revenue settlement criteria.

Electric energy consumption is continuously increasing worldwide. However, since the amount of energy resources based on fossil fuels is limited, there is a trend to increase the proportion of power generation from renewable energy sources such as solar power generation and wind power generation.

In the case of producing electric energy by utilizing such new and renewable energy generation, it is possible to reduce environmental pollutants such as greenhouse gases and fine dust, as well as increase the stability of energy supply from the perspective of sustainable future energy. have.

However, the output power (hereinafter, generation amount) of the renewable power generation system varies throughout the day due to the influence of external factors such as dust, clouds, and snow, and is also greatly affected by seasonal factors.

In order to improve the uncertainty caused by the highly volatile new and renewable power generation system, to improve the reliability of the power system, and to improve the power quality, the Korea Power Exchange has foretold the introduction of a renewable energy generation forecasting system.

Renewable energy generation forecasting system is conducted in the previous day's bidding method. Renewable energy generators submit (bid) the predicted value of generation for each time period of the next day (the trading day) to the Power Exchange by the specified time on the previous day (bidding date).

If the actual power generation (actual value) on the day of the transaction and the predicted power generation amount submitted the previous day (bid value) are similar, the power generation company will receive a profit. Specifically, revenue is generated by multiplying the actual power generation by the unit price only for the time period when the actual power generation versus capacity exceeds the minimum standard for revenue settlement. At this time, the unit price (KRW/kWh) is determined according to the range of the error rate calculated from the actual value and the bid value. In other words, the lower the error rate, the higher the profit.

At this time, the result of the power generation prediction algorithm does not always give the bid value that expects the lowest error rate. For example, if a prediction algorithm that gives a biased prediction result in the direction of underprediction is used, bidding the corrected value in consideration of the bias helps to lower the error rate. Furthermore, although there is a general relationship that a lower error rate leads to higher profits, there are other factors that determine profits, so the bid price with the lowest error rate does not always mean the highest expected profit. That is, for optimal profit, a process of determining the optimal bid value within a given revenue settlement rule is required based on the result of the power generation forecasting algorithm.

: Korea Patent Publication No. 10-2021-0043387 (published on 21.04.02.)

The problem to be solved by the present invention is to figure out the relationship between the predicted value and the actual value from the past power generation record, to estimate the probability distribution of the actual value for a given predicted value, and to estimate the probability distribution and the profit function of the actual value (revenue settlement standard) It is to provide an optimal power generation bid value determination system that can determine the bid value with the maximum expected profit as the optimal bid value using

In order to solve the above-described problem, the optimal power generation bid value determination system according to an embodiment of the present invention includes the predicted value and the actual value for the new and renewable power that have been collected when the predicted value for the renewable power is received. Based on the conditional distribution estimator for estimating the actual value probability distribution for the received predicted value from the power generation data and the electricity market operation rule of the Korea Power Exchange, the expected return using the preset revenue settlement standard and the estimated actual value probability distribution It may include a bid value determiner that calculates a bid value that maximizes the bid value, and determines the calculated bid value as a final bid value.

In addition, the conditional distribution estimating unit includes a prediction value discretization unit that discretizes the prediction value and sets the discretized prediction value having the same value as a group for the past power generation data of a specific period, each based on the type of the distribution and the maximum likelihood estimation method. and a distribution parameter estimator for calculating an optimal distribution parameter of actual values for a group, and an actual value distribution estimator for estimating an actual value distribution for each group according to the preset distribution using the calculated optimal distribution parameter. .

In addition, the conditional distribution estimator may estimate an actual value probability distribution of the corresponding group including the received predicted value as an actual value probability distribution with respect to the received predicted value.

In this case, the expected revenue may be a step function for a bid value calculated by integrating the product of the revenue settlement standard and the actual value probability distribution.

In addition, the revenue settlement standard may be calculated as a product of whether or not the revenue calculation is applied, an actual value that is an actual power generation amount, and an applied unit price.

At this time, whether the revenue calculation is applied or not, the condition is established when the actual value for the renewable power generation capacity exceeds the minimum utilization rate, 1 is applied when the condition is established, 0 is applied when the condition is not established, and the applied unit price is the price of the power exchange. It may be determined according to the error rate between the actual value and the bid value based on the electricity market operation rules.

In addition, the optimal power generation bid value determination system according to an embodiment of the present invention includes a receiving step of receiving a predicted value for renewable power generation, from the past power generation data including pre-collected predicted values and actual values for renewable power generation, the above A conditional distribution estimation step of estimating the actual value probability distribution for the received prediction value, a bid value that maximizes the expected profit using a preset revenue settlement standard based on the electricity market operation rules of the Korea Power Exchange and the estimated actual value probability distribution , and may include a bid value determination step of determining the calculated bid value as a final bid value.

In addition, with respect to the past power generation data of a specific period, discretizing the predicted value and setting the discretized predicted value having the same value as a group, the optimal distribution of the actual values for each group based on the preset type of distribution and the maximum likelihood estimation method The method further includes calculating a parameter and estimating an actual value distribution of estimating an actual value distribution for each group according to the preset distribution by using the calculated optimal distribution parameter, and may be performed before receiving the predicted value.

In addition, the conditional distribution estimating step may estimate an actual value probability distribution of the group including the received predicted value as an actual value probability distribution with respect to the received predicted value.

In this case, the expected revenue may be a step function for a bid value calculated by integrating the product of the revenue settlement criterion and the actual value probability distribution.

In addition, the revenue calculation criterion is calculated by the product of whether the revenue calculation is applied or not, the actual value that is the actual amount of power generation and the applied unit price, and whether the revenue calculation is applied is, It is established, and 1 is applied when the condition is established and 0 is applied when the condition is not established, and the applied unit price may be determined according to the error rate between the actual value and the bid value based on the electricity market operation rules of the Korea Power Exchange.

The optimal generation bid value determination system according to an embodiment of the present invention grasps the relationship between the predicted value and the actual value from the past generation record, calculates the probability distribution of the actual value for the given predicted value, and the probability distribution of the calculated actual value The maximum profit can be expected by determining the optimal bid value using the revenue settlement criteria.

In addition, it is possible to estimate the optimal actual value probability distribution by calculating the optimal distribution parameter that determines the distribution of actual values matching the predicted value. You can determine the bid price.

The effect according to the present invention is not limited by the contents exemplified above, and more various effects are included in the present specification.

1 is a schematic diagram of a renewable power generation system for explaining an optimal power generation bid value determination system according to an embodiment of the present invention.
FIG. 2 is a block diagram for explaining the configuration of the optimal generation bid value determination system of FIG. 1 .
3 is a graph for explaining a unit price function according to an embodiment of the present invention.
4 is a flowchart illustrating a method for determining an optimal power generation bid value according to an embodiment of the present invention.
FIG. 5 is a flowchart for explaining a grouping process for estimating the distribution of actual values of FIG. 4 .

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in a variety of different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the technical field to which the present invention belongs It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the scope of the claims.

Sizes and relative sizes of components indicated in the drawings may be exaggerated for clarity of description. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited items.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components.

Although the first, second, etc. are used to describe various elements or elements, these elements or elements are not limited by these terms, of course. These terms are only used to distinguish one element or component from another. Therefore, it goes without saying that the first element or component mentioned below may be the second element or component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly defined in particular.

The following detailed description is not intended to be taken in a limiting sense, and the scope of the present invention, if properly described, is limited only by the appended claims, along with all scope equivalents to those claimed. Like reference numerals in the drawings refer to the same or similar functions throughout the various aspects.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a schematic diagram of a renewable power generation system for explaining an optimal power generation bid value determination system according to an embodiment of the present invention. Hereinafter, solar power generation is illustrated as an example for understanding of description, but is not limited thereto, and may be applied when determining a bid value in a renewable power generation system such as solar heat, bio, wind power, hydro power, and fuel. In addition, in the present invention, the amount of generation predicted by using the prediction algorithm is hereinafter referred to as a predicted value, the amount of power actually measured is referred to as an actual value, and a predicted value for bidding participation may be defined as a bid value.

The renewable power generation system (1000; hereinafter, power generation system) according to an embodiment of the present invention is a cloud-based software based on power generation facilities such as small-scale energy generation, storage batteries, fuel cells, etc. distributed such as home solar power, and power demand. It can be a virtual power plant (VPP) that is integrated and managed in a systematic way. It is essential to accurately predict the amount of electricity generated by VPP because it is necessary to supply the amount of electricity that satisfies the electricity demand by predicting the amount of electricity generated by the related power generation facilities.

The prediction system 200 receives, for example, data necessary for predicting the amount of renewable energy generation, such as temperature and solar radiation, from an external server or database 300 . Through the predictive model, it is possible to estimate the amount of renewable energy generation in the region in real time. The prediction system 200 may provide the predicted real-time generation amount for each site and the real-time total generation amount predicted value to the optimal generation bid value determination system 250 (hereinafter, bid value determination system) according to an embodiment of the present invention.

Specifically, according to FIG. 1 , the renewable power generation system 1000 according to an embodiment of the present invention receives the actual power generation amount of the solar module array 11 from the connected solar power generation facility 10 .

The power generation system 1000 according to an embodiment of the present invention is an RTU 100-1, a prediction system 200, a bid value determination system 250, and a database 300 that can receive data on the actual amount of solar power generation. ) and various types of sensors 350 installed in the vicinity of the solar module array 11 . In this case, the power generation system 1000 may be connected to the solar power generation facility 10 and the power sales and purchase system, that is, the power exchange 400 .

The photovoltaic power generation facility 10 may include a photovoltaic module array 11 , a connecting board 12 and an inverter 13 , and in an embodiment of the present invention, as shown in FIG. 1 , but a coupling method of each configuration can be easily changed by the designer.

In the solar module array 11 , a plurality of solar cell modules that convert sunlight incident on the surface into electrical energy are connected in series or in parallel. The photovoltaic module array 11 may output a DC current and provide it to the connection panel 12 , and a plurality of solar module arrays 11 may be connected to one connection panel 12 .

The connection panel 12 may measure voltage information and current information for each solar module and each time period. A plurality of solar module arrays 11 may be connected in parallel to the connection panel 12 . The connection panel 12 may connect the solar module array 11 and the inverter 13-1 to connect DC power generated from the solar module array 11 in series/parallel to collect. At least one connection panel 12 may be connected to one inverter 13 - 1 .

The inverter 13 may be connected to a plurality of connection boards 12 and cables to receive DC power. In addition, the inverter 13-1 converts the generated power provided in the DC form from the connection panel 12 into an AC to transmit power through the grid power. At this time, the information on the AC power generated by the inverter can be monitored in real time in the estimation system through the RTU (Remote Terminal Unit, 100-1 to 100-n) for each site. The RTU 100 - 1 may store the actual amount of power generation of the solar module arrays 11 required for prediction in the prediction system 200 in the database 300 . The RTU 100-1 and the inverter 13-1 may be connected through wired/wireless communication means.

In addition, the prediction system 200 obtains information such as the surface temperature of the photovoltaic module cell, the site temperature of the photovoltaic module array 11, humidity and wind direction from the sensor 350 installed around the photovoltaic module array, and It can be used to calculate the real-time power generation forecast value.

The prediction system 200 according to an embodiment of the present invention may set a benchmarking group based on the geographic location of a plurality of renewable energy generation sites, and may set a benchmarking site for each benchmarking group. In addition, the prediction system 200 calculates and calculates the real-time generation amount predicted value for each site except the benchmarking site among the sites included in the corresponding benchmarking group using a preset prediction model based on the real-time generation amount measured value for the benchmarking site The predicted value of estimating the real-time total power generation for all sites by adding up the real-time generation amount predicted value for each site and the real-time generation amount actual value for the benchmarking site may be transmitted to the bid value determination system 250 .

The bid value determination system 250 according to an embodiment of the present invention may determine a bid value capable of deriving a maximum profit based on a prediction value received in real time.

FIG. 2 is a block diagram for explaining the configuration of the optimal generation bid value determination system of FIG. 1 . Referring to FIG. 2 , the bid value determination system 250 may include a setting unit 251 , a conditional distribution estimating unit 252 , and a bid value determining unit 253 , and the conditional distribution estimating unit 252 is a predicted value It may include a discretization unit 2521 , a distribution parameter estimator 2522 , and an actual value distribution estimator 2523 .

The setting unit 251 may collect past power generation data for the predicted value and the actual value generated by the prediction system 200 from the DB 300 for calculating the optimal bid value, and at this time, a specific period for collection is selected by the user (administrator). etc.) can be set.

In addition, the setting unit 251 may receive input from the user, such as the type of distribution for estimating the distribution, setting a section for discretizing the predicted value, and the number of groups. In this case, the type of distribution may be a normal distribution, a gamma distribution, a Bay Boolean distribution, and the like.

The conditional distribution estimator 252 receives the predicted value for the renewable power generation from the prediction system 200, from the previously collected historical power generation data including the predicted value and the actual value for the renewable power generation, to the predicted value received for bidding. It is possible to estimate the actual value probability distribution for In this case, the actual value probability distribution may be a conditional probability distribution following the actual value when the predicted value is given as a condition.

In an embodiment of the present invention, conditional probability distribution estimation may be performed to determine whether the prediction algorithm tends to underestimate the prediction tendency. That is, by judging the tendency of the prediction algorithm from the relationship between the prediction value (received prediction value) predicted by the prediction algorithm and the actual value, if the algorithm under-predicts, it is possible to obtain a greater profit than the received prediction value. Predictions can be found as bid values.

To this end, the conditional distribution estimator 252 may estimate the discretized prediction value and the actual value probability distribution for each discretized prediction value group.

Specifically, the predicted value discretization unit 2521 may discretize the predicted values for the past generation amount data of a specific period and set the discretized predicted values having the same value into groups. In this case, the group may be determined according to the section setting for discretizing the predicted value input from the setting unit 251, the number of groups, and the like.

As an example, when the range of 0 to facility capacity is set as a section divided into 10 equal parts, each predicted value may be discretized by converting it into a section including the corresponding predicted values among the decile sections. Accordingly, the discretized prediction values included in the same section are composed of one group, so that the prediction values can be discretized into n groups.

The distribution parameter estimator 2522 may calculate the optimal distribution parameter of actual values for each group based on the distribution type selected by the setting unit 2521 and the maximum likelihood estimation method. In this case, the optimal distribution parameter is a distribution parameter that best describes the actual data, and can be an important value that determines the shape of the probability distribution.

Maximum likelihood estimation is a parametric data density estimation method. When there is a sample data set observed in a certain probability density function composed of parameters, it is a method of estimating the parameter with the highest probability that these samples will appear.

)로 표현되는 확률변수 X의 확률밀도함수가

이고, 이 확률변수로부터 독립시행을 반복하여 값

을 얻었다고 하면, 이때의 우도(likelihood: 어떤 모수가 주어졌을때 해당 관측값들이 나올 가능성)는

로 정의된다. 여기서 우도를 최대로 만드는

를 찾을 수 있다면, 이 값이 바로 최대우도추정법을 통해 추정된 분포 파라미터가 된다.Specifically, what parameters (

), the probability density function of the random variable X expressed as

, and repeating independent trials from this random variable

, the likelihood at this time is

is defined as Here, the likelihood is maximized

If can be found, this value becomes the distribution parameter estimated through the maximum likelihood estimation method.

At this time, the corresponding distribution parameter is determined according to the type of distribution, and in the case of solar and wind power generation, there are a lower limit (0) and an upper limit (installation capacity), so a gamma distribution or a Beibull distribution may be suitable. Also, a normal distribution may be set according to a user's setting.

The actual value distribution estimator 2523 estimates the actual value distribution for each group according to a preset distribution type using the calculated optimal distribution parameter, and sets n groups and n actual value probability distributions for the discretized predicted values. can be put In this case, the distribution type may be set differently for each group.

In addition, when the prediction value for bidding is received from the prediction system 200 , the actual value distribution estimator 2523 extracts the actual value probability distribution of the corresponding group including the received prediction value, and the actual value probability distribution for the received prediction value can be estimated as

The bid value determination unit 253 calculates and calculates a bid value that maximizes the expected revenue by using the actual value probability distribution according to the given predicted value estimated by the actual value distribution estimation unit 2523 and the revenue function serving as the revenue settlement standard The bid value may be determined as the final bid value.

In this case, the revenue settlement criterion may be generated as a revenue function based on the power market operation rules of the Power Exchange, and in the present invention, it may be a product of whether the revenue calculation is applied, the actual value that is the actual amount of power generation, and the applied unit price.

Here, as to whether or not to apply the revenue calculation, the condition is established when the actual value compared to the renewable power generation capacity exceeds the minimum utilization rate, and 1 when the condition is established and 0 when the condition is not established. In addition, the applied unit price may be determined according to the error rate between the actual value and the bid value based on the electricity market operation rules of the Korea Power Exchange.

As an example of a revenue function that follows the electricity market operation rules of the Korea Power Exchange, a revenue function as shown in Equation 1 below may be used as a revenue settlement criterion.

는 실제값,

는 입찰값이 된다.Here, C is the installed capacity (fixed value), 1 is the indicator function (1 if the condition is satisfied, otherwise 0), and g is the applied unit cost function according to the error rate. g(x) := 4 Won/kWh if 0<= x <= 0.06, 3 Won/kWh if 0.06 < x <= 0.08, 0 Won/kWh The rest of the cases can be. Also,

is the actual value,

is the bid value.

Alternatively, a profit function such as the following Equation and 2 may be applied.

Here, h(x; x_0, C) is the applied unit cost function and is the same as g(|x - x_0| / C), and 4 won/kWh if x_0 - 0.06 * C <= x <= x_0 + 0.06 *C, 3 won/kWh if x_0 - 0.08 * C <= x < x_0 - 0.06 * C or x_0 + 0.06 * C < x <= x_0 + 0.08 * C, otherwise it can be 0.

In this case, the unit price function according to Equation 2 may be expressed as a graph as shown in FIG. 3 . As such, the smaller the error between the actual value and the bid value presented at the time of bidding, the larger the profit (P) tends to be.

On the other hand, in the embodiment of Equations 1 and 2, the case where the applied unit price function is a linear function is exemplified, but it may be changed to various functions based on the power market operation rules (generation amount prediction system) of the Power Exchange.

The bid value determination unit 253 may be calculated by integrating the product of the probability distribution of the actual value estimated when the revenue settlement standard and the received prediction value are given. The expected revenue according to an embodiment of the present invention may be defined as in Equation 3 below.

는 상기 수학식2의 수익정산기준인 수익함수,

는 조건부 실제값 추정부(252)에서 예측값이 주어졌을때 추정된 실제값 확률분포함수가 될 수 있다.here,

is a revenue function that is the revenue settlement standard of Equation 2,

may be an actual value probability distribution function estimated when a predicted value is given by the conditional actual value estimator 252 .

As an example, if it is assumed that the estimated actual value probability distribution function follows a normal distribution when the prediction value (the prediction value received from the prediction system 200) is given, the estimated actual value probability distribution function becomes the following Equation 4 can

는 평균,

는 표준편차가 된다.here,

is the average,

is the standard deviation.

When the profit function of Equation 2 and the probability distribution function of Equation 4 are applied to the expected return of Equation 3, the expected return can be calculated as in Equation 5 below.

In this way, the expected return according to an embodiment of the present invention can be approximated by the sum by discretizing the integral calculation. In this case, the expected revenue may be a step function for the bid value.

)에 대한 함수로 바라보고, 기대수익을 최대화시키는 입찰값을 최종 입찰을 위한 최적 입찰값으로 결정할 수 있다.The bid value determination unit 253 determines the expected revenue from the bid value (

), it is possible to determine the bid value that maximizes the expected profit as the optimal bid value for the final bid.

4 is a flowchart illustrating a method for determining an optimal power generation bid value according to an embodiment of the present invention. Also, FIG. 5 is a flowchart for explaining a grouping process for estimating the distribution of actual values of FIG. 4 .

The optimal generation bid value determination method of the present invention can be performed by the optimum generation bid value determination system of FIGS. 2 and 3, and since specific operations and equations have been described in the system description, the following briefly describes the method and focuses on the method to do it

According to FIG. 4, upon receiving the predicted value for the renewable power generation for bidding from the prediction system 200 (S410), from the previous generation data including the predicted value and the actual value for the previously collected renewable power generation, in step S410 It is possible to estimate the actual value probability distribution for the received predicted value (S420).

For this, steps S400 to S402 of FIG. 5 are performed before the prediction value is received, the prediction values of the past record are divided into sections and discretized, and the actual value distribution for each group is estimated and prepared through grouping of the discretized prediction values. can be put

Specifically, in order to calculate the optimal bid value, it is possible to collect historical power generation data for the predicted value and the actual value generated by the prediction system 200 from the DB 300, and at this time, a specific period for collection is provided from the user (administrator, etc.) can be set. In addition, the type of distribution for distribution estimation, interval setting for discretization of predicted values, number of groups, etc. may be input from the user.

Next, the prediction values may be discretized and grouped (S400). Specifically, with respect to the past generation amount data of a specific period set by the user, the predicted values may be discretized and the discretized predicted values having the same value (same section) may be set as a group.

Accordingly, the discretized prediction values included in the same section are composed of one group, so that the prediction values can be discretized into n groups.

Next, an optimal distribution parameter of actual values for each group may be calculated ( S401 ). Specifically, it is possible to calculate the optimal distribution parameter of actual values for each group based on the distribution type selected by the user and the maximum likelihood estimation method.

Next, an actual value distribution for each group according to a preset distribution type may be estimated using the calculated optimal distribution parameter of the corresponding group ( S402 ). Accordingly, n groups and n actual value probability distributions for the discretized predicted values can be set. In this case, the distribution type may be set differently for each group.

Next, when the prediction value for bidding is received from the prediction system 200 as in step S410, the actual value probability distribution of the group including the received prediction value is extracted and estimated as the actual value probability distribution for the received prediction value. There is (S420).

Next, a bid value that maximizes the expected revenue is calculated using the probability distribution of the actual value according to the given prediction value estimated in step S420 and the revenue function serving as the revenue settlement criterion (S430), and the calculated bid value is used as the final bid value. It can be determined (S440).

At this time, the expected revenue may be calculated by integrating the product of the probability distribution of the actual value estimated when the revenue settlement standard and the received prediction value are given, and may be a step function for the bid value. Accordingly, the expected revenue may be viewed as a function of the bid value, and a bid value maximizing the expected revenue may be determined as the optimal bid value for the final bid.

At least some of the embodiments of the present invention described above may be implemented as computer-readable codes on a computer-readable recording medium. For example, the operation of the optimal power generation bid value determination system 250 shown in FIGS. 2 to 5 may be implemented as computer-readable codes on a computer-readable recording medium.

The computer-readable recording medium may include any type of recording device in which data readable by a computer system is stored.

Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. may include

In addition, the computer-readable recording medium is distributed and implemented in network-connected computer systems, so that the computer-readable code can be stored and executed in a distributed manner.

The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, but may be manufactured in a variety of different forms, and those of ordinary skill in the art to which the present invention pertains. It will be understood by those skilled in the art that the present invention may be embodied in other specific forms without changing the technical spirit or essential features of the present invention. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

1000: Renewable power generation system
100, 100a to 100n: RTU 200: prediction system
250: bid price determination system
251: setting unit 252: conditional distribution estimator
253: bid value determination unit 2521: predicted value discretization unit
2522: distribution parameter estimator 2523: actual value distribution estimator

Claims (10)

a conditional distribution estimator for estimating an actual value probability distribution with respect to the received predicted value from past power generation data including previously collected predicted values and actual values for renewable power generation when a predicted value for renewable power is received; and
A bid value for calculating a bid value that maximizes the expected profit using a predetermined revenue settlement standard and the estimated actual value probability distribution based on the electricity market operation rules of the Korea Power Exchange, and determining the calculated bid value as the final bid value comprising a determinant;
The conditional distribution estimating unit,
a predicted value discretization unit for discretizing the predicted values with respect to the past generation amount data of a specific period and setting the discretized predicted values having the same value as a group;
a distribution parameter estimator that calculates an optimal distribution parameter of actual values for each group based on a preset type of distribution and a maximum likelihood estimation method; and
and an actual value distribution estimator for estimating an actual value distribution for each group according to the preset distribution by using the calculated optimal distribution parameter. delete According to claim 1,
The conditional distribution estimator,
The optimal generation bid value determination system for estimating the actual value probability distribution of the group including the received prediction value as the actual value probability distribution for the received prediction value. According to claim 1,
The expected return is
The optimal power generation bid value determination system, which is a step-by-step function for a bid value, calculated by integrating the product of the revenue settlement criterion and the actual value probability distribution. According to claim 1,
The income calculation criteria are:
It is calculated as the product of the application of the revenue calculation and the actual value, which is the actual power generation, and the applied unit price,
Whether the above revenue calculation is applied or not, the condition is established when the actual value compared to the renewable power generation capacity exceeds the minimum utilization rate, and 1 is applied when the condition is established and 0 is applied when the condition is not established,
The applied unit price is determined according to an error rate between the actual value and the bid value based on the electricity market operation rules of the power exchange, the optimal power generation bid value determination system. Conditional distribution for estimating an actual value probability distribution for the received predicted value from the previously collected historical power generation data including the predicted value and the actual value for the previously collected new and renewable power generation when the conditional distribution estimating unit receives the predicted value for the renewable power generation estimation step; and
The bid value determination unit calculates a bid value for calculating a bid value that maximizes the expected profit by using a predetermined revenue settlement criterion and the estimated actual value probability distribution based on the electricity market operation rule of the Korea Power Exchange, and the calculated bid value including a bid value determination step of determining as the final bid value,
The conditional distribution estimation step is,
setting the discretized predicted values having the same value as a group by discretizing the predicted values with respect to the past generation amount data of a specific period;
calculating an optimal distribution parameter of actual values for each group based on a preset distribution type and a maximum likelihood estimation method;
estimating an actual value distribution of estimating an actual value distribution for each group according to the preset distribution using the calculated optimal distribution parameter;
receiving a predicted value for renewable power generation; and
Including the step of estimating an actual value probability distribution for the received prediction value from the actual value distribution for each group, the optimal generation bid value determination method. delete 7. The method of claim 6,
The conditional distribution estimation step is
The optimal generation bid value determination method for estimating the actual value probability distribution for the received prediction value as the actual value probability distribution of the group including the received prediction value. 7. The method of claim 6,
The expected return is
The optimal power generation bid value determination method, which is a step-by-step function for the bid value, calculated by integrating the product of the revenue settlement criterion and the actual value probability distribution. 7. The method of claim 6,
The income calculation criteria are:
It is calculated as the product of the application of the revenue calculation and the actual value, which is the actual power generation, and the applied unit price,
Whether the above revenue calculation is applied or not, the condition is established when the actual value compared to the renewable power generation capacity exceeds the minimum utilization rate, and 1 is applied when the condition is established and 0 is applied when the condition is not established,
The applied unit price is determined according to an error rate between the actual value and the bid value based on the electricity market operation rules of the power exchange, the optimal power generation bid value determination method.

Images