KR-20260067583-A - DEVICE AND METHOD FOR PREDICTING THE SYSTEM MARGINAL PRICE

KR20260067583AKR 20260067583 AKR20260067583 AKR 20260067583AKR-20260067583-A

Abstract

The present invention relates to a device for predicting a voluntary demand response bid through a System Marginal Price, comprising: a demand prediction unit that predicts future hourly power demand to derive a predicted power demand and a power load increase/decrease amount; a power generation prediction unit that derives a predicted power generation amount by power source based on the predicted power demand, the power generation amount by power source, and the power generation potential by power source regarding the additional power generation possible by power source; a model selection unit that selects one of a plurality of System Marginal Price prediction models based on the power generation amount by power source, the power generation potential by power source, and the hourly power load increase/decrease amount; and a System Marginal Price prediction unit that derives a predicted System Marginal Price by inputting the predicted power demand and the predicted power generation amount by power source into the selected System Marginal Price prediction model.

Inventors

이근모
박수민

Assignees

주식회사 케이티

Dates

Publication Date: 20260513
Application Date: 20241106

Claims (19)

In a System Marginal Price (SMFP) forecasting device, A demand forecasting unit that predicts future time-based power demand and derives predicted power demand and power load increase/decrease amounts; A power generation prediction unit that derives a predicted power generation amount for each power source based on the above-mentioned predicted power demand, the power generation amount for each power source, and the power generation potential for each power source regarding the additional power generation possible for each power source; A model selection unit that selects one of a plurality of system marginal price prediction models based on the power generation amount by power source, the power generation potential by power source, and the increase/decrease amount of power load by time period; and A device comprising: a system marginal price prediction unit that derives a predicted system marginal price by inputting the predicted power demand and the predicted power generation amount by power source into a selected system marginal price prediction model.
In paragraph 1, The above-mentioned demand forecasting unit includes a demand forecasting model that derives the above-mentioned predicted power demand based on weather information regarding past weather conditions, past power usage information, and past power demand information by period.
In paragraph 1, The device comprises a power source prediction model that derives the predicted power generation amount for each power source on an hourly basis, based on the predicted power demand, the power generation amount for each power source, the power generation potential for each power source, and the hourly change amount of the predicted power demand.
In paragraph 1, A device in which the above model selection unit selects one of the above system marginal price prediction models based on the above power generation amount by power source, the above power generation potential by power source, the above power load increase/decrease amount derived by time period, and the type of power source used to determine the system marginal price in the time prior to the time to be predicted.
In paragraph 4, The above model selection unit, when the type of power source used to determine the system marginal price at a time prior to the time to be predicted is thermal power generation, A device that selects one of the above-mentioned system marginal price prediction models by comparing the thermal power generation potential among the above-mentioned power generation potentials by power source with the above-mentioned power load increase/decrease amount.
In paragraph 4, The above model selection unit, when the type of power source used to determine the system marginal price at a time prior to the time to be predicted is LNG (Liquefied Natural Gas) power generation, A device for selecting one of the above-mentioned system marginal price prediction models by comparing the LNG power generation amount among the above-mentioned power generation amounts by power source or the LNG power generation potential among the above-mentioned power generation potentials by power source with the above-mentioned power load increase/decrease amount.
In paragraph 4, The above model selection unit, when the type of power source used to determine the system marginal price at a time prior to the time to be predicted is oil-fired power generation, A device that selects one of the above-mentioned system marginal price prediction models by comparing the oil power generation amount among the above-mentioned power generation amounts by power source with the above-mentioned power load increase/decrease amount.
In paragraph 1, The above-mentioned system marginal price prediction unit is a device that derives the predicted system marginal price for a time to be predicted by inputting the predicted power demand, the predicted generation amount by power source, and past system marginal prices into a selected system marginal price prediction model.
In paragraph 1, A device further comprising a voluntary demand response prediction unit that predicts a voluntary demand response winning bid rate based on the above-mentioned predicted power demand and the above-mentioned predicted system marginal price.
In Paragraph 9, The above-mentioned voluntary demand response prediction unit includes a bid success rate prediction model that predicts the voluntary demand response bid success rate based on the above-mentioned predicted power demand amount, the above-mentioned predicted system marginal price, and the net benefit threshold of the system marginal price.
In Paragraph 10, The above-mentioned bid success rate prediction model is a device that receives additional input of information regarding whether it is a metropolitan area and predicts the voluntary demand response bid success rates for metropolitan and non-metropolitan areas.
In paragraph 1, The above-described voluntary demand response prediction unit is a device that predicts the voluntary demand response winning bid rate for a time period of at least 48 hours later.
In a method using a System Marginal Price (SMRP) prediction device, A step of predicting future hourly power demand to derive the predicted power demand and the increase/decrease in power load; A step of deriving the predicted power generation amount for each power source based on the above-mentioned predicted power demand, the power generation amount for each power source, and the power generation potential for each power source regarding the additional power generation possible for each power source; A step of selecting one of a plurality of system marginal price prediction models based on the power generation amount by power source, the power generation potential by power source, and the increase/decrease amount of power load; and A method comprising the step of deriving a predicted system marginal price by inputting the predicted power demand and the predicted power generation amount by power source into a selected system marginal price prediction model.
In Paragraph 13, A method comprising the step of deriving the predicted power demand based on weather information regarding past weather conditions, past power usage information, and past power demand information by period.
In Paragraph 14, A method comprising the step of deriving the predicted power generation amount, wherein the step of deriving the predicted power generation amount by power source on an hourly basis is based on the predicted power demand amount, the power generation amount by power source, the power generation potential by power source, and the hourly change amount of the predicted power demand amount.
In Paragraph 13, A method comprising the step of selecting one of the above-mentioned system marginal price prediction models, wherein the step of selecting one of the above-mentioned system marginal price prediction models is based on the amount of power generated by each power source, the power generation potential by each power source, the amount of increase or decrease in power load derived by time period, and the type of power source used to determine the system marginal price in the time prior to the time to be predicted.
In Paragraph 13, A method comprising the step of deriving the predicted system marginal price, wherein the step of deriving the predicted system marginal price includes inputting the predicted power demand, the predicted generation amount by power source, and past system marginal prices into a selected system marginal price prediction model to derive the predicted system marginal price for the time to be predicted.
In Paragraph 13, A method comprising the step of deriving the voluntary demand response bid rate, which includes the step of predicting the voluntary demand response bid rate based on the predicted power demand quantity, the predicted system marginal price, and the net benefit threshold of the system marginal price.
A computer program stored on a computer-readable recording medium, comprising instructions for providing a method for predicting a Demand Response bid outcome through the System Marginal Price, When the above computer program is executed by a computing device, Deriving the predicted power demand by forecasting future power demand by time of day, and Based on the above-mentioned predicted power demand, the generation amount by power source, and the generation potential by power source regarding the additional generation possible by power source, the predicted generation amount by power source is derived, and Based on the power generation amount by power source, the power generation potential by power source, and the increase/decrease in power load, one of a plurality of system marginal price prediction models is selected, and A computer program stored on a computer-readable recording medium, comprising instructions to derive a predicted system marginal price by inputting the predicted power demand and the predicted power generation amount by power source into a selected system marginal price prediction model.

Description

Device and Method for Predicting the System Marginal Price The present invention relates to an apparatus and method for predicting the system marginal price for predicting the winning bid of a Demand Response (DR) in the power market. Voluntary Demand Response (DR) is a method of adjusting power supply by reducing electricity demand, and is widely used as a means to stabilize power supply and demand even without operating power generation facilities. In particular, voluntary demand response programs are operated as a system in which electricity consumers voluntarily participate in the electricity market to bid for power reduction, and if their bid is successful, they receive compensation for reducing their electricity usage during the corresponding time period. Voluntary demand response plays a crucial role in balancing power supply and demand in the electricity market. However, a problem arises for both consumers and operators participating in voluntary demand response due to the difficulty of obtaining accurate market information in advance. Currently, market information is generally released the afternoon of the day prior, which creates the challenge of having to bid while lacking the information necessary for decision-making. The System Marginal Price (SMP) refers to the marginal cost of a generator awarded in the electricity market, and it is determined by the market's trading price. The SMP fluctuates according to electricity supply and demand conditions and is determined by the operating status of power sources (nuclear, thermal, LNG, oil, etc.), as well as their fuel costs and efficiency. However, predicting the SMP is a highly complex task that requires forecasting the operating status, fuel costs, and potential generation capacity of each source; in particular, the SMP can vary depending on generator operating patterns and hourly fluctuations in electricity demand. The success of a voluntary demand response bid is closely related to the System Marginal Price, and technology is required to predict the System Marginal Price in advance and, based on this, predict the bid success rate of the voluntary demand response. Although various methods have been proposed in conventional technology to predict the System Marginal Price, it was difficult to accurately predict power demand and the operating status of each power source, and there was a lack of technology to predict in advance whether voluntary demand response bids would be accepted based on this. Figure 1 is a configuration diagram of a system marginal price prediction system according to one embodiment of the present invention. FIG. 2 is a configuration diagram of a system marginal price prediction device according to one embodiment of the present invention. Figure 3 is a diagram illustrating the process of determining the system marginal price. FIG. 4 is a flowchart showing the operation process of the model selection unit according to the present invention. Figure 5 is a diagram showing the structure of a System Marginal Price (SMP) prediction model according to the present invention. FIG. 6 is a flowchart of a system marginal price prediction method according to one embodiment of the present invention. Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals. Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "electrically connected" with other elements interposed between them. Furthermore, when a part is described as "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components, and it should be understood that this does not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware. Some of the operations or functions described in this specification as being performed by a terminal or device may instead be performed by a server connected to said terminal or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal or device connected to said server. The functions r