Virtual Power Plant With Digital Twin Modeling And Artificial Intelligence-based Optimal Pricing And Contract Renewal System

Abstract

The present invention relates to a virtual power plant to which an optimal price determination and contract renewal system based on digital twin modeling and artificial intelligence is applied. More specifically, the invention comprises: an optimal price determination system including a power generation estimation module that estimates the power generation amount of a power source per reference period, a power demand estimation module that estimates the power consumption amount of a power demander, and a price determination module that derives an optimal price by reinforcement-learned artificial intelligence based on power generation and power consumption data estimated from the power generation estimation module and the power demand estimation module, respectively; a power source management module that manages data on real-time energy transactions and history of power sources and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power generation estimation module; a demand source management module that manages data on real-time energy transactions and history of power demanders and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power demand estimation module; and a monitoring module that manages the optimal price determination system, monitors real-time power transactions, and manages their history. A cloud data server module that processes and manages all data regarding power trading input / output from the above monitoring module and provides it to the user;A contract renewal system comprising: a supply-side digital twin modeling module that generates multiple supply-side contract renewal digital twin modules by modeling supply-side contract renewal conditions based on supply-side power supply history data for the entire contract period and maximum / minimum range data calculated therefrom from the cloud data server module; a demand-side digital twin modeling module that generates multiple demand-side contract renewal digital twin modules by modeling demand-side contract renewal conditions based on demand-side power demand or consumption history data for the entire contract period and maximum / minimum range data calculated therefrom from the cloud data server module; and a contract renewal module that combines multiple supply-side contract renewal digital twin modules and demand-side contract renewal digital twin modules to calculate and output contract matching condition ranges by artificial intelligence for each, wherein the power generation estimation module includes multiple supply-side digital twin models that model supply quantities for price based on data regarding estimated power supply and maximum / minimum range data calculated therefrom, and the power demand estimation module includes multiple demand quantities that model demand quantities for price based on data regarding estimated power demand and maximum / minimum range data calculated therefrom The present invention relates to a virtual power plant to which a system for optimal price determination and contract renewal by digital twin modeling and artificial intelligence is applied, wherein the system includes a demand-side digital twin model, and the price determination module determines an optimal price range by artificial intelligence from multiple prices determined by matching the supply and demand quantities for each price derived from multiple supply-side digital twin models and multiple demand-side digital twin models.

Description

Technology Field

[0001] The present invention relates to a virtual power plant to which an optimal price determination and contract renewal system based on digital twin modeling and artificial intelligence is applied. More specifically, the invention comprises: an optimal price determination system including a power generation estimation module that estimates the power generation amount of a power source per reference period, a power demand estimation module that estimates the power consumption amount of a power demander, and a price determination module that derives an optimal price by reinforcement-learned artificial intelligence based on power generation and power consumption data estimated from the power generation estimation module and the power demand estimation module, respectively; a power source management module that manages data on real-time energy transactions and history of power sources and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power generation estimation module; a demand source management module that manages data on real-time energy transactions and history of power demanders and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power demand estimation module; and a monitoring module that manages the optimal price determination system, monitors real-time power transactions, and manages their history. A cloud data server module that processes and manages all data regarding power trading input / output from the above monitoring module and provides it to the user;A contract renewal system comprising: a supply-side digital twin modeling module that generates multiple supply-side contract renewal digital twin modules by modeling supply-side contract renewal conditions based on supply-side power supply history data for the entire contract period and maximum / minimum range data calculated therefrom from the cloud data server module; a demand-side digital twin modeling module that generates multiple demand-side contract renewal digital twin modules by modeling demand-side contract renewal conditions based on demand-side power demand or consumption history data for the entire contract period and maximum / minimum range data calculated therefrom from the cloud data server module; and a contract renewal module that combines multiple supply-side contract renewal digital twin modules and demand-side contract renewal digital twin modules to calculate and output contract matching condition ranges by artificial intelligence for each, wherein the power generation estimation module includes multiple supply-side digital twin models that model supply quantities for price based on data regarding estimated power supply and maximum / minimum range data calculated therefrom, and the power demand estimation module includes multiple demand quantities that model demand quantities for price based on data regarding estimated power demand and maximum / minimum range data calculated therefrom The present invention relates to a virtual power plant to which a system for optimal price determination and contract renewal by digital twin modeling and artificial intelligence is applied, wherein the system includes a demand-side digital twin model, and the price determination module determines an optimal price range by artificial intelligence from multiple prices determined by matching the supply and demand quantities for each price derived from multiple supply-side digital twin models and multiple demand-side digital twin models. Background Technology

[0002] In general, for the operational management of power facilities in a distributed resource operating environment, it is necessary to accurately collect real-time information on each facility; to this end, research and development for the integrated management of distributed resources is being actively conducted.

[0003] Eco-friendly and renewable energy sources such as solar and wind power tend to be distributed, and there is a problem with inconsistent power generation depending on external factors such as weather. As the number of such distributed resources increases, this uncertainty can become more severe. Therefore, the role of a Virtual Power Plant (VPP) (see Fig. 2), which can respond as if it were a single power plant by integrating and managing distributed power generation facilities and electricity demand through software based on the cloud, is becoming important.

[0004] Referring to Figures 1 and 2, in order to build such a virtual power plant, it is necessary to not only collect distributed resources and manage and control them in an integrated manner to ensure a stable power supply, but also to conduct research on a real-time pricing system that can consider the interests of distributed power plants, virtual power plants, and consumers.

[0005] Furthermore, due to the nature of contracts, renewing a contract after the expiration of the previous term requires a process of mutual agreement between the parties. However, since renewing contracts offline or without a dedicated platform is a very cumbersome process, there is an urgent need for platform technology that can analyze data from the previous contract period to reset contract terms and renew the contract in a way that benefits both parties.

[0006] According to the prior art, a registered Korean patent (Title of Invention: System and Method for Integrated Management of Distributed Resources Using a Deep Learning Model, Date of Publication: August 22, 2024), in order to provide a system and method for integrated management of distributed resources using a deep learning model that unifies the communication methods of various distributed resources and conducts communication based on standardized rules, the invention comprises the steps of: receiving data from a plurality of distributed resources in the power generation field; preprocessing the data provided from the plurality of distributed resources and extracting data for managing, operating, and analyzing the plurality of distributed resources; generating a representative component for the extracted data based on a pre-trained first deep learning model; inputting the representative component into a pre-trained second deep learning model to design a unified communication protocol capable of loading data for managing, operating, and analyzing the plurality of distributed resources; and loading the data for managing, operating, and analyzing the plurality of distributed resources into the designed communication protocol and transmitting it to an external device. Accordingly, the present technology focuses on the management of distributed power plants, where the virtual power plant is a distributed resource, and practically, the virtual power plant interacts with the distributed power plant and therewith Not only is there insufficient consideration for the relationship with electricity consumers, but there is also a lack of consideration for real-time prices and contract renewals upon the expiration of the contract period. Therefore, it is now necessary to discuss an AI-based system for determining the optimal price of supplied electricity, a system capable of defining the optimal price range for customer grading, and furthermore, methods or systems for contract renewal. Prior art literature

[0007] Republic of Korea Registered Patent (Title of Invention: System and Method for Integrated Management of Distributed Resources Using a Deep Learning Model, Date of Registration Publication: August 22, 2024) The problem to be solved

[0008] The virtual power plant to which the optimal price determination and contract renewal system based on digital twin modeling and artificial intelligence of the present invention is applied has the following objectives.

[0009] (1) The objective of the present invention is to provide an optimal price determination system by artificial intelligence for distributed power supply power of a commercial virtual power plant, which derives the optimal price by artificial intelligence between the distributed power plant and the power demander in the commercial virtual power plant, thereby allowing for the increase in profit of the distributed power plant, the increase in surplus of the power demander, and the profit of the commercial virtual power plant.

[0010] (2) Another objective of the present invention is to convert the contract conditions and contents between a virtual power plant and a distributed power plant into data or conditions, and based on this, enable the optimal price to be derived by artificial intelligence, thereby allowing mutual understanding between the distributed power plant and the virtual power plant that provide power and providing (current and future) benefits.

[0011] (3) Another objective of the present invention is to provide an optimal price determination system by artificial intelligence of a commercial virtual power plant that can easily calculate the surplus (profit) of consumers (consumers) by utilizing the existing price elasticity of consumers based on the retail price determined by artificial intelligence, and can adjust the surplus of consumers by determining the direction of increase or decrease of the price elasticity of consumers according to mutual interests.

[0012] (4) Another objective of the present invention is to provide a system that can easily increase consumer benefits from short-term units such as hourly and daily units to long-term units such as quarterly and yearly units by inputting the contractual matters determined by the contract with the demander as variables, and to present the optimal power trading price through big data analysis of accumulated energy trading, and to bring about maximum utility that satisfies all parties, such as power supply sources like power generators, commercial virtual power plants, and consumers, by implementing a trading point where consumer surplus and producer surplus are high, and furthermore, to enable contract renewal at the end of the contract by having an artificial intelligence learned to analyze data on power supply and demand between the parties within the entire contract period to set and renew the next contract conditions.

[0013] (5) Another objective of the present invention is to apply a digital twin model that can determine the grade of the counterpart as a contracting party on the supply and demand sides and determine the optimal price range corresponding to the grade. means of solving the problem

[0014] A virtual power plant to which the optimal price determination system by digital twin modeling and artificial intelligence according to the present invention is applied comprises: an optimal price determination system (100) comprising a power generation estimation module (110) that estimates the power generation amount per reference period of a power source, a power demand estimation module (120) that estimates the power consumption amount of a power demander, and a price determination module (130) that derives an optimal price by reinforcement learning artificial intelligence based on power generation and power consumption data estimated from the power generation estimation module and the power demand estimation module, respectively; a power source management module (310) that manages data on real-time energy trading and history of a power source and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power generation estimation module; and a demand source management module (320) that manages data on real-time energy trading and history of a power demander and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power demand estimation module. A cloud data server module (300) that processes and manages all data regarding actual power trading and provides it to the user, and a monitoring module (200) that manages the optimal price determination system (100), monitors real-time power trading, and manages its history; and a plurality of supply side contract renewal digital twin modules (411) that model the supply side contract renewal conditions based on the supply side power supply history data for the entire contract period and the maximum and minimum range data calculated therefrom from the cloud data server module (300). 1,2,3...n A supply-side digital twin modeling module (410) that generates ) and a cloud data server module (300) model the contract renewal conditions of the demand-side based on the power demand or consumption history data of the demand-side during the entire contract period and the maximum and minimum range data calculated therefrom, thereby creating a plurality of demand-side contract renewal digital twin modules (421 1,2,3...nA contract renewal system (400) is configured to include a demand-side digital twin modeling module (420) that generates a demand-side digital twin, and a contract renewal module (430) that combines a plurality of supply-side contract renewal digital twin modules and a demand-side contract renewal digital twin module to calculate and output a contract matching condition range by artificial intelligence.

[0015] The above power generation estimation module (110) has a plurality of supply-side digital twin models (111) that model the supply amount for the price based on data regarding the estimated power generation supply and maximum and minimum range data calculated therefrom. 1,2,3...n ...including ) and the power demand estimation module (120) comprises a plurality of demand-side digital twin models (121) that model the demand for price based on data regarding the estimated power demand and maximum and minimum range data calculated therefrom. 1,2,3...n ...including ), and the price determination module (130) comprises a plurality of supply-side digital twin models (111 1,2,3...n ) and multiple demand-side digital twin models (121 1,2,3...n It is characterized by determining the optimal price range by artificial intelligence from multiple prices determined by matching the supply and demand quantities for each price derived from ).

[0017] The above price determination module (130) is

[0018] Data on the daily to annual supply power volume, type of generation technology, annual capital cost of generation technology, installed capacity of generation technology, and equipment failure rate of each distributed power plant contracted with the aforementioned commercial virtual power plant, as well as data on the daily to annual total supply power volume, total annual capital cost, and total installed capacity for each generation technology of all distributed power plants, are stored and analyzed; wherein a supply curve function for electricity is calculated according to the price elasticity of supply value agreed upon between the contractors, and constraint condition data based on the profit value of the distributed power source and the total profit value within the contract period agreed upon between the contractors are input, calculated, and output.

[0019] For each power source contracted with the above-mentioned commercial virtual power plant, data on power demand on a daily to annual basis and total power demand for all power sources on a daily to annual basis are stored and analyzed; wherein a demand curve function for electricity is calculated according to the price elasticity of demand value and range determined between the contractors, the consumer surplus value and range of the demand source determined between the contractors are calculated, and the data is output.

[0020] It is characterized by having an embedded optimal price determination algorithm that receives each output data as input and determines an optimal price including wholesale and retail prices within the range of constraints set between contractors.

[0021] The above power generation estimation module (110) preferably includes a power generation failure prediction module that predicts and estimates power generation equipment failures.

[0023] The above optimal price determination algorithm is

[0024] A full data input step (S110) for inputting data on the price elasticity of demand for the standard time period, consumer surplus, distributed power source profit, commercial virtual power plant profit, and the amount of change and accumulated value of each value;

[0025] A price determination step by artificial intelligence (S120) in which the price is determined by artificial intelligence learned based on input data;

[0026] A step for determining whether the above-determined price is included within the constraint range (S130);

[0027] A step of calculating and storing various indicators according to the determined price, which calculates the consumer surplus value, distributed power source profit value, commercial virtual power plant profit value, and the amount of change and accumulation of each value based on the above-determined price (S140);

[0028] A step for resetting the price elasticity of demand (S150) to newly set and determine the direction of increase or decrease of the price elasticity of demand based on the above-determined price and calculated data; and

[0029] It consists of a new reference time arrival determination step (S160) that determines whether the next reference time has arrived.

[0030] The step for determining whether the above constraint applies (S130) is

[0031] A step for determining whether the consumer surplus value calculated by the determined retail price falls within a set range (S131);

[0032] A step for determining whether the virtual power plant profit value calculated by the determined retail price falls within the range set by the commercial virtual power plant (S132); and

[0033] It is preferable that this can be classified into a step (S133) for determining whether the distributed power source profit value range corresponds to a value range determined between each distributed power plant that has entered into a contract with a commercial virtual power plant, which determines whether the distributed power source profit value calculated by the determined wholesale price falls within the value range set between them.

[0035] In the step of determining whether the above consumer surplus value range applies, the consumer surplus value range is characterized by being determined by the following formula 1.

[0037] [Formula 1]

[0038]

[0039] A t : A parameter in which the determined retail price is adjusted to the actual observed demand of the power system

[0040] e: Price elasticity of demand

[0041] P t : Retail price set at the relevant standard time

[0043] In the step of determining whether the virtual power plant profit value range applies, the virtual power plant profit value range is characterized by being determined by the following formula 2.

[0045] [Equation 2]

[0046]

[0047] P t : Retail price set at the relevant standard time

[0048] w t : Wholesale price set at the relevant standard time

[0049] A t : A parameter in which the determined retail price is adjusted to the actual observed demand of the power system

[0050] e: Price elasticity of demand

[0052] In the step of determining whether the distributed power source profit value range applies, the distributed power source profit value range is characterized by being determined by the following formula 3.

[0054] [Equation 3]

[0055]

[0056] w t : Wholesale price set at the relevant standard time

[0057] c i : Short-term production costs of distributed power sources

[0058] : Total electricity demand for the corresponding distributed power source at a reference time in the wholesale market (the market formed between distributed power sources and commercial virtual power plants)

[0060] The above contract renewal module (430) is

[0061] After estimating the range of maximum and minimum values ​​of price elasticity of demand for the next contract period by artificial intelligence learned from the average value of parameters in which the retail price determined during the entire contract period input from the supply-side contract renewal digital twin module (411n) is adjusted to match the actual observed demand of the power system, the price elasticity of demand derived for the entire contract period and the total power consumption of the corresponding consumer, the total profit of distributed power sources during the entire contract period, the total profit of virtual power plants, and the total surplus value of consumers, the maximum and minimum values ​​of the demand source surplus are set as new contract conditions and output.

[0062] The above-mentioned demand-side contract renewal digital twin module (421n) receives input of the average value of parameters in which the price determined during the entire contract period is adjusted to match the actual observed demand of the power system, wholesale price fluctuation history data and short-term production cost data of the distributed power source under the contract, and total power demand data for the distributed power source in the wholesale market (a market formed between the distributed power source and the commercial virtual power plant) during the entire contract period, and estimates the range of maximum and minimum values ​​of the price elasticity of power supply from this, and then determines and outputs the estimated total profit amount of the distributed power source during the entire next contract period and the minimum and maximum range of the profit amount of the distributed power source at the reference time.

[0063] It is characterized by receiving each output data as input, estimating and determining the average price elasticity of demand during the next contract period using artificial intelligence via a contract renewal algorithm, and determining and outputting the estimated total profit of the virtual power plant and the maximum and minimum ranges of the virtual power plant profit during the next contract period.

[0065] The above contract renewal algorithm is

[0066] A previous reference time zone data input step in which the average value of parameters for which the determined retail price within the previous contract period is adjusted to the actual observed demand of the power system, the total profit of distributed generation sources within the previous contract period, the total profit of commercial virtual power plants, the total consumer surplus value for power demand sources, and the average value of the price elasticity of demand are input;

[0067] A reference factor data calculation step that calculates the total profit amount of distributed power sources, the total profit amount of commercial virtual power plants, and the total consumer surplus value for power demand sources within the previous contract period, based on the total power consumption value among the data entered in the previous reference time zone data input step;

[0068] A step for determining the price elasticity range by artificial intelligence, which estimates the price elasticity range based on demand using artificial intelligence trained on input and output data;

[0069] A contract condition determination step by AI that determines the maximum and minimum ranges of distributed power source profit, virtual power plant profit, and consumer surplus from the range of price elasticity of demand estimated by AI, feeds back the determined values ​​to the AI-based price elasticity range determination step to reset the range of price elasticity of demand, and repeats this to confirm the maximum and minimum ranges of distributed power source profit and consumer surplus, and determines the range of maximum and minimum profits of the virtual power plant; and

[0070] It consists of a step of presenting the determined contract renewal conditions to the contracting parties via wired or wireless communication to distributed power sources and power consumers.

[0072] It is preferable that the above power source management module (310) and demand source management module (320) have the function of notifying the power supply contractor and power consumption contractor, respectively, of various information of cloud server data (330) using wired or wireless communication. Effects of the invention

[0073] The present invention has the following effects.

[0074] (1) The present invention provides an optimal price determination system by artificial intelligence for distributed power supply power of a commercial virtual power plant, which derives the optimal price by artificial intelligence between the distributed power plant and the power demander in the commercial virtual power plant, thereby allowing for the increase in profit of the distributed power plant, the increase in surplus of the power demander, and the profit of the commercial virtual power plant.

[0075] (2) The present invention converts the contract conditions and contents between a virtual power plant and a distributed power plant into data or conditions, and based on this, enables the optimal price to be derived by artificial intelligence, thereby providing mutual understanding between the distributed power plant and the virtual power plant that provide power and (current and future) benefits.

[0076] (3) The present invention provides an optimal price determination system by artificial intelligence of a commercial virtual power plant that can easily calculate the surplus (profit) of consumers (consumers) by using the existing price elasticity of consumers based on the retail price determined by artificial intelligence, and can adjust the surplus of consumers by determining the direction of increase or decrease of the price elasticity of consumers according to mutual interests.

[0077] (4) The present invention has the advantage of easily increasing consumer benefits from short-term periods such as hourly and daily units to long-term periods such as quarterly and yearly units by inputting the contractual matters determined by the contract with the demander as variables, i.e., contractual matters, and by presenting the optimal power trading price through big data analysis of accumulated energy trading, and by implementing a trading point where consumer surplus and producer surplus are high, it can bring about maximum utility that satisfies all power supply sources such as power generation sources, commercial virtual power plants, and consumers. Furthermore, it provides a system that can set and renew the next contract conditions by having an artificial intelligence learned from the data on power supply and demand between the parties within the entire contract period analyze the data to enable contract renewal at the end of the contract.

[0078] (5) The present invention allows for the determination of a rating for the counterparty as a contracting party on the supply and demand sides by digital twin modeling and the determination of an optimal price range corresponding to the rated rating by artificial intelligence. Brief explanation of the drawing

[0079] Figure 1 is a diagram conceptually illustrating the use of artificial intelligence to advance operational technology for a commercial virtual power plant. Figure 2 is a diagram briefly conceptually illustrating the relationship between a commercial virtual power plant, power suppliers, demanders, and managers. Figure 3 is a simplified conceptual diagram of a virtual power plant to which the optimal price determination and contract renewal system by digital twin modeling and artificial intelligence of the present invention is applied. Figure 4 is a conceptual diagram showing the optimal price determination system by digital twin modeling and artificial intelligence of the virtual power plant according to the present invention, and a cloud data server, etc. Figure 5 is a diagram showing the optimal price determination algorithm embedded in the optimal price determination system by artificial intelligence of the virtual power plant of the present invention in a time series. Figure 6 is a diagram showing the step of determining whether a constraint applies among the optimal price determination algorithms embedded in the optimal price determination system by artificial intelligence of the virtual power plant of the present invention. Figure 7 is a diagram showing the optimal price determination algorithm embedded in the optimal price determination system by artificial intelligence of the virtual power plant of the present invention in a time series. FIG. 8 is a conceptual diagram illustrating the digital twin modeling of a virtual power plant and a contract renewal system by artificial intelligence according to the present invention. Figure 9 illustrates a process of plotting price elasticity curves for supply and demand using data accumulated within the contract standard period, determining the minimum and maximum ranges of price elasticity thereon, and adjusting based on the relationship between the minimum and maximum ranges of profit for distributed power sources, the minimum and maximum ranges of profit for commercial virtual power plants, and the minimum and maximum ranges of surplus for power consumers. Figure 10 is a diagram showing the process of determining contract conditions and renewing contracts by artificial intelligence of the virtual power plant of the present invention in a time series. Specific details for implementing the invention

[0080] First, prior to proceeding with the specific description of the present invention, if it is determined that a detailed description of known technologies or configurations related to the present invention could unnecessarily obscure the essence of the invention, such detailed description is omitted.

[0081] Furthermore, the terms described below are defined considering their functions in the present invention, and since these may vary depending on the intentions or practices of the user or operator, their definitions must be based on the content throughout this specification describing the "virtual power plant to which the optimal price determination and contract renewal system by digital twin modeling and artificial intelligence is applied" according to the present invention.

[0082] The technical terms used in this specification are for the reference of specific embodiments only and are not intended to limit the invention. The singular forms used herein include plural forms unless phrases clearly indicate otherwise.

[0083] As used in this specification, the meaning of “comprising” specifies certain characteristics, regions, integers, steps, actions, elements, and / or components, and does not exclude the existence or addition of other specific characteristics, regions, integers, steps, actions, elements, components, and / or groups.

[0084] All terms used herein, including technical and scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms defined in advance are further interpreted to have meanings consistent with relevant technical literature and the present disclosure, and are not interpreted in an ideal or highly formal sense unless otherwise defined.

[0086] In one aspect, the present invention is characterized in that FIG. 1 is a conceptual diagram illustrating the use of artificial intelligence for the advancement of operational technology for a commercial virtual power plant; FIG. 2 is a simplified conceptual diagram illustrating the relationship between a commercial virtual power plant and power suppliers, demanders, and managers; FIG. 3 is a simplified conceptual diagram of a virtual power plant to which the optimal price determination and contract renewal system by digital twin modeling and artificial intelligence of the present invention is applied; FIG. 4 is a conceptual diagram illustrating the optimal price determination system by digital twin modeling and artificial intelligence of the virtual power plant and the cloud data server, etc. of the present invention; FIG. 5 is a diagram illustrating the optimal price determination algorithm embedded in the optimal price determination system by artificial intelligence of the virtual power plant of the present invention in a time series; FIG. 6 is a diagram illustrating the step of determining whether constraint conditions apply among the optimal price determination algorithm embedded in the optimal price determination system by artificial intelligence of the virtual power plant of the present invention; FIG. 7 is a diagram illustrating the optimal price determination algorithm embedded in the optimal price determination system by artificial intelligence of the virtual power plant of the present invention in a time series; and FIG. 8 is a diagram illustrating the digital twin modeling and Figure 9 is a diagram conceptually illustrating a contract renewal system by artificial intelligence, and Figure 9 illustrates a process of plotting price elasticity curves for supply and demand using data accumulated within the contract standard period, determining the minimum and maximum ranges of price elasticity thereon, and adjusting the relationship between the minimum and maximum ranges of profit for distributed power sources, the minimum and maximum ranges of profit for commercial virtual power plants, and the minimum and maximum ranges of surplus for power consumers. Figure 10 is a diagram chronologically illustrating the process of determining contract conditions and renewing contracts by artificial intelligence of the virtual power plant according to the present invention.

[0088] The Virtual Power Plant (VPP) in this invention refers to a commercial virtual power plant capable of generating revenue by providing power with mitigated variability to the market, that is, a virtual power plant that makes a profit by purchasing electricity from distributed power sources at wholesale prices and selling it to demand centers at retail prices; however, the composition, operation, and the invention as a whole can also be applied to a virtual power plant that purchases electricity from distributed power sources and sells it to demand centers through an intermediary.

[0089] Virtual power plants play a major role in integrated energy monitoring, ESS-based energy control, power trading support, and power market support, such as power generation and demand forecasting, energy trading, energy operation scheduling, automatic control of energy flow, energy rate analysis, and energy trading settlement.

[0091] Referring to FIG. 3, the virtual power plant to which the optimal price determination system by digital twin modeling and artificial intelligence according to the present invention is applied comprises: an optimal price determination system (100) comprising a power generation estimation module (110) that estimates the power generation amount per reference period of a power source, a power demand estimation module (120) that estimates the power consumption amount of a power demand source, and a price determination module (130) that derives an optimal price by reinforcement learning artificial intelligence based on power generation and power consumption data estimated from the power generation estimation module and the power demand estimation module, respectively; a power source management module (310) that manages data on real-time energy trading and history of a power source and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power generation estimation module; and a demand source management module (320) that manages data on real-time energy trading and history of a power demand source and calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power demand estimation module. A cloud data server module (300) that processes and manages all data regarding actual power trading and provides it to the user, and a monitoring module (200) that manages the optimal price determination system (100), monitors real-time power trading, and manages its history; and a plurality of supply side contract renewal digital twin modules (411) that model the supply side contract renewal conditions based on the supply side power supply history data for the entire contract period and the maximum and minimum range data calculated therefrom from the cloud data server module (300). 1,2,3...n A supply-side digital twin modeling module (410) that generates ) and a cloud data server module (300) model the contract renewal conditions of the demand-side based on the power demand or consumption history data of the demand-side during the entire contract period and the maximum and minimum range data calculated therefrom, thereby creating a plurality of demand-side contract renewal digital twin modules (421 1,2,3...nA contract renewal system (400) is configured to include a demand-side digital twin modeling module (420) that generates a demand-side digital twin, and a contract renewal module (430) that combines a plurality of supply-side contract renewal digital twin modules and a demand-side contract renewal digital twin module to calculate and output a contract matching condition range by artificial intelligence.

[0092] Referring to FIGS. 3 and 4, the power generation estimation module (110) has a plurality of supply-side digital twin models (111) that model the supply amount for the price based on data regarding the estimated power generation supply and maximum and minimum range data calculated therefrom. 1,2,3...n ...including ) and the power demand estimation module (120) comprises a plurality of demand-side digital twin models (121) that model the demand for price based on data regarding the estimated power demand and maximum and minimum range data calculated therefrom. 1,2,3...n ...including ), and the price determination module (130) comprises a plurality of supply-side digital twin models (111 1,2,3...n ) and multiple demand-side digital twin models (121 1,2,3...n It is characterized by determining the optimal price range by artificial intelligence from multiple prices determined by matching the supply and demand quantities for each price derived from ).

[0094] The supply-side digital twin model and the demand-side digital twin model model the supply and demand curves for a specific electricity price, respectively, based on parameters provided by the supply and demand sides. This is not learned by artificial intelligence but uses various mathematical estimation methods.

[0096] A single supply-side digital twin model and a single demand-side digital twin model each derive a supply curve and a demand curve for electricity prices, and an AI-based pricing module combines the derived multiple supply and demand curves to determine the optimal price range. This is intended not to treat the parties on the supply and demand sides uniformly, but rather to provide optimal prices to graded parties.

[0097] In other words, the purpose is to provide more favorable pricing conditions to contracting parties who have been under contract for several years rather than to the initial contracting party; therefore, instead of determining a single optimal price, multiple determined prices are decided by reinforcement-learned artificial intelligence to provide a specific price to a specific party.

[0098] The supply-side contract renewal digital twin module and the demand-side contract renewal digital twin module also use historical data from the entire period as parameters to determine the optimal range of contract conditions. Instead of deriving a single contract condition between each contracting party, they limit the range of contract conditions to a number of combinations corresponding to the number of supply-side contract renewal digital twin modules and demand-side contract renewal digital twin modules, and then proceed to the step of redefining the optimal range of contract conditions from that range.

[0100] Referring to FIGS. 3 and 4, the price determination module (130)

[0101] Data on the daily to annual supply power volume, type of generation technology, annual capital cost of generation technology, installed capacity of generation technology, and equipment failure rate of each distributed power plant contracted with the aforementioned commercial virtual power plant, as well as data on the daily to annual total supply power volume, total annual capital cost, and total installed capacity for each generation technology of all distributed power plants, are stored and analyzed; wherein a supply curve function for electricity is calculated according to the price elasticity of supply value agreed upon between the contractors, and constraint condition data based on the profit value of the distributed power source and the total profit value within the contract period agreed upon between the contractors are input, calculated, and output.

[0102] For each power source contracted with the above-mentioned commercial virtual power plant, data on power demand on a daily to annual basis and total power demand for all power sources on a daily to annual basis are stored and analyzed; wherein a demand curve function for electricity is calculated according to the price elasticity of demand value and range determined between the contractors, the consumer surplus value and range of the demand source determined between the contractors are calculated, and the data is output.

[0103] It is characterized by having an embedded optimal price determination algorithm that receives each output data as input and determines an optimal price including wholesale and retail prices within the range of constraints set between contractors.

[0105] The price elasticity of supply in the distributed generation power data module (110) is a value indicating how sensitively a distributed generation power supplier responds to fluctuations in power prices, and represents the change in the ratio of the power supplier's generated power when the power price changes. It is not determined immediately in the short term, such as one hour or one day, but is usually determined on a quarterly or one-year basis. However, the change may occur under certain conditions such as contract renewal, environmental changes, or the occurrence of reasons for contractual change. This is not a concept determined by calculation as in economics, but rather the direction of the change, that is, a certain limit line, is set by policy, and the increase or decrease can be determined within that range. This corresponds to a conceptual dependent variable rather than an independent variable in the present invention.

[0107] The above power generation estimation module (110) preferably includes a power generation failure prediction module that predicts and estimates power generation equipment failures.

[0109] Referring to FIGS. 5 to 7, the optimal price determination algorithm is

[0110] A full data input step (S110) for inputting data on the price elasticity of demand for the standard time period, consumer surplus, distributed power source profit, commercial virtual power plant profit, and the amount of change and accumulated value of each value;

[0111] A price determination step by artificial intelligence (S120) in which the price is determined by artificial intelligence learned based on input data;

[0112] A step for determining whether the above-determined price is included within the constraint range (S130);

[0113] A step of calculating and storing various indicators according to the determined price, which calculates the consumer surplus value, distributed power source profit value, commercial virtual power plant profit value, and the amount of change and accumulation of each value based on the above-determined price (S140);

[0114] A step for resetting the price elasticity of demand (S150) to newly set and determine the direction of increase or decrease of the price elasticity of demand based on the above-determined price and calculated data; and

[0115] It consists of a new reference time arrival determination step (S160) that determines whether the next reference time has arrived.

[0116] In the process of determining the price by an artificial intelligence (reinforced) based on input data such as the price elasticity of demand for the entire reference time period, consumer surplus, profit value of distributed power sources, profit value of commercial virtual power plants, and the change and accumulation values ​​of each value during the entire data input stage, the price elasticity of demand for the entire reference time period may be a reset value, or it may be utilized as is by bypassing the reset process. When the amount of power supplied from distributed power sources is input, the price is determined according to the demand curve based on the price elasticity of demand. At this time, the price is temporarily determined by the artificial intelligence reinforced, including both the wholesale price at which power is acquired from distributed power sources and the retail price at which power is sold to consumers by adding the profit of commercial virtual power plants from this. When all of the following constraint determination steps (S30) are satisfied, the determined price is finalized.

[0117] According to the above-mentioned determined price, the consumer surplus value, distributed power source profit value, commercial virtual power plant profit value, and the change amount and accumulated value of each value are calculated and stored based on the price determined in the various indicator calculation and storage step (S40), and this becomes a part of the big data that artificial intelligence will utilize in the future.

[0119] The above-mentioned price elasticity of demand reset step (S50) corresponds to an institutional and technical mechanism that allows i) to be changed according to the policy direction of the upper organization of the commercial virtual power plant, ii) to be changed if necessary for the achievement of the contract between the contracting parties, and iii) to derive the optimal price by identifying the power consumption pattern of the power consumer using the P&O (Purtube & Observe) algorithm.

[0121] Referring to FIGS. 6 and 7, the step (S130) for determining whether the above constraint applies is

[0122] A step for determining whether the consumer surplus value calculated by the determined retail price falls within a set range (S131);

[0123] A step for determining whether the virtual power plant profit value calculated by the determined retail price falls within the range set by the commercial virtual power plant (S132); and

[0124] It is preferable that this can be classified into a step (S133) for determining whether the distributed power source profit value range corresponds to a value range determined between each distributed power plant that has entered into a contract with a commercial virtual power plant, which determines whether the distributed power source profit value calculated by the determined wholesale price falls within the value range set between them.

[0126] The function representing total market demand when the price is Pt at time t is defined by the following formula.

[0127]

[0128] A t : A parameter where the determined price is adjusted to match the actual observed demand of the power system

[0129] e : Price elasticity of demand (e≤0)

[0131] In the step of determining whether the above consumer surplus value range applies, the consumer surplus value range is characterized by being determined by the following formula 1.

[0133] [Formula 1]

[0134]

[0135] A t : A parameter in which the determined retail price is adjusted to the actual observed demand of the power system

[0136] e: Price elasticity of demand

[0137] P t : Retail price set at the relevant standard time

[0139] In the step of determining whether the virtual power plant profit value range applies, the virtual power plant profit value range is characterized by being determined by the following formula 2.

[0141] [Equation 2]

[0142]

[0143] P t : Retail price set at the relevant standard time

[0144] w t : Wholesale price set at the relevant standard time

[0145] A t : A parameter in which the determined retail price is adjusted to the actual observed demand of the power system

[0146] e: Price elasticity of demand

[0148] In the step of determining whether the distributed power source profit value range applies, the distributed power source profit value range is characterized by being determined by the following formula 3.

[0150] [Equation 3]

[0151]

[0152] w t : Wholesale price set at the relevant standard time

[0153] c i : Short-term production costs of distributed power sources

[0154] : Total electricity demand for the corresponding distributed power source at a reference time in the wholesale market (the market formed between distributed power sources and commercial virtual power plants)

[0156] The distributed generation source profit value determined between the contractors is determined in relation to price determination and is determined by the following Formula 4.

[0157] [Equation 4]

[0158]

[0159] i : Types of power generation technology

[0160] w t : Wholesale price of supplied electricity

[0161] c i : Short-term production costs incurred for the supplied power

[0162] : Total electricity demand for the corresponding distributed power source at a reference time in the wholesale market (the market formed between distributed power sources and commercial virtual power plants)

[0164] In addition, the total profit value within the contract period is determined by the following formula 5.

[0165] [Formula 5]

[0166]

[0167] T : Contract period

[0168] w T : Wholesale price of supplied electricity

[0169] c i : Production costs incurred within the contract period for the supplied electricity

[0170] r i : Annual capital cost of distributed power sources for power generation technology i

[0171] K i : Installed capacity of distributed power sources for power generation technology i

[0173] The above distributed power source profit value and the total profit value within the contract period correspond to contractual matters concluded between the distributed power source operator and the commercial virtual power plant operator in the present invention.

[0174] The price elasticity value for demand of the above-mentioned power demand source data module (130) represents the change in the ratio of the amount of power demanded or consumed by power consumers to the change in the power price (retail price), and affects the consumer surplus value below.

[0175] The consumer surplus value and range of demand sources determined between the contractors are determined by the following formulas 6 and 7.

[0176] [Equation 6]

[0177]

[0178] [Equation 7]

[0179]

[0181] A t : A parameter in which the determined retail price is adjusted to the actual observed demand of the power system

[0182] e: Price elasticity of demand

[0183] P t : Retail price set at the relevant standard time

[0185] Referring to Figure 9, the price elasticity of demand is a concept that can be calculated in both the short and long term. Since it can be determined or calculated for specific consumers in both the short and long term, it serves as important data for consumers to identify trends or patterns in electricity consumption that change according to fluctuations in electricity supply prices. The accumulation of such data enables artificial intelligence to predict electricity consumption and the amount of electricity consumed based on the price elasticity of electricity consumption in the long term, and from this, it becomes a foundation for determining the optimal price that can bring mutual benefits to the electricity supplier and the electricity consumer.

[0186] The surplus value and total amount of the aforementioned demanders or consumers are concepts that must be reduced for policy purposes to reduce electricity consumption, and in this sense, it is desirable to reset the price elasticity of demand at every reference time.

[0188] The artificial intelligence in the optimal price determination module based on the above artificial intelligence is based on general reinforcement learning and is not attributed to any special or novel technical features of artificial intelligence itself. It performs the roles of collecting, storing, processing, managing, and analyzing data regarding power trading, distributed power sources, and various variables of demand centers based on existing reinforcement learning methods, and contributes to the purpose, structure, and effects of the present invention as a whole through combination with other inventive components.

[0190] Referring to FIG. 8, the contract renewal module (430) is

[0191] After estimating the range of maximum and minimum values ​​of price elasticity of demand for the next contract period by artificial intelligence learned from the average value of parameters in which the retail price determined during the entire contract period input from the supply-side contract renewal digital twin module (411n) is adjusted to match the actual observed demand of the power system, the price elasticity of demand derived for the entire contract period and the total power consumption of the corresponding consumer, the total profit of distributed power sources during the entire contract period, the total profit of virtual power plants, and the total surplus value of consumers, the maximum and minimum values ​​of the demand source surplus are set as new contract conditions and output.

[0192] The above-mentioned demand-side contract renewal digital twin module (421n) receives input of the average value of parameters in which the price determined during the entire contract period is adjusted to match the actual observed demand of the power system, wholesale price fluctuation history data and short-term production cost data of the distributed power source under the contract, and total power demand data for the distributed power source in the wholesale market (a market formed between the distributed power source and the commercial virtual power plant) during the entire contract period, and estimates the range of maximum and minimum values ​​of the price elasticity of power supply from this, and then determines and outputs the estimated total profit amount of the distributed power source during the entire next contract period and the minimum and maximum range of the profit amount of the distributed power source at the reference time.

[0193] It is characterized by receiving each output data as input, estimating and determining the average price elasticity of demand during the next contract period using artificial intelligence via a contract renewal algorithm, and determining and outputting the estimated total profit of the virtual power plant and the maximum and minimum ranges of the virtual power plant profit during the next contract period.

[0195] Referring to Fig. 10, the above contract renewal algorithm is

[0196] A previous reference time zone data input step (S210) in which the average value of parameters for which the retail price determined within the previous contract period is adjusted to the actual observed demand of the power system, the total profit amount of distributed power sources within the previous contract period, the total profit amount of commercial virtual power plants, the total consumer surplus value for power demand sources, and the average value of price elasticity for demand are input;

[0197] A reference factor data calculation step (S220) for calculating the total profit amount of distributed power sources, the total profit amount of commercial virtual power plants, and the total consumer surplus value for power demand sources within the previous contract period among the data entered in the previous reference time zone data input step, based on the total power consumption value;

[0198] A step for determining the price elasticity range by artificial intelligence, which estimates the price elasticity range based on demand using artificial intelligence trained on input and output data;

[0199] A contract condition determination step (S230) by AI that determines the maximum and minimum ranges of distributed power source profit, virtual power plant profit, and consumer surplus value from the range of price elasticity of demand estimated by AI, feeds back the determined values ​​to the step of determining the range of price elasticity of demand by AI to reset the range of price elasticity of demand, and repeats this to confirm the maximum and minimum range of distributed power source profit and consumer surplus value, and determines the range of maximum and minimum profit of the virtual power plant; and

[0200] It consists of a step (S240) of presenting the determined contract renewal conditions to the contracting parties via wired or wireless communication to the distributed power generation source and the power consumer.

[0202] The important conditions that constitute the content of the following contract are, for the distributed power source, the range of total profit within the next contract period of the distributed power source, and the minimum and maximum range of profit within the reference time when prices are determined in real time; for the power demand source, the total amount of the demander's surplus and the range of minimum and maximum values ​​of the demander's surplus within the reference time; and for the commercial virtual power plant, the range of total profit during the contract period and the minimum and maximum range of profit during the reference time for price determination.

[0204] Referring to FIG. 10, there is a mutual feedback relationship between the step of determining the price elasticity range by artificial intelligence (S230) and the step of determining contract conditions by artificial intelligence (S240). If the minimum and maximum range interval of the contract conditions to be determined is shortened, the predictability regarding it increases, thereby increasing the likelihood of the contract parties being able to form a contract. However, if the interval is excessively wide, the predictability decreases relatively. Therefore, it is necessary to reasonably determine the minimum and maximum range interval, and this condition must be input by the user.

[0206] Referring to Fig. 9, the figure illustrates a process of plotting price elasticity curves for supply and demand using data accumulated within the contract standard period, determining the minimum and maximum ranges of price elasticity thereon, and adjusting the relationship between the minimum and maximum ranges of profit for distributed power sources, the minimum and maximum ranges of profit for commercial virtual power plants, and the minimum and maximum ranges of surplus for power consumers. It conceptually represents the mutual feedback process between the stage of determining the price elasticity range due to demand and the stage of determining contract conditions by artificial intelligence. Once the range of price elasticity due to demand is determined, the minimum and maximum ranges of profit for distributed power sources, power consumers, and virtual power plants can be determined by the learned artificial intelligence.

[0208] The present invention has the following effects.

[0209] (1) The present invention provides an optimal price determination system by artificial intelligence for distributed power supply power of a commercial virtual power plant, which derives the optimal price by artificial intelligence between the distributed power plant and the power demander in the commercial virtual power plant, thereby allowing for the increase in profit of the distributed power plant, the increase in surplus of the power demander, and the profit of the commercial virtual power plant.

[0210] (2) The present invention converts the contract conditions and contents between a virtual power plant and a distributed power plant into data or conditions, and based on this, enables the optimal price to be derived by artificial intelligence, thereby providing mutual understanding between the distributed power plant and the virtual power plant that provide power and (current and future) benefits.

[0211] (3) The present invention provides an optimal price determination system by artificial intelligence of a commercial virtual power plant that can easily calculate the surplus (profit) of consumers (consumers) by using the existing price elasticity of consumers based on the retail price determined by artificial intelligence, and can adjust the surplus of consumers by determining the direction of increase or decrease of the price elasticity of consumers according to mutual interests.

[0212] (4) The present invention has the advantage of easily increasing consumer benefits from short-term periods such as hourly and daily units to long-term periods such as quarterly and yearly units by inputting the contractual matters determined by the contract with the demander as variables, i.e., contractual matters, and by presenting the optimal power trading price through big data analysis of accumulated energy trading, and by implementing a trading point where consumer surplus and producer surplus are high, it can bring about maximum utility that satisfies all power supply sources such as power generation sources, commercial virtual power plants, and consumers. Furthermore, it provides a system that can set and renew the next contract conditions by having an artificial intelligence learned from the data on power supply and demand between the parties within the entire contract period analyze the data to enable contract renewal at the end of the contract.

[0213] (5) The present invention allows for the determination of a rating for the counterparty as a contracting party on the supply and demand sides by digital twin modeling and the determination of an optimal price range corresponding to the rated rating by artificial intelligence. Explanation of the symbols

[0215] 100: Optimal Pricing System 110: Power generation estimation module 1111,2,3...n Supply-side digital twin model 1,2,3...n 120: Power Demand Estimation Module 121 1,2,3...n Supply-side digital twin model 1,2,3...n 130: AI Pricing Module 200: Monitoring Module 300: Cloud Data Server Module 310: Power source management module 320 : Demand Source Management Module 400: Contract Renewal System 410: Supply-side digital twin modeling module 411 1,2,3...n : Supplier Contract Renewal Digital Twin Module 1,2,3...n 420: Demand-side digital twin modeling module 421 1,2,3...n Demand-side contract renewal digital twin module 1,2,3...n 430: Contract Renewal Module S110: Full data input step S120: AI-driven pricing stage S130: Step to determine whether constraints apply S131: Step to determine whether the consumer surplus value falls within the range S132: Step to determine whether the virtual power plant profit value falls within the range S133: Step to determine whether the distributed power source profit value falls within the range S140: Step for calculating and storing various indicators based on the determined price S150: Resetting the price elasticity of demand step S160: Step to determine whether the new reference time has arrived S210: Data input step for the previous reference time zone S220: Calculation step for standard factor data per total power consumption S230: Step of determining the price elasticity of demand range by artificial intelligence S240: Contract terms determination stage by artificial intelligence S250: Stage of presenting contract renewal conditions to the contracting parties

Claims

Claim 1 An optimal price determination system comprising: a power generation estimation module that estimates the power generation amount per reference period of a power source; a power demand estimation module that estimates the power consumption amount of a power demander; and a price determination module that derives an optimal price by reinforcement-learned artificial intelligence based on power generation and power consumption data estimated respectively from the power generation estimation module and the power demand estimation module; a power source management module that manages data on real-time energy transactions and their history of power sources, calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power generation estimation module; a demand source management module that manages data on real-time energy transactions and their history of power demanders, calculates a parameter value that compensates for the difference between the price determined by the optimal price determination system and the actual transaction price, and outputs it to the power demand estimation module; a monitoring module that manages the optimal price determination system, monitors real-time power transactions, and manages their history; and a cloud data server module that processes and manages all data regarding power transactions input and output from the monitoring module and provides it to a user. A contract renewal system comprising: a supply-side digital twin modeling module that generates a plurality of supply-side contract renewal digital twin modules by modeling the supply-side contract renewal conditions based on the supply-side power supply history data for the entire contract period and the maximum / minimum range data calculated therefrom from the cloud data server module; a demand-side digital twin modeling module that generates a plurality of demand-side contract renewal digital twin modules by modeling the demand-side contract renewal conditions based on the demand-side power demand or consumption history data for the entire contract period and the maximum / minimum range data calculated therefrom from the cloud data server module; and a contract renewal module that combines the plurality of supply-side contract renewal digital twin modules and the demand-side contract renewal digital twin modules to calculate and output the contract matching condition range by artificial intelligence for each.A virtual power plant to which a system for optimal price determination and contract renewal by digital twin modeling and artificial intelligence is applied, comprising: a power generation estimation module including a plurality of supply-side digital twin models that model the supply quantity for price based on data regarding the estimated power supply and maximum / minimum range data calculated therefrom; a power demand estimation module including a plurality of demand-side digital twin models that model the demand quantity for price based on data regarding the estimated power demand and maximum / minimum range data calculated therefrom; and a price determination module characterized by determining an optimal price range by artificial intelligence from a plurality of prices determined by matching the supply quantity and demand quantity for each price derived from the plurality of supply-side digital twin models and the plurality of demand-side digital twin models. Claim 2 In claim 1, the price determination module stores and analyzes data on the daily to annual supply of electricity, type of power generation technology, annual capital cost of power generation technology, installed capacity of power generation technology, and installed failure rate of each distributed power plant contracted with the virtual power plant, as well as data on the daily to annual total supply of electricity, total annual capital cost, and total installed capacity of each distributed power plant by power generation technology, wherein it calculates a supply curve function for electricity according to the price elasticity of supply determined between the contractors, inputs and calculates constraint condition data based on the profit value of the distributed power source determined between the contractors and the total profit value within the contract period, and outputs the result; wherein it stores and analyzes data on the daily to annual electricity demand for each power demand source contracted with the virtual power plant and the total electricity demand for all power demand sources, wherein it calculates a demand curve function for electricity according to the price elasticity of demand determined between the contractors and the range thereof, and the contractor A virtual power plant with an optimal price determination and contract renewal system based on digital twin modeling and artificial intelligence, characterized by having an embedded optimal price determination algorithm that calculates the consumer surplus value and range of mutually determined demand sources, outputs data, and receives each output data to determine an optimal price including wholesale and retail prices within the range of constraints set between contractors. Claim 3 In claim 1, the contract renewal module estimates the range of maximum and minimum values ​​of price elasticity due to demand for the next contract period by means of artificial intelligence learned from the average value of parameters in which the retail price determined during the entire contract period input from the supply-side contract renewal digital twin module is adjusted to match the actual observed demand of the power system, the price elasticity of demand derived for the entire contract period and the total power consumption of the relevant consumer, the total profit of the distributed power source during the entire contract period, the total profit of the virtual power plant, and the total surplus value data of the consumer, and then sets the maximum and minimum values ​​of the demand source surplus as new contract conditions and outputs them; and receives input from the demand-side contract renewal digital twin module the average value of parameters in which the price determined during the entire contract period is adjusted to match the actual observed demand of the power system, wholesale price fluctuation history data and short-term production cost data of the distributed power source under the entire contract, and total power demand data for the relevant distributed power source in the wholesale market (a market formed between the distributed power source and the commercial virtual power plant) during the entire contract period, and thereby determines the range of maximum and minimum values ​​of price elasticity of power supply A virtual power plant to which a digital twin modeling and artificial intelligence-based optimal price determination and contract renewal system is applied, characterized by estimating and then determining and outputting the minimum and maximum ranges of the estimated total profit of the distributed power source during the entire next contract period and the profit of the distributed power source at the reference time, receiving each output data as input, estimating and determining the average value of the price elasticity of demand during the next contract period by artificial intelligence through a contract renewal algorithm, and determining and outputting the maximum and minimum ranges of the estimated total profit of the virtual power plant and the profit of the virtual power plant during the next contract period. Claim 4 A virtual power plant to which an optimal price determination and contract renewal system by digital twin modeling and artificial intelligence is applied, wherein the power generation estimation module includes a power generation failure prediction module that predicts and estimates power generation equipment failures in accordance with claim 1. Claim 5 A virtual power plant to which a digital twin modeling and artificial intelligence-based optimal price determination and contract renewal system is applied, wherein the optimal price determination algorithm comprises: a data input step for inputting data regarding the price elasticity of demand for the previous reference time period, consumer surplus value, distributed power source profit value, commercial virtual power plant profit value, and the change amount and accumulated value of each value; a price determination step by artificial intelligence for determining the price by an artificial intelligence learned based on the input data; a constraint compliance determination step for determining whether the determined price is included within the constraint range; a step of calculating and storing various indicators according to the determined price by calculating the consumer surplus value, distributed power source profit value, commercial virtual power plant profit value, and the change amount and accumulated value of each value based on the determined price; a price elasticity of demand resetting step for newly setting and determining the direction of increase or decrease of the price elasticity of demand based on the determined price and the calculated data; and a new reference time arrival determination step for determining whether the next reference time has arrived. Claim 6 A virtual power plant to which an optimal price determination and contract renewal system by digital twin modeling and artificial intelligence is applied, wherein the step for determining whether the constraint applies is classified into: a step for determining whether the consumer surplus value calculated by the determined retail price is within a set range; a step for determining whether the virtual power plant profit value calculated by the determined retail price is within a range set by the commercial virtual power plant; and a step for determining whether the distributed power source profit value calculated by the determined wholesale price is within a value range determined between each distributed power plant that has entered into a contract with the commercial virtual power plant. Claim 7 A virtual power plant to which an optimal price determination and contract renewal system based on digital twin modeling and artificial intelligence is applied, characterized in that, in the step of determining whether the consumer surplus value range applies, the consumer surplus value range is determined by the following Formula 1; in the step of determining whether the virtual power plant profit value range applies, the virtual power plant profit value range is determined by the following Formula 2; and in the step of determining whether the distributed power source profit value range applies, the distributed power source profit value range is determined by the following Formula 3. [Formula 1] A t : Parameter e where the determined retail price is adjusted to the actual observed demand of the power system : Price elasticity of demand P t : Retail price set at the corresponding standard time [Formula 2] P t : Retail price set at the relevant standard time w t : Wholesale price A set at the relevant standard time t : Parameter where the determined retail price is adjusted to the actual observed demand of the power system e : Price elasticity of demand [Equation 3] w t : Wholesale price c set at the corresponding standard time i : Short-term production costs of distributed power sources : Total electricity demand for the corresponding distributed power source at a reference time in the wholesale market (the market formed between distributed power sources and commercial virtual power plants) Claim 8 In claim 3, the contract renewal algorithm comprises: a previous reference time zone data input step in which the average value of parameters for which the retail price determined within the previous contract period is adjusted to match the actual observed demand of the power system, the total profit of distributed power sources within the previous contract period, the total profit of commercial virtual power plants, the total consumer surplus value for power demanders, and the average value of price elasticity for demand are input; a reference factor data calculation step in which the total profit of distributed power sources within the previous contract period, the total profit of commercial virtual power plants, and the total consumer surplus value for power demanders among the data input in the previous reference time zone data input step are calculated based on the total power consumption value; a price elasticity range determination step by artificial intelligence in which the range of price elasticity due to demand is estimated by artificial intelligence learned based on the input and calculated output data; and the maximum and minimum ranges of the profit of distributed power sources, the profit of virtual power plants, and the consumer surplus value are determined from the price elasticity due to demand range estimated by artificial intelligence, and the determined values ​​are fed back to the price elasticity range determination step by artificial intelligence. A virtual power plant to which an optimal price determination and contract renewal system by digital twin modeling and artificial intelligence is applied, characterized by comprising: a contract condition determination step by artificial intelligence that resets the price elasticity range based on demand and repeats this to determine the maximum and minimum range of profit for distributed power sources and the maximum and minimum range of consumer surplus values, and determines the maximum and minimum profit range for virtual power plants; and a step of presenting the determined contract renewal conditions to contract parties via wired or wireless communication to present the determined contract renewal conditions to distributed power sources and power consumers. Claim 9 A virtual power plant to which an optimal price determination and contract renewal system based on digital twin modeling and artificial intelligence is applied, wherein, in claim 1, the power source management module and the demand source management module each have the function of notifying the power supply contractor and the power consumption contractor, respectively, of various information of cloud server data using wired or wireless communication.

Images