A step hydropower medium and long term contract decomposition method and system considering multi-source information uncertainty
By generating typical scenarios for hydropower station and CCER prices, and combining power load data and carbon market constraints, the decomposition of medium- and long-term contracts for cascade hydropower was optimized, which solved the uncertainty problem in the connection between the medium- and long-term market and the spot market, and improved market stability and returns.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUAZHONG UNIV OF SCI & TECH
- Filing Date
- 2026-03-05
- Publication Date
- 2026-06-23
AI Technical Summary
Existing technologies, in the process of linking the medium- and long-term market and the spot market, have neglected the impact of the carbon market on power generation companies and lack effective consideration of uncertainties from multiple sources of information. This has led to inaccurate methods for decomposing medium- and long-term contracts, as well as insufficient market stability and returns.
We use Latin hypercube sampling and K-means clustering to generate typical scenarios of hydropower generation data and CCER prices. Combined with power load data, we estimate the clearing price and establish a decomposition optimization model for medium- and long-term contracts of cascade hydropower. With the goal of maximizing expected returns in the spot market, we consider hydropower, power generation capacity and CCER trading constraints to solve for the optimal contract power decomposition curve.
It improves the expected returns of cascade hydropower in the electricity spot market under a multi-market environment, enhances market stability and overall returns, and optimizes the contract decomposition process by taking into account the uncertainty of multi-source information and carbon market prices.
Smart Images
Figure CN122267776A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of power dispatching technology, specifically relating to a method and system for decomposing medium- and long-term contracts for cascade hydropower projects that considers the uncertainty of multi-source information. Background Technology
[0002] As the "ballast" of the electricity market, medium- and long-term trading is not only an important prerequisite and foundation for spot market trading, but also a key mechanism supporting the overall development of the electricity market. The development of the electricity market is a core link in economic transformation and energy revolution, with its core objective being to build a clean, low-carbon, safe, and efficient modern energy system, achieve optimal resource allocation, and ensure energy security. This process has undergone a profound transformation from a highly centralized planning and management system to a market-oriented mechanism. Since the launch of a new round of electricity market reform in 2015, the medium- and long-term market has continuously explored and innovated to supplement and accelerate the construction of the electricity spot market. One key measure is encouraging market participants to submit bidding strategies with hourly bidding curves or to break down trading contracts, aiming to promote effective connections between the medium- and long-term market and the spot market. Furthermore, with the launch of the national carbon market in 2021 and the expansion of its industry coverage by 2025, the carbon market has become an indispensable factor for power generation companies when formulating power generation plans and market transactions. Although the carbon market and the electricity market operate independently, the power generation industry is the first and currently the only industry included in the national carbon market, thus power generation companies participating in both markets closely link the electricity market and the carbon market. Therefore, with the continuous development and coupling of the electricity market and the carbon market, greater challenges have been brought to market participants' participation in multi-scale, multi-market transactions and the decomposition of medium- and long-term contract curves.
[0003] Many existing studies have extensively investigated the interaction between the medium- and long-term markets and the spot market. Some studies focus on the impact of medium- and long-term contract decomposition on the spot market. However, most studies only consider the decision-making methods of power generation companies in the electricity market, neglecting the impact of the carbon market on the transition between the medium- and long-term markets and the spot market, and lacking research on the decomposition methods of power generation companies in an electricity-carbon coupled market environment. Summary of the Invention
[0004] The purpose of this invention is to provide a method and system for decomposing medium- and long-term contracts for cascade hydropower that takes into account the uncertainty of multi-source information, thereby improving the expected returns of cascade hydropower in the electricity spot market under multi-market environments and enhancing market stability.
[0005] To achieve the above objectives, this invention provides a method for decomposing medium- and long-term contracts for cascade hydropower projects that considers the uncertainty of multi-source information, comprising the following steps: S1. Collect raw power generation data of cascade hydropower stations at different times and CCER price data at different times. Then, use Latin hypercube sampling and clustering algorithm to generate typical scenarios of power generation data of cascade hydropower stations and typical scenarios of CCER prices. Combine them in pairs to obtain S typical scenario sets. S2. Estimate the clearing price of the spot market based on electricity load data; S3. Based on the curve of power load change over time, the total contracted power of the cascade hydropower stations is decomposed to obtain the contracted power at each time t. S4. With the goal of maximizing expected returns in the spot market, establish a decomposition optimization model for medium- and long-term contracts of cascade hydropower that considers spot market prices and CCER prices. The constraints of the model include hydraulic constraints of cascade hydropower, power generation constraints of hydropower stations, contract power decomposition constraints, and CCER trading constraints. S5. Solve the decomposition and optimization model of the medium and long-term contracts for cascade hydropower to obtain the optimal contract power decomposition curve.
[0006] Furthermore, in step S1, the generation of the typical scenario specifically includes: S11. Divide the interval [0,1] of the cumulative probability distribution function into... N Divide the sample into equal parts, and then obtain the prediction error for each sample n based on the cumulative probability distribution function. Then, based on the original power generation data and CCER price, the power generation data sample value and CCER price sample value are calculated respectively, thereby generating uncertain scenarios for cascade hydropower stations and CCER prices respectively; S12. The K-means clustering method is used to cluster the uncertain scenarios to generate typical scenarios for hydropower cascade power stations and CCER prices, and the probability of occurrence of each typical scenario is calculated. S13. Use Cartesian products to combine the typical scenarios of the hydropower station and CCER price in pairs to obtain S typical scenario sets, and calculate the occurrence probability of each typical scenario set according to the occurrence probability of the typical scenarios.
[0007] Furthermore, in step S2, the clearing price in the spot market includes: normalizing the electricity load data and then calculating it using the following formula:
[0008] In the formula, For normalized power load data at time t, Here is the original power load data at time t. The raw power load data is for the total transaction time T of medium- and long-term contracts. for t Real-time estimated clearing electricity price and These are the upper and lower limits of the clearing electricity price.
[0009] Furthermore, the initial contract power determined at each time t is calculated using the following formula:
[0010] In the formula, The initial contract power for the cascade hydropower stations at time t. The total contracted electricity volume for the cascade hydropower stations. This represents the change over time.
[0011] Furthermore, in step S4, the objective function of the long-term contract decomposition and optimization model for cascade hydropower is as follows:
[0012]
[0013]
[0014]
[0015] In the formula, The expected returns of cascade hydropower in the spot market. For cascade hydropower in s Spot market stage in the scenario t Expected revenue from electricity sales at any given moment. For cascade hydropower in s Spot market stage in the scenario t The expected returns from participating in the carbon market and selling CCERs. For cascade hydropower in s In the scene t Expected power generation cost at any given time For the scene s The probability of occurrence, For cascade hydropower h Hydropower station s Spot market stage in the scenario t Planned power generation capacity at any given time For cascade hydropower in s In the scene t Contract decomposition power at any given time For cascade hydropower in s In the scene t The number of CCERs sold at any given time. for s In the scene t CCER predicts transaction prices at any given time. Hydropower station in cascade hydropower h The power generation cost coefficient.
[0016] Furthermore, the hydraulic constraints of the cascade hydropower are as follows:
[0017] In the formula, , and They represent h Hydropower station in the scene s Down t Water level at the end of the time period and its upper and lower limits; Indicates hydroelectric power station h The reservoir water level-capacity curve function; H represents the total number of hydropower stations; and They represent hydroelectric power stations h The initial water level constraints and the final water level constraints; , and They represent s In the scene h hydroelectric power station t The discharge flow rate and its upper and lower limits for each time period; , and They represent s Scenario 1 h A hydropower station t The power generation flow rate at any given time and its upper and lower limits; express s Scenario 1 h A hydropower station t Storage capacity at any given time; R s,h,t for s Scenario 1 h A hydropower station t Inbound traffic at any given time; I s,h,t for s Scenario 1 h A hydropower station t Real-time outbound flow; For the first h -1 hydropower station's outflow reached the first h The time of the hydroelectric power station.
[0018] Furthermore, the power generation constraints of the hydropower station are as follows:
[0019] In the formula, h express hWater consumption rate of hydropower stations; and They represent h The maximum and minimum generating capacity of a hydroelectric power station; P cap This indicates the capacity of the power transmission line.
[0020] Furthermore, the contract electricity decomposition constraints are as follows:
[0021]
[0022]
[0023]
[0024] The CCER transaction constraints are as follows:
[0025]
[0026]
[0027] In the formula, For the scene s Mid-time t Contract breakdown adjustment coefficients for cascade hydropower projects. The maximum value of the set adjustment coefficient. This represents the maximum number of CCERs sold. For the context s Mid-time t The tradable CCERs for cascade hydropower. This is the exchange coefficient for converting hydroelectricity to CCER.
[0028] Furthermore, in step S5, the optimal contract electricity decomposition curve includes the electricity decomposed under the total transaction time T of medium and long-term contracts as a function of time, and the electricity reserved for bidding in the spot market as a function of time; the total transaction time T of medium and long-term contracts is greater than or equal to 3 days.
[0029] This invention also provides a cascade hydropower medium- and long-term contract decomposition system that considers the uncertainty of multi-source information, comprising: The scenario generation module is used to collect raw power generation data of cascade hydropower stations at different times and CCER price data at different times. Then, through Latin hypercube sampling and clustering algorithm, typical scenarios of power generation data of cascade hydropower stations and typical scenarios of CCER prices are generated. By combining them in pairs, S typical scenario sets are obtained. The clearing price estimation module is used to estimate the clearing price in the spot market based on electricity load data; The contract power decomposition module is used to decompose the total contract power of the cascade hydropower stations according to the power load variation curve over time, and obtain the contract power at each time t. The contract decomposition and optimization model construction module is used to establish a medium- and long-term contract decomposition and optimization model for cascade hydropower with the goal of maximizing expected returns in the spot market. The model's constraints include hydraulic constraints for cascade hydropower, power generation constraints for hydropower stations, contract power decomposition constraints, and CCER trading constraints. The model solving module solves the decomposition and optimization model of the medium- and long-term contracts for cascade hydropower, and obtains the optimal contract power decomposition curve.
[0030] In summary, compared with the prior art, the above-described technical solutions conceived by this invention mainly possess the following technical advantages: 1. This invention provides a method for decomposing medium- and long-term contracts for cascade hydropower projects that considers the uncertainties of multi-source information. It innovatively proposes using Latin hypercube sampling and K-means clustering to generate prediction errors for reservoir runoff and CCER (Consumer Rights Transaction) prices, thereby generating a set of uncertain scenarios for runoff and CCER prices. Simultaneously, based on the probability of occurrence of each scenario set, a weighted summation of spot market returns is performed to reduce the limitations of a single scenario, ultimately improving the accuracy of the final contract decomposition. This invention, based on maximizing spot market returns, allocates electricity in the medium- and long-term market, which is beneficial for improving the expected returns of cascade hydropower in the electricity spot market under multi-market environments and enhancing market stability.
[0031] 2. This invention estimates the clearing price of the electricity spot market based on electricity load. By taking into account the supply and demand balance through this price estimation method, when the electricity price is high, more electricity is allocated to the spot market while ensuring the supply of medium and long-term contracted electricity, thereby increasing the overall revenue.
[0032] 3. This invention proposes a method for decomposing the contracted electricity volume of cascade hydropower based on the electricity load curve. With the objective of maximizing expected returns in the spot market, it establishes a decomposition optimization model for medium- and long-term cascade hydropower contracts, considering both spot market prices and CCER prices. The constraints of this model include hydraulic constraints, hydropower output constraints, and market transaction constraints. Under these constraints, the optimal decomposition model is solved to obtain the optimal contracted electricity volume decomposition curve. Compared to previous methods, this invention considers not only the bidding space in the electricity spot market but also the uncertainties of carbon market prices and hydropower station runoff during the medium- and long-term contract decomposition process, thereby improving the overall returns of cascade hydropower in a multi-market environment. Attached Figure Description
[0033] Figure 1 This is a schematic diagram of the process for decomposing medium- and long-term contracts for cascade hydropower projects, which takes into account the uncertainty of multi-source information, provided by the present invention.
[0034] Figure 2 This is a schematic diagram of the model solution process for the decomposition method of medium- and long-term contracts for cascade hydropower projects that considers the uncertainty of multi-source information, provided by the present invention.
[0035] Figure 3 This is a schematic diagram of the structure of the method for decomposing medium- and long-term contracts for cascade hydropower projects that considers the uncertainty of multi-source information provided by the present invention.
[0036] Figure 4 This is a map showing the contract power decomposition region based on power load trends and contract decomposition adjustment coefficients. Detailed Implementation
[0037] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.
[0038] Please see Figure 1-3 This invention provides a method for decomposing medium- and long-term contracts for cascade hydropower projects that considers the uncertainty of multi-source information, comprising the following steps: S1. Collect raw power generation data of cascade hydropower stations at different times and price data of CCER (China Certified Emission Reduction) at different times. Then, use Latin hypercube sampling and clustering algorithm to generate typical scenarios of power generation data of cascade hydropower stations and typical scenarios of CCER prices. Combine them in pairs to obtain S typical scenario sets. S2. Estimate the clearing price of the spot market based on electricity load data; S3. Based on the curve of power load variation over time, the total contracted power of the cascade hydropower stations is decomposed to obtain the contracted power at each time t. S4. With the goal of maximizing expected returns in the spot market, establish a decomposition optimization model for medium- and long-term contracts of cascade hydropower that considers spot market prices and CCER prices. The constraints of the model include hydraulic constraints of cascade hydropower, power generation constraints of hydropower stations, contract power decomposition constraints, and CCER trading constraints. S5. Solve the decomposition and optimization model of the medium and long-term contracts for cascade hydropower to obtain the optimal contract power decomposition curve.
[0039] Step S1 specifically includes: using the Latin hypercube sampling method and K-means clustering algorithm to generate the prediction error of reservoir runoff and CCER trading price, thereby generating a set of uncertain scenarios for runoff and CCER price.
[0040] 1) Generation of uncertain scenarios for runoff and CCER prices based on Latin hypercube sampling method set up N The number of samples represents the prediction error range, which is [-10%, 10%]. The cumulative probability distribution function of the prediction error is: The sampling process is as follows: First, the interval [0,1] of the cumulative probability distribution function is divided into... N Divide the data into equal parts; then, randomly select a point in each sub-interval. θ n,t As prediction error x n,t Sampling points; finally, take Inverse function calculation x n,t As shown in the following formula:
[0041] In the formula, Let be the prediction error of sample n at time t.
[0042] Compared with the original forecast data The product is the final sample value, as follows:
[0043] Each sample value's curve over time constitutes an uncertain scenario. By performing the above calculations on the raw forecast data of cascade hydropower stations and CCER prices respectively, several uncertain scenarios for hydropower stations and wind and solar power generation units are obtained. The raw forecast data for cascade hydropower stations is reservoir runoff (i.e., raw power generation data).
[0044] 2) Generation of typical scenarios for runoff and CCER prices based on K-means clustering algorithm K-means clustering was used to cluster uncertain scenarios, generating typical scenarios (i.e., sample value changes over time curves) for hydropower cascade power stations and CCER prices. The probability of occurrence for each scenario was calculated, which is equal to the ratio of that scenario to the total number of scenarios. Using this method, in subsequent revenue calculations, the revenue of each scenario is weighted and summed based on its probability, resulting in a more reasonable revenue and reducing the limitations of a single scenario.
[0045] 3) Using Cartesian product combined runoff and CCER price scenario The Cartesian product is used to combine the typical scenarios of each random variable after K-means classification to obtain the final typical scenario set. The total number of combined typical scenario sets is the product of the numbers of the original two scenario sets, and the probability of each scenario is the product of the probabilities of the original scenarios.
[0046] Step S2 is as follows: The load scenario data is normalized, compressing its numerical range to [0,1], and the trend of load curve changes is extracted. Then, based on the upper and lower limits of the liquidation price, the normalized scenario data is inversely normalized to obtain the estimated liquidation price scenario. The specific calculation formula is as follows:
[0047] In the formula, For normalized power load data at time t, Here is the original power load data at time t. The raw power load data is for the total transaction time T of medium- and long-term contracts. for t Real-time estimated clearing electricity price and These represent the upper and lower limits of the clearing price. This price estimation method considers supply and demand balance; that is, the greater the electricity load (higher demand), the higher the clearing price. This allows for a relative increase in the amount of electricity allocated to power generators (i.e., bidding entities) in the spot market, thereby improving overall revenue. The difference between the expected power generation capacity of the power generator and the amount allocated in the spot market represents the contracted electricity that can be allocated to the medium- and long-term markets.
[0048] In step S3, when decomposing the contracted electricity volume for cascade hydropower projects, it is necessary to consider both the changing trend of power load and the overall revenue of the projects in the spot market. Therefore, a method for formulating and adjusting the contracted electricity volume decomposition curve based on the power load curve is designed. The basic decomposition curve is determined according to the medium- and long-term contracted electricity volume of each cascade hydropower project and the system power load curve, as shown in the following formula:
[0049] In the formula, The initial contract power for the cascade hydropower project at time t is determined based on the power load curve. The total contracted electricity volume for cascade hydropower. This represents the change over time.
[0050] In step S4, with the goal of maximizing the expected revenue of cascade hydropower in the spot market, the contractual breakdown of hydropower volume for each time period is determined, and the objective function of the optimization model is as follows:
[0051]
[0052]
[0053]
[0054] In the formula, The expected returns of cascade hydropower in the spot market. For cascade hydropower in s Spot market stage in the scenario t Expected revenue from electricity sales at any given moment. For cascade hydropower in s Spot market stage in the scenario t The expected returns from participating in the carbon market and selling CCERs. For cascade hydropower in s In the scene t Expected power generation cost at any given time For the scene s The probability of occurrence, For cascade hydropower h Hydropower station s In the scene t Planned power generation capacity at any given time For cascade hydropower in s In the scene t Contract decomposition power at any given time For cascade hydropower in s In the scene t The number of CCERs sold at any given time. for s In the scene t CCER predicts transaction prices at any given time. Hydropower station in cascade hydropower h The power generation cost coefficient.
[0055] The constraints include cascade hydropower hydraulic constraints, hydropower station power generation constraints, contract power allocation constraints, and CCER transaction constraints.
[0056] The hydraulic constraints are as follows:
[0057] In the formula, , and They represent h Hydropower station in the scene s Down t Water level at the end of the time period and its upper and lower limits; Indicates hydroelectric power station h The reservoir water level-capacity curve function; and They represent hydroelectric power stations h The initial water level constraints and the final water level constraints; , and They represent s In the scene h hydroelectric power station t The discharge flow rate and its upper and lower limits for each time period; , and They represent s Scenario 1 h A hydropower station t The power generation flow rate at any given time and its upper and lower limits; express s Scenario 1 h A hydropower station t Storage capacity at any given time; R s,h,t for s Scenario 1 h A hydropower station t Inbound traffic at any given time; I s,h,t for s Scenario 1 h A hydropower station t Real-time outbound flow; For the first h -1 hydropower station's outflow reached the first h The time of the hydroelectric power station.
[0058] The power generation constraints of the hydropower station are as follows:
[0059] In the formula, h express h Water consumption rate of hydropower stations; and They represent h The maximum and minimum output of the hydropower station; P cap This indicates the capacity of the power transmission line.
[0060] The contracted electricity volume decomposition constraints are as follows:
[0061]
[0062]
[0063]
[0064] like Figure 4The trend graph obtained from the first formula in the contract power decomposition constraint condition is used to obtain the trend of cascade hydropower in... s In the scene t Contract decomposition power at time It falls within the upper and lower limits of the feasible range of the contracted power.
[0065] CCER transaction constraints are as follows:
[0066]
[0067]
[0068] In the formula, For the context s Mid-time t Contract breakdown adjustment coefficients for cascade hydropower projects. To set the maximum value of the adjustment factor, This represents the maximum number of CCERs sold. For the context s Mid-time t The tradable CCERs for cascade hydropower. This is the exchange coefficient for converting hydroelectricity to CCER.
[0069] In step S5, the optimal contract volume decomposition curve includes the volume decomposition curve of medium- and long-term contracts changing over time under the total transaction time T of medium- and long-term contracts, and the volume reserved for bidding in the spot market changing over time; the total transaction time T of medium- and long-term contracts is greater than or equal to 3 days.
[0070] like Figure 3 The present invention also provides a cascade hydropower medium- and long-term contract decomposition system that considers the uncertainty of multi-source information, comprising: The scenario generation module is used to collect raw power generation data of cascade hydropower stations at different times and CCER price data at different times. Then, through Latin hypercube sampling and clustering algorithm, typical scenarios of power generation data of cascade hydropower stations and typical scenarios of CCER prices are generated. By combining them in pairs, S typical scenario sets are obtained. The clearing price estimation module is used to estimate the clearing price in the spot market based on electricity load data; The contract power decomposition module is used to decompose the total contract power of the cascade hydropower stations according to the power load variation curve over time, and obtain the contract power at each time t. The contract decomposition and optimization model construction module is used to establish a medium- and long-term contract decomposition and optimization model for cascade hydropower with the goal of maximizing expected returns in the spot market. The model's constraints include hydraulic constraints for cascade hydropower, power generation constraints for hydropower stations, contract power decomposition constraints, and CCER trading constraints. The model solving module solves the decomposition and optimization model of the medium- and long-term contracts for cascade hydropower, and obtains the optimal contract power decomposition curve.
[0071] In summary, this invention employs Latin hypercube sampling and K-means clustering to generate prediction errors for reservoir runoff and CCER trading prices, thereby generating a set of uncertain scenarios for runoff and CCER prices. It proposes an estimation method for the clearing price in the electricity spot market; a method for decomposing cascade hydropower contract volumes based on electricity load curves; and, with the objective of maximizing expected spot market returns, establishes a cascade hydropower medium- and long-term contract decomposition optimization model considering spot market prices and CCER prices. The constraints of this model include hydraulic constraints, hydropower output constraints, and market transaction constraints. Under these constraints, the optimal contract volume decomposition curve is obtained by solving the cascade hydropower medium- and long-term contract decomposition optimization model. This invention improves the expected returns of cascade hydropower in the electricity spot market under multi-market environments and enhances market stability.
[0072] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information, characterized in that, Includes the following steps: S1. Collect raw power generation data of cascade hydropower stations at different times and CCER price data at different times. Then, use Latin hypercube sampling and clustering algorithm to generate typical scenarios of power generation data of cascade hydropower stations and typical scenarios of CCER prices. Combine them in pairs to obtain S typical scenario sets. S2. Estimate the clearing price of the spot market based on electricity load data; S3. Based on the curve of power load change over time, the total contracted power of the cascade hydropower stations is decomposed to obtain the contracted power at each time t. S4. With the goal of maximizing expected returns in the spot market, establish a decomposition optimization model for medium- and long-term contracts of cascade hydropower that considers spot market prices and CCER prices. The constraints of the model include hydraulic constraints of cascade hydropower, power generation constraints of hydropower stations, contract power decomposition constraints, and CCER trading constraints. S5. Solve the decomposition and optimization model of the medium and long-term contracts for cascade hydropower to obtain the optimal contract power decomposition curve.
2. The method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information as described in claim 1, characterized in that, In step S1, the generation of the typical scenario specifically includes: S11. Divide the interval [0,1] of the cumulative probability distribution function into... N Divide the sample into equal parts, and then obtain the prediction error for each sample n based on the cumulative probability distribution function. Then, based on the original power generation data and CCER price, the power generation data sample value and CCER price sample value are calculated respectively, thereby generating uncertain scenarios for cascade hydropower stations and CCER prices respectively; S12. The K-means clustering method is used to cluster the uncertain scenarios to generate typical scenarios for hydropower cascade power stations and CCER prices, and the probability of occurrence of each typical scenario is calculated. S13. Use Cartesian products to combine the typical scenarios of the hydropower station and CCER price in pairs to obtain S typical scenario sets, and calculate the occurrence probability of each typical scenario set according to the occurrence probability of the typical scenarios.
3. The method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information as described in claim 1, characterized in that, In step S2, the clearing price of the spot market includes: normalizing the electricity load data and then calculating it using the following formula: In the formula, For normalized power load data at time t, Here is the original power load data at time t. The raw power load data is for the total transaction time T of medium- and long-term contracts. for t Real-time estimated clearing electricity price and These are the upper and lower limits of the clearing electricity price.
4. The method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information as described in claim 3, characterized in that, The initial contract power at each time t is calculated using the following formula: In the formula, The initial contract power for the cascade hydropower stations at time t. The total contracted electricity volume for the cascade hydropower stations. This represents the change over time.
5. The method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information as described in claim 1, characterized in that, In step S4, the objective function of the long-term contract decomposition and optimization model for cascade hydropower is as follows: In the formula, The expected returns of cascade hydropower in the spot market. For cascade hydropower in s Spot market stage in the scenario t Expected revenue from electricity sales at any given moment. For cascade hydropower in s Spot market stage in the scenario t The expected returns from participating in the carbon market and selling CCERs. For cascade hydropower in s In the scene t Expected power generation cost at any given time For the scene s The probability of occurrence, For cascade hydropower h Hydropower station s Spot market stage in the scenario t Planned power generation capacity at any given time For cascade hydropower in s In the scene t Contract decomposition power at any given time For cascade hydropower in s In the scene t The number of CCERs sold at any given time. for s In the scene t CCER predicts transaction prices at any given time. Hydropower station in cascade hydropower h The power generation cost coefficient.
6. The method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information as described in claim 5, characterized in that, The hydraulic constraints of the cascade hydropower are as follows: In the formula, , and They represent h Hydropower station in the scene s Down t Water level at the end of the time period and its upper and lower limits; Indicates hydroelectric power station h The reservoir water level-capacity curve function; H represents the total number of hydropower stations; and They represent hydroelectric power stations h The initial water level constraints and the final water level constraints; , and They represent s In the scene h hydroelectric power station t The discharge flow rate and its upper and lower limits for each time period; , and They represent s Scenario 1 h A hydropower station t The power generation flow rate at any given time and its upper and lower limits; express s Scenario 1 h A hydropower station t Storage capacity at any given time; R s,h,t for s Scenario 1 h A hydropower station t Inbound traffic at any given time; I s,h,t for s Scenario 1 h A hydropower station t Real-time outbound flow; For the first h -1 hydropower station's outflow reached the first h The time of the hydroelectric power station.
7. The method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information as described in claim 5, characterized in that, The power generation constraints of the hydropower station are as follows: In the formula, h express h Water consumption rate of hydropower stations; and They represent h The maximum and minimum generating capacity of a hydroelectric power station; P cap This indicates the capacity of the power transmission line.
8. The method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information as described in claim 5, characterized in that, The contracted electricity volume decomposition constraints are as follows: The CCER transaction constraints are as follows: In the formula, For the scene s Mid-time t Contract breakdown adjustment coefficients for cascade hydropower projects. The maximum value of the set adjustment coefficient. This represents the maximum number of CCERs sold. For the context s Mid-time t The tradable CCERs for cascade hydropower. This is the exchange coefficient for converting hydroelectricity to CCER.
9. The method for decomposing medium- and long-term contracts for cascade hydropower projects considering the uncertainty of multi-source information as described in claim 5, characterized in that, In step S5, the optimal contract volume decomposition curve includes the volume decomposition curve of medium- and long-term contracts changing over time under the total transaction time T of medium- and long-term contracts, and the volume reserved for bidding in the spot market changing over time; the total transaction time T of medium- and long-term contracts is greater than or equal to 3 days.
10. A decomposition system for medium- and long-term contracts in cascade hydropower projects considering the uncertainty of multi-source information, characterized in that, include: The scenario generation module is used to collect raw power generation data of cascade hydropower stations at different times and CCER price data at different times. Then, through Latin hypercube sampling and clustering algorithm, typical scenarios of power generation data of cascade hydropower stations and typical scenarios of CCER prices are generated. By combining them in pairs, S typical scenario sets are obtained. The clearing price estimation module is used to estimate the clearing price in the spot market based on electricity load data; The contract power decomposition module is used to decompose the total contract power of the cascade hydropower stations according to the power load variation curve over time, and obtain the contract power at each time t. The contract decomposition and optimization model construction module is used to establish a medium- and long-term contract decomposition and optimization model for cascade hydropower with the goal of maximizing expected returns in the spot market. The model's constraints include hydraulic constraints for cascade hydropower, power generation constraints for hydropower stations, contract power decomposition constraints, and CCER trading constraints. The model solving module solves the decomposition and optimization model of the medium- and long-term contracts for cascade hydropower, and obtains the optimal contract power decomposition curve.