System and method for optimizing transaction strategy of wind-solar power generator under evidence-electricity separation background
The system optimizes trading strategies for wind and solar power generators by predicting revenues and volumes across multiple markets, addressing profit maximization and enabling automatic trading, thus enhancing profitability and promoting diversified power generation.
Patent Information
- Application Number
- CN202411535353.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing trading strategies for wind and solar power generators fail to maximize profits and do not enable automatic trading across multiple markets, including electricity, green certificate, and CCER markets, due to reliance on manual experience and lack of integration between these markets.
A system and method that includes data acquisition, calculation, and generation modules to optimize trading strategies by predicting transaction revenues and volumes across multiple markets, enabling automatic trading and maximizing overall revenue.
Enables wind and solar power generators to achieve greater profits by automatically optimizing transactions in multiple markets, considering the interdependencies of electricity, green certificate, and CCER markets, thereby promoting diversified power generation methods.
Smart Images

Figure CN119067715A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of renewable energy power generation technology, and in particular to a system and method for optimizing trading strategies for wind and solar power companies under the background of separation of certificate and electricity. Background Art
[0002] Increasing the proportion of renewable energy power generation is a key measure for low-carbon energy transformation, which can promote the transformation of energy structure to a cleaner and greener direction and promote the transformation of the global energy system to a sustainable development path. At present, wind and solar renewable energy power is developing rapidly, and solar thermal power has gradually become a hot spot in the dispatch of renewable energy. However, the intermittent and volatile nature of wind and solar power has led to serious challenges in large-scale grid connection and consumption. How to promote the consumption of renewable energy through market-oriented means has become a major issue. Therefore, the Green Certificate Trading (GCT) mechanism and the China Certified Emission Reduction (CCER) trading mechanism, as key market mechanisms to promote the power industry to reduce carbon emissions and encourage renewable energy power generation to go online, are being favored by more and more countries. With the introduction of the green certificate trading market and the carbon trading market, the interest structure and business decisions of renewable energy power generators have undergone tremendous changes. Therefore, studying the trading strategies of renewable energy power generators under the coupling of the electricity-green certificate-CCER market can effectively promote the development of renewable energy and promote more social resources to the low-carbon field.
[0003] The prior art has studied the transaction strategies of e-commerce companies under multi-market coupling.
[0004] However, the research in the existing technology is mainly based on the perspective of the power grid, and the optimization research is carried out with the goal of maximizing social welfare, which cannot maximize the benefits of new energy power generators. In addition, the trading platforms in various markets are independent of each other. During the transaction process, new energy power generators need to estimate the transaction volume in each market based on their own experience, and initiate trading operations on the trading platforms of each market respectively, which makes it impossible for new energy power generators to realize automatic trading in multiple markets. Summary of the invention
[0005] This specification provides a system and method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity, so as to solve the problem that the trading strategy of generators under the existing multi-market coupling cannot maximize the profits of new energy generators and cannot enable new energy generators to realize automatic trading in multiple markets.
[0006] In order to solve the above technical problems, the first aspect of this specification provides a wind and solar power plant trading strategy optimization system under the background of separation of certificates and electricity, including: a data acquisition module, used to obtain the operating data of each generator set of the target power plant, as well as the historical transaction data in the electricity market, green certificate market and CCER market; a first calculation module, used to calculate the predicted value expressions of the transaction revenue of the target power plant in the electricity market, green certificate market and CCER market according to the data acquired by the data acquisition module, wherein the transaction volume in the corresponding market is an unknown variable; a second calculation module, used to determine the predicted expression of the overall revenue in the three markets according to the calculation result of the first calculation module, and calculate the predicted value of the transaction volume in each market when the overall revenue is maximized; a generation module, respectively connected to the trading platforms of the electricity market, green certificate market and CCER market; the generation module is used to generate the transaction instructions of the corresponding market trading platform according to the predicted value of the transaction volume in each market when the overall revenue is maximized, and send it to the trading platform of the corresponding market, so that the target power plant can automatically execute the trading strategy on the trading platform of each market.
[0007] In some embodiments, the system further includes: an interaction module for receiving a profit time scale input by a target power producer, wherein the profit time scale is used to indicate a time scale within which the overall profit is expected to be maximized.
[0008] In some embodiments, the maximum value of the overall revenue under the three markets is calculated according to the following formula:
[0009] Where i is the ID of the target power producer; E i It represents the predicted value of the overall revenue of target generator i in the three markets; It represents the predicted value of the transaction revenue of target power generator i in the electricity market; It represents the predicted value of the transaction revenue of target power generator i in the green certificate market; It represents the predicted value of the transaction revenue of the target power producer i in the CCER market; when the target power producer is a wind power producer or a photovoltaic power producer, The value of is 1; when the target power producer is a CSP power producer, The value of is 0.
[0010] In some embodiments, the maximum value of the overall benefit is calculated according to the following formula:
[0011]
[0012] Where i is the ID of the target power producer; E iIt represents the predicted value of the overall revenue of target generator i in the three markets; It represents the predicted value of the transaction revenue of target power generator i in the electricity market; It represents the predicted value of the transaction revenue of target power generator i in the green certificate market; It represents the predicted value of the transaction revenue of the target power producer i in the CCER market; when the target power producer is a wind power producer or a photovoltaic power producer, The value of is 1; when the target power producer is a CSP power producer, The value of is 0; δ is the risk weight coefficient of the target power generator, and its value is [0,1]; W i1 Represents the predicted loss value of target generator i.
[0013] In some embodiments, the system further includes: an interaction module for receiving a value of a risk weight coefficient input by a target power producer.
[0014] In some embodiments, the loss prediction value of the target power generator is calculated according to the following formula:
[0015] Among them, W i1 represents the loss prediction value of target power generator i; W i2 represents the acceptable loss threshold of the target generator; β represents the confidence level; π(ω) represents the probability of the occurrence of scenario ω, П represents the set of scenarios; f(ω) represents the loss value under scenario ω, P(f(ω)≥W i2 ) represents the probability that the loss value under scenario ω is greater than or equal to the acceptable loss threshold.
[0016] In some embodiments, the system further includes: an interaction module for receiving a value of an acceptable loss threshold input by a target power producer.
[0017] In some embodiments, the system also includes: a first statistical module, used to count the transaction prices in the electricity market, green certificate market, and CCER market in various time periods over many years in history; a first determination module, used to determine the normal distribution data of the transaction prices in the electricity market, green certificate market, and CCER market in various time periods based on the statistical results; a first extraction module, used to randomly determine the transaction price forecast value corresponding to each time period based on the normal distribution data of the transaction price, and take a combination of the transaction price forecast values corresponding to each time period in the electricity market, green certificate market, and CCER market as a scenario; determine a predetermined number of scenarios based on the normal distribution data of the transaction price.
[0018] In some embodiments, the system also includes: a second statistical module, used to count the demand in the electricity market, green certificate market, and CCER market in various time periods over many years in history; a second determination module, used to determine the normal distribution data of the demand in the electricity market, green certificate market, and CCER market in various time periods based on the statistical results; a second extraction module, used to randomly determine the demand forecast value corresponding to each time period based on the normal distribution data of demand, and take a combination of the transaction price forecast value and the demand forecast value corresponding to each time period in the electricity market, green certificate market, and CCER market as a scenario; determine a predetermined number of scenarios based on the normal distribution data of demand.
[0019] In some embodiments, the system further comprises: an interaction module for inputting a predetermined number of values of the scene.
[0020] The second aspect of this specification provides a method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificates and electricity, including: obtaining the operating data of each generator set of the target power generator, as well as the historical trading data in the electricity market, green certificate market, and CCER market; calculating the predicted value expressions of the transaction revenue of the target power generator in the electricity market, green certificate market, and CCER market respectively according to the acquired data, wherein the transaction volume in the corresponding market is an unknown variable in the predicted value expressions; determining the predicted expression of the overall revenue in the three markets according to the calculation results, and calculating the predicted value of the transaction volume in each market when the overall revenue is maximized; generating the transaction instructions of the corresponding market trading platform according to the predicted value of the transaction volume in each market when the overall revenue is maximized, and sending them to the trading platform of the corresponding market, so that the target power generator can automatically execute the trading strategy on each market trading platform.
[0021] The third aspect of this specification provides an electronic device, including: a memory and a processor, the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to implement the wind and solar power generator trading strategy optimization system under the background of separation of certificate and electricity as described in the first aspect.
[0022] The system and method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity provided in this specification automatically obtains the operating data of each generator set of the target generator and the historical trading data in the electricity market, green certificate market and CCER market through the data acquisition module, automatically calculates the predicted value expression of the transaction revenue of the target generator in the electricity market, green certificate market and CCER market through the first calculation unit, determines the predicted expression of the overall revenue in the three markets through the second calculation unit, and calculates the predicted value of the transaction volume in each market when the overall revenue is maximized, and generates the transaction instructions of the corresponding market trading platform according to the predicted value of the transaction volume in each market when the overall revenue is maximized through the generation module, and sends them to the trading platform of the corresponding market, which can enable the new energy generator to realize automatic trading in each trading market under the scenario of multi-market coupling, and can ensure that the new energy generator has greater revenue from the perspective of the new energy generator, which is conducive to promoting a single new energy generator to put into operation generator sets with diversified power generation methods.
[0023] The system and method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificates and electricity provided in this specification take into account the trading strategies of wind and solar new energy power generators, including solar thermal power generation, and fully consider the impact of the three markets of electricity, green certificates and CCER on the decision-making of power generators in the electricity-green certificate-CCER coupling market, and obtain the optimal trading strategy that maximizes the benefits of wind and solar new energy power generators under the background of separation of certificates and electricity. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to more clearly illustrate the implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some implementation methods recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0025] Figure 1 A schematic diagram of a wind and solar power generator trading strategy optimization system under the background of certificate-electricity separation provided in this specification; Figure 2 Another schematic diagram of the wind and solar power generator trading strategy optimization system under the background of certificate-electricity separation provided in this specification; Figure 3 A schematic diagram of the wind and solar power generator transaction strategy optimization method under the background of separation of certificate and electricity provided in this specification; Figure 4 This is a schematic diagram of the structure of the electronic device provided in this manual. DETAILED DESCRIPTION
[0026] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.
[0027] For individual new energy power generators, the most important thing they care about during the transaction process is the profit. Traditional power generators with a single power generation method can only participate in transactions in the electricity market. With the development of new energy power generation technology, a variety of new energy power generation methods such as wind power generation, photovoltaic power generation, and solar thermal power generation have emerged. The power generation methods of some new energy power generators are becoming more and more diversified. In addition to participating in transactions in the electricity market, new energy power generators can also participate in transactions in the green certificate market and CCER market to obtain profits.
[0028] New energy power generators mainly participate in green certificate transactions through the trading platform of the green certificate market. Specifically, after generating electricity through wind power generation, photovoltaic power generation, solar thermal power generation, etc., new energy power generators can obtain a corresponding number of green certificates, and these green certificates can be put on sale on the trading platform of the green certificate market. Green certificate consumers log in to the trading platform of the green certificate market to purchase on demand. Similarly, new energy power generators mainly participate in CCER transactions through the trading platform of the CCER market. Specifically, after generating electricity through wind power generation, photovoltaic power generation, solar thermal power generation, etc., new energy power generators can obtain a corresponding number of CCERs, and these CCERs can be put on sale on the trading platform of the CCER market. CCER consumers log in to the trading platform of the CCER market to purchase on demand.
[0029] Since the real-time prices of resources such as electricity, green certificates, and CCERs are changing, when to sell each resource will affect the profits of new energy power generators. When prices are low, new energy power generators can temporarily not sell or reduce the sale of electricity, green certificates, CCERs and other resources, and store them until prices are higher before putting them up for sale.
[0030] At present, new energy power generators can only participate in multi-market transactions by relying on their own experience and the real-time price trends of various resources (resources can be electricity, green certificates, CCER) to evaluate how much of each resource should be sold to maximize their own profits, and log in to the trading platform of the electricity market, the trading platform of the green certificate market, and the trading platform of the CCER market to sell the corresponding amount of resources according to their own evaluation results. However, the resource prices in the electricity, green certificate, and CCER markets are coupled and influence each other. The existing way for new energy power generators to participate in multi-market transactions is too dependent on manual experience, and manual experience makes it difficult to clarify the mutual influence of resource prices in multiple markets, making it difficult for new energy power generators to always obtain greater profits. In response to this, some new energy power generators have deliberately reduced their power generation methods and restricted the commissioning of multiple power generation methods.
[0031] In order to simplify the complexity of new energy power generators participating in multi-market transactions, this specification provides a wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity, so that new energy power generators can customize transactions in multiple markets and obtain greater profits.
[0032] like Figure 1 As shown, the wind-solar power generator transaction strategy optimization system under the background of separation of certificate and electricity includes a data acquisition module 10, a first calculation module 20, a second calculation module 30 and a generation module 40.
[0033] The data acquisition module 10 is used to obtain the operating data of each generating unit of the target power producer, as well as the historical transaction data in the electricity market, green certificate market, and CCER market.
[0034] The target power generator may have multiple power generation units, each of which has a different power generation capacity, and different power generation methods of different power generation units may also be different.
[0035] The operating data of each generator set may include: Historical transaction data in the electricity market, green certificate market, and CCER market may include: The first calculation module 20 is used to calculate the predicted value expressions of the target power generator's transaction revenue in the electricity market, green certificate market, and CCER market respectively according to the data acquired by the data acquisition module, wherein the transaction volume in the corresponding market is an unknown variable in the predicted value expressions.
[0036] For example, —— (1) represents the predicted value of the transaction revenue of target power producer i in the electricity market, Q GE represents the amount of electricity sold by target power producer i, λ GE Indicates the electricity price corresponding to the amount of electricity sold.
[0037] —— (2) represents the predicted value of the transaction revenue of target power generator i in the green certificate market, Q TGC represents the total amount of green certificates sold by target power producer i, λ TGC Indicates the price corresponding to the sale of the green certificate.
[0038] —— (3) represents the predicted value of the transaction revenue of target power producer i in the CCER market, Q CCER represents the total amount of CCER sold by target power producer i, λ GE Indicates the price at which CCER is sold.
[0039] The second calculation module 30 is used to determine the prediction expression of the overall return in the three markets according to the calculation results of the first calculation module, and calculate the predicted value of the transaction volume in each market when the overall return is maximized.
[0040] For example, the maximum value of the overall benefit can be expressed as: ,in Represents the target power generation company's power generation cost. According to the above formulas (1), (2), and (3), it can be seen that the value of the overall revenue changes with the changes in the sales quantity and sales price in each market. Usually, the sales price in each market is determined by the supply and demand relationship, which is not controllable by the new energy power generation company. Therefore, the new energy power generation company can only change the actual value of the overall revenue by adjusting the sales quantity in each market.
[0041] The generation module 40 is connected to the trading platforms of the power market, green certificate market, and CCER market respectively. The generation module 40 is used to generate the trading instructions of the corresponding market trading platform according to the predicted value of the transaction volume of each market when the overall revenue value is maximized, and send it to the trading platform of the corresponding market, so that the target power generator can automatically execute the trading strategy on each market trading platform.
[0042] like Figure 1 As shown, after the second calculation module 30 calculates the predicted value of each market transaction volume when the overall return value is maximized, the generation module 40 can automatically generate the transaction instructions of the corresponding trading market according to the predicted value of each market transaction volume.
[0043] The trading order can be the specific amount of resources sold in the trading market. For example, the trading order in the power market is to sell x kWh, the trading order in the green certificate market is to sell y kWh, and the trading order in the CCER market is to sell z kWh. When the revenue time scale includes multiple time periods, the trading order can also be the specific amount of resources sold in the trading market in each time period. For example, the trading order in the power market is to sell x1 kWh in January, x2 kWh in February... The above-mentioned trading instructions can be sent to the corresponding trading platform through the first interface component, and the corresponding trading platform can be automatically operated through the second interface component to automatically execute the trading strategy according to the trading instructions.
[0044] The wind and solar power company trading strategy optimization system under the background of separation of certificate and electricity provided in this specification automatically obtains the operating data of each generator set of the target generator and the historical transaction data in the electricity market, green certificate market and CCER market through the data acquisition module, and automatically calculates the predicted value expression of the transaction revenue of the target generator in the electricity market, green certificate market and CCER market through the first calculation unit, determines the predicted expression of the overall revenue in the three markets through the second calculation unit, and calculates the predicted value of the transaction volume in each market when the overall revenue is maximized, and generates the transaction instructions of the corresponding market trading platform according to the predicted value of the transaction volume in each market when the overall revenue is maximized through the generation module, and sends them to the trading platform of the corresponding market, which can enable the new energy generator to realize automatic trading in each trading market under the scenario of multi-market coupling, and can ensure that the new energy generator has a larger profit from the perspective of the new energy generator, which is conducive to promoting a single new energy generator to put into operation generator sets with diversified power generation methods.
[0045] In some embodiments, Figure 2 As shown, the wind-solar power generation company transaction strategy optimization system under the background of separation of certificate and electricity also includes an interactive module, which is used to receive the profit time scale input by the target power generation company, and the profit time scale is used to indicate the time scale within which the overall profit is expected to be maximized.
[0046] Specifically, the revenue time scale may be one year, one quarter, one month, etc., and of course may be other time scales, which are not listed here one by one.
[0047] Each year can be divided into a predetermined number of time periods, each of which is equal to the minimum revenue time scale. When performing calculations, the first calculation module 20 and the second calculation module 30 can calculate the prediction expression of the overall revenue according to the divided fixed time periods.
[0048] For example, if each year is divided into 12 months, and the revenue time scale is one year, the revenue expression of each month in the 12 months is calculated separately, and then the revenue expressions of the 12 months are accumulated to obtain the predicted expression of the overall revenue; if the revenue time scale is one month (it can be a specified month or the next month of the current time), Each year can also be divided into one week, one quarter, etc. It should be noted that since the transaction price of resources in each market is determined by the supply and demand relationship, the influencing factors are relatively complex and changeable. At present, there is no method that can accurately predict the real-time transaction price. Therefore, it is not appropriate to divide the time period too finely when calculating the overall revenue.
[0049] It is understandable that when the overall revenue of a year is the largest, the overall revenue of a certain month may not be the largest; conversely, when the overall revenue of a certain month is the largest, the overall revenue of a year may not be the largest. By setting the transaction component to receive the revenue time scale input by the target power generator, the new energy power generator can adjust the time scale for calculating the overall revenue according to its own needs, which is more flexible and more in line with actual production needs.
[0050] In some embodiments, the maximum value of the overall revenue under the three markets can be calculated according to the following formula: —— (4) Where i is the ID of the target power producer; E i It represents the predicted value of the overall revenue of target generator i in the three markets; It represents the predicted value of the transaction revenue of target power generator i in the electricity market; It represents the predicted value of the transaction revenue of target power generator i in the green certificate market; It represents the predicted value of the transaction revenue of the target power producer i in the CCER market; when the target power producer is a wind power producer or a photovoltaic power producer, The value of is 1; when the target power producer is a CSP power producer, The value of is 0.
[0051] In this specification: 1. If the target power generator is both a wind power generator or a photovoltaic power generator and a solar thermal power generator, the target power generator may include two identifiers; 2. The value of determines whether each generating unit of the target power company participates in the transaction of the green certificate market or the CCER market. Usually, a generating unit can only participate in the transaction of one of the green certificate market and the CCER market.
[0052] In some embodiments, the prediction expression of the target power generator's transaction revenue in the power market can be: —— (5) Where: i is the number of the target generator; t is the sequence number of the operating time period; Δt is the length of each time period; T is the set of operating time periods; n is the number of the generator set; Ω i is the set of all generating units owned by target power producer i; is the electricity price under scenario ω; is the amount of electricity sold by generator n in time period t, where The unit is MWh.
[0053] The prediction expression of the target power generator's transaction revenue in the green certificate market can be: —— (6) in, —— (7) —— (8) —— (9) —— (10) —— (11) Where: ω is the number of the scene; П is the set of all scenes; π ω is the probability of scenario ω occurring; is the selling price of the green certificate in the scenario; is the number of green certificates sold by the target power generator in scenario ω and time period t; Ω RE is a collection of wind turbine generator sets and photovoltaic generator sets; n is a wind turbine generator set or a photovoltaic generator set; is the total number of green certificates sold by the target power generator under scenario ω; a0 and b0 are two parameters respectively; The basic transaction price of green certificates; It is the transaction price ratio calculated based on historical data.
[0054] The prediction expression of the target power generator's transaction revenue in the CCER market can be: —— (12) —— (13) —— (14) Where: is the price of CCER in the scenario ω; is the number of CCERs sold by wind and solar power generators in scenario ω and time period t; Ω GRis the set of CSP power producers; τ is the carbon emission allocation coefficient per unit of renewable energy electricity; F OM is the marginal emission factor of electricity; F BM is the capacity marginal emission factor.
[0055] The prediction expression for the total return under the three markets is actually: —— (15) —— (16) Since the operating cost of a new energy generator set is relatively fixed once it is put into operation and is less affected by the amount of power generated, the above formula (15) can be simplified to —— (17) Substituting equations (5)-(14) and (16) into equation (17), we can obtain: —— (18) Where i is the ID of the target power producer; E i It represents the predicted value of the overall revenue of target generator i in the three markets; It represents the predicted value of the transaction revenue of target power generator i in the electricity market; It represents the predicted value of the transaction revenue of target power generator i in the green certificate market; It represents the predicted value of the transaction revenue of the target power producer i in the CCER market; when the target power producer is a wind power producer or a photovoltaic power producer, The value of is 1; when the target power producer is a CSP power producer, The value of is 0; δ is the risk weight coefficient of the target power generator, and its value is [0,1].
[0056] In some other embodiments, the maximum value of the overall benefit can be calculated according to the following formula: —— (19) Where i is the ID of the target power producer; E i represents the predicted value of the overall return of the target power producer i in the three markets; δ is the risk weight coefficient of the target power producer, which takes the value of [0,1]; W i1 Represents the predicted loss value of target generator i.
[0057] This implementation method calculates the overall return from a "global perspective" of the return time scale, taking into account the situation where there will be losses in individual time periods under the return time scale, which is more in line with actual trading conditions, thereby being able to more accurately calculate the overall return and keep the overall return larger.
[0058] In some embodiments, Figure 2As shown, the wind and solar power generator trading strategy optimization system under the background of separation of certificate and electricity also includes: an interactive module for receiving the value of the risk weight coefficient and the expected return input by the target power generator.
[0059] By setting up an interactive module to receive the risk weight coefficient input by the target power producer, the target power producer can adjust the calculation result of the overall profit according to the actual operating conditions and its own operating preferences. The target power producer can use it in a personalized way, so that the trading strategy formulated by the system is more in line with the expectations of the target power producer.
[0060] Furthermore, in some embodiments, the loss prediction value of the target power generator is calculated according to the following formula: —— (20) Among them, W i1 represents the loss prediction value of target power generator i; W i2 represents the acceptable loss threshold of the target generator; β represents the confidence level; π(ω) represents the probability of the occurrence of scenario ω, П represents the set of scenarios; f(ω) represents the loss value under scenario ω, P(f(ω)≥W i2 ) represents the probability that the loss value under scenario ω is greater than or equal to the acceptable loss threshold.
[0061] Next, we consider the calculation method of the loss prediction value of target power generator i. Since the market prices are uncertain, the predicted prices and actual prices often deviate from each other, so it is necessary to quantify the uncertainty of each market price to ensure the expected income of the power generator.
[0062] Under normal market fluctuation conditions, within a specific confidence level and revenue time scale, the maximum potential loss that the target generator may face can be defined as follows: --(twenty one) Among them, f(x,y) is the loss function within the return time scale; W1 is the risk value; β is the confidence level; x is the sales volume combination vector of each market; y is a random variable.
[0063] On this basis, the weighted average of the sales volume combinations in each market under the condition of losses exceeding the W1 level can better reflect the impact of small probability events in the risk. The calculation formula is as follows: --(twenty two) Where: W1 is the total loss of the target power generator; W2 is the acceptable loss threshold of the target power generator; E(·) is the weighted average of excess losses, which refers to the loss value when the loss exceeds the acceptable loss threshold of the target power generator.
[0064] However, in order to apply formula (22), it is necessary to first construct the loss function of the sales volume combination in each market. Therefore, by adopting the multi-scenario analysis method, the given confidence level β∈(0,1) is restated as the expected value when the return is lower than the (1-β) quantile in the return distribution, thereby obtaining the expected value of the return outside the confidence range. Quantifying the risk by the expected value of the return outside the confidence level can avoid the construction of a complex loss function. It is worth noting that in this case, the larger the expected value of the return outside the confidence level, the smaller the risk. The calculation formula is as follows: --(twenty three) Among them, W i1 represents the loss prediction value of target power generator i; W i2 represents the acceptable loss threshold of the target generator; β represents the confidence level; π(ω) represents the probability of the occurrence of scenario ω, П represents the set of scenarios; f(ω) represents the loss value under scenario ω, P(f(ω)≥W i2 ) represents the probability that the loss value under scenario ω is greater than or equal to the acceptable loss threshold.
[0065] The target power producer faces multiple sales volume combination decisions when participating in the three market transactions. The loss value of the target power producer under scenario ω is defined as the difference between the predicted income E and the actual income E(ω) under scenario ω. At the same time, for the convenience of solving, an auxiliary decision variable μ(ω) is introduced, and the expression is as follows: --(twenty four) —— (25) —— (26) Substituting equations (24), (25), and (26) into equations (23) and (17), we can obtain equations (27) and (28): —— (27) —— (28) In some embodiments, the wind and solar power generator trading strategy optimization system under the background of certificate-electricity separation also includes: an interaction module, and the system also includes: an interaction module for receiving the value of an acceptable loss threshold input by the target power generator.
[0066] By setting the interactive module to receive the value of the acceptable loss threshold input by the target power producer, the target power producer can adjust the calculation result of the overall profit according to the actual operating conditions and its own operating preferences. The target power producer can use it in a personalized way so that the trading strategy formulated by the system is more in line with the expectations of the target power producer.
[0067] The above formula (28) is used to calculate the overall benefit Ei When predicting the transaction volume of each market in the maximum case, the following constraints (29)-(36) are adopted: ——(29) —— (30) —— (31) —— (32) —— (33) —— (34) —— (35) —— (36) Where: Used to indicate whether the target power generator i participates in the green certificate market. The value of is 0 or 1; is the power generation cost of the target power producer; and are the lower and upper limits of the target power generator’s bid in the power market respectively; and They are the lower and upper limits of the target power generators’ quotations in the green certificate market respectively; and are the lower and upper limits of the target power generator’s bid in the CCER market; T a The average daily generating hours of the same type of units during the same period of the year; is the installed capacity of generator set n; r1 is the upper limit coefficient of green electricity energy traded by renewable power generation entities; r2 is the upper limit coefficient of green certificates traded by renewable power generation entities; Q GE The total amount of electricity sold by target wind and solar power generators; The amount of electricity required by the electricity buyer in the market during time period t; is the number of CCERs required by the electricity buyer in the day-ahead market at time period t; is the total number of CCERs sold by the target power generator under the scenario.
[0068] The above scenarios can be predetermined. A scenario refers to a combination of quotations from multiple renewable energy power generators. The quotations from the same renewable energy power generator in different scenarios during the same time period can be the same or different.
[0069] In the future, the quotations of new energy power generators are extremely uncertain. This makes it difficult to accurately predict the scenarios. In the above embodiment, when calculating the overall revenue, multiple scenarios are used for calculation, which can balance the errors of scenario predictions, improve the accuracy of overall revenue prediction, and improve the overall revenue of the target power generator.
[0070] In some embodiments, Figure 2 As shown, a first statistical module, a first determination module and a first extraction module may be set to predetermine a set of scenes.
[0071] The first statistical module is used to count the transaction prices in the electricity market, green certificate market, and CCER market in various time periods over many years in history.
[0072] The first determination module is used to determine the normal distribution data of transaction prices in the electricity market, green certificate market, and CCER market in each time period based on statistical results.
[0073] For example, we can count the transaction prices of electricity market in January of each year, and calculate the average and variance of the transaction prices of electricity market in January of each year to obtain the normal distribution data of January. Similarly, we can obtain the normal distribution data of transaction prices in other months, as well as the normal distribution data of transaction prices in each month of the green certificate market and CCER market.
[0074] The first extraction module is used to randomly determine the transaction price forecast value corresponding to each time period based on the normal distribution data of the transaction price, and take a combination of the transaction price forecast values corresponding to each time period in the electricity market, green certificate market, and CCER market as a scenario; determine a predetermined number of scenarios based on the normal distribution data of the transaction price.
[0075] For example, we can extract one data from each of the 12 normally distributed data in the electricity market from January to December, and get the 12-month electricity market transaction price forecast; extract one data from each of the 12 normally distributed data in the green certificate market from January to December, and get the 12-month green certificate market transaction price forecast; extract one data from each of the 12 normally distributed data in the CCER market from January to December, and get the 12-month CCER market transaction price forecast. Finally, the combination of the 36 transaction price forecasts of the three markets is used as a scenario.
[0076] In some embodiments, Figure 2 As shown, the wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity also includes a second statistical module, a second determination module and a second extraction module.
[0077] The second statistical module is used to count the demand in the electricity market, green certificate market, and CCER market in various time periods over many years in history.
[0078] The second determination module is used to determine the normal distribution data of demand in the electricity market, green certificate market and CCER market in each time period based on statistical results.
[0079] For example, the electricity market demand in January of each year can be counted, and the average and variance of the electricity market demand in January of each year can be calculated to obtain the normal distribution data for January. Similarly, the normal distribution data of demand in other months can be obtained, as well as the normal distribution data of demand in each month under the green certificate market and CCER market.
[0080] The second extraction module is used to randomly determine the demand forecast value corresponding to each time period based on the normal distribution data of demand, and take a combination of the transaction price forecast value and demand forecast value corresponding to each time period in the electricity market, green certificate market and CCER market as a scenario; determine a predetermined number of scenarios based on the normal distribution data of demand.
[0081] For example, we can extract one data from each of the 12 normally distributed data in the electricity market from January to December, and get the 12-month electricity market demand forecast; extract one data from each of the 12 normally distributed data in the green certificate market from January to December, and get the 12-month green certificate market demand forecast; extract one data from each of the 12 normally distributed data in the CCER market from January to December, and get the 12-month CCER market demand forecast. Finally, the combination of the 36 demand forecasts of the three markets and the 36 transaction price forecasts of the three markets is used as a scenario.
[0082] In some embodiments, the wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity further includes: an interactive module for inputting a predetermined number of values of the scenario.
[0083] Generally speaking, the more reservations a scenario has, the more accurate the normal distribution data is, and the more accurate the predictions of transaction price and demand are. By setting the value of the reservation quantity of the scenario input into the interactive module, the prediction accuracy of transaction price and demand can be flexibly adjusted, thereby improving the prediction accuracy of overall revenue and the overall revenue of the target power generator.
[0084] This manual provides a method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity. Figure 3 As shown, the method includes: S10: Obtain the operating data of each generating unit of the target power producer, as well as the historical transaction data in the electricity market, green certificate market, and CCER market.
[0085] S20: Calculate the predicted value expressions of the target power generator's transaction revenue in the electricity market, green certificate market, and CCER market respectively according to the data acquired by the data acquisition module, wherein the transaction volume in the corresponding market is an unknown variable in the predicted value expressions.
[0086] S30: Determine a prediction expression for the overall revenue in the three markets according to the calculation result of the first calculation module, and calculate the predicted value of the transaction volume in each market when the overall revenue is maximized.
[0087] S40: Generate trading instructions for corresponding market trading platforms according to the predicted values of trading volumes in each market when the overall revenue is maximized, and send them to the trading platforms of the corresponding markets so that target power generators can automatically execute trading strategies on the trading platforms of each market.
[0088] The description and functions of the above methods can be understood by referring to the content of the wind and solar power generator trading strategy optimization system under the background of separation of certificate and electricity, and will not be repeated here.
[0089] The embodiment of the present invention further provides an electronic device, such as Figure 4 As shown, the electronic device may include a processor 401 and a memory 402, wherein the processor 401 and the memory 402 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.
[0090] The processor 401 may be a central processing unit (CPU). The processor 401 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.
[0091] The memory 402, as a non-transient computer-readable storage medium, can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the wind-solar power generation company trading strategy optimization method under the background of certificate-electricity separation in the embodiment of the present invention. The processor 401 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory 402, that is, to implement the wind-solar power generation company trading strategy optimization method under the background of certificate-electricity separation in the above method embodiment.
[0092] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor 401, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 402 may optionally include a memory remotely arranged relative to the processor 401, and these remote memories may be connected to the processor 401 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0093] The one or more modules are stored in the memory 402, and when executed by the processor 401, the following is performed: Figure 3 The illustrated embodiment shows a method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity.
[0094] The specific details of the above electronic device can be understood by referring to the corresponding descriptions and effects in the method embodiment, and will not be repeated here.
[0095] This specification also provides a computer storage medium, which stores computer program instructions. When the computer program instructions are executed, the steps of the method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity are implemented.
[0096] This specification also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for optimizing the trading strategy of wind and solar power generators under the background of separation of certificate and electricity.
[0097] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.
[0098] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0099] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions.
[0100] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0101] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute certain parts of the methods of each implementation method of the present application.
[0102] The present application can be used in many general or special computer system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.
[0103] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0104] Although the present application has been described through embodiments, those skilled in the art will appreciate that there are many modifications and variations to the present application without departing from the spirit of the present application, and it is intended that the appended claims include these modifications and variations without departing from the spirit of the present application.
Claims
1. A wind and solar power generation company transaction strategy optimization system under the background of separation of certificate and electricity, characterized in that: include: The data acquisition module is used to obtain the operating data of each generator set of the target power producer, as well as the historical transaction data in the power market, green certificate market, and CCER market; The first calculation module is used to calculate the predicted value expressions of the transaction revenue of the target power generator in the power market, the green certificate market, and the CCER market respectively according to the data acquired by the data acquisition module, wherein the transaction volume in the corresponding market is an unknown variable in the predicted value expression; A second calculation module is used to determine the prediction expression of the overall return in the three markets according to the calculation result of the first calculation module, and calculate the predicted value of the transaction volume of each market when the overall return is maximized; The generation module is connected to the trading platforms of the electricity market, green certificate market, and CCER market respectively; the generation module is used to generate trading instructions for the corresponding market trading platform according to the predicted value of the transaction volume of each market when the overall profit is maximized, and send it to the trading platform of the corresponding market, so that the target power generator can automatically execute the trading strategy on each market trading platform.
2. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 1 is characterized in that: The system further comprises: The interactive module is used to receive the profit time scale input by the target power producer, wherein the profit time scale is used to indicate the time scale within which the overall profit is expected to be maximized.
3. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 1 is characterized in that: The maximum value of the overall return under the three markets is calculated according to the following formula: ; Where i is the ID of the target power producer; E i It represents the predicted value of the overall revenue of target generator i in the three markets; It represents the predicted value of the transaction revenue of target power generator i in the electricity market; It represents the predicted value of the transaction revenue of target power generator i in the green certificate market; It represents the predicted value of the transaction revenue of the target power producer i in the CCER market; when the target power producer is a wind power producer or a photovoltaic power producer, The value of is 1; when the target power producer is a CSP power producer, The value of is 0.
4. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 1 is characterized in that: The maximum value of the overall benefit is calculated according to the following formula: ; ; Where i is the ID of the target power producer; E i It represents the predicted value of the overall revenue of target generator i in the three markets; It represents the predicted value of the transaction revenue of target power generator i in the electricity market; It represents the predicted value of the transaction revenue of target power generator i in the green certificate market; It represents the predicted value of the transaction revenue of the target power producer i in the CCER market; when the target power producer is a wind power producer or a photovoltaic power producer, The value of is 1; when the target power producer is a CSP power producer, The value of is 0; δ is the risk weight coefficient of the target power generator, and its value is [0,1]; W i1 Represents the predicted loss value of target generator i.
5. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 1 is characterized in that: The system further comprises: The interactive module is used to receive the value of the risk weight coefficient input by the target power producer.
6. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 5 is characterized in that: The loss forecast value of the target power generator is calculated according to the following formula: ; Among them, W i1 represents the loss prediction value of target power generator i; W i2 represents the acceptable loss threshold of the target generator; β represents the confidence level; π(ω) represents the probability of the occurrence of scenario ω, П represents the set of scenarios; f(ω) represents the loss value under scenario ω, P(f(ω)≥W i2 ) represents the probability that the loss value under scenario ω is greater than or equal to the acceptable loss threshold.
7. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 6 is characterized in that: The system further comprises: The interactive module is used to receive the value of the acceptable loss threshold input by the target power producer.
8. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 1 is characterized in that: The system further comprises: The first statistical module is used to count the transaction prices in the electricity market, green certificate market, and CCER market in various time periods over many years in history; The first determination module is used to determine the normal distribution data of transaction prices in the power market, green certificate market, and CCER market in each time period according to the statistical results; The first extraction module is used to randomly determine the transaction price forecast value corresponding to each time period based on the normal distribution data of the transaction price, and take a combination of the transaction price forecast values corresponding to each time period in the electricity market, green certificate market, and CCER market as a scenario; determine a predetermined number of scenarios based on the normal distribution data of the transaction price.
9. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 8 is characterized in that: The system further comprises: The second statistical module is used to count the demand in the electricity market, green certificate market, and CCER market in various time periods over many years in history; The second determination module is used to determine the normal distribution data of demand in the power market, green certificate market, and CCER market in each time period according to the statistical results; The second extraction module is used to randomly determine the demand forecast value corresponding to each time period based on the normal distribution data of demand, and take a combination of the transaction price forecast value and demand forecast value corresponding to each time period in the electricity market, green certificate market and CCER market as a scenario; determine a predetermined number of scenarios based on the normal distribution data of demand.
10. The wind and solar power generator transaction strategy optimization system under the background of separation of certificate and electricity according to claim 8 or 9, characterized in that: The system further comprises: The interactive module is used to input a predetermined number of values of the scene.
11. A method for optimizing the trading strategy of wind and solar power generators under the background of separation of license and electricity, characterized in that: include: Obtain the operating data of each generating unit of the target power producer, as well as the historical transaction data in the power market, green certificate market, and CCER market; Calculate the predicted value expressions of the target power generator's transaction revenue in the electricity market, green certificate market, and CCER market respectively based on the acquired data, wherein the transaction volume in the corresponding market is an unknown variable in the predicted value expressions; Determine the prediction expression of the overall return under the three markets based on the calculation results, and calculate the predicted value of the transaction volume of each market when the overall return is the largest; The trading instructions of the corresponding market trading platform are generated according to the predicted value of the transaction volume of each market when the overall profit is maximized, and sent to the trading platform of the corresponding market, so that the target power generator can automatically execute the trading strategy on each market trading platform.
12. An electronic device, characterized in that: include: A memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor implements the wind-solar power generation company trading strategy optimization system in the context of separation of certificate and electricity as described in any one of claims 1 to 10 by executing the computer instructions.
Citation Information
Patent Citations
Foreground theory-based power generator auxiliary quotation system and method for electric power spot market
CN112001744A
Typical scene generation method and system for high-proportion new energy power system
CN117955098A
Electricity-carbon-green evidence multi-subject coupled power plant optimal power generation decision balancing system
CN118554425A
Park electricity purchase combination optimization method and device based on electricity, carbon and green certificate market coupling
CN118839802A
High-energy-consumption user energy combination transaction method and computing device
CN118863373A
