Cooperative scheduling method and system for carbon transaction

Abstract

The invention provides a collaborative scheduling method and system for carbon transaction, and relates to the technical field of power scheduling. Reading a predetermined carbon emission quota; carrying out multi-energy complementary power supply quota analysis by taking the carbon emission quota smaller than the preset carbon emission quota as a limit in order to meet the predicted power consumption demand, and determining a plurality of simulation power supply schemes; screening the plurality of simulation power supply schemes by using a power supply evaluation function to determine an expected power supply scheme; and executing power supply cooperative scheduling of a future window based on the expected power supply scheme. According to the method, the technical problem that the existing scheduling method always focuses on scheduling of single energy and neglects the potential of multi-energy complementation, so that the flexibility of energy supply is insufficient is solved, and the technical effects of improving the flexibility and reliability of energy supply and promoting efficient utilization of green energy are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of power dispatching, and specifically to a collaborative dispatching method and system for carbon trading. Background Art

[0003] The coordinated dispatching method of carbon trading is one of the key technologies to achieve this goal. It involves multiple energy resources in the power system, such as thermal power generation, wind power generation and photovoltaic power generation. It controls carbon emissions within the predetermined quota while meeting electricity demand through optimized dispatching. Existing carbon trading dispatching methods usually focus on the dispatching optimization of a single energy source and lack in-depth analysis and utilization of the complementarity of multiple energy sources. These methods often rely on historical data and simple statistical models when predicting electricity demand, making it difficult to accurately predict future electricity consumption trends and respond to emergencies. In addition, the existing methods fail to achieve refined management when dealing with the matching of carbon emission quotas with energy supply, which may lead to quota waste or excessive emissions, affecting the effectiveness of carbon trading and the economic interests of enterprises. Summary of the invention

[0004] The present application provides a collaborative scheduling method and system for carbon trading, which solves the technical problem that existing scheduling methods often focus on the scheduling of a single energy source, ignore the potential for complementarity among multiple energy sources, and lead to insufficient flexibility in energy supply. It achieves the technical effect of improving the flexibility and reliability of energy supply and promoting the efficient use of green energy.

[0005] In view of the above problems, on the one hand, the present application provides a collaborative scheduling method for carbon trading, which includes: predicting the electricity demand of future windows in the target area; reading a predetermined carbon emission quota; with the purpose of meeting the predicted electricity demand and with the limit of being less than the predetermined carbon emission quota, conducting a multi-energy complementary power supply quota analysis and determining multiple simulated power supply schemes; using a power supply evaluation function to screen the multiple simulated power supply schemes to determine an expected power supply scheme; and performing collaborative power supply scheduling for future windows based on the expected power supply scheme.

[0006] On the other hand, the present application also provides a collaborative scheduling system for carbon trading, the system comprising: an electricity demand prediction module, the electricity demand prediction module is used to predict the electricity demand of future windows in the target area; a carbon emission quota reading module, the carbon emission quota reading module is used to read a predetermined carbon emission quota; a simulated power supply plan determination module, the simulated power supply plan determination module is used to perform multi-energy complementary power supply quota analysis for the purpose of meeting the predicted electricity demand, with the limit of being less than the predetermined carbon emission quota, and determine multiple simulated power supply plans; an expected power supply plan determination module, the expected power supply plan determination module is used to use the power supply evaluation function to screen the multiple simulated power supply plans and determine the expected power supply plan; a plan execution module, the plan execution module is used to execute power supply collaborative scheduling of future windows based on the expected power supply plan.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Predict the electricity demand of future windows in the target area, provide data support for the subsequent determination of power supply plans, and ensure the reliability and efficiency of power supply. Read the predetermined carbon emission quota to provide an upper limit of carbon emissions for energy scheduling, and ensure the environmental friendliness of the scheduling plan. With the purpose of meeting the predicted electricity demand and the limit of being less than the predetermined carbon emission quota, conduct multi-energy complementary power supply quota analysis and determine multiple simulated power supply plans. This step takes into account the complementarity of multiple energy sources to achieve the optimization of energy structure and the minimization of carbon emissions. Use the power supply evaluation function to screen the multiple simulated power supply plans and determine the expected power supply plan; based on the expected power supply plan, perform coordinated power supply scheduling for future windows.

[0009] In summary, this application achieves accurate matching of energy supply and demand and refined management of carbon emissions through accurate prediction, multi-energy complementary analysis, fine optimization and real-time scheduling. Multi-energy complementary power supply quota analysis optimizes the energy structure, enhances the flexibility of energy supply while meeting the carbon emission quota limit, and promotes the efficient use of green energy and the development of a low-carbon economy.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of a process flow of a coordinated scheduling method for carbon trading provided in an embodiment of the present application;

[0012] Figure 2A schematic diagram of a flow chart for performing multi-energy complementary power supply quota analysis in a coordinated scheduling method for carbon trading provided in an embodiment of the present application;

[0013] Figure 3 A schematic diagram of the structure of a collaborative scheduling system for carbon trading provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: electricity demand prediction module 10 , carbon emission quota reading module 20 , simulated power supply plan determination module 30 , expected power supply plan determination module 40 , plan execution module 50 . DETAILED DESCRIPTION

[0015] The embodiments of the present application provide a collaborative scheduling method and system for carbon trading, which solves the technical problem that existing scheduling methods often focus on the scheduling of a single energy source, ignore the potential for complementarity among multiple energy sources, and lead to insufficient flexibility in energy supply. This achieves the technical effect of improving the flexibility and reliability of energy supply and promoting the efficient use of green energy.

[0016] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a coordinated scheduling method for carbon trading, the method comprising:

[0017] Step S1: predicting the electricity demand of future windows in the target area.

[0018] Specifically, the future window refers to a period of time in the future, such as a specific time period in the next week, month or day. The target area refers to a specific geographical area for coordinated scheduling, such as a city or region. By predicting the electricity demand in the future window in the target area, a decision-making basis is provided for energy coordinated scheduling.

[0019] Furthermore, step S1 of the embodiment of the present application further includes:

[0020] Call the historical electricity consumption log of the target area, match the historical electricity consumption log with a future window, and obtain a historical electricity consumption data set; determine the historical electricity consumption mean and the electricity consumption trend within the historical period based on the historical electricity consumption data set; compensate the historical electricity consumption mean with the electricity consumption trend to obtain the predicted electricity demand.

[0021] Specifically, the historical electricity consumption logs of the target area are first called. These historical electricity consumption logs contain the electricity consumption data of the target area in a certain period in the past. They usually record the daily and hourly electricity consumption in detail, which is an important reference for predicting future electricity demand. Among the large number of historical electricity consumption logs called, the data matching the future window time period is screened out to form a historical electricity consumption data set. For example, if the future window is the first week of August 2023, the daily electricity consumption data is extracted from the electricity consumption logs from 2018 to the first week of August 2022. The average electricity consumption of the historical electricity consumption data set in a specific period is calculated to reflect the average electricity consumption level of the target area. Based on the electricity consumption data in the historical period, the law of electricity consumption changes over time is analyzed, including seasonal fluctuations, differences between working days and holidays, etc. The electricity consumption trend is applied to the historical electricity consumption mean, that is, the mean is adjusted according to the electricity consumption trend to obtain a more accurate prediction of electricity demand.

[0022] For example, the historical electricity consumption dataset shows that the average daily electricity consumption in the first week of August in the past five years is 5 million kWh, so the historical average electricity consumption is 5 million kWh. Analysis of the historical electricity consumption dataset shows that electricity consumption in the first week of August usually drops by 10% on weekends and increases by 10% on weekdays. Based on the electricity consumption trend, the demand is adjusted to 4.5 million kWh on weekends and 5.5 million kWh on weekdays.

[0023] The above steps comprehensively consider the historical electricity consumption patterns and time patterns, and can accurately predict the electricity demand in the future window based on historical data and electricity consumption trends, providing an accurate basis for subsequent power supply scheduling.

[0024] Step S2: Reading the predetermined carbon emission quota.

[0025] Specifically, the scheduled carbon emission quota is the carbon emission quota that has been determined and allocated to the target area before power dispatch and carbon trading. Read the scheduled carbon emission quota data from the database provided by the regulatory agency. These data may be provided in electronic files, database records or through an API interface. Verify the read scheduled carbon emission quota, including checking the allocation time, validity period and whether there are any latest adjustments or updates to ensure its accuracy and timeliness. Store the verified scheduled carbon emission quota in the system so that in the subsequent multi-energy complementary power supply quota analysis and power supply coordinated dispatching steps, these quota data can be used to ensure that all simulated power supply plans and actually implemented dispatching plans meet the requirements of carbon emission quotas.

[0026] Step S3: For the purpose of meeting the predicted electricity demand and subject to the limit of being less than the predetermined carbon emission quota, a multi-energy complementary power supply quota analysis is performed to determine a plurality of simulated power supply schemes.

[0027] Furthermore, the multi-energy power supply types described in the embodiments of the present application include at least thermal power generation, wind power generation and photovoltaic power generation.

[0028] Specifically, multi-energy complementary power supply refers to a power supply method that combines multiple energy forms to improve energy utilization efficiency and power supply reliability by optimizing the combined use of different energy sources. These energy types include but are not limited to thermal power generation, wind power generation and photovoltaic power generation.

[0029] In step S3, firstly, according to different energy types and their power generation characteristics, the power supply capacity of different energy types is analyzed, and multiple possible power supply schemes are constructed. These schemes will take into account factors such as the availability, cost, and environmental impact of various energy sources. For each simulated power supply scheme, its total carbon emissions under the predicted electricity demand are calculated. Check whether the carbon emissions of each simulated power supply scheme are less than or equal to the predetermined carbon emission quota. The scheme that meets the predetermined carbon emission quota limit is determined as the simulated power supply scheme. Through this analysis, it is possible to effectively control carbon emissions while ensuring power supply and support sustainable development goals.

[0030] Further, such as Figure 2 As shown, in step S3 of the embodiment of the present application, a multi-energy complementary power supply quota analysis is performed, including:

[0031] The historical power supply log of the target area is read, and the historical power supply log is matched with the future window and the power supply type to obtain a wind power generation data set and a photovoltaic power generation data set, wherein the power generation data includes a sample power generation factor set and a sample power generation; the BP neural network is trained using the wind power generation data set and the photovoltaic power generation data set to obtain a wind power generation predictor and a photovoltaic power generation predictor; based on the wind power generation predictor and the photovoltaic power generation predictor, the predicted wind power generation and the predicted photovoltaic power generation of the future window are predicted; based on the predicted wind power generation and the predicted photovoltaic power generation, a multi-energy complementary power supply quota analysis is performed to determine multiple simulated power supply schemes.

[0032] Specifically, the historical power supply log of the target area is called, and by matching the future window and power supply type, wind power generation data and photovoltaic power generation data under similar conditions to the future window are extracted from the historical power supply log, including power generation factors and sample power generation, to form wind power generation data sets and photovoltaic power generation data sets. Among them, power generation factors are environmental factors that affect power generation, such as wind speed, light intensity, etc.

[0033] A BP neural network is trained using the wind power generation data set and the photovoltaic power generation data set to obtain a wind power generation predictor and a photovoltaic power generation predictor. The BP neural network is trained using the back propagation algorithm, and by adjusting the weights and biases, a prediction model that can predict wind power and photovoltaic power generation is finally obtained.

[0034] Obtain the predicted power generation factors in the future window, such as wind speed and light intensity. These predicted power generation factors can be obtained through the forecast data of the meteorological station. Input the predicted power generation factors in the future window into the trained wind power generation predictor and photovoltaic power generation predictor to predict the predicted wind power generation and photovoltaic power generation in the future window.

[0035] Based on the predicted wind and photovoltaic power generation, as well as the fixed emissions of thermal power generation, a multi-energy complementary power supply quota analysis is conducted to determine multiple simulated power supply plans that meet electricity demand and do not exceed the carbon emission quota.

[0036] The above steps fully take into account the instability of renewable energy. Through prediction technology, the accuracy of the multi-energy complementary power supply strategy is improved, ensuring the low-carbon and high-efficiency of power supply scheduling.

[0037] Furthermore, in step S3 of the embodiment of the present application, multiple simulated power supply schemes are determined, including:

[0038] Based on unit thermal power carbon emissions, unit wind power carbon emissions and unit photovoltaic carbon emissions, with the purpose of meeting the predicted electricity demand and the limit of being less than the predetermined carbon emission quota, a multi-energy complementary power supply quota analysis is performed according to the predicted wind power generation and the predicted photovoltaic power generation, and multiple simulated power supply plans are determined, wherein the simulated power supply plan includes a simulated thermal power generation ratio, a simulated wind power generation ratio and a simulated photovoltaic power generation ratio.

[0039] Specifically, unit thermal power carbon emissions, unit wind power carbon emissions and unit photovoltaic carbon emissions refer to the carbon dioxide emissions generated per unit of power generation in thermal power generation, wind power generation and photovoltaic power generation, respectively. The unit thermal power carbon emissions, unit wind carbon emissions and unit photovoltaic carbon emissions of thermal power generation, wind power generation and photovoltaic power generation are determined based on historical data. Under the predicted electricity demand, based on the unit carbon emissions, the total carbon emissions of different energy combinations are calculated, and multiple simulated power supply plans that meet the conditions are designed with the limit of being less than the predetermined carbon emission quota. Each simulated power supply plan includes a simulated thermal power generation ratio, a simulated wind power generation ratio and a simulated photovoltaic power generation ratio.

[0040] Step S4: screening the multiple simulated power supply schemes using the power supply evaluation function to determine the expected power supply scheme.

[0041] Specifically, the power supply evaluation function is a mathematical function used to evaluate the performance of the power supply scheme. This function evaluates the simulated power supply scheme by integrating multiple factors including power supply reliability and carbon emissions. First, according to the specific scheduling requirements and goals, the power supply evaluation function is defined, and the evaluation function is used to score each generated simulated power supply scheme to obtain multiple scoring results. Each scoring result reflects the comprehensive performance of the corresponding scheme in all evaluation indicators. According to the scoring results, the scheme with the highest score is selected as the expected power supply scheme for subsequent power supply coordinated scheduling.

[0042] Furthermore, step S4 of the embodiment of the present application also includes:

[0043] Constructing a power supply evaluation function; based on the credibility of thermal power generation, wind power generation and photovoltaic power generation, using the power supply evaluation function to screen the multiple simulated power supply schemes, and selecting the simulated power supply scheme with the largest evaluation fitness as the expected power supply scheme.

[0044] Furthermore, the power supply evaluation function in step S4 of the embodiment of the present application is:

[0045]

[0046] Among them, F(i) is the evaluation fitness of the ith simulated power supply scheme, w1 is the power generation credibility weight, w2 is the carbon emission weight, P i is the overall power generation credibility of the ith simulated power supply scheme, T i is the overall power supply carbon emissions of the ith simulated power supply scheme.

[0047] Specifically, firstly, an evaluation function is constructed based on power generation credibility and carbon emissions as follows:

[0048]

[0049] In this function, F(i) is the output of the evaluation function, which indicates the evaluation fitness of the i-th simulated power supply scheme, and i is the number of the simulated power supply scheme. The higher the fitness, the more the power supply scheme can meet the predetermined goals and constraints. w1 is the power generation credibility weight, which is used to adjust the importance of power generation credibility in the evaluation function. w2 is the carbon emission weight, which is used to adjust the importance of carbon emissions in the evaluation function. w1 and w2 can be determined through expert consultation, historical data analysis or policy guidance.

[0050] P i is the overall power generation credibility of the ith simulated power supply scheme, which can be obtained by calculating the power generation credibility of each energy type and taking the weighted average. i is the overall power supply carbon emission of the ith simulated power supply scheme, which is obtained by calculating the carbon emission of each energy type and summing them up.

[0051] In this function, power generation credibility is the accuracy of predicted power generation or the stability of power generation resources. In a multi-energy complementary power supply system, the credibility of thermal power generation, wind power generation, and photovoltaic power generation will affect the power supply security and economy of the entire system. Power generation methods with high credibility are more reliable and can reduce power supply gaps caused by inaccurate predictions. Power generation credibility can be evaluated based on historical data, equipment performance, weather conditions, and other factors. Thermal power generation usually has a higher credibility, while wind and photovoltaic power generation are greatly affected by weather conditions and have lower credibility.

[0052] The overall power generation credibility and overall carbon emissions of each simulated power supply scheme are calculated and input into the above-constructed evaluation function. The power supply evaluation function is used to evaluate multiple simulated power supply schemes and calculate the fitness score of each scheme. The higher the score, the better the overall performance of the scheme in all indicators considered by the evaluation function. Finally, the scheme with the largest evaluation fitness is selected from all simulated power supply schemes as the expected power supply scheme. This scheme is considered to be the best under the current evaluation system. It can meet the electricity demand while reaching the predetermined carbon emission quota limit, and has high credibility and environmental friendliness.

[0053] Step S5: Execute power supply coordinated scheduling for future windows based on the expected power supply plan.

[0054] Specifically, according to the best power supply plan selected in step S4, the power supply proportion of different energy types in the future window is coordinated, the expected power supply plan is communicated to each power generation unit and the grid control system, and specific power generation and transmission operations are performed to ensure that the power system operates in the best way while meeting power demand and carbon emission quota restrictions. In addition, during the execution process, the dispatching system will dynamically adjust the ratio of thermal, wind and photovoltaic power generation according to the real-time changes in actual power generation and power demand to ensure the stability and economy of power supply. For example, if wind power generation exceeds expectations, thermal power generation can be appropriately reduced to reduce carbon emissions.

[0055] In summary, the coordinated scheduling method for carbon trading provided in the embodiments of the present application has the following technical effects:

[0056] Deep learning of historical electricity consumption data and combining electricity consumption trends to predict electricity demand in future windows in the target area provide data support for the subsequent determination of power supply plans, ensuring the reliability and efficiency of power supply. Reading the predetermined carbon emission quota provides an upper limit of carbon emissions for energy scheduling, ensuring the environmental friendliness of the scheduling plan. With the purpose of meeting the predicted electricity demand and the limit of being less than the predetermined carbon emission quota, a multi-energy complementary power supply quota analysis is carried out to determine multiple simulated power supply plans. This step takes into account the complementarity of multiple energy sources and balances the ratio of thermal, wind and photovoltaic power generation to achieve energy structure optimization and minimize carbon emissions. The use of BP neural network to predict wind and photovoltaic power generation further enhances the scientific nature and predictability of energy scheduling and ensures the maximum utilization of green energy. The multiple simulated power supply plans are screened using the power supply evaluation function to determine the expected power supply plan, ensuring the optimization of scheduling decisions. Power supply collaborative scheduling of future windows is performed based on the expected power supply plan.

[0057] Overall, the embodiments of the present application achieve accurate matching of energy supply and demand and refined management of carbon emissions through accurate prediction, multi-energy complementary analysis, fine optimization and real-time scheduling. Multi-energy complementary power supply quota analysis optimizes the energy structure, enhances the flexibility of energy supply while meeting the carbon emission quota limit, and promotes the efficient use of green energy and the development of a low-carbon economy.

[0058] Embodiment 2, as Figure 3 As shown, the embodiment of the present application provides a coordinated scheduling system for carbon trading, the system comprising:

[0059] The power demand prediction module 10 is used to predict the power demand of future windows in the target area.

[0060] The carbon emission quota reading module 20 is used to read a predetermined carbon emission quota.

[0061] The simulated power supply scheme determination module 30 is used to perform multi-energy complementary power supply quota analysis and determine multiple simulated power supply schemes for the purpose of meeting the predicted power demand and subject to a limit of being less than the predetermined carbon emission quota.

[0062] The expected power supply scheme determining module 40 is used to screen the multiple simulated power supply schemes by using a power supply evaluation function to determine an expected power supply scheme.

[0063] A scheme execution module 50 is used to execute power supply coordinated scheduling of future windows based on the expected power supply scheme.

[0064] Furthermore, the power demand prediction module 10 of the embodiment of the present application is also used to perform the following steps:

[0065] Call the historical electricity consumption log of the target area, match the historical electricity consumption log with a future window, and obtain a historical electricity consumption data set; determine the historical electricity consumption mean and the electricity consumption trend within the historical period based on the historical electricity consumption data set; compensate the historical electricity consumption mean with the electricity consumption trend to obtain the predicted electricity demand.

[0066] Furthermore, the multi-energy power supply types described in the embodiments of the present application include at least thermal power generation, wind power generation and photovoltaic power generation.

[0067] Furthermore, the simulated power supply scheme determination module 30 of the embodiment of the present application is also used to perform the following steps:

[0068] The historical power supply log of the target area is read, and the historical power supply log is matched with the future window and the power supply type to obtain a wind power generation data set and a photovoltaic power generation data set, wherein the power generation data includes a sample power generation factor set and a sample power generation; the BP neural network is trained using the wind power generation data set and the photovoltaic power generation data set to obtain a wind power generation predictor and a photovoltaic power generation predictor; based on the wind power generation predictor and the photovoltaic power generation predictor, the predicted wind power generation and the predicted photovoltaic power generation of the future window are predicted; based on the predicted wind power generation and the predicted photovoltaic power generation, a multi-energy complementary power supply quota analysis is performed to determine multiple simulated power supply schemes.

[0069] Furthermore, the simulated power supply scheme determination module 30 of the embodiment of the present application is also used to perform the following steps:

[0070] Based on unit thermal power carbon emissions, unit wind power carbon emissions and unit photovoltaic carbon emissions, with the purpose of meeting the predicted electricity demand and the limit of being less than the predetermined carbon emission quota, a multi-energy complementary power supply quota analysis is performed according to the predicted wind power generation and the predicted photovoltaic power generation, and multiple simulated power supply plans are determined, wherein the simulated power supply plan includes a simulated thermal power generation ratio, a simulated wind power generation ratio and a simulated photovoltaic power generation ratio.

[0071] Furthermore, the power supply scheme determination module 40 of the embodiment of the present application is expected to be further configured to perform the following steps:

[0072] Constructing a power supply evaluation function; based on the credibility of thermal power generation, wind power generation and photovoltaic power generation, using the power supply evaluation function to screen the multiple simulated power supply schemes, and selecting the simulated power supply scheme with the largest evaluation fitness as the expected power supply scheme.

[0073] Furthermore, the power supply evaluation function in the power supply scheme determination module 40 of the embodiment of the present application includes:

[0074]

[0075] Among them, F(i) is the evaluation fitness of the ith simulated power supply scheme, w1 is the power generation credibility weight, w2 is the carbon emission weight, P i is the overall power generation credibility of the ith simulated power supply scheme, T i is the overall power supply carbon emissions of the ith simulated power supply scheme.

[0076] Through the above detailed description of the collaborative scheduling method for carbon trading in this specification, those skilled in the art can clearly understand the collaborative scheduling system for carbon trading in this embodiment. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, the relevant parts can be referred to the description of the method part.

[0077] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A collaborative scheduling method for carbon trading, characterized in that: include: Predict future window electricity demand in the target area; Read the scheduled carbon emission quota; To meet the predicted electricity demand and to be less than the predetermined carbon emission quota, a multi-energy complementary power supply quota analysis is performed to determine multiple simulated power supply plans; Using a power supply evaluation function to screen the multiple simulated power supply schemes to determine an expected power supply scheme; Power supply coordinated scheduling of future windows is performed based on the expected power supply plan.

2. The coordinated scheduling method for carbon trading according to claim 1, characterized in that: Get forecasted electricity demand, including: Call the historical electricity consumption log of the target area, match the historical electricity consumption log with the future window, and obtain the historical electricity consumption data set; Determine the historical electricity consumption average and the electricity consumption trend within the historical period based on the historical electricity consumption data set; The historical average power consumption is compensated by the power consumption trend to obtain the predicted power demand.

3. The coordinated scheduling method for carbon trading according to claim 1, characterized in that: Multi-energy power supply types include at least thermal power generation, wind power generation and photovoltaic power generation.

4. The coordinated scheduling method for carbon trading according to claim 3 is characterized in that: Conduct multi-energy complementary power supply quota analysis, including: Read the historical power supply log of the target area, match the historical power supply log with the future window and power supply type, and obtain a wind power generation data set and a photovoltaic power generation data set, wherein the power generation data includes a sample power generation factor set and a sample power generation; Using the wind power generation data set and the photovoltaic power generation data set to train a BP neural network to obtain a wind power generation predictor and a photovoltaic power generation predictor; Based on the wind power generation predictor and the photovoltaic power generation predictor, predict the predicted wind power generation and the predicted photovoltaic power generation in the future window; Based on the predicted wind power generation and the predicted photovoltaic power generation, a multi-energy complementary power supply quota analysis is performed to determine a plurality of simulated power supply schemes.

5. The coordinated scheduling method for carbon trading according to claim 4, characterized in that: Identify multiple simulated power supply options, including: Based on unit thermal power carbon emissions, unit wind power carbon emissions and unit photovoltaic carbon emissions, with the purpose of meeting the predicted electricity demand and the limit of being less than the predetermined carbon emission quota, a multi-energy complementary power supply quota analysis is performed according to the predicted wind power generation and the predicted photovoltaic power generation, and multiple simulated power supply plans are determined, wherein the simulated power supply plan includes a simulated thermal power generation ratio, a simulated wind power generation ratio and a simulated photovoltaic power generation ratio.

6. The coordinated scheduling method for carbon trading according to claim 5, characterized in that: Determine the expected power supply plan, including: Construct power supply evaluation function; Based on the credibility of thermal power generation, wind power generation and photovoltaic power generation, the multiple simulated power supply schemes are screened using the power supply evaluation function, and the simulated power supply scheme with the largest evaluation fitness is selected as the expected power supply scheme.

7. The coordinated scheduling method for carbon trading according to claim 6, characterized in that: Construct a power supply evaluation function, including: Among them, F(i) is the evaluation fitness of the ith simulated power supply scheme, w1 is the power generation credibility weight, w2 is the carbon emission weight, P i is the overall power generation credibility of the ith simulated power supply scheme, T i is the overall power supply carbon emissions of the ith simulated power supply scheme.

8. A coordinated dispatching system for carbon trading, characterized in that: The system is used to execute the coordinated scheduling method for carbon trading according to any one of claims 1 to 7, comprising: A power demand prediction module, which is used to predict the power demand of future windows in the target area; A carbon emission quota reading module, wherein the carbon emission quota reading module is used to read a predetermined carbon emission quota; A simulated power supply scheme determination module, the simulated power supply scheme determination module is used to perform a multi-energy complementary power supply quota analysis and determine a plurality of simulated power supply schemes for the purpose of meeting the predicted power demand and subject to a limit of being less than the predetermined carbon emission quota; An expected power supply scheme determination module, the expected power supply scheme determination module is used to screen the multiple simulated power supply schemes using a power supply evaluation function to determine an expected power supply scheme; A scheme execution module is used to execute power supply coordinated scheduling of future windows based on the expected power supply scheme.

Images