Renewable energy consumption responsibility evaluation method based on carbon market system

By acquiring and processing meteorological, power grid, and power load data, and using machine learning models to predict renewable energy generation, calculate carbon emissions, and conduct carbon market trading, the problems of low renewable energy utilization efficiency and inaccurate carbon emission management have been solved, achieving optimized power system scheduling and efficient renewable energy consumption.

CN119026831APending Publication Date: 2024-11-26ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410992482.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Existing technologies suffer from low renewable energy utilization efficiency, imprecise carbon emission management, and a lack of dynamic adjustment mechanisms, resulting in inflexible grid dispatching and carbon market operation, which hinders the integration and utilization of a higher proportion of renewable energy.

Method used

By acquiring meteorological, power grid, and electricity load data, machine learning models are used to predict renewable energy power generation, calculate carbon emissions, design and optimize models, conduct carbon market trading, determine renewable energy consumption responsibilities and assessment standards, and dynamically adjust consumption responsibility targets.

Benefits of technology

It has improved the accuracy and fairness of renewable energy consumption, optimized power system dispatch and carbon emission management, and promoted the efficient use of renewable energy and the achievement of carbon emission reduction targets.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026831A_ABST
    Figure CN119026831A_ABST
Patent Text Reader

Abstract

The invention relates to the field of power markets, and discloses a renewable energy consumption responsibility evaluation method based on a carbon market system, and the method comprises the following steps: S1, obtaining meteorological data, power grid data and power load data, and carrying out the preprocessing; s2, on the basis of the preprocessed data, utilizing a machine learning model to predict the future renewable energy power generation amount; s3, calculating carbon emission according to the power generation data and the emission factors; s4, designing an optimization model based on renewable energy prediction and carbon emission calculation results, determining an optimization target and constraint conditions, and solving an optimal scheduling scheme; s5, designing a carbon quota allocation method and a transaction rule, and carrying out carbon market transaction; and S6, calculating the renewable energy consumption responsibility of each region, and formulating a consumption responsibility target and an assessment standard. According to the invention, the accuracy and fairness of renewable energy consumption are improved, the scheduling and carbon emission management of the power system are optimized, and the efficient utilization of renewable energy and the realization of the target of carbon emission reduction are promoted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electricity market, and in particular to a method for evaluating the responsibility for absorbing renewable energy based on a carbon market system. Background Art

[0002] In the context of the current global energy transition, integrating renewable energy into the power system has become an urgent task. Although renewable energy such as wind and solar power is essential for reducing carbon emissions, its unstable and unpredictable characteristics pose significant challenges to the dispatch and management of the power grid. In addition, the existing electricity market mechanism often fails to fully incentivize the use of renewable energy, and carbon emission management lacks sufficient flexibility and precision, which limits the promotion and application of low-carbon technologies.

[0003] In the carbon emissions trading market, although a carbon trading mechanism has been established, market participants often face problems such as large fluctuations in carbon prices and opaque trading rules, which are not conducive to long-term investment and planning by enterprises. At the same time, the monitoring and reporting system for carbon emissions usually lacks the flexibility to adapt to the dynamics of the power market, resulting in carbon emissions data sometimes being out of sync with the actual situation, affecting the effective operation of the carbon market.

[0004] The existing assessment and regulatory mechanisms for renewable energy consumption are usually relatively static and difficult to cope with the high volatility of renewable energy output, which hinders the access and utilization of a higher proportion of renewable energy. Therefore, existing technologies have obvious shortcomings in improving energy efficiency, optimizing carbon emission management, and promoting the wider application of renewable energy. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a renewable energy consumption responsibility assessment method based on the carbon market system, which solves the problems of low renewable energy utilization efficiency, inaccurate carbon emission management and lack of dynamic adjustment mechanism in the existing technology, and improves the environmental performance and economic efficiency of the power market by optimizing the scheduling and consumption of carbon emissions and renewable energy.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A renewable energy consumption responsibility assessment method based on a carbon market system comprises the following steps:

[0007] Obtain meteorological data, power grid data and power load data, and clean and pre-process the data;

[0008] Based on the preprocessed data, the machine learning model is used to predict the future renewable energy generation;

[0009] Calculate carbon emissions based on power generation data and emission factors;

[0010] Based on renewable energy forecasts and carbon emission calculation results, design optimization models, determine optimization objectives and constraints, and solve the optimal scheduling plan;

[0011] Design carbon quota allocation methods and trading rules, and conduct carbon market transactions;

[0012] Calculate the renewable energy consumption responsibility of each region, and formulate consumption responsibility targets and assessment standards.

[0013] Preferably, the step of acquiring meteorological data, power grid data and power load data, and cleaning and preprocessing the data comprises the following steps:

[0014] Obtain data from weather stations, satellite remote sensing, SCADA systems, and power grid dispatch centers;

[0015] Perform data cleaning and preprocessing, detect and handle outliers, and fill in missing values.

[0016] Preferably, the step of predicting future renewable energy power generation using a machine learning model based on the preprocessed data comprises the following steps:

[0017] Perform feature engineering to extract time features, environmental features, and historical power generation features;

[0018] Select a suitable prediction model and conduct model training and validation.

[0019] Preferably, the step of calculating carbon emissions according to power generation data and emission factors comprises the following steps:

[0020] To calculate carbon emissions, the formula is as follows:

[0021]

[0022] Among them, E CO2 is carbon emissions, P gen,i is the power generation of the ith power plant, EF i is the emission factor of the ith power plant;

[0023] The calculation results are adjusted according to the power balance constraint, and the formula is as follows:

[0024] P gen (t)+P renew (t)≥P load (t)

[0025] Among them, P gen (t) is the conventional power generation, P renew (t) is the electricity generated by renewable energy, P load (t) is the load demand;

[0026] Compare the adjusted carbon emission data with the carbon quota to calculate the excess or shortfall in carbon emissions using the following formula:

[0027] ΔE CO2 =E CO2 -E quota

[0028] Among them, ΔE CO2 is the excess or deficit carbon emissions, E quota The allocated carbon quota.

[0029] Preferably, the step of designing an optimization model based on renewable energy forecasts and carbon emission calculation results, determining optimization objectives and constraints, and solving the optimal scheduling solution includes the following steps:

[0030] Design the optimization model, determine the optimization objectives and constraints, and the formula is as follows:

[0031]

[0032] Among them, C gen (t) is the power generation cost in the tth period, P gen (t) is the power generation in the tth period, C carbon is the carbon emission cost, E CO2 (t) Carbon emissions during the period;

[0033] Set constraints, including power balance constraints, power generation capacity constraints, and carbon emission constraints. The formula is as follows:

[0034] P gen (t)+P renew (t) = P load (t)

[0035]

[0036] E CO2 (t)≤E quota (t)

[0037] in, and are the minimum and maximum power generation, E quota (t) is the carbon quota for the tth period;

[0038] Solve the optimal scheduling plan and use the optimization algorithm to obtain the optimal power generation and carbon emission allocation plan for each time period.

[0039] Preferably, the steps of designing a carbon quota allocation method and trading rules and conducting carbon market transactions include the following steps:

[0040] Determine the amount of tradable carbon quotas, the calculation formula is as follows:

[0041] E trade =E quota -E actual

[0042] Among them, E trade is the amount of tradable carbon quota, E quota is the amount of carbon quota allocated, E actual is the actual carbon emissions;

[0043] Choose trading methods in the carbon market, including direct trading and auction trading;

[0044] Direct trading: Buy and sell based on the real-time market carbon price. The trading formula is as follows:

[0045] P trade =C carbon ·E trade

[0046] Among them, P trade is the transaction amount, C carbon is the market carbon price;

[0047] Auction transaction: Carbon quota auction is carried out on the market platform, and the final transaction price is determined through a bidding mechanism:

[0048] Record transaction information, update carbon quota accounts, and ensure transaction transparency and traceability;

[0049] Based on the transaction results, the company's carbon emission strategy and quota allocation will be adjusted to optimize subsequent production and emission plans.

[0050] Preferably, the step of calculating the renewable energy consumption responsibility of each region includes the following steps:

[0051] According to the total energy consumption and renewable energy power generation in each region, the proportion of renewable energy consumption is calculated using the following formula:

[0052]

[0053] Among them, R consumption is the proportion of renewable energy consumption, E renewable is the electricity generated by renewable energy, E total is the total energy consumption;

[0054] Determine the benchmark consumption ratio R according to the national or regional policy objectives. baseline ;

[0055] Calculate the consumption responsibility of each region, the calculation formula is as follows:

[0056] Dregion =E total ·(R target -R baseline )

[0057] Among them, D region is the consumption responsibility of each region, R target is the target consumption ratio;

[0058] Analyze the consumption capacity and resource potential of each region, and adjust and optimize the consumption responsibility allocation plan.

[0059] Preferably, the step of formulating the consumption responsibility target and assessment standard includes the following steps:

[0060] According to the consumption responsibility of each region D region , formulate annual and long-term consumption responsibility targets;

[0061] Formulate specific assessment standards and indicators, including but not limited to the following steps:

[0062] The annual consumption rate is calculated as follows:

[0063]

[0064] Among them, A annual is the annual consumption rate, E consumed_annual is the annual amount of renewable energy actually consumed, D region_annual The annual consumption responsibility volume;

[0065] The growth rate of renewable energy installed capacity is calculated as follows:

[0066]

[0067] Among them, G capacity is the installed capacity growth rate, C new For newly added installed capacity, C total The total installed capacity is:

[0068] The carbon emission reduction achievement rate is calculated as follows:

[0069]

[0070] Among them, R reduction is the carbon emission reduction rate, E reduced is the actual carbon emission reduction, E target_reduction The target carbon reduction amount;

[0071] Regularly evaluate the implementation of each region's consumption responsibility targets and assessment standards, and make adjustments and optimizations.

[0072] Preferably, the consumption responsibility allocation further includes:

[0073] Dynamically adjust the consumption responsibility targets and allocation plans based on the real-time operation of the power grid and the volatility of renewable energy generation;

[0074] The adjustment coefficient is used to make real-time corrections to the consumption responsibilities of various regions. The formula is as follows:

[0075]

[0076] Among them, R adjust,i is the adjusted consumption responsibility of the ith region, R target,i is the initial consumption responsibility target of the ith region, β is the adjustment coefficient, P renew,i is the actual renewable energy power generation in the ith region, is the predicted renewable energy power generation for the ith region.

[0077] The present invention also provides a renewable energy consumption responsibility assessment device based on a carbon market system, comprising:

[0078] Data acquisition module, used to obtain data from weather stations, satellite remote sensing, SCADA systems and power grid dispatch centers;

[0079] A data processing module, used for cleaning and preprocessing the acquired data;

[0080] A forecasting module for predicting future renewable energy generation based on the processed data;

[0081] A calculation module for calculating carbon emissions and renewable energy consumption responsibilities;

[0082] Optimization scheduling module, used to design optimization models and solve the optimal scheduling solution;

[0083] Trading module, used for carbon market transactions;

[0084] Dynamic adjustment module, used to dynamically adjust consumption responsibility targets and quotas.

[0085] The present invention provides a renewable energy consumption responsibility assessment method based on a carbon market system. It has the following beneficial effects:

[0086] 1. The present invention is based on a renewable energy consumption responsibility assessment method for a carbon market system. By acquiring and processing meteorological, power grid and power load data, a machine learning model is used to predict renewable energy power generation, carbon emissions are calculated by combining power generation data and emission factors, an optimization model is designed to determine the optimal scheduling plan, and carbon market transactions are realized through carbon quota allocation and trading rules. Finally, the renewable energy consumption responsibility of each region is calculated and consumption responsibility targets and assessment standards are formulated. This method improves the accuracy and fairness of renewable energy consumption, optimizes the scheduling and carbon emission management of the power system, and promotes the efficient use of renewable energy and the realization of carbon emission reduction targets.

[0087] 2. The present invention uses machine learning technology to predict future renewable energy generation, and can dynamically adjust the prediction model based on historical data and real-time environmental information, thereby improving the accuracy of the prediction. Such accurate predictions enable the power system to plan and dispatch resources more effectively, ensuring that renewable energy is fully utilized during the best period and reducing resource waste.

[0088] 3. The present invention provides a systematic method to monitor and manage carbon emissions of the power system by calculating and comparing actual carbon emissions with quotas. This method not only helps achieve environmental protection goals, but also encourages power producers and consumers to adopt low-carbon technologies through the carbon market mechanism, further promoting the green transformation of the power industry.

[0089] 4. The present invention provides a clear trading platform for carbon market participants by designing the rules and mechanisms of carbon quota trading. This institutionalized trading method increases market liquidity, improves transaction transparency, helps to form a reasonable carbon price, and better reflects the market supply and demand relationship.

[0090] 5. By calculating the renewable energy consumption ratio of each region and setting specific consumption responsibility targets and assessment standards, the present invention helps local governments and power companies to clarify their responsibilities and implement renewable energy consumption according to predetermined targets. This not only ensures the diversity and sustainability of energy consumption, but also helps achieve national and regional energy policy goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0092] Figure 2 It is a schematic diagram of the device structure of the present invention.

[0093] Among them, 100, data collection module; 200, data processing module; 300, prediction module; 400, calculation module; 500, optimization scheduling module; 600, transaction module; 700, dynamic adjustment module. DETAILED DESCRIPTION

[0094] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0095] Please see attached Figure 1 The embodiment of the present invention provides a method for evaluating the renewable energy consumption responsibility based on the carbon market system, comprising the following steps:

[0096] S1. Data acquisition, cleaning and preprocessing

[0097] In step S1, meteorological data, power grid data, and power load data need to be obtained from multiple channels. These data will be used for subsequent power generation forecasts and carbon emission calculations. Specific data acquisition sources include meteorological stations, satellite remote sensing, SCADA systems, and power grid dispatch centers. The acquired data needs to be cleaned and preprocessed to ensure its quality and consistency. This step includes detecting and processing outliers and filling in missing values ​​to ensure the integrity and accuracy of the data.

[0098] In this embodiment, data acquisition, cleaning and preprocessing include the following specific steps:

[0099] 1. Data acquisition:

[0100] Meteorological data acquisition: Meteorological data related to renewable energy generation are obtained from weather stations and satellite remote sensing systems, including solar radiation intensity, wind speed, wind direction, temperature and humidity, etc. These data are crucial for the prediction of solar and wind power generation.

[0101] Grid data acquisition: Obtain grid operation status data from the SCADA system and grid dispatch center, including power generation, transmission line load, grid frequency, etc. These data help to understand the real-time operation and load distribution of the grid.

[0102] Power load data acquisition: Obtain historical load data and forecast load data for each power consumption area from the power market operator. These data will be used to predict future power demand.

[0103] 2. Data cleaning:

[0104] Detect outliers: Detect outliers on the acquired data and use statistical methods (such as the 3σ principle, box plot method, etc.) to identify outliers in the data. Outliers may be caused by sensor failure, data transmission errors, etc., and need to be processed.

[0105] Processing outliers: For detected outliers, you can use interpolation, regression analysis, etc. to correct them, or delete them according to the actual situation. Specific methods include:

[0106] Linear interpolation: For continuous data, linear interpolation of adjacent data can be used to fill in outliers.

[0107] Regression analysis: For multivariate data, a regression model can be established to estimate outliers based on the values ​​of other variables.

[0108] 3. Data preprocessing:

[0109] Filling missing values: For missing values ​​in the data, interpolation, mean filling, KNN filling, etc. can be used for processing. Specific methods include:

[0110] Mean imputation: fill missing values ​​with the mean of the dataset.

[0111] KNN filling method: Use the K nearest neighbor algorithm to fill in the missing values ​​based on the values ​​of the K data points that are most similar to the missing values.

[0112] Data standardization: Standardize the data to make data of different dimensions comparable.

[0113] Data normalization: Normalize the data so that the data value range is between [0, 1].

[0114] Through the above data acquisition, cleaning and preprocessing steps, the quality and consistency of data can be effectively improved, and the impact of noise and abnormal data on subsequent analysis can be reduced. This provides a reliable data basis for the assessment of renewable energy consumption responsibility based on the carbon market system, helps to improve the accuracy and reliability of prediction models and optimization models, and thus better achieve the goal of renewable energy consumption.

[0115] S2. Renewable energy generation forecast

[0116] In step S2, feature engineering is first required to extract time features, environmental features, and historical power generation features related to renewable energy generation. These features will serve as input data for the prediction model. Next, a suitable machine learning prediction model is selected, and the model is trained and validated to ensure the accuracy and reliability of the prediction results.

[0117] In this embodiment, the renewable energy power generation prediction includes the following specific steps:

[0118] 1. Feature Engineering:

[0119] Time feature extraction: Time features include season, month, day of the week, time period, etc. These features reflect the impact of time on power generation. For example, there may be significant differences in solar radiation intensity and wind speed in winter and summer. Specific methods include:

[0120] Extract seasonal features: Convert timestamps to corresponding seasons (spring, summer, autumn, winter).

[0121] Extract month features: Convert the timestamp to the corresponding month (1-12).

[0122] Extract day of week features: Convert the timestamp to the corresponding day of the week (1-7).

[0123] Extract time period features: Divide a day into several time periods, such as early morning, morning, afternoon, and evening.

[0124] Environmental feature extraction: Environmental features include temperature, humidity, wind speed, wind direction, solar radiation intensity, etc. These features directly affect the power generation of renewable energy. Specific methods include:

[0125] The above environmental characteristics are extracted from meteorological data and standardized.

[0126] The wind speed and wind direction are decomposed to extract the horizontal and vertical wind speed components.

[0127] Historical power generation feature extraction: Historical power generation features include past power generation data, which can help predict future power generation trends. Specific methods include:

[0128] The power generation data of the previous day, previous week, and previous month are extracted as features.

[0129] The moving average of power generation is calculated as the smoothed historical power generation characteristics.

[0130] 2. Select the prediction model:

[0131] Model selection: Select a machine learning model suitable for time series prediction, including but not limited to long short-term memory network (LSTM), support vector machine (SVM), random forest, etc. The specific selection can be made based on data characteristics and prediction accuracy requirements.

[0132] The LSTM model is suitable for processing time series data and can capture long-term dependencies.

[0133] The SVM model is suitable for processing high-dimensional data and has good generalization ability.

[0134] The random forest model is suitable for dealing with nonlinear relationships and has strong robustness.

[0135] Model training and validation:

[0136] Training set and validation set division: Divide the dataset into training set and validation set, for example, in a ratio of 8:2. The training set is used for model training, and the validation set is used for model validation.

[0137] Model training: Use the training set data to train the selected model.

[0138] Model validation: Use validation set data to evaluate the prediction accuracy of the model. Common evaluation indicators include mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE).

[0139] Through the above steps, we can obtain high-precision forecast results of renewable energy power generation, providing reliable basic data support for subsequent carbon emission calculation and optimization model design. This process ensures the comprehensiveness of data characteristics and the accuracy of the prediction model, and can effectively improve the scientificity and rationality of renewable energy consumption responsibility assessment.

[0140] S3. Carbon emissions calculation and adjustment

[0141] In step S3, the carbon emissions of each power plant need to be calculated first, based on the predefined emission factors and power generation. Then, the calculation results are adjusted according to the power balance constraints to ensure the balance between supply and demand. Finally, the adjusted carbon emission data is compared with the carbon quota to calculate the excess or insufficient carbon emissions. This process ensures the accuracy of carbon emission calculations and provides basic data for subsequent carbon market transactions.

[0142] In this embodiment, the carbon emission calculation and adjustment includes the following specific steps:

[0143] 1. Calculate carbon emissions:

[0144] According to the power generation of each power plant and the corresponding emission factor, the carbon emissions of each power plant are calculated. The calculation formula is as follows:

[0145]

[0146] Among them, E CO2 is carbon emissions, P gen,i is the power generation of the ith power plant, EF i is the emission factor of the ith power plant.

[0147] 2. Power balance constraint adjustment:

[0148] Ensure that the calculated power generation meets the power balance constraint, that is, the total power generation (including conventional power generation and renewable energy generation) must be greater than or equal to the load demand. The adjustment formula is as follows:

[0149] P gen (t)+P renew (t)≥P load (t)

[0150] Among them, P gen (t) is the conventional power generation, P renew (t) is the electricity generated by renewable energy, P load (t) is the load demand.

[0151] 3. Calculation of excess or insufficient carbon emissions:

[0152] Compare the adjusted carbon emission data with the allocated carbon quota to calculate the excess or insufficient carbon emissions. The calculation formula is as follows:

[0153] ΔE CO2 =E CO2 -E quota

[0154] Among them, ΔE CO2 is the excess or deficit carbon emissions, E quota The allocated carbon quota.

[0155] In this embodiment, relevant features are first extracted from meteorological data, power grid data, and power load data and cleaned and preprocessed. Then, these data are used to predict the power generation of renewable energy, and the carbon emissions of each power plant are calculated based on the prediction results. By introducing power balance constraints, the rationality and accuracy of the calculation results are ensured. Finally, by comparing the adjusted carbon emissions and carbon quotas, the excess or insufficient carbon emissions are calculated, providing reliable data support for subsequent carbon market transactions and responsibility assessments.

[0156] This process not only ensures the scientificity and accuracy of carbon emissions calculations, but also effectively helps manage and control carbon emissions in different regions, promotes the consumption and utilization of renewable energy, and thereby improves the operating efficiency and fairness of the overall carbon market.

[0157] S4. Optimization model design and optimal scheduling solution

[0158] In step S4, firstly, an optimization model needs to be designed based on the renewable energy forecast and carbon emission calculation results. Then, the optimization target and constraints are determined, and the optimization algorithm is used to solve the optimal scheduling scheme. Through this optimization process, the comprehensive cost of the system, including power generation cost and carbon emission cost, can be minimized while satisfying various constraints, thereby achieving carbon emission control and improving energy utilization efficiency.

[0159] In this embodiment, the optimization model design and the optimal scheduling solution solution include the following specific steps:

[0160] 1. Design optimization model:

[0161] The design of the optimization model is based on the power generation and carbon emissions of the system, aiming to minimize the overall cost of the system through a reasonable scheduling scheme. The mathematical expression of the optimization objective is:

[0162]

[0163] Among them, C gen (t) is the power generation cost in the tth period, P gen (t) is the power generation in the tth period, C carbon is the carbon emission cost, E CO2 (t) Carbon emissions during the period.

[0164] 2. Determine the optimization objectives and constraints:

[0165] Set constraints to ensure the feasibility and rationality of the optimization model in actual operation. The main constraints include:

[0166] 1) Power balance constraints:

[0167] P gen (t)+P renew (t) = P load (t)

[0168] Among them, P renew (t) is the electricity generated by renewable energy, P load (t) is the load demand.

[0169] 2) Power generation capacity constraints:

[0170]

[0171] in, and are the minimum and maximum power generation respectively.

[0172] 3) Carbon emission constraints:

[0173] E CO2 (t)≤E quota (t)

[0174] Among them, E quota (t) is the carbon quota for the tth period.

[0175] 3. Solve the optimal scheduling solution:

[0176] Optimization algorithms are used to solve the problem, and commonly used methods include linear programming, mixed integer programming, and genetic algorithms. Through the optimization algorithm, the optimal power generation and carbon emission allocation plan for each period can be obtained, thereby minimizing the overall cost of the system and effectively controlling carbon emissions.

[0177] In this embodiment, by designing an optimization model and determining optimization objectives and constraints, and using predicted renewable energy power generation data and carbon emission calculation results, it is possible to reasonably dispatch power generation resources and minimize comprehensive costs. The optimization model not only takes into account the power generation cost, but also incorporates the carbon emission cost, ensuring the dual goals of carbon emission control and energy efficiency. At the same time, by introducing constraints such as power balance, power generation capacity and carbon emissions, the practical operability of the optimization model is guaranteed, and finally the optimal scheduling solution is obtained through the optimization algorithm.

[0178] This process has significant advantages in achieving carbon emission control and efficient use of renewable energy, and can provide scientific and effective technical support for the assessment of renewable energy consumption responsibilities under the carbon market system.

[0179] S5. Carbon quota allocation and carbon market transactions

[0180] The main task of step S5 is to design a carbon quota allocation method based on the optimized carbon emission data, determine the tradable carbon quota amount, and trade it in the carbon market. Through this process, not only can the company's carbon emission targets be achieved, but also the carbon emission costs can be optimized through market mechanisms, promoting the consumption and development of renewable energy.

[0181] In this embodiment, carbon quota allocation and carbon market transactions include the following specific steps:

[0182] 1. Determine the amount of tradable carbon quotas:

[0183] According to the optimization results, the actual carbon emissions of each enterprise are determined and compared with the allocated carbon quota to calculate the tradable carbon quota. The calculation formula is as follows:

[0184] E trade =E quota -E actual

[0185] Among them, E trade is the amount of tradable carbon quota, E quota is the amount of carbon quota allocated, E actual is the actual carbon emissions.

[0186] 2. Choose a transaction method:

[0187] In the carbon market, companies can choose to buy and sell carbon quotas through direct transactions or auction transactions.

[0188] 1) Direct Trading:

[0189] Enterprises buy and sell carbon quotas based on the real-time market carbon price. The transaction formula is as follows:

[0190] P trade =C carbon ·E trade

[0191] Among them, P trade is the transaction amount, C carbon is the market carbon price.

[0192] 2) Auction transactions:

[0193] Enterprises conduct carbon quota auctions on the market platform and determine the final transaction price through a bidding mechanism. Auction transactions help discover market prices and ensure the fairness and transparency of transactions.

[0194] 4. Record transaction information:

[0195] After the transaction is completed, the enterprise needs to record the transaction information in detail, including transaction time, transaction amount, transaction volume, etc. At the same time, update the carbon quota account to ensure the liquidity and traceability of carbon quotas.

[0196] 5. Adjust carbon emission strategy:

[0197] According to the transaction results, enterprises can adjust their carbon emission strategies and quota allocations and optimize subsequent production and emission plans. Through carbon market transactions, enterprises can flexibly respond to carbon emission constraints and achieve a win-win situation in terms of economic and environmental benefits.

[0198] In this embodiment, firstly, the formula E is calculated trade =E quota -E actual Determine the amount of tradable carbon quotas. When the actual carbon emissions of an enterprise are lower than the allocated carbon quotas, the enterprise can sell the remaining carbon quotas in the market; conversely, when the actual carbon emissions are higher than the allocated carbon quotas, the enterprise needs to purchase additional carbon quotas in the market to meet the emission requirements.

[0199] When choosing a trading method, enterprises can choose direct trading or auction trading according to actual conditions. In direct trading, the market real-time carbon price C carbon To conduct a transaction, the transaction amount is calculated by formula P trade =C carbon ·E trade In auction transactions, companies bid to acquire or sell carbon quotas through market platforms, ensuring the rationality of transaction prices and the discovery function of market prices.

[0200] After all transactions are completed, enterprises need to record detailed transaction information and update carbon quota accounts in a timely manner to ensure the transparency and traceability of transactions. At the same time, based on the transaction results, enterprises can flexibly adjust their carbon emission strategies and optimize subsequent production and emission plans to better respond to changes in the carbon market and regulatory requirements.

[0201] Through the above steps, enterprises can effectively utilize the carbon market mechanism, optimize the use of carbon quotas, achieve carbon emission control goals and maximize economic benefits. At the same time, it can promote the consumption and development of renewable energy and make positive contributions to achieving carbon neutrality goals.

[0202] S6. Calculate the renewable energy consumption responsibility of each region and formulate consumption responsibility targets and assessment standards.

[0203] In the first few steps, by acquiring data, predicting power generation, calculating carbon emissions, designing optimization models and conducting carbon market transactions, we have initially achieved optimized management of carbon emissions and renewable energy generation. The last step is to calculate the renewable energy consumption responsibility of each region, formulate consumption responsibility targets and assessment standards to ensure that each region can reasonably undertake and complete the task of renewable energy consumption. This step determines the consumption responsibility of each region through detailed calculations and analysis, and dynamically adjusts it to optimize the overall renewable energy consumption effect.

[0204] In this embodiment, calculating the renewable energy consumption responsibility of each region and formulating the consumption responsibility target and assessment standard include the following specific steps:

[0205] 1. Calculate the proportion of renewable energy consumption in each region:

[0206] According to the total energy consumption and renewable energy power generation in each region, the proportion of renewable energy consumption is calculated using the following formula:

[0207]

[0208] Among them, R consumption is the proportion of renewable energy consumption, E renewable is the electricity generated by renewable energy, E total is the total energy consumption.

[0209] 2. Determine the benchmark consumption ratio:

[0210] Determine the benchmark consumption ratio R according to the national or regional policy objectives. baseline .

[0211] 3. Calculate the consumption responsibility of each region:

[0212] According to the calculated consumption ratio and policy objectives, the consumption responsibility of each region is determined. The calculation formula is as follows:

[0213] D region =E total ·(R target -R baseline )

[0214] Among them, D region is the consumption responsibility of each region, R target is the target consumption ratio.

[0215] 4. Analyze the consumption capacity and resource potential of each region:

[0216] Based on the consumption capacity and resource potential of each region, the consumption responsibility allocation plan will be adjusted and optimized.

[0217] 5. Formulate consumption responsibility targets and assessment standards:

[0218] According to the consumption responsibility of each region D region , formulate annual and long-term consumption responsibility targets, and formulate specific assessment standards and indicators.

[0219] As examples, specific assessment criteria include:

[0220] 1. Annual consumption rate:

[0221]

[0222] Among them, A annual is the annual consumption rate, E consumed_annual is the annual amount of renewable energy actually consumed, D region_annual It is the annual consumption responsibility amount.

[0223] 2. Growth rate of renewable energy installed capacity:

[0224]

[0225] Among them, G capacity is the installed capacity growth rate, C new For newly added installed capacity, C total is the total installed capacity.

[0226] 3. Carbon emission reduction rate:

[0227]

[0228] Among them, R reduction is the carbon emission reduction rate, E reduced is the actual carbon emission reduction, E taret_reduction The target carbon emission reduction.

[0229] 6. Dynamically adjust consumption responsibilities:

[0230] Dynamically adjust the consumption responsibility targets and allocation plans based on the real-time operation of the power grid and the volatility of renewable energy generation.

[0231] The adjustment coefficient is used to make real-time corrections to the consumption responsibility of each region. The calculation formula is as follows:

[0232]

[0233] Among them, R adjust,i is the adjusted consumption responsibility of the ith region, R target,i is the initial consumption responsibility target of the ith region, β is the adjustment coefficient, P renew,i is the actual renewable energy power generation in the ith region, is the predicted renewable energy power generation for the ith region.

[0234] Through the above steps, this embodiment can effectively calculate the renewable energy consumption responsibility of each region, and ensure that each region reasonably undertakes the consumption task through dynamic adjustment, thereby promoting the development of renewable energy and effective control of carbon emissions.

[0235] The present invention is based on a renewable energy consumption responsibility assessment method for a carbon market system. By acquiring and processing meteorological, power grid and power load data, a machine learning model is used to predict renewable energy power generation, carbon emissions are calculated by combining power generation data and emission factors, an optimization model is designed to determine the optimal scheduling plan, and carbon market transactions are realized through carbon quota allocation and trading rules. Finally, the renewable energy consumption responsibility of each region is calculated and consumption responsibility targets and assessment standards are formulated. This method improves the accuracy and fairness of renewable energy consumption, optimizes the scheduling and carbon emission management of the power system, and promotes the efficient use of renewable energy and the realization of carbon emission reduction targets.

[0236] The renewable energy consumption responsibility assessment device based on the carbon market system described below and the renewable energy consumption responsibility assessment method based on the carbon market system described above can be referenced to each other.

[0237] Please see attached Figure 2 The present invention also provides a renewable energy consumption responsibility assessment device based on a carbon market system, comprising:

[0238] Data acquisition module 100, used to obtain data from weather stations, satellite remote sensing, SCADA systems and power grid dispatching centers;

[0239] The data processing module 200 is used to clean and pre-process the acquired data;

[0240] A prediction module 300, for predicting future renewable energy generation based on the processed data;

[0241] A calculation module 400 is used to calculate carbon emissions and renewable energy consumption responsibilities;

[0242] The optimization scheduling module 500 is used to design an optimization model and solve the optimal scheduling solution;

[0243] The trading module 600 is used for conducting carbon market transactions;

[0244] The dynamic adjustment module 700 is used to dynamically adjust the consumption responsibility targets and quotas.

[0245] The device of this embodiment can be used to execute the above method embodiment, and its principles and technical effects are similar, which will not be repeated here.

[0246] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A renewable energy consumption responsibility assessment method based on a carbon market system, characterized in that: The following steps are involved: Obtain meteorological data, power grid data and power load data, and clean and pre-process the data; Based on the preprocessed data, a machine learning model is used to predict future renewable energy generation; Calculate carbon emissions based on power generation data and emission factors; Based on the forecast of renewable energy and the calculation results of carbon emissions, design the optimization model, determine the optimization objectives and constraints, and solve the optimal scheduling plan; Design carbon quota allocation methods and trading rules, and conduct carbon market transactions; Calculate the renewable energy consumption responsibility of each region, and formulate consumption responsibility targets and assessment standards.

2. The renewable energy consumption responsibility assessment method based on the carbon market system according to claim 1 is characterized in that: The steps of obtaining meteorological data, power grid data and power load data, and cleaning and preprocessing the data include the following steps: Obtain data from weather stations, satellite remote sensing, SCADA systems, and power grid dispatch centers; Perform data cleaning and preprocessing, detect and handle outliers, and fill in missing values.

3. The renewable energy consumption responsibility assessment method based on the carbon market system according to claim 1 is characterized in that: The step of predicting the future renewable energy power generation using a machine learning model based on the preprocessed data includes the following steps: Perform feature engineering to extract time features, environmental features, and historical power generation features; Select a suitable prediction model and conduct model training and validation.

4. The renewable energy consumption responsibility assessment method based on the carbon market system according to claim 1 is characterized in that: The step of calculating carbon emissions according to power generation data and emission factors includes the following steps: To calculate carbon emissions, the formula is as follows: Among them, E CO2 is carbon emissions, P gen,i is the power generation of the ith power plant, EF i is the emission factor of the ith power plant; The calculation results are adjusted according to the power balance constraint, and the formula is as follows: P gen (t)+P renew (t)≥P load (t) Among them, P gen (t) is the conventional power generation, P renew (t) is the electricity generated by renewable energy, P load (t) is the load demand; Compare the adjusted carbon emission data with the carbon quota to calculate the excess or shortfall in carbon emissions using the following formula: ΔE CO2 =E CO2 -E quota Where, ΔE CO2 is the excess or deficit carbon emissions, E quota The allocated carbon quota.

5. The renewable energy consumption responsibility assessment method based on the carbon market system according to claim 1 is characterized in that: The steps of designing an optimization model, determining optimization objectives and constraints, and solving the optimal scheduling solution based on renewable energy prediction and carbon emission calculation results include the following steps: Design the optimization model, determine the optimization objectives and constraints, and the formula is as follows: Among them, C gen (t) is the power generation cost in the tth period, P gen (t) is the power generation in the tth period, C carbon is the carbon emission cost, E CO2 (t) Carbon emissions during the period; Set constraints, including power balance constraints, power generation capacity constraints, and carbon emission constraints. The formula is as follows: P gen (t)+P renew (t)=P load (t) E CO2 (t)≤E quota (t) in, and are the minimum and maximum power generation, E quota (t) is the carbon quota for the tth period; Solve the optimal scheduling plan and use the optimization algorithm to obtain the optimal power generation and carbon emission allocation plan for each time period.

6. The renewable energy consumption responsibility assessment method based on the carbon market system according to claim 1 is characterized in that: The steps of designing the carbon quota allocation method and trading rules and conducting carbon market transactions include the following steps: Determine the amount of tradable carbon quotas, the calculation formula is as follows: AND trade =And quota -AND actual Among them, E trade is the amount of tradable carbon quota, E quota is the amount of carbon quota allocated, E actual is the actual carbon emissions; Choose trading methods in the carbon market, including direct trading and auction trading; Direct trading: Buy and sell based on the real-time market carbon price. The trading formula is as follows: P trade =C carbon ·E trade Among them, P trade is the transaction amount, C carbon is the market carbon price; Auction transaction: Carbon quota auction is carried out on the market platform, and the final transaction price is determined through a bidding mechanism: Record transaction information, update carbon quota accounts, and ensure transaction transparency and traceability; Based on the transaction results, the company's carbon emission strategy and quota allocation will be adjusted to optimize subsequent production and emission plans.

7. The renewable energy consumption responsibility assessment method based on the carbon market system according to claim 1 is characterized in that: The step of calculating the renewable energy consumption responsibility of each region includes the following steps: According to the total energy consumption and renewable energy power generation in each region, the proportion of renewable energy consumption is calculated using the following formula: Among them, R consumption is the proportion of renewable energy consumption, E renewable is the electricity generated by renewable energy, E total is the total energy consumption; Determine the benchmark consumption ratio R according to the national or regional policy objectives. baseline ; Calculate the consumption responsibility of each region, the calculation formula is as follows: D region =E total ·(R target -R baseline ) Among them, D region is the consumption responsibility of each region, R target is the target consumption ratio; Analyze the consumption capacity and resource potential of each region, and adjust and optimize the consumption responsibility allocation plan.

8. The renewable energy consumption responsibility assessment method based on the carbon market system according to claim 7 is characterized in that: The steps of formulating consumption responsibility targets and assessment standards include the following steps: According to the consumption responsibility of each region D region , formulate annual and long-term consumption responsibility targets; Formulate specific assessment standards and indicators, including but not limited to the following steps: The annual consumption rate is calculated as follows: Among them, A annual is the annual consumption rate, E consumed_annual is the annual amount of renewable energy actually consumed, D region_annual The annual consumption responsibility volume; The growth rate of renewable energy installed capacity is calculated as follows: Among them, G capacity is the installed capacity growth rate, C new For newly added installed capacity, C total is the total installed capacity; The carbon emission reduction achievement rate is calculated as follows: Among them, R reduction is the carbon emission reduction achievement rate, E reduced is the actual carbon emission reduction, E target_reduction is the target carbon emission reduction; Regularly evaluate the implementation of each region's consumption responsibility targets and assessment standards, and make adjustments and optimizations.

9. The renewable energy consumption responsibility assessment method based on the carbon market system according to claim 7 is characterized in that: The allocation of consumption responsibilities further includes: Dynamically adjust the consumption responsibility targets and allocation plans based on the real-time operation of the power grid and the volatility of renewable energy generation; The adjustment coefficient is used to make real-time corrections to the consumption responsibilities of various regions. The formula is as follows: Among them, R adjust,i is the adjusted consumption responsibility of the ith region, R target,i is the initial consumption responsibility target of the ith region, β is the adjustment coefficient, P renew,i is the actual renewable energy power generation in the ith region, is the predicted renewable energy power generation for the ith region.

10. A renewable energy consumption responsibility assessment device based on a carbon market system, used to implement the method according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, used to obtain data from weather stations, satellite remote sensing, SCADA systems and power grid dispatch centers: A data processing module, used for cleaning and preprocessing the acquired data; A forecasting module for predicting future renewable energy generation based on the processed data; A calculation module for calculating carbon emissions and renewable energy consumption responsibilities; Optimization scheduling module, used to design optimization models and solve the optimal scheduling solution; Trading module, used for carbon market transactions; Dynamic adjustment module, used to dynamically adjust consumption responsibility targets and quotas.