Carbon emission dynamic accounting and carbon quota transaction intelligent decision optimization method and system

Abstract

The present application relates to the technical field of industrial carbon emission measurement and carbon asset transaction, and particularly relates to a carbon emission dynamic accounting and carbon quota transaction intelligent decision optimization method and system, comprising a dynamic accounting module, a quota dynamic prediction and optimization module, and a carbon quota transaction intelligent decision module; carbon emission rolling accounting is realized through high-frequency data acquisition of multi-system docking, quota surplus and deficiency accurate prediction is realized by introducing rolling prediction, dynamic adjustment and multi-scenario simulation mechanism using the improved baseline method, adaptive transaction strategies are respectively constructed for the supply and demand sides, and a price-related two-way hierarchical risk early warning mechanism is matched. The present application can realize dynamic management and control of the whole process of carbon emission, greatly improve the quota prediction accuracy, effectively reduce the enterprise compliance cost, improve the intelligent level and risk prevention and control ability of carbon asset management, and is suitable for key high-energy-consuming industries such as electric power and steel.

Description

Technical Field

[0001] This invention relates to the field of industrial carbon emission measurement and carbon asset trading technology, and in particular to a method and system for dynamic carbon emission accounting and intelligent decision-making optimization of carbon quota trading. Background Technology

[0002] High-energy-consuming and high-emission key industries (such as power, steel, cement, chemicals, and flat glass) are the main sources of carbon emissions and are also the key targets of the national carbon emissions trading market. With the expansion of the carbon market's coverage and the deepening of policies, enterprises face increasingly stringent carbon emission constraints and compliance pressures. However, existing enterprise-level carbon asset management systems still have the following prominent problems: (1) Accounting lag: Current mainstream accounting methods rely on annual static reports and lack real-time or near-real-time data support, making it impossible for enterprises to achieve process-level proactive carbon management and real-time decision-making; (2) Lack of quota forecasting: Enterprises have difficulty accurately predicting their future carbon emission trends and quota surplus or shortage status, resulting in blind and delayed trading decisions, failure to effectively seize market opportunities, and increased compliance costs. (3) Extensive trading strategies: Existing trading relies heavily on experience and lacks systematic and quantitative trading models, which makes it impossible to maximize the value of carbon assets.

[0003] (4) System isolation: The accounting, prediction and trading links are separated, and a data closed loop is not formed, making it difficult to support refined and intelligent carbon asset management.

[0004] Therefore, there is an urgent need in this field for an integrated solution that can realize near real-time dynamic accounting of corporate carbon emissions, rolling forecasting of quotas, and intelligent trading decisions, so as to improve corporate carbon asset management capabilities, reduce compliance costs, and enhance the effectiveness of the carbon market. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies, such as lagging accounting, missing quota budgets, extensive trading strategies, and isolated systems, and to provide a method and system for dynamic carbon emission accounting and intelligent optimization of carbon quota trading applicable to key industries. It enables near real-time rolling accounting of enterprise carbon emissions, dynamically predicts the quota surplus or deficit status of enterprises based on industry benchmark methods, and provides enterprises with scientific and adaptive trading strategies, thereby assisting enterprises in proactively managing carbon assets, optimizing trading decisions, and reducing compliance costs.

[0006] To achieve the above objectives, the present invention provides a dynamic carbon emission accounting and carbon quota trading intelligent decision-making system, including a dynamic accounting module, a quota dynamic prediction and optimization module, and a quota trading intelligent decision-making module; The dynamic accounting module includes a dynamic activity data acquisition system. The dynamic accounting module determines the accounting boundary and identifies emission sources. It collects key activity data of the enterprise through the dynamic activity data acquisition system and performs rolling accounting (such as daily accounting) based on the collected data. The dynamic activity data acquisition system integrates the enterprise's energy management system (EMS), manufacturing execution system (MES), distributed control system (DCS), and Internet of Things (IoT) smart meters to automatically collect key activity data (including: consumption of various fossil fuels, input of raw materials (especially carbon-containing raw materials), and product output (by variety / specification)) at a preset frequency (daily or higher, such as hourly). The dynamic accounting module determines the accounting boundaries and identifies emission sources by: targeting key industry enterprises, clearly defining organizational and accounting boundaries based on the national greenhouse gas emission accounting and reporting standards (such as the GB / T 32150 series of standards) of their respective industries; and systematically identifying and covering all relevant emission sources, mainly including: fossil fuel combustion emissions (such as coal, oil, natural gas, etc.) and industrial process emissions (such as carbonate decomposition, oxidation of raw materials containing carbon, etc.). The quota dynamic prediction and optimization module uses an improved baseline method to predict enterprise quota surplus or deficit; the improved baseline method introduces rolling prediction, dynamic adjustment and multi-scenario simulation mechanisms on the basis of the baseline method. The intelligent strategy module for carbon quota trading incorporates supply-side and demand-side strategies. Companies with quota surpluses execute supply-side strategies, while companies with quota deficits execute demand-side strategies.

[0007] Furthermore, the specific process of the dynamic accounting module performing rolling accounting based on the collected data is as follows: Calculation of carbon dioxide emissions from fossil fuel combustion: ; In the formula, This indicates the amount of carbon dioxide emitted from the combustion of fossil fuels, expressed in tons of carbon dioxide (t CO2). Indicates the type of fossil fuel. Indicates the first The average lower heating value of fossil fuels, where the unit for solid or liquid fuels is gigajoules per ton (GJ / t), and the unit for gaseous fuels is gigajoules per 10,000 cubic meters (GJ / 10⁻¹⁰). 4 Nm 3 ); Indicates the first The net consumption of fossil fuels, where solid or liquid fuels are measured in tons (t) and gaseous fuels in ten thousand cubic meters (10). 4 Nm 3 ); Indicates the first The carbon content per unit calorific value of a fossil fuel, expressed in tons of carbon per gigajoules (tC / GJ); Indicates the first Carbon oxidation rate of fossil fuels, in % This indicates the molecular weight ratio of carbon dioxide to carbon. Calculation of carbon dioxide emissions from industrial processes: The carbon dioxide emissions from industrial processes include two parts: process emissions calculated using the material balance method and emissions from the carbonate utilization process. The expression is as follows: ; In the formula, This indicates the amount of carbon dioxide emitted during industrial processes, expressed in tons of carbon dioxide (t CO2). Indicates the first Such materials, This indicates the total number of material types. Indicates the first The quantity of each type of input material is determined based on the specific emission source. Indicates the first The quantity of each type of output material is determined by the specific emission source. Indicates the first The carbon content of the input material is specified in units that match the quantity of the input material. Indicates the first The carbon content of the output material is specified in units that match the quantity of the input material. Indicates the type of carbonate. Indicates the number of carbonate species. Indicates the first The consumption of various carbonates, expressed in tons (t); Indicates the first The emission factor of various carbonates is expressed in tons of carbon dioxide per ton (tCO2 / t). Indicates the first The purity of a carbonate, expressed as a percentage (%). Calculation of total carbon dioxide emissions from enterprises: ; In the formula, Indicates the first The total carbon dioxide emissions of each enterprise during the accounting period; Corporate carbon intensity: ; In the formula, Indicates the first Carbon emission intensity of an individual enterprise (tCO2 / t product). Indicates the first The total output of qualified products for an enterprise during the accounting period is usually expressed in tons (t); for multi-product enterprises, the output is summarized or classified according to the standard provisions.

[0008] Furthermore, the improved baseline method for predicting enterprise quota surpluses and deficits specifically involves: This module, based on the traditional baseline method, introduces rolling forecasting, dynamic adjustment, and multi-scenario simulation mechanisms to upgrade from "static annual quota" to "dynamic rolling quota". Baseline quota calculation: The baseline method is adopted as the basic method for quota allocation, and a baseline value for product carbon emissions is set. (tCO2 / t product), based on dynamic accounting results and production data, predict the quota surplus or deficit status of enterprises in a certain period: ; In the formula, Indicates enterprise Pre-allocation quotas based on the baseline method, in tons of carbon dioxide (tCO2). Indicates enterprise Product output during the forecast period (dynamically updated), in tons (t). This indicates the benchmark value of carbon emissions per ton of CO2 (t CO2 / t product) issued by the industry's regulatory authority. Rolling production and emissions forecasts: Based on enterprise production plans, historical output trends, and equipment operating status, an output forecasting model is constructed, including an ARIMA time series model and an LSTM neural network model, to predict future output. Rolling production forecasts for a period of 1-12 months, combined with real-time emission intensity from a dynamic accounting module. The formula for predicting future carbon emissions is: ; In the formula, Indicates the current time (current day or current hour). This indicates the offset for the future forecast period. ; Indicates the first Individual companies Predicted output at any given time Indicates the first Individual companies Predicted emission intensity at any given time This indicates a projected future carbon emissions; Dynamic quota adjustment factor: Introducing dynamic quota adjustment factor This reflects the impact of policy adjustments, market supply and demand, and seasonal fluctuations, and is expressed as: ; In the formula, This indicates the pre-allocated quota after dynamic adjustment, which can be dynamically calculated based on changes in historical quota allocation policies, industry emission reduction target progress, market liquidity, etc. Indicates enterprise Pre-allocation quotas based on the baseline method; Dynamic assessment of quota surplus / shortage status: Compare and The size, if If so, it is a quota surplus (supply measurement); if If so, it is a quota gap (demand measurement); if This indicates a quota balance; Introducing quota surplus / deficit rate , This refers to the proportion of the difference between the pre-allocated carbon emission allowance and the predicted carbon emission amount after dynamic adjustment by the enterprise to the pre-allocated allowance: ; when A value greater than 0 indicates a corporate quota surplus, with the surplus amount being... ; when When =0, it indicates that the enterprise quota is balanced; when When the value is less than 0, it indicates that the company has a quota shortfall, and the shortfall amount is... ; The larger the absolute value, the more severe the quota shortage, and the higher the risk level faced by the enterprise.

[0009] Furthermore, the quota dynamic prediction and optimization module also includes multi-scenario simulation and risk warning functions. Specifically, it adjusts the formula in the improved baseline method based on scenarios including production fluctuations, benchmark adjustments, and market price changes, and outputs quota surpluses and deficits under different scenarios; based on the quota surplus / deficit rate... Output a probability distribution chart of quota surplus or shortage to provide enterprises with visualized risk warnings.

[0010] Furthermore, the supply-side strategy specifically includes: S1. Calculate dynamic transaction volume: S11, Calculate the benchmark trading volume : ; In the formula, Indicates the benchmark trading volume. This indicates a projected annual quota surplus. Indicates the basic carryover amount. This indicates the predicted market demand for the day. This represents the total remaining projected demand for the entire year; S12, Calculate the error correction component : Based on the cumulative error between previous transaction volume and planned volume, the remaining market demand is dynamically allocated according to the proportion of remaining demand, expressed as: ; In the formula, Indicates the error correction component. Indicates the planned transaction volume. Indicates the actual transaction volume; S13. Determine the final daily trading volume. : ; In the formula, This indicates the final day's trading volume. For smoothing coefficients, ; S2, Dynamic Pricing Model: Determine the floor price using a model based on the opportunity cost of holding (or directly use the historical weighted average price as the floor price), including the following parts: S21, Opportunity Cost of Holding Quotas : The cost of capital tied up by a company that does not sell its quota now but holds it until it sells or uses it in the future is expressed as follows: ; In the formula, This represents a predicted value for carbon prices at a future point in time. Indicates the company's cost of capital. Indicates the holding period in years; This represents the discount factor under continuously compounded interest. S22. Define transaction costs and risk premiums. This includes transaction fees, fund settlement costs, and risks arising from future policy uncertainties; Base price for: ; In practical applications, to simplify the model, it can be... It can be directly set to a fixed value that is meaningful to the enterprise, such as the weighted average price of the previous year's quota transactions or the marginal emission reduction cost of the enterprise's carbon management project; S3. Determine the expected market price level. Obtain it through the following methods: Historical price analysis: Moving average price over a past period (e.g., 30 days); Fundamental analysis: Predicting price trends based on policy news, industry dynamics, energy prices, etc. Technical analysis: Analysis includes price charts and trading volume data; S4, Dynamic Pricing Model: S41. Introduce a transaction urgency factor. (A number between 0 and 1 that gradually increases as the deadline approaches), dynamically calculated based on the number of days remaining until the official deadline. value: ; In the formula, It is a constant that adjusts the sensitivity. This indicates the unified compliance deadline for the national carbon market. Indicates the current date; S42. Generate the final bid price The dynamic pricing formula is as follows: ; Among them, when the performance period is still far away ( (Close to 0), companies are not in a hurry to sell, and their asking prices are closer to their ideal market expectations. Strive to sell at a high price. When the performance period is very close ( (1) As companies are eager to cash out their surplus quotas to avoid waste, their bids will approach or even equal the reserve price. To ensure a successful transaction, .

[0011] S5. Combined Declaration: Calculated daily trading volume With dynamic prices Combine and submit to the carbon trading system.

[0012] Furthermore, the demand-side strategy includes: Under a uniform procurement strategy: ; In the formula, Indicates daily purchase volume. This indicates the anticipated daily quota shortfall; under this strategy, market price fluctuations are often ignored, and excessive purchases at high prices may be made, pushing up costs. The uniform procurement strategy is optimized, while the original plan is retained as a benchmark to ensure basic security of contract performance. A dynamic procurement model based on price forecasting and risk preference is constructed.

[0013] T1. Dynamic Procurement Strategy: Constructing a dynamic procurement model based on price forecasting and risk appetite; T11, Calculate the benchmark procurement quantity : ; In the formula, This indicates the anticipated daily quota shortfall. T12, Computerized procurement volume This is used to purchase excess quantities when prices are low, establishing quota inventory to smooth future procurement costs. ; in, This represents the company's risk appetite coefficient. Conservative enterprises tend to take lower values; Indicates the remaining quota shortfall; Indicates the current market price; , These represent the high and low points of the preset recent price range, respectively. This indicates the trigger price for opportunity purchases (e.g., when it is below the 60-day moving average). T13, Final Daily Purchase Quantity : ; T2. Scientific Pricing Strategy: From fixed cost to flexible range: Under the fixed cost strategy, the bid price equals the carbon opportunity cost. This price is the highest psychological price, which is effective, but not precise enough. ; In the formula, Indicates the declared price. Indicates carbon opportunity cost; If the cost of purchasing quotas exceeds the profit from producing the product, then economically speaking, it is more cost-effective for the company to halt production and sell the quotas; in this case, it represents the absolute maximum price. Conversely, if the market price remains consistently below the shadow price for implementing a particular energy-saving technological upgrade, then purchasing quotas is more economical than investing in the upgrade. Therefore, a flexible pricing range should be established. ; Price ceiling This is the opportunity cost of carbon: ; Price floor The shadow price is based on the cost of technological upgrades: ; Final declared price: The system in Within the specified range, prices are dynamically adjusted based on market conditions and the urgency of the procurement; for example, in the early stages of contract fulfillment, prices closer to [the specified range] are offered. Quotation; as the performance period approaches, the quotation will be gradually increased, but will never exceed [a certain amount]. .

[0014] Furthermore, the system also includes a price-related two-way hierarchical risk early warning module, specifically: Market price position :set up The current market price, and The market price position is determined by the 20th and 80th percentiles of historical price data, respectively. Defined as: Low bit: < Median: ≤ ≤ High position: > ; Supply-side early warning, quota surplus enterprises >0: >10%: When When the level is low, a level 3 warning is issued; observe and wait. When the price is at the median, a level-two warning is issued, and sales should be initiated at an opportune time; when... When prices are high, issue a Level 1 warning and sell at the high price. 5% ≤10%: When When the level is low, a level 3 warning is issued; observe and wait. When the price is in the middle range, a level 3 warning is issued; observe and wait. When prices are high, a level-two warning is issued, and selling should be considered when the opportunity arises. 0< ≤5%: When When the level is low, a level 3 warning is issued; observe and wait. When the price is in the median, a level 3 warning is issued; observe and wait. When the price is high, a level-three warning is issued; observe and wait. Equilibrium state warning, =0: when When the price is low, a level three warning is issued, and the system suggests waiting and observing, recommending that a small amount of inventory be established. When the price is in the median, a level 3 warning is issued; observe and wait. When the price is high, a level 3 warning is issued, and the system suggests waiting and observing, with the suggestion being: consider selling a small amount. Demand-side warning, enterprises with quota gaps <0: -5%≤ <0: When When the price is low, a Level 1 warning is issued, and low-price procurement is initiated; when... When the price is in the median, a level 3 warning is issued; observe and wait. When the price is high, a level-three warning is issued; observe and wait. -10%≤ <-5%: When When the price is low, a Level 1 warning is issued, and low-price procurement is initiated; when... When the median is reached, a level-two warning is issued, and operational optimization is implemented; when... When the price is high, a level-three warning is issued; wait and see. <-10%: When When the price is low, a Level 1 warning is issued, and low-price procurement is initiated; when... When the median value is reached, a Level 1 warning is issued, and procurement is initiated as appropriate; when... When the level is high, a level-two warning is issued, and strategic adjustments are made.

[0015] This invention also provides an optimization method for dynamic carbon emission accounting and intelligent decision-making in carbon quota trading, employing the aforementioned intelligent decision-making system for dynamic carbon emission accounting and carbon quota trading, comprising the following steps: Step 1: Real-time data collection: Collect carbon emission-related data from the enterprise's production and emission activities, including fuel combustion, production processes, and energy use; Step 2, Dynamic Calculation: The dynamic calculation module performs rolling calculations based on the collected data and outputs carbon emissions and emission intensity; Step 3, Quota Dynamic Prediction: Based on the improved baseline method, the quota surplus and shortage are dynamically predicted, and multi-scenario simulation is supported. The rolling quota surplus and shortage status and quota surplus and shortage probability distribution map are output. Step 4, Intelligent Decision-Making for Carbon Quota Trading: Execute dynamic trading strategies based on quota surplus or shortage status. Execute supply-side strategies when there is a quota surplus and demand-side strategies when there is a quota shortage. Generate corresponding risk warnings and output trading instructions including price, quantity, and timing.

[0016] The present invention employs the above-mentioned method and system for dynamic carbon emission accounting and intelligent decision-making optimization of carbon quota trading, and its beneficial effects are as follows: (1) This invention realizes near real-time dynamic accounting of carbon emissions and accurate prediction of quotas. It achieves daily rolling accounting of carbon emissions through high-frequency data collection, innovates and improves the baseline method, and provides rolling prediction and dynamic adjustment mechanism. The quota surplus and shortage prediction is accurate, providing full-cycle quantitative support for enterprise carbon management and improving management efficiency. (2) This invention constructs a supply and demand-side adaptive trading strategy, and customizes trading models for enterprises with quota surplus and deficit respectively, replacing the traditional experience-based extensive decision-making, greatly reducing the enterprise's compliance costs, and maximizing the value of carbon assets while ensuring compliance security. (3) This invention creates a closed-loop management system for the entire process, connects the data links of the entire process of “accounting-prediction-trading-early warning”, and breaks the information silos of traditional carbon management; the price-related two-way graded risk early warning mechanism realizes precise strategy matching and strengthens risk prevention and control and industry adaptability. Attached Figure Description

[0017] Figure 1 This is the overall framework diagram of the intelligent decision-making optimization method and system for dynamic carbon emission accounting and carbon quota trading of the present invention; Figure 2 This is a flowchart of the dynamic accounting module of the present invention, which is a method and system for optimizing dynamic carbon emission accounting and intelligent decision-making for carbon quota trading. Figure 3 This is a flowchart of the quota dynamic prediction and optimization module of the carbon emission dynamic accounting and carbon quota trading intelligent decision optimization method and system of the present invention; Figure 4 This is a diagram of the intelligent carbon quota trading strategy module architecture of the method and system for dynamic carbon emission accounting and intelligent decision-making optimization of carbon quota trading according to the present invention. Figure 5 This is a flowchart of the demand-side dynamic trading strategy of a method and system for dynamic carbon emission accounting and intelligent decision-making optimization of carbon quota trading according to the present invention. Figure 6 This is a flowchart of the supply-side dynamic trading strategy of a method and system for dynamic carbon emission accounting and intelligent decision-making optimization of carbon quota trading according to the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0019] This invention provides a method and system for optimizing dynamic carbon emission accounting and intelligent carbon quota trading, and conducts simulation verification of the system for dynamic carbon emission accounting and intelligent carbon quota trading for a steel company.

[0020] I. Simulation Object and Parameter Settings: 1. Overview of the research subject: A steel conglomerate with an annual crude steel production of 5 million tons was selected as the verification subject. The main production processes of this enterprise include sintering, pelletizing, ironmaking, steelmaking, and rolling. It belongs to a key high-energy-consuming and high-emission industry and has been included in the national carbon emission trading market.

[0021] 2. Data Basis: Based on the company's full-year production and operation data for 2024, including daily fuel consumption (washed coal, anthracite, coke, natural gas, etc.), input of carbon-containing raw materials (iron ore, limestone, dolomite, etc.), and output of various products (sintered ore, pig iron, crude steel, etc.), with a data frequency of once daily. Carbon price data adopts the actual transaction price series of the national carbon market in 2024, including the daily opening price, closing price, highest price, lowest price, and trading volume.

[0022] 3. Key parameter settings: Table 1 Key Parameter Settings

[0023] II. Simulation Process: This embodiment follows the three main modules described in the technical solution of the present invention (such as...). Figure 1 As shown in the figure, a complete simulation operation process was constructed; 1. Dynamic accounting module operation: The system connects to the enterprise's production database and automatically collects key activity data such as fuel consumption, raw material input, and product output daily. According to the rolling accounting process (such as) Figure 2 As shown), daily dynamic accounting of fossil fuel combustion emissions and industrial process emissions, and rolling calculation of cumulative monthly and annual total emissions; Taking January 2024 as an example, the system outputs the daily carbon emission change curve for that month, identifies emission fluctuations caused by blast furnace maintenance, and achieves timely early warning of abnormal emissions.

[0024] 2. Operation of the quota dynamic prediction and optimization module (e.g.) Figure 3 (as shown) Based on the production plan for each process over the next 6 months provided by the company's production planning department, an LSTM neural network model is used to make rolling predictions of production output. By combining the real-time emission intensity output by the dynamic accounting module, the carbon emission trend for the next 6 months can be predicted. Introducing dynamic quota adjustment factor (Based on industry policy trends and market supply and demand data, the pre-allocated quota is dynamically adjusted.) Calculate the quota surplus / deficit rate The system outputs the following assessment results: The predicted quota shortfall for enterprises in 2024 is approximately 85,000 tCO2. The deficit is approximately -0.92%, with the main gap concentrated in the third quarter (peak production season during the high-temperature period).

[0025] 3. The carbon quota trading intelligent strategy module is running (e.g.) Figure 4 (as shown) Demand-side strategy (for the steel company in this case): The system is based on demand-side strategies (such as...) Figure 5 As shown in the figure, based on the benchmark uniform purchase strategy, an opportunity window is identified where the market price is lower than the trigger threshold, and opportunity purchase is initiated to over-purchase the quota at the low price. In terms of pricing strategy, the system dynamically bids within the flexible range of [85, 185] yuan / ton. In the early stages of contract fulfillment, it makes exploratory purchases at lower prices and appropriately raises the bid as the contract fulfillment period approaches to ensure contract fulfillment. Risk warning module operation: The system monitors the quota surplus / deficit rate of enterprises in real time. and market price position The system provides differentiated decision support based on its price-related two-way hierarchical early warning matrix.

[0026] Supply-side strategy (for other related companies with surpluses; this example is a multi-entity test): The system is based on supply-side strategies (such as...) Figure 6 As shown in the figure, calculate the trading volume on the benchmark day and dynamically adjust the daily trading volume in combination with the error correction component; Meanwhile, daily order prices are generated based on a dynamic pricing model, and surplus quotas are gradually released when the market price is higher than the floor price.

[0027] III. Comparison Scenario Settings: To verify the overall effectiveness of the present invention, the following four comparison scenarios were set up, and the simulation system was run in each scenario; Table 2 Comparison of Scene Settings

[0028] IV. Comparison of Simulation Results and Beneficial Effects: By running simulations of the four scenarios described above and comparing and analyzing various key indicators, the results are shown in the table below: Table 3 Comparison of Beneficial Effects

[0029] Results analysis: 1. Significantly Reduced Fulfillment Costs: Using the complete solution of this invention (Scenario 4), the annual fulfillment cost is RMB 7.684 million, a reduction of 31.7% compared to the baseline scenario and a reduction of 22.0% compared to Scenario 2 which only uses dynamic accounting. This demonstrates that the intelligent trading strategy effectively capitalizes on low market price windows, reducing the average purchase price; dynamic quota prediction reduces cost losses from blind trading; the opportunistic purchasing mechanism accumulates over-purchased quotas of approximately 8,200 tons at low prices, saving approximately RMB 672,000; and the high-price selling mechanism accumulates over-sold surplus quotas of approximately 3,500 tons at high prices, increasing revenue by approximately RMB 284,000.

[0030] 2. Improved timeliness and predictive capability of carbon emission accounting: This invention increases the frequency of carbon emission accounting from annual to daily, achieving near real-time dynamic updates of emission data. Based on this, combined with a production forecasting model and a dynamic quota adjustment factor, the accuracy rate of quota surplus / deficit prediction reaches 91.6%, providing a reliable basis for enterprises to plan their trading strategies in advance.

[0031] 3. Optimized transaction execution: The demand-side strategy, through opportunistic purchasing mechanisms and dynamic pricing strategies, resulted in an average purchase price 12.7 yuan / ton lower than the market average, a reduction of 13.7%. The dynamic pricing strategy enabled companies to make exploratory purchases at lower prices in the early stages of contract fulfillment, and then appropriately raise their bids as the fulfillment period approached to ensure compliance, thus achieving a balance between cost and performance risk.

[0032] 4. Enhanced Risk Control Capabilities (Price-Related Two-Way Tiered Early Warning): The price-related two-way tiered early warning system constructed in this invention is based on the quota surplus / deficit rate. and market price position Provides differentiated decision support. Examples of quarterly early warning applications are shown below in this embodiment: Table 4 Examples of Early Warning Applications in Each Quarter

[0033] Early warning accuracy matching rate: After adopting this invention, the early warning system can accurately match the target data based on the target data. and The accuracy of matching suggested strategies was improved, and the accuracy of early warning matching rate increased from 76.5% in scenario 3 to 93.2%, reducing losses caused by strategy misjudgment.

[0034] Therefore, this invention employs the aforementioned method and system for dynamic carbon emission accounting and intelligent decision-making optimization of carbon quota trading. It achieves near real-time dynamic carbon emission accounting and accurate quota prediction, enabling daily rolling carbon emission accounting through high-frequency data acquisition. It innovatively improves the baseline method, incorporating a rolling forecasting and dynamic adjustment mechanism, ensuring accurate quota surplus / deficit prediction. This provides full-cycle quantitative support for enterprise carbon management, improving management efficiency. Furthermore, it constructs a supply-demand-side adaptive trading strategy, customizing trading models for enterprises with quota surpluses and deficits, replacing traditional experience-based extensive decision-making, significantly reducing enterprise compliance costs, and maximizing carbon asset value while ensuring compliance security. It also creates a closed-loop management system, connecting the data links of "accounting-prediction-trading-early warning," breaking down information silos in traditional carbon management. A price-linked two-way graded risk early warning mechanism enables precise strategy matching, strengthening risk control and industry adaptability.

[0035] It is worth noting that all contents not described in detail in this invention are existing technologies and are well known to those skilled in the art.

[0036] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A dynamic carbon emission accounting and carbon quota trading intelligent decision-making system, characterized in that, It includes a dynamic accounting module, a quota dynamic prediction and optimization module, and a quota transaction intelligent decision-making module; The dynamic accounting module includes a dynamic activity data acquisition system. The dynamic accounting module determines the accounting boundary and identifies emission sources. It collects key activity data of the enterprise through the dynamic activity data acquisition system and performs rolling accounting based on the collected data. The dynamic activity data acquisition system integrates the enterprise's energy management system, manufacturing execution system, distributed control system, and IoT smart meters to automatically collect key activity data at a preset frequency. The quota dynamic prediction and optimization module uses an improved baseline method to predict the quota surplus or deficit of enterprises. The improved baseline method introduces rolling prediction, dynamic adjustment and multi-scenario simulation mechanisms on the basis of the traditional baseline method; The intelligent strategy module for carbon quota trading incorporates supply-side and demand-side strategies. Enterprises with quota surpluses execute supply-side strategies, while enterprises with quota deficits execute demand-side strategies. The improved baseline method for predicting enterprise quota surpluses and deficits specifically involves: Baseline quota calculation: The baseline method is adopted as the basic method for quota allocation, and a baseline value for product carbon emissions is set. Based on dynamic accounting results and production data, the quota surplus or shortage status of enterprises in a certain period can be predicted: ； In the formula, Indicates enterprise Pre-allocation of quotas based on the baseline method Indicates enterprise Product output during the forecast period This refers to the benchmark carbon emission values ​​for products published by the industry's regulatory authority; Rolling production and emissions forecasts: Based on enterprise production plans, historical output trends, and equipment operating status, an output forecasting model is constructed, including an ARIMA time series model and an LSTM neural network model, to predict future output. Rolling production forecasts for the period, combined with real-time emission intensity from the dynamic accounting module. The formula for predicting future carbon emissions is: ； In the formula, Indicates the current moment. This indicates the offset for the future forecast period. ; Indicates the first Individual companies Predicted output at any given time Indicates the first Individual companies Predicted emission intensity at any given time This indicates a projected future carbon emissions; Dynamic quota adjustment factor: Introducing dynamic quota adjustment factor This reflects the impact of policy adjustments, market supply and demand, and seasonal fluctuations, and is expressed as: ； In the formula, This indicates the pre-allocated quota after dynamic adjustment. Indicates enterprise Pre-allocation quotas based on the baseline method; Dynamic assessment of quota surplus / shortage status: Compare and The size, if If so, it is a quota surplus; if If so, it is a quota shortfall; if This indicates a quota balance; Introducing quota surplus / deficit rate , This refers to the proportion of the difference between the pre-allocated carbon emission allowance and the predicted carbon emission amount after dynamic adjustment by the enterprise to the pre-allocated allowance: ； when A value greater than 0 indicates a corporate quota surplus, with the surplus amount being... ; when When =0, it indicates that the enterprise quota is balanced; when When the value is less than 0, it indicates that the company has a quota shortfall, and the shortfall amount is... ; The supply-side strategy specifically refers to: S1. Calculate dynamic trading volume: Determine the final daily trading volume. ; S2. Dynamic pricing model: Determine the floor price by adopting a model based on the opportunity cost of holding; S3. Determine the expected market price level. ; S4, Dynamic Pricing Model: S41. Introduce a transaction urgency factor. Based on the number of days remaining until the official deadline for fulfillment, the calculation is dynamically performed. value: ； In the formula, It is a constant that adjusts the sensitivity. This indicates the unified compliance deadline for the national carbon market. Indicates the current date; S42. Generate the final bid price The dynamic pricing formula is as follows: ； S5. Combined Declaration: Calculated daily trading volume With dynamic prices Combine and submit to the carbon trading system.

2. The intelligent decision-making system for dynamic carbon emission accounting and carbon quota trading according to claim 1, characterized in that, The specific process of the dynamic accounting module performing rolling accounting based on the collected data is as follows: Calculation of carbon dioxide emissions from fossil fuel combustion: ； In the formula, This indicates the amount of carbon dioxide emissions produced by burning fossil fuels. Indicates the type of fossil fuel. Indicates the first The average lower heating value of fossil fuels Indicates the first Net consumption of fossil fuels. Indicates the first The carbon content per unit calorific value of a fossil fuel. Indicates the first Carbon oxidation rate of fossil fuels; Calculation of carbon dioxide emissions from industrial processes: The carbon dioxide emissions from industrial processes include two parts: process emissions calculated using the material balance method and emissions from the carbonate utilization process. The expression is as follows: ； In the formula, This indicates the amount of carbon dioxide emitted during industrial processes. Indicates the first Such materials, This indicates the total number of material types. Indicates the first The amount of input material. Indicates the first The amount of output material. Indicates the first The carbon content of the input material. Indicates the first The carbon content of the output material. Indicates the type of carbonate. Indicates the number of carbonate species. Indicates the first The consumption of various carbonates. Indicates the first The emission factors of various carbonates, Indicates the first The purity of the carbonate; Calculation of total carbon dioxide emissions from enterprises: ； In the formula, Indicates the first The total carbon dioxide emissions of each enterprise during the accounting period; Corporate carbon intensity: ； In the formula, Indicates the first Carbon emission intensity of individual enterprises Indicates the first The total output of qualified products of each enterprise during the accounting period.

3. The intelligent decision-making system for dynamic carbon emission accounting and carbon quota trading according to claim 2, characterized in that, The quota dynamic prediction and optimization module also includes multi-scenario simulation and risk warning functions, specifically: adjusting the formula in the improved baseline method according to scenarios including production fluctuations, benchmark value adjustments, and market price changes, and outputting quota surpluses and deficits under different scenarios; Based on quota surplus / shortage rate Output a probability distribution chart of quota surplus or shortage to provide enterprises with visualized risk warnings.

4. The intelligent decision-making system for dynamic carbon emission accounting and carbon quota trading according to claim 2, characterized in that, The supply-side strategy specifically refers to: S1. Calculate dynamic transaction volume: S11, Calculate the benchmark trading volume : ； In the formula, Indicates the benchmark trading volume. This indicates a projected annual quota surplus. Indicates the basic carryover amount. This indicates the predicted market demand for the day. This represents the total remaining projected demand for the entire year; S12, Calculate the error correction component : Based on the cumulative error between previous transaction volume and planned volume, the remaining market demand is dynamically allocated according to the proportion of remaining demand, expressed as: ； In the formula, Indicates the error correction component. Indicates the planned transaction volume. Indicates the actual transaction volume; S13. Determine the final daily trading volume. : ； In the formula, This indicates the final day's trading volume. For smoothing coefficients, ; S2, Dynamic Pricing Model: The floor price for the offer is determined using a model based on the opportunity cost of holding, and includes the following components: S21, Opportunity Cost of Holding Quotas : The cost of capital tied up by a company that does not sell its quota now but holds it until it sells or uses it in the future is expressed as follows: ； In the formula, This represents a predicted value for carbon prices at a future point in time. Indicates the company's cost of capital. Indicates the holding period in years; This represents the discount factor under continuously compounded interest. S22. Define transaction costs and risk premiums. This includes transaction fees, fund settlement costs, and risks arising from future policy uncertainties; Base price for: ； S3. Determine the expected market price level. Obtain it through the following methods: Historical price analysis: Moving average price over a past period; Fundamental analysis: Predicting price trends based on policy news, industry dynamics, energy prices, etc. Technical analysis: Analysis includes price charts and trading volume data; S4, Dynamic Pricing Model: S41. Introduce a transaction urgency factor. Based on the number of days remaining until the official deadline for fulfillment, the calculation is dynamically performed. value: ； In the formula, It is a constant that adjusts the sensitivity. This indicates the unified compliance deadline for the national carbon market. Indicates the current date; S42. Generate the final bid price The dynamic pricing formula is as follows: ； S5. Combined Declaration: Calculated daily trading volume With dynamic prices Combine and submit to the carbon trading system.

5. The intelligent decision-making system for dynamic carbon emission accounting and carbon quota trading according to claim 2, characterized in that, The demand-side strategies include: T1. Dynamic Procurement Strategy: Constructing a dynamic procurement model based on price forecasting and risk appetite; T11, Calculate the benchmark procurement quantity : ； In the formula, This indicates the anticipated daily quota shortfall. T12, Computerized procurement volume This is used to purchase excess quantities when prices are low, establishing quota inventory to smooth future procurement costs. ； in, This represents the company's risk appetite coefficient. ; Indicates the remaining quota shortfall; Indicates the current market price; , These represent the high and low points of the preset recent price range, respectively. Indicates the trigger price for opportunity purchase; T13, Final Daily Purchase Quantity : ； T2. Scientific Pricing Strategy: Set up a flexible pricing range ; Price ceiling This is the opportunity cost of carbon: ； Price floor The shadow price is based on the cost of technological upgrades: ； Final declared price: The system in Within the specified range, prices are dynamically adjusted based on market conditions and the urgency of the procurement; for example, in the early stages of contract fulfillment, prices closer to [the specified range] are offered. Quotation; as the performance period approaches, the quotation will be gradually increased, but will never exceed [a certain amount]. .

6. The intelligent decision-making system for dynamic carbon emission accounting and carbon quota trading according to claim 5, characterized in that, The system also includes a price-related two-way hierarchical risk early warning module, specifically: Determine market price position :set up The current market price, and The market price position is determined by the 20th and 80th percentiles of historical price data, respectively. Defined as: Low bit: < Median: ≤ ≤ High position: > ; Supply-side early warning, quota surplus enterprises >0: >10%: When When the level is low, a level 3 warning is issued; observe and wait. When the price is at the median, a level-two warning is issued, and sales should be initiated at an opportune time; when... When prices are high, issue a Level 1 warning and sell at the high price. 5% ≤10%: When When the level is low, a level 3 warning is issued; observe and wait. When the price is in the median, a level 3 warning is issued; observe and wait. When prices are high, a level-two warning is issued, and selling should be considered when the opportunity arises. 0< ≤5%: When When the level is low, a level 3 warning is issued; observe and wait. When the price is in the median, a level 3 warning is issued; observe and wait. When the price is high, a level-three warning is issued; observe and wait. Equilibrium state warning, =0: when When the price is low, a level three warning is issued, and the system suggests waiting and observing, recommending that a small amount of inventory be established. When the price is in the median, a level 3 warning is issued; observe and wait. When the price is high, a level 3 warning is issued, and the system suggests waiting and observing, with the suggestion being: consider selling a small amount. Demand-side warning, enterprises with quota gaps <0: -5%≤ <0: When When the price is low, a Level 1 warning is issued, and low-price procurement is initiated; when... When the price is in the median, a level 3 warning is issued; observe and wait. When the price is high, a level-three warning is issued; observe and wait. -10%≤ <-5%: When When the price is low, a Level 1 warning is issued, and low-price procurement is initiated; when... When the median is reached, a level-two warning is issued, and operational optimization is implemented; when... When the price is high, a level-three warning is issued; wait and see. <-10%: When When the price is low, a Level 1 warning is issued, and low-price procurement is initiated; when... When the median value is reached, a Level 1 warning is issued, and procurement is initiated as appropriate; when... When the level is high, a level-two warning is issued, and strategic adjustments are made.

7. A method for optimizing dynamic carbon emission accounting and intelligent decision-making for carbon allowance trading, employing the intelligent decision-making system for dynamic carbon emission accounting and carbon allowance trading as described in any one of claims 1-6, characterized in that... Includes the following steps: Step 1: Real-time data collection: Collect carbon emission-related data from the enterprise's production and emission activities, including fuel combustion, production processes, and energy use; Step 2, Dynamic Calculation: The dynamic calculation module performs rolling calculations based on the collected data and outputs carbon emissions and emission intensity; Step 3, Quota Dynamic Prediction: Based on the improved baseline method, the quota surplus and shortage are dynamically predicted, and multi-scenario simulation is supported. The rolling quota surplus and shortage status and quota surplus and shortage probability distribution map are output. Step 4, Intelligent Decision-Making for Carbon Quota Trading: Execute dynamic trading strategies based on quota surplus or shortage status. Execute supply-side strategies when there is a quota surplus and demand-side strategies when there is a quota shortage. Generate corresponding risk warnings and output trading instructions including price, quantity, and timing.

Images