Carbon quota intelligent transaction method, system and device based on production plan and medium

Abstract

This invention relates to the field of carbon emission management technology, and proposes a method, system, equipment, and medium for intelligent carbon quota trading based on production planning. The method includes: acquiring carbon emission regulatory constraints, future production schedule data, and current carbon trading price time series data; calculating the predicted carbon emissions for each target time period based on the future production schedule data and preset emission factors for each product; predicting the carbon trading price for each target time period based on the current carbon trading price time series data; and using an optimization model with the objective function of minimizing the overall carbon cost, solving for the target carbon quota trading volume for each target time period based on the carbon emission regulatory constraints, the predicted carbon emissions for each target time period, and the carbon trading price for each target time period, to conduct carbon trading based on the target carbon quota trading volume for each target time period. This method can proactively capture favorable market opportunities and truly achieve scientific decision-making in carbon asset management.

Description

Technical Field

[0001] This invention relates to the field of carbon emission management technology, and in particular to a method, system, device and medium for intelligent trading of carbon quotas based on production planning. Background Technology

[0002] As the global carbon neutrality strategy deepens, industrial enterprises are facing increasing pressure to manage carbon emissions, with increasingly stringent compliance constraints, including carbon quota caps, carbon tax rates, and penalties for exceeding limits. At the same time, frequent price fluctuations in the carbon trading market are placing higher demands on enterprises' carbon asset management capabilities.

[0003] Currently, enterprises generally use month-end energy consumption data collection to estimate carbon emissions, that is, calculating carbon emissions based on actual monthly energy consumption statistics and making carbon quota trading decisions accordingly. However, this ex-post statistical method has significant data lag and cannot reflect the dynamic changes in carbon emissions during the enterprise's production process in real time. Decisions based on lagging data often cause enterprises to miss favorable market opportunities: for example, when market prices are at a short-term high, enterprises may miss the window of opportunity to sell quotas because they have not yet grasped their actual emissions situation; or when quotas are scarce, information delays may force them to buy at high prices, increasing compliance costs. In addition, centralized month-end accounting can easily lead to multiple enterprises trading at the same time, creating a buying frenzy and further driving up transaction costs.

[0004] It is worth noting that most manufacturing enterprises have accumulated stable and accurate future production scheduling data in their Enterprise Resource Planning (ERP) or Manufacturing Execution System (MES) systems. Their actual output in the short term (e.g., the next month) is highly consistent with the plan, demonstrating high predictability. However, current technologies have not effectively utilized this production scheduling data for forward-looking carbon emission forecasting and quota trading optimization. They still primarily rely on manual judgment and lagging historical data, resulting in low efficiency and poor decision-making quality in carbon asset management. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method, system, device and medium for intelligent trading of carbon quotas based on production planning, so as to solve the above-mentioned technical problem.

[0006] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A method for intelligent carbon quota trading based on production planning, comprising: acquiring carbon emission regulatory constraint information, future production schedule data, and current carbon trading price time series data, wherein the future production schedule data includes the planned output of each product in each target time period; calculating the predicted carbon emission amount for each target time period based on the future production schedule data and preset emission factors corresponding to each product; predicting the carbon trading price for each target time period based on the current carbon trading price time series data; and using an optimization model with the objective function of minimizing the comprehensive carbon cost, solving for the target carbon quota trading amount for each target time period based on the carbon emission regulatory constraint information, the predicted carbon emission amount for each target time period, and the carbon trading price for each target time period, so as to conduct carbon trading based on the target carbon quota trading amount for each target time period.

[0007] The beneficial effects of this invention are as follows: This method achieves accurate time-segmented prediction of a company's future carbon emissions and carbon trading prices by acquiring information on carbon emission regulatory constraints, future production scheduling data including planned product output for each time period, and current carbon trading price time series data. Based on this, it deeply integrates regulatory constraints, emission prediction, and price prediction to construct an optimization model with minimizing overall carbon costs as the objective function. This model automatically solves for the optimal carbon quota trading volume for each time period, thereby transforming traditional ex-post decision-making relying on human experience into data-driven, intelligent, and refined ex-ante planning. Through this method, favorable market opportunities can be proactively captured, effectively reducing compliance costs or increasing carbon asset returns while ensuring compliance, truly achieving scientific decision-making in carbon asset management.

[0008] Based on the above technical solution, the present invention can be further improved as follows.

[0009] Furthermore, the carbon emission regulatory constraint information is obtained through the following methods: acquiring the carbon emission regulatory text using robotic process automation technology; semantically parsing the carbon emission regulatory text using a large language model based on preset prompts to generate parsing results; and converting the parsing results into a structured data format to obtain the carbon emission regulatory constraint information.

[0010] The beneficial effects of adopting the above-mentioned further solution are: by automatically acquiring the original text of regulations through robotic process automation technology, and combining the semantic understanding capabilities of large language models, intelligent parsing and structured conversion of unstructured carbon emission regulatory texts are achieved, eliminating the need for manual reading and input, and significantly improving the efficiency and accuracy of regulatory information extraction.

[0011] Furthermore, the step of calculating the predicted carbon emissions for each target time period based on the future production schedule data and the preset emission factors corresponding to each product includes: for each target time period, calculating the carbon emission contribution of each product within the target time period based on the planned output of each product within the target time period and the preset emission factors corresponding to each product; and summing the carbon emission contributions of each product within each target time period to obtain the predicted carbon emissions for each target time period.

[0012] The beneficial effects of adopting the above-mentioned further solutions are: by combining the company's existing production scheduling data with preset emission factors, it is possible to achieve refined time-segmented prediction of future carbon emissions, without the need for a large amount of historical data accumulation and complex model training, and can respond to adjustments in production plans in real time, providing accurate and reliable emission data support for carbon quota trading decisions.

[0013] Furthermore, the objective function of the optimization model includes a carbon trading cost item and an excess penalty item. The carbon trading cost item is determined based on the carbon trading price for each target time period, and the excess penalty item is determined based on the maximum emission limit and penalty rate in the carbon emission regulatory constraint information, the obtained historical carbon emission volume, and the carbon emission prediction for each target time period.

[0014] The beneficial effect of adopting the above-mentioned further scheme is that the penalty for exceeding the limit is directly incorporated into the objective function, enabling the optimization model to actively choose to pay the penalty instead of purchasing quotas when the carbon price is high, thus achieving an optimized choice for flexible compliance.

[0015] Furthermore, the target carbon allowance trading volume for each target time period includes both buying and selling volumes; the constraints of the optimization model include at least the following: the buying and selling volumes for each target time period obtained are both greater than or equal to zero; the sum of the initial allowance and net buying volume in the carbon emission regulatory constraint information is greater than or equal to the sum of the obtained historical carbon emissions and the predicted carbon emissions for each target time period; wherein, the net buying volume is determined by the buying and selling volumes for each target time period obtained.

[0016] The beneficial effects of adopting the above-mentioned further scheme are: by setting non-negative constraints on the purchase and sale quantities, the physical realizability of the solution is ensured; by using quota balancing constraints, it is ensured that the total quota held by the enterprise throughout the entire compliance period can fully cover the actual emissions, thus avoiding the risk of violations due to insufficient quotas.

[0017] Furthermore, the step of conducting carbon trading based on the target carbon quota trading volume for each target time period includes: upon entering each target time period, acquiring the actual carbon price in real time and calculating the deviation between the carbon trading price for the target time period and the actual carbon price to obtain the carbon price deviation; when the carbon price deviation is less than a preset threshold, converting the target carbon quota trading volume for the target time period into a trading instruction to execute a buy / sell operation based on the trading instruction; and when the carbon price deviation is still less than the preset threshold by the end of the target time period, generating a manual decision-making prompt signal to prompt manual confirmation of whether to execute the transaction.

[0018] The beneficial effects of adopting the above-mentioned further scheme are: by comparing the actual carbon price with the predicted price in real time within the target time period, and automatically executing the transaction only when the deviation is controllable, it not only seizes favorable market opportunities, but also effectively avoids the trading risks caused by excessive prediction deviation.

[0019] Furthermore, the method also includes: real-time monitoring of closed-loop feedback triggering events, wherein the closed-loop feedback triggering events include at least one of carbon emission regulation text update events, future production scheduling data change events, carbon trading market fluctuation events, and transaction non-execution events; when the closed-loop feedback triggering event is detected, the target carbon quota trading volume for each target time period is automatically triggered to update.

[0020] The beneficial effects of adopting the above-mentioned further solutions are: by monitoring changes in regulations, production, market and transaction execution status in real time, the entire process can be automatically recalculated, enabling the trading strategy to dynamically respond to changes in the external environment and ensuring the continued effectiveness of the strategy.

[0021] To address the aforementioned technical problems, this invention also provides a carbon quota intelligent trading system based on production planning, comprising: The data acquisition module is used to acquire carbon emission regulatory constraints, future production schedule data, and current carbon trading price time series data. The future production schedule data includes the planned output of each product in each target time period in the future. The carbon emission calculation module is used to calculate the predicted carbon emissions for each target time period based on the future production schedule data and the preset emission factors corresponding to each product. The price prediction module is used to predict the carbon trading price for each target time period based on the current carbon trading price time series data. The automatic trading module is used to calculate the target carbon allowance trading volume for each target time period based on the carbon emission regulatory constraints, the predicted carbon emissions for each target time period, and the carbon trading price for each target time period, using an optimization model with the objective function of minimizing the overall carbon cost, so as to conduct carbon trading based on the target carbon allowance trading volume for each target time period.

[0022] To address the aforementioned technical problems, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aforementioned intelligent carbon quota trading method based on production planning.

[0023] To address the aforementioned technical problems, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the aforementioned carbon quota smart trading method based on production planning. Attached Figure Description

[0024] Figure 1 This is a flowchart of the intelligent carbon quota trading method based on production planning according to the present invention; Figure 2 This is a schematic diagram of the intelligent carbon quota trading system based on production planning according to the present invention; Figure 3 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0025] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0026] Example 1 like Figure 1 As shown, this embodiment provides a smart trading method for carbon quotas based on production planning, including: S101. Obtain carbon emission regulatory constraints, future production schedule data, and current carbon trading price time series data, wherein the future production schedule data includes the planned output of each product in each target time period in the future.

[0027] The target time period can be a preset time granularity such as hour, day, or week, and can be flexibly set according to the enterprise's production characteristics and transaction needs.

[0028] Current carbon trading price time series data can be obtained in real time by connecting to the carbon exchange's API interface, specifically including the carbon trading price at the current moment and the carbon trading price over a period of time before the current moment.

[0029] S102. Calculate the predicted carbon emissions for each target time period based on the future production schedule data and the preset emission factors for each product.

[0030] S103. Based on the current carbon trading price time series data, predict the carbon trading price for each target time period.

[0031] S104. Based on the carbon emission regulatory constraints, the predicted carbon emissions for each target time period, and the carbon trading price for each target time period, the target carbon allowance trading volume for each target time period is obtained using an optimization model with the objective function of minimizing the overall carbon cost, so as to conduct carbon trading based on the target carbon allowance trading volume for each target time period.

[0032] This method achieves accurate time-segmented predictions of future carbon emissions and carbon trading prices by acquiring information on carbon emission regulations, future production scheduling data including planned product output for each time period, and current carbon trading price time-series data. Based on this, it deeply integrates regulatory constraints, emission predictions, and price predictions to construct an optimization model with minimizing overall carbon costs as the objective function. This model automatically solves for the optimal carbon allowance trading volume for each time period, transforming traditional ex-post decision-making relying on human experience into data-driven, intelligent, and refined ex-ante planning. This method proactively captures favorable market opportunities, effectively reducing compliance costs or increasing carbon asset returns while ensuring compliance, truly achieving scientific decision-making in carbon asset management.

[0033] Optionally, in an embodiment, the carbon emission regulatory constraint information is obtained by: acquiring the carbon emission regulatory text through robotic process automation (RPA); performing semantic parsing of the carbon emission regulatory text using a large language model based on preset prompts to generate parsing results; and converting the parsing results into a structured data format to obtain the carbon emission regulatory constraint information.

[0034] Specifically, Robotic Process Automation (RPA) technology is used to obtain the original text of regulations from official documents or API interfaces of the target country or region. Using an existing Large Language Model (LLM) combined with preset prompts, semantic recognition is performed on the obtained carbon emission regulations text to automatically extract core field information related to carbon emission management, such as maximum carbon emission limits, excess emission rates, and free allowances.

[0035] For example, the format of a Prompt message is as follows: Please read the carbon emission regulations text and extract key information related to carbon quota management, including: 1. The countries or regions to which this regulation applies; 2. The type of industry targeted (e.g., steel, cement, etc.); 3. Maximum allowable emission limits (tonnes) for each cycle; 4. Penalty standards for exceeding emission limits (RMB / ton); 5. The effective date and expiration date of the regulations (e.g., January 1, 2025 to December 31, 2025); 6. The amount of carbon emission allowances (tons) that can be obtained free of charge during this cycle.

[0036] Please answer directly in natural language, one line per item, concise and clear.

[0037] The large language model parses the regulatory text based on the prompt word. After parsing, the model writes the identified information (i.e., the parsing result) into a `regulationInfo` structure and matches it with the current time period to determine if it is the latest requirement for this month. The key fields of the `regulationInfo` structure include: Country or region: Indicate which country or region the regulation is in effect.

[0038] Industry type: such as "steel", indicating the industry scope covered by this regulation.

[0039] Maximum emission limit: For example, 10,000 tons, which means the maximum amount of emissions allowed in this cycle.

[0040] Penalty rate: For example, 50 yuan / ton, the amount exceeding the limit shall be subject to a penalty according to this standard.

[0041] Effective start and end dates: such as January 1, 2025 to December 31, 2025, used to determine whether the current month is within the regulatory control period.

[0042] Initial quota: such as 2,000 tons, represents the emission allowance allocated free of charge within this regulatory cycle.

[0043] This step enables the automatic extraction and structured modeling of carbon emission regulations, avoiding manual reading and input, and significantly improving policy response efficiency and system adaptability.

[0044] Optionally, in an embodiment, the step of calculating the predicted carbon emissions for each target time period based on the future production schedule data and the preset emission factors corresponding to each product includes: for each target time period, calculating the carbon emission contribution of each product within the target time period based on the planned output of each product within the target time period and the preset emission factors corresponding to each product; and summing the carbon emission contributions of each product within each target time period to obtain the predicted carbon emissions for each target time period.

[0045] Specifically, by using the API interface of the enterprise's ERP or MES system, existing future production scheduling data can be obtained, thereby acquiring information on the output and equipment usage time of each product at different time periods. The emission factors corresponding to each product can be pre-set based on national accounting guidelines, industry standards, or actual enterprise measurement data. The acquired future production scheduling data and the emission factors corresponding to each product are stored according to the scheduledProductionPlan data structure, as follows: Factory or production line identifier: For example, "SteelFactory_A" is used to distinguish different factories or production lines.

[0046] Time unit: can be set to hour, day, week or other appropriate granularity to indicate the time span of subsequent planned data.

[0047] Production scheduling information includes the start and end times of multiple time periods, corresponding product types (such as "hot_rolled_coil"), production output values, and production equipment numbers, so that subsequent emission calculations can accurately locate specific time periods and equipment.

[0048] Single-product emission factor: Records the unit emission amount corresponding to various products or processes. For example, a certain product is set to 1.8 tons of CO2 / ton of product, which is then used for multiplication calculation when calculating the total emission amount for subsequent periods.

[0049] For each target time period, the planned output of each product is multiplied by its corresponding emission factor to obtain the carbon emission contribution of each product within that target time period. For each target time period, the carbon emission contributions of each product are summed to obtain the predicted carbon emissions for that target time period. The calculation formula is as follows: ; in, This represents the predicted carbon emissions per unit time period t. It is the output of product p in a unit time period t. The emission factor is p, which is the unit product.

[0050] Emissions are calculated by combining the emission factor for each product and process, and then combined by time period to obtain the predicted emission list. Each entry in this list includes a time interval and the corresponding predicted carbon emissions, thus providing accurate time-period emission data for subsequent emission compliance or carbon quota strategies, as detailed below: Start time: For example, "January 1, 2025, 08:00:00"; End time: For example, "January 1, 2025, 09:00:00"; Total emissions: The total carbon emissions of all products during this period (e.g., 540 tons of CO2).

[0051] The scheduling and emission data are standardized and tested. If problems such as missing production, duplicate time periods, or unreasonable emission factors are found, an early warning will be issued automatically, and the administrator will be guided to manually intervene to correct the data.

[0052] In this embodiment, a Long Short-Term Memory (LSTM) neural network model is used for carbon price prediction. Specifically, historical price data is obtained from historical records or exchange interfaces, and real-time market quotes are captured. Simultaneously, basic data cleaning and time-series alignment are performed to ensure the accuracy of subsequent model training.

[0053] Trading Market Name: Used to identify the name of the carbon emissions trading market currently associated with the transaction.

[0054] Historical Price List: This list stores the transaction dates and corresponding carbon prices for each transaction. For example, the price on December 25, 2024 was 60 yuan / ton, and the price on December 26 was 62 yuan / ton.

[0055] Current real-time price: The real-time market carbon price at the current moment, such as 65 yuan / ton.

[0056] List of future projected prices: This indicates the time span (e.g., 30 days) that is intended to be projected in the subsequent forecasting process.

[0057] Historical carbon trading price data is used as training samples to train an LSTM model (parameters include the number of hidden layer nodes, learning rate, training batches, and training epochs) to make the prediction results as close as possible to the real prices. LSTM can better capture nonlinearity and long-term dependencies, making it suitable for the volatile and complex carbon trading market.

[0058] The current carbon trading price time series data is input into a trained LSTM model to predict short-term and medium-to-long-term carbon price trends, and outputs the carbon price prediction results for various time periods in the future (e.g., the next 30 days). ,in, This represents the predicted carbon trading price for the nth target time period in the future.

[0059] The prediction results are saved as a list called predictedPrices, where each record contains a target time period (such as a day or an hour) and the predicted price for that period. Businesses can set the prediction range according to their own strategies (such as the next week or month) and view price trends at each prediction point in time through a visualization interface. The data structure of predictedPrices is as follows: predictedPrices: Lists the predicted carbon trading prices for each corresponding period, for example, 64 yuan / ton on February 3, 2025, and 65 yuan / ton on February 10.

[0060] When the latest trading data deviates significantly from existing forecasts, or when a set time interval is reached, the platform automatically triggers a retraining or fine-tuning process. Through rolling updates, the platform can continuously adapt to market changes and improve the accuracy of carbon price forecasts.

[0061] Optionally, in an embodiment, the objective function of the optimization model includes a carbon trading cost item and an excess penalty item. The carbon trading cost item is determined based on the carbon trading price for each target time period, and the excess penalty item is determined based on the maximum emission limit and penalty rate in the carbon emission regulatory constraint information, the obtained historical carbon emissions, and the predicted carbon emissions for each target time period.

[0062] Specifically, let's set This represents the purchase volume corresponding to time period t. Let t be the sales volume corresponding to time period t. The objective function is set to minimize the comprehensive carbon cost calculation formula: ; Where t is the time period index; T is the total number of time periods; Let be the carbon trading price for time period t; This indicates historical carbon emissions (before t). This indicates the projected future carbon emissions (time period t and beyond); Represents the maximum emission limit; This refers to the penalty rate.

[0063] Cumulative carbon emissions data from the first day of that year to time t-1 Obtain it from the API interface of the energy and carbon management system.

[0064] Optionally, in the embodiments, the target carbon allowance trading volume for each target time period includes the purchase volume and the sales volume; the constraints of the optimization model include at least: the purchase volume and sales volume for each target time period obtained by the solution are both greater than or equal to zero; the sum of the initial allowance and the net purchase volume in the carbon emission regulatory constraint information is greater than or equal to the sum of the obtained historical carbon emissions and the carbon emission predictions for each target time period; wherein, the net purchase volume is determined by the purchase volume and sales volume for each target time period obtained by the solution.

[0065] The above constraints can be expressed as: Quantity limits for buying and selling: and ; Initial quota limits: .

[0066] The carbon allowance optimization problem is transformed into a linear programming model, aiming to minimize the total cost of carbon trading. Constraints include emission compliance, allowance limits, and non-negativity of trading. The existing optimization solver Gurobi is used to automatically complete the modeling and calculation, outputting the optimal allowance purchase and sale quantities for each time period, which are then used to generate the final carbon allowance trading strategy. An existing linear programming LP algorithm is then used to solve for the appropriate allowance purchase / sale quantities for each time period.

[0067] Finally, the amount of quota to buy / sell for each time period and the predicted total cost are generated and written into the buySellPlan data structure. The content includes: Trading Plan: List in detail the amount of carbon allowances to be bought or sold for each specific period (e.g., February 2025) (e.g., buy 20 tons, sell 0 tons), and the expected cost impact (e.g., RMB 1280), and explain the specific reasons for the transaction in the form of remarks (e.g., buy 20 tons of allowances when the price is RMB 64 / ton in February).

[0068] Estimated total cost: The estimated total cost after considering all trading operations across all time periods (e.g., 12,500 yuan).

[0069] Fine Amount: If there is an emission exceeding the standard, this value shows the amount of the fine that needs to be paid (e.g., 0 yuan means that the emission does not exceed the standard).

[0070] Final quota balance: The amount of carbon emission quotas remaining for a company after all buying and selling operations are completed (e.g., 2010 tons).

[0071] Optionally, in an embodiment, the step of conducting carbon trading based on the target carbon quota trading volume for each target time period includes: after entering each target time period, obtaining the actual carbon price in real time, and calculating the deviation between the carbon trading price of the target time period and the actual carbon price to obtain the carbon price deviation; when the carbon price deviation is less than a preset threshold, converting the target carbon quota trading volume of the target time period into a trading instruction, and executing a buy / sell operation based on the trading instruction; when the carbon price deviation is less than the preset threshold still does not meet the requirement of the preset threshold until the preset end threshold of the target time period, generating a manual decision prompt signal to prompt manual confirmation of whether to execute the transaction.

[0072] By using an LLM agent to parse the buySellPlan data structure and injecting prompt word templates in a unified format as request parameters into the LLM model, the model generates instruction text or parameter sets that conform to the trading platform's or internal execution standards based on the context. This eliminates the need for businesses to manually write trading commands; instead, they can use natural language prompts or preset templates to allow the agent to generate detailed instructions for placing and canceling orders.

[0073] When the next time period t begins, the actual carbon price is retrieved from the exchange's API. If the difference between the actual price and the predicted price is less than a preset threshold (e.g., 1%), the trading plan is considered valid, and the agent can automatically trigger buy / sell orders. If the requirement is not met by the last third of time period t, a manual decision is made regarding whether to execute the buy / sell order. This process continues until the end of the natural audit year.

[0074] If the API or automated trading agent of the carbon trading platform has been integrated, the agent will directly send instructions and track the execution results. If the enterprise requires manual review, it can view the details of the instructions converted by the agent in the platform UI and submit them manually after confirmation. Regardless of the method, the execution record will be written to the system log for subsequent traceability and optimization.

[0075] Optionally, in an embodiment, the method further includes: real-time monitoring of closed-loop feedback triggering events, wherein the closed-loop feedback triggering events include at least one of carbon emission regulation text update events, future production scheduling data change events, carbon trading market fluctuation events, and transaction non-execution events; when the closed-loop feedback triggering event is detected, the target carbon quota trading volume for each target time period is automatically triggered to update.

[0076] When significant changes in key parameters are detected, including but not limited to adjustments in production scheduling (such as a surge in orders or production stoppages), updates to regulations, sudden fluctuations in the carbon trading market, or failure to execute the original trading strategy due to a large deviation between the actual carbon price and the forecast, the system will trigger a re-aggregation of current production plans, emission forecasts, regulatory constraints, and carbon price forecasts. The core optimization engine will then be invoked to regenerate a new trading strategy. This new strategy will be encapsulated into executable trading instructions again using LLM, and its execution will be automatically determined based on the current carbon price matching degree, or manual confirmation will be pushed to the relevant personnel. This involves re-executing steps S101 to S104 to ensure the real-time nature of the strategy.

[0077] In summary, this method, by deeply integrating intelligent regulatory analysis, production plan-driven emission forecasting, and carbon price prediction, can accurately pinpoint and meet carbon emission regulatory requirements in the production process, significantly reducing the risk of penalties due to exceeding limits or violations. Simultaneously, by combining carbon price trends, it allows for the timely purchase or sale of allowances, effectively optimizing costs or generating additional revenue amidst price fluctuations. Since it only requires generating trading strategies using existing enterprise production scheduling data without altering existing production plans, its overall implementation and operation are simple. Furthermore, this method can be adjusted according to emission factors and applicable regulations in different industries, demonstrating good versatility and scalability across various scenarios.

[0078] Example 2 like Figure 2 As shown, this embodiment provides a carbon quota intelligent trading system 200 based on production planning, including: Data acquisition module 201 is used to acquire carbon emission regulatory constraints, future production schedule data and current carbon trading price time series data. The future production schedule data includes the planned output of each product in each target time period in the future. The carbon emission calculation module 202 is used to calculate the predicted carbon emissions for each target time period based on the future production schedule data and the preset emission factors corresponding to each product. The price prediction module 203 is used to predict the carbon trading price for each target time period based on the current carbon trading price time series data. The automatic trading module 204 is used to calculate the target carbon allowance trading volume for each target time period based on the carbon emission regulatory constraints, the predicted carbon emissions for each target time period, and the carbon trading price for each target time period, using an optimization model with the objective function of minimizing the overall carbon cost, so as to conduct carbon trading based on the target carbon allowance trading volume for each target time period.

[0079] Optionally, in an embodiment, the carbon emission regulatory constraint information is obtained by: acquiring the carbon emission regulatory text through robotic process automation (RPA); performing semantic parsing of the carbon emission regulatory text using a large language model based on preset prompts to generate parsing results; and converting the parsing results into a structured data format to obtain the carbon emission regulatory constraint information.

[0080] Optionally, in an embodiment, the carbon emission calculation module 202 includes: A single-product calculation unit is used to calculate the carbon emission contribution of each product in the target time period based on the planned output of each product in the target time period and the preset emission factors corresponding to each product. The carbon emission calculation unit is used to sum up the carbon emission contribution of each product in each target time period to obtain the predicted carbon emission for each target time period.

[0081] Optionally, in an embodiment, the objective function of the optimization model includes a carbon trading cost item and an excess penalty item. The carbon trading cost item is determined based on the carbon trading price for each target time period, and the excess penalty item is determined based on the maximum emission limit and penalty rate in the carbon emission regulatory constraint information, the obtained historical carbon emissions, and the predicted carbon emissions for each target time period.

[0082] Optionally, in the embodiments, the target carbon allowance trading volume for each target time period includes the purchase volume and the sales volume; the constraints of the optimization model include at least: the purchase volume and sales volume for each target time period obtained by the solution are both greater than or equal to zero; the sum of the initial allowance and the net purchase volume in the carbon emission regulatory constraint information is greater than or equal to the sum of the obtained historical carbon emissions and the carbon emission predictions for each target time period; wherein, the net purchase volume is determined by the purchase volume and sales volume for each target time period obtained by the solution.

[0083] Optionally, in an embodiment, the automated trading module 204 includes: The deviation calculation unit is used to obtain the actual carbon price in real time after entering each target time period, and calculate the deviation between the carbon trading price of the target time period and the actual carbon price to obtain the carbon price deviation. An automatic execution unit is used to convert the target carbon quota trading volume for the target time period into a trading instruction when the carbon price deviation is less than a preset threshold, so as to execute a buy or sell operation based on the trading instruction; The prompt generation unit is used to generate a manual decision prompt signal to prompt manual confirmation of whether to execute the transaction when the carbon price deviation is less than the preset threshold until the preset end threshold of the target time period is still not met.

[0084] Optionally, in an embodiment, the system further includes: The event monitoring module is used to monitor closed-loop feedback trigger events in real time. The closed-loop feedback trigger events include at least one of the following: carbon emission regulation text update events, future production scheduling data change events, carbon trading market fluctuation events, and transaction non-execution events. The event triggering module is used to automatically trigger the update of the target carbon quota trading volume for each target time period when the closed-loop feedback triggering event is detected.

[0085] In some embodiments, the carbon quota intelligent trading system 200 based on production planning of the present invention can be implemented in a combination of hardware and software. As an example, the carbon quota intelligent trading system 200 based on production planning of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the carbon quota intelligent trading method based on production planning of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0086] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0087] Example 3 like Figure 3 As shown, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent carbon quota trading method based on production planning as described in Embodiment 1.

[0088] In other words, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store computer programs; the processor is used to execute the carbon quota smart trading method based on production planning shown in any embodiment of the present invention by calling the computer programs.

[0089] In one alternative embodiment, an electronic device is provided. Figure 3The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may further include a transceiver 304, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present invention.

[0090] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0091] Bus 302 may include a path for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus 302 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0092] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0093] The memory 303 is used to store application code (computer program) for executing the present invention, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0094] Among them, electronic devices can also be terminal devices, which can be any device that can install applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0095] It should be noted that, Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0096] Example 4 This embodiment provides a non-transitory computer-readable storage medium that stores computer instructions for causing a computer to execute a carbon quota smart trading method based on production planning, as described in Embodiment 1.

[0097] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0098] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned carbon quota smart trading method based on production planning.

[0099] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0100] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0101] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EEPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0102] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0103] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0104] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0105] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0106] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A smart trading method for carbon quotas based on production planning, characterized in that, include: Acquire carbon emission regulatory constraints, future production schedule data, and current carbon trading price time series data, wherein the future production schedule data includes the planned output of each product within each target time period in the future; Based on the future production schedule data and the preset emission factors corresponding to each product, calculate the predicted carbon emissions for each target time period. Based on the current carbon trading price time series data, predict the carbon trading price for each target time period; Based on the carbon emission regulatory constraints, the predicted carbon emissions for each target time period, and the carbon trading price for each target time period, an optimization model with the objective function of minimizing the overall carbon cost is used to solve for the target carbon allowance trading volume for each target time period, so as to conduct carbon trading based on the target carbon allowance trading volume for each target time period.

2. The carbon quota intelligent trading method based on production planning according to claim 1, characterized in that, The carbon emission regulatory constraints information is obtained through the following methods: Obtain carbon emission regulations texts through robotic process automation (RPA) technology; Based on preset prompts, the carbon emission regulations text is semantically parsed using a large language model to generate parsing results; The parsing results are converted into a structured data format to obtain the carbon emission regulatory constraints information.

3. The intelligent carbon quota trading method based on production planning according to claim 1, characterized in that, The step of calculating the predicted carbon emissions for each target time period based on the future production schedule data and the preset emission factors corresponding to each product includes: For each target time period, the carbon emission contribution of each product in the target time period is calculated based on the planned output of each product in the target time period and the preset emission factors corresponding to each product. The carbon emission contribution of each product within each target time period is summed to obtain the predicted carbon emission for each target time period.

4. The intelligent carbon quota trading method based on production planning according to claim 1, characterized in that, The objective function of the optimization model includes a carbon trading cost item and an excess penalty item. The carbon trading cost item is determined based on the carbon trading price for each target time period, and the excess penalty item is determined based on the maximum emission limit and penalty rate in the carbon emission regulatory constraint information, the obtained historical carbon emission volume, and the carbon emission prediction for each target time period.

5. The intelligent carbon quota trading method based on production planning according to claim 4, characterized in that, The target carbon allowance trading volume for each target time period includes both purchase and sale volumes; the constraints of the optimization model include at least: The calculated buy and sell volumes for each target time period are all greater than or equal to zero. The sum of the initial allowance and net purchase amount in the carbon emission regulatory constraint information is greater than or equal to the sum of the obtained historical carbon emissions and the predicted carbon emissions for each target time period; wherein, the net purchase amount is determined by the purchase and sales amounts for each target time period obtained by solving.

6. The intelligent carbon quota trading method based on production planning according to claim 1, characterized in that, The carbon trading based on the target carbon allowance trading volume for each target time period includes: After entering each target time period, the actual carbon price is obtained in real time, and the deviation between the carbon trading price of the target time period and the actual carbon price is calculated to obtain the carbon price deviation. When the carbon price deviation is less than a preset threshold, the target carbon quota trading volume for the target time period is converted into a trading instruction, and a buy / sell operation is executed based on the trading instruction. If the carbon price deviation is less than the preset threshold by the end of the target time period, a manual decision prompt signal is generated to prompt manual confirmation on whether to execute the transaction.

7. The intelligent carbon quota trading method based on production planning according to claim 1, characterized in that, Also includes: Real-time monitoring of closed-loop feedback trigger events, including at least one of the following: carbon emission regulation text update events, future production scheduling data change events, carbon trading market fluctuation events, and unexecuted trading events; When the closed-loop feedback trigger event is detected, the target carbon quota trading volume for each target time period is automatically updated.

8. A carbon quota intelligent trading system based on production planning, characterized in that, include: The data acquisition module is used to acquire carbon emission regulatory constraints, future production schedule data, and current carbon trading price time series data. The future production schedule data includes the planned output of each product in each target time period in the future. The carbon emission calculation module is used to calculate the predicted carbon emissions for each target time period based on the future production schedule data and the preset emission factors corresponding to each product. The price prediction module is used to predict the carbon trading price for each target time period based on the current carbon trading price time series data. The automatic trading module is used to calculate the target carbon allowance trading volume for each target time period based on the carbon emission regulatory constraints, the predicted carbon emissions for each target time period, and the carbon trading price for each target time period, using an optimization model with the objective function of minimizing the overall carbon cost, so as to conduct carbon trading based on the target carbon allowance trading volume for each target time period.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the carbon quota smart trading method based on production planning as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the intelligent carbon quota trading method based on production planning as described in any one of claims 1 to 7.

Images