Personalized carbon emission optimization scheme generation and effect simulation method and system and medium

Abstract

The invention provides a personalized carbon emission optimization scheme generation and effect simulation method and system and a medium, and belongs to the technical field of carbon emission management.The method comprises the steps that basic information data, real-time operation data and external associated data related to carbon emission of a user are collected; big data analysis including preprocessing, carbon emission feature analysis and optimization potential evaluation is carried out; constructing and dynamically updating an expert knowledge base covering the target industry; generating a plurality of sets of carbon emission candidate optimization schemes through a multi-objective optimization algorithm based on a big data analysis result and the constructed expert knowledge base, and performing quantitative simulation of emission reduction potential simulation, economic benefit simulation and sensitivity analysis; and according to a quantitative simulation result, performing visual display, multi-dimensional comparison and parameter adjustment interaction on each carbon emission optimization scheme. The personalized carbon emission optimization scheme is automatically generated based on the big data and the knowledge base, the effect is simulated in advance, and the decision risk is reduced.

Description

Technical Field

[0001] This application belongs to the field of carbon emission management technology, specifically involving a method, system, and medium for generating and simulating the effects of personalized carbon emission optimization schemes. Background Technology

[0002] With the increasing stringent carbon emission control requirements across various industries, all types of carbon emitters (such as industrial enterprises, industrial parks, and cities) are facing enormous carbon emission pressure and urgently need reasonable carbon emission optimization solutions to guide their low-carbon transformation. Currently, carbon emission optimization solutions mainly rely on two models. One is based on manual surveys and expert judgment. This involves customized solutions developed through on-site inspections and data collection by expert teams, combined with the experience of individuals or teams. The other is the use of general, standardized solution templates.

[0003] Existing carbon emission optimization schemes suffer from the following problems: First, insufficient personalization. Most existing schemes are generic templates, failing to consider the specific characteristics of the entity, such as industry attributes, production processes, existing equipment levels, and energy structure. This results in poor implementation and emissions reduction effects falling short of expectations. Second, low matching between technology and strategy. Recommendations for emissions reduction technologies and management strategies lack systematic support, relying solely on the experience of a few experts. This easily overlooks highly adaptable technologies or strategies and struggles to cover the diverse and multi-dimensional carbon emission optimization needs. Third, delayed and one-sided effect evaluation. The effectiveness of the schemes can only be verified after actual implementation. It's impossible to simulate the emissions reduction potential and economic benefits of different schemes in advance, leading to high decision-making risks and potentially wasting resources or missing the optimal emissions reduction opportunity. Finally, low data utilization. Various entities generate a large amount of carbon emission-related data during production and operation (such as energy consumption data, production process data, and emissions monitoring data). Existing technologies do not fully utilize this data for in-depth analysis, making it difficult to uncover the carbon emission optimization potential hidden within the data.

[0004] Therefore, there is an urgent need for a technical solution that can integrate big data analysis and expert knowledge to achieve automatic generation of personalized solutions and advance simulation of effects. Summary of the Invention

[0005] In a first aspect, embodiments of this application provide a method for generating and simulating the effects of a personalized carbon emission optimization scheme, comprising the following steps: S1. Collect basic information, real-time operational data, and external related data related to the carbon emissions of target users; S2. Perform big data analysis on the collected data, including preprocessing, carbon emission characteristic analysis, and optimization potential assessment; S3. Construct and dynamically update an expert knowledge base covering the target industry, the expert knowledge base including an emission reduction solution library and a management strategy library; S4. Based on the big data analysis results and the constructed expert knowledge base, several sets of carbon emission candidate optimization schemes are generated through multi-objective optimization algorithms; S5. Perform quantitative simulation on the generated carbon emission candidate optimization schemes, including emission reduction potential simulation, economic benefit simulation and sensitivity analysis; S6. Based on the quantitative simulation results, visualize, compare, and interact with the parameters of each carbon emission optimization scheme.

[0006] Furthermore, in step S1, user carbon emission-related data is collected through API interface connection, IoT device access, and manual upload supplementation. The collected real-time operational data includes energy consumption data, production process data, and carbon emission monitoring data with minute-level or hour-level accuracy; Basic information data includes the user's industry, production scale, geographical region, and equipment list; External data includes regional carbon emission quota data, industry benchmark carbon emission data, energy price data, and market data on emission reduction schemes.

[0007] Furthermore, the specific steps of step S2 are as follows: S21. Perform data preprocessing, cleaning the collected data through outlier detection, missing value imputation, and data standardization; S22. Perform carbon emission characteristic analysis, calculate the target user's current total carbon emissions and carbon emission intensity, identify key carbon emission links, and analyze carbon emission change trends; Specifically, total carbon emissions are calculated by summing the products of activity level data and corresponding emission factors, using the following formula:

[0008] in, Total carbon emissions; For the i-th type of activity level data, the activity level data includes fossil fuel consumption and purchased electricity; The carbon emission factor corresponding to the i-th type of activity; Carbon emission intensity is calculated as the ratio of total carbon emissions to output value, using the following formula:

[0009] in, For carbon emission intensity, The total output value within the preset period; The identification of key carbon emission links is achieved by calculating the carbon emission ratio of each link, and links with a ratio exceeding a preset threshold are identified as key links. S23. Conduct an optimization potential assessment, based on industry benchmark data and user historical data, to determine the user's potential emission reduction space in the dimensions of energy structure optimization, process improvement, equipment upgrade, and management optimization.

[0010] Furthermore, the specific steps of step S3 are as follows: S31. Build an emission reduction solution library, storing solution names, solution principles, applicable industries and scenarios, key solution parameters, typical investment costs, expected emission reduction rates, and links to successful implementation cases in the form of structured data tables submitted by front-end users or imported in batches. The emission reduction scheme library is constructed at the database level using a knowledge graph, with entities such as schemes, equipment, materials, and industries as nodes and relationships between entities as edges, to enable subsequent semantic-based intelligent matching and retrieval. S32. Construct a management strategy library to store information in the form of strategy entries, label each strategy entry with a strategy type, and define key attributes for each strategy; The strategy types include energy management strategies, production scheduling optimization strategies, and carbon asset management and trading strategies, and are marked with applicable conditions, implementation difficulty, and expected results; The key attributes include the applicable enterprise size, the required preconditions, the estimated implementation period, the expected economic and environmental benefits quantified by the level of implementation difficulty; S33. Dynamically update the emission reduction scheme library and management strategy library, which serve as a knowledge base, through expert manual updates and automatic data crawling.

[0011] Furthermore, the specific steps of step S4 are as follows: S41. Based on the list of key carbon emission links, the results of optimization potential assessment, and the user-preset optimization goals and constraints, construct multi-dimensional matching query conditions and perform retrieval and matching in the expert knowledge base; The matching process employs a weight-based similarity calculation algorithm:

[0012] in, , , These are preset weighting coefficients; The algorithm uses similarity calculation to initially screen suitable emission reduction schemes and management strategies from the expert knowledge base, generating an initial set of strategies. S42. Using a multi-objective optimization algorithm, with the objective functions of maximizing emission reduction potential, maximizing economic benefits, and minimizing implementation difficulty, the algorithm combines and optimizes the schemes and strategies in the initial strategy set to generate N sets of candidate optimization schemes. The multi-objective optimization algorithm employs a fast non-dominated sorting genetic algorithm with an elitist retention strategy, and its execution steps include: S421. Perform encoding and population initialization, combining different schemes and management strategies into chromosomes, and randomly generating the initial population; S422. Perform fast non-dominated sorting, sorting the individuals in the population into Pareto ranks based on the three objective function values; S423. Perform crowding calculations to determine the crowding of individuals within the same non-dominated layer in order to maintain population diversity; S424. Perform selection, crossover, and mutation, conduct tournament selection based on non-dominance level and crowding, and perform simulated binary crossover and polynomial mutation to produce offspring populations. S425. Implement elite retention, merge the parent and offspring populations, and select a new generation of population based on non-dominance level and crowding. S426. Perform iteration and output, repeat steps S422 to S425 until the maximum number of iterations is reached, and output the final non-dominated solution set as N candidate optimization schemes; Each set of candidate optimization solutions includes: The list includes a core recommended technologies and strategies, a Gantt chart outlining the phased implementation steps, and a detailed list of quantified resource requirements. The resource requirements include the total investment amount, estimated human resource input, and time periods for each stage.

[0013] Furthermore, the specific steps of step S5 are as follows: S51. Based on the user's current carbon emission data, the emission reduction rate parameters of the candidate optimization schemes and the expected effects of the management strategy, and combined with the time series prediction model, simulate the carbon emission change curve within N years after the implementation of the scheme, calculate the cumulative emission reduction, the average annual emission reduction rate and the decrease in carbon emission intensity, and complete the emission reduction potential simulation. S52. Integrate the investment cost, operating cost, and revenue data of candidate optimization schemes, calculate the investment payback period, net present value (NPV), and internal rate of return (IRR), and consider the uncertainties of energy price fluctuations and changes in carbon market rules to generate economic benefit range predictions and complete economic benefit simulations. S53. Identify the key factors affecting the effectiveness of the scheme, simulate the changes in the scheme's emission reduction potential and economic benefits when the key factors change, and complete the sensitivity analysis.

[0014] Furthermore, the time series prediction model in step S51 adopts the ARIMA model; The expression for the ARIMA model is:

[0015] in, It is an autoregressive polynomial. It is a moving average polynomial. For lag operators, d For the degree of difference, For time series data, It is a white noise sequence; The formula for calculating Net Present Value (NPV) in step S52 is as follows:

[0016] in, Let t be the net cash flow in year t. For the discount rate, For the lifespan of the solution, This refers to the initial investment cost; In step S52, the internal rate of return It is to make the net present value A discount rate of zero is obtained by iteratively solving the following equation:

[0017] in, Let t be the net cash flow in year t. For the lifespan of the solution, This represents the initial investment cost.

[0018] Furthermore, step S6 is detailed as follows: S61. Visualize the implementation plan, and display the core measures, implementation steps, emission reduction potential and economic benefits of each candidate optimization plan in the form of charts; S62. Implementation plan comparison and analysis: Responding to the user's selection of any two or more plans, a visual comparison is conducted from three dimensions: emission reduction effect, economic benefits, and implementation difficulty, and a comparison report is generated. S63. Allows users to adjust scheme parameters, update the simulation effect of the scheme in real time, and export the scheme.

[0019] Secondly, embodiments of this application also provide a personalized carbon emission optimization scheme generation and effect simulation system, including: The data acquisition module is used to collect basic information data, real-time operational data and external related data related to the carbon emissions of target users; The big data analytics module is used to perform big data analysis on the collected data, including preprocessing, carbon emission characteristic analysis, and optimization potential assessment. The expert knowledge base module is used to build and dynamically update an expert knowledge base covering the target industry. The expert knowledge base includes an emission reduction solution library and a management strategy library. The scheme generation module is used to generate several carbon emission candidate optimization schemes based on big data analysis results and the constructed expert knowledge base through multi-objective optimization algorithms; The effect simulation module is used to perform quantitative simulation of the generated carbon emission candidate optimization schemes. The quantitative simulation includes emission reduction potential simulation, economic benefit simulation and sensitivity analysis. The visualization and interaction module is used to visualize, compare, and adjust parameters of various carbon emission optimization schemes based on the quantitative simulation results.

[0020] Thirdly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the personalized carbon emission optimization scheme generation and effect simulation method described in the first aspect.

[0021] As can be seen from the above technical solutions, this application has the following advantages: The personalized carbon emission optimization scheme generation and effect simulation method, system, and medium provided in this application automatically collect and analyze actual user data, combine it with an updatable industry knowledge base, generate multiple optimization schemes for different users' specific situations, and simulate the emission reduction effects and economic benefits after the implementation of these schemes in advance. This allows users to compare different schemes before implementation and choose the one that is more suitable for their own conditions, avoiding the risks of blind decision-making. Through parameter adjustment and real-time updating of simulation results, users can make flexible decisions based on actual needs, improve the data support for carbon emission management decisions, and reduce the workload of manual analysis. Attached Figure Description

[0022] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating the method for generating and simulating the effects of personalized carbon emission optimization schemes according to the present invention.

[0024] Figure 2 This is a schematic diagram of the personalized carbon emission optimization scheme generation and effect simulation system of the present invention. Detailed Implementation

[0025] The various embodiments of this disclosure will be described more fully in the detailed steps below for generating personalized carbon emission optimization schemes and simulating their effects. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0026] This embodiment provides a method for generating and simulating the effects of personalized carbon emission optimization schemes. Based on big data and a knowledge base, it automatically generates personalized carbon emission optimization schemes, simulates the effects in advance, and reduces decision-making risks.

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Please see Figure 1 The diagram shows a flowchart of a method for generating and simulating the effects of a personalized carbon emission optimization scheme in a specific embodiment. The method includes the following steps: S1. Collect basic information, real-time operational data, and external related data related to the carbon emissions of target users; It should be noted that this step can automatically obtain users' basic information, real-time operational data, and data on external market rules, prices, and carbon emissions, reducing the workload of manual data collection, ensuring the timeliness and completeness of the data, and providing comprehensive input for subsequent analysis; S2. Perform big data analysis on the collected data, including preprocessing, carbon emission characteristic analysis, and optimization potential assessment; It should be noted that preprocessing the raw data can improve data quality; carbon emission characteristic analysis can help users clearly understand their current carbon emission status and problems; and performing optimization potential assessment can objectively determine which aspects have greater room for improvement, thus pointing the way for solution generation. S3. Construct and dynamically update an expert knowledge base covering the target industry, the expert knowledge base including an emission reduction solution library and a management strategy library; It should be noted that the process involves organizing and storing emission reduction plans and management strategies to generate reusable knowledge resources. S4. Based on the big data analysis results and the constructed expert knowledge base, several sets of carbon emission candidate optimization schemes are generated through multi-objective optimization algorithms; It should be noted that, based on the user's actual situation and knowledge base resources, multiple solutions are automatically combined through algorithms; compared with manual design, it can more systematically consider the combination of various technologies, generate solutions with a wider coverage, and achieve a reasonable balance between emission reduction effect and cost through multi-objective optimization. S5. Perform quantitative simulation on the generated carbon emission candidate optimization schemes, including emission reduction potential simulation, economic benefit simulation and sensitivity analysis; It should be noted that the emission reduction potential simulation can simulate the changes in carbon emissions and economic benefits of the plan over 1-5 years. Users can see key indicators such as cumulative emission reductions and investment payback period. Sensitivity analysis can reveal which factors have a greater impact on the plan, helping users to predict risks and avoid the results falling short of expectations after implementation. S6. Based on the quantitative simulation results, visualize, compare, and interactively adjust the parameters of each carbon emission optimization scheme. It should be noted that complex plans and economic analysis results are presented intuitively using charts and graphs, lowering the barrier to understanding; the multi-plan comparison function makes it easier for users to weigh the pros and cons; parameter adjustment and real-time refresh allow users to flexibly optimize according to budget, time and other constraints, so as to quickly determine the final implementation plan.

[0029] This embodiment integrates big data analysis and expert knowledge base, automatically generates multiple personalized carbon emission optimization schemes through multi-objective optimization algorithms, quantifies and simulates their emission reduction potential, economic benefits and risks, provides a visual interactive interface, reduces decision-making risks and improves optimization efficiency.

[0030] Furthermore, as a refinement and extension of the specific implementation methods of the above embodiments, in order to fully illustrate the specific implementation process in this embodiment, another method for generating and simulating the effects of personalized carbon emission optimization schemes is provided. Taking a medium-sized chemical enterprise (annual production capacity of 50,000 tons of chemical products, located in East China) as the target user, the method includes the following steps: S1. Collect basic information, real-time operational data, and external related data related to the carbon emissions of target users; In step S1, user carbon emission-related data is collected through API interface connection, IoT device access, and manual upload supplementation. The collected real-time operational data includes energy consumption data, production process data, and carbon emission monitoring data with minute-level or hour-level accuracy; Basic information data includes the user's industry, production scale, geographical region, and equipment list; External related data includes regional carbon emission quota data, industry benchmark carbon emission data, energy price data, and market data on emission reduction schemes; For example, data is collected using a combination of API integration, IoT access, and manual supplementation, as detailed below: Basic information data: obtained through API integration with the enterprise ERP system, including industry (e.g., chemical-organic synthesis), production scale (e.g., annual capacity of 50,000 tons), geographical region (e.g., an industrial park in a certain region), and equipment list (e.g., 3 coal-fired boilers, 2 sets of reaction vessels, 1 set of refrigeration units, etc., totaling 15 core equipment). Real-time operational data: Access is achieved through IoT devices (such as smart meters, gas meters, and carbon emission monitors) to obtain minute-level energy consumption data (e.g., daily coal consumption of approximately 30 tons and daily electricity consumption of approximately 8000 kWh), hourly production process data (e.g., reactor temperature of 80-120℃ and pressure of 0.3-0.5 MPa), and hourly carbon emission monitoring data (e.g., real-time carbon emission concentration of 200-300 mg / m³). 3 ); External data sources: Carbon emission quota data (annual quota of 8,000 tons of CO2) is obtained through the regional environmental protection platform API; industry benchmark carbon emission data (benchmark carbon emission per unit product of chemical industry is 1.2 tons of CO2 / ton of product) is crawled from the industry database; energy price data (coal 900 yuan / ton, industrial electricity 0.65 yuan / kWh) is obtained through the energy supplier interface; and market data on emission reduction schemes is crawled from the market platform (solar photovoltaic module unit price 3.2 yuan / W, energy-saving motor unit price 15,000 yuan / unit). S2. Perform big data analysis on the collected data, including preprocessing, carbon emission characteristic analysis, and optimization potential assessment; The specific steps of step S2 are as follows: S21. Perform data preprocessing, cleaning the collected data through outlier detection, missing value imputation, and data standardization; The outlier detection method uses box plots or the 3σ criterion to identify and remove values ​​that exceed a preset reasonable range. The missing value imputation adopts a data imputation method based on the K nearest neighbor algorithm, which fills the missing values ​​according to the similarity between the data. The data standardization adopts the Z-score standardization method to convert data of different dimensions and magnitudes into dimensionless standardized values; For example, outlier detection: using the 3σ criterion, an abnormal data point of 50 tons of daily coal consumption (exceeding the normal range of 30±5 tons) recorded once by a certain boiler due to a sensor malfunction was removed; Missing value imputation: The K-nearest neighbor algorithm is used to impute 3 missing hourly temperature data of the reactor (for example, based on the average temperature under similar operating conditions over 24 hours before and after, the data is imputed to be 95℃, 102℃, and 110℃). Data standardization: Z-score standardization is adopted to convert data with different dimensions, such as coal consumption (tons) and electricity consumption (kWh), into dimensionless values ​​to facilitate subsequent analysis; S22. Perform carbon emission characteristic analysis, calculate the target user's current total carbon emissions and carbon emission intensity, identify key carbon emission links, and analyze carbon emission change trends; Specifically, total carbon emissions are calculated by summing the products of activity level data and corresponding emission factors, using the following formula:

[0031] in, Total carbon emissions; For the i-th type of activity level data, the activity level data includes fossil fuel consumption and purchased electricity; The carbon emission factor corresponding to the i-th type of activity; Carbon emission intensity is calculated as the ratio of total carbon emissions to output value, using the following formula:

[0032] in, For carbon emission intensity, The total output value within the preset period; The identification of key carbon emission links is achieved by calculating the carbon emission ratio of each link, and links with a ratio exceeding a preset threshold are identified as key links. For example, the total carbon emissions are calculated as follows: the activity level data includes an annual coal consumption of 10,950 tons (30 tons / day × 365 days) and an annual external electricity purchase of 2.92 million kWh (8,000 kWh / day × 365 days), corresponding to emission factors of 2.6 tons of CO2 / ton of coal and 0.6 tons of CO2 / kWh, respectively. According to the formula, the total carbon emissions are calculated as follows: 10,950 × 2.6 + 2,920,000 × 0.0006 = 28,470 + 1,752 = 30,222 tons of CO2 / year. Carbon emission intensity calculation: The company's annual total output value is 150 million yuan. According to the formula, the carbon emission intensity is calculated as 30,222 tons of CO2 / 150 million yuan = 2.015 tons of CO2 per 10,000 yuan. Key link identification: Calculate the carbon emission proportion of each link. The coal-fired boiler emits 28,470 tons of CO2, accounting for 94% (exceeding the preset threshold of 70%), and is identified as a key link in carbon emission; the auxiliary power consumption of the reactor accounts for 4% of the emissions, and the refrigeration unit accounts for 2%, both of which are non-critical links. Trend analysis: Based on data from the past three years, total carbon emissions have decreased from 32,100 tons to 30,222 tons, with an average annual decrease of 6.16%, but are still higher than the industry benchmark level; S23. Conduct an optimization potential assessment, based on industry benchmark data and user historical data, to determine the user's potential emission reduction space in the dimensions of energy structure optimization, process improvement, equipment upgrade, and management optimization; The potential for emission reduction is determined in the following ways: Calculate the difference between the proportion of high-carbon energy in the current energy structure and the industry benchmark, and evaluate it in conjunction with the emission reduction rate of energy substitution schemes to achieve energy structure optimization; Identify the gap between the current energy efficiency level of the equipment and the advanced energy efficiency level in the industry, calculate the potential emission reduction based on the gap and the equipment operating load, and assess the potential emission reduction of equipment upgrades; For example, energy structure optimization: Currently, coal accounts for 85% of energy consumption, while the advanced level in the industry is 60%. By replacing coal with natural gas or renewable energy, it is expected that emissions can be reduced by 15%-20%. Equipment upgrade: The existing coal-fired boiler has an energy efficiency of 82%, while the industry-leading energy efficiency is 92%. Replacing it with a high-efficiency boiler or installing energy-saving devices is expected to reduce emissions by 8%-12%. Process improvement: The insulation layer of the reactor was aging, with a heat loss rate of 15%. After adopting new insulation materials, the heat loss rate can be reduced to 5%, which is expected to indirectly reduce emissions by 3%-5%. Management optimization: Currently, there is a lack of peak-valley electricity dispatching strategies. The peak-valley price difference for industrial electricity is 0.3 yuan / kWh. By optimizing production scheduling, it is expected that electricity costs can be reduced by 10%, indirectly reducing emissions by 2%-3%. S3. Construct and dynamically update an expert knowledge base covering the target industry, the expert knowledge base including an emission reduction solution library and a management strategy library; The specific steps of step S3 are as follows: S31. Build an emission reduction solution library, storing solution names, solution principles, applicable industries and scenarios, key solution parameters, typical investment costs, expected emission reduction rates, and links to successful implementation cases in the form of structured data tables submitted by front-end users or imported in batches. The emission reduction scheme library is constructed at the database level using a knowledge graph, with entities such as schemes, equipment, materials, and industries as nodes and relationships between entities as edges, to enable subsequent semantic-based intelligent matching and retrieval. For example, solutions adapted to the chemical industry are stored in the form of structured data tables, as shown in Table 1 below: Table 1

[0033] The database is constructed using a knowledge graph, with nodes including natural gas boiler retrofit solutions, photovoltaic power station solutions, chemical industry, and reactor equipment, and edges representing relationships such as applicable industries and compatible equipment. S32. Construct a management strategy library to store information in the form of strategy entries, label each strategy entry with a strategy type, and define key attributes for each strategy; The strategy types include energy management strategies, production scheduling optimization strategies, and carbon asset management and trading strategies, and are marked with applicable conditions, implementation difficulty, and expected results; The key attributes include the applicable enterprise size, the required preconditions, the estimated implementation period, the expected economic and environmental benefits quantified by the level of implementation difficulty; For example, they are stored as policy entries, as shown in the following example: Strategy type: Energy management strategy; Strategy content: Optimize peak-valley electricity scheduling, and run high-power-consuming equipment during off-peak hours (e.g., 23:00-7:00); Key attributes: Applicable scale (e.g., chemical enterprises), prerequisites (e.g., 24-hour continuous production capacity), implementation period (e.g., 1 month), implementation difficulty (e.g., low), expected economic benefits (e.g., annual electricity cost savings of 288,000 yuan), and expected emission reduction rate (e.g., 2%). S33. Dynamically update the emission reduction scheme library and management strategy library, which serve as a knowledge base, through expert manual updates and automatic data crawling; Among them, manual updates by experts are performed through an online editing interface with permission management functions, responding to certified experts' operations of adding, deleting, modifying, and querying entries in the knowledge base; Automatic crawling is achieved by configuring a targeted web crawler. The web crawler regularly crawls the latest emission reduction scheme dynamics, regulatory texts and market data from preset industry standard websites, technical journal websites and industry standard databases, and extracts and structures key information through natural language processing. After review, the information is automatically or semi-automatically entered into the corresponding knowledge base. For example, manual updates: invite 3 emission reduction experts from the chemical industry to review new solutions, such as carbon capture device adaptation solutions, every quarter and add them to the emission reduction solution library; Automatic crawling: Regularly crawl the latest emission reduction plan updates, regulatory texts and market data from xx journal websites and xx industry standard official websites through web crawlers, and update the applicable conditions fields in the management strategy library; S4. Based on the big data analysis results and the constructed expert knowledge base, several sets of carbon emission candidate optimization schemes are generated through multi-objective optimization algorithms; The specific steps of step S4 are as follows: S41. Based on the list of key carbon emission links, the results of optimization potential assessment, and the user-preset optimization goals and constraints, construct multi-dimensional matching query conditions and perform retrieval and matching in the expert knowledge base; The matching process employs a weight-based similarity calculation algorithm:

[0034] in, , , These are preset weighting coefficients; The algorithm uses similarity calculation to initially screen suitable emission reduction schemes and management strategies from the expert knowledge base, generating an initial set of strategies. For example, based on key components (coal-fired boilers), optimization potential assessment results (energy structure optimization and equipment upgrades have the highest priority), and user-preset targets (emission reduction rate ≥ 15%, investment payback period ≤ 5 years), matching conditions are constructed, and a weighted similarity algorithm is used. =0.5 - Industry adaptability =0.3 - emission reduction potential =0.2 - investment cost), select 3 core solutions and 2 management strategies from the knowledge base to generate an initial strategy set: natural gas boiler renovation, photovoltaic power station construction, reactor insulation material replacement, peak-valley electricity dispatch, and carbon asset ledger management; S42. Using a multi-objective optimization algorithm, with the objective functions of maximizing emission reduction potential, maximizing economic benefits, and minimizing implementation difficulty, the algorithm combines and optimizes the schemes and strategies in the initial strategy set to generate N sets of candidate optimization schemes. The multi-objective optimization algorithm employs a fast non-dominated sorting genetic algorithm with an elitist retention strategy, and its execution steps include: S421. Perform encoding and population initialization, combining different schemes and management strategies into chromosomes, and randomly generating the initial population; S422. Perform fast non-dominated sorting, sorting the individuals in the population into Pareto ranks based on the three objective function values; S423. Perform crowding calculations to determine the crowding of individuals within the same non-dominated layer in order to maintain population diversity; S424. Perform selection, crossover, and mutation, conduct tournament selection based on non-dominance level and crowding, and perform simulated binary crossover and polynomial mutation to produce offspring populations. S425. Implement elite retention, merge the parent and offspring populations, and select a new generation of population based on non-dominance level and crowding. S426. Perform iteration and output, repeat steps S422 to S425 until the maximum number of iterations is reached, and output the final non-dominated solution set as N candidate optimization schemes; Each set of candidate optimization solutions includes: The list includes a core recommended technologies and strategies, a Gantt chart outlining the phased implementation steps, and a detailed list of quantified resource requirements. The resource requirements include the total investment amount, estimated human resource input, and time period for each stage; For example, a fast non-dominated sorting genetic algorithm with an elite retention strategy is used to generate three candidate schemes with the objectives of maximizing emission reduction potential, maximizing economic benefits, and minimizing implementation difficulty: Option 1 (Prioritizing High Emission Reduction): Natural Gas Boiler Retrofitting + Photovoltaic Power Plant Construction + Peak-Valley Electricity Dispatch Core technologies and strategies: Replace 3 natural gas boilers, construct a 500kW photovoltaic power station, and implement peak-valley electricity dispatch. Implementation steps (Gantt chart): Photovoltaic power plant construction completed in months 1-3; boiler replacement in months 4-6; dispatch strategy activated in month 7. Resource requirements: Total investment of 4 million yuan, manpower of 15 people (including construction and technical debugging), and a total cycle of 7 months. Option 2 (i.e., prioritizing economic efficiency): Replacement of reactor insulation materials + peak-valley electricity dispatch + carbon asset ledger management Core technologies and strategies: Replace the insulation materials of two sets of reactors, implement peak-valley electricity dispatch, and establish a carbon asset ledger. Implementation steps (Gantt chart): Insulation material replacement completed in months 1-2; ledger established and scheduling initiated in month 3. Resource requirements: Total investment of 240,000 yuan, manpower of 5 people, and a total cycle of 3 months. Option 3 (i.e., balanced type): Natural gas boiler modification + replacement of reactor insulation material + peak-valley electricity dispatching Core technologies and strategies: Replace one natural gas boiler, retain two high-efficiency coal-fired boilers, replace insulation materials, and implement scheduling. Implementation steps (Gantt chart): Replace insulation material in months 1-2; replace one boiler in months 3-5; start scheduling in month 6. Resource requirements: Total investment of RMB 1.56 million, human resources of 10 people, and a total cycle of 6 months; S5. Perform quantitative simulation on the generated carbon emission candidate optimization schemes, including emission reduction potential simulation, economic benefit simulation and sensitivity analysis; The specific steps of step S5 are as follows: S51. Based on the user's current carbon emission data, the emission reduction rate parameters of the candidate optimization schemes and the expected effects of the management strategy, and combined with the time series prediction model, simulate the carbon emission change curve within N (e.g., 1-5) years after the implementation of the scheme, calculate the cumulative emission reduction, the average annual emission reduction rate and the decrease in carbon emission intensity, and complete the emission reduction potential simulation. In step S51, the time series forecasting model uses the ARIMA model; The expression for the ARIMA model is:

[0035] in, It is an autoregressive polynomial. It is a moving average polynomial. For lag operators, d For the degree of difference, For time series data, It is a white noise sequence; For example, the ARIMA model is used to simulate the changes in carbon emissions over five years after the implementation of three scenarios: Option 1: Cumulative emission reduction = 30222 × (28% + 6% + 2%) × 5 = 30222 × 36% × 5 = 54400 tons of CO2, with an average annual emission reduction rate of 36%, and the carbon emission intensity is reduced to 1.29 tons of CO2 / 10,000 yuan; Option 2: Cumulative emission reduction = 30222 × (4% + 2% + 1%) × 5 = 30222 × 7% × 5 = 10578 tons of CO2, with an average annual emission reduction rate of 7%, and the carbon emission intensity reduced to 1.87 tons of CO2 / 10,000 yuan; Option 3: Cumulative emission reduction = 30222 × (10% + 4% + 2%) × 5 = 30222 × 16% × 5 = 24178 tons of CO2, with an average annual emission reduction rate of 16%, and the carbon emission intensity is reduced to 1.70 tons of CO2 / 10,000 yuan; S52. Integrate the investment cost, operating cost, and revenue data of candidate optimization schemes, calculate the investment payback period, net present value (NPV), and internal rate of return (IRR), and consider the uncertainties of energy price fluctuations and changes in carbon market rules to generate economic benefit range predictions and complete economic benefit simulations. The formula for calculating Net Present Value (NPV) in step S52 is as follows:

[0036] in, Let t be the net cash flow in year t. For the discount rate, For the lifespan of the solution, This refers to the initial investment cost; In step S52, the internal rate of return It is to make the net present value A discount rate of zero is obtained by iteratively solving the following equation:

[0037] in, Let t be the net cash flow in year t. For the lifespan of the solution, This refers to the initial investment cost; For example, Option 1: Initial investment of 4 million yuan, annual operating cost increase of 1.2 million yuan for natural gas, annual savings of 9.855 million yuan for coal (i.e., 10,950 tons × 900 yuan / ton), 330,000 yuan for electricity (i.e., 550,000 kWh × 0.6 yuan / kWh), and annual carbon quota savings of approximately 450,000 yuan; Calculate the investment payback period = 400 / (985.5 + 33 + 45 - 120) = 400 / 943.5 ≈ 0.42 years; Net present value (NPV) (discount rate 8%, lifespan 10 years) = -400 + Σ(943.5 / (1 + 8%)^t)(t = 1 - 10) ≈ 58.6 million yuan; Internal rate of return (IRR) ≈ 235%; Option 2: Initial investment of 240,000 yuan, annual electricity savings of 288,000 yuan, and annual carbon quota revenue of approximately 210,000 yuan; Investment payback period = 24 / (288,000 + 210,000) = 24 / 498,000 ≈ 0.48 years; NPV ≈ 3.1 million yuan; IRR ≈ 208%; Option 3: Initial investment of 1.56 million yuan, annual savings of 3.285 million yuan in coal costs, 288,000 yuan in electricity costs, and approximately 360,000 yuan in carbon allowance revenue per year; Payback period = 1.56 / (3.285 + 288 + 36) = 1.56 / 3.933 ≈ 0.40 years; NPV ≈ 24.5 million yuan; IRR ≈ 262%; S53. Identify the key factors affecting the effectiveness of the scheme, simulate the changes in the emission reduction potential and economic benefits of the scheme when the key factors change, and complete the sensitivity analysis; For example, key factors are identified as: natural gas price, coal price, photovoltaic module power generation efficiency, and carbon allowance price; Simulation results: A 10% increase in natural gas prices reduces annual revenue by 360,000 yuan for Scheme 1, with no change in emission reduction potential; a 10% increase in coal prices increases annual revenue by 985,500 yuan for Scheme 1 and 328,500 yuan for Scheme 3; a 20% increase in carbon quota prices increases annual revenue by 90,000 yuan, 42,000 yuan, and 72,000 yuan for the three schemes, respectively; a 5% decrease in photovoltaic module power generation efficiency reduces annual revenue by 16,500 yuan for Scheme 1, with a relatively small impact. S6. Based on the quantitative simulation results, visualize, compare, and interactively adjust the parameters of each carbon emission optimization scheme. The specific steps of step S6 are as follows: S61. Visualize the implementation plan, and display the core measures, implementation steps, emission reduction potential and economic benefits of each candidate optimization plan in the form of charts; Specifically, through the front-end chart library, the core measures of each candidate optimization scheme are displayed in a mixed text and graphics format, the implementation steps are rendered in an interactive Gantt chart, and the emission reduction potential and economic benefits are comprehensively visualized through line charts, bar charts and dashboards. For example, the core measure is to display the equipment list and technical route of each scheme in the form of pictures and text, such as the physical picture and installation layout diagram of Scheme 1 with natural gas boiler and photovoltaic power station; Implementation steps: An interactive Gantt chart displays the time nodes for each stage. Clicking on the "Boiler Replacement" stage allows you to view the construction process and personnel configuration. Performance data: A line graph shows the change in carbon emissions over 5 years, a bar chart compares the annual emission reduction of each scheme, and a dashboard shows the carbon emission intensity compliance status (i.e., Scheme 1 meets the standard, while Schemes 2 and 3 do not reach the advanced level in the industry). S62. Implementation plan comparison and analysis: Responding to the user's selection of any two or more plans, a visual comparison is conducted from three dimensions: emission reduction effect, economic benefits, and implementation difficulty, and a comparison report is generated. Specifically, it provides a multi-select interactive interface to respond to users' selection of any two or more schemes. In the backend, it calculates the quantitative indicators of each scheme in terms of preset emission reduction effect, economic benefits, and implementation difficulty in real time. In the frontend, it performs multi-dimensional visualization comparison through parallel bar charts, radar charts and data tables, and automatically generates a structured comparison report document containing comparison conclusions. For example, users select three options for comparison, generating a visual report: Emission reduction effect: Option 1 (36%) > Option 3 (16%) > Option 2 (7%) (radar chart shown); Economic benefits: Option 1 (NPV 58.6 million yuan) > Option 3 (24.5 million yuan) > Option 2 (3.1 million yuan) (parallel bar chart shown); Implementation difficulty: Option 2 (low, 3 months) < Option 3 (medium, 6 months) < Option 1 (high, 7 months) (data table shown); Comparative conclusion: Option 1 has the best emission reduction effect, Option 2 requires the least investment and is the fastest to implement, and Option 3 has the highest overall cost performance. S63. Allows users to adjust scheme parameters, update the simulation effect of the scheme in real time, and export the scheme; Specifically, a parameter adjustment panel is provided, allowing users to dynamically adjust key parameters of any candidate solution through a graphical interface slider or input box. These parameters include investment amount, implementation period, or technical options. The front end sends the adjusted parameters to the back end effect simulation module in real time. Based on the updated parameters, the back end re-executes the simulation calculation within seconds using a trained time series prediction model and economic calculation model, and pushes the refreshed simulation effect data back to the front end interface in real time for dynamic updates and display, thereby assisting users in making decisions. At the same time, the final selected solution or comparison report can be exported in a standard document format. For example, parameter adjustment: the user adjusts the photovoltaic installed capacity of Scheme 1 from 500kW to 600kW by using the slider, and the system updates in real time: the total investment increases by 320,000 yuan, the annual power generation increases by 110,000 kWh, the annual income increases by 66,000 yuan, the investment payback period is extended to 0.45 years, and the carbon emission intensity is reduced to 1.27 tons CO2 / 10,000 yuan; Solution Export: When the user selects Solution 3, a PDF solution document is exported, which includes the implementation plan, cost-benefit table, sensitivity analysis results, and other complete content.

[0038] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0039] like Figure 2 As shown, the following are embodiments of the personalized carbon emission optimization scheme generation and effect simulation system provided in this disclosure. This system and the personalized carbon emission optimization scheme generation and effect simulation method of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the personalized carbon emission optimization scheme generation and effect simulation system, please refer to the embodiments of the personalized carbon emission optimization scheme generation and effect simulation method described above.

[0040] The system includes: The data acquisition module is used to collect basic information data, real-time operational data and external related data related to the carbon emissions of target users; The big data analytics module is used to perform big data analysis on the collected data, including preprocessing, carbon emission characteristic analysis, and optimization potential assessment. The expert knowledge base module is used to build and dynamically update an expert knowledge base covering the target industry. The expert knowledge base includes an emission reduction solution library and a management strategy library. The scheme generation module is used to generate several carbon emission candidate optimization schemes based on big data analysis results and the constructed expert knowledge base through multi-objective optimization algorithms; The effect simulation module is used to perform quantitative simulation of the generated carbon emission candidate optimization schemes. The quantitative simulation includes emission reduction potential simulation, economic benefit simulation and sensitivity analysis. The visualization and interaction module is used to visualize, compare, and adjust parameters of various carbon emission optimization schemes based on the quantitative simulation results.

[0041] This embodiment effectively addresses the problems of insufficient personalization and delayed effect evaluation in existing solutions through the interactive collaboration of data acquisition module, big data analysis module, expert knowledge base module, solution generation module, effect simulation module, and visualization interaction module. It reduces decision-making risks, improves the efficiency and rationality of carbon emission management, and provides reliable tools for industrial enterprises to carry out precise emission reduction.

[0042] The storage medium provided in this application stores a program product capable of generating personalized carbon emission optimization schemes and simulating their effects.

[0043] The method for generating and simulating personalized carbon emission optimization schemes includes: collecting basic information data, real-time operational data, and external related data related to carbon emissions from target users; performing big data analysis on the collected data, including preprocessing, carbon emission characteristic analysis, and optimization potential assessment; constructing and dynamically updating an expert knowledge base covering the target industry, which includes an emission reduction scheme library and a management strategy library; generating several sets of carbon emission candidate optimization schemes based on the big data analysis results and the constructed expert knowledge base through a multi-objective optimization algorithm; performing quantitative simulation on the generated carbon emission candidate optimization schemes, which includes emission reduction potential simulation, economic benefit simulation, and sensitivity analysis; and visually displaying, comparing, and adjusting parameters of each carbon emission optimization scheme based on the quantitative simulation results.

[0044] In some possible implementations, the personalized carbon emission optimization scheme generation and effect simulation method of this disclosure can be implemented as a program product, which includes program code. When the program product is run on a terminal device, the program code is used to cause the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0045] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0046] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating and simulating the effects of personalized carbon emission optimization schemes, characterized in that, Includes the following steps: S1. Collect basic information, real-time operational data, and external related data related to the carbon emissions of target users; S2. Perform big data analysis on the collected data, including preprocessing, carbon emission characteristic analysis, and optimization potential assessment; S3. Construct and dynamically update an expert knowledge base covering the target industry, the expert knowledge base including an emission reduction solution library and a management strategy library; S4. Based on the big data analysis results and the constructed expert knowledge base, several sets of carbon emission candidate optimization schemes are generated through multi-objective optimization algorithms; S5. Perform quantitative simulation on the generated carbon emission candidate optimization schemes, including emission reduction potential simulation, economic benefit simulation and sensitivity analysis; S6. Based on the quantitative simulation results, visualize, compare, and interact with the parameters of each carbon emission optimization scheme.

2. The method for generating and simulating the effects of personalized carbon emission optimization schemes according to claim 1, characterized in that, In step S1, user carbon emission-related data is collected through API interface connection, IoT device access, and manual upload supplementation. The collected real-time operational data includes energy consumption data, production process data, and carbon emission monitoring data with minute-level or hour-level accuracy; Basic information data includes the user's industry, production scale, geographical region, and equipment list; External data includes regional carbon emission quota data, industry benchmark carbon emission data, energy price data, and market data on emission reduction schemes.

3. The method for generating and simulating the effects of personalized carbon emission optimization schemes according to claim 2, characterized in that, The specific steps of step S2 are as follows: S21. Perform data preprocessing, cleaning the collected data through outlier detection, missing value imputation, and data standardization; S22. Perform carbon emission characteristic analysis, calculate the target user's current total carbon emissions and carbon emission intensity, identify key carbon emission links, and analyze carbon emission change trends; Specifically, total carbon emissions are calculated by summing the products of activity level data and corresponding emission factors, using the following formula: in, Total carbon emissions; For the i-th type of activity level data, the activity level data includes fossil fuel consumption and purchased electricity; The carbon emission factor corresponding to the i-th type of activity; Carbon emission intensity is calculated as the ratio of total carbon emissions to output value, using the following formula: in, For carbon emission intensity, The total output value within the preset period; The identification of key carbon emission links is achieved by calculating the carbon emission ratio of each link, and links with a ratio exceeding a preset threshold are identified as key links. S23. Conduct an optimization potential assessment, based on industry benchmark data and user historical data, to determine the user's potential emission reduction space in the dimensions of energy structure optimization, process improvement, equipment upgrade, and management optimization.

4. The method for generating and simulating the effects of personalized carbon emission optimization schemes according to claim 3, characterized in that, The specific steps of step S3 are as follows: S31. Build an emission reduction solution library, storing solution names, solution principles, applicable industries and scenarios, key solution parameters, typical investment costs, expected emission reduction rates, and links to successful implementation cases in the form of structured data tables submitted by front-end users or imported in batches. The emission reduction scheme library is constructed at the database level using a knowledge graph, with entities such as schemes, equipment, materials, and industries as nodes and relationships between entities as edges, to enable subsequent semantic-based intelligent matching and retrieval. S32. Construct a management strategy library to store information in the form of strategy entries, label each strategy entry with a strategy type, and define key attributes for each strategy; The strategy types include energy management strategies, production scheduling optimization strategies, and carbon asset management and trading strategies, and are marked with applicable conditions, implementation difficulty, and expected results; The key attributes include the applicable enterprise size, the required preconditions, the estimated implementation period, the expected economic and environmental benefits quantified by the level of implementation difficulty; S33. Dynamically update the emission reduction scheme library and management strategy library, which serve as a knowledge base, through expert manual updates and automatic data crawling.

5. The method for generating and simulating the effects of personalized carbon emission optimization schemes according to claim 4, characterized in that, The specific steps of step S4 are as follows: S41. Based on the list of key carbon emission links, the results of optimization potential assessment, and the user-preset optimization goals and constraints, construct multi-dimensional matching query conditions and perform retrieval and matching in the expert knowledge base; The matching process employs a weight-based similarity calculation algorithm: in, , , These are preset weighting coefficients; The algorithm uses similarity calculation to initially screen suitable emission reduction schemes and management strategies from the expert knowledge base, generating an initial set of strategies. S42. Using a multi-objective optimization algorithm, with the objective functions of maximizing emission reduction potential, maximizing economic benefits, and minimizing implementation difficulty, the algorithm combines and optimizes the schemes and strategies in the initial strategy set to generate N sets of candidate optimization schemes. The multi-objective optimization algorithm employs a fast non-dominated sorting genetic algorithm with an elitist retention strategy, and its execution steps include: S421. Perform encoding and population initialization, combining different schemes and management strategies into chromosomes, and randomly generating the initial population; S422. Perform fast non-dominated sorting, sorting the individuals in the population into Pareto ranks based on the three objective function values; S423. Perform crowding calculations to determine the crowding of individuals within the same non-dominated layer in order to maintain population diversity; S424. Perform selection, crossover, and mutation, conduct tournament selection based on non-dominance level and crowding, and perform simulated binary crossover and polynomial mutation to produce offspring populations. S425. Implement elite retention, merge the parent and offspring populations, and select a new generation of population based on non-dominance level and crowding. S426. Perform iteration and output, repeat steps S422 to S425 until the maximum number of iterations is reached, and output the final non-dominated solution set as N candidate optimization schemes; Each set of candidate optimization solutions includes: The list includes a core recommended technologies and strategies, a Gantt chart outlining the phased implementation steps, and a detailed list of quantified resource requirements. The resource requirements include the total investment amount, estimated human resource input, and time periods for each stage.

6. The method for generating and simulating the effects of personalized carbon emission optimization schemes according to claim 5, characterized in that, The specific steps of step S5 are as follows: S51. Based on the user's current carbon emission data, the emission reduction rate parameters of the candidate optimization schemes and the expected effects of the management strategy, and combined with the time series prediction model, simulate the carbon emission change curve within N years after the implementation of the scheme, calculate the cumulative emission reduction, the average annual emission reduction rate and the decrease in carbon emission intensity, and complete the emission reduction potential simulation. S52. Integrate the investment cost, operating cost, and revenue data of candidate optimization schemes, calculate the investment payback period, net present value (NPV), and internal rate of return (IRR), and consider the uncertainties of energy price fluctuations and changes in carbon market rules to generate economic benefit range predictions and complete economic benefit simulations. S53. Identify the key factors affecting the effectiveness of the scheme, simulate the changes in the scheme's emission reduction potential and economic benefits when the key factors change, and complete the sensitivity analysis.

7. The method for generating and simulating the effects of personalized carbon emission optimization schemes according to claim 6, characterized in that, In step S51, the time series forecasting model uses the ARIMA model; The expression for the ARIMA model is: in, It is an autoregressive polynomial. It is a moving average polynomial. For lag operators, d For the degree of difference, For time series data, It is a white noise sequence; The formula for calculating Net Present Value (NPV) in step S52 is as follows: in, Let t be the net cash flow in year t. For the discount rate, For the lifespan of the solution, This refers to the initial investment cost; In step S52, the internal rate of return It is to make the net present value A discount rate of zero is obtained by iteratively solving the following equation: in, Let t be the net cash flow in year t. For the lifespan of the solution, This represents the initial investment cost.

8. The method for generating and simulating the effects of personalized carbon emission optimization schemes according to claim 6, characterized in that, The specific steps of step S6 are as follows: S61. Visualize the implementation plan, and display the core measures, implementation steps, emission reduction potential and economic benefits of each candidate optimization plan in the form of charts; S62. Implementation plan comparison and analysis: Responding to the user's selection of any two or more plans, a visual comparison is conducted from three dimensions: emission reduction effect, economic benefits, and implementation difficulty, and a comparison report is generated. S63. Allows users to adjust scheme parameters, update the simulation effect of the scheme in real time, and export the scheme.

9. A system for generating and simulating the effects of personalized carbon emission optimization schemes, characterized in that, include: The data acquisition module is used to collect basic information data, real-time operational data and external related data related to the carbon emissions of target users; The big data analytics module is used to perform big data analysis on the collected data, including preprocessing, carbon emission characteristic analysis, and optimization potential assessment. The expert knowledge base module is used to build and dynamically update an expert knowledge base covering the target industry. The expert knowledge base includes an emission reduction solution library and a management strategy library. The scheme generation module is used to generate several carbon emission candidate optimization schemes based on big data analysis results and the constructed expert knowledge base through multi-objective optimization algorithms; The effect simulation module is used to perform quantitative simulation of the generated carbon emission candidate optimization schemes. The quantitative simulation includes emission reduction potential simulation, economic benefit simulation and sensitivity analysis. The visualization and interaction module is used to visualize, compare, and adjust parameters of various carbon emission optimization schemes based on the quantitative simulation results.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the personalized carbon emission optimization scheme generation and effect simulation method as described in any one of claims 1 to 8.

Images