Carbon emission reduction intelligent decision-making auxiliary management method and system

Abstract

The application discloses a carbon emission reduction intelligent decision-making auxiliary management method and system, and relates to the technical field of carbon emission reduction.The method comprises the following steps: collecting carbon emission related data, constructing an integrated perception trusted data chain, performing multi-dimensional associated carbon twin modeling based on the integrated perception trusted data chain, constructing a multi-driven carbon twin body, embedding a multi-factor time sequence constraint scene in the multi-driven carbon twin body, outputting predicted carbon emission data, performing collaborative autonomous optimization through an autonomous carbon management intelligent agent alliance based on the predicted carbon emission data, generating multi-dimensional adaptive carbon emission reduction collaborative decisions, feeding the multi-dimensional adaptive carbon emission reduction collaborative decisions back to the multi-driven carbon twin body, automatically calculating the carbon economy impact when the carbon emission reduction collaborative decisions are executed, and performing adaptive real-time calibration of the decisions-cost.The application can realize the transformation of carbon emission reduction management from passive response to active optimization, improve management efficiency and adaptability, and is suitable for carbon emission reduction management in multiple scenes such as industry, construction and transportation.

Description

Technical Field

[0001] This invention relates to the field of carbon emission reduction technology, and in particular to a method and system for intelligent decision-making support management of carbon emission reduction. Background Technology

[0002] As the complexity of carbon emission reduction management at the enterprise and regional levels increases, existing technological solutions have significant shortcomings and fail to meet actual needs. On the one hand, carbon emission data collection is often characterized by "single-point and fragmented" features, covering only single links such as industrial production and building energy consumption, lacking the support of a three-dimensional "space-air-ground" sensing network, and the data formats are inconsistent, making it difficult to verify reliability (e.g., data deviations caused by sensor failures are not identified), failing to form a reliable data foundation that spans the entire scenario, resulting in a lack of accurate data support for subsequent modeling and decision-making. On the other hand, existing carbon twin modeling is mostly static mapping, only reflecting the current carbon emission status, without considering the time-series constraints of multiple factors such as "fluctuations in production load, adjustments to carbon tax policies, and changes in green electricity supply," making it impossible to accurately predict carbon emission trends under different operating conditions, and decisions are prone to lag behind actual needs. Furthermore, carbon emission reduction decisions often rely on human experience or single-scenario optimization, failing to achieve cross-scenario resource coordination (such as conflicts in green electricity allocation between industrial and transportation scenarios). Moreover, after the decisions are implemented, there is a lack of real-time assessment and dynamic calibration mechanisms for carbon economics. When carbon prices fluctuate or equipment operating parameters deviate, contradictions such as "emission reduction targets are met but costs exceed budgets" or "costs are controllable but emission reductions are insufficient" are likely to occur. Overall, management efficiency is low and adaptability is poor, making it difficult to meet the needs of full-process, intelligent carbon emission reduction management. Summary of the Invention

[0003] This invention provides a smart decision-making support management method for carbon emission reduction, comprising:

[0004] The intelligent decision-making support management method for carbon emission reduction described above includes the following sub-steps for collecting carbon emission-related data and constructing an integrated, reliable data chain for perception:

[0005] Step S11: Construct a space-air-ground carbon trace sensing network through multi-dimensional technology fusion to collect carbon emission related data;

[0006] Step S12: Use blockchain and distributed technologies to integrate and trust carbon emission-related data to build an integrated perception and trust data chain.

[0007] The intelligent decision-making support management method for carbon emission reduction described above includes the following sub-steps for collecting carbon emission-related data by constructing a space-air-ground carbon trace sensing network through multi-dimensional technology fusion:

[0008] Step S111: Construct a space-based satellite remote sensing macro-capture network based on satellite remote sensing technology to capture macro-carbon emission trends within the region;

[0009] Step S112: Construct an airborne patrol precision source tracing network based on UAV patrol technology to obtain carbon emission source information;

[0010] Step S113: Construct a ground-based micro-sensing network based on ground-based carbon sensing technology to obtain carbon emission correlation data for specific equipment;

[0011] Step S114: Collaborate and fuse the data collected from the sky, ground and air levels to output full-scale, multi-dimensional carbon emission correlation data.

[0012] The intelligent decision-making support management method for carbon emission reduction described above includes the following sub-steps for constructing a multi-driven carbon twin based on an integrated perception and trusted data chain for multi-dimensional correlated carbon twin modeling:

[0013] Step S21: Analyze and process the data in the integrated perception trusted data chain, and perform multi-dimensional correlation carbon twin modeling;

[0014] Step S22: Add a multi-drive dynamic update and verification mechanism to the multi-dimensional correlated carbon twin modeling to construct a multi-drive carbon twin.

[0015] The intelligent decision-making support management method for carbon emission reduction described above includes the following sub-steps for parsing and processing data in the integrated sensing trusted data chain and performing multi-dimensional correlated carbon twin modeling:

[0016] Step S211: Decompose the data in the integrated perception trusted data chain into physical space data, carbon flow data and business data;

[0017] Step S212: Perform three-dimensional visualization modeling based on physical space data to construct a carbon twin skeleton;

[0018] Step S213: Based on carbon flow data, business data and carbon twin skeleton, perform multi-dimensional correlation to construct a multi-dimensional correlated carbon twin model.

[0019] The intelligent decision-making support management method for carbon emission reduction described above, wherein embedding a multi-factor time-series constraint scenario into a multi-driven carbon twin and outputting predicted carbon emission data includes the following sub-steps:

[0020] Step S31: Obtain internal and external constraint factors for carbon emissions and construct a multi-factor time-series constraint scenario;

[0021] Step S32: Embed the multi-factor time-series constraint scenario into the multi-drive carbon twin, link the data according to different scenarios, and output the predicted carbon emission data of multiple scenarios.

[0022] The intelligent decision-making support management method for carbon emission reduction described above, which embeds multi-factor time-series constraint scenarios into a multi-driven carbon twin, performs data linkage across scenarios, and outputs carbon emission data for multiple scenarios, includes the following sub-steps:

[0023] Step S321: Embed the multi-factor temporal constraint scenario into the multi-driver carbon twin to construct a dynamic constraint multi-driver carbon twin;

[0024] Step S322: Adjust the constraint factor parameters in the dynamic constraint multi-drive carbon twin and output the predicted carbon emission data for the multi-constraint scenario.

[0025] The carbon emission reduction intelligent decision-making auxiliary management method described above includes the following sub-steps: Based on predicted carbon emission data, it generates multi-dimensional adaptive carbon emission reduction collaborative decisions through collaborative autonomous optimization via an autonomous carbon management intelligent agent alliance.

[0026] Step S41: Based on the functional scenarios and objectives of regional carbon emission reduction, establish an autonomous carbon management intelligent agent alliance;

[0027] Step S42: Based on the predicted carbon emission data, the autonomous carbon management intelligent agent alliance performs single-scenario autonomous optimization and cross-scenario collaborative optimization to generate multi-dimensional adaptive carbon emission reduction collaborative decisions.

[0028] The carbon emission reduction intelligent decision-making auxiliary management method described above includes the following sub-steps: Based on predicted carbon emission data, it generates multi-dimensional adaptive carbon emission reduction collaborative decisions through a consortium of autonomous carbon management intelligent agents, performing single-scenario autonomous optimization and cross-scenario collaborative optimization.

[0029] Step S421: Based on the predicted carbon emission data, perform single-scenario autonomous optimization through the autonomous carbon management intelligent agent alliance to generate a single-scenario collaborative optimization scheme.

[0030] Step S422: Based on each scenario, the single-scenario collaborative optimization schemes are optimized across scenarios through the autonomous carbon management intelligent agent alliance, and output multi-dimensional identification of carbon emission reduction collaborative decisions.

[0031] The intelligent decision-making support management method for carbon emission reduction described above includes the following sub-steps: feeding back multi-dimensional adaptive carbon emission reduction collaborative decisions to a multi-driven carbon twin; automatically calculating the carbon economic impact of executing collaborative carbon emission reduction decisions; and performing adaptive real-time calibration of decision-cost.

[0032] Step S51: Feed back the multi-dimensional adaptive carbon emission reduction collaborative decision to the multi-drive carbon twin and automatically calculate the carbon economic impact when executing the carbon emission reduction collaborative decision.

[0033] Step S52: Based on the impact of carbon economy, set adaptive decision-making-cost adaptive real-time calibration trigger rules, and perform adaptive real-time calibration and effect monitoring.

[0034] The present invention also provides a carbon emission reduction intelligent decision-making auxiliary management system, including: an integrated perception trusted data chain construction module, which collects carbon emission related data and constructs an integrated perception trusted data chain;

[0035] The multi-driven carbon twin construction module is based on an integrated perception trusted data chain to perform multi-dimensional correlation carbon twin modeling and construct multi-driven carbon twins.

[0036] The carbon emission prediction data acquisition module embeds multi-factor time-series constraint scenarios into a multi-driver carbon twin and outputs predicted carbon emission data.

[0037] The multi-dimensional adaptive carbon emission reduction collaborative decision generation module generates multi-dimensional adaptive carbon emission reduction collaborative decisions based on predicted carbon emission data and through collaborative and autonomous optimization by an autonomous carbon management intelligent agent alliance.

[0038] The adaptive real-time calibration module feeds back multi-dimensional adaptive carbon emission reduction collaborative decision-making to the multi-drive carbon twin, automatically calculates the carbon economic impact of executing carbon emission reduction collaborative decision-making, and performs adaptive real-time calibration of decision-cost.

[0039] The beneficial effects achieved by this invention are as follows: This invention can integrate multi-source data collection and reliably store it, achieving comprehensive coverage and reliability assurance of carbon emission data across scenarios, providing a high-quality data foundation for subsequent implementation, and ensuring the accuracy of the physical mapping of carbon twins; it can also accurately simulate carbon emission changes under different time dimensions and constraints, outputting forward-looking predictive data to provide a scientific basis for decision-making and avoid the blindness of experience-based decisions; it can also adapt to decision-making from multiple dimensions such as emission reduction effect, economic cost, and business compatibility, solving the locality problem of single-scenario optimization and improving the global optimality of decisions; it ensures stable emission reduction results and controllable costs, realizing the transformation of carbon emission reduction management from passive response to proactive optimization, improving management efficiency and adaptability, and is applicable to carbon emission reduction management in multiple scenarios such as industry, construction, and transportation, with broad application prospects. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0041] Figure 1 This is a flowchart of a carbon emission reduction intelligent decision-making auxiliary management method provided in Embodiment 1 of this application;

[0042] Figure 2 This is a schematic diagram of a carbon emission reduction intelligent decision support management system provided in Embodiment 2 of this application. Detailed Implementation

[0043] 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, not all, of the embodiments of the present invention. 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.

[0044] Example 1

[0045] like Figure 1 As shown in Embodiment 1 of this application, a method for intelligent decision-making assistance in carbon emission reduction is provided, which includes the following steps:

[0046] Step S1: Collect carbon emission-related data and construct an integrated, trusted data chain for perception.

[0047] Furthermore, collecting carbon emission-related data and constructing an integrated, trusted data chain for perception includes the following sub-steps:

[0048] Step S11: Construct a space-air-ground carbon trace sensing network through multi-dimensional technology fusion to collect carbon emission related data;

[0049] Specifically, based on multi-dimensional technologies such as satellite remote sensing, drone patrols, and ground-based carbon sensing, a three-layer space-air-ground carbon trace sensing network is constructed, consisting of macroscopic capture by space-based satellite remote sensing, precise source tracing by airborne patrols, and microscopic sensing by ground-based systems. Each layer conducts collaborative data collection and data association and fusion according to the collection tasks to obtain multi-dimensional carbon emission correlation data across the entire scale.

[0050] Furthermore, by integrating multi-dimensional technologies to construct a space-air-ground carbon trace sensing network, the collection of carbon emission-related data includes the following sub-steps:

[0051] Step S111: Construct a space-based satellite remote sensing macro-capture network based on satellite remote sensing technology to capture macro-carbon emission trends within the region;

[0052] Specifically, based on satellite remote sensing technology, access to carbon monitoring satellites is used to construct a space-based satellite remote sensing macro-capture network. This network collects carbon monitoring satellite data within the target area, aligns the data with electronic maps, and labels the geographic information within the target area. The average carbon emissions within the target area are calculated at preset intervals to generate macro-carbon emission trends within the target area. Simultaneously, abnormal carbon emission areas with carbon emission concentrations exceeding the carbon emission threshold are identified.

[0053] Step S112: Construct an airborne patrol precision source tracing network based on UAV patrol technology to obtain carbon emission source information;

[0054] Specifically, an airborne patrol precision source tracing network is constructed based on UAV patrol technology. Each UAV in the airborne patrol precision source tracing network and its onboard high-precision carbon emission detection equipment patrols the abnormal carbon emission area as a whole to obtain the overall carbon concentration distribution of the abnormal carbon emission area. Each UAV flies around at a preset interval to obtain precise carbon emission information such as the location coordinates, concentration data, and thermal imaging images of the precise carbon emission sources in the abnormal carbon emission area.

[0055] Step S113: Construct a ground-based micro-sensing network based on ground-based carbon sensing technology to obtain carbon emission correlation data for specific equipment;

[0056] Specifically, by deploying various types of sensing devices in the carbon flow production process, carbon emission-related data from different devices in each stage are collected. For example, in the energy consumption stage, smart flow meters deployed in industrial boilers, motors and other equipment are used to collect energy consumption data. In the material conversion stage, RFID tags, smart weighbridges and other sensing devices deployed in raw material warehouses are used to collect raw material inbound and outbound volumes. Through API interfaces, the carbon emission-related data is linked to the enterprise system and collected in conjunction with the business data of each enterprise.

[0057] Step S114: Collaborate and fuse the data collected from the sky, ground and air levels to output full-scale, multi-dimensional carbon emission correlation data;

[0058] Specifically, a carbon data collaborative association and fusion platform for the target area is built to receive three layers of data from the sky-ground carbon trace sensing network, align the three layers of data in time and space, and collaboratively associate and fuse the three layers of data according to grid positions. The platform outputs full-scale, multi-dimensional carbon emission association data according to a three-level structure of region-carbon emission source-equipment.

[0059] Step S12: Use blockchain and distributed technologies to integrate and trust carbon emission-related data to build an integrated perception and trust data chain;

[0060] Specifically, a consortium blockchain is built using a consortium blockchain framework, with the data collectors, verifiers, and regulators within the target region acting as consensus nodes. Carbon emission-related data is stored in a distributed file system using a hash-on-chain + distributed storage model. Data hash values ​​and metadata are stored on the blockchain for evidence preservation. Data sharing authorization and sharing scope are set through smart contracts, and authorized access history is recorded on the blockchain. An integrated perception and trusted data chain is constructed to monitor the data collection, transmission, and storage status in real time, set automatic verification rules to automatically verify the data, and conduct regular security audits on the integrated perception and trusted data chain.

[0061] Step S2: Based on the integrated perception trusted data chain, perform multi-dimensional correlation carbon twin modeling and construct a multi-driven carbon twin;

[0062] Furthermore, based on an integrated sensing trusted data chain, multi-dimensional correlated carbon twin modeling is performed to construct a multi-driven carbon twin, which includes the following sub-steps:

[0063] Step S21: Analyze and process the data in the integrated perception trusted data chain, and perform multi-dimensional correlation carbon twin modeling;

[0064] Furthermore, the data in the integrated sensing trusted data chain is parsed and processed to perform multi-dimensional correlated carbon twin modeling, including the following sub-steps:

[0065] Step S211: Decompose the data in the integrated perception trusted data chain into physical space data, carbon flow data and business data;

[0066] Specifically, the data in the integrated perception trusted data chain is divided into physical space data, carbon flow data, and business data. Physical space data includes target area layout maps, equipment parameters, geographic information, and other related data. Carbon flow data includes real-time energy consumption of equipment, material consumption, carbon emission concentration and rate, and other related data. Business data includes production work orders, purchase orders, logistics scheduling plans, and other related data. The three types of data are indexed by timestamp-region ID-equipment ID.

[0067] Step S212: Perform three-dimensional visualization modeling based on physical space data to construct a carbon twin skeleton;

[0068] Specifically, a macro framework of the target area is first constructed based on physical space data, including macro structures such as terrain, roads, and green spaces. Building structures are then added on the basis of the macro framework, including data such as floor distribution, door and window locations, and building walls. Equipment models are then embedded on the above basis, and visual identifiers are added to key carbon flow nodes to construct a carbon twin framework.

[0069] Step S213: Based on carbon flow data, business data and carbon twin skeleton, perform multi-dimensional correlation to construct a multi-dimensional correlated carbon twin model;

[0070] Specifically, carbon flow data is mapped to the corresponding equipment and space in the carbon twin framework using device IDs and location coordinates. Carbon emission intensity is marked with different colors, and a carbon emission heat map is overlaid above the target area to display the carbon emission distribution. Based on business data, business event triggers are added to the carbon twin framework. When business data is received, the equipment of the corresponding production line in the carbon twin framework automatically switches to the running state, automatically calculates the estimated carbon emissions of the business, establishes the linkage logic between carbon flow and business, and displays the associated business events in the carbon twin framework, forming a multi-dimensional associated carbon twin model that integrates physical form, carbon flow changes, and business activities.

[0071] Step S22: Add a multi-drive dynamic update and verification mechanism to the multi-dimensional correlated carbon twin modeling, and construct a multi-drive carbon twin;

[0072] Specifically, a real-time data synchronization channel is established to inject the latest data from the integrated perception trusted data chain into the multi-dimensional correlated carbon twin model in real time. Based on changes in carbon flow data, equipment status and carbon flow heatmap updates are triggered, forming a carbon flow-driven mechanism. Based on changes in business data, equipment actions and estimated carbon emissions are triggered, forming a business-driven mechanism. Based on changes in physical space data, model updates are triggered, forming a physical-driven mechanism. A multi-drive dynamic update mechanism is formed based on carbon flow-driven, business-driven, and physical-driven mechanisms and added to the multi-dimensional correlated carbon twin model to construct a multi-drive carbon twin. Based on a preset period, the modeling data of the multi-drive carbon twin is compared with the real data in the integrated perception trusted data chain to calculate the deviation rate. When the deviation rate exceeds a preset threshold, the parameters of the multi-drive carbon twin are adjusted and updated based on the integrated perception trusted data chain.

[0073] Step S3: Embed a multi-factor time-series constraint scenario into the multi-driver carbon twin and output predicted carbon emission data;

[0074] Furthermore, embedding multi-factor time-series constraints into the multi-driver carbon twin to output predicted carbon emission data includes the following sub-steps:

[0075] Step S31: Obtain internal and external constraint factors for carbon emissions and construct a multi-factor time-series constraint scenario;

[0076] Specifically, internal constraint factors are collected based on enterprise systems, including business factors, technology factors, equipment factors, and other internal influencing factors. External constraint factors are collected based on multiple data sources such as government platforms, energy supply, and meteorological stations, including policy factors, market factors, environmental factors, and other external influencing factors. Time-series scenarios are divided into short-term, medium-term, and long-term scenarios. High-frequency change factors are embedded in short-term scenarios, medium-frequency change factors are embedded in medium-term scenarios, and low-frequency change factors are embedded in long-term scenarios. Scenario constraints of time range, constraint factor combination, and expected goal are set in each time-series scenario to construct multi-factor time-series constraint scenarios.

[0077] Step S32: Embed the multi-factor time-series constraint scenario into the multi-driver carbon twin, perform data linkage for different scenarios, and output predicted carbon emission data for multiple scenarios.

[0078] Furthermore, embedding multi-factor time-series constrained scenarios into multi-driver carbon twins and linking data across scenarios to output carbon emission data for multiple scenarios includes the following sub-steps:

[0079] Step S321: Embed the multi-factor temporal constraint scenario into the multi-driver carbon twin to construct a dynamic constraint multi-driver carbon twin;

[0080] Specifically, corresponding time-series driving logic is set for multi-factor time-series constraint scenarios. Short-term scenarios use real-time parameter refresh driving logic, medium-term scenarios use periodic parameter update driving logic, and long-term scenarios use stage parameter switching driving logic. Based on the multi-factor time-series constraint scenarios and their driving logic, a scenario interaction panel is built in the multi-driving carbon twin to display the current scenario's multi-constraint factor combination and effective time range in real time, forming a dynamic constraint multi-driving carbon twin with linkage between time-series, constraint factors, and multi-driving carbon twin states.

[0081] Step S322: Adjust the constraint factor parameters in the dynamic constraint multi-drive carbon twin and output the predicted carbon emission data for the multi-constraint scenario;

[0082] Specifically, the system allows users to set constraint factor parameters for different time series through a scenario interaction panel, generating multiple constraint scenarios such as baseline scenarios, policy change scenarios, technology change scenarios, and resource change scenarios for different time series. During the setting process, the system displays the correlation between time series changes, parameter changes, and carbon emission changes in real time. The system simulates carbon emission data for each constraint scenario under each time series using a dynamic constraint multi-drive carbon twin, and outputs the predicted carbon emission data for each constraint scenario in the format of constraint scenario name - constraint factor combination - predicted total carbon emission - carbon emission details by equipment - prediction deviation rate.

[0083] Step S4: Based on the predicted carbon emission data, the autonomous carbon management intelligent agent alliance conducts collaborative autonomous optimization to generate multi-dimensional adaptive carbon emission reduction collaborative decisions.

[0084] Furthermore, based on predicted carbon emission data, collaborative and autonomous optimization is carried out through an autonomous carbon management intelligent agent alliance to generate multi-dimensional adaptive carbon emission reduction collaborative decisions, including the following sub-steps:

[0085] Step S41: Based on the functional scenarios and objectives of regional carbon emission reduction, establish an autonomous carbon management intelligent agent alliance;

[0086] Specifically, based on the functional scenarios involving carbon emission reduction in the target area, such as industry, construction, and transportation, an autonomous carbon management intelligent agent alliance is established, consisting of multiple specialized intelligent agents. These specialized intelligent agents communicate and share data in real time. The specialized intelligent agents include a data access and analysis agent, a functional scenario decomposition agent, a path optimization agent, a cost analysis and accounting agent, a business adaptation agent, a functional scenario solution generation agent, and a multi-scenario solution collaborative optimization agent. The data access and analysis agent receives predicted carbon emission data from various constraint scenarios and analyzes the carbon emission capacity of each functional scenario. The functional scenario decomposition agent breaks down the overall carbon emission reduction target for the target area into sub-scenarios according to functional scenarios. The objectives are: to simultaneously label the predicted carbon emission gap for each functional scenario; to generate multiple emission reduction paths based on the carbon emission capacity of each functional scenario and calculate data such as carbon emission reduction, investment, and payback period for each path; to calculate the unit emission reduction cost of the multiple emission reduction paths generated by the path optimization agent by combining cost factors such as the carbon emission reduction budget, internal and external costs, and carbon emission reduction benefits of the target area; to verify the compatibility between emission reduction paths and business operations; to generate multiple carbon emission reduction schemes for each functional scenario and label the advantages and disadvantages of each scheme; and to collaboratively optimize the carbon emission reduction schemes for each scenario.

[0087] Step S42: Based on the predicted carbon emission data, the autonomous carbon management intelligent agent alliance performs single-scenario autonomous optimization and cross-scenario collaborative optimization to generate multi-dimensional adaptive carbon emission reduction collaborative decisions.

[0088] Furthermore, based on predicted carbon emission data, a multi-dimensional adaptive carbon reduction collaborative decision is generated through a consortium of autonomous carbon management intelligent agents, involving single-scenario autonomous optimization and cross-scenario collaborative optimization. This includes the following sub-steps:

[0089] Step S421: Based on the predicted carbon emission data, perform single-scenario autonomous optimization through the autonomous carbon management intelligent agent alliance to generate a single-scenario collaborative optimization scheme.

[0090] Specifically, based on predicted carbon emission data, the target area is broken down into multiple functional scenarios and analyzed by an autonomous carbon management intelligent agent alliance. This generates analysis results for each specialized intelligent agent, and the formula is autonomously optimized within each scenario. Select single-scenario collaborative optimization solutions for each functional scenario, among which, For the first A single-scenario collaborative optimization solution for each functional scenario. The range of values ​​is , The number of functional scenarios within the target area. For the first A set of optional emission reduction paths for each functional scenario The first in Group of emission reduction pathway combinations For emission reduction path combination Total emission reductions, For the first Permissible emission reduction deviation coefficient for each functional scenario For the first Carbon emission reduction targets for each functional scenario For emission reduction path combination The average unit emission reduction cost, This represents the upper limit of the unit emission reduction cost. For emission reduction path combination Business compatibility, This is the minimum level of compatibility required for the adapted services.

[0091] Step S422: Based on each scenario, the single-scenario collaborative optimization schemes are optimized across scenarios through the autonomous carbon management intelligent agent alliance, and multi-dimensional identification of carbon emission reduction collaborative decisions is output.

[0092] Specifically, the single-scenario collaborative optimization schemes based on various functional scenarios are optimized through the multi-scenario scheme collaborative optimization formula of the autonomous carbon management intelligent agent alliance. Cross-scenario collaborative optimization is performed to generate multi-dimensional identification of collaborative carbon emission reduction decisions. To identify collaborative carbon reduction decisions from multiple dimensions, This is a collection of single-scenario collaborative optimization solutions for various functional scenarios. For the first A single-scenario collaborative optimization solution for each functional scenario. The range of values ​​is , The number of functional scenarios within the target area. As a resource-dimensional collaborative optimization factor, For the first The number of emission reduction paths for a single scenario requiring collaborative optimization in each functional scenario. The range of values ​​is , For the first The first single-scenario collaborative optimization solution for each functional scenario. The amount of shared resources consumed by each emission reduction path. For the first The maximum total amount of resources that can be allocated to each functional scenario. For the first Resource scarcity coefficient for each functional scenario As a factor for synergistic optimization of emission reduction costs, For the first The first functional scenario The total cost of the emission reduction path, For cross-scenario collaboration The amount of cost saved in each functional scenario For business-dimensional collaborative optimization factors, For the first The business compatibility coefficient of the single-scenario collaborative optimization solution for each functional scenario. The range of values ​​is , For the first The first functional scenario and the first Business relevance of each functional scenario For the first The business compatibility coefficient of the single-scenario collaborative optimization solution for each functional scenario. As a factor for coordinated optimization across policy and rule dimensions, For the first The policy compliance coefficient of the single-scenario collaborative optimization solution for each functional scenario. For the first Policy and regulatory factors for each functional scenario.

[0093] Step S5: Feed back the multi-dimensional adaptive carbon emission reduction collaborative decision to the multi-drive carbon twin, automatically calculate the carbon economic impact when executing the carbon emission reduction collaborative decision, and perform adaptive real-time calibration of decision-cost.

[0094] Furthermore, the multi-dimensional adaptive carbon emission reduction collaborative decision-making is fed back to the multi-driven carbon twin to automatically calculate the carbon economic impact of executing the carbon emission reduction collaborative decision-making, and to perform adaptive real-time calibration of decision-cost, including the following sub-steps:

[0095] Step S51: Feed back the multi-dimensional adaptive carbon emission reduction collaborative decision to the multi-drive carbon twin and automatically calculate the carbon economic impact when executing the carbon emission reduction collaborative decision.

[0096] Specifically, the data format adapted to multi-dimensional carbon emission reduction collaborative decision-making is processed into a data format recognizable by the multi-driven carbon twin, and then imported into the multi-driven carbon twin for carbon emission simulation operation. Based on the carbon emission simulation operation data, the carbon economic impact is calculated using the formula. Calculate the carbon economic impact of the target region, where, This represents the carbon economic impact value. The number of benefits from carbon emission reduction. The range of values ​​is , For the first The amount of revenue from each revenue item For initial investment costs, For the life cycle of carbon reduction-related equipment, The range of values ​​is , For the first Annual carbon emission reduction related equipment operation and maintenance costs This represents the actual emission reduction. To achieve the target emission reduction, This is the preset maximum emission reduction rate. This represents the average annual net income. This is the preset maximum payback period.

[0097] Step S52: Based on the impact of carbon economy, set adaptive decision-making-cost adaptive real-time calibration trigger rules, and perform adaptive real-time calibration and effect monitoring;

[0098] Specifically, a three-level adaptive decision-making and cost-adaptive real-time calibration triggering rule is set based on the impact of carbon economics. Three levels of triggering conditions are established according to preset deviation rates, costs, and payback periods. Adaptive real-time calibration is automatically executed based on the triggering condition level, generating a fine-tuning control command set for the equipment. This set is then rapidly simulated and verified using multi-drive carbon twins. Once verified, the fine-tuning control command set is distributed to the corresponding edge nodes of each device. Each edge node translates the received commands into equipment execution commands to fine-tune the equipment's operating status. The carbon emission reduction effect is monitored in real time during equipment operation, and the calibration results are synchronized to the Autonomous Carbon Management Intelligent Agent Alliance to update its parameters.

[0099] Example 2

[0100] like Figure 2 As shown, Embodiment 2 of this application provides a carbon emission reduction intelligent decision-making support management system, including:

[0101] The integrated sensing trusted data chain construction module 21 collects carbon emission related data and constructs an integrated sensing trusted data chain.

[0102] The multi-driven carbon twin construction module 22 is based on an integrated perception trusted data chain to perform multi-dimensional correlation carbon twin modeling and construct a multi-driven carbon twin.

[0103] The carbon emission prediction data acquisition module 23 embeds a multi-factor time-series constraint scenario into a multi-driving carbon twin and outputs predicted carbon emission data.

[0104] The multi-dimensional adaptive carbon emission reduction collaborative decision generation module 24 generates multi-dimensional adaptive carbon emission reduction collaborative decisions based on predicted carbon emission data and through collaborative autonomous optimization by an autonomous carbon management intelligent agent alliance.

[0105] The adaptive real-time calibration module 25 feeds back multi-dimensional adaptive carbon emission reduction collaborative decision to the multi-drive carbon twin, automatically calculates the carbon economic impact when executing carbon emission reduction collaborative decision, and performs adaptive real-time calibration of decision-cost.

[0106] Corresponding to the above embodiments, the present invention provides a computer storage medium, including: at least one memory and at least one processor;

[0107] The memory is used to store one or more program instructions;

[0108] A processor is used to run one or more program instructions to execute a smart decision-making support management method for carbon emission reduction.

[0109] Corresponding to the above embodiments, this embodiment of the invention provides a computer-readable storage medium containing one or more program instructions, which are used by a processor to provide a carbon emission reduction intelligent decision-making auxiliary management method.

[0110] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions. When the computer program instructions are executed on a computer, the computer performs the aforementioned intelligent decision-making assistance management method for carbon emission reduction.

[0111] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0112] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0113] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0114] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0115] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0116] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0117] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0118] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent decision-making support management of carbon emission reduction, characterized in that, include: Step S1: Collect carbon emission-related data and construct an integrated and trusted data chain; specifically, this includes: constructing a space-air-ground carbon trace sensing network through multi-dimensional technology integration to collect carbon emission-related data; and using blockchain and distributed technologies to integrate and trust the carbon emission-related data to construct an integrated and trusted data chain. Step S2: Perform multi-dimensional correlated carbon twin modeling based on the integrated perception trusted data chain to construct a multi-driven carbon twin; specifically, this includes: parsing and processing the data in the integrated perception trusted data chain to perform multi-dimensional correlated carbon twin modeling; adding a multi-driven dynamic update and verification mechanism to the multi-dimensional correlated carbon twin modeling to construct a multi-driven carbon twin. Step S3: Embed multi-factor time-series constraint scenarios into the multi-driver carbon twin and output predicted carbon emission data; specifically, this includes: obtaining internal and external constraint factors for carbon emissions, constructing multi-factor time-series constraint scenarios; embedding the multi-factor time-series constraint scenarios into the multi-driver carbon twin, performing data linkage between different scenarios, and outputting predicted carbon emission data for multiple scenarios. Step S4: Based on predicted carbon emission data, conduct collaborative and autonomous optimization through an autonomous carbon management intelligent agent alliance to generate multi-dimensional adaptive carbon emission reduction collaborative decisions; specifically including: building an autonomous carbon management intelligent agent alliance based on the functional scenarios and objectives of regional carbon emission reduction; and conducting single-scenario autonomous optimization and cross-scenario collaborative optimization through the autonomous carbon management intelligent agent alliance based on predicted carbon emission data to generate multi-dimensional adaptive carbon emission reduction collaborative decisions. Step S5: Feed back the multi-dimensional adaptive carbon emission reduction collaborative decision to the multi-driven carbon twin, automatically calculate the carbon economic impact of executing the carbon emission reduction collaborative decision, and perform adaptive real-time calibration of decision-cost; specifically, this includes: feeding back the multi-dimensional adaptive carbon emission reduction collaborative decision to the multi-driven carbon twin, automatically calculating the carbon economic impact of executing the carbon emission reduction collaborative decision; setting adaptive decision-cost adaptive real-time calibration trigger rules based on the carbon economic impact, and performing adaptive real-time calibration and effect monitoring.

2. The intelligent decision-making support management method for carbon emission reduction as described in claim 1, characterized in that, By integrating multi-dimensional technologies to construct a space-air-ground carbon trace sensing network, the collection of carbon emission-related data includes the following sub-steps: Step S111: Construct a space-based satellite remote sensing macro-capture network based on satellite remote sensing technology to capture macro-carbon emission trends within the region; Step S112: Construct an airborne patrol precision source tracing network based on UAV patrol technology to obtain carbon emission source information; Step S113: Construct a ground-based micro-sensing network based on ground-based carbon sensing technology to obtain carbon emission correlation data for specific equipment; Step S114: Collaborate and fuse the data collected from the sky, ground and air levels to output full-scale, multi-dimensional carbon emission correlation data.

3. The intelligent decision-making support management method for carbon emission reduction as described in claim 1, characterized in that, The process of parsing and processing data in the integrated sensing trusted data chain and performing multi-dimensional correlated carbon twin modeling includes the following sub-steps: Step S211: Decompose the data in the integrated perception trusted data chain into physical space data, carbon flow data and business data; Step S212: Perform three-dimensional visualization modeling based on physical space data to construct a carbon twin skeleton; Step S213: Based on carbon flow data, business data and carbon twin skeleton, perform multi-dimensional correlation to construct a multi-dimensional correlated carbon twin model.

4. The intelligent decision-making support management method for carbon emission reduction as described in claim 1, characterized in that, Embedding multi-factor time-series constrained scenarios into multi-driver carbon twins, and linking data across different scenarios to output carbon emission data for multiple scenarios includes the following sub-steps: Step S321: Embed the multi-factor temporal constraint scenario into the multi-driver carbon twin to construct a dynamic constraint multi-driver carbon twin; Step S322: Adjust the constraint factor parameters in the dynamic constraint multi-drive carbon twin and output the predicted carbon emission data for the multi-constraint scenario.

5. The intelligent decision-making support management method for carbon emission reduction as described in claim 1, characterized in that, Based on predicted carbon emission data, a multi-dimensional adaptive carbon emission reduction collaborative decision is generated through a self-managing carbon management intelligent agent alliance, involving single-scenario autonomous optimization and cross-scenario collaborative optimization. The process includes the following sub-steps: Step S421: Based on the predicted carbon emission data, perform single-scenario autonomous optimization through the autonomous carbon management intelligent agent alliance to generate a single-scenario collaborative optimization scheme. Step S422: Based on each scenario, the single-scenario collaborative optimization schemes are optimized across scenarios through the autonomous carbon management intelligent agent alliance, and output multi-dimensional identification of carbon emission reduction collaborative decisions.

6. A carbon emission reduction intelligent decision support management system, characterized in that, include: The integrated sensing and trusted data chain construction module collects carbon emission-related data and constructs an integrated sensing and trusted data chain. Specifically, it includes: constructing an air-space-ground carbon trace sensing network through multi-dimensional technology integration to collect carbon emission-related data; and using blockchain and distributed technologies to perform integrated and trusted processing of carbon emission-related data to construct an integrated sensing and trusted data chain. The multi-driven carbon twin construction module is based on an integrated perception trusted data chain to perform multi-dimensional correlated carbon twin modeling and construct a multi-driven carbon twin. Specifically, it includes: parsing and processing the data in the integrated perception trusted data chain to perform multi-dimensional correlated carbon twin modeling; adding a multi-driven dynamic update and verification mechanism to the multi-dimensional correlated carbon twin modeling and constructing a multi-driven carbon twin. The carbon emission prediction data acquisition module embeds multi-factor time-series constraint scenarios into a multi-driver carbon twin and outputs predicted carbon emission data. Specifically, it includes: acquiring internal and external constraint factors for carbon emissions, constructing multi-factor time-series constraint scenarios, embedding multi-factor time-series constraint scenarios into a multi-driver carbon twin, performing data linkage between different scenarios, and outputting predicted carbon emission data for multiple scenarios. The multi-dimensional adaptive carbon emission reduction collaborative decision generation module generates multi-dimensional adaptive carbon emission reduction collaborative decisions based on predicted carbon emission data and through collaborative autonomous optimization by an autonomous carbon management intelligent agent alliance. Specifically, it includes: building an autonomous carbon management intelligent agent alliance based on the functional scenarios and objectives of regional carbon emission reduction; and generating multi-dimensional adaptive carbon emission reduction collaborative decisions by performing single-scenario autonomous optimization and cross-scenario collaborative optimization through the autonomous carbon management intelligent agent alliance based on predicted carbon emission data. The adaptive real-time calibration module feeds back multi-dimensional adaptive carbon emission reduction collaborative decisions to the multi-driven carbon twin, automatically calculates the carbon economic impact of executing collaborative carbon emission reduction decisions, and performs adaptive real-time calibration of decision-cost. Specifically, this includes: feeding back multi-dimensional adaptive carbon emission reduction collaborative decisions to the multi-driven carbon twin, automatically calculating the carbon economic impact of executing collaborative carbon emission reduction decisions; setting adaptive decision-cost adaptive real-time calibration trigger rules based on the carbon economic impact, and performing adaptive real-time calibration and effect monitoring.

Images