Carbon emission prediction and regulation system and method based on multi-scale dynamic optimization

Abstract

The application discloses a carbon emission prediction and regulation system and method based on multi-scale dynamic optimization, and the system comprises a data acquisition layer, a five-dimensional coupling model layer and an optimization and regulation layer; the data acquisition layer collects multi-source heterogeneous data in real time by deploying an Internet of Things sensor network; the five-dimensional coupling model layer has a five-dimensional dynamic coupling model, including a multi-scale carbon emission dynamics equation, an industrial correlation network model, a space-time coupling prediction model and a dynamic optimization control model; the optimization and regulation layer integrates an improved particle swarm optimization algorithm and a non-dominated sorting genetic algorithm, and based on the multi-source heterogeneous data collected by the data acquisition layer, realizes dynamic identification of parameters in the five-dimensional dynamic coupling model and multi-objective optimization solution. The application can be applied to a regional carbon emission management platform, can be embedded into a high-energy-consumption enterprise production system, realizes real-time optimization of energy distribution and technology investment, and can also be used for auxiliary decision-making of a carbon trading market, and provides data support for enterprise carbon quota allocation and emission reduction strategy formulation.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of carbon emission prediction, and relates to a carbon emission prediction and regulation system and method based on multi-scale dynamic optimization. BACKGROUND

[0002] Current carbon emission prediction and regulation technology mainly relies on single-scale static models and extensive regulation strategies. Traditional methods use a single time-space scale analysis framework (such as annual time scale or provincial space scale), which can only process data in a specific dimension in isolation and is difficult to capture the multi-scale dynamic coupling evolution characteristics (such as the interactive influence of short-term climate fluctuations and long-term industrial upgrading) from minutes to years and from parks to countries, resulting in prediction results that cannot reflect the true dynamics of the system.

[0003] In terms of nonlinear mechanism modeling, existing technologies (such as traditional regression models and simple time series analysis) can only handle linear or weakly nonlinear relationships, and are insufficient in describing complex nonlinear characteristics such as diminishing marginal effects of technological progress and delayed industrial correlation transmission, resulting in weak model generalization ability and prediction accuracy that cannot meet the regulation requirements. In terms of spatio-temporal adaptability, existing strategies ignore differences in regional industrial structure, energy endowment, and climate conditions, and use fixed proportion energy structure adjustment and unified intensity emission reduction targets, which cannot dynamically adapt to the characteristics of different scenarios such as high-energy consumption parks and clean energy bases, resulting in significant spatial deviations in the implementation effect of regulation schemes. In the field of multi-objective collaborative optimization, existing technologies lack a multi-objective coupling framework for economy-energy-environment, and only take a single carbon emission indicator as the optimization target without considering key factors such as GDP growth rate, energy transformation cost, and technology investment benefit, resulting in emission reduction strategies often at the expense of economic growth, making it difficult to achieve the Pareto optimal balance of carbon emission peak control, peak time optimization, and economic cost.

[0004] That is, the existing carbon emission prediction technology field has the following defects and deficiencies:

[0005] 1. Single-scale static modeling limitations: only single time / space scale analysis is supported, which cannot reflect the dynamic changes of the system under multi-scale coupling, such as the immediate impact of short-term climate fluctuations on energy consumption and the cumulative effects of long-term industrial upgrading.

[0006] 2. Insufficient nonlinear relationship modeling: traditional regression methods cannot describe complex mechanisms such as diminishing marginal effects of technological progress and delayed industrial correlation transmission, resulting in weak model generalization ability in complex scenarios.

[0007] 3. Lack of collaborative optimization: no multi-objective optimization framework is established, which cannot simultaneously consider carbon emission peak, peak time, and economic cost, often leading to an imbalance between the economic and environmental benefits of emission reduction strategies.

[0008] 4. Poor spatio-temporal adaptability: ignoring regional industrial structure, energy endowment, and climate condition differences, the strategy design lacks pertinence, for example, the regulation strategy of high-energy consumption park and clean energy base does not reflect the differentiation.

[0009] In summary, the existing technology is limited by single-scale isolated modeling, lack of nonlinear mechanism description, rough spatio-temporal adaptation, and lack of multi-objective coordination, which has the core bottleneck of "insufficient prediction accuracy - low regulation efficiency - unbalanced development goals", and an innovative solution is needed to build a multi-dimensional dynamic coupling, spatio-temporal differentiation adaptation, and multi-objective intelligent optimization. SUMMARY

[0010] The present application aims to overcome the shortcomings of the prior art and provide a carbon emission prediction and regulation system and method based on multi-scale dynamic optimization.

[0011] The technical solution adopted by the present application is:

[0012] A carbon emission prediction and regulation system based on multi-scale dynamic optimization, comprising

[0013] a data acquisition layer, a five-dimensional coupling model layer, and an optimization and regulation layer; wherein:

[0014] The data acquisition layer acquires multi-source heterogeneous data in real time by deploying an Internet of Things sensor network.

[0015] The five-dimensional coupling model layer has a five-dimensional dynamic coupling model, including a multi-scale carbon emission dynamics equation, an industrial correlation network model, a spatio-temporal coupling prediction model, and a dynamic optimization control model, which realizes deep fusion modeling of multi-dimensional data.

[0016] The optimization and regulation layer integrates improved particle swarm optimization (IPSO) algorithm and non-dominated sorting genetic algorithm (NSGA-III), and based on the multi-source heterogeneous data collected by the data acquisition layer, realizes dynamic identification of parameters in the five-dimensional dynamic coupling model and multi-objective optimization solution.

[0017] In the above technical solution, further, the multi-source heterogeneous data includes product category energy data, including economic indicators such as GDP growth rate and industrial output value, and environmental parameters such as climate factors and carbon emission monitoring data.

[0018] Further, the system further comprises a decision support layer, which generates a visual regulation strategy based on the solution results of the optimization and regulation layer, provides an interactive decision interface, and supports the customization needs of users at different levels.

[0019] Further, the five-dimensional dynamic coupling model is firstly to calculate the carbon emission intensity of each industry through the industry correlation network model, which uses the industry correlation matrix to track the carbon emission transfer between industries, and introduces the Gaussian term to capture the short-term effect of policy intervention; the industry emission data is used as input to drive the multi-scale carbon emission dynamics equation, which integrates four factors of energy consumption, economic growth, technology emission reduction and climate impact to generate the time series of cumulative carbon emissions;

[0020] The cumulative carbon emissions are then input into the spatio-temporal coupling prediction model, which combines the spatial diffusion equation and the source-sink dynamic function to quantitatively measure the influence of geographical factors on carbon emission propagation, and finally outputs the carbon emission concentration distribution of different regional grids in the future; these prediction results are captured by the dynamic optimization control model, which solves the optimal combination of energy structure adjustment rate, industrial upgrading rate and technology investment intensity under the constraints of system dynamics equation, policy boundary and emission reduction target, so as to minimize the sum of long-term emission penalty and regulation cost;

[0021] The optimization generated regulation instructions are fed back to the industry correlation network in real time, by adjusting the carbon emission transfer coefficient and the benchmark emission intensity between industries, forming a closed loop, and the whole process continues to iterate, ensuring the economic and reliable emission reduction path under the influence of climate change and policy disturbance.

[0022] Further, the industry correlation network model is specifically: based on the carbon emission transfer relationship between industries, an association matrix is established, the emission intensity between industries is quantified through the carbon emission conduction equation, and a Gaussian function is introduced to simulate the short-term effect of policy intervention, thereby generating dynamic industry emission source intensity data.

[0023] Further, the multi-scale carbon emission dynamics equation couples energy consumption, economic growth, technology emission reduction and climate impact to obtain the cumulative carbon emissions in time dimension, specifically:

[0024]

[0025] Wherein: represents the cumulative carbon emissions at time t (ten thousand tons), represents the energy consumption of the i-th type (ten thousand tons of standard coal), represents the GDP growth rate (%), represents the emission reduction technology index (0-1), represents the climate impact factor, represents the dynamic coupling coefficient.

[0026] Further, the spatio-temporal coupling prediction model discretizes the geographical area into a grid, quantifies the spatial propagation characteristics of carbon emissions by using a diffusion coefficient, and generates a three-dimensional distribution map of carbon emission concentration in the future period by combining a source-sink dynamic function, wherein the source-sink dynamic function is composed of an emission source term for representing carbon emission intensity in the region, a carbon sink absorption term for quantifying the absorption of carbon by natural or artificial systems, and an economic activity modulation term for reflecting the spatio-temporal modulation effect of economic activities on emissions.

[0027] Further, the dynamic optimization control model aims to minimize emission penalty cost and regulation economic cost, and solves an optimal regulation scheme, including a real-time combination strategy of energy structure adjustment rate, industrial upgrading rate and technology investment intensity, under the premise of meeting system dynamics constraints, policy boundary conditions and initial emission state.

[0028] Further, the improved particle swarm optimization (IPSO) algorithm adds a gradient term in the particle swarm optimization algorithm to guide the particles to move in the direction where the fitness function decreases fastest, so as to perform more fine search in the local area.

[0029] The application also provides a carbon emission prediction and regulation method based on multi-scale dynamic optimization, which constructs a five-dimensional dynamic coupling model in the system according to any one of the above and optimizes and solves the model.

[0030] The application also provides an electronic device, which comprises:

[0031] one or more processors;

[0032] a memory for storing one or more programs;

[0033] When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of the above.

[0034] A computer readable storage medium storing computer executable instructions, the instructions being executed to implement the method according to any one of the above.

[0035] Compared with the prior art, the application has the following beneficial effects:

[0036] The application firstly integrates time, space, industry, energy and technology dimensions, constructs a multi-scale dynamic equation and a space-time diffusion model, realizes multi-scale carbon emission prediction through five-dimensional dynamic coupling modeling, and realizes multi-scale carbon emission prediction by combining the IPSO method with the gradient guiding term and the parameter identification and multi-objective optimization of NSGA-III. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 It is a structural block diagram of the system of the application. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the specific embodiments of the application will be described in detail below in combination with the drawings. In the following description, a large number of specific details are set forth in order to facilitate a full understanding of the application. However, the application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the application, so the application is not limited by the specific embodiments disclosed below. The technical features in each embodiment of the application can be combined accordingly without conflict.

[0039] The application provides a carbon emission prediction and regulation system based on multi-scale dynamic optimization. According to a specific embodiment of the application, the system adopts a four-layer five-dimensional modeling framework:

[0040] The four-layer technical architecture is adopted, including a data acquisition layer, a five-dimensional dynamic model layer, an optimization and regulation layer, and a decision support layer. Specifically:

[0041] The data acquisition layer: deploy an Internet of Things sensor network to collect multi-source heterogeneous data such as energy consumption (classified energy data), economic indicators (GDP growth rate, industrial output value), environmental parameters (climate factors, carbon emission monitoring data) and the like in real time, and support minute-level data update.

[0042] The five-dimensional dynamic model layer: a five-dimensional dynamic coupling model is constructed, including a multi-scale carbon emission dynamics equation, an industry correlation network model, a space-time coupling prediction model and a dynamic optimization control model, realizing deep fusion modeling of multi-dimensional data.

[0043] The optimization and regulation layer: the improved particle swarm optimization (IPSO) algorithm and the non-dominated sorting genetic algorithm (NSGA-III) are integrated to realize dynamic identification of model parameters and multi-objective optimization solution, and support real-time iterative optimization of strategies.

[0044] Decision support layer: based on the results, generate visual control strategies, provide interactive decision-making interfaces, and support the customized needs of users at different levels (government, enterprises, and parks).

[0045] The five-dimensional coupling modeling system (time dimension, space dimension, industry dimension, energy dimension, and technology dimension) in the application innovatively integrates five dimensions of time (minutes to years), space (parks to countries), industry (industry classification), energy (energy category), and technology (emission reduction technology index), constructs a multi-scale coupling model, and realizes dynamic simulation of carbon emissions from micro-enterprises to macro-regions.

[0046] 1. Industry correlation network model

[0047] Based on the carbon emission transfer relationship between industries, a correlation matrix is established, and the industry correlation matrix is defined as follows:

[0048]

[0049] Wherein the element is the ratio of carbon emission transfer from industry i to j to the total carbon emission output of industry i, which represents the proportion of carbon emission transfer from industry i to industry j, that is:

[0050]

[0051] The emission intensity between industries is quantified by a carbon emission conduction equation, and a Gaussian function is introduced to simulate the short-term effect of policy intervention, thereby generating dynamic industry emission source intensity data, wherein the carbon emission conduction equation is:

[0052]

[0053] In the formula, is the total input carbon flow of industry i, is the output carbon flow of industry j, is the baseline emission intensity of industry j, that is, the carbon emission per unit output without intervention, is a Gaussian term, which represents the short-term impact of the policy (such as production limit order) introduced at time t0, controls the duration of the impact.

[0054] After deducting the carbon emissions transferred to the downstream, the net emission amount generated by the production activities of the industry itself is the emission source intensity.

[0055] 2. Multi-scale carbon emission dynamics equation

[0056] Coupling energy consumption, economic growth, technology emission reduction and climate impact to construct a dynamic equation to describe the evolution mechanism of cumulative carbon emissions:

[0057]

[0058] wherein: represents the cumulative carbon emissions (million tons) at time t, represents the energy consumption of the i-th type (million tons of standard coal), represents the GDP growth rate (%), represents the emission reduction technology index (0-1), represents the climate impact factor, represents the dynamic coupling coefficient.

[0059] 3. Spatiotemporal coupling prediction model

[0060] The geographical area is discretized into a grid, and the spatial propagation characteristics of carbon emissions are quantified using a diffusion coefficient, with high-weight areas diffusing faster. The three-dimensional distribution of carbon emission concentration in the future period is generated by combining the source-sink dynamic function, accurately positioning the regional emission hotspots.

[0061] Spatial discretization:

[0062]

[0063] wherein the diffusion coefficient:

[0064]

[0065] In the formula, is the weight of the geographical grid (e.g., industrial area weight > farmland), , is the grid space step, is the spatiotemporal dimension carbon emission concentration field, wherein the source-sink dynamic function is composed of an emission source term C representing the carbon emission intensity in the region, a carbon sink absorption term E quantifying the absorption of carbon by natural or artificial systems, and an economic activity modulation term G reflecting the spatiotemporal modulation effect of economic activity on emissions.

[0066] 4. Dynamic optimization control model

[0067] The objective function is to minimize the emission penalty cost and the regulation economic cost:

[0068]

[0069] The constraint conditions are in turn the system dynamics, policy boundaries, emission reduction targets, and initial state:

[0070]

[0071] wherein the control variables: represent the energy structure adjustment rate, the industrial upgrading rate, and the technology investment intensity, respectively.

[0072] In the present application, gradient guided particle swarm, NSGA-III are used for multi-objective optimization solution, wherein the gradient guiding term is introduced into IPSO to improve the parameter identification accuracy, and NSGA-III is used to process high-dimensional multi-objective optimization problem.

[0073] The working process of the carbon emission prediction and dynamic regulation system in the present application starts from the construction of the industrial correlation network model: first, an association matrix is established based on the carbon emission transfer relationship between industries, the emission intensity between industries is quantified through the carbon emission transmission equation, and a Gaussian function is introduced to simulate the short-term effect of policy intervention, thereby generating dynamic industrial emission source intensity data. These emission data are immediately input into the multi-scale carbon emission dynamics equation, which synchronously integrates the economic growth rate, the emission reduction technology index and the climate impact factor, and calculates the evolution trend of cumulative carbon emissions through dynamic coupling coefficients.

[0074] The obtained cumulative carbon emissions immediately drive the spatio-temporal coupling prediction model: the system discretizes the geographical area into grids, quantifies the spatial propagation characteristics of carbon emissions (industrial areas, transportation hubs and other high-weight areas diffuse faster) using diffusion equation, and generates a three-dimensional distribution map of carbon emission concentration in the future period by combining the source-sink dynamic function, accurately locating the regional emission hotspots. The prediction results immediately trigger the dynamic optimization control model, which aims to minimize the "emission penalty cost" and "regulation economic cost", and solves the optimal control instruction - including the real-time combination strategy of energy structure adjustment rate, industrial upgrading rate and technology investment intensity, under the premise of meeting the system dynamics constraints, policy boundary conditions and initial emission state.

[0075] Finally, these control instructions are fed back to the industrial correlation network: by adjusting the carbon emission transfer coefficient between industries, reducing the weight of high-energy-consuming industries or improving the correlation strength of clean technology industries, the emission transmission path is reconstructed, and the industrial emission source intensity data is updated.

[0076] The whole system forms a continuous iterative closed loop of "industrial network → dynamic equation → spatio-temporal prediction → optimization and regulation → industrial network", which dynamically maintains the economy and sustainability of the emission reduction path under the disturbance of climate change and policy.

[0077] Take a certain industrial park in a certain province in 2025 as an example for prediction and carbon regulation, wherein the system deployment is as follows:

[0078] Internet of Things monitoring nodes: 50, covering main energy-consuming equipment in the park; data acquisition frequency: 1Hz (real-time monitoring of energy consumption and emission data); model update period: 1 hour (edge nodes process data in real time, and cloud optimizes model parameters regularly); strategy adjustment period: 24 hours (generate optimal control scheme every day).

[0079] After optimization and regulation by the scheme of the application, through energy structure adjustment, the proportion of renewable energy is improved, combined with technology investment and industry upgrading, the emission intensity per unit of output value is reduced, and the energy distribution is intelligently regulated and optimized, the equipment downtime is reduced, and the carbon emission reduction, production efficiency improvement and energy consumption reduction are realized.

[0080] Those skilled in the art will appreciate that embodiments of the application can be supplied as methods, systems, or computer program products. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be embodied in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) having computer usable program code embodied therein.

[0081] The application is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by the flow or flows and / or block or blocks.

[0082] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions means that implement the function specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by the flow or flows and / or block or blocks.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by the flow or flows and / or block or blocks.

[0084] The above-described embodiments have described the technical solutions and beneficial effects of the present application in detail, and it should be understood that the above-described is only a specific embodiment of the present application and is not intended to limit the present application, and any modification, supplement and equivalent replacement made within the principle range of the present application should be included in the protection range of the present application.

Claims

1. A carbon emission prediction and regulation system based on multi-scale dynamic optimization, characterized in that, The system comprises a data acquisition layer, a five-dimensional coupling model layer and an optimization control layer. The data acquisition layer acquires multi-source heterogeneous data in real time by deploying an Internet of Things sensor network. The five-dimensional coupling model layer comprises a five-dimensional dynamic coupling model, wherein the five dimensions are time, space, industry, energy and technology, and the five-dimensional dynamic coupling model comprises a multi-scale carbon emission kinetics equation, an industry correlation network model, a time-space coupling prediction model and a dynamic optimization control model, and realizes deep fusion modeling of multi-dimensional data. Specifically, the carbon emission intensity of each industry is calculated by the industry correlation network model, the model traces the carbon emission transfer between industries by using an industry correlation matrix, and a Gaussian term is introduced to capture the short-term effect of policy intervention; the industry emission data is taken as input to drive the multi-scale carbon emission kinetics equation, which comprehensively considers four factors, i.e., energy consumption, economic growth, technology emission reduction and climate impact, to generate a time series of cumulative carbon emissions; The cumulative carbon emissions are then input into the time-space coupling prediction model, which combines a spatial diffusion equation and a source-sink dynamic function to quantitatively reflect the influence of geographical factors on carbon emission propagation, and finally outputs the carbon emission concentration distribution of different regional grids in the future; the prediction results are captured by the dynamic optimization control model, which solves the optimal combination of energy structure adjustment rate, industrial upgrading rate and technology investment intensity under the constraints of system dynamics equation, policy boundary and emission reduction target, so as to minimize the sum of long-term emission penalty and control cost; The optimization-generated control instructions are fed back to the industry correlation network in real time, the carbon emission transfer coefficient and the baseline emission intensity between industries are adjusted to form a closed loop, and the whole process is continuously iterated to ensure the economy and reliability of the emission reduction path under climate change and policy disturbance; The IPSO algorithm and the NSGA-III algorithm are integrated in the optimization control layer to realize dynamic identification of parameters and multi-objective optimization solution in the five-dimensional dynamic coupling model based on the multi-source heterogeneous data collected by the data acquisition layer.

2. The multi-scale dynamic optimization based carbon emission prediction and regulation system according to claim 1, wherein, The multi-source heterogeneous data comprises product category energy data, economic indicators such as GDP growth rate and industrial output value, and environmental parameters such as climate factors and carbon emission monitoring data.

3. The multi-scale dynamic optimization based carbon emission prediction and regulation system of claim 1, wherein, The system further comprises a decision support layer, which generates a visual control strategy based on the solution results of the optimization control layer, provides an interactive decision interface, and supports customized needs of users at different levels.

4. The multi-scale dynamic optimization based carbon emission prediction and regulation system of claim 1, wherein, The industry correlation network model specifically comprises: establishing a correlation matrix based on the carbon emission transfer relationship between industries, quantifying the emission intensity between industries by a carbon emission transmission equation, and introducing a Gaussian function to simulate the short-term effect of policy intervention, thereby generating dynamic industry emission source intensity data.

5. The multi-scale dynamic optimization based carbon emission prediction and regulation system of claim 1, wherein, The multi-scale carbon emission kinetics equation couples energy consumption, economic growth, technology emission reduction and climate impact to obtain time-dimension cumulative carbon emissions, specifically as follows: ， Wherein: represents the cumulative carbon emissions at time t, represents the energy consumption of the i-th type, represents the GDP growth rate, represents the emission reduction technology index, represents the climate impact factor, represents the dynamic coupling coefficient.

6. The multi-scale dynamic optimization based carbon emission prediction and regulation system of claim 1, wherein, The spatio-temporal coupling prediction model discretizes a geographical area into a grid, quantifies the spatial propagation characteristics of carbon emissions by using a diffusion coefficient, and generates a three-dimensional distribution map of carbon emission concentration in a future period by combining a source-sink dynamic function, wherein the source-sink dynamic function is composed of an emission source term for representing carbon emission intensity in the area, a carbon sink absorption term for quantifying the absorption of carbon by natural or artificial systems, and an economic activity modulation term for reflecting the spatio-temporal modulation effect of economic activities on emissions.

7. The multi-scale dynamic optimization based carbon emission prediction and regulation system of claim 1, wherein, The dynamic optimization control model aims to minimize emission penalty cost and regulation economic cost, and solves an optimal regulation scheme, including a real-time combination strategy of energy structure adjustment rate, industrial upgrading rate and technology investment intensity, under the premise of meeting system dynamics constraints, policy boundary conditions and initial emission state.

8. The multi-scale dynamic optimization based carbon emission prediction and regulation system of claim 1, wherein, The improved particle swarm optimization (IPSO) algorithm adds a gradient term to the particle swarm optimization algorithm to guide particles to move in the direction where the fitness function decreases fastest, thereby performing more fine search in a local area.

9. A method for carbon emission prediction and regulation based on multi-scale dynamic optimization, characterized in that, A five-dimensional dynamic coupling model in the system of any one of claims 1-8 is constructed and optimized. A five-dimensional dynamic coupling model in the system of any one of claims 1-8 is constructed and optimized.

Images