Traffic industry carbon reduction method and system based on multi-Agent-SD decision model simulation

Abstract

The invention discloses a traffic industry carbon reduction method and system based on multi-Agent-SD decision model simulation, and relates to the technical field of urban traffic, and the method comprises the steps: obtaining a historical data set of the traffic industry in a to-be-researched region; processing the historical data set, and dividing the historical data set into a training data set and an inspection data set; constructing a multi-Agents-SD decision model, performing comparative analysis on simulation data simulated by the training data set and the test data set, and calibrating parameters of the multi-Agents-SD decision model; corresponding parameters are designed according to different development situations, the adjusted parameters are input into the multi-Agent-SD decision model for simulation, a differentiation result is obtained, and then the traffic industry carbon reduction strategy is obtained. According to the method, the advantages of the two models are combined, the multi-Agents model for exploring micro individual behavior changes and the SD model for a macroscopic complex system are combined, and a more suitable traffic carbon reduction scheme is researched from multiple angles.

Description

Technical Field

[0001] The present invention relates to the field of urban transportation technology, and more particularly to a method and system for reducing carbon emissions in the transportation industry based on multi-Agents-SD decision model simulation. Background Art

[0002] The transportation industry is one of the fastest-growing sources of carbon emissions globally. Effectively calculating the transportation industry's carbon emissions is of great significance for designing carbon reduction plans for the transportation industry and accelerating the achievement of the "dual carbon" goals. Common methods for calculating carbon emissions in the transportation industry include LCA (life cycle approach), LMDI (log mean Dirichlet index decomposition method), and fuel emission factor calculation. However, the research content of these methods is not comprehensive. For example, although the LCA method is a full-cycle calculation, its wide scope and boundary setting affect the results; LMDI considers the complexity of urban transportation and takes multiple factors into account, but it is difficult to handle changes caused by emergencies and can only be used for static research; the fuel classification method is suitable for real-time measurement of carbon emissions and cannot estimate long-term carbon emissions.

[0003] Therefore, how to provide a carbon reduction method and system for the transportation industry based on multi-agent-SD decision-making model simulation, combining the advantages of the two models, combining the multi-agent model for exploring changes in micro-individual behavior and the SD model for macro-complex systems, and studying more suitable carbon reduction solutions from multiple angles is an urgent problem that technical personnel in this field need to solve. Summary of the Invention

[0004] In view of this, the present invention provides a method and system for reducing carbon in the transportation industry based on the simulation of a multi-agents-SD decision model. Since there are certain limitations in using a multi-agents model or an SD model alone to study the entire system, urban transportation carbon emissions are not only a long-cycle and complex system, but also a system with multiple participants and multiple influences. The multi-agents model combined with the SD model can realize interaction with the outside world, simulate and study the changes in the macro-influence of decision-makers, and explore the carbon reduction plan for the transportation industry from the overall perspective of the system. Therefore, the present invention combines the advantages of the two models, combines the multi-agents model for exploring changes in micro-individual behavior with the SD model for macro-complex systems, establishes a multi-agents-SD decision model, realizes a holistic study of carbon reduction in the transportation industry, and puts forward more detailed suggestions for achieving the carbon reduction goals of the transportation industry as soon as possible.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a method for reducing carbon emissions in the transportation industry based on multi-agents-SD decision model simulation, comprising:

[0006] Determine the spatiotemporal scope of the area to be studied, and obtain a historical data set of the transportation industry in the area to be studied;

[0007] Processing the historical data set and dividing it into a training data set and a test data set;

[0008] Constructing a multi-agents-SD decision model, performing comparative analysis using simulated data from the training data set and the test data set, and calibrating parameters of the multi-agents-SD decision model;

[0009] Design corresponding parameters according to different development scenarios, input the adjusted parameters into the multi-agents-SD decision model for simulation, and obtain differentiated results;

[0010] Based on the differentiated results, a carbon reduction strategy for the transportation industry is obtained.

[0011] Preferably, the multi-agents-SD decision model includes a multi-agents section and a SD section;

[0012] The multi-agents module is used to simulate the behavior and decision-making of micro-agents;

[0013] The SD block is used to calculate the total annual carbon emissions at a macro level.

[0014] Preferably, the multi-agents section includes a single agent and a group agent; the policy of the single agent guides the behavior of the group agent, and the behavior of the group agent provides feedback to the policy of the single agent.

[0015] Preferably, the SD sector includes a socio-economic subsystem, an environmental subsystem, an energy subsystem, and a transportation subsystem, and there are causal loops and positive and negative feedback relationships between the subsystems.

[0016] Preferably, the calculation formula for the total annual carbon emissions of the transportation industry is:

[0017] C t =∑(E j ×T j ×I×F i );

[0018] Where, t is the year; C t represents the total carbon emissions in year t, j represents different car models; i represents the different energy types corresponding to car j; F i refers to the carbon emission factor of energy i; E j Refers to the unit energy consumption of vehicle type j, T j It refers to the travel volume of vehicle j, and I refers to the standard coal conversion coefficient of energy i.

[0019] Preferably, the development scenarios include a status quo baseline scenario, a traditional energy suppression scenario, an economic development regulation scenario, and a transportation balanced development scenario.

[0020] Preferably, the single subject is the government, the attributes are government taxation and environmental pollution input, and the decision-making behaviors include establishing a lottery-based restriction system for motor vehicles and preferential policies for public transportation;

[0021] The group subjects are residents, the attributes are household income at different levels and group size, and the decision-making behaviors include travel mode and travel distance.

[0022] Preferably, a transportation industry carbon reduction system based on multi-agents-SD decision model simulation includes:

[0023] A data acquisition module, used to determine the spatiotemporal scope of the area to be studied and obtain a historical data set of the transportation industry in the area to be studied;

[0024] A data processing module, configured to process the historical data set and divide it into a training data set and a test data set;

[0025] A model building and calibration module is used to build a multi-agents-SD decision model, compare and analyze the simulated data of the training data set with the test data set, and calibrate the parameters of the multi-agents-SD decision model;

[0026] A simulation module, configured to design corresponding parameters according to different development scenarios, input the adjusted parameters into the multi-agents-SD decision model for simulation, and obtain differentiated results;

[0027] The result output module is used to obtain a carbon reduction strategy for the transportation industry based on the differentiation results.

[0028] Through the above technical solutions, it can be seen that compared with the existing technology, the present invention discloses a method and system for reducing carbon in the transportation industry based on the simulation of a multi-agents-SD decision model, including: determining the spatiotemporal scope of the area to be studied, obtaining a historical data set of the transportation industry in the area to be studied; processing the historical data set and dividing it into a training data set and a test data set; constructing a multi-agents-SD decision model, using the simulated data of the training data set to compare and analyze with the test data set, and calibrating the parameters of the multi-agents-SD decision model; designing corresponding parameters according to different development scenarios, inputting the adjusted parameters into the multi-agents-SD decision model for simulation, and obtaining differentiated results; based on the differentiated results, obtaining a carbon reduction strategy for the transportation industry. The present invention combines the advantages of the two models, combining the multi-agents model for exploring changes in micro-individual behavior with the SD model for macro-complex systems, and studying more suitable carbon reduction solutions from multiple angles. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0030] Figure 1 A schematic flow chart of a method for reducing carbon emissions in the transportation industry based on a multi-Agents-SD decision model simulation according to an embodiment of the present invention;

[0031] Figure 2 A schematic diagram of the connection relationship of the multi-Agents-SD decision model provided by an embodiment of the present invention;

[0032] Figure 3 Schematic diagram of different development scenario designs provided by the embodiments of the present invention. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] The embodiment of the present invention discloses a method for reducing carbon emissions in the transportation industry based on a multi-agents-SD decision model simulation, comprising:

[0035] Determine the spatiotemporal scope of the area to be studied, and obtain a historical data set of the transportation industry in the area to be studied;

[0036] Processing the historical data set and dividing it into a training data set and a test data set;

[0037] Constructing a multi-agents-SD decision model, performing comparative analysis using simulated data from the training data set and the test data set, and calibrating parameters of the multi-agents-SD decision model;

[0038] Design corresponding parameters according to different development scenarios, input the adjusted parameters into the multi-agents-SD decision model for simulation, and obtain differentiated results;

[0039] Based on the differentiated results, a carbon reduction strategy for the transportation industry is obtained.

[0040] Specifically, such as Figure 1As shown in the figure, a) determine the spatiotemporal scope of the target city and obtain a historical data set for the transportation industry within this scope. The 10-year historical data of the study area is used as the training data set, and the following 5 years of historical data is used as the test data set to simulate the evolution trend over the next 30 years.

[0041] b) Process the dataset and input the relevant data into the multi-agent-SD decision-making model, completing the model parameter settings, including initial values and weights. Use the 10-year historical data as the training dataset, then simulate the next five years of data with the five-year historical data as the test dataset for error analysis. Based on the error, verify the accuracy of the model, including the accuracy of relevant parameters in the multi-agent and SD segments. Continue adjusting parameters to establish a highly credible and scientifically sound multi-agent-SD decision-making model.

[0042] c) Design corresponding parameters for the four development scenarios: the status quo baseline scenario, the traditional energy suppression scenario, the economic development regulation scenario, and the transportation balanced development scenario. Input the adjusted parameters into the multi-agents-SD decision model simulation to obtain differentiated results, focusing on parameters with high sensitivity.

[0043] d) Analyze simulation results from different development scenarios and highly sensitive parameters. Based on these differentiated simulation results and highly sensitive parameters, policy design can focus on limiting or incentivizing the growth of these parameters. This allows recommendations tailored to the carbon reduction development of the transportation sector from the perspectives of government decision-makers, resident decision-makers, and macro-societal development, enabling a holistic and multi-faceted design of a carbon reduction plan for the transportation sector and contributing to low-carbon development in society.

[0044] Specifically, the multi-agents-SD decision model includes a multi-agents section and a SD section;

[0045] The multi-agents module is used to simulate the behavior and decision-making of micro-agents;

[0046] The SD block is used to calculate the total annual carbon emissions.

[0047] Based on the micro-agent behavior decision-making, the SD section and the multi-agent section cooperate with each other to obtain the carbon emissions of the transportation industry from both micro and macro levels.

[0048] Specifically, the multi-agent module includes single agents and group agents. The policies of the single agent guide the behavior of the group agent, and the behavior of the group agent provides feedback to the policies of the single agent. The decision-making behaviors of the single agent and the group agent influence each other.

[0049] Specifically, the development scenarios include a status quo baseline scenario, a traditional energy suppression scenario, an economic development regulation scenario, and a transportation balanced development scenario.

[0050] Specifically, such as Figure 3 As shown in the figure, four different development scenarios were designed.

[0051] Maintaining the status quo baseline scenario: Keeping all parameters unchanged, this serves as the basic scenario for comparison.

[0052] Traditional energy suppression scenario: Increased subsidies for new energy vehicles, reduced gasoline vehicle turnover, and increased investment in transportation and environmental protection are intended to suppress the use of traditional energy.

[0053] Economic development regulation scenario: increase in per capita GDP, increase in electric locomotive turnover, increase in consumption of various types of energy, etc., focusing on the impact of economic development on transportation and energy-related parameters.

[0054] Balanced transportation development scenario: Increased travel volume across all modes of transportation, increased turnover of new energy vehicles, and increased preferential policies for public transportation reflect balanced development in all aspects of the transportation sector.

[0055] First, the corresponding parameters are adjusted according to different development scenarios, and then the adjusted parameters are input into the multi-agents-SD decision-making model. Finally, simulation is carried out to study the development of the transportation industry under different development scenarios and provide a reference for carbon reduction plans.

[0056] Specifically, the single subject is the government, its attributes are government taxation and environmental pollution input, and its decision-making behaviors include establishing a lottery-based restriction system for motor vehicles and preferential policies for public transportation;

[0057] The group subjects are residents, the attributes are household income at different levels and group size, and the decision-making behaviors include travel mode and travel distance.

[0058] Specifically, such as Figure 2 As shown, the government agent in the multi-agent section is a single entity, with attributes representing government tax revenue and environmental pollution input. Its decision-making behaviors include establishing a lottery-based vehicle restriction system and preferential public transportation policies. When government tax revenue is low and environmental pollution is severe, it may implement strict vehicle restrictions; when government tax revenue is high and environmental protection is important, it may implement preferential public transportation policies; and when government tax revenue is high and environmental pollution is severe, it may implement both policies simultaneously. The resident agent is a group combination, not a single entity. Its attributes represent household income levels and group size. Its decision-making behaviors include travel mode and travel distance. Residents of different income levels will choose different travel modes based on their circumstances and travel distance. For example, a middle-income resident may choose a new energy vehicle with preferential rates to travel to a more distant destination.

[0059] Specifically, the SD sector includes the socioeconomic, environmental, energy, and transportation subsystems. The energy subsystem's standard coal conversion coefficients for different energy sources, the environmental subsystem's carbon emission factors for different energy sources, and the transportation subsystem's variables, such as vehicle distance traveled and vehicle turnover, interact to influence urban transportation carbon emissions, with the socioeconomic subsystem also playing a role. Causal loops and positive and negative feedback relationships exist between these subsystems.

[0060] Specifically, the behavioral decisions of government agents (e.g., those formulating vehicle lottery restrictions and public transportation preferential policies) and resident agents (e.g., those choosing travel modes and distances) in the multi-agent model will interact with the variables of each subsystem of the SD model. For example, government policies will alter parameters such as vehicle turnover in the transportation subsystem, while resident travel choices will affect variables such as energy consumption. Conversely, changes in the variables of the SD subsystem may also affect the behavioral decisions of the agents.

[0061] Specifically, key parameters for the socioeconomic subsystem within the SD sector include population, urbanization rate, per capita GDP, environmental pollution losses, transportation and environmental protection investment, and subsidies for new energy vehicles. Key parameters for the environmental subsystem include annual total carbon emissions, annual carbon reductions, annual carbon gains, CO2 emission intensity, carbon tax, CO2 governance coefficient, and carbon emission factors for gasoline, diesel, kerosene, natural gas, electricity, and new energy sources. Key parameters for the energy subsystem include unit energy consumption, total energy consumption, and energy efficiency for gasoline, diesel, internal combustion locomotives, civil aircraft, new energy vehicles, natural gas vehicles, and electric locomotives, as well as standard coal conversion coefficients for gasoline, diesel, kerosene, natural gas, electricity, and new energy sources. Key parameters for the transportation subsystem include driving distance, turnover, and vehicle ownership for gasoline, diesel, internal combustion locomotives, civil aircraft, new energy vehicles, natural gas vehicles, and electric locomotives.

[0062] Specifically, the calculation formula for the total annual carbon emissions of the transportation industry in this decision model is:

[0063] C t =∑(E j ×T j ×I×F i );

[0064] Where t is the year; C t represents the total carbon emissions in year t, j represents different car models; i represents the different energy types corresponding to car j; F i refers to the carbon emission factor of energy i; E j Refers to the unit energy consumption of vehicle type j, in tons / 100 million passenger kilometers; T jrefers to the travel volume of vehicle j, in units of 100 kilometers; I refers to the standard coal conversion coefficient of energy i, with electricity in kgce / (kw·h) and natural gas in kgce / m 3 , other units are kgce / kg.

[0065] In a specific embodiment of the present invention, a transportation industry carbon reduction system based on multi-agents-SD decision model simulation includes:

[0066] A data acquisition module, used to determine the spatiotemporal scope of the area to be studied and obtain a historical data set of the transportation industry in the area to be studied;

[0067] A data processing module, configured to process the historical data set and divide it into a training data set and a test data set;

[0068] A model building and calibration module is used to build a multi-agents-SD decision model, compare and analyze the simulated data of the training data set with the test data set, and calibrate the parameters of the multi-agents-SD decision model;

[0069] A simulation module, configured to design corresponding parameters according to different development scenarios, input the adjusted parameters into the multi-agents-SD decision model for simulation, and obtain differentiated results;

[0070] The result output module is used to obtain a carbon reduction strategy for the transportation industry based on the differentiation results.

[0071] In a specific embodiment of the present invention, the transportation industry is one of the fastest growing sources of carbon emissions in the world. Effectively calculating the carbon emissions of the transportation industry is of great significance for designing carbon reduction plans for the transportation industry.

[0072] Emission reduction in the transportation sector is a key component of the dual carbon goals. This embodiment of the present invention quantifies the impact of economic influences, policy adjustments, and resident decision-making on transportation sector carbon emissions into carbon emissions calculations, integrating dynamic and static perspectives, as well as macro and micro perspectives, for a more holistic accounting of transportation sector carbon emissions. By setting up multiple development scenarios and comparing and analyzing simulation results from a multi-agent-SD decision-making model, we explore multiple perspectives to identify the most appropriate transportation sector carbon reduction solutions, helping to address this issue.

[0073] Multi-agent models, which can use agents with diverse attributes and behaviors, simulate the decision-making of micro-agents to study emergent group phenomena. These models are often used to study emergency management responses to social issues, such as the spread of infectious diseases and the evacuation of people in disaster situations. In the transportation industry, some researchers have constructed transportation logistics systems comprised of multiple agents, including shippers, consignees, and carriers, to evaluate the impact of different logistics and transportation policies on logistics patterns and efficiency. Others have constructed emergency models for urban rail transit under high passenger flow scenarios based on both human-vehicle and human-human interactions. However, multi-agent models are limited to the behavior of micro-agents and lack external connections.

[0074] The SD model is a common method used to study complex dynamic systems at the macro level over long periods of time, such as urban resource management, population forecasting, and the long-term evolution of land use patterns. In the transportation industry, the SD model can be used to study the evolution of freight demand, the impact of freight weight restrictions and other control measures on the social benefits of cities, and the growth forecast of demand for new energy vehicles. Some scholars have also used this method to predict the number of private cars in cities and simulate the effects of license plate restrictions on alleviating traffic congestion. However, using the SD model alone to study carbon emissions lacks the ability to account for changes caused by human decision-making or other interactive behaviors, and tends to focus on the macro-theoretical analysis of transportation industry development.

[0075] The multi-agent-SD decision model in the embodiment of the present invention calculates the carbon emissions of the transportation industry (divided by energy consumption type) in the following categories: gasoline vehicles, diesel vehicles, internal combustion locomotives, new energy vehicles, natural gas vehicles, electric locomotives, and civil aircraft. Only the commonly used modes of transportation in cities are considered, excluding waterways, and non-road mobile machinery is also not included. The multi-agent section in this decision model includes government agents and resident agents. The government and residents produce different decision-making results due to changes in their own attributes. The SD section includes the socio-economic subsystem, the environmental subsystem, the energy subsystem, and the transportation subsystem. There is a strong correlation between transportation and socio-economy, transportation and environment, and transportation and energy, which satisfies the causal loop and positive and negative feedback relationship of the SD section.

[0076] In one specific embodiment of the present invention, when studying carbon emission reduction in a region's transportation sector, the temporal and spatial scope of the study area is first determined. For example, simulating 30 years of change is used to obtain data for a multi-agent-SD decision-making model within this temporal and spatial scope. Ten years of historical data are input into the model as a training dataset, and the following five years of historical data are used as a test dataset. The five-year simulated dataset generated by simulating the training dataset is compared with the test dataset, and parameters with significant deviations are adjusted to make the model results more reliable, thereby completing the adaptation of the multi-agent-SD decision-making model to the study area.

[0077] Different development scenarios are set based on multi-agent behavior and SD parameters. Using a bias-adjusted multi-agent-SD decision-making model, all parameters remain unchanged, and evolutionary trends over the next 30 years are simulated. This is the status quo baseline scenario. When environmental pressures are severe, the government implements corresponding measures, and residents also respond to policy changes, leading to corresponding adjustments in the affected SD parameters. This includes increased environmental pollution losses, increased investment in transportation and environmental protection, increased subsidies for new energy vehicles, increased turnover of new energy vehicles, and decreased turnover of gasoline vehicles. This is the traditional energy suppression scenario. When socioeconomic pressures are severe, the government and residents adjust their measures, leading to corresponding adjustments in the affected SD parameters. This includes reduced investment in transportation and environmental protection, reduced subsidies for new energy vehicles, increased consumption of traditional energy, and increased turnover of electric locomotives. This is the economic development regulation scenario. When economic development is favorable and new energy is rapidly developing, the population size of residents changes, and the affected SD parameters also change. This includes increased travel by various modes of transportation, increased subsidies for new energy vehicles, and greater public transportation discounts. This is the transportation balanced development scenario. Simulating different development scenarios is achieved by adjusting the parameters of the multi-agent-SD decision-making model.

[0078] By comparing the simulation results of different development scenarios, we explore the important parameters that have a high sensitivity to carbon reduction in the transportation industry, design plans to promote carbon emission reduction in the transportation industry under different circumstances, and put forward suggestions suitable for carbon reduction development in the transportation industry from different perspectives for government decision-makers, residents' decision-makers, and macro-social development.

[0079] The embodiments of the present invention can simulate and study the evolution trend of carbon emissions in the urban transportation industry based on the existing parameter values; modify the parameters of the decision-making model based on existing historical data to make suggestions for promoting the low-carbonization of urban transportation; take practical measures based on the changing trends and suggestions to reduce carbon emissions in the transportation industry and improve the level of green development of urban transportation; and provide methodological support for alleviating similar urban problems.

[0080] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0081] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one 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 present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for reducing carbon emissions in the transportation industry based on multi-agents-SD decision model simulation, characterized by: include: Determine the spatiotemporal scope of the area to be studied, and obtain a historical data set of the transportation industry in the area to be studied; Processing the historical data set and dividing it into a training data set and a test data set; Constructing a multi-agents-SD decision model, performing comparative analysis using simulated data from the training data set and the test data set, and calibrating parameters of the multi-agents-SD decision model; Design corresponding parameters according to different development scenarios, input the adjusted parameters into the multi-agents-SD decision model for simulation, and obtain differentiated results; Based on the differentiated results, a carbon reduction strategy for the transportation industry is obtained.

2. The method for reducing carbon emissions in the transportation industry based on multi-agents-SD decision model simulation according to claim 1 is characterized in that: The multi-agents-SD decision model includes a multi-agents section and a SD section; The multi-agents module is used to simulate the behavior and decision-making of micro-agents; The SD block is used to calculate the total annual carbon emissions at a macro level.

3. The method for reducing carbon emissions in the transportation industry based on multi-agents-SD decision model simulation according to claim 2 is characterized in that: The multi-agents section includes single agents and group agents; the policies of single agents guide the behavior of group agents, and the behavior of group agents provides feedback to the policies of single agents.

4. The method for reducing carbon emissions in the transportation industry based on multi-agents-SD decision model simulation according to claim 2 is characterized in that: The SD sector includes the socio-economic subsystem, the environmental subsystem, the energy subsystem, and the transportation subsystem. There are causal loops and positive and negative feedback relationships between the subsystems.

5. The method for reducing carbon emissions in the transportation industry based on multi-agents-SD decision model simulation according to claim 2 is characterized in that: The calculation formula for the total annual carbon emissions of the transportation industry is: C t =∑(E j ×T j ×I×F i ); Where t is the year; C t represents the total carbon emissions in year t, j represents different car models; i represents the different energy types corresponding to car j; F i refers to the carbon emission factor of energy i; E j Refers to the unit energy consumption of vehicle type j, T j It refers to the travel volume of vehicle j, and I refers to the standard coal conversion coefficient of energy i.

6. The method for reducing carbon emissions in the transportation industry based on multi-agents-SD decision model simulation according to claim 1, characterized in that: The development scenarios include a status quo baseline scenario, a traditional energy suppression scenario, an economic development regulation scenario, and a transportation balanced development scenario.

7. The method for reducing carbon emissions in the transportation industry based on multi-agents-SD decision model simulation according to claim 3 is characterized in that: The single entity is the government, its attributes are government taxation and environmental pollution input, and its decision-making behaviors include establishing a lottery-based restriction system for motor vehicles and preferential policies for public transportation; The group subjects are residents, the attributes are household income at different levels and group size, and the decision-making behaviors include travel mode and travel distance.

8. A transportation industry carbon reduction system based on multi-agents-SD decision model simulation, applying a transportation industry carbon reduction method based on multi-agents-SD decision model simulation according to any one of claims 1 to 7, characterized in that: include: A data acquisition module, used to determine the spatiotemporal scope of the area to be studied and obtain a historical data set of the transportation industry in the area to be studied; A data processing module, configured to process the historical data set and divide it into a training data set and a test data set; A model building and calibration module is used to build a multi-agents-SD decision model, compare and analyze the simulated data of the training data set with the test data set, and calibrate the parameters of the multi-agents-SD decision model; A simulation module, configured to design corresponding parameters according to different development scenarios, input the adjusted parameters into the multi-agents-SD decision model for simulation, and obtain differentiated results; The result output module is used to obtain a carbon reduction strategy for the transportation industry based on the differentiation results.

Images