A highway low-carbon reconstruction scheme simulation evaluation and optimization system based on reinforcement learning
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-23
- Publication Date
- 2026-08-11
AI Technical Summary
此类灯源长期处于不间断工作状态，极大的加大了能源的消耗，致使碳排放水平受到影响
[0014]1. Through the established detection unit, the vehicle flow detection module can detect the time intervals between vehicles traveling in the same direction on the highway in real time. This, combined with the vehicle flow extraction module in the optimization unit, extracts the detected time interval data. The reinforcement learning execution module optimizes the control of tunnel lighting and guide lights based on the extracted time interval data. The "enable execution" module runs the optimized control scheme to turn off tunnel lighting and guide lights when the time interval is long, while the "disable execution" module disables the optimized control scheme to keep tunnel lighting and guide lights on when the time interval is short. The prediction module estimates the time intervals based on the detected time interval data. When a vehicle approaches the tunnel, the traffic module controls the activation of tunnel lighting and guide lights based on the estimated time. This dynamically optimizes the control strategy of tunnel lighting and guide lights based on the real-time detected vehicle time intervals. When the time interval between adjacent vehicles is large, the lights are turned off promptly after the preceding vehicle leaves the tunnel and turned on in advance before the following vehicle approaches. When the vehicle spacing is small, the lights remain on after the preceding vehicle passes until the following vehicle passes smoothly, avoiding the extra energy consumption and losses caused by frequent switching of lights. This achieves refined optimization of energy consumption based on the real-time time interval between vehicles, thereby effectively reducing energy consumption and carbon emission levels.
Smart Images
Figure CN122549709A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing, and in particular to a simulation, evaluation and optimization system for low-carbon retrofitting schemes for highways based on reinforcement learning. Background Technology
[0002] Carbon emissions from highways refer to greenhouse gas emissions generated throughout the entire life cycle of highways due to energy consumption, material production, vehicle traffic, and equipment operation. This part of the emissions is an important component of carbon emissions in the transportation sector.
[0003] In highway operations, tunnel sections are often limited by traffic safety, visibility requirements, and traditional control methods, leading to the widespread use of continuous, all-weather lighting for both illumination and guidance lights. This constant operation significantly increases energy consumption and consequently impacts carbon emissions. Summary of the Invention
[0004] The purpose of this invention is to address the shortcomings of the prior art by proposing a simulation evaluation and optimization system for low-carbon retrofitting schemes of highways based on reinforcement learning.
[0005] To achieve the above objectives, the technical solution adopted by this invention is as follows: a simulation evaluation and optimization system for low-carbon retrofitting schemes of highways based on reinforcement learning, comprising a smart computing center, an output terminal of which is connected to a database, an output terminal of which is connected to an optimization unit, an output terminal of which is connected to a digital twin simulation module, an output terminal of which is connected to a scene modeling module, and an input terminal of which is connected to an evaluation unit. The database is used to collect and store the detected data, the optimization unit is used to optimize and retrofit based on the detected data, the scene modeling module is used to construct basic models such as tunnel lighting and roads, the digital twin simulation module is used to simulate the operation of the basic model according to the optimization scheme, and the evaluation unit is used to evaluate the energy consumption during the simulation operation.
[0006] Preferably, the input end of the database is connected to a data acquisition module, the input end of the data acquisition module is connected to a data communication module, the input end of the data communication module is connected to a detection unit, the detection unit is used to detect road segments in a real-world scenario, the data communication module is used to transmit the detected data, and the data acquisition module is used to acquire the detected data.
[0007] Preferably, the input end of the database is also connected to a data protection module, which is used to protect the data in the database.
[0008] Preferably, the detection unit includes a power detection module and a traffic flow detection module. The output terminal of the power detection module is connected to a photovoltaic power generation module, which is used to generate electricity using solar energy. The power detection module is used to detect the amount of electricity generated by the solar power generation in real time, and the traffic flow detection module is used to detect the time interval between vehicles traveling in the same direction on the highway in real time.
[0009] Preferably, the optimization unit includes a traffic flow extraction module, the output of which is connected to a reinforcement learning execution module. The output of the reinforcement learning execution module is connected to enable execution and disable execution respectively. The traffic flow extraction module is used to extract the time interval data between detected vehicles traveling in the same direction. The reinforcement learning execution module is used to optimize the control of tunnel lighting and guide lights based on the extracted time interval data.
[0010] Preferably, the enable execution is used to run an optimized control scheme to turn off the tunnel lighting and guide lights when the time interval is long, and the disable execution is used to disable the optimized control scheme to keep the tunnel lighting and guide lights on when the time interval is short. The output of the enable execution is connected to a prediction module, and the output of the prediction module is connected to a passage module. The prediction module is used to estimate the time point when a vehicle approaches the tunnel based on the detected time interval data, and the passage module is used to control the turning on of the tunnel lighting and guide lights based on the estimated time point.
[0011] Preferably, the evaluation unit includes a power extraction module, the output of which is connected to a simulated energy consumption acquisition module, the output of which is connected to a comparison module, and the output of which is connected to an image conversion module. The power extraction module is used to extract power generation data, the simulated energy consumption acquisition module is used to acquire energy consumption during simulated operation, the comparison module is used to compare the simulated energy consumption with the power generation, and the image conversion module is used to convert the numerical results of the comparison into image results.
[0012] Preferably, the output end of the image conversion module is connected to a display terminal, the input end of the image conversion module is connected to a color module, the input end of the color module is connected to a color setting, the display terminal is used to display the converted image result, the color module is used to display the portion of the image where the simulated energy consumption is greater than the power generation and the surplus portion where the simulated energy consumption is less than the power generation in two different colors, and the color setting is used to select the displayed color.
[0013] Compared with the prior art, the present invention has the following beneficial effects:
[0014] 1. Through the established detection unit, the vehicle flow detection module can detect the time intervals between vehicles traveling in the same direction on the highway in real time. This, combined with the vehicle flow extraction module in the optimization unit, extracts the detected time interval data. The reinforcement learning execution module optimizes the control of tunnel lighting and guide lights based on the extracted time interval data. The "enable execution" module runs the optimized control scheme to turn off tunnel lighting and guide lights when the time interval is long, while the "disable execution" module disables the optimized control scheme to keep tunnel lighting and guide lights on when the time interval is short. The prediction module estimates the time intervals based on the detected time interval data. When a vehicle approaches the tunnel, the traffic module controls the activation of tunnel lighting and guide lights based on the estimated time. This dynamically optimizes the control strategy of tunnel lighting and guide lights based on the real-time detected vehicle time intervals. When the time interval between adjacent vehicles is large, the lights are turned off promptly after the preceding vehicle leaves the tunnel and turned on in advance before the following vehicle approaches. When the vehicle spacing is small, the lights remain on after the preceding vehicle passes until the following vehicle passes smoothly, avoiding the extra energy consumption and losses caused by frequent switching of lights. This achieves refined optimization of energy consumption based on the real-time time interval between vehicles, thereby effectively reducing energy consumption and carbon emission levels.
[0015] 2. Through the set detection unit, the power generation of solar power can be detected in real time using the power detection module, and the power extraction module in the evaluation unit can extract the power generation data. The simulated energy consumption acquisition module is used to collect energy consumption during the simulation operation. The comparison module is used to compare the simulated energy consumption with the power generation. The image conversion module is used to convert the compared digital results into image results. The display terminal is used to display the converted image results. The color module is used to display the part of the image where the simulated energy consumption is greater than the power generation and the part where the simulated energy consumption is less than the power generation in two different colors. The color setting is used to select the display color. In this way, the energy consumption and photovoltaic power generation during the simulation operation can be compared and analyzed in real time. The gap where the energy consumption is higher than the photovoltaic power generation and the electricity needs to be purchased from the conventional grid, as well as the part of the surplus electricity where the energy consumption is lower than the power generation, are presented in two preset different colors to intuitively reflect the energy supply and demand balance. This provides an intuitive basis for carbon emission accounting and assessment in the simulation scenario. Attached Figure Description
[0016] Figure 1 This is a schematic diagram of a simulation evaluation and optimization system for a low-carbon retrofit scheme for highways based on reinforcement learning, according to the present invention.
[0017] Figure 2 This is a schematic diagram of the optimization unit of a simulation evaluation and optimization system for a low-carbon retrofit scheme for highways based on reinforcement learning, according to the present invention.
[0018] Figure 3This is a schematic diagram of the evaluation unit of a simulation evaluation and optimization system for a low-carbon transformation scheme of highways based on reinforcement learning, according to the present invention. Detailed Implementation
[0019] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.
[0020] like Figures 1-3 The system shown is a simulation evaluation and optimization system for low-carbon highway retrofitting based on reinforcement learning. It includes a smart computing center, whose output is connected to a database. The database's output is connected to an optimization unit, the optimization unit's output is connected to a digital twin simulation module, the digital twin simulation module's output is connected to a scene modeling module, and the digital twin simulation module's input is connected to an evaluation unit. The database is used to collect and store the detected data. The optimization unit is used to perform optimization and retrofitting based on the detected data. The scene modeling module is used to construct basic models of tunnel lighting, roads, etc. The digital twin simulation module is used to simulate the basic models according to the optimization scheme. The evaluation unit is used to evaluate the energy consumption during the simulation.
[0021] The database input is connected to a data acquisition module, the data acquisition module input is connected to a data communication module, and the data communication module input is connected to a detection unit. The detection unit is used to detect road sections in real-world scenarios, the data communication module is used to transmit the detected data, and the data acquisition module is used to acquire the detected data.
[0022] The database input is also connected to a data protection module, which is used to protect the data in the database.
[0023] The detection unit includes a power detection module and a traffic flow detection module. The output of the power detection module is connected to a photovoltaic power generation module, which generates electricity using solar energy. The power detection module is used to detect the amount of electricity generated by the solar power generation in real time. The traffic flow detection module is used to detect the time interval between vehicles traveling in the same direction on the highway in real time. The photovoltaic power generation module can use a solar position astronomical calculation algorithm to control and correct the photovoltaic system, ensuring that the photovoltaic system always faces the sun to generate electricity. The solar position astronomical calculation algorithm model is as follows:
[0024] Step 1: Calculate Julian Days / Accumulated Days
[0025] Only use the accumulated days within the year
[0026] =30 × (month - 1) + date
[0027] Date correction:
[0028] March and beyond:
[0029] = +1
[0030] Add 1 for leap years.
[0031] Step 2: Calculate the solar declination
[0032] Declination: The north-south angle of the Sun on the celestial sphere.
[0033]
[0034] Step 3: Calculate the hour angle
[0035] Hour angle: the angle of the sun in the east-west direction, 0 degrees at noon.
[0036]
[0037] For true solar time, approximately:
[0038]
[0039] For every 1° difference in longitude, there is a 4-minute time difference.
[0040] Step 4: Calculate the solar altitude angle
[0041]
[0042] =Local latitude
[0043] Angle of elevation:
[0044]
[0045] Step 5: Calculate the solar azimuth angle
[0046]
[0047]
[0048] Morning is negative / west, afternoon is positive / east; adjust according to the actual direction.
[0049] The optimization unit includes a traffic flow extraction module, the output of which is connected to a reinforcement learning execution module. The output of the reinforcement learning execution module is connected to enable execution and disable execution respectively. The traffic flow extraction module is used to extract the time interval data between detected vehicles traveling in the same direction. The reinforcement learning execution module is used to optimize the control of tunnel lighting and guide lights based on the extracted time interval data.
[0050] The "Enable Execution" function is used to run an optimized control scheme to turn off tunnel lighting and guide lights when the time interval is long. The "Disable Execution" function is used to disable the optimized control scheme to keep tunnel lighting and guide lights on when the time interval is short. The output of the "Enable Execution" function is connected to a prediction module, and the output of the prediction module is connected to a passage module. The prediction module is used to estimate the time point when a vehicle approaches the tunnel based on the detected time interval data, and the passage module is used to control the tunnel lighting and guide lights to turn on based on the estimated time point.
[0051] The evaluation unit includes a power extraction module, the output of which is connected to a simulated energy consumption acquisition module, the output of which is connected to a comparison module, and the output of which is connected to an image conversion module. The power extraction module is used to extract power generation data, the simulated energy consumption acquisition module is used to collect energy consumption during simulated operation, the comparison module is used to compare the simulated energy consumption with the power generation, and the image conversion module is used to convert the numerical results of the comparison into image results.
[0052] The output of the image conversion module is connected to a display terminal, the input of the image conversion module is connected to a color module, the input of the color module is connected to a color setting, the display terminal is used to display the converted image result, the color module is used to display the part of the image where the simulated energy consumption is greater than the power generation and the part where the simulated energy consumption is less than the power generation in two different colors, and the color setting is used to select the displayed color.
[0053] In summary, the detection unit utilizes a traffic flow detection module to detect the time intervals between vehicles traveling in the same direction on highways in real time. This, combined with a traffic flow extraction module in the optimization unit, extracts the time interval data. A reinforcement learning execution module optimizes the control of tunnel lighting and guide lights based on the extracted time interval data. An enable execution module runs the optimized control scheme to turn off tunnel lighting and guide lights when the time interval is long, while a disable execution module disables the optimized control scheme to keep tunnel lighting and guide lights on when the time interval is short. An estimation module estimates the time when vehicles approach the tunnel based on the detected time interval data. A passage module controls the on / off of tunnel lighting and guide lights based on the estimated time. This dynamically optimizes the control strategy for tunnel lighting and guide lights based on real-time vehicle time intervals. When the time interval between adjacent vehicles is large, the lights are turned off promptly after the preceding vehicle leaves the tunnel and turned on in advance before the following vehicle approaches. When the vehicle spacing is small, the lights remain on after the preceding vehicle passes until the following vehicle passes smoothly, avoiding excessive energy consumption and losses caused by frequent switching of lights. The time interval between vehicles enables refined optimization of energy consumption, thereby effectively reducing energy consumption and carbon emissions. Through a detection unit, the power generation of solar power can be detected in real time using a power detection module, and the power extraction module in the evaluation unit extracts the power generation data. A simulated energy consumption acquisition module collects energy consumption data during simulation operation. A comparison module compares the simulated energy consumption with the power generation. An image conversion module converts the compared digital results into image results. A display terminal displays the converted image results. A color module displays the portion of the image where simulated energy consumption exceeds power generation and the surplus portion where simulated energy consumption is less than power generation in two different colors. Color settings allow for the selection of display colors, enabling real-time comparative analysis of energy consumption and photovoltaic power generation during simulation operation. The gap where energy consumption exceeds photovoltaic power generation and requires purchasing electricity from the conventional grid, as well as the surplus power where energy consumption is less than power generation, are visualized using two preset colors to intuitively reflect the energy supply and demand balance, providing a direct basis for carbon emission accounting and assessment in the simulation scenario.
[0054] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.
Claims
1. A system for simulating, evaluating and optimizing a low-carbon reconstruction scheme of an expressway based on reinforcement learning, comprising a wisdom operation center, characterized in that: The intelligent computing center's output is connected to a database, the database's output is connected to an optimization unit, the optimization unit's output is connected to a digital twin simulation module, the digital twin simulation module's output is connected to a scene modeling module, and the digital twin simulation module's input is connected to an evaluation unit. The database is used to collect and store the detected data, the optimization unit is used to optimize and modify the data based on the detected data, the scene modeling module is used to construct basic models such as tunnel lighting and roads, the digital twin simulation module is used to simulate the basic model according to the optimization scheme, and the evaluation unit is used to evaluate the energy consumption during the simulation.
2. The system according to claim 1, wherein: The database has an input terminal connected to a data acquisition module, an input terminal connected to a data communication module, and an input terminal connected to a detection unit. The detection unit is used to detect road segments in a real-world scenario, the data communication module is used to transmit the detected data, and the data acquisition module is used to acquire the detected data.
3. The system of claim 1, wherein the system is characterized in that: The database input terminal is also connected to a data protection module, which is used to protect the data in the database.
4. The system according to claim 2, wherein the system is characterized in that: The detection unit includes a power detection module and a traffic flow detection module. The output of the power detection module is connected to a photovoltaic power generation module, which is used to generate electricity using solar energy. The power detection module is used to detect the amount of electricity generated by the solar power generation in real time. The traffic flow detection module is used to detect the time interval between vehicles traveling in the same direction on the highway in real time.
5. The system of claim 1, wherein: The optimization unit includes a traffic flow extraction module, the output of which is connected to a reinforcement learning execution module. The output of the reinforcement learning execution module is connected to enable execution and disable execution respectively. The traffic flow extraction module is used to extract the time interval data between detected vehicles traveling in the same direction. The reinforcement learning execution module is used to optimize the control of tunnel lighting and guide lights based on the extracted time interval data.
6. The system according to claim 5, wherein the system is characterized in that: The "Enable Execution" is used to run an optimized control scheme to turn off the tunnel lighting and guide lights when the time interval is long, and the "Deactivation Execution" is used to deactivate the optimized control scheme to keep the tunnel lighting and guide lights on when the time interval is short. The output of the "Enable Execution" is connected to a prediction module, and the output of the prediction module is connected to a passage module. The prediction module is used to estimate the time point when a vehicle approaches the tunnel based on the detected time interval data, and the passage module is used to control the tunnel lighting and guide lights to turn on based on the estimated time point.
7. The system of claim 1, wherein: The evaluation unit includes a power extraction module, the output of which is connected to a simulated energy consumption acquisition module, the output of which is connected to a comparison module, and the output of which is connected to an image conversion module. The power extraction module is used to extract power generation data, the simulated energy consumption acquisition module is used to collect energy consumption during simulated operation, the comparison module is used to compare the simulated energy consumption with the power generation, and the image conversion module is used to convert the numerical results of the comparison into image results.
8. The system according to claim 7, wherein the system is characterized in that: The output of the image conversion module is connected to a display terminal, the input of the image conversion module is connected to a color module, the input of the color module is connected to a color setting, the display terminal is used to display the converted image result, the color module is used to display the part of the image where the simulated energy consumption is greater than the power generation and the surplus part where the simulated energy consumption is less than the power generation in two different colors, and the color setting is used to select the displayed color.