A highland linkage traffic flow induction method based on friability index

Abstract

This invention discloses a high-ground integrated traffic flow guidance method based on fragility indices. It relies on the collaborative operation of edge computing modules and the cloud, and its steps include: 1. Abstracting the high-ground integrated road network into a hierarchical composite directed graph model; 2. Collecting various data information; 3. Using edge computing modules to quantify the dynamic fragility indices of ground roads in real time and synchronizing them to the cloud, setting fragility safety boundary thresholds for each level of ground roads and determining their status; 4. In the cloud, using dynamic fragility indices as the core safety hard constraint, reconstructing the dynamic impedance function, and solving the dual-layer SP-MC hybrid path guidance model to generate a global diversion scheme. This invention solves the core problem of congestion caused by the blind dumping of traffic flow in traditional diversion schemes by applying fragility constraints throughout the entire path guidance process, achieving the dual optimization of overall network traffic efficiency and ground road network carrying capacity safety.

Description

Technical Field

[0001] This invention relates to the field of traffic control technology, specifically a high-altitude linkage traffic flow guidance method based on fragility indicators. Background Technology

[0002] In recent years, transportation networks have developed rapidly, and their stable operation is crucial for public travel efficiency and safety. Normally, a dynamic equilibrium of traffic flow is maintained between highways and surface networks. However, during peak holiday periods and under the influence of complex weather conditions, highway trunk lines are prone to capacity bottlenecks and severe congestion. In such situations, employing scientific traffic flow guidance strategies to appropriately divert through traffic from highways to the surface network is a key means of alleviating localized congestion and maintaining the overall stable operation of the road network. However, facing complex and ever-changing traffic environments and massive amounts of multi-source sensing data, existing high- and low-level traffic flow guidance methods still have significant limitations. Traditional guidance methods often focus on unilaterally reducing traffic pressure on highways, adopting a static path planning strategy of "nearby diversion," ignoring the impact of uncontrolled diversion on the dynamic "fragility" of the ground road network, blindly dumping traffic flow onto vulnerable ground nodes, causing large-scale congestion or even network paralysis. Secondly, existing guidance systems heavily rely on centralized control architectures, and the concurrent uploading of massive amounts of underlying sensing data easily leads to communication congestion and cloud computing bottlenecks, resulting in severe delays in the distribution of guidance schemes. Finally, traditional traffic guidance lacks a dynamic feedback mechanism based on the underlying physical safety boundaries, and cannot perform impedance reconstruction and topology updates in real time at the model level based on the road network, resulting in guidance schemes that lack immediate adaptability and physical feasibility to rapidly changing road conditions. Summary of the Invention

[0003] This invention aims to address the shortcomings of existing technologies by proposing a high-ground linkage traffic flow guidance method based on fragility indices. This method is designed to meet the needs of large-scale traffic congestion relief and ensure the load-bearing safety of the ground road network while improving the overall traffic efficiency of the high-ground linkage road network.

[0004] To achieve the above-mentioned objectives, the present invention adopts the following technical solution: The present invention discloses a high-ground integrated traffic flow guidance method based on fragility index, characterized in that it is applied to a high-ground integrated road network that includes edge computing modules and the cloud. The high-ground integrated traffic flow guidance method is performed according to the following steps: Step 1: Abstract the high-altitude interconnected road network into a layered composite directed graph model. ,in, For a set of nodes, For the first A subset of nodes at each level; For directed road segments, For the first The set of road segments within the hierarchy, A collection of road segments that span multiple levels; Indicates the first Level and number The collection of road segments between different levels For the set of traffic capacity, For the first Middle section of the hierarchy Traffic capacity; A set of road levels; For highway level; For trunk highways or urban arterial roads; This is the level of secondary arterial roads in the city; For urban branch roads and alleyways: Step 2: Utilize edge computing modules to collect operational data from the high-altitude interconnected road network, thereby calculating... Time of the first Hierarchical road sections Dynamic fragility index ; Step 3: Calculate the road segment weight set based on the dynamic fragility index. ,in, For the first From nodes in the hierarchy Pointing to node section of road The weight, Indicates the weight of road segments across different levels. Indicates flow rate Down The first moment Level to Road segment weights between different levels; Step 4: The cloud will Refactoring to traffic-based Dynamic fragility function Used for refactoring Time of the first Middle section of the hierarchy Dynamic BPR impedance function This allows for the construction and solution of a two-layer SP-MC hybrid path induction model, generating an induction scheme.

[0005] 2. The high-altitude traffic flow guidance method based on fragility index according to claim 1, characterized in that step one includes: Step 1.1: Calculate using equation (1) At that time, highway section Traffic capacity : (1) In equation (1), This represents the baseline traffic capacity of a single lane in a highway layer. For road section The number of lanes in one direction, For large vehicles, the correction factor is... This is a correction factor for lane width or lateral clearance; Step 1.2: Calculate using equation (2) At that time, the first Tiered ground road sections Traffic capacity : (2) In equation (2), For the first The baseline capacity of a single lane in a tiered ground road section. This is a correction factor for signalized intersections. This is a correction factor for mixed traffic flow. This is the correction factor for roadside parking interference.

[0006] 3. The high-altitude traffic flow guidance method based on fragility index according to claim 2, characterized in that, in step two, the edge computing module collects... Time of the first Middle section of the hierarchy Traffic flow Therefore, equation (3) is used to calculate Time of the first Hierarchical road sections Dynamic fragility index : (3) In formula (3): For the first Basic brittleness parameters of hierarchical road sections This is the steepness coefficient of the brittle phase transition. For road section Density of intersections or entrances per unit length for Time of the first Dynamic disturbance terms of mixed traffic flow in the hierarchy, for The event disturbance amplification factor at any given time. It is a non-negative value.

[0007] 4. The high-altitude traffic flow guidance method based on fragility index according to claim 3, characterized in that step three includes: Step 3.1: Obtain using equation (4) : (4) In equation (4), Indicates the first Road sections in the hierarchy The travel time under free flow, and , For road section The actual length, For the first Road sections in the hierarchy Vehicle speed under free flow; This is a hierarchical correction factor; Step 3.2: Obtain the flow rate using equation (5) Down Road segment weights between the high-speed level and the ground road level at any given time : (5) In equation (5), For traffic Down Travel time at each ramp For traffic Down The passage time at the toll station. For traffic Down Queues in the high-altitude intersecting area cause delays. This is the conversion factor for the fragility penalty. For traffic Down The road section connecting to the ramp in the first level of the timetable Real-time fragility index; Step 3.3: Obtain the flow rate using equation (6) Down Road segment weights between the high-speed level and the ground road level at any given time : (6) In equation (6), For traffic Down Turning delay time of time level transition nodes For traffic Down Queuing delays caused by bottlenecks in downstream road sections. For traffic Down The moment enters the first Road sections connecting to ramps in the hierarchy Real-time fragility index.

[0008] 5. The high-altitude coordinated traffic flow guidance method based on fragility index according to claim 4, characterized in that step four includes: Step 4.1, let Time of the first Middle section of the hierarchy Traffic flow For the allocated traffic , obtain based on traffic Dynamic fragility function Thus, by using equation (7) to reconstruct Time of the first Middle section of the hierarchy Dynamic BPR impedance function : (7) In equation (7): , For the first Impedance sensitivity coefficient of hierarchical road sections The conversion factor for fragility penalty; Step 4.2: Construct a two-layer SP-MC hybrid path-inducing model: Step 4.2.1: Construct the objective function of the upper-level MC model using equation (8). : (8) In equation (8), To be allocated to the Traffic flow in the middle section of the hierarchy To be assigned to cross-level intermediate road sections Traffic; Step 4.2.2: Construct the constraints of the upper-level MC model using equation (8), including: flow conservation constraint, non-negativity constraint, capacity hard constraint, and fragility safety hard constraint. ,in, For the first The circuit breaker threshold at each level; Step 4.2.3: Construct the lower-level SP model: Step 4.2.3.1: The edge computing module performs real-time determination of the road segment's fragility status and transmits the determination results to the cloud. when At that time, it was determined to be in a safe state and could normally accept the diverted traffic flow; when When this occurs, it is determined to be a warning state, and the increase in diversion traffic is limited; when When the situation is determined to be a warning-level circuit breaker, the ramp release rate and the green light duration at ground intersections will be forcibly restricted. when When the circuit breaker is activated, the user is immediately added to the diversion and exclusion list. and The first Fragility safety thresholds and early warning thresholds for road sections at different levels; Step 4.2.3.2: Cloud-based composite directed graph of road network The road network sub-map is formed by removing the road segments and branch roads that are under circuit breaker conditions; and for road segments under early warning circuit breaker conditions, the travel time of ramps connecting inter-level networks is increased. Thus, the updated composite directed graph of the road network is obtained; Step 4.2.3.3: Solve the updated road network composite directed graph using the shortest path algorithm and output the set of alternative induced paths; Step 4.3: Based on the set of alternative guidance paths, the cloud uses the improved Frank-Wolfe algorithm to solve the two-layer SP-MC model and output the optimal traffic allocation and diversion guidance scheme.

[0009] The present invention provides an electronic device, including a memory and a processor, characterized in that the memory is used to store a program supporting the processor in performing the method described therein, and the processor is configured to execute the program stored in the memory.

[0010] The present invention discloses a computer-readable storage medium storing a computer program, characterized in that the computer program is executed by a processor to perform the steps of the method described thereon.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention quantifies the "dynamic fragility" of ground roads and introduces multi-factor coupled modeling of foundation brittleness, intersection density, and sudden events. It can accurately reflect the characteristics of dynamic attenuation of physical bearing capacity of complex ground road networks under multiple external disturbances. This invention significantly improves the perception and foresight of vulnerable nodes at the bottom layer, avoids the secondary congestion caused by blindly dumping traffic flow to vulnerable nodes, and overcomes the safety blind spots caused by traditional diversion schemes that ignore the characteristics of ground disturbance and rely solely on static physical distance for guidance.

[0012] 2. This invention innovatively reconstructs the dynamic impedance function by incorporating "dynamic fragility" as a capacity attenuation term, and embeds it into a two-layer SP-MC hybrid path guidance model, constructing a traffic allocation iterative mechanism driven by the actual safety carrying capacity of the road network. This invention enables the guidance algorithm to keenly perceive and proactively avoid ground streets where the absolute flow appears insufficient but is extremely vulnerable to external disturbances. It overcomes the theoretical shortcomings of traditional traffic allocation models, which rely solely on static free-flow time as impedance and are unable to characterize the nonlinear evolution of congestion in complex ground road networks. It achieves the optimal dynamic balance between global traffic efficiency and underlying physical safety in cross-layer traffic flow allocation.

[0013] 2. This invention relies on an edge-cloud collaborative architecture technology of "edge computing + cloud coordination" to construct a division of labor mechanism in which the edge is responsible for multi-source data collection and fragile quantification calculation, while the cloud coordinates global path planning and macro-algorithm iteration. This achieves efficient processing of massive amounts of underlying multi-source data and reasonable decoupling of system computing power. This invention reduces the concurrent processing pressure of the central cloud and the core network transmission latency, improves the real-time performance and reliability of the guidance scheme generation, and breaks through the limitations of traditional centralized guidance systems in the face of communication congestion and core computing power bottlenecks in the face of sudden large traffic scenarios. Attached Figure Description

[0014] Figure 1 This is a flowchart of the execution steps of the present invention; Figure 2 This is a schematic diagram of the layout framework of the present invention. Detailed Implementation

[0015] In this embodiment, a high-ground linkage traffic flow guidance method based on fragility index is implemented through collaboration between edge computing modules and the cloud. It is suitable for scenarios such as peak-hour congestion relief and emergency traffic diversion in areas where highways connect with urban surface roads. The physical deployment framework is as follows: Figure 2 As shown, the edge computing module includes a 5G smart gateway with multi-protocol conversion, a regional edge server cluster, an Ethernet switching matrix, and an edge storage array. The cloud-based guidance and control center includes a high-performance server cluster, distributed cluster storage, a core network interface gateway, and a deep protection firewall. Figure 1 As shown, the method is performed according to the following steps.

[0016] Step 1: Abstract the high-altitude interconnected road network into a layered composite directed graph model. ,in, For a set of nodes, For the first A subset of nodes at each level; For directed road segments, For the first The set of road segments within the hierarchy, A collection of road segments that span multiple levels; Indicates the first Level and number The collection of road segments between different levels For the set of traffic capacity, For the first Middle section of the hierarchy Traffic capacity; A set of road levels; For highway level; For trunk highways or urban arterial roads; This is the level of secondary arterial roads in the city; For urban branch roads and alleyways: Step 1.1: By road level Perform differentiated node abstraction to match the operational characteristics and inherent fragility differences of different road network levels: highway layer ( ): Node set ,in For highway toll stations, interchange hubs; trunk roads or urban arterial roads ( ): Node set ,in It is a planar signalized intersection node. This is the connection point between the highway off-ramp and the ground-level road; urban secondary arterial road level ( ): Node set ,in, For the area's signalized intersection nodes; urban branch roads and street levels ( ): Node set ,in, These are intersection nodes along the branch road.

[0017] Step 1.2: Calculate using equation (1) At that time, the traffic capacity of the highway layer : (1) In equation (1), This represents the baseline traffic capacity of a single lane in the highway layer, taken as 2200 vehicles per lane per hour. For road section The number of lanes in one direction, This is a correction factor for large vehicles, which is related to the proportion of trucks. If the proportion of large vehicles is 15%, the value is 0.85. This is a correction factor for lane width or lateral clearance, which is the effect of narrowing of highway lanes or the presence of roadside obstacles. The road section has a standard 3.75-meter lane and a wide hard shoulder, and the value is 1.0.

[0018] Step 1.3: Unlike highways, surface roads, due to their openness, are highly susceptible to external interference in terms of traffic capacity. Calculate using equation (2). At that time, the first Tiered ground road sections Traffic capacity : (2) In equation (2), For the first The baseline capacity of a single lane in a tiered ground road section. The value is 1600 vehicles per lane per hour. The value is 1300 vehicles per lane per hour. The value is 900 vehicles per lane per hour. This is a correction factor for signalized intersections, reflecting the reduction in the green light ratio caused by traffic lights. For example, if the green light ratio at the intersection is 0.55, then... The value is 0.55. This is a correction factor for mixed traffic flow, reflecting the impact of non-motorized vehicles and pedestrians, with a value of 0.90. This is a correction factor for roadside parking interference, reflecting the interference of roadside parking on the effective lanes, with a value of 0.95.

[0019] Step 2: Utilize edge computing modules to collect operational data from the high-altitude interconnected road network, thereby calculating... Time of the first Hierarchical road sections Dynamic fragility index .

[0020] Edge computing module data collection Time of the first Middle section of the hierarchy Traffic flow Therefore, equation (3) is used to calculate Time of the first Hierarchical road sections Dynamic fragility index : (3) In formula (3): For the first Basic brittleness parameters of hierarchical road sections The value is 0.25. The value is 0.35. The value is 0.50. This is the steepness coefficient of the brittle phase transition, with a value of 4.0. For road section The density of intersections or entrances / exits per unit length, such as this road segment. If there are two intersections per kilometer The value is 2.0. for Time of the first Dynamic disturbance terms of mixed traffic flow in the hierarchy, for The event disturbance amplification factor at any given time; if no event occurs, The value is 1.0; if an event occurs, it will... The value is 1.5. It is a non-negative value, with a value of 0.02.

[0021] Step 3: Calculate the road segment weight set based on the dynamic fragility index. ,in, For the first From nodes in the hierarchy Pointing to node section of road The weight, Indicates the weight of road segments across different levels. Indicates flow rate Down The first moment Level to Road segment weights between different levels; Step 3.1: Obtain using equation (4) : (4) In equation (4), Indicates the first Road sections in the hierarchy The travel time under free flow, and , For road section The actual length, For the first Road sections in the hierarchy Vehicle speed under free flow; This is a hierarchical correction factor. The value is 1.0. The value is 1.2. The value is 1.5. The value is 2.0.

[0022] Step 3.2: Obtain the flow rate using equation (5) Down Road segment weights between the high-speed level and the ground road level at any given time : (5) In equation (5), For traffic Down Travel time at each ramp For traffic Down The passage time at the toll station. For traffic Down Queues in the high-altitude intersecting area cause delays. This is the conversion factor for the fragility penalty. For traffic Down The road section connecting to the ramp in the first level of the timetable Real-time fragility index; Step 3.3: Obtain the flow rate using equation (6) Down Road segment weights between the high-speed level and the ground road level at any given time : (6) In equation (6), For traffic Down Turning delay time of time level transition nodes For traffic Down Queuing delays caused by bottlenecks in downstream road sections. For traffic Down The moment enters the first Road sections connecting to ramps in the hierarchy Real-time fragility index.

[0023] Step 4: The cloud will Refactoring to traffic-based Dynamic fragility function Used for refactoring Time of the first Middle section of the hierarchy Dynamic BPR impedance function This allows for the construction and solution of a two-layer SP-MC hybrid path induction model, generating an induction scheme.

[0024] Step 4.1: Traditional BPR impedance functions only consider the static ratio of flow rate to capacity, and the parameters are fixed. This step adopts... Time of the first Middle section of the hierarchy Traffic flow For the allocated traffic , obtain based on traffic Dynamic fragility function Thus Incorporate it into the impedance function and reconstruct it using equation (7). Time of the first Middle section of the hierarchy Dynamic BPR impedance function : (7) In equation (7): , For the first Impedance sensitivity coefficient of hierarchical road sections; The value is 0.15. The value is 4. The value is 0.30. The value is 5. The value is 0.45. The value is 6. The value is 0.60. The value is 7. This is the fragility penalty conversion factor, with a value of 500.

[0025] Step 4.2: Construct a two-layer SP-MC hybrid path-inducing model: Step 4.2.1: The MC model plans routes for each traveler to minimize the total travel cost of the transportation network. The objective function of the upper-level MC model is constructed using equation (8). : (8) In equation (8), To be allocated to the Traffic flow in the middle section of the hierarchy To be assigned to cross-level intermediate road sections Traffic; Step 4.2.2: The constraints for constructing the upper-level MC model using equation (8) include: flow conservation constraint (OD demand remains unchanged), and non-negativity constraint. and Hard constraints on traffic capacity: Fragility safety hard constraints: ,in, For the first The circuit breaker threshold for each level is set to 0.95.

[0026] Step 4.2.3: The SP model assumes that each traveler chooses the shortest time path between the origin and destination under free-flow conditions, and constructs the lower-level SP model: Step 4.2.3.1: The edge computing module performs real-time determination of the road segment's fragility status and transmits the determination results to the cloud. when At that time, it was determined to be in a safe state and could normally accept the diverted traffic flow; when When this occurs, it is determined to be a warning state, and the increase in diversion traffic is limited; when When the situation is determined to be a warning-level circuit breaker, the ramp release rate and the green light duration at ground intersections will be forcibly restricted. when When the circuit breaker is activated, the user is immediately added to the diversion and exclusion list. and The first Fragility safety thresholds and early warning thresholds for road sections at different levels; The value is 0.5. The value is 0.75.

[0027] Step 4.2.3.2: Cloud-based composite directed graph of road network The road network sub-map is formed by removing the road segments and branch roads that are under circuit breaker conditions; and for road segments under early warning circuit breaker conditions, the travel time of ramps connecting inter-level networks is increased. Thus, the updated road network composite directed graph is obtained.

[0028] Step 4.2.3.3: Solve the updated road network composite directed graph using the shortest path algorithm and output a set of alternative induced paths.

[0029] Step 4.3: Based on the set of alternative guidance paths, the cloud uses the improved Frank-Wolfe algorithm to solve the two-layer SP-MC model and output the optimal traffic allocation and diversion guidance scheme.

[0030] 1. Initialization: An edge computing module is introduced to derive a real-time dynamic OD demand matrix based on real-time collected data as the basic load. Based on free-flow impedance, the load is allocated to obtain the first load that satisfies the flow conservation constraint. Flow in the next iteration The initial flow contains the first Hierarchical road sections In the Flow in the next iteration and cross-level road sections In the Flow in the next iteration ; 2. Update impedance: based on the first Flow in the next iteration Calculate the number of road segments within all levels in the first... Dynamic impedance under the next iteration and cross-level road sections in the first Weighted impedance in the next iteration ; 3. Direction Finding: Based on the updated impedance, perform an all-or-nothing assignment on the set of candidate induced paths verified by the lower-level SP model to obtain the first... Auxiliary flow in the next iteration , including the Hierarchical road sections In the Auxiliary flow in the next iteration and cross-level road sections In the Auxiliary flow in the next iteration ; 4. Step size calculation: Solve the step size using the exact line search algorithm. Optimal iteration step size in the next iteration This makes the objective function of the upper-level MC model... Minimum, and satisfies equation (9): (9) 5. Flow update: Utilize the solved optimal step size The current road network traffic is updated in the direction of auxiliary traffic to obtain the first... New flow distribution in the next iteration : No. Hierarchical road sections In the Flow in the next iteration Cross-level road sections In the Flow in the next iteration ; 6. Convergence Criterion: If Stop iteration and output the first iteration. The optimal traffic allocation and diversion guidance scheme under the next iteration; otherwise Return to step 2.

[0031] In this embodiment, an electronic device includes a memory and a processor. The memory stores a program that supports the processor in executing the above-described method, and the processor is configured to execute the program stored in the memory.

[0032] In this embodiment, a computer-readable storage medium stores a computer program, which is executed by a processor to perform the steps of the above method.

Claims

1. A high-altitude coordinated traffic flow guidance method based on fragility index, characterized in that, This method is applied to high-altitude integrated road networks that include edge computing modules and cloud computing. The high-altitude integrated traffic flow guidance method is performed according to the following steps: Step 1: Abstract the high-altitude interconnected road network into a layered composite directed graph model. ,in, For a set of nodes, For the first A subset of nodes at each level; For directed road segments, For the first The set of road segments within the hierarchy, A collection of road segments that span multiple levels; Indicates the first Level and number The collection of road segments between different levels For the set of traffic capacity, For the first Middle section of the hierarchy Traffic capacity; A set of road levels; For highway level; For trunk highways or urban arterial roads; This is the level of secondary arterial roads in the city; For urban branch roads and alleyways: Step 2: Utilize edge computing modules to collect operational data from the high-altitude interconnected road network, thereby calculating... Time of the first Hierarchical road sections Dynamic fragility index ; Step 3: Calculate the road segment weight set based on the dynamic fragility index. ,in, For the first From nodes in the hierarchy Pointing to node section of road The weight, Indicates the weight of road segments across different levels. Indicates flow rate Down The first moment Level to Road segment weights between different levels; Step 4: The cloud will Refactoring to traffic-based Dynamic fragility function Used for refactoring Time of the first Middle section of the hierarchy Dynamic BPR impedance function This allows for the construction and solution of a two-layer SP-MC hybrid path induction model, generating an induction scheme.

2. The high-altitude traffic flow guidance method based on fragility index according to claim 1, characterized in that, Step one includes: Step 1.1: Calculate using equation (1) At that time, highway section Traffic capacity : (1) In equation (1), This represents the baseline traffic capacity of a single lane in a highway layer. For road section The number of lanes in one direction, For large vehicles, the correction factor is... This is a correction factor for lane width or lateral clearance; Step 1.2: Calculate using equation (2) At that time, the first Tiered ground road sections Traffic capacity : (2) In equation (2), For the first The baseline capacity of a single lane in a tiered ground road section. This is a correction factor for signalized intersections. This is a correction factor for mixed traffic flow. This is the correction factor for roadside parking interference.

3. The high-altitude traffic flow guidance method based on fragility index according to claim 2, characterized in that, In step two, the edge computing module collects data. Time of the first Middle section of the hierarchy Traffic flow Therefore, equation (3) is used to calculate Time of the first Hierarchical road sections Dynamic fragility index : (3) In formula (3): For the first Basic brittleness parameters of hierarchical road sections This is the steepness coefficient of the brittle phase transition. For road section Density of intersections or entrances per unit length for Time of the first Dynamic disturbance terms of mixed traffic flow in the hierarchy, for The event disturbance amplification factor at any given time. It is a non-negative value.

4. The high-altitude traffic flow guidance method based on fragility index according to claim 3, characterized in that, Step three includes: Step 3.1: Obtain using equation (4) : (4) In equation (4), Indicates the first Road sections in the hierarchy The travel time under free flow, and , For road section The actual length, For the first Road sections in the hierarchy Vehicle speed under free flow; This is a hierarchical correction factor; Step 3.2: Obtain the flow rate using equation (5) Down Road segment weights between the high-speed level and the ground road level at any given time : (5) In equation (5), For traffic Down Travel time at each ramp For traffic Down The passage time at the toll station. For traffic Down Queues in the high-altitude intersecting area cause delays. This is the conversion factor for the fragility penalty. For traffic Down The road section connecting to the ramp in the first level of the timetable Real-time fragility index; Step 3.3: Obtain the flow rate using equation (6) Down Road segment weights between the high-speed level and the ground road level at any given time : (6) In equation (6), For traffic Down Turning delay time of time level transition nodes For traffic Down Queuing delays caused by bottlenecks in downstream road sections. For traffic Down The moment enters the first Road sections connecting to ramps in the hierarchy Real-time fragility index.

5. The high-altitude traffic flow guidance method based on fragility index according to claim 4, characterized in that, Step four includes: Step 4.1, let Time of the first Middle section of the hierarchy Traffic flow For the allocated traffic , obtain based on traffic Dynamic fragility function Thus, by using equation (7) to reconstruct Time of the first Middle section of the hierarchy Dynamic BPR impedance function : (7) In equation (7): , For the first Impedance sensitivity coefficient of hierarchical road sections The conversion factor for fragility penalty; Step 4.2: Construct a two-layer SP-MC hybrid path-inducing model: Step 4.2.1: Construct the objective function of the upper-level MC model using equation (8). : (8) In equation (8), To be allocated to the Traffic flow in the middle section of the hierarchy To be assigned to cross-level intermediate road sections Traffic; Step 4.2.2: Construct the constraints of the upper-level MC model using equation (8), including: flow conservation constraint, non-negativity constraint, capacity hard constraint, and fragility safety hard constraint. ,in, For the first The circuit breaker threshold at each level; Step 4.2.3: Construct the lower-level SP model: Step 4.2.3.1: The edge computing module performs real-time determination of the road segment's fragility status and transmits the determination results to the cloud. when At that time, it was determined to be in a safe state and could normally accept the diverted traffic flow; when When this occurs, it is determined to be a warning state, and the increase in diversion traffic is limited; when When the situation is determined to be a warning-level circuit breaker, the ramp release rate and the green light duration at ground intersections will be forcibly restricted. when When the circuit breaker is activated, the user is immediately added to the diversion and exclusion list. and The first Fragility safety thresholds and early warning thresholds for road sections at different levels; Step 4.2.3.2: Cloud-based composite directed graph of road network The road network sub-map is formed by removing the road segments and branch roads that are under circuit breaker conditions; and for road segments under early warning circuit breaker conditions, the travel time of ramps connecting inter-level networks is increased. Thus, the updated composite directed graph of the road network is obtained; Step 4.2.3.3: Solve the updated road network composite directed graph using the shortest path algorithm and output the set of alternative induced paths; Step 4.3: Based on the set of alternative guidance paths, the cloud uses the improved Frank-Wolfe algorithm to solve the two-layer SP-MC model and output the optimal traffic allocation and diversion guidance scheme.

6. An electronic device, comprising a memory and a processor, characterized in that, The memory is used to store a program that supports a processor in executing the method of any one of claims 1-5, the processor being configured to execute the program stored in the memory.

7. A computer-readable storage medium storing a computer program thereon, characterized in that, The computer program is executed by the processor to perform the steps of the method according to any one of claims 1-5.

Images