Elastic modeling simulation method of traffic vehicle road cloud system and related device

Abstract

The invention discloses an elastic modeling simulation method of a traffic vehicle and road cloud system and a related device, and relates to the field of traffic system design and simulation, and the method comprises the steps: firstly, carrying out the analysis operation of the vehicle and road cloud system, obtaining an analysis result, and building a simulation model of the traffic vehicle and road cloud system based on the analysis result; then, simulation information required by the traffic vehicle and road cloud system is determined; then, the simulation model of the traffic vehicle road cloud system is initialized by using simulation information required by the traffic vehicle road cloud system, and an initialized simulation model of the traffic vehicle road cloud system is obtained; and finally, setting a simulation clock, propelling the initialized simulation model of the traffic vehicle road cloud system, and obtaining an efficiency index and a toughness index after each round of propelling of the simulation clock. According to the method, the elastic modeling simulation technology is adopted, the system efficiency and toughness of the traffic vehicle road cloud system in the normal state and the emergency state can be evaluated at the same time, and more comprehensive and systematic evaluation is provided.

Description

Technical Field

[0001] This application relates to the field of traffic system design and simulation, and particularly to a method and related device for elastic modeling and simulation of a traffic vehicle-road-cloud system. Background Art

[0002] With the rapid development of intelligent technologies, urban traffic systems are gradually evolving towards a vehicle-road-cloud (vehicle networking, road intelligence, cloud computing platform) system. Especially in future urban traffic systems, traffic mobility and elasticity will be important goals in traffic system design. Traditional traffic systems usually rely on fixed infrastructure and manual operations to maintain their normal operation. Such systems are prone to problems such as low efficiency, slow response, and even paralysis when faced with traffic accidents, extreme weather, emergencies, or traffic flow fluctuations.

[0003] Currently, many urban traffic simulation technologies and systems mainly focus on traffic flow prediction, congestion analysis, and route optimization, but there is still a lack of in-depth research on the "elastic" characteristics of the system, especially the compressive capacity, recovery ability in emergency situations, and the performance of the system under various disturbance conditions. Therefore, establishing a simulation platform that can not only evaluate normal traffic performance but also effectively measure the resilience and recovery ability of the traffic system in emergency situations is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] The purpose of this application is to provide a method and related device for elastic modeling and simulation of a traffic vehicle-road-cloud system, aiming to provide an important basis for the optimal design, emergency management, and decision-making support of urban traffic systems.

[0005] To achieve the above purpose, this application provides the following solutions:

[0006] In the first aspect, this application provides a method for elastic modeling and simulation of a traffic vehicle-road-cloud system, including:

[0007] Perform analysis operations on the traffic vehicle-road-cloud system to obtain analysis results, and based on the analysis results, construct a simulation model of the traffic vehicle-road-cloud system; the analysis operations include requirements analysis and capacity analysis. Determine the simulation information required for the traffic vehicle-road-cloud system; the simulation information includes the attributes and behaviors of each agent unit in the traffic vehicle-road-cloud system, the perturbation application scenarios and the impacts of the applied perturbations on the traffic vehicle-road-cloud system, and the basic simulation parameters of the traffic vehicle-road-cloud system. Initialize the simulation model of the traffic vehicle-road-cloud system using the simulation information to generate an initialized simulation model of the traffic vehicle-road-cloud system; the initialized simulation model of the traffic vehicle-road-cloud system includes a road network model, each agent unit, and the interaction connection relationships between each agent unit. According to the set simulation clock, perform simulation advancement on the initialized simulation model of the traffic vehicle-road-cloud system, and calculate the effectiveness index and resilience index of the traffic vehicle-road-cloud system after each round of simulation advancement.

[0008] In a second aspect, the present application provides an elastic modeling and simulation system for a traffic vehicle-road-cloud system, including:

[0009] A simulation model construction module, configured to perform analysis operations on the traffic vehicle-road-cloud system to obtain analysis results, and based on the analysis results, construct a simulation model of the traffic vehicle-road-cloud system; the analysis operations include requirements analysis and capacity analysis. A simulation information determination module, configured to determine the simulation information required for the traffic vehicle-road-cloud system; the simulation information includes the attributes and behaviors of each agent unit in the traffic vehicle-road-cloud system, the perturbation application scenarios and the impacts of the applied perturbations on the traffic vehicle-road-cloud system, and the basic simulation parameters of the traffic vehicle-road-cloud system. A simulation model initialization module, configured to initialize the simulation model of the traffic vehicle-road-cloud system using the simulation information to generate an initialized simulation model of the traffic vehicle-road-cloud system; the initialized simulation model of the traffic vehicle-road-cloud system includes a road network model, each agent unit, and the interaction connection relationships between each agent unit. A simulation advancement and simulation result calculation module, configured to perform simulation advancement on the initialized simulation model of the traffic vehicle-road-cloud system according to the set simulation clock, and calculate the effectiveness index and resilience index of the traffic vehicle-road-cloud system after each round of simulation advancement.

[0010] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the elastic modeling and simulation method for the traffic vehicle-road-cloud system described in the first aspect.

[0011] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the elastic modeling and simulation method for the traffic vehicle-road-cloud system described in the first aspect.

[0012] In a fifth aspect, the present application provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the elastic modeling and simulation method of the traffic vehicle-road-cloud system described in the first aspect.

[0013] According to the specific embodiments provided by the present application, the following technical effects are disclosed:

[0014] The present application provides an elastic modeling and simulation method for a traffic vehicle-road-cloud system and related devices. First, an analysis operation is performed on the vehicle-road-cloud system to obtain an analysis result, and based on the analysis result, a simulation model of the traffic vehicle-road-cloud system is constructed; then, the simulation information required for the traffic vehicle-road-cloud system is determined; next, the simulation information required for the traffic vehicle-road-cloud system is used to initialize the simulation model of the traffic vehicle-road-cloud system to obtain an initialized simulation model of the traffic vehicle-road-cloud system; finally, a simulation clock is set, and the initialized simulation model of the traffic vehicle-road-cloud system is advanced to obtain the performance index and resilience index after each advancement of the simulation clock. The present application adopts elastic modeling and simulation technology, which can simultaneously evaluate the system performance and resilience of the traffic vehicle-road-cloud system in normal and emergency states, providing a more comprehensive and systematic evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is an application environment diagram of an elastic modeling and simulation method for a traffic vehicle-road-cloud system provided by an embodiment of the present application;

[0017] Figure 2 It is a flowchart of an elastic modeling and simulation method for a traffic vehicle-road-cloud system provided by an embodiment of the present application;

[0018] Figure 3 It is a schematic diagram of the capacity analysis of a traffic vehicle-road-cloud system provided by an embodiment of the present application;

[0019] Figure 4 It is a schematic diagram of the index system of a traffic vehicle-road-cloud system provided by an embodiment of the present application;

[0020] Figure 5 It is a system operation mechanism diagram of a traffic vehicle-road-cloud system provided by an embodiment of the present application;

[0021] Figure 6Perception reconstruction mechanism diagram of the vehicle-road-cloud system provided by an embodiment of the present application;

[0022] Figure 7 Simulation case road network diagram of the vehicle-road-cloud system provided by an embodiment of the present application;

[0023] Figure 8 Simulation case system diagram of the vehicle-road-cloud system provided by an embodiment of the present application;

[0024] Figure 9 System perception network diagram of the vehicle-road-cloud system provided by an embodiment of the present application;

[0025] Figure 10 Simulation case perturbation diagram of the vehicle-road-cloud system provided by an embodiment of the present application;

[0026] Figure 11a Graph of the change in the average order completion time in the vehicle-road-cloud system simulation model in the simulation case of the vehicle-road-cloud system provided by an embodiment of the present application;

[0027] Figure 11b Graph of the change in the number of completed orders in the vehicle-road-cloud system simulation model in the simulation case of the vehicle-road-cloud system provided by an embodiment of the present application;

[0028] Figure 11c Graph of the change in the number of generated orders in the vehicle-road-cloud system simulation model in the simulation case of the vehicle-road-cloud system provided by an embodiment of the present application;

[0029] Figure 11d Graph of the change in the number of current unfinished orders in the vehicle-road-cloud system simulation model in the simulation case of the vehicle-road-cloud system provided by an embodiment of the present application;

[0030] Figure 11e Graph of the change in the empty vehicle percentage in the vehicle-road-cloud system simulation model in the simulation case of the vehicle-road-cloud system provided by an embodiment of the present application;

[0031] Figure 11f Graph of the change in the average empty vehicle time in the vehicle-road-cloud system simulation model in the simulation case of the vehicle-road-cloud system provided by an embodiment of the present application;

[0032] Figure 11g Graph of the change in the average degree of the road network in the vehicle-road-cloud system simulation model in the simulation case of the vehicle-road-cloud system provided by an embodiment of the present application;

[0033] Figure 11h Graph of the change in the average degree of the perception network in the vehicle-road-cloud system simulation model in the simulation case of the vehicle-road-cloud system provided by an embodiment of the present application;

[0034] Figure 12 A structural schematic diagram of a computer device provided by an embodiment of the present application. Specific embodiments

[0035] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0036] As described in the background art section, with the rapid development of intelligent technologies, urban transportation systems are gradually evolving towards a vehicle-road-cloud (vehicle networking, road intelligence, cloud computing platform) system. Especially in future cities, traffic mobility and resilience will be important goals in traffic system design. Traditional traffic systems usually rely on fixed infrastructure and manual operations to maintain their normal operation. Such systems are prone to problems such as low efficiency, slow response, and even paralysis when facing traffic accidents, extreme weather, emergencies, or traffic flow fluctuations. Currently, many urban traffic simulation technologies and systems mainly focus on traffic flow prediction, congestion analysis, and route optimization, but there is still a lack of in-depth research on the "resilience" characteristics of the system, especially the anti-pressure ability, recovery ability in emergency situations, and the performance of the system under various disturbance conditions. Traditional traffic simulation systems cannot fully simulate the behavior of agents in complex traffic networks and cannot accurately evaluate the system performance when facing various emergencies. Especially when emergencies such as extreme weather events or natural disasters occur, there is no effective evaluation mechanism for the dynamic response and recovery ability of the existing simulation technology for traffic systems. The vehicle-road-cloud system, as the core framework of future urban intelligent transportation systems, can provide a more efficient, intelligent, and flexible management and operation method for traffic systems through the deep integration of vehicle networking, intelligent roads, and cloud computing platforms. Through data sharing and intelligent decision-making based on the cloud platform, the vehicle-road-cloud system can not only monitor traffic flow in real time and predict traffic congestion, but also make dynamic adjustments and optimizations when encountering system pressure and emergencies, thereby improving the resilience and recovery ability of the traffic system. However, in the existing technology, there are relatively few studies on the resilience modeling and simulation of future urban traffic systems. The existing resilience simulation technologies mainly focus on system stability analysis and conventional traffic flow prediction, lacking a multi-dimensional and systematic evaluation method for the performance (including efficiency and resilience) of traffic systems in complex emergency situations. Moreover, most simulation systems fail to deeply consider the interaction and cooperation among various agents (such as central clouds, edge clouds, intelligent vehicles, low-altitude unmanned aerial vehicles, etc.) in the vehicle-road-cloud system, resulting in the simulation results being difficult to accurately reflect the actual response ability of the system when facing large-scale disturbances.

[0037] Therefore, based on the structure of the future urban traffic vehicle-road-cloud system, how to establish a simulation platform that can not only evaluate the normal traffic efficiency but also effectively measure the resilience and recovery ability of the traffic system in emergency situations has become a technical problem that needs to be solved urgently. For this reason, this application proposes a traffic vehicle-road-cloud system elastic modeling and simulation technology, aiming to construct a modeling and simulation framework that can comprehensively evaluate the system efficiency and resilience of the future urban traffic system in normal and emergency states. Through the requirement analysis, capacity analysis, definition of agent attributes and behaviors of the vehicle-road-cloud system, especially by simulating the impacts of different disturbance scenarios in the simulation environment, this application realizes the elastic modeling of the vehicle-road-cloud system, thus providing an important basis for the optimal design, emergency management and decision support of the urban traffic system.

[0038] To make the above objects, features, and advantages of this application more obvious and understandable, the following further detailed description of this application will be given in conjunction with the accompanying drawings and specific embodiments.

[0039] It should be noted that the terms "traffic vehicle-road-cloud system", "vehicle-road-cloud system", "urban vehicle-road-cloud system", and "urban traffic vehicle-road-cloud system" appearing in this article all represent the traffic vehicle-road-cloud system.

[0040] The elastic modeling and simulation method of the traffic vehicle-road-cloud system provided by the embodiments of this application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set separately, integrated on the server 104, placed on the cloud or other servers. The terminal 102 can send the data for traffic vehicle-road-cloud system modeling and simulation to the server 104. After receiving the data for traffic vehicle-road-cloud system modeling and simulation, the server 104 performs analysis operations on the traffic vehicle-road-cloud system, obtains the analysis results, and based on the analysis results, constructs a simulation model of the traffic vehicle-road-cloud system; determines the simulation information required for the traffic vehicle-road-cloud system; the simulation information includes the attributes and behaviors of each intelligent agent unit in the traffic vehicle-road-cloud system, the perturbation application scenarios and the impact of applied perturbations on the traffic vehicle-road-cloud system, and the basic simulation parameters of the traffic vehicle-road-cloud system; initializes the simulation model of the traffic vehicle-road-cloud system using the simulation information to generate an initialized simulation model of the traffic vehicle-road-cloud system; the initialized simulation model of the traffic vehicle-road-cloud system includes a road network model, each intelligent agent unit, and the interaction connection relationships between each intelligent agent unit; according to the set simulation clock, performs simulation advancement on the initialized simulation model of the traffic vehicle-road-cloud system, and calculates the performance index and resilience index of the traffic vehicle-road-cloud system after each round of simulation advancement. The server 104 can feedback the performance index and resilience index of the traffic vehicle-road-cloud system after each round of simulation advancement to the terminal 102. In addition, in some embodiments, the elastic modeling and simulation method of the traffic vehicle-road-cloud system can also be implemented separately by the server 104 or the terminal 102. For example, the terminal 102 can directly process the data for traffic vehicle-road-cloud system modeling and simulation, or the server 104 can obtain the data for traffic vehicle-road-cloud system modeling and simulation from the data storage system and process the data for traffic vehicle-road-cloud system modeling and simulation.

[0041] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0042] In an exemplary embodiment, as Figure 2 shown, a method for elastic modeling and simulation of a traffic vehicle-road-cloud system is provided. This method is executed by a computer device, and specifically can be executed separately by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the server 104 in

[0043] as an example for illustration, it includes the following steps 201 to step 204.

[0043] Among them:

[0044] Step 201: Analyze the traffic vehicle-road-cloud system to obtain an analysis result, and based on the analysis result, construct a simulation model of the traffic vehicle-road-cloud system; the analysis operation includes requirements analysis and capacity analysis. Among them, the requirements analysis includes requirements positioning and requirements decomposition. Requirements positioning includes the efficient operation of the traffic vehicle-road-cloud system under normal conditions and the rapid emergency response and recovery of the traffic vehicle-road-cloud system under emergency conditions.

[0045] Requirements decomposition includes: effectiveness requirements and resilience requirements. Effectiveness requirements include: shorter average navigation waiting time, shorter average navigation completion time, and lower average empty vehicle rate. The resilience requirement is: shorter effectiveness recovery time of the vehicle-road-cloud system. Capacity analysis refers to analyzing the effectiveness of the traffic vehicle-road-cloud system and the resilience capacity of the traffic vehicle-road-cloud system. The effectiveness of the traffic vehicle-road-cloud system includes navigation operation capacity and resource utilization capacity. The resilience capacity of the traffic vehicle-road-cloud system includes resistance capacity and recovery capacity.

[0046] Step 202: Determine the simulation information required by the traffic vehicle-road-cloud system; the simulation information includes the attributes and behaviors of each intelligent agent unit in the traffic vehicle-road-cloud system, the disturbance application scenarios and the impacts of the applied disturbances on the traffic vehicle-road-cloud system, and the basic simulation parameters of the traffic vehicle-road-cloud system.

[0047] Among them, the intelligent agent units include: central cloud, edge cloud, and intelligent terminal. The disturbance application scenario refers to the application location of the disturbance in the traffic vehicle-road-cloud system. The disturbance impacts include: severe impact, mild impact, and no impact. The disturbance can be a traffic accident, extreme weather, an emergency event, or traffic flow fluctuations. In this application, by applying disturbance information to the traffic vehicle-road-cloud system, elastic modeling and simulation of the traffic vehicle-road-cloud system are realized.

[0048] Step 203: Initialize the simulation model of the traffic vehicle-road-cloud system using the simulation information to generate an initialized simulation model of the traffic vehicle-road-cloud system; the initialized simulation model of the traffic vehicle-road-cloud system includes a road network model, each intelligent agent unit, and the interaction connection relationships between each intelligent agent unit.

[0049] Step 204: According to the set simulation clock, perform simulation advancement on the initialized simulation model of the traffic vehicle-road-cloud system, and calculate the effectiveness index and resilience index of the traffic vehicle-road-cloud system after each round of simulation advancement.

[0050] In an exemplary embodiment, step 201 specifically includes:

[0051] Step 201.1: Analyze the traffic vehicle-road-cloud system to obtain an analysis result.

[0052] 1) Conduct requirements analysis on the traffic vehicle-road-cloud system to obtain a requirements analysis result.

[0053] The requirements of the transportation vehicle-road-cloud system come from two aspects. On the one hand, it is to achieve the efficient operation of the vehicle-road-cloud system under normal conditions, and on the other hand, it is to achieve the rapid emergency response and recovery of the system under emergency conditions. Based on this, efficiency requirements and resilience capacity requirements are put forward for the transportation vehicle-road-cloud system.

[0054] The efficiency of the transportation vehicle-road-cloud system involves multiple dimensions, including dispatching ability, resource utilization efficiency, service quality, and other aspects. What this embodiment focuses on is the order completion ability of the system, that is, the efficiency and effectiveness in the whole process from order reception to order completion. The efficiency of the transportation vehicle-road-cloud system is not only reflected in the speed of order allocation by the system, but also includes the order completion time and the effective utilization rate of the vehicles in the whole system. Therefore, in terms of efficiency requirements, it is expected that the average order waiting time and average completion time are shorter, and the average empty vehicle rate of the system is lower.

[0055] The resilience of the transportation vehicle-road-cloud system refers to the ability of the vehicle-road-cloud system to maintain its core functions unaffected and respond quickly and resume normal operation when facing various emergencies. The resilience requirement of the transportation vehicle-road-cloud system is: to make the system's efficiency recovery time as short as possible.

[0056] 2) Conduct an ability analysis on the transportation vehicle-road-cloud system to obtain the ability analysis results.

[0057] As Figure 3 shown, according to the efficiency requirements and resilience requirements of the vehicle-road-cloud system, the ability requirements of the vehicle-road-cloud system are: efficiency and resilience ability. System efficiency is a proprietary ability that reflects the system's ability to complete specified tasks, while resilience ability is a general ability that reflects the system's ability to absorb, resist, and adapt to unconventional disturbances. System efficiency is composed of order operation ability and resource utilization ability; system resilience ability is composed of system resistance ability and system recovery ability.

[0058] Step 201.2, based on the analysis results, construct a simulation model of the transportation vehicle-road-cloud system; the analysis results include demand analysis results and ability analysis results.

[0059] As an optional implementation method, step 201.2 specifically includes:

[0060] According to the analysis results, construct an index system of the transportation vehicle-road-cloud system, and construct a simulation model of the transportation vehicle-road-cloud system according to the index system of the transportation vehicle-road-cloud system.

[0061] Among them, the traffic vehicle-road-cloud system index system includes: order operation ability related indexes, resource utilization ability related indexes, system resistance ability related indexes, and system recovery ability related indexes. The order operation ability related indexes include: the current number of running orders, the number of completed orders, the average order waiting time, and the average order completion time. The resource utilization ability related indexes include: the percentage of empty vehicles, the average empty vehicle time, and the number of normal vehicles. The system resistance ability related indexes include: the average degree of the road network, the average clustering coefficient of the road network, the average betweenness of the road network, the scale of the largest connected sub-clique of the road network, the average degree of the perception network, the average clustering coefficient of the perception network, the average betweenness of the perception network, and the scale of the largest connected sub-clique of the perception network. The system recovery ability related indexes include: the system reconstruction time and the system reconstruction efficiency.

[0062] A schematic diagram of the traffic vehicle-road-cloud system index system is as Figure 4 shown. The steps to construct the traffic vehicle-road-cloud system index system include:

[0063] 1) Based on the analysis results, design the system effectiveness indexes

[0064] The system effectiveness index system measures various performances during operation, including but not limited to the comprehensive effects in multiple dimensions such as order operation ability and resource utilization ability. The system effectiveness indexes include order operation ability related indexes and resource utilization ability related indexes.

[0065] The order operation ability related indexes include the current number of running orders, the number of completed orders, the average order waiting time, and the average order completion time. These indexes are used to measure the efficiency and effectiveness of the system in processing orders, including all stages from order reception, allocation, processing to completion, and can intuitively reflect the performance of the system in normal operation and the changes in order processing ability in emergency situations. The resource utilization ability related indexes include the percentage of empty vehicles, the average empty vehicle time, and the number of normal vehicles. These indexes focus on how the system efficiently utilizes available resources such as vehicles and road networks to maximize service output while avoiding excessive idleness of resources in the system, and help to evaluate the resource allocation and utilization efficiency of the system under different market conditions, as well as its adaptability and pressure resistance to market changes.

[0066] 2) Based on the analysis results, design the system resilience indexes

[0067] The system resilience index system measures the system resistance ability and the system recovery ability.

[0068] The indicators related to the system's resistance ability include the average degree of the road network, the average clustering coefficient of the road network, the average betweenness of the road network, the scale of the largest connected sub-clique of the road network, the average degree of the perception network, the average clustering coefficient of the perception network, the average betweenness of the perception network, and the scale of the largest connected sub-clique of the perception network. These indicators reflect the stability and continuous operation ability of the system when encountering adverse or unexpected events, and can evaluate how the system resists the impact brought by the external environment and the system's ability to maintain its core operation functions. The indicators related to the system's recovery ability include the system reconstruction time and the system reconstruction efficiency. These indicators measure the speed and efficiency of the system to return to the normal operation state after being disturbed by the emergency state, and can evaluate the resilience impact of the system reconstruction and the system's ability to restore the original operation ability through resource reallocation, reconstruction or other means.

[0069] In an exemplary embodiment, step 202 specifically includes:

[0070] Step 202.1, define the attributes and behaviors of each intelligent agent unit in the vehicle-road-cloud system.

[0071] In this embodiment, the following three-layer architecture and its intelligent agent units are mainly concerned: the cloud layer (central cloud), the edge layer (edge cloud), and the end layer (information points, intelligent highways, intelligent vehicles, low-altitude unmanned aerial vehicles).

[0072] Defining the attributes and behaviors of the intelligent agent units in the vehicle-road-cloud system specifically includes:

[0073] ① Define the behavior of the central cloud. Specifically, it includes:

[0074] First, the central cloud processes the waiting orders. The central cloud will discard all orders with the starting or ending point in the severely affected area and obtain all UAVs and intelligent vehicles with an empty vehicle status in the area. The central cloud gives priority to matching orders for UAVs. Due to the characteristics of UAVs flying at low altitudes and being unaffected by congestion, orders with a relatively large distance between the starting and ending points of the order are preferentially assigned to UAVs, which can improve the operating efficiency of the system to a certain extent. After completing the UAV order matching, the central cloud matches orders for intelligent vehicles. First, the central cloud calculates the shortest path from each intelligent vehicle to each order based on the Dijkstra algorithm and obtains the information matrix from each vehicle to the starting point of the order considering the waiting time of the order. A weight matrix is constructed based on the Kuhn - Munkres algorithm to complete the matching of orders and intelligent vehicles. Then, the central cloud evaluates whether the number of intelligent vehicles in the area can meet the order requirements. When the number of waiting orders exceeds the waiting order threshold, a certain number of unmanned empty vehicles are put into the simulation to achieve vehicle number regulation. After that, the central cloud aggregates and processes the status information of all edge clouds. Based on the status information of all edge clouds and RSU (Road Side Unit), the status of the sensing network is updated. For edge clouds affected by the severely affected area, they will be directly removed from the sensing network; for edge clouds affected by the lightly affected area, there is a certain probability of losing the sensing ability. Finally, the central cloud will evaluate the overall disaster situation and complete the repair of the disaster area. The evaluation process is that the central cloud scores the area under the jurisdiction of each edge cloud: First is the number of surrounding edge clouds, and the areas with more surrounding edge clouds are preferentially repaired. In the case of the same number, for each normal edge cloud, 25 points are counted, for each lightly affected area edge cloud, 5 points are counted, and for each severely affected area edge cloud, 1 point is counted. The central cloud preferentially repairs the areas under the jurisdiction of edge clouds with higher scores. At the same time, the central cloud has a repair interval. After completing one repair, it is necessary to wait for the repair interval before continuing to repair the disaster area.

[0075] ② Define the behavior of the edge cloud. Specifically, it includes:

[0076] First, the edge cloud collects and processes the health status information of the RSU in its jurisdiction and sends it to the central cloud. For RSU affected by the severely affected area, they will be directly removed from the sensing network; for RSU affected by the lightly affected area, there is a certain probability of losing the sensing ability. Then, the edge cloud dredges the congested roads. Here, the specific method of congestion dredging is simplified, so only by increasing the road capacity, the whole road is no longer congested to complete congestion regulation. For edge clouds with a normal status, it is considered that they have the ability to regulate 4 roads in their jurisdiction; for edge clouds affected by the lightly affected area, it is considered that they can only regulate the most congested road in their jurisdiction and give priority to dealing with roads affected by the lightly affected area. Finally, the edge cloud processes the path information of all vehicles in its jurisdiction. Since the traffic flow changes with time, the previously judged path may not be optimal. Therefore, if a vehicle arrives at an intersection, the driving path of the vehicle is updated.

[0077] ③Define the behaviors of Points of Interest (POIs), specifically including:

[0078] First, the intelligent road determines whether each point on the road is normal and obtains the status information of the Road Side Units (RSUs) on that road and transmits it to the edge cloud in the jurisdiction. Then, the intelligent road senses the vehicles and congestion information on the road based on the RSUs and transmits the congestion information to the edge cloud in the jurisdiction.

[0079] ④Define the behaviors of intelligent vehicles. Specifically including:

[0080] First, the intelligent vehicle determines whether it needs to update the edge cloud unit connected to itself based on its current location. Then, the intelligent vehicle selects different operating logics according to whether it currently has an order. When the intelligent vehicle has an order, it updates the empty vehicle time to 0 and at the same time seeks to the edge cloud to judge whether the starting point and the ending point of the order are in the severely affected area: If the intelligent vehicle is currently unoccupied but the starting point of the order is in the severely affected area, it abandons the order and records the abandonment time of the order, and at the same time clears its own destination path; If the intelligent vehicle is already occupied and the starting point of the order is in the severely affected area, it changes the ending point to a POI point not in the severely affected area, and at the same time updates the order destination information and the driving destination information of the intelligent vehicle. If there is no problem with the order, the intelligent vehicle continues its moving behavior. The intelligent vehicle calculates the moving direction and speed by itself and obtains the result of the change in its own position. After completing the position movement, it determines whether it has reached the current destination and updates the order status information and the occupancy information. When the intelligent vehicle has no order, it judges whether the current destination ending point is in the severely affected area to the edge cloud. If it is in the severely affected area, it changes to a point not in the severely affected area. Since there is no order currently, the intelligent vehicle updates the current empty vehicle time, and then moves randomly, calculates the moving direction and speed according to the random destination, and obtains the result of the change in its own position. Finally, the intelligent vehicle updates its own road information to the road it is on.

[0081] ⑤Define the behaviors of low-altitude unmanned aerial vehicles. Specifically including: The operating logic of low-altitude unmanned aerial vehicles is similar to that of intelligent vehicles, except that the speed of the unmanned aerial vehicle is not restricted.

[0082] Step 202.2, design the perturbation application scenarios and the impact of applying perturbations for the vehicle-road-cloud system. Specifically including:

[0083] 1) Design the perturbation application scenarios for the vehicle-road-cloud system. Specifically, the perturbations are divided into normal areas, lightly affected areas, and severely affected areas. By setting the various states of the grids in the simulation scenario, various influences are imposed on each agent in the simulation scenario.

[0084] 2) Define the impact of perturbations on each agent unit. Specifically:

[0085] ①Define the impact of perturbations on the central cloud. Specifically:

[0086] In the current simulation scenario, the disturbance has no impact on the central cloud.

[0087] ② Define the impact of the disturbance on the edge cloud. Specifically,

[0088] For the edge cloud affected by the severely affected area, it is determined that it cannot operate normally.

[0089] ③ Define the impact of the disturbance on the information points. Specifically,

[0090] The probability of a POI in the state affected by the lightly affected area generating an order is halved, and a POI in the state affected by the severely affected area does not generate an order.

[0091] ④ Define the impact of the disturbance on the intelligent highway (including roadside units). Specifically,

[0092] Based on the degree of impact on the road section, the traffic capacity of the road will be changed.

[0093] ⑤ Define the impact of the disturbance on intelligent vehicles. Specifically,

[0094] For vehicles in the state affected by the severely affected area, if affected by the severely affected area and there is a current order, the order is abandoned and the order abandonment time is recorded. At the same time, the Car is removed from the simulation.

[0095] ⑥ Define the impact of the disturbance on low-altitude unmanned aerial vehicles. Specifically,

[0096] In the current simulation scenario, the disturbance has no impact on low-altitude unmanned aerial vehicles.

[0097] Step 202.3, determine the basic simulation parameters of the vehicle-road-cloud system.

[0098] The basic simulation parameters of the vehicle-road-cloud system include traffic system road network parameters, simulation duration, disturbance start time, disturbance mode, disturbance intensity, and agent unit parameters. Determining the simulation parameters of the vehicle-road-cloud system specifically includes:

[0099] ① Determine the road network parameters.

[0100] Define the basic structure of the traffic network, including road sections, intersections, number of lanes, etc. At the same time, consider factors such as traffic flow distribution, traffic capacity, speed limit, etc., to provide basic road network data support for the simulation.

[0101] ② Determine the simulation duration.

[0102] Set the start and end points of the simulation time, and set the simulation time step according to requirements.

[0103] ③ Determine the disturbance start time.

[0104] Determine the simulation time step corresponding to the start of the disturbance event.

[0105] ④ Determine the perturbation pattern.

[0106] Set the type of perturbation and its change pattern. Perturbations may include traffic accidents, abnormal weather, road closures, etc. Different types of perturbations will affect the change of traffic flow and have different degrees of impact on the stability of the traffic system.

[0107] ⑤ Determine the perturbation intensity.

[0108] Specifically, define the degree of impact of the perturbation on the traffic system. The perturbation intensity can be adjusted according to the actual scenario. For example, the impacts of a minor traffic accident and a serious accident on traffic flow and route selection are different. Setting the perturbation intensity helps to conduct simulation tests in different scenarios.

[0109] ⑥ Determine the agent unit parameters.

[0110] Set the specific parameters of various agents in the simulation. In this embodiment, the parameter mainly refers to the number of such agents in the simulation.

[0111] In an exemplary embodiment, step 203 specifically includes:

[0112] Step 203.1, initialize the simulation model according to the basic simulation parameters. The implementation process of this step is as follows:

[0113] First, build a simulation environment and define the scenario module, operation module, and perturbation module. The scenario module realizes the formation of the simulation environment and each agent unit; the operation module realizes the advancement of the simulation clock and the calculation of various indicators; the perturbation module realizes the loading and implementation of perturbations in the simulation scenario after the simulation clock advances to the perturbation start time. Secondly, generate an agent set, specifically including a central cloud, an edge cloud, information points, intelligent roads (including roadside units), intelligent vehicles, low-altitude unmanned aerial vehicles, and a perturbation agent model.

[0114] Step 203.2, generate a road network model corresponding to the road network parameters, each agent unit, and the interaction connection relationships between each agent. This step specifically includes:

[0115] ① Build and initialize the road network model in detail. The implementation process of this step is as follows:

[0116] First, define the grid scale according to the road network parameters, that is, the number of horizontal and vertical lines of the road network in the simulation model. Then, generate intersection points at each grid intersection and connect adjacent intersection points with roads at a specified interval. Next, initialize the load capacity, health status, and congestion status information of each road. Finally, generate a graph model of the road network based on the networkx library function to facilitate updating and analyzing the real-time operation status of the road network.

[0117] ② Initialize the agent unit and set up the interactive connections. The implementation process of this step is as follows:

[0118] Generate the corresponding number of agent units according to the simulation initialization parameters, including: central cloud, edge cloud, information point, intelligent road (including roadside units), intelligent vehicle, and low-altitude unmanned aerial vehicle. Since the generation order of agents will affect the establishment of interactive connections between agents, therefore, this application exemplarily provides an agent generation order, specifically:

[0119] (1) Generate the central cloud according to the simulation input parameters, define the identifier, category, and coordinates of the central cloud, and add the central cloud to the running module.

[0120] (2) Generate each edge cloud according to the simulation input parameters, define the identifier, category, coordinates, and jurisdiction scope of the edge cloud, establish the interactive relationship between each edge cloud and the central cloud, and add the edge cloud to the running module.

[0121] (3) Generate each intelligent road according to the simulation input parameters, define the identifier, category, starting point coordinates of the intelligent road, generate each roadside unit on the intelligent road, establish the interactive relationship between the roadside unit and its affiliated edge cloud, and add the intelligent road to the running module.

[0122] (4) Generate each information point according to the simulation input parameters, define the identifier, category, coordinates, boarding point coordinates, and order generation probability of the information point, establish the interactive relationship between the information point and the central cloud, and add the information point to the running module.

[0123] (5) Generate each intelligent vehicle according to the simulation input parameters, define the identifier, category, coordinates, initial destination, and initial path of the intelligent vehicle, establish the interactive relationship between the intelligent vehicle and the currently affiliated edge cloud, and add the intelligent vehicle to the running module.

[0124] (6) Generate each low-altitude unmanned aerial vehicle according to the simulation input parameters, define the identifier, category, and initial coordinates of the low-altitude unmanned aerial vehicle, establish the interactive relationship between the low-altitude unmanned aerial vehicle and the currently affiliated edge cloud, and add the low-altitude unmanned aerial vehicle to the running module.

[0125] (7) Generate a perturbation agent, define the perturbation area, perturbation intensity, and perturbation mode of the perturbation agent, and add the perturbation agent to the running module.

[0126] In an exemplary embodiment, step 204 specifically includes:

[0127] Step 204.1, according to the set simulation clock, perform simulation advancement on the initialized simulation model of the traffic vehicle-road-cloud system.

[0128] Such as Figure 5 AndFigure 6 As shown in the figure, the simulation clock advancement follows the system operation mechanism and the perception reconstruction mechanism. The specific implementation process is as follows:

[0129] ① The grid agent executes its own actions for the first time; ② The information point agent executes its own actions; ③ The intelligent vehicle agent executes its own actions; ④ The low-altitude unmanned aerial vehicle agent executes its own actions; ⑤ The intelligent road agent executes its own actions; ⑥ The edge cloud agent executes its own actions; ⑦ The central cloud agent executes its own actions; ⑧ The grid agent executes its own actions for the second time.

[0130] Step 204.2: Calculate the effectiveness index and resilience index of the traffic vehicle-road-cloud system after each round of simulation advancement.

[0131] Specifically, it includes:

[0132] Step 204.21: Calculate the indicators related to order operation capabilities. Specifically,

[0133] The order operation capability indicators are used to measure the efficiency and effectiveness of the system in processing orders, covering all stages from order reception, allocation, processing to completion. Through these indicators, the performance of the system in normal operation and the changes in order processing capabilities in emergency situations can be intuitively reflected. The specific indicators and their calculation methods are as follows:

[0134] (1) Calculate the current number of running orders

[0135]

[0136] Among them, order status i = 1 indicates that order i is being processed, and N is the total number of orders.

[0137] (2) Calculate the number of completed orders

[0138] Definition: The number of orders that have been completed and delivered, reflecting the order processing efficiency of the system. The calculation method for the number of completed orders is:

[0139]

[0140] Among them, order status i = 2 indicates that order i has been completed, and N is the total number of orders.

[0141] (3) Calculate the average order waiting time

[0142] Definition: The average waiting time of an order from reception to the start of processing, used to evaluate the timeliness of the system in processing orders. The calculation method for the average order waiting time is:

[0143]

[0144] Among them, the start processing time iThe time when processing for order i starts, the order reception time i The time when order i is received, N is the total number of orders.

[0145] (4) Calculate the average order completion time

[0146] Definition: The average value of the time from order reception to completion, used to measure the overall efficiency of the system in processing orders. The calculation method of the average order completion time is as follows:

[0147]

[0148] Among them, the order completion time i The time when order i is completed, the order reception time i The time when order i is received, N is the total number of orders.

[0149] Step 204.22, calculate the indicators related to resource utilization ability. Specifically,

[0150] The resource utilization ability indicators mainly focus on how the system efficiently utilizes resources such as vehicles and road networks to maximize service output while avoiding excessive resource idle. The specific indicators and their calculation methods are as follows:

[0151] (1) Empty vehicle percentage

[0152]

[0153] Among them, the number of empty vehicles is the number of vehicles carrying no orders, and the total number of vehicles is the total number of all vehicles in the system.

[0154] (2) Average empty vehicle time

[0155]

[0156] Among them, the empty vehicle time i Is the idle time of vehicle i, M is the number of empty vehicles.

[0157] (3) Number of normal vehicles

[0158]

[0159] Among them, the vehicle status i Indicates that vehicle i is working normally, N is the total number of vehicles.

[0160] Step 204.23, calculate the indicators related to the system resistance ability. Specifically,

[0161] The system resistance ability index measures the stability and continuous operation ability of the system in the face of adverse or unexpected events, reflecting how the system responds to the impact of the external environment and maintains its core operation functions. The specific indicators include the average degree of the road network, the average clustering coefficient of the road network, the average betweenness of the road network, the scale of the largest connected sub-clique of the road network, the average degree of the perception network, the average clustering coefficient of the perception network, the average betweenness of the perception network, and the scale of the largest connected sub-clique of the perception network.

[0162] Step 204.24, calculate the relevant indicators of the system recovery ability. Specifically,

[0163] The system recovery ability index measures the recovery speed and efficiency of the system after encountering an emergency disturbance, and evaluates the ability of the system to reconstruct after encountering an unexpected event. The specific indicators and their calculation methods are as follows:

[0164] (1) Calculate the system reconstruction time

[0165] Definition: The time required for the system to recover from the disturbance to the normal operation state, which measures the recovery speed of the system. The calculation method of the system reconstruction time is:

[0166] System reconstruction time = Recovery completion time - Disturbance start time

[0167] Among them, the recovery completion time is the time when the system completely recovers to normal operation, and the disturbance start time is the time when the system is disturbed.

[0168] (2) Calculate the system reconstruction effectiveness

[0169] Definition: The effectiveness of the resources and functions recovered during the system recovery process, which is used to measure the effectiveness of the recovery strategy. The calculation method of the system reconstruction effectiveness is:

[0170]

[0171] Among them, the number of recovered functions and resources is the number of resources and functions recovered during the recovery process, and the total number of functions and resources is the total amount of functions and resources that the system can provide under normal conditions.

[0172] This application also provides an application scenario, which applies the elastic modeling and simulation method of the above-mentioned vehicle-road-cloud system for transportation. Specifically: The elastic modeling and simulation method of the vehicle-road-cloud system provided in this embodiment can be applied in the construction process of the urban traffic system. Through the demand analysis, capacity analysis, definition of agent attributes and behaviors of the vehicle-road-cloud system, especially by simulating the impact of different disturbance scenarios in the simulation environment, this application realizes the elastic modeling of the vehicle-road-cloud system, and can provide an important basis for the optimal design, emergency management and decision support of the urban traffic system.

[0173] The following introduces a specific embodiment of the elastic modeling and simulation of the traffic vehicle-road-cloud system in this application. For the simulation case, a road network with a vertical and horizontal count of 8×8 is selected, the initial number of POIs is 100, and the number of intelligent vehicles is 100, forming a simulation area of 80×80, specifically as Figures 7 to 8 shown.

[0174] Figure 7 It is a road network diagram of the simulation case of the traffic vehicle-road-cloud system. In the figure, the blue color represents the road network. In the grid in the middle of the road network, there are large orange squares, representing the central cloud, and the squares in the remaining grids are edge clouds. The red dots outside the grid lines are information points, and the dots on the grid lines represent intelligent vehicles. Among them, the green dots on the grid lines represent vehicles without orders and passengers; the yellow dots on the grid lines represent vehicles with orders but without passengers; the red dots on the grid lines represent vehicles with orders and passengers.

[0175] Figure 8 It is a system diagram of the simulation case of the traffic vehicle-road-cloud system. From the figure, the distribution of the central cloud, edge cloud, and roadside unit can be viewed.

[0176] Figure 9 It is the corresponding system perception network diagram. In the figure, the red dots represent the central cloud, the blue dots represent the edge cloud, the green dots represent the roadside unit (RSU), and the black connections indicate that there is an interaction relationship between two intelligent agents.

[0177] As Figure 10 shown, a perturbation is applied to the traffic vehicle-road operation system model. The perturbation mode is: the red area is selected as the severely affected area, and the orange area is selected as the lightly affected area, so as to obtain the simulation case perturbation diagram.

[0178] Furthermore, the simulation time is set to 100s, and the moment when the perturbation is applied is the 60th second. Figures 11(a) to 11(h) respectively show the changes in the average order completion time, the number of completed orders, the number of generated orders, the number of current uncompleted orders, the empty vehicle percentage, the average empty vehicle time, the average degree of the road network, and the average degree of the perception network. Based on the simulation results, the following conclusions can be drawn:

[0179] ① After being affected by the perturbation, the number of generated orders, the number of current uncompleted orders, and the number of completed orders gradually recover, indicating that resilience regulation can, to a certain extent, restore the system performance status.

[0180] ② There is a lag effect in the change of the average order completion time because the application of the perturbation does not immediately affect the system performance indicators.

[0181] ③ The average degree of the road network and the average degree of the perception network gradually recover after being affected by the perturbation, indicating that resilience regulation enables the system to complete reconstruction to a certain extent.

[0182] Based on the same inventive concept, an embodiment of the present application further provides a flexible modeling and simulation system for a transportation vehicle-road-cloud system, including:

[0183] A requirements analysis module for performing requirements analysis on the transportation vehicle-road-cloud system to provide a basis for carrying out the capacity design of the vehicle-road-cloud system.

[0184] A capacity analysis module for performing capacity analysis on the transportation vehicle-road-cloud system.

[0185] An index system module for constructing an index system of the transportation vehicle-road-cloud system to measure and evaluate the specific performance of the urban transportation vehicle-road-cloud system capacity.

[0186] Each agent attribute and behavior module for defining the attributes and behaviors of the agent units in the transportation vehicle-road-cloud system and also for designing the interaction relationships between each agent unit.

[0187] A simulation initialization module for initializing the simulation model of the transportation vehicle-road-cloud system to generate an initialized simulation model of the transportation vehicle-road-cloud system. The simulation initialization module is also used to determine simulation parameters, initialize each agent unit, connection, and inject perturbations in the simulation model.

[0188] A simulation operation mechanism module for setting a simulation clock and advancing the simulation of the initialized simulation model of the transportation vehicle-road-cloud system. The simulation operation mechanism module specifically includes: a system operation module and a perception reconstruction module. The system operation module includes an order generation module, an orderless vehicle operation module, and an ordered vehicle operation module. The perception reconstruction module includes a system health perception module and a system reconstruction module.

[0189] A simulation result calculation module for calculating the effectiveness index and resilience index of the transportation vehicle-road-cloud system after each round of simulation advancement.

[0190] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 12As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data for traffic vehicle-road-cloud system modeling and simulation. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for elastic modeling and simulation of a traffic vehicle-road-cloud system.

[0191] Those skilled in the art can understand that Figure 12 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0192] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0193] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0194] The database involved in the embodiments provided in the present application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., and is not limited thereto. The processor involved in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., and is not limited thereto.

[0195] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0196] In this text, specific examples are used to elaborate on the principles and implementation manners of this application. The descriptions of the above embodiments are only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. To sum up, the content of this specification should not be construed as a limitation to this application.

Claims

1. An elastic modeling and simulation method for a traffic vehicle-road-cloud system, characterized in that, The elastic modeling and simulation method of the transportation vehicle-road-cloud system includes: Performing an analysis operation on the transportation vehicle-road-cloud system to obtain an analysis result, and based on the analysis result, constructing a simulation model of the transportation vehicle-road-cloud system; the analysis operation includes requirement analysis and capacity analysis; Determining the simulation information required for the transportation vehicle-road-cloud system; the simulation information includes the attributes and behaviors of each intelligent agent unit in the transportation vehicle-road-cloud system, the perturbation application scenarios and the impact of applied perturbations on the transportation vehicle-road-cloud system, and the basic simulation parameters of the transportation vehicle-road-cloud system; Initializing the simulation model of the transportation vehicle-road-cloud system by using the simulation information to generate an initialized simulation model of the transportation vehicle-road-cloud system; the initialized simulation model of the transportation vehicle-road-cloud system includes a road network model, each intelligent agent unit, and the interaction connection relationships between each intelligent agent unit; According to the set simulation clock, performing simulation advancement on the initialized simulation model of the transportation vehicle-road-cloud system, and calculating the effectiveness index and resilience index of the transportation vehicle-road-cloud system after each round of simulation advancement.

2. The elastic modeling and simulation method of the transportation vehicle-road-cloud system according to claim 1, characterized in that The requirement analysis includes requirement positioning and requirement decomposition; The requirement positioning includes: the efficient operation of the transportation vehicle-road-cloud system under normal conditions and the rapid emergency response and recovery of the transportation vehicle-road-cloud system under emergency conditions; The requirement decomposition includes: effectiveness requirements and resilience requirements; The effectiveness requirements include: shorter average navigation waiting time, shorter average navigation completion time, and lower average empty vehicle rate; The resilience requirement is: shorter effectiveness recovery time of the transportation vehicle-road-cloud system.

3. The elastic modeling and simulation method of the transportation vehicle-road-cloud system according to claim 1, characterized in that The capacity analysis refers to: analyzing the effectiveness of the transportation vehicle-road-cloud system and the resilience capacity of the transportation vehicle-road-cloud system; The effectiveness of the transportation vehicle-road-cloud system includes navigation operation capacity and resource utilization capacity; The resilience capacity of the transportation vehicle-road-cloud system includes resistance capacity and recovery capacity.

4. The elastic modeling and simulation method of the traffic vehicle road cloud system according to claim 1, characterized in that Based on the analysis result, constructing a simulation model of the transportation vehicle-road-cloud system specifically includes: According to the analysis result, constructing an index system of the transportation vehicle-road-cloud system, and according to the index system of the transportation vehicle-road-cloud system, constructing a simulation model of the transportation vehicle-road-cloud system; Among them, the index system of the transportation vehicle-road-cloud system includes: order operation capacity-related indexes, resource utilization capacity-related indexes, system resistance capacity-related indexes, and system recovery capacity-related indexes; The order operation capacity-related indexes include: the current number of running orders, the number of completed orders, the average order waiting time, and the average order completion time; The resource utilization capacity-related indexes include: the percentage of empty vehicles, the average empty vehicle time, and the number of normal vehicles; The system resistance capacity-related indexes include: the average degree of the road network, the average clustering coefficient of the road network, the average betweenness of the road network, the size of the largest connected sub-clique of the road network, the average degree of the perception network, the average clustering coefficient of the perception network, the average betweenness of the perception network, and the size of the largest connected sub-clique of the perception network; The system recovery capacity-related indexes include: system reconstruction time and system reconstruction effectiveness.

5. The elastic modeling and simulation method of the traffic vehicle road cloud system according to claim 1, characterized in that The agent unit includes: a central cloud, an edge cloud, and intelligent terminals.

6. The elastic modeling and simulation method of the traffic vehicle road cloud system according to claim 1, characterized in that The basic simulation parameters of the traffic vehicle-road-cloud system include: traffic system road network parameters, simulation duration, disturbance start time, disturbance mode, disturbance intensity, and agent unit parameters.

7. An elastic modeling and simulation system for a traffic vehicle-road-cloud system, characterized in that Including: A simulation model construction module, configured to perform analysis operations on the traffic vehicle-road-cloud system to obtain analysis results, and based on the analysis results, construct a simulation model of the traffic vehicle-road-cloud system; the analysis operations include requirements analysis and capacity analysis; A simulation information determination module, configured to determine the simulation information required for the traffic vehicle-road-cloud system; the simulation information includes the attributes and behaviors of each agent unit in the traffic vehicle-road-cloud system, the disturbance application scenarios and the impacts of applied disturbances of the traffic vehicle-road-cloud system, and the basic simulation parameters of the traffic vehicle-road-cloud system; A simulation model initialization module, configured to initialize the simulation model of the traffic vehicle-road-cloud system by using the simulation information to generate an initialized simulation model of the traffic vehicle-road-cloud system; The initialized simulation model of the traffic vehicle-road-cloud system includes a road network model, each agent unit, and the interactive connection relationships between each agent unit; A simulation advancement and simulation result calculation module, configured to perform simulation advancement on the initialized simulation model of the traffic vehicle-road-cloud system according to the set simulation clock, and calculate the effectiveness index and resilience index of the traffic vehicle-road-cloud system after each round of simulation advancement.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the elastic modeling and simulation method of the traffic vehicle-road-cloud system according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the elastic modeling and simulation method of the traffic vehicle-road-cloud system according to any one of claims 1-6.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the elastic modeling and simulation method of the traffic vehicle-road-cloud system according to any one of claims 1-6.

Images