Ice and snow disaster road network operation resilience management system based on end road cloud cooperation

Abstract

This invention relates to a road network operation resilience management system based on end-to-end cloud collaboration for snow and ice disasters, belonging to the field of intelligent transportation system technology. The system includes: a real-time operation status perception module, an intelligent operation situation prediction module, a road network operation resilience assessment module, a road network traffic control module, an emergency response and rescue module, and a multi-party information collaboration module. The intelligent operation situation prediction module uses artificial intelligence algorithms based on multi-source data to predict future road network traffic flow, road surface ice and snow conditions, emergency response time, impact range of sudden abnormal events, and road network operation status. The road network operation resilience assessment module evaluates the expected duration of road network operation performance decline under the influence of snow and ice disasters, the timing of de-icing and snow removal for each road segment and node, the expected duration of road network operation performance recovery, the expected degree of road network operation performance recovery, and road network operation resilience based on a defined road network operation performance function. This invention can achieve road network safety and smooth traffic flow under snow and ice disasters.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation systems technology, and relates to a traffic control system, specifically a road network operation resilience management system based on end-to-road-cloud collaboration for snow and ice disasters. Background Technology

[0002] Ensuring road traffic safety during snow and ice disasters has long faced significant challenges and technical difficulties. Under severe weather conditions such as low temperatures, rain, snow, and ice, roads are prone to snow accumulation and ice formation, leading to a significant reduction in the road friction coefficient, increased vehicle braking distance, and a high risk of traffic accidents. This seriously threatens people's lives and property and severely impacts the normal operation of regional transportation networks.

[0003] Currently, existing technologies and management models have many shortcomings in responding to such snow and ice disasters. While passive control methods can ensure short-term safety to some extent, they lead to a rapid decline in the operational efficiency of the highway network, a severe lack of network resilience, and a high risk of large-scale, long-distance traffic congestion.

[0004] In terms of emergency response operations, the existing snow and ice removal mode has two major drawbacks: First, it is impossible to accurately and in real time obtain the snow and ice coverage of the entire road network and the real-time effect of snow and ice removal operations; second, the command and dispatch efficiency is low, which often leads to snow and ice removal equipment performing repetitive and inefficient operations on the same road section, resulting in waste of resources and delaying the best time to restore road traffic.

[0005] Despite significant advancements in highway operation and management systems in recent years, these systems generally prioritize routine traffic control over emergency response to severe weather. When sudden events such as snowstorms occur, existing systems often exhibit passive emergency response and slow decision-making. Specifically, this manifests as a lack of effective coordination between emergency response equipment (terminals), roadside control facilities (roads), and the operation command center (cloud), resulting in data silos, inefficient command transmission, and ultimately, low emergency response efficiency.

[0006] In summary, existing technologies for responding to snow and ice disasters generally suffer from problems such as incomplete perception of road network operation status, inaccurate prediction of snow and ice disaster impacts, unscientific decision-making regarding snow and ice removal operations, passive and simplistic emergency traffic control measures, and a lack of efficient coordination between terminals, roads, and the cloud. Therefore, there is an urgent need to develop a new type of road traffic control system. Summary of the Invention

[0007] In view of this, the purpose of this invention is to provide a road network operation resilience management system based on end-to-end cloud collaboration. This system integrates functions such as intelligent prediction of road network operation resilience under snow and ice weather, intelligent decision-making on the timing of road de-icing and snow removal operations, proactive traffic control before and after de-icing and snow removal operations, optimized configuration and dynamic scheduling of various emergency response equipment (such as drones, de-icing and snow removal equipment, warning vehicles, and obstacle clearing and rescue vehicles), networked grouping and operation of de-icing and snow removal equipment, and efficient information collaboration between multiple platforms. This fundamentally improves the safety assurance capability and traffic flow efficiency of the road traffic system under snow and ice disasters.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] Option 1: A road network operation resilience management system based on end-to-end cloud collaboration, comprising:

[0010] The real-time operational status sensing module is used to acquire multi-source data related to snow and ice disasters in real time, including severe weather data, sudden abnormal event data, road network traffic flow status data, road surface ice and snow status data, and emergency response equipment status data, etc.

[0011] The intelligent operational status prediction module is connected to the real-time operational status perception module and is used to predict future road network traffic flow, road surface icing and snow conditions, emergency response time, impact range of sudden abnormal events and road network operational status based on the multi-source data and artificial intelligence algorithms.

[0012] The road network operation resilience assessment module is connected to the intelligent operation status inference module. It is used to quantitatively assess the expected duration of the decline in road network operation performance under the influence of ice and snow disasters, the timing of de-icing and snow removal for each road segment and node, the expected duration of road network operation performance recovery, and the expected degree of road network operation performance recovery based on the defined time-varying road network operation performance function, thereby calculating the road network operation resilience.

[0013] The road network traffic control module is connected to the road network operation resilience assessment module and is used to carry out road network traffic control before and after snow and ice removal, with the goal of improving the road network operation resilience, and to generate and execute active traffic control strategies.

[0014] The emergency response and rescue module is connected to the real-time operation status perception module and the intelligent operation situation simulation module, and is used to dynamically schedule and coordinate the operation of emergency response equipment based on real-time and predicted status.

[0015] The multi-party information collaboration module is used to enable the sharing and interaction of system data and decision-making information across multiple platforms.

[0016] Furthermore, the real-time operational status sensing module specifically includes:

[0017] Obtain severe weather data in real time through a third-party meteorological platform;

[0018] Real-time acquisition of data on sudden abnormal events is achieved through roadside event detection equipment (such as roadside event detection PTZ cameras) and machine vision algorithms;

[0019] Real-time traffic flow data is obtained through roadside surveillance cameras, internet map platforms (such as Gaode / Baidu Maps), and machine vision algorithms.

[0020] Real-time data on road surface ice and snow conditions can be obtained using sensors (such as lidar) and image segmentation algorithms carried by drones.

[0021] Real-time status data of emergency response equipment can be obtained through positioning devices (such as GPS) mounted on the equipment.

[0022] Furthermore, the intelligent operational status simulation module specifically includes:

[0023] Based on historical and real-time road network traffic flow status data, a long short-term memory neural network model is used to obtain road network traffic flow prediction results.

[0024] Based on real-time perceived severe weather data and road icing and snow conditions data, the prediction results of road icing and snow conditions are obtained through an atmosphere-road coupled thermal energy field model.

[0025] Based on historical emergency response times and statistical results, we obtain predictions for emergency response times.

[0026] Based on traffic flow simulation software, the location of sudden abnormal events, real-time road network traffic flow status data, road network traffic flow prediction results, and emergency response time prediction results are used as input variables, and the road surface ice and snow coverage status prediction results are used as simulation environment parameters to simulate road network traffic flow and obtain the prediction results of the impact range of sudden abnormal events and the prediction results of road network operation status.

[0027] Furthermore, the road network operational resilience assessment module defines road network operational performance as a function that changes over time. And set the time when snow and ice weather occurs. The moment when snow and ice weather occurs, causing snow and ice disasters and resulting in a significant decline in the operational performance of the road network (such as traffic blockage on some road sections). When will the snow and ice removal emergency response and rescue take effect? The moment when the snow and ice removal emergency response and rescue operation ends. And the time when the snow and ice disaster ends , For the operational performance of the road network under normal conditions, To ensure the operational performance of the road network at the end of the snow and ice removal emergency response and rescue operation, To assess the operational performance of the road network before the snow and ice disaster caused traffic disruptions. The quantitative assessment of road network operational performance at the start of snow and ice removal emergency response includes:

[0028] Calculate the estimated duration of the road network performance degradation C1= ;

[0029] Determine the snow and ice removal time C2 for each road segment and node in the road network. ;

[0030] Calculate the estimated duration of road network operation performance recovery C3 ;

[0031] Calculate the expected recovery level of road network operating performance C4= ;

[0032] Calculate the operational resilience of the road network The expression is:

[0033]

[0034] in, , ;

[0035]

[0036] in, Indicates time The overall performance of the road network operation For the initial operating performance of the road network; For road section The importance weight of resilience, For road section Traffic capacity, Let be the set of directed edges in the road network graph;

[0037] Road segment performance degradation model:

[0038]

[0039] in, For a moment Section The performance degradation rate, For the first Such equipment in road sections Recovery efficiency This represents the maximum performance degradation rate. For road section The moment when performance begins to degrade To reach the moment of maximum degradation, and This is a parameter related to the degradation rate. This is the moment when performance begins to recover. The greater the resilience, The smaller.

[0040] Furthermore, the road network traffic control module specifically includes: based on the road network traffic flow simulation established by the intelligent operational situation inference module, loading traffic control strategies as intelligent agents, and employing a multi-agent deep reinforcement learning method to minimize the road network operational resilience. To optimize the objective, generate the optimal strategy combination.

[0041] The traffic control strategies include: variable speed limits for each section of highways, the per-minute traffic flow at each toll station on highways, and the cycle and green light ratio of traffic lights at urban road intersections.

[0042] Furthermore, the emergency response and rescue module specifically includes:

[0043] Responsive dynamic dispatching of emergency response equipment: A dynamic vehicle route planning optimization model is established, taking road network traffic flow status data, emergency response equipment status data, and road surface ice and snow status prediction as inputs. The objective is to minimize the total travel distance of emergency response equipment and prioritize the treatment of resilient critical road sections, while also considering the resilience recovery speed and the importance of road section resilience. Solving the model yields the optimal dispatching route for each emergency response equipment and the number of de-icing and snow removal equipment that needs to be dispatched.

[0044] Snow and ice removal equipment networked and coordinated operation: For road sections requiring multiple emergency response equipment operations, based on the number of snow and ice removal equipment and road surface ice and snow status data through responsive dynamic scheduling of emergency response equipment, and according to the vehicle dynamics model of snow and ice removal equipment, with the optimization objectives of maximizing snow and ice removal efficiency and coordination while minimizing costs, the system automatically plans the operation path, equipment spacing, and equipment operating speed of snow and ice removal equipment.

[0045] In the networked collaborative operation of the snow and ice removal equipment, the multi-objective optimization problem is expressed as follows:

[0046]

[0047] in,

[0048]

[0049] The constraints are:

[0050]

[0051] in, Let the de-icing efficiency be the objective function. Let the objective function be the total cost of de-icing. To equip the coordination objective function, This is a collection of mechanical de-icing and snow removal equipment (Type H) designed for re-icing. A collection of ice-melting equipment (L-type) designed for light ice formations; H-type de-icing efficiency. For L-shaped de-icing efficiency; , For H-type and L-type equipment, the operating cost coefficient is used. , The operating time for H-type and L-type equipment; For equipment The state vector, For a safe distance, For equipment At any moment The control input vector, , Equipment type The lower and upper limits of the control input vector, For equipment type At any moment Overall de-icing efficiency, For equipment type The lowest overall de-icing efficiency.

[0052] Emergency monitoring and command: Based on the road network operation resilience calculated by the road network operation resilience assessment module, the key nodes and road sections with the greatest road network operation resilience are identified, and drones are dispatched according to preset flight routes for emergency monitoring and command.

[0053] Option 2: A management method based on the ice and snow disaster road network operation resilience management system described in Option 1, comprising the following steps:

[0054] Sensing steps: Through the real-time operational status sensing module, multi-source data related to snow and ice disasters are acquired in real time, including severe weather data, sudden abnormal event data, road network traffic flow status data, road surface ice and snow status data, and emergency response equipment status data, etc.

[0055] The simulation process involves using the intelligent simulation module to predict future road network traffic flow, road surface icing and snow conditions, emergency response time, impact range of sudden abnormal events, and road network operation status.

[0056] Analysis steps: Using the road network operation resilience analysis module, based on the defined time-varying road network operation performance function and key time nodes, quantitatively calculate the relevant indicators of road network operation resilience;

[0057] Decision-making and control steps: Based on the analysis results, a traffic control strategy aimed at improving resilience is generated through the road network traffic control module, and a dynamic scheduling and collaborative operation plan for emergency response equipment is generated through the emergency response and rescue module.

[0058] Execution and coordination steps: Implement traffic control strategies and emergency response plans, and push relevant information to various platforms through the multi-party information collaboration module to support collaborative consultation.

[0059] The beneficial effects of this invention are as follows:

[0060] (1) Achieving a shift from passive response to proactive prediction: This invention establishes an intelligent operational situation simulation module, which can accurately predict the development trend of snow and ice disasters and their impact on the road network based on real-time data. This changes the traditional passive mode of relying on disasters to be dealt with after they occur, and realizes early warning and proactive intervention, winning valuable preparation time for traffic control and emergency response.

[0061] (2) Providing scientific and quantitative decision-making basis: This invention has innovatively proposed a quantitative assessment model of "road network operational resilience". It describes the performance loss and recovery process of the road network with specific mathematical indicators, so that managers can intuitively and scientifically assess the impact of disasters and the effectiveness of response, thereby replacing the decision-making method that relied on subjective experience in the past, making the decision more accurate and scientific.

[0062] (3) Significantly improve the intelligence and precision of traffic management: With the clear goal of improving the "road network operational resilience", the system uses artificial intelligence algorithms such as deep reinforcement learning to automatically optimize and generate the optimal combination of traffic management strategies (such as variable speed limits, flow control, etc.). This precision management with the goal of global optimization can slow down the rate of decline in traffic performance to the greatest extent and ensure the operational efficiency of the road network in disasters.

[0063] (4) Significantly improves the efficiency and coordination of emergency response: By dynamically optimizing the scheduling of emergency equipment and enabling networked formation collaborative operations, this invention solves the problems of blind scheduling, low operational efficiency, and resource waste in traditional emergency response. It achieves precise deployment and efficient utilization of emergency resources, significantly shortening the time required to restore road traffic.

[0064] (5) Breaking down information barriers between multiple platforms to achieve efficient collaborative operations: The "terminal-road-cloud" collaborative architecture and multi-party information collaboration platform constructed by this invention effectively integrate the data and command processes of multiple platforms. This breaks the deadlock of information isolation and inconsistent actions among various platforms in the past, forming an integrated emergency response system with unified command, information sharing, and rapid linkage, and comprehensively improving the overall synergy in responding to snow and ice disasters.

[0065] In summary, through technological innovation, this invention constructs a complete closed-loop management system for prediction, analysis, decision-making, control, and collaboration, which can fundamentally improve the safety assurance capability and traffic flow efficiency of the road traffic system under ice and snow disasters, and has extremely high practical value and promotion prospects.

[0066] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0067] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein:

[0068] Figure 1 This is a schematic diagram of the functional architecture of the control system proposed in Example 1;

[0069] Figure 2 This is a schematic diagram of a long short-term memory neural network architecture; Figure 3 A conceptual diagram illustrating the resilience of the road network.

[0070] Figure 4 This is a schematic diagram of road network traffic control strategies.

[0071] Figure 5 This is a schematic diagram of the information transmission architecture of the control system proposed in Example 1;

[0072] Figure 6 This is a schematic diagram of the application scenario of the control system proposed in Example 2. Detailed Implementation

[0073] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0074] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0075] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0076] Example 1:

[0077] Please see Figures 1-5 This embodiment proposes a road network operation resilience management system for snow and ice disasters based on end-to-road-cloud collaboration. Its functional architecture mainly includes six modules:

[0078] 1) Real-time operating status sensing module

[0079] It is used for real-time perception of severe weather data (pushed through a third-party meteorological platform) (denoted as A1), sudden abnormal event data (pushed through roadside event detection PTZ cameras) (denoted as A2), road network traffic flow status data (pushed through roadside monitoring cameras and Gaode / Baidu Maps platforms) (denoted as A3), road surface ice and snow status data (perceived through drones equipped with LiDAR and other sensors) (denoted as A4), and emergency response equipment status data (transmitted by GPS on the equipment) (denoted as A5).

[0080] Among them, A2, A3, and A4 are all perceived through machine vision-based target recognition or region segmentation algorithms.

[0081] 2) Intelligent operational status simulation module

[0082] Based on real-time operational status perception data, and through AI algorithms such as deep learning and reinforcement learning, the system obtains prediction results for road network traffic flow (denoted as B1), road surface icing and snow conditions (denoted as B2), emergency response time (denoted as B3), impact range of sudden abnormal events (denoted as B4), and road network operation status (denoted as B5). Furthermore, based on the AI ​​large model, the system fine-tunes to improve the generalization ability of each inference model to new scenarios outside the system scenario library.

[0083] Specifically, the input for road network traffic flow prediction based on a Long Short-Term Memory (LSTM) neural network is historical and real-time acquired road network traffic flow status data A3, specifically referring to historical and real-time acquired traffic flow data from highway mainline gantries and toll stations. After preprocessing the raw data, it is input into the LSTM neural network model for training, evaluation, and optimization. Using a "many-to-one" approach, the traffic flow for the next time period is predicted using traffic flow data from n time periods prior to the prediction time, thus outputting the road network traffic flow prediction result B1, specifically referring to the traffic flow from highway mainline gantries and toll stations in the next time period.

[0084] Long Short-Term Memory Neural Network Architecture, such as Figure 2 As shown, a complex gating mechanism (forget gate, input gate, output gate) is introduced to control and protect the information in the storage unit. The input gate determines how the information from the input layer is passed to the memory module in the hidden layer; the forget gate determines how the historical information of the memory module at the current time is retained; and the output gate determines how the information from the memory module is passed out. The state of the storage unit at time t is... The output of the storage unit at time t is The activation vector of the forget gate at time t The input gate activation vector at time t The activation function is The hyperbolic tangent function is tanh, and the input of the storage unit at time t is... .

[0085] Based on real-time perceived severe weather data A1 and road icing and snow condition data A4, a road icing and snow condition prediction result B2 is obtained through an atmosphere-road coupled thermal energy field model. Severe weather data A1 specifically includes air temperature A11, snowfall A12, air pressure A13, and wind speed A14; road icing and snow condition data A4 specifically includes road surface temperature A41 and road surface humidity A42; and the road icing and snow condition prediction result B2 specifically includes icing thickness. The atmosphere-road coupled thermal energy field model is as follows: input severe weather data A1 and road icing and snow condition data A4, and the road icing and snow condition prediction result B2 will be output.

[0086]

[0087] in, The weighting coefficients for the atmosphere-road coupled thermal energy field model were obtained through specific experiments.

[0088] Based on historical emergency response times and statistical results, the predicted emergency response time B3 is obtained. Using traffic flow simulation software (such as VISSIM or SUMO traffic simulation software), with the sudden abnormal event data A2 (using the location of the sudden abnormal event), road network traffic flow status data A3, road network traffic flow prediction result B1, and emergency response time prediction result B3 as input variables, and with the road surface ice and snow status prediction result B2 as the simulation environment parameter, road network traffic flow simulation is performed to obtain the predicted impact range of the sudden abnormal event B4 and the predicted road network operation status B5.

[0089] 3) Road network operation resilience assessment module

[0090] Based on historical system data, the following assessment parameters are calculated using the road network operation performance function: the expected duration of road network operation performance decline (denoted as C1), the timing of snow and ice removal for each road segment and node (denoted as C2), the expected duration of road network operation performance recovery (denoted as C3), and the expected degree of road network operation performance recovery (denoted as C4).

[0091] Specifically: Set the road network operating performance to be time-dependent. changing function This can be described using indicators such as the average speed of the expected journey from the road network's origin-destination (OD) point (from B5). Let... For the time when snow and ice occur, This refers to the moment when snow and ice weather occurs, causing snow and ice disasters and resulting in a significant decline in the operational performance of the road network (such as traffic blockages on some road sections). The moment when snow and ice removal emergency response and rescue take effect (i.e., the moment when system performance reaches its lowest point). ), This marks the end of the snow and ice removal emergency response and rescue operation (from B3). This marks the end of the snow and ice disaster (from A1). For the operational performance of the road network under normal conditions, To ensure the operational performance of the road network at the end of the snow and ice removal emergency response and rescue operation, To assess the operational performance of the road network before the snow and ice disaster caused traffic disruptions. To ensure the operational performance of the road network at the start of snow and ice removal emergency response and rescue operations. Therefore:

[0092] The expected duration of the decline in road network operational performance is C1= ;

[0093] Snow and ice removal time C2 for each road segment and node in the road network ;

[0094] Road network operational performance begins to recover; estimated duration C3= ;

[0095] The expected recovery level of road network operation performance is C4= ;

[0096] Road network operation performance functions:

[0097]

[0098] in, Indicates time The overall performance of the road network operation This represents the initial operational performance of the road network. For road section The importance weight of resilience (determined by managers based on experience). For road section The traffic capacity (i.e., the maximum number of vehicles that can theoretically pass through in one hour, which can be determined once the road is built, and is a constant in this model). Let be the set of directed edges in the road network graph.

[0099] To facilitate cross-scenario comparisons, normalized performance is defined as follows:

[0100] ,

[0101] Constructing a triangular index of road network operational resilience: ;

[0102] in, For road network operational resilience (the greater the resilience, the better) (smaller) Human recovery time for road network operation performance ( (This corresponds to the natural recovery time).

[0103] Area of ​​toughness loss: ;

[0104] Peak impact depth: ;

[0105] Average recovery speed ,in, The moment when system performance reaches its lowest point. .

[0106] Road segment performance degradation model:

[0107]

[0108] in, For a moment Section The performance degradation rate, For the first Such equipment in road sections Recovery efficiency This represents the maximum performance degradation rate. For road section The moment when performance begins to degrade To reach the moment of maximum degradation, and This is the degradation rate parameter. This is the moment when performance begins to recover. Therefore, yes and The function, i.e. .also,

[0109] .

[0110] Road segment resilience contribution:

[0111]

[0112] in, For road section The resilience contribution, The duration of snowy or icy weather.

[0113] 4) Road network traffic control module

[0114] Traffic control measures are implemented on the road network before and after snow and ice removal, aiming to improve... , stretch ,shorten To reduce This value enhances the resilience of the road network. A diagram illustrating road network resilience is shown below. Figure 3 As shown.

[0115] With the goal of improving the resilience of the road network, it includes road network traffic control functions such as variable speed limits on highway sections (denoted as D1), traffic flow control at highway toll stations (denoted as D2), and signal control of urban road networks (denoted as D3). The traffic guidance information generated by the control strategy is released through roadside information boards (roadside) and mobile phone navigation (accompanying).

[0116] Control strategies: such as Figure 4 As shown, based on the simulation established by the intelligent operational situation inference module, the control strategy is loaded as an intelligent agent (the intelligent agent includes the variable speed limit values ​​of each road segment in D1, the minute release flow value of each toll station in D2, and the cycle and green light ratio of traffic lights at urban road intersections in D3). Through multi-agent deep reinforcement learning methods, the road network operational resilience is assessed. The optimal policy combination is obtained by optimizing the reward function.

[0117] 5) Emergency Response and Rescue Module

[0118] Emergency response equipment responsive dynamic scheduling (denoted as E1): The road network is abstracted as a dynamic network. Using road network traffic flow status data (A3), emergency response equipment (i.e., snow and ice removal equipment) status data (A5), and road surface icing and snow conditions prediction results (B2) as inputs, a dynamic vehicle routing planning (DVRP) optimization model is constructed. This model aims to minimize the total travel distance of emergency response equipment and prioritize the treatment of resilient critical road segments, while considering both resilience recovery speed and the importance of road segment resilience impact. Solving this model yields the optimal scheduling path for each emergency response equipment and the number of equipment required for scheduling.

[0119] The objective function of the constructed Dynamic Vehicle Routing Planning (DVRP) optimization model is:

[0120]

[0121] in, The objective function is... For road network map, For a set of nodes, It is a directed edge set; For formation assembly; , The duration of snowy or icy weather; It is a set of road network nodes; For road section direction The set of lanes; For road section A set of driving directions; For road section Length; For formation At any moment Is it driving on a road section? Above, 1 represents yes, and 0 represents no; For formation At any moment The number of vehicles; For formation At any moment Is it at a road network node? A separation occurs; 1 represents yes, and 0 represents no. For formation and At any moment Is it at a road network node? Merge, 1 represents yes, 0 represents no; For road section The importance weight of resilience; For road section direction The Lane at time Has snow removal been completed? For formation On the road section direction Formation width; For formation At any moment Is it for the road section? direction Conduct the first For de-icing operations, 1 represents yes, and 0 represents no. For formation At any moment The number of vehicles; The operating width for road de-icing and snow removal equipment; For average recovery speed, For road section Resilience contribution; , These are the weighting coefficients.

[0122] Snow and ice removal equipment networked group collaborative operation (denoted as E2): For road sections requiring multiple vehicles to operate, based on the number of snow and ice removal equipment dispatched by E1 and the road surface ice and snow status data (A4), and according to the vehicle dynamics model of the snow and ice removal equipment, with the optimization objectives of maximizing snow and ice removal efficiency and coordination and minimizing costs, the system automatically plans the operation path, equipment spacing, and equipment operating speed of the snow and ice removal equipment, and issues instructions through vehicle-to-everything (V2X) technology to achieve centimeter-level collaborative operation, avoiding duplicate operations and blind spots.

[0123] The method for constructing the vehicle dynamics model of snow and ice removal equipment is as follows: taking into account air resistance, rolling resistance, slope resistance and different types of snow and ice removal resistance, the longitudinal dynamic equation and velocity influence function of the equipment are established.

[0124] (1) The longitudinal dynamic equation of the equipment

[0125]

[0126] This formula describes the motion state of a de-icing truck during de-icing operations. Among them, For equipment At any moment The weight of the L-shaped equipment will decrease as the de-icing agent is sprayed. For equipment At any moment speed; For equipment At any moment traction force; For equipment At any moment The driving resistance; For equipment At any moment De-icing resistance.

[0127]

[0128] in, For equipment The drag coefficient depends on the vehicle's shape; air density, For equipment Work speed; For equipment Frontal area, i.e., the projected area of ​​the front of the vehicle; For equipment Rolling resistance coefficient, For equipment At any moment quality It is the acceleration due to gravity. This refers to the road slope angle.

[0129] Classification of de-icing resistance models:

[0130]

[0131] in, The coefficient of friction on the ice surface for H-type equipment; The coefficient of friction for L-shaped equipment on ice surface; For H-type equipment cutting resistance; For L-type equipment, the resistance to de-icing agent spraying or the resistance to hot air blowing; The support force required for the equipment to withstand ice is related to the vehicle's weight and the road's gradient. This can be obtained in real time through vehicle sensors, or it can be... Estimate.

[0132] (2) Uniform velocity influence function

[0133]

[0134] This formula describes the impact of operating speed on de-icing efficiency and is applicable to all equipment types.

[0135] The multi-objective optimization problem is formulated as follows:

[0136]

[0137] in,

[0138]

[0139] The constraints are:

[0140]

[0141] in, Let the de-icing efficiency be the objective function. Let the objective function be the total cost of de-icing. To equip the coordination objective function, This is a collection of mechanical de-icing and snow removal equipment (Type H) designed for re-icing. A collection of ice-melting equipment (L-type) designed for light ice formations; H-type de-icing efficiency. For L-shaped de-icing efficiency; , For H-type and L-type equipment, the operating cost coefficient is used. , The operating time for H-type and L-type equipment; For equipment The state vector, For a safe distance, For equipment At any moment The control input vector, , Equipment type The lower and upper limits of the control input vector, For equipment type At any moment Overall de-icing efficiency, For equipment type The lowest overall de-icing efficiency.

[0142] Emergency Monitoring and Command (E3): The system automatically dispatches drones to the snowplow operation area for aerial hovering monitoring, transmitting high-definition video streams back to the command center in real time, providing a global and dynamic perspective for human command. The system automatically dispatches drones to these key areas for aerial hovering monitoring, transmitting high-definition video streams back to the command center in real time, providing a global and dynamic perspective for human command.

[0143] 6) Multi-party information collaboration module

[0144] like Figure 5As shown, this system acts as an information hub, capable of pushing relevant information to various platforms and breaking down data barriers between them. Deployed in the cloud, the system is accessible to all platforms. The system can push analysis and decision-making results, such as severe weather warnings, traffic control recommendations, and snow removal operation plans, to various platforms with a single click via standard data interfaces. Simultaneously, the system incorporates video conferencing and electronic map plotting functions, supporting real-time consultations and collaborative command among multiple parties on the same platform, forming a unified emergency response force.

[0145] Example 2: Application Scenario (refer to) Figure 6 )

[0146] 1) Forecast and Early Warning: The system senses impending heavy snow through a real-time operational status sensing module (such as a third-party meteorological platform). The intelligent operational status simulation module predicts a high risk of icing on key road sections (such as long uphill sections and bridges). The system automatically pushes early warning information to the platform.

[0147] 2) Proactive Control: When snowfall begins, the real-time operational status sensing module detects a decrease in vehicle speed. The road network traffic control module is activated, calculates the optimal speed limit scheme through a reinforcement learning model, and publishes information such as "The road ahead is slippery, speed limit 60km / h" through roadside information boards.

[0148] 3) Intelligent Decision-Making: A drone inspection detected that the snow depth on a certain road section exceeded a threshold. The road network resilience assessment module determined that if no action was taken, traffic on this road section would be interrupted in 20 minutes. (moment), leading to resilience indicators R The snowfall is rapidly increasing. The system decides to immediately initiate snow removal operations (determined). time).

[0149] 4) Collaborative Response: The emergency response and rescue module is activated. The emergency response equipment responsive dynamic dispatch (E1) function plans the optimal route based on real-time road conditions and equipment location, dispatching the three nearest snowplows to the affected area. The snow removal equipment network-connected platooning and collaborative operation (E2) function generates a triangular platooning operation plan for these three vehicles. Simultaneously, the road network traffic control module issues messages such as "Operation ahead, do not overtake" on the upstream road section of the snow removal operation. The emergency monitoring and command (E3) function dispatches drones to monitor the operation's effectiveness throughout the process.

[0150] 5) Information sharing: Throughout the process, all users share all information on the collaborative platform, keep abreast of the situation on site in real time, and link with the map provider platform to update event information and road closure status on the navigation map in real time.

[0151] 6) Traffic Restoration: After snow removal is completed and drones confirm that road conditions have been restored to traffic, the system lifts traffic restrictions and continuously monitors the road network to restore it to normal operation. The process.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A road network operation resilience management system based on end-to-end cloud collaboration, characterized in that, include: The real-time operational status sensing module is used to acquire multi-source data related to snow and ice disasters in real time, including severe weather data, sudden abnormal event data, road network traffic flow status data, road surface ice and snow status data, and emergency response equipment status data. The intelligent operational status prediction module is connected to the real-time operational status perception module and is used to predict future road network traffic flow, road surface icing and snow conditions, emergency response time, impact range of sudden abnormal events and road network operational status based on the multi-source data and artificial intelligence algorithms. The road network operation resilience assessment module is connected to the intelligent operation status inference module. It is used to quantitatively assess the expected duration of the decline in road network operation performance under the influence of ice and snow disasters, the timing of de-icing and snow removal for each road segment and node, the expected duration of road network operation performance recovery, and the expected degree of road network operation performance recovery based on the defined time-varying road network operation performance function, thereby calculating the road network operation resilience. The road network operational resilience assessment module specifically includes defining road network operational performance as a function that changes over time. And set the time when snow and ice weather occurs. The moment when snow and ice weather occurs, resulting in snow and ice disasters and a significant decline in the operational performance of the road network. When will the snow and ice removal emergency response and rescue take effect? The moment when the snow and ice removal emergency response and rescue operation ends. And the time when the snow and ice disaster ends , For the operational performance of the road network under normal conditions, To ensure the operational performance of the road network at the end of the snow and ice removal emergency response and rescue operation, To assess the operational performance of the road network before the snow and ice disaster caused traffic disruptions. The quantitative assessment of road network operational performance at the start of snow and ice removal emergency response includes: Calculate the estimated duration of the road network performance degradation C1= ; Determine the snow and ice removal time C2 for each road segment and node in the road network. ; The estimated duration for the road network's operational performance to begin recovering is C3. ; Calculate the expected recovery level of road network operating performance C4= ; Calculate the operational resilience of the road network The expression is: in, , ; in, Indicates time The overall performance of the road network operation For the initial operating performance of the road network; For road section The importance weight of resilience, For road section Traffic capacity, Let be the set of directed edges in the road network graph; Road segment performance degradation model: in, For a moment Section The performance degradation rate, For the first Such equipment in road sections Recovery efficiency This represents the maximum performance degradation rate. For road section The moment when performance begins to degrade To reach the moment of maximum degradation, and This is a parameter related to the degradation rate. This is the moment when performance begins to recover; The road network traffic control module is connected to the road network operation resilience assessment module and is used to carry out road network traffic control before and after snow and ice removal, with the goal of improving the road network operation resilience, and to generate and execute active traffic control strategies. The emergency response and rescue module is connected to the real-time operation status perception module and the intelligent operation situation simulation module, and is used to dynamically schedule and coordinate the operation of emergency response equipment based on real-time and predicted status. The multi-party information collaboration module is used to enable the sharing and interaction of system data and decision-making information across multiple platforms.

2. The road network operation resilience management system for ice and snow disasters according to claim 1, characterized in that, The real-time operational status sensing module specifically includes: Obtain severe weather data in real time through a third-party meteorological platform; Real-time acquisition of data on sudden abnormal events is achieved through roadside event detection equipment and machine vision algorithms; Real-time traffic flow data of the road network is obtained through roadside surveillance cameras, internet map platforms, and machine vision algorithms; Real-time data on road surface ice and snow conditions is obtained using sensors and image segmentation algorithms carried by drones. The positioning equipment on the emergency response equipment can be used to obtain real-time status data of the emergency response equipment.

3. The road network operation resilience control system for ice and snow disasters according to claim 1, characterized in that, The intelligent operational status simulation module specifically includes: Based on historical and real-time road network traffic flow status data, a long short-term memory neural network model is used to obtain road network traffic flow prediction results. Based on real-time perceived severe weather data and road icing and snow conditions data, the prediction results of road icing and snow conditions are obtained through an atmosphere-road coupled thermal energy field model. Based on historical emergency response times and statistical results, we obtain predictions for emergency response times. Based on traffic flow simulation software, the road network traffic flow status data, road network traffic flow prediction results, and emergency response time prediction results are used as input variables, and the road surface ice and snow coverage prediction results are used as simulation environment parameters to simulate road network traffic flow and obtain the prediction results of the impact range of sudden abnormal events and the prediction results of road network operation status.

4. The road network operation resilience control system for ice and snow disasters according to claim 1, characterized in that, The aforementioned road network traffic management module specifically includes: based on the road network traffic flow simulation established by the intelligent operational situation simulation module, loading traffic management strategies as intelligent agents, and employing a multi-agent deep reinforcement learning method to minimize the road network operational resilience. To optimize the objective, generate the optimal strategy combination; The traffic control strategies include: variable speed limits for each section of highways, the per-minute traffic flow at each toll station on highways, and the cycle and green light ratio of traffic lights at urban road intersections.

5. The road network operation resilience control system for ice and snow disasters according to claim 1, characterized in that, The emergency response and rescue module specifically includes: Responsive dynamic dispatching of emergency response equipment: A dynamic vehicle route planning optimization model is established, taking road network traffic flow status data, emergency response equipment status data, and road surface ice and snow status prediction as inputs. The objective is to minimize the total travel distance of emergency response equipment and prioritize the treatment of resilient critical road sections, while also considering the resilience recovery speed and the importance of road section resilience. Solving the model yields the optimal dispatching route for each emergency response equipment and the number of de-icing and snow removal equipment that needs to be dispatched. Snow and ice removal equipment networked and coordinated operation: For road sections requiring multiple emergency response equipment operations, based on the number of snow and ice removal equipment and road surface ice and snow status data of emergency response equipment response dynamic scheduling, and according to the vehicle dynamics model of snow and ice removal equipment, with the optimization objectives of maximizing snow and ice removal efficiency and coordination and minimizing costs, the system automatically plans the operation path, equipment spacing and equipment operating speed of snow and ice removal equipment. Emergency monitoring and command: Based on the road network operation resilience calculated by the road network operation resilience assessment module, the key nodes and road sections with the greatest road network operation resilience are identified, and drones are dispatched according to preset flight routes for emergency monitoring and command.

6. The road network operation resilience control system for snow and ice disasters according to claim 5, characterized in that, In the networked collaborative operation of the snow and ice removal equipment, the multi-objective optimization problem is expressed as follows: in, The constraints are: in, Let the de-icing efficiency be the objective function. Let the objective function be the total cost of de-icing. To equip the coordination objective function, This is a collection of mechanical de-icing and snow removal equipment designed for refreezing ice. A collection of ice and snow melting equipment designed for light, frozen ice. H-type de-icing efficiency. For L-shaped de-icing efficiency; , For H-type and L-type equipment, the operating cost coefficient is used. , The operating time for H-type and L-type equipment; For equipment The state vector, For a safe distance, For equipment At any moment The control input vector, , Equipment type The lower and upper limits of the control input vector, For equipment type At any moment Overall de-icing efficiency, For equipment type The lowest overall de-icing efficiency.

7. A control method based on the road network operation resilience control system for snow and ice disasters as described in any one of claims 1 to 6, characterized in that, The method includes the following steps: Sensing steps: Through the real-time operational status sensing module, multi-source data related to snow and ice disasters are acquired in real time, including severe weather data, sudden abnormal event data, road network traffic flow status data, road surface ice and snow status data, and emergency response equipment status data. The simulation process involves using the intelligent simulation module to predict future road network traffic flow, road surface icing and snow conditions, emergency response time, impact range of sudden abnormal events, and road network operation status. Analysis steps: Using the road network operation resilience analysis module, based on the defined time-varying road network operation performance function and key time nodes, quantitatively calculate the relevant indicators of road network operation resilience; Decision-making and control steps: Based on the analysis results, a traffic control strategy aimed at improving resilience is generated through the road network traffic control module, and a dynamic scheduling and collaborative operation plan for emergency response equipment is generated through the emergency response and rescue module. Execution and coordination steps: Implement traffic control strategies and emergency response plans, and push relevant information to various platforms through the multi-party information collaboration module to support collaborative consultation.

Images