Expressway reconstruction and extension traffic diversion method, system, equipment and medium

Abstract

The invention discloses an expressway reconstruction and extension traffic diversion method, system and device and a medium, and the method comprises the steps: obtaining multi-source dynamic traffic data, and constructing a road network origin-destination matrix through data fusion and demand deduction; a traffic flow distribution result is obtained by constructing a system optimal traffic distribution model; identifying the first congestion time period, and calculating the traffic flow exceeding the residual traffic capacity in the congestion time period to obtain the traffic flow to be shunted; solving an optimal shunting path under the target of minimizing the total travel time of the system through a hybrid intelligent algorithm to obtain an optimal shunting path scheme; and verifying the optimal shunting path scheme by using microscopic traffic simulation software, updating traffic data based on a simulation result, and carrying out iterative optimization to obtain a differentiated traffic organization scheme. According to the invention, the traffic flow passing efficiency during the highway reconstruction and extension period is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation systems, and in particular to a method, system, device and medium for traffic diversion of highway reconstruction and expansion. BACKGROUND

[0002] With the rapid growth of highway traffic in China, many early built highways have gradually appeared problems such as insufficient traffic capacity, declining service level, and serious road damage. These situations often become important reasons for frequent traffic congestion and increasing traffic accidents on highways. In order to improve the road network capacity and adapt to the continuous growth of traffic demand, it has become a common practice to reconstruct and expand highways. However, it is inevitable to occupy the lane during construction, which leads to a significant decrease in road traffic capacity, and easily causes serious traffic congestion, increases the probability of traffic accidents, and lengthens the vehicle delay time, increases exhaust emissions, and aggravates environmental pollution.

[0003] Traditional traffic diversion management methods mostly rely on experience to develop a fixed diversion scheme, or take some temporary emergency measures when the road is already severely congested. This approach lacks early prediction of traffic condition changes and lacks the ability to dynamically adjust. In the face of the time-varying and random nature of traffic flow, these methods often seem inadequate, and the actual effect is not ideal.

[0004] In existing technologies, although there are studies that attempt to plan diversion paths through traffic simulation or simple algorithms, these methods also have some obvious shortcomings. First, most schemes are only designed for static diversion strategies at a certain moment, and cannot achieve all-weather, rolling dynamic optimization, and cannot keep up with the changing rhythm of real traffic flow. Second, the algorithm used to solve the diversion path is relatively simple, either fast in calculation but not ideal in result, or pursuing global optimization but taking too long, making it difficult to balance between solution efficiency and scheme quality. Third, these methods usually only stay at the macro-level model calculation, lack of a closed-loop mechanism of putting the macro-scheme into the micro-simulation environment for repeated verification and iterative optimization, resulting in insufficient reliability and adaptability of the final generated diversion scheme in actual application. Therefore, there is an urgent need for an intelligent diversion method that can be based on real-time traffic data, achieve dynamic allocation, and undergo multiple rounds of simulation verification and optimization, to effectively cope with the complex traffic pressure brought by reconstruction and expansion construction. SUMMARY

[0005] In view of the above existing problems, the present application is proposed.

[0006] Therefore, the application provides a highway reconstruction and expansion traffic diversion method, system, equipment and medium to solve the problems that the existing traffic diversion method is difficult to cope with the time-varying and complexity of traffic flow during reconstruction and expansion due to the lack of dynamic optimization and simulation feedback iteration mechanism based on real-time data, resulting in poor predictability and insufficient reliability of the scheme.

[0007] To solve the above technical problems, the application provides the following technical solutions: In a first aspect, the application provides a highway reconstruction and expansion traffic diversion method, comprising: Obtaining multi-source dynamic traffic data, constructing a road network origin-destination matrix through data fusion and demand deduction; Based on the road network origin-destination matrix, a system optimal traffic assignment model is constructed to obtain traffic flow assignment results; Based on the traffic flow assignment results, the first congestion period is identified, and the traffic volume exceeding the remaining traffic capacity of the congestion period is calculated to obtain the traffic volume to be diverted; Based on the traffic volume to be diverted, the optimal diversion path under the minimum system total travel time objective is solved by a hybrid intelligent algorithm to obtain an optimal diversion path scheme; The optimal diversion path scheme is verified by using microscopic traffic simulation software, and the traffic data is updated and iteratively optimized based on the simulation results to obtain a differentiated traffic organization scheme.

[0008] As a preferred scheme of the highway reconstruction and expansion traffic diversion method of the application, wherein: the traffic flow assignment results are obtained, comprising: Based on multi-source dynamic traffic data, a road network topology structure including nodes, road segments and origin-destination pairs is constructed to form a basic expression of the traffic network; Based on the road network topology structure, a mathematical model with the optimization objective of minimizing the total vehicle travel time of the road network is set to establish a modeling framework for system optimal traffic assignment; Based on the optimization objective, the travel time of each road segment is calculated by using a function that increases with the power of the ratio of flow to capacity, to determine the functional relationship between road segment impedance and flow; Based on the functional relationship between road segment impedance and flow, a complete system optimal traffic assignment model is constructed by introducing flow conservation constraints and capacity constraints; Based on the system optimal traffic assignment model, the optimal solution that satisfies all constraints is solved to obtain the traffic flow assignment results of the road network in each period.

[0009] As a preferred scheme of the highway reconstruction and expansion traffic diversion method of the application, wherein: the first congestion period is identified, comprising: Divide the target prediction period into multiple consecutive time intervals; For each time interval, the ratio of traffic volume to capacity of the key section of the construction road section is calculated based on the traffic flow distribution result; When the road saturation first exceeds the preset threshold, the corresponding time interval is determined as the first congestion period.

[0010] As a preferred scheme of the expressway reconstruction and expansion traffic diversion method, the mixed intelligent algorithm comprises: An improved shortest path algorithm is used to generate multiple feasible paths with the shortest travel time for each origin-destination pair based on real-time traffic state, and the feasible path set of all origin-destination pairs constitutes an initial path set; Based on the initial path set, a swarm intelligence optimization algorithm is used for global optimization solution.

[0011] As a preferred scheme of the expressway reconstruction and expansion traffic diversion method, the improved shortest path algorithm and the swarm intelligence optimization algorithm comprise: In the improved shortest path algorithm, the dynamic travel time calculated based on real-time traffic data is used as the path weight, and the time-varying limit of the construction road section capacity is considered to generate multiple shortest feasible paths for each origin-destination pair; In the swarm intelligence optimization algorithm, a fitness function is constructed with the minimization of the total travel time as the target, and population evolution is performed through selection, crossover and mutation operations; In the mutation operation, the improved shortest path algorithm is called to generate a new feasible path, and the path combination of the individual is updated.

[0012] The preferred technical scheme has the beneficial effects that by integrating dynamic traffic state and construction constraints into path generation and dynamically calling the improved shortest path algorithm to expand the search space in the optimization process, efficient global optimization of large-scale road network diversion paths is realized, and the adaptability and reliability of the traffic organization scheme are improved.

[0013] As a preferred scheme of the expressway reconstruction and expansion traffic diversion method, the micro-traffic simulation tool comprises: A refined road network model including the reconstructed and expanded expressway, interchanges, parallel trunk highways and local roads is established in the simulation software; Vehicle type ratio, driving behavior parameters, signal timing and path selection logic are set; After running the simulation, the average vehicle speed, vehicle delay and traffic load level of each road section at different time periods are output as the basis for operation state evaluation.

[0014] As a preferred scheme of the expressway reconstruction and expansion traffic diversion method, the difference traffic organization scheme comprises: Based on the optimal diversion path scheme, the diversion scheme is finely simulated and run through micro-traffic simulation software; According to the simulation output road section average speed, vehicle delay time and road saturation, the service level classification standard is comprehensively analyzed; If the service level of any road section in any time period is lower than the third service level, it is determined that there is time period congestion; When it is determined that there is time period congestion, based on the simulation output traffic flow data of each road section, the traffic demand of each time period is back calculated and updated, and traffic flow distribution and optimal diversion path solving are re-executed; If the service levels of all key road sections in the target prediction time period are not lower than the third service level, it is determined that there is no time period congestion; When it is determined that there is no time period congestion, based on the optimal diversion path scheme solved last time, a difference traffic organization scheme for transit traffic, external traffic and regional traffic is generated.

[0015] The beneficial effects of the preferred technical scheme are that the micro-simulation results are dynamically fed back to the macro-model, the traffic demand and diversion path are iteratively updated, the closed-loop optimization of the traffic organization scheme is realized, the time period congestion is effectively eliminated, and the road network operation efficiency and the fine level of the scheme are improved.

[0016] In a second aspect, the present application provides an expressway reconstruction and expansion traffic diversion system, comprising: The matrix construction module is used for obtaining multi-source dynamic traffic data, constructing a road network origin-destination matrix through data fusion and demand deduction; The system optimal traffic flow distribution module is used for obtaining traffic flow distribution results based on the road network origin-destination matrix by constructing a system optimal traffic distribution model; The to-be-diverted traffic flow calculation module is used for identifying a first congestion time period based on the traffic flow distribution results, calculating the traffic flow exceeding the remaining traffic capacity in the congestion time period, and obtaining the to-be-diverted traffic flow; The hybrid intelligent diversion path optimization module is used for solving the optimal diversion path under the system total travel time minimization target based on the to-be-diverted traffic flow through a hybrid intelligent algorithm, and obtaining an optimal diversion path scheme; The traffic organization scheme generation module is used for verifying the optimal diversion path scheme by using micro-traffic simulation software, updating traffic data based on the simulation results and iteratively optimizing, and obtaining a difference traffic organization scheme.

[0017] In a third aspect, the present application provides an electronic device, comprising: a memory for storing a program; a processor for executing the computer executable instructions, which, when executed by the processor, implement the steps of the expressway reconstruction traffic diversion method.

[0018] In a fourth aspect, the present application provides a computer readable storage medium, comprising: the program, when executed by a processor, implements the steps of the expressway reconstruction traffic diversion method.

[0019] The present application has the following beneficial effects: the present application dynamically couples a macroscopic traffic distribution model with a microscopic traffic simulation tool, and uses road saturation, vehicle speed and delay and other indicators output by the simulation as evaluation basis, to achieve fine verification and iterative optimization of the traffic organization scheme; the present application fuses an improved shortest path algorithm with a swarm intelligence optimization algorithm in a hybrid intelligent algorithm, and dynamically calls a path generation mechanism in a mutation operation, to achieve efficient global search and adaptive optimization of large-scale road network diversion paths; the present application backtracks and updates origin-destination traffic demand based on simulation feedback, reconstructs a system optimal traffic distribution model and re-solves optimal diversion paths, to achieve closed-loop optimization of traffic demand evolution and coordinated evolution of control strategies, and effectively eliminate time-periodic congestion of the reconstruction section. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor. Among them: Figure 1 A basic flowchart of an expressway reconstruction traffic diversion method provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0022] Embodiment 1, refer to Figure 1 An expressway reconstruction traffic diversion method is provided by an embodiment of the present application, comprising: S100: acquiring multi-source dynamic traffic data, constructing a road network origin-destination matrix through data fusion and demand deduction; S200: Based on the road network origin-destination matrix, the traffic flow distribution result is obtained by constructing a system optimal traffic assignment model; S300: Based on the traffic flow distribution result, the first congestion period is identified, and the traffic flow exceeding the remaining traffic capacity of the congestion period is calculated to obtain the traffic flow to be distributed; S400: Based on the traffic flow to be distributed, the optimal distribution path under the minimum system travel time is solved by a hybrid intelligent algorithm to obtain the optimal distribution path scheme; S500: The optimal distribution path scheme is verified by using micro-traffic simulation software, and the traffic data is updated based on the simulation result and iteratively optimized to obtain a differentiated traffic organization scheme.

[0023] It should be noted that the existing traffic distribution method faces many challenges during operation, including the dependence on static traffic data and fixed path planning, the difficulty in adapting to the time-varying nature of traffic demand and sudden congestion, the lack of fine depiction of the dynamic changes of construction road section traffic capacity, leading to the disconnection between the distribution scheme and the actual road network operation state, the use of a single optimization model in most methods, the lack of effective coupling between macro-traffic distribution and micro-traffic simulation, and the inability to accurately evaluate the actual operation effect after the implementation of the scheme, the lack of iterative optimization mechanism based on simulation feedback, the difficulty in identifying and eliminating period congestion, and the limited distribution effect. In addition, there is a lack of differentiated guidance for different types of traffic flow such as transit, external and regional, making it difficult to provide fine and adaptive traffic organization strategies for complex road networks.

[0024] Therefore, in view of the above-mentioned problems of the existing traffic distribution method, such as the lack of dynamic optimization based on real-time data and simulation feedback iteration mechanism, the difficulty in dealing with the time-varying nature and complexity of traffic flow during reconstruction and expansion, the poor predictability and insufficient reliability of the scheme, through the steps of S100-S500, by fusing macro-traffic distribution and micro-traffic simulation, combining the improved path algorithm considering dynamic travel time and time-varying traffic capacity and the closed-loop iterative optimization mechanism, the precise identification, efficient distribution and continuous optimization of transit, external and regional traffic flow during highway reconstruction and expansion are realized, the period congestion is effectively alleviated, and the overall operation efficiency of the road network and the intelligent and fine level of the traffic organization scheme are significantly improved.

[0025] Embodiment 2, which is an embodiment of the present application, provides a highway reconstruction and expansion traffic distribution method based on the previous embodiment, comprising: In the embodiment of the present application, the multi-source dynamic traffic data in step S100 refers to real-time information such as traffic flow, average speed, time occupancy rate, etc. collected by fixed detectors, floating car GPS and historical files. The Origin-Destination Matrix, i.e. the origin-destination traffic demand matrix, describes the traffic flow distribution between each origin and destination. In the embodiment of the present application, the multi-source dynamic traffic data is obtained, combined with historical same-day traffic characteristics and real-time state, and the traffic demand of each period within 24 hours in the future is deduced. Through data fusion and demand deduction, the time-varying Origin-Destination Matrix of the road network is constructed. In the embodiment of the present application, the multi-source dynamic traffic data fusion and OD demand deduction in step S100 includes fusing multi-source data such as fixed detectors, floating car GPS and historical traffic flow, deducing the traffic demand of each period within 24 hours in the future after cleaning and completing, and constructing the time-varying Origin-Destination Matrix of the road network.

[0026] In an optional implementation, the multi-source dynamic traffic data fusion and OD demand deduction in step S100 can also use the mobile phone user base station handover record provided by the operator to calculate the user origin-destination location through space-time clustering and trip chain identification technology, generate and update the time-varying Origin-Destination Matrix of the road network within 24 hours in the future, and use it as the input of the system optimal traffic assignment model.

[0027] In an optional implementation, the multi-source dynamic traffic data fusion and OD demand deduction in step S100 can also construct a time series prediction model such as LSTM or Transformer, input historical traffic flow, weather, holiday and other feature data, train and predict the OD demand of each period within 24 hours in the future, and generate the time-varying Origin-Destination Matrix of the road network for traffic assignment calculation.

[0028] In the embodiment of the present application, the traffic flow assignment result obtained in step S200 includes: Based on the multi-source dynamic traffic data, a road network topology structure including nodes, road segments and origin-destination pairs is constructed to form the basic expression of the traffic network; Based on the road network topology structure, a mathematical model with the optimization objective of minimizing the total vehicle travel time of the road network is set to establish the modeling framework of the system optimal traffic assignment; Based on the optimization objective, the travel time of each road segment is calculated by using a function whose travel time increases with the power of the ratio of flow to capacity, to determine the functional relationship between road segment impedance and flow; Based on the functional relationship between the road segment impedance and the flow, a complete system optimal traffic assignment model is constructed by introducing flow conservation constraints and capacity constraints; Based on the system optimal traffic assignment model, by solving the optimal solution satisfying all constraint conditions, the traffic flow distribution result of the road network in each period is obtained.

[0029] In the embodiment of the application, the system optimal (SO) traffic assignment model construction in step S200 includes minimizing the total travel time of the road network as the target, using the BPR function to calculate the dynamic travel time of the link, introducing the flow conservation, the link flow expression and the non-negative constraint to construct and solve the system optimal traffic assignment model satisfying the Wardrop second principle, and obtaining the traffic flow distribution result in each period.

[0030] In an optional implementation, the system optimal (SO) traffic assignment model construction in step S200 can also model the road network as a Markov decision process, design a reward function with the minimum total travel time of the system as the target, learn the optimal path selection strategy by training the DQN or PPO intelligent agent of reinforcement learning, and dynamically output the traffic flow distribution result in each period as the distribution basis.

[0031] In an optional implementation, the system optimal (SO) traffic assignment model construction in step S200 can also calculate the link travel time based on the BPR function, take the Wardrop first principle as the equilibrium condition, solve the user equilibrium state that the travel times of all used paths between each OD pair are equal and minimum by using the iterative distribution algorithm, and obtain the traffic flow distribution result conforming to the path selection behavior of actual travelers.

[0032] In the embodiment of the application, based on the road network topology, a modeling framework of system optimal traffic assignment is established by setting a mathematical model with the minimum total vehicle travel time of the road network as the optimization target; the objective function is represented as: wherein, is the flow on the link is the travel time function on the link

[0033] In the embodiment of the application, based on the optimization target, the function relationship between the link impedance and the flow is determined by using a function with the power function growth of the link travel time with the ratio of the flow to the capacity; specifically, the travel time is calculated by using the BPR (Bureau of Public Roads) function and represented as: wherein, is the free flow time of the link is the capacity of the link is the link​​​​ The parameters of the BPR function.

[0034] In this embodiment, based on the functional relationship between the road segment impedance and traffic flow, a complete optimal traffic assignment model is constructed by introducing the following constraints: (1) The traffic demand between all origin-destination pairs must be satisfied, i.e., the flow conservation constraint must be satisfied: in, To start from the beginning To the finish line via path Traffic, To correspond to the demand for OD pairs, For the set of all feasible paths, It is the set of all origin-endpoint pairs.

[0035] (2) The traffic flow of a road segment is obtained by summing the traffic flows of each path, and is consistent with the path-segment correlation: in, For path-segment association indicator variables, if path Included road sections If the value is 1, then the value is 1; otherwise, it is 0.

[0036] (3) Path flow non-negativity constraint: In addition, the model also implicitly includes road segment capacity constraints, namely , used to reflect the time-varying restrictions on the traffic capacity of the construction section.

[0037] In this embodiment, based on the system's optimal traffic assignment model, the traffic flow assignment results for each time period are obtained by solving for the optimal solution that satisfies all constraints. This optimal solution satisfies Wardrop's second principle, that is, all used paths have equal and minimum marginal travel costs. Its mathematical expression is: in, For road section The marginal travel time is defined as: In this embodiment of the application, identifying the first congestion period in step S300 includes: Divide the target forecast period (e.g., the next 24 hours) into multiple consecutive time intervals; for example, divide it into time intervals of 0:00–1:00, 1:00–2:00, …, 8:00–9:00, etc., using 1 hour as the unit; For each time interval, the ratio of traffic volume and capacity of the key section of the construction road section is calculated based on the traffic flow distribution result; When the road saturation first exceeds the preset threshold, the corresponding time interval is determined as the first congestion period.

[0038] In the embodiment of the present application, the preset threshold is that the road saturation is greater than 1.0 or the average speed of the road section is less than 60% of the free flow speed; In the embodiment of the present application, the hybrid intelligent algorithm in step S400 includes: An improved shortest path algorithm is used to generate a plurality of feasible paths with the shortest travel time for each origin-destination pair based on real-time traffic state, and the feasible path set of all origin-destination pairs constitutes an initial path set; Based on the initial path set, a swarm intelligence optimization algorithm is used for global optimization solution.

[0039] In the embodiment of the present application, the improved shortest path algorithm is specifically an improved Dijkstra algorithm, which takes the dynamic travel time as the edge weight and records the first K shortest paths during the algorithm execution process to realize the generation of K shortest paths (KSP); the swarm intelligence optimization algorithm is specifically a genetic algorithm (GA), which calls the improved Dijkstra algorithm to generate new paths in the mutation operation, and calculates the fitness function according to the path combination, and realizes the population evolution through selection, crossover and mutation operations.

[0040] In the embodiment of the present application, the dynamic travel time used for path search in step S400 adopts the road section travel time calculated by the system optimization model in step S200 as the initial weight, and is dynamically updated according to the road section flow after the load of the diversion path in the iteration process of the genetic algorithm.

[0041] In the embodiment of the present application, the hybrid intelligent algorithm for solving the optimal diversion path in step S400 includes using the improved Dijkstra algorithm to generate a plurality of shortest paths of each OD pair as the initial path set with the dynamic travel time as the weight, and then combining the genetic algorithm to realize global optimization through selection, crossover and mutation operations, and calling the improved Dijkstra to generate new paths in the mutation process, and finally solving the optimal diversion path scheme with the minimum system total travel time.

[0042] In an optional embodiment, the hybrid intelligent algorithm for solving the optimal diversion path in step S400 can also take the reciprocal of the path travel time as heuristic information, construct paths in the road network by the ant individuals and release pheromone, and after multiple iterations, converge to the optimal path combination with the minimum system total travel time by using the pheromone concentration update mechanism, so as to generate the optimal diversion path scheme.

[0043] In an alternative embodiment, the mixed intelligent algorithm in step S400 can also model the road network as a graph structure, learn the embedding representation of nodes and edges using GNN, decode the origin and destination nodes of the OD pair using a pointer network, and generate the optimal path combination with the minimum system total travel time, thereby outputting the optimal split path scheme.

[0044] In the embodiments of the present application, the improved shortest path algorithm and swarm intelligence optimization algorithm in step S400 include: In the improved shortest path algorithm, the dynamic travel time calculated based on real-time traffic data is used as the path weight, and the time-varying restriction of the construction section passing capacity is considered to generate multiple shortest feasible paths for each origin-destination pair; and during the execution of the algorithm, when the target node is visited or the current node cannot continue to expand (i.e. u==0), the search is immediately terminated to improve the calculation efficiency.

[0045] In the swarm intelligence optimization algorithm, a fitness function is constructed to minimize the system total travel time, and population evolution is performed through selection, crossover and mutation operations. In the mutation operation, the improved shortest path algorithm is called to generate a new feasible path, and the path combination of the individual is updated.

[0046] In the embodiments of the present application, the microscopic traffic simulation software in step S500 includes: In the simulation software, a refined road network model is established, which includes the expanded expressway, interchanges, parallel trunk highways and local roads; the optimal split path scheme is converted into the path decision points, vehicle path selection proportion and flow allocation parameters required by the simulation software; and the vehicle type composition, driving behavior parameters, signal timing and path selection logic are set; The vehicle type proportion, driving behavior parameters, signal timing and path selection logic are set; After running the simulation, the average vehicle speed, vehicle delay and traffic load level of each road section at different time periods are output as the basis for evaluating the running state.

[0047] In the embodiments of the present application, the generation of the final differentiated traffic organization scheme in step S500 includes: Based on the optimal split path scheme, the split scheme is simulated and run in detail by the microscopic traffic simulation software; According to the simulation output of the average vehicle speed, vehicle delay time and road saturation, the comprehensive analysis is performed by referring to the highway service level classification standard; If the service level of any road section at any time period is lower than the third level service level, it is determined that there is time-dependent congestion; When it is determined that there is period congestion, based on the simulation output of each road traffic flow data, the traffic demand of each period is back calculated and updated, and the traffic flow distribution and optimal diversion path solving are re-executed; If the service level of all key road segments in the target prediction period is not lower than the third level, it is determined that there is no period congestion. When it is determined that there is no period congestion, based on the optimal diversion path scheme solved last time, a differentiated traffic organization scheme is obtained.

[0048] In the embodiments of the present application, the residual error between the road segment flow and the current OD matrix The calculated road segment flow is corrected by using the generalized least squares method (GLS) or maximum likelihood estimation method to obtain the updated time-varying OD demand matrix.

[0049] In the embodiments of the present application, the micro-traffic simulation verification and iterative optimization in step S500 includes constructing a refined road network model in a micro-traffic simulation software such as VISSIM and setting vehicle path selection, driving behavior and signal control parameters based on the optimal diversion path scheme, analyzing the vehicle speed, delay and saturation of each road segment after running the simulation, and if there is period congestion with service level lower than the third level, updating the OD demand and iteratively optimizing the diversion scheme until the service level of the whole road network within 24 hours meets the standard.

[0050] In an optional embodiment, the micro-traffic simulation verification and iterative optimization in step S500 can also include constructing a road network in SUMO, configuring traffic demand and path selection logic based on the optimal diversion path scheme, running a lightweight simulation and outputting the vehicle speed, delay and saturation of each period, and if period congestion with service level lower than the third level is identified, updating the OD demand and iteratively optimizing the diversion scheme until the operation state of the whole road network within 24 hours meets the standard.

[0051] In an optional embodiment, the micro-traffic simulation verification and iterative optimization in step S500 can also divide the road network into a plurality of cells, simulate the propagation and congestion evolution process of traffic flow in each period by using CTM, combine local micro-models to process key node behaviors, judge whether there is period congestion by outputting the road segment flow, density and speed, and if not, update the OD demand and iteratively optimize the diversion scheme until the service level of the whole road network within 24 hours is not lower than the third level.

[0052] In the embodiments of the present application, the transit traffic is guided to the parallel expressway away from the urban area; the external traffic is guided to the trunk highway such as national highway and provincial highway; the regional traffic is provided with multiple path selection, and the optimal path information is dynamically published through channels such as variable message sign and navigation APP.

[0053] In the embodiment of the present application, if the service levels of all key road sections in each time period within the target prediction period of 24 hours are not lower than the third level, it is determined that there is no time period congestion; the iteration process continues until the simulation verification shows that the service levels of all key road sections within 24 hours are not lower than the third level, ensuring that the road network is smooth in all time periods.

[0054] In the embodiment of the present application, the judgment threshold of the third level of service is set based on the "Highway Service Level Standard", and is quantitatively evaluated according to the average speed of road sections, vehicle delay time and saturation (V / C ratio) output by VISSIM simulation.

[0055] In the embodiment of the present application, the present application aims to generate differentiated traffic organization schemes for different travel groups, which are divided according to travel purposes, origin-destination locations and travel path characteristics; for example, including transit traffic groups characterized by long-distance passing traffic, external traffic groups for the purpose of commuting or freight into and out of the city, and regional traffic groups mainly for internal commuting and living traffic in the city; for different group travel demand characteristics, differentiated path guidance and information release strategies are adopted: for transit traffic groups, preferentially guide to parallel highways away from urban areas to provide seamless and efficient passing channels; the external traffic group uses the trunk roads such as national and provincial roads as alternative paths to ensure the traffic efficiency of entering and leaving the city; for the regional traffic group, multiple path options including local roads are provided, and real-time optimal paths are dynamically released through channels such as CMS, navigation APP, etc. to induce vehicles to be evenly distributed in the local road network.

[0056] Embodiment 3, this is an embodiment of the present application, which is different from the first embodiment in that a highway reconstruction and expansion traffic diversion system is provided.

[0057] It should be noted that the technical scheme of the highway reconstruction and expansion traffic diversion system belongs to the same concept as the technical scheme of the highway reconstruction and expansion traffic diversion method described above, and the details of the technical scheme of the highway reconstruction and expansion traffic diversion system in the present embodiment can be referred to the description of the technical scheme of the highway reconstruction and expansion traffic diversion method.

[0058] The highway reconstruction and expansion traffic diversion system in the present embodiment comprises: A matrix construction module is configured to obtain multi-source dynamic traffic data, and construct a road network origin-destination point matrix through data fusion and demand deduction. A system optimal traffic flow distribution module is configured to obtain a traffic flow distribution result by constructing a system optimal traffic distribution model based on the road network origin-destination point matrix. The to-be-shunted traffic flow calculation module is configured to identify a first congestion period based on the traffic flow distribution result, and calculate a traffic flow exceeding the remaining traffic capacity in the congestion period to obtain a to-be-shunted traffic flow; The hybrid intelligent shunting path optimization module is configured to solve an optimal shunting path under a system total travel time minimization target based on the to-be-shunted traffic flow by using a hybrid intelligent algorithm to obtain an optimal shunting path scheme. The traffic organization scheme generation module is configured to verify the optimal shunting path scheme by using a microscopic traffic simulation software, update traffic data based on a simulation result, and iteratively optimize to obtain a differential traffic organization scheme.

[0059] The embodiment also provides an electronic device suitable for the case of the expressway reconstruction and expansion traffic shunting method, which comprises: The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the expressway reconstruction and expansion traffic shunting method.

[0060] The embodiment also provides a storage medium having a computer program stored thereon, and the program is executed by a processor to implement the expressway reconstruction and expansion traffic shunting method.

[0061] The storage medium provided by the embodiment belongs to the same inventive concept as the expressway reconstruction and expansion traffic shunting method, and the technical details not described in the embodiment can be referred to the above embodiments, and the embodiment has the same beneficial effects as the above embodiments.

[0062] From the above description about the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH, a hard disk or an optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method of each embodiment of the present application.

[0063] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A method for diverting traffic during reconstruction and expansion of a highway, characterized by, The method comprises the following steps: acquiring multi-source dynamic traffic data, constructing a road network origin-destination matrix through data fusion and demand deduction; based on the road network origin-destination matrix, obtaining traffic flow distribution results by constructing a system optimal traffic distribution model; based on the traffic flow distribution results, identifying a first congestion period and calculating the traffic volume exceeding the remaining traffic capacity in the congestion period to obtain a traffic volume to be distributed; based on the traffic volume to be distributed, solving an optimal distribution path under the minimum system total travel time by a hybrid intelligent algorithm to obtain an optimal distribution path scheme; verifying the optimal distribution path scheme by using a microscopic traffic simulation software, updating the traffic data based on the simulation results and iteratively optimizing to obtain a differentiated traffic organization scheme.

2. The highway reconstruction and expansion traffic diversion method according to claim 1, characterized in that: The traffic flow distribution results are obtained by: based on multi-source dynamic traffic data, forming a basic expression of the traffic network by constructing a road network topology structure including nodes, road segments and origin-destination pairs; based on the road network topology structure, establishing a modeling framework of system optimal traffic distribution by setting a mathematical model with the minimum total vehicle travel time of the road network as the optimization objective; based on the optimization objective, determining the functional relationship between road segment impedance and flow by calculating the travel time of each road segment using a function with the power of the ratio of flow to capacity; based on the functional relationship between road segment impedance and flow, constructing a complete system optimal traffic distribution model by introducing flow conservation constraints and capacity constraints; based on the system optimal traffic distribution model, obtaining the traffic flow distribution results of the road network in each period by solving the optimal solution that meets all the constraints.

3. The highway reconstruction and expansion traffic diversion method according to claim 1 or 2, characterized by: The first congestion period is identified by: dividing the target prediction period into multiple continuous time intervals; for each time interval, calculating the ratio of traffic volume to capacity of the key section of the construction road based on the traffic flow distribution results; when the road saturation first exceeds the preset threshold, determining the corresponding time interval as the first congestion period.

4. The highway reconstruction and expansion traffic diversion method according to claim 3, characterized in that: The hybrid intelligent algorithm comprises: using an improved shortest path algorithm to generate multiple feasible paths with the shortest travel time for each origin-destination pair based on real-time traffic conditions, and constructing an initial path set by combining the feasible paths of all origin-destination pairs; based on the initial path set, using a swarm intelligence optimization algorithm for global optimization.

5. The highway reconstruction and expansion traffic diversion method according to claim 4, characterized in that: The improved shortest path algorithm and the swarm intelligence optimization algorithm comprise: in the improved shortest path algorithm, using the dynamic travel time calculated based on real-time traffic data as the path weight, and considering the time-varying limit of the construction road capacity, to generate multiple shortest feasible paths for each origin-destination pair; in the swarm intelligence optimization algorithm, constructing a fitness function with the minimum system total travel time as the objective, and performing population evolution through selection, crossover and mutation operations; in the mutation operation, calling the improved shortest path algorithm to generate new feasible paths and updating the path combination of individuals.

6. The highway reconstruction and expansion traffic diversion method according to claim 5, characterized in that: The microscopic traffic simulation software comprises: establishing a refined road network model in the simulation software, including the improved and expanded expressway, interchanges, parallel trunk highways and local roads; setting the vehicle type ratio, driving behavior parameters, signal timing and path selection logic; After running the simulation, the average vehicle speed, vehicle delay and traffic load level of each section at different time periods are output as the basis for operation state evaluation.

7. The highway reconstruction and expansion traffic diversion method according to claim 6, characterized in that: The obtained differentiated traffic organization scheme comprises: Based on the optimal shunting path scheme, the shunting scheme is finely simulated and run through micro-traffic simulation software; According to the average speed of the section, the vehicle delay time and the road saturation degree output by the simulation, the service level classification standard is comprehensively analyzed; If the service level of any section at any time period is lower than the third level service level, it is determined that there is time period congestion; When it is determined that there is time period congestion, based on the traffic flow data of each section output by the simulation, the traffic demand of each time period is backstepped and updated, and the traffic flow distribution and optimal shunting path solving are re-executed; If the service level of all key sections in the target prediction time period is not lower than the third level service level, it is determined that there is no time period congestion; When it is determined that there is no time period congestion, based on the optimal shunting path scheme solved last time, a differentiated traffic organization scheme for transit traffic, external traffic and regional traffic is generated.

8. A highway reconstruction and traffic diversion system using the method according to any one of claims 1 to 7, characterized in that, Comprise: The matrix construction module is used for obtaining multi-source dynamic traffic data, constructing the road network origin-destination matrix through data fusion and demand deduction; The system optimal traffic flow distribution module is used for obtaining traffic flow distribution results by constructing a system optimal traffic distribution model based on the road network origin-destination matrix; The shunted traffic flow calculation module is used for identifying the first congestion period based on the traffic flow distribution results, calculating the traffic flow exceeding the remaining traffic capacity in the congestion period, and obtaining the shunted traffic flow; The hybrid intelligent shunting path optimization module is used for solving the optimal shunting path under the minimum system total travel time through a hybrid intelligent algorithm based on the shunted traffic flow, and obtaining the optimal shunting path scheme; The traffic organization scheme generation module is used for verifying the optimal shunting path scheme by using micro-traffic simulation software, updating traffic data based on the simulation results and iteratively optimizing, and obtaining a differentiated traffic organization scheme.

9. An electronic device, comprising: Comprise: A memory for storing a program; A processor for loading the program to execute the steps of the method according to any one of claims 1-7.

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

Images