Highway hard shoulder management and control method, equipment and medium

Abstract

The invention discloses an expressway hard road shoulder management and control method, equipment and a medium, relates to the field of traffic management, and is used for solving the problems of expressway congestion and low passing efficiency caused by hard road shoulder management and control lag. The method comprises the steps of obtaining highway section traffic flow parameters through a nomadic work station, analyzing the traffic flow parameters, obtaining a hard road shoulder management and control state, determining an initial control sequence of a hard road shoulder, obtaining highway section future predicted traffic flow parameters according to a prediction model and the traffic flow parameters, generating a road shoulder management and control target function, and obtaining a road shoulder management and control target function. Rolling optimization is conducted on the initial control sequence through a genetic algorithm, the optimized control sequence is input into the fitness function, the optimized total time is obtained, rolling optimization is stopped until the optimized total time is smaller than a preset time threshold value, and the hard shoulder is managed and controlled according to the optimized control sequence. According to the invention, through prediction model simulation and genetic algorithm efficient optimization, real-time performance, intelligence and global optimization of hard road shoulder management and control are realized.

Description

Technical Field

[0001] The present application relates to the field of traffic management, and in particular to a method, device and medium for controlling hard shoulders of highways. Background Art

[0002] The hard shoulder of a highway is a road surface area adjacent to the carriageway with a certain strength. It is mainly used for temporary parking of broken-down vehicles and passage of emergency vehicles. However, its current utilization rate is extremely low, accounting for only 0.0005-0.02% of the traffic volume of the adjacent lanes. With the growth of traffic demand, highway congestion is becoming increasingly serious, and reconstruction and expansion face high economic, environmental and resource costs. In this context, it is crucial to intelligently control the hard shoulder and fully tap its traffic potential.

[0003] At present, although hard shoulders are opened in various places during peak congestion periods such as holidays, control measures mostly rely on manual labor, lack real-time traffic status information and mature control methods and systems, and the opening and closing of hard shoulders depend entirely on the experience of managers and lack scientific strategy optimization. This leads to a lag in the dynamic control response of the hard shoulder, and is unable to respond to real-time traffic changes in a timely manner, making it difficult to effectively improve traffic efficiency and ensure traffic safety. Summary of the invention

[0004] The embodiments of the present application provide a method, device and medium for controlling hard shoulders on highways, which are used to solve the problems of highway congestion and low traffic efficiency caused by delayed hard shoulder control.

[0005] The present application embodiment adopts the following technical solutions: On the one hand, the present application proposes a method for controlling hard shoulders of highways, including: obtaining the first traffic flow parameters of the highway section at different time points within a first preset time period through a nomadic workstation; the first traffic flow parameters include the number of lanes, and the number of lanes includes the hard shoulder, and then analyzing the first traffic flow parameters at different time points to obtain the simulated hard shoulder control state at each time point, and determining the initial control sequence of the hard shoulder according to the simulated hard shoulder control state at each time point, and then obtaining the first predicted traffic flow parameters of the highway section at different time points in the future time period according to the METANET model and the first traffic flow parameters, and then generating the objective function of shoulder control according to the first predicted traffic flow parameters and the preset objective function framework, the objective function is related to the total travel time of all vehicles in the highway section, and then rolling optimization of the initial control sequence is performed through a genetic algorithm, and the optimized control sequence of each time is input into the fitness function to obtain the total time of each optimization, until the total optimization time is less than the preset time threshold, the rolling optimization is stopped; the fitness function is the inverse of the objective function, and finally, according to the target optimization control sequence corresponding to the final optimization total time, the hard shoulders at different time points are controlled.

[0006] In one example, after controlling the hard shoulders at different time points according to the target optimization control sequence corresponding to the final optimization total time, the method also includes: obtaining the second traffic flow parameters of the expressway section at different time points within a second preset time period through a nomadic workstation; the second preset time period and the future time period are in the same time period, and then according to the METANET model and the second traffic flow parameters, obtaining the second predicted traffic flow parameters of the expressway section at different time points within the second preset time period, and then generating an updated objective function for shoulder control according to the second predicted traffic flow parameters and the preset objective function framework, and then performing rolling optimization on the target optimization control sequence through a genetic algorithm, inputting the target optimization control sequence of each optimization into the updated fitness function, and obtaining the total time of each optimization, until the total optimization time is less than the preset time threshold, stopping the rolling optimization; the updated fitness function is the inverse of the updated objective function, and controlling the hard shoulders at different time points according to the target optimization control sequence corresponding to the final optimization total time.

[0007] In one example, the first traffic flow parameters at different time points are analyzed to obtain the simulated hard shoulder control status at each time point, specifically including: matching the first traffic flow parameters at different time points in a preset event state library respectively; turning on the simulated hard shoulder control status of the successfully matched first traffic flow parameters; when the match is not successful, judging whether the expressway section has a historical control sequence; the historical control sequence includes a historical initial control sequence and a historical optimized control sequence; when there is a historical control sequence, matching the unmatched first traffic flow parameters with the historical traffic flow parameters corresponding to each historical time point in the historical control sequence; determining the historical hard shoulder control status of the successfully matched historical traffic flow parameters as the simulated hard shoulder control status of the unmatched first traffic flow parameters.

[0008] In one example, the method further includes: when there is no historical control sequence or no successfully matched historical traffic flow parameters, randomly generating a simulated hard shoulder control state according to a probability distribution using the unmatched first traffic flow parameters.

[0009] In one example, the initial control sequence is subjected to rolling optimization through a genetic algorithm, specifically including: determining a chromosome encoding method, and determining the simulated hard shoulder control state of the initial control sequence as the chromosome encoding in the genetic algorithm; each encoding bit corresponds to a simulated hard shoulder control state; and the genetic algorithm is subjected to rolling optimization through a preset population size, population evolution generation, crossover probability, and mutation probability.

[0010] In one example, the hard shoulder is controlled at different time points according to the target optimization control sequence corresponding to the final optimization total time, specifically including: generating the hard shoulder control status at different time points according to the target optimization control sequence corresponding to the final optimization total time, and sending the hard shoulder control status at different time points to the nomadic workstation; in the nomadic workstation, generating the hard shoulder display information for different control time windows in each rolling display cycle of the expressway section according to the preset rolling event window and the hard shoulder control status at different time points, so as to perform rolling display on the variable information board.

[0011] In one example, after controlling the hard shoulder at different time points according to the target optimization control sequence corresponding to the final optimized total time, the method also includes: when an accident is detected, overwriting the hard shoulder control state at the time of the accident, and determining the hard shoulder control state at the time of the accident to be on.

[0012] In one example, before obtaining the first traffic flow parameters of a highway section at different time points within a first preset time period through a nomadic workstation, the method also includes: dividing the highway into multiple directed sections through the section nodes of the METANET model; the section nodes are obtained by analyzing the section characteristic data of the highway, and each directed section is evenly divided to obtain multiple highway sections for each directed section.

[0013] On the other hand, an embodiment of the present application provides a highway hard shoulder control device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above-mentioned highway hard shoulder control methods.

[0014] On the other hand, an embodiment of the present application provides a non-volatile computer storage medium for highway hard shoulder control, which stores computer executable instructions, and the computer executable instructions can execute any of the above-mentioned methods for highway hard shoulder control.

[0015] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: This application uses a nomadic integrated workstation to collect real-time traffic flow data on highways, and combines it with a rolling time window to dynamically update the control strategy, achieving a response in seconds, significantly shortening the delay in strategy generation and implementation. The METANET macro-dynamic model is used to simulate the evolution of traffic flow under different shoulder control strategies, and accurately predict the trend of congestion diffusion. The model dynamically corrects the number of lanes and the impact of speed limits, quantifies the impact of complex scenarios such as ramp merging and lane reduction, and improves the authenticity of the simulation. A genetic algorithm is introduced, with the minimization of total travel time as the objective function. The arrangement of chromosome-encoded control variables is used to achieve multi-time period and multi-section joint optimization. Compared with traditional heuristic methods, the algorithm has high convergence efficiency and can efficiently solve the optimal control strategy under complex road networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the present application, some embodiments of the present application will be described in detail below in conjunction with the accompanying drawings, in which: Figure 1 A schematic diagram of a process flow of a highway hard shoulder control method provided in an embodiment of the present application; Figure 2 A schematic diagram of the steps of a method for controlling a hard shoulder of a highway provided in an embodiment of the present application; Figure 3 A schematic diagram of the appearance of a storage and computing integrated nomadic workstation provided in an embodiment of the present application; Figure 4 A hard shoulder rolling control diagram of a highway hard shoulder control method provided in an embodiment of the present application; Figure 5 A node section diagram of a METANET model of a highway hard shoulder control method provided in an embodiment of the present application; Figure 6 A schematic diagram of dividing a road section m of a highway hard shoulder control method provided in an embodiment of the present application; Figure 7 A flow update diagram of a METANET model of a highway hard shoulder control method provided in an embodiment of the present application; Figure 8 A schematic structural diagram of a highway hard shoulder control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0018] Some embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0019] Figure 1 A schematic diagram of a process flow of a highway hard shoulder control method provided in an embodiment of the present application. The method can be applied to different business areas. Certain input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy.

[0020] The analysis method involved in the embodiments of the present application may be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For ease of understanding and description, the following embodiments are described in detail by taking a control system as an example.

[0021] Based on this, the application process is as follows: S101: Acquire first traffic flow parameters of a highway section at different time points within a first preset time period through a nomadic workstation; the first traffic flow parameters include the number of lanes, and the number of lanes includes hard shoulders.

[0022] In some embodiments of the present application, it should be noted that before obtaining the first traffic flow parameters of the expressway section at different time points within the first preset time period through the nomadic workstation, it is necessary to deploy the nomadic workstation first. Specifically, the present application requires more than two nomadic workstations to work together. Among them, one nomadic workstation is set at the starting section of the expressway section to collect the traffic flow status entering the target section, and the remaining workstations are arranged in the middle of the section to calculate the optimal control strategy according to the traffic flow status, and display the hard shoulder control strategy in real time through the variable information board equipped by itself, or it can also realize the linkage with the gantry variable information board to display the control strategy of the hard shoulder.

[0023] It should also be noted that the METANET model is a deterministic, spatiotemporally random macroscopic traffic flow model, which can well simulate various traffic flow conditions such as free flow, congestion, and accident conditions. We use the METANET model to simulate the traffic flow state of the highway under the dynamic management of the hard shoulder.

[0024] Before obtaining the first traffic flow parameters of the highway section at different time points within the first preset time period through the nomadic workstation, the present application also divides the highway into multiple directed sections through the section nodes of the METANET model, and divides each directed section evenly to obtain multiple highway sections for each directed section. Specifically: The METANET model regards the highway section as a directed graph consisting of sections and nodes. The model regards the location where the highway characteristics change as a node, which can be an entrance ramp, an exit ramp, or the starting position of a slope. In this way, a section of highway can be divided into M sections, and the sections between nodes The number of lanes is , the road section can be evenly divided into Nm small sections. For the convenience of description, we refer to different sections in the model as "large sections" and "small sections". Large sections m are sections between different nodes, and small sections It is the nth small section after the large road section m is divided into Nm sections. Each small section has the same length Lm, which is usually 300~500 meters. For the entrance ramp of the expressway, the vehicles entering the entrance ramp include vehicles from the upstream main line section and vehicles from the ramp section, and the vehicles on the entrance ramp continue to enter the next main line section; for the exit ramp node of the expressway, its vehicles enter from the upstream main line section, and then enter the next main line section or ramp section from the ramp node according to the diversion ratio.

[0025] Then, the first traffic flow parameters of the expressway section at different time points within the first preset time period are obtained through the nomadic workstation. The preset time period here is determined according to the actual situation, the different time points are evenly divided time points, and the obtained section is the small section described above.

[0026] S102: Analyze the first traffic flow parameters at different time points to obtain a simulated hard shoulder control state at each time point, and determine an initial control sequence of the hard shoulder according to the simulated hard shoulder control state at each time point.

[0027] In some embodiments of the present application, it should be noted that the first traffic flow parameters at different time points are analyzed, specifically: the first traffic flow parameters at different time points are matched in the preset event state library respectively; the simulated hard shoulder control state of the successfully matched first traffic flow parameter is turned on; the time state library includes car accidents, harsh environments, etc. For example: if a car accident is found, the simulated hard shoulder control state is turned on. When the match is not successful, it is determined whether the expressway section has a historical control sequence; the historical control sequence includes a historical initial control sequence and a historical optimized control sequence; when there is the historical control sequence, the first traffic flow parameter that is not successfully matched is matched with the historical traffic flow parameters corresponding to each historical time point in the historical control sequence, and the historical hard shoulder control state of the successfully matched historical traffic flow parameter is determined as the simulated hard shoulder control state of the unmatched first traffic flow parameter.

[0028] When there is no historical control sequence or no successfully matched historical traffic flow parameters, the unmatched first traffic flow parameters are randomly generated according to probability distribution to simulate the hard shoulder control state.

[0029] The simulated hard shoulder control state generated according to the rules is combined with the randomly generated simulated hard shoulder control state to obtain the initial control sequence of the hard shoulder. This initial control sequence is the simulated control sequence before the hard shoulder starts to be controlled.

[0030] S103: Obtaining first predicted traffic flow parameters of the expressway section at different time points in the future according to the METANET model and the first traffic flow parameters.

[0031] In some embodiments of the present application, it should be noted that in the process of simulating traffic flow with the METANET model, the three parameters of traffic flow - flow, density, and speed - are obtained by iterating simulation steps one by one in a discrete time series. The discrete time interval T is the simulation step, which is usually taken as 10~20 s. K is the total time distribution quantity, and the discrete sampling time is expressed as t = kT, k = 0,1,…K. We take the nth small section of the large road section m as an example to establish a dynamic model of traffic flow on the main road section of the highway, The downstream exit of the nth small section of the large road section m is The average flow rate during the time period, in vehicles / hour / lane; is the average density of the nth small section of the large road section m at time t = kT, in vehicles / km; It is the average speed of the nth small section of the large road section m at the time t = kT, in kilometers per hour.

[0032] According to the relationship between the three parameters of traffic flow, the exit of the nth small section of the large road section m is The average flow rate in a time period is the average density of the small section at the time , average speed The number of lanes in road segment m The product of the three:

[0033] exist At the moment, the number of vehicles on the nth segment of the large road segment m is equal to the number of vehicles on the nth segment. Small paragraph Number of vehicles leaving at any given moment With the nth segment Number of vehicles remaining at the time The sum is shown in the following formula:

[0034] The nth small section of the large road section m is The average density at a given moment is the number of vehicles in the small road section at that moment. Length of small road section Number of lanes Ratio of:

[0035] In the present invention, the highway performs dynamic shoulder control. Therefore, the number of lanes in the large road section m may be different at different times. We use To indicate that the large road section m is Therefore, the average density update formula of the nth small section of the large road section m can be further expressed as:

[0036] When the density of the large road section is The corresponding steady-state speed It can be expressed as:

[0037] Among them, a is the basic graph parameter, is the free flow speed of section m, is the critical density of section m.

[0038] When a hard shoulder is used, a speed limit is usually set. For large sections m Considering that some drivers may not obey the speed limit control, the expected speed of the nth small section of the large road section m can be expressed as:

[0039] The nth small section of the large road section m is The average speed at time is , as shown below. Among them, , and It is a parameter that characterizes the traffic characteristics of the road network. is the expected constant, which is the parameter for adjusting the vehicle speed according to the density ahead. is the relevant constant, is the driver's reaction time to adjust the speed according to the traffic density ahead, is a correction factor used to prevent division by zero.

[0040]

[0041] The present invention takes into account the queuing delay of the ramp and proposes a strategy optimization method for dynamic control of the hard shoulder. Indicates that node o is in The queue length of the entrance ramp at time t, for The demand flow of the ramp at time At time , the queue length update formula of the entrance ramp is:

[0042] exist At time , the flow into node o As shown below:

[0043] In the formula, is the capacity of the ramp. For a road network node, when there is a ramp merging (increased traffic) or a reduction in the number of lanes behind the node (decreased capacity), it will cause traffic flow converging or interweaving, resulting in a decrease in vehicle speed. In these cases, the average vehicle speed needs to be corrected, as shown in the following formula:

[0044] When there is a ramp merge, ;on the contrary, Similarly, when the number of lanes behind the node decreases ;on the contrary, .also, , The first small section downstream of the node The average speed and density at each moment, The last small segment upstream of the node is The average density at the moment. and is a parameter that characterizes the traffic flow characteristics of the road network. is the impact coefficient of ramp inflow, is the impact coefficient of the reduction in the number of lanes.

[0045] S104: Generate an objective function for shoulder control based on the first predicted traffic flow parameter and a preset objective function framework; the objective function is related to the total travel time of all vehicles in the expressway section.

[0046] In some embodiments of the present application, it should be noted that the objective function of the hard shoulder intelligent control is the total travel time of all vehicles, specifically including the total travel time of mainline vehicles and the queue waiting time of vehicles on the entrance ramp:

[0047] In the formula, It is the ratio of the waiting time of vehicles in the ramp to the total travel time.

[0048] S105: Perform rolling optimization on the initial control sequence through a genetic algorithm, input each optimized control sequence into a fitness function, obtain the total time of each optimization, and stop the rolling optimization when the total optimization time is less than a preset time threshold; the fitness function is the inverse of the objective function.

[0049] In some embodiments of the present application, it should be noted that, assuming that the capacity of a single lane of a highway is about 2,000 vehicles per hour, when the hard shoulder is temporarily enabled, its capacity is about 1,200 vehicles per hour, which is less than the capacity of an ordinary lane. In the METANET model, the capacity of a highway section is determined by whether the hard shoulder is enabled.

[0050] In the dynamic control of hard shoulders, in order to efficiently solve the shoulder control strategy, the simulated hard shoulder control state of the initial control sequence is represented by H. When the hard shoulder is temporarily enabled, ;on the contrary, . This application uses a genetic algorithm to solve the control strategy of the hard shoulder. In each control cycle, the arrangement of the control variables H of the shoulders of different sections is represented as a chromosome code in the genetic algorithm, and each code bit corresponds to a simulated hard shoulder control state; The genetic algorithm is subjected to rolling optimization through preset population size, population evolution generation number, crossover probability and mutation probability.

[0051] Assuming that the population size is 80, the population evolution generation is set to 60, the crossover probability is 0.9, and the mutation probability is set to 0.1, if three sections are controlled, the chromosome may be [1,0,1], indicating that the hard shoulder is enabled in the first and third sections, and the second section is closed. Then randomly generate 80 binary-coded chromosomes of the population size, or heuristically generate the initial solution based on historical data. Select high-quality individuals to enter the next generation according to the fitness value ratio. The higher the fitness, the greater the probability of being selected. The smaller the total vehicle travel time J, the greater the individual's fitness function.

[0052] Randomly select the crossover point and exchange the genes in the second half of the chromosomes of the two parents. For example, after the parents [1,0,1] and [0,1,0] cross, the offspring [1,1,0] and [0,0,1] are generated. Then randomly select the gene position and change 0 to 1 or vice versa, for example, the chromosome [1,0,1] mutates to [1,1,1]. Finally, iterate until the total optimization time is less than the preset time threshold.

[0053] S106: Controlling the hard shoulder at different time points according to the target optimization control sequence corresponding to the final optimization total time.

[0054] In some embodiments of the present application, it should be noted that, according to the target optimization control sequence corresponding to the final optimization total time, the hard shoulder control status at different time points is generated, and the hard shoulder control status at different time points is sent to the nomadic workstation; In the nomadic workstation, based on the preset rolling event window and the hard shoulder control status at different time points, the hard shoulder display information of the expressway section for different control time windows in each rolling display cycle is generated for rolling display on the variable information board.

[0055] It should also be noted that when an accident is detected, the hard shoulder control state at the time of the accident is overwritten, and the hard shoulder control state at the time of the accident is determined to be on.

[0056] Further, after determining the target optimization control sequence corresponding to the first final optimization total time, the second traffic flow parameters of the expressway section at different time points within a second preset time are obtained through the nomadic workstation; the second preset time and the future time are in the same time period; According to the METANET model and the second traffic flow parameters, the second predicted traffic flow parameters of the expressway section at different time points within the second preset time are obtained; then, according to the second predicted traffic flow parameters and the preset objective function framework, an updated objective function of shoulder control is generated; and the target optimization control sequence is rolled optimized by a genetic algorithm, and the target optimization control sequence optimized each time is input into the updated fitness function to obtain the total time of each optimization, until the total optimization time is less than the preset time threshold, the rolling optimization is stopped; the updated fitness function is the inverse of the updated objective function; According to the target optimization control sequence corresponding to the final optimized total time, the hard shoulder is controlled at different time points.

[0057] It should be noted that although the embodiments of the present application are based on Figure 1 Steps S101 to S106 are described in sequence, but this does not mean that steps S101 to S106 must be performed in a strict order. Figure 1 The order shown in the figure is to introduce and explain step S101 to step S106 in sequence, in order to facilitate those skilled in the art to understand the technical solution of the embodiment of the present application. In other words, in the embodiment of the present application, the order between step S101 to step S106 can be appropriately adjusted according to actual needs.

[0058] pass Figure 1 The method uses a nomadic integrated workstation to collect real-time traffic flow data on highways, and dynamically updates the control strategy with a rolling time window to achieve a response in seconds, significantly shortening the delay in strategy generation and implementation. The METANET macro-dynamic model is used to simulate the evolution of traffic flow under different shoulder control strategies and accurately predict the trend of congestion diffusion. The model quantifies the impact of complex scenarios such as ramp merging and lane reduction by dynamically correcting the number of lanes and speed limits to improve the authenticity of the simulation. The genetic algorithm is introduced, with the minimization of the total travel time as the objective function. The arrangement of chromosome-encoded control variables is used to achieve multi-period and multi-section joint optimization. Compared with traditional heuristic methods, the algorithm has high convergence efficiency and can efficiently solve the optimal control strategy under complex road networks.

[0059] Figure 2 A schematic diagram of the steps of a method for controlling hard shoulders of highways provided in an embodiment of the present application.

[0060] exist Figure 2 In the process, the steps are as follows: traffic flow state data is input into the METANET model to predict traffic flow state, the objective function is obtained, and then the control strategy is obtained through the genetic algorithm, and then the control strategy is input into the METANET model for iteration to obtain a new control strategy.

[0061] Figure 3 A schematic diagram of the appearance of a storage and computing-in-one nomadic workstation provided in an embodiment of the present application.

[0062] The storage and computing integrated nomadic workstation has an upper and lower structure.

[0063] Figure 4 A hard shoulder rolling control diagram of a highway hard shoulder control method provided in an embodiment of the present application.

[0064] exist Figure 4 In the figure, C represents the length of the rolling control cycle, and C1 is the time interval for updating the control strategy. Since the intelligent control of the hard shoulder is a dynamic control process with the real-time operating status of the road section traffic flow as input, the present invention adopts a rolling event window method to achieve dynamic control of the hard shoulder.

[0065] Figure 5 A node section diagram of a METANET model of a highway hard shoulder control method provided in an embodiment of the present application.

[0066] exist Figure 5 In, q m-1 and q m There are two road section nodes, which divide the road section into m sections, namely the large road section mentioned above.

[0067] Figure 6 A schematic diagram of the road section m division of a highway hard shoulder control method provided in an embodiment of the present application.

[0068] exist Figure 6 In the above example, the road section m is evenly divided into n small sections. , , are the average density, speed and flow of the nth small section of the large road section m at time t = kT.

[0069] Figure 7 A flow update diagram of a METANET model of a highway hard shoulder control method provided in an embodiment of the present application.

[0070] exist Figure 7 in At the moment, the number of vehicles on the nth segment of the large road segment m is equal to the number of vehicles on the nth segment. Small paragraph Number of vehicles leaving at any given moment With the nth segment Number of vehicles remaining at the time The sum.

[0071] Figure 8 A schematic diagram of a structure of a highway hard shoulder control device provided in an embodiment of the present application includes: at least one processor; and, a memory communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can execute any one of the above-mentioned methods for controlling the hard shoulder of a highway.

[0072] Some embodiments of the present application provide a non-volatile computer storage medium for hard shoulder control of a highway, which stores computer executable instructions, and the computer executable instructions can execute any one of the above-mentioned methods for hard shoulder control of a highway.

[0073] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0074] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0075] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM), and non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0081] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0083] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the technical principle of the present application should fall within the protection scope of the present application.

Claims

1. A method for controlling hard shoulders of highways, characterized in that: The method comprises: Acquire, through a nomadic workstation, first traffic flow parameters of a highway section at different time points within a first preset time period; the first traffic flow parameters include the number of lanes, and the number of lanes includes hard shoulders; Analyze the first traffic flow parameters at different time points to obtain a simulated hard shoulder control state at each time point, and determine an initial control sequence of the hard shoulder according to the simulated hard shoulder control state at each time point; According to the METANET model and the first traffic flow parameter, first predicted traffic flow parameters of the expressway section at different time points in the future are obtained; Generate an objective function for shoulder control based on the first predicted traffic flow parameter and a preset objective function framework; the objective function is related to the total travel time of all vehicles in the highway section; The initial control sequence is subjected to rolling optimization by a genetic algorithm, and each optimized control sequence is input into a fitness function to obtain a total time for each optimization, and the rolling optimization is stopped when the total optimization time is less than a preset time threshold; the fitness function is the inverse of the objective function; The hard shoulder at different time points is controlled according to the target optimization control sequence corresponding to the final optimization total time.

2. The method according to claim 1, characterized in that: After controlling the hard shoulder at different time points according to the target optimization control sequence corresponding to the final optimization total time, the method further includes: Acquiring, by means of the nomadic workstation, second traffic flow parameters of the expressway section at different time points within a second preset duration; the second preset duration and the future duration being in the same time period; According to the METANET model and the second traffic flow parameter, obtaining the second predicted traffic flow parameter of the expressway section at different time points within the second preset time period; Generate an updated objective function for shoulder control based on the second predicted traffic flow parameter and a preset objective function framework; The target optimization control sequence is subjected to rolling optimization by a genetic algorithm, and the target optimization control sequence optimized each time is input into an updated fitness function to obtain the total time of each optimization, and the rolling optimization is stopped when the total optimization time is less than the preset time threshold; the updated fitness function is the inverse of the updated target function; According to the target optimization control sequence corresponding to the final optimized total time, the hard shoulder is controlled at different time points.

3. The method according to claim 1, characterized in that The first traffic flow parameters at different time points are analyzed to obtain the simulated hard shoulder control state at each time point, specifically including: Matching the first traffic flow parameters at different time points in a preset event state library respectively; The simulated hard shoulder control state of the first traffic flow parameter that is successfully matched is turned on; When the matching fails, determining whether the expressway section has a historical control sequence; the historical control sequence includes a historical initial control sequence and a historical optimized control sequence; When the historical control sequence is present, matching the first traffic flow parameter that has not been successfully matched with the historical traffic flow parameter corresponding to each historical time point in the historical control sequence; The historical hard shoulder control state of the successfully matched historical traffic flow parameter is determined as the simulated hard shoulder control state of the unsuccessfully matched first traffic flow parameter.

4. The method according to claim 3, characterized in that The method further comprises: When there is no historical control sequence or no successfully matched historical traffic flow parameters, the unmatched first traffic flow parameters are randomly generated according to probability distribution to simulate the hard shoulder control state.

5. The method according to claim 1, characterized in that The genetic algorithm is used to The initial control sequence is optimized for rolling, including: Determine a chromosome encoding method, and determine the simulated hard shoulder control state of the initial control sequence as the chromosome encoding in the genetic algorithm; each encoding bit corresponds to a simulated hard shoulder control state; The genetic algorithm is subjected to rolling optimization through preset population size, population evolution generation number, crossover probability and mutation probability.

6. The method according to claim 1, characterized in that The control of the hard shoulder at different time points according to the target optimization control sequence corresponding to the final optimization total time specifically includes: Generate hard shoulder control states at different time points according to the target optimization control sequence corresponding to the final optimization total time, and send the hard shoulder control states at different time points to the nomadic workstation; In the nomadic workstation, based on the preset rolling event window and the hard shoulder control status at different time points, the hard shoulder display information of the expressway section for different control time windows in each rolling display cycle is generated for rolling display on the variable information board.

7. The method according to claim 1, characterized in that After controlling the hard shoulder at different time points according to the target optimization control sequence corresponding to the final optimization total time, the method further includes: When an accident is detected, the hard shoulder control state at the time of the accident is overwritten, and the hard shoulder control state at the time of the accident is determined to be on.

8. The method according to claim 1, characterized in that Before obtaining the first traffic flow parameters of the expressway section at different time points within the first preset time period through the nomadic workstation, the method further includes: The expressway is divided into a plurality of directional sections by means of the section nodes of the METANET model; the section nodes are obtained by analyzing the section characteristic data of the expressway; Each directed road section is divided equally to obtain multiple high-speed road sections for each directed road section.

9. A highway hard shoulder control device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for controlling hard shoulders of highways as described in any one of claims 1 to 8.

10. A highway hard shoulder control storage medium storing computer executable instructions, characterized in that: The computer executable instructions are capable of executing a highway hard shoulder control method as described in any one of claims 1-8 above.

Images