Long trunk road multi-path coordination green wave optimization method and system based on electronic police data

Abstract

The invention relates to the technical field of traffic signal control, and discloses a long trunk road multi-path coordination green wave optimization method and system based on electronic police data, and the optimization method comprises the following steps: obtaining a long trunk road structure, intersection signal timing parameters and electronic police data; acquiring path flow and path average travel time in the target trunk road according to the electronic police data; identifying a key path in the trunk road based on the path information; constructing and solving an optimization model aiming at maximizing the weighted sum of the green wave bandwidth of the key path; and adjusting the signal control parameters of the actual road section according to the optimization result of the optimization model. The method can be applied to an urban long trunk road scene, independent green waves are provided for multiple paths, and the traffic flow passing efficiency of the urban trunk road is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic signal control, and in particular to a method and system for optimizing multi-path coordinated green waves on long trunk roads based on electric police data. Background Art

[0002] For many years, cities around the world have been exploring effective ways to improve road traffic flow and reduce traffic congestion. The initial design of traffic signal control systems for single-point intersections was gradually developed for this purpose, including the development of various models to adjust parameters such as signal cycle duration, green-to-signal ratio, and phase switching sequence. However, the operating efficiency of a single intersection does not exist in isolation, and its performance is deeply affected by the traffic conditions of adjacent intersections. This understanding has prompted the concept of regional traffic signal linkage control to be proposed in the field of traffic management. Under the guidance of this concept, the signal configuration of a single intersection is no longer optimized separately, but is placed in a larger traffic network for overall consideration. Signal coordination technology has thus emerged and has long been regarded as one of the key means to improve overall traffic efficiency and economic benefits. By coordinating traffic lights at different intersections, an orderly and coherent traffic flow can be formed throughout the entire area, thereby significantly reducing vehicle stagnation time and unnecessary acceleration, deceleration and parking, effectively improving road capacity and alleviating traffic congestion.

[0003] With the continuous acceleration of urbanization and the continuous expansion of urban space, the total extension length of the trunk road system has shown a significant growth trend, making long-distance trunk roads increasingly become the core component of modern urban transportation infrastructure. There are two limitations in the existing research on the coordination of long trunk roads: first, the research mainly focuses on the straight-moving traffic in the trunk road, while insufficient attention is paid to the needs and characteristics of other directions such as left-turning traffic, which may lead to the problem of left-turning traffic overflow in actual traffic flow, thus interfering with the smooth driving of straight-moving traffic; second, the existing long trunk road zoning method lacks consideration of zoning costs, and the overall optimization of trunk road sub-division and coordination control strategy is not sufficient, which makes it difficult to obtain the ideal coordinated green wave bandwidth. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a method and system for optimizing multi-path coordinated green waves on long trunk roads based on electric police data, which can be applied to long urban trunk road scenarios, provide independent green waves for multiple paths, and improve the traffic efficiency of urban trunk roads.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a long trunk road multi-path coordinated green wave optimization method based on electric police data, the method comprising the following steps:

[0007] In a first aspect, the present invention proposes a long trunk road multi-path coordinated green wave optimization method based on electric police data, comprising:

[0008] Obtain real-time long trunk road structure, intersection signal timing parameters and electric alarm data;

[0009] The real-time long trunk road structure, intersection signal timing parameters and electric alarm data are input into the pre-built optimization model, the optimization model is solved, and the optimized signal control parameters are output; the signal control parameters of the actual road section are adjusted according to the optimized signal control parameters to obtain the optimization result of the multi-path coordinated green wave of the long trunk road;

[0010] Wherein, the construction method of the optimization model is:

[0011] Obtain historical long-distance road structure, intersection signal timing parameters and electric alarm data;

[0012] Obtain the path flow and average path travel time in the target trunk road based on historical electronic police data;

[0013] Identify the critical path in the target trunk road based on the path information;

[0014] The optimization model includes an objective function and constraints; the objective function of the optimization model is obtained by maximizing the weighted sum of the green wave bandwidth of the critical path; the constraints of the optimization model include intersection grouping constraints, bandwidth constraints, cyclic integer constraints and phase order constraints.

[0015] In combination with the first aspect, further, the road structure of the long trunk road includes the number of intersections, the distance between adjacent intersections, the type and number of lanes at each intersection; the intersection signal timing parameters include the cycle of each intersection, the green-to-signal ratio, the phase structure, the phase sequence and the phase difference; the phase structure includes the signal phase; the electric alarm data includes the starting position, the end position, the time when the vehicle passes the starting position and the time when the vehicle arrives at the end position of all vehicles in the long trunk road.

[0016] In combination with the first aspect, further, the method for obtaining the path flow in the target trunk road based on the historical electric police data is:

[0017] Based on the historical electric police data, the starting position and the end position of each vehicle in the target trunk road are extracted, that is, the vehicle OD data of each vehicle is obtained;

[0018] Summarize all vehicle OD data to obtain the path at the observation time The number of observed vehicles and the observation time of each path Observation path flow within;

[0019] The OD data of all vehicles are summarized to obtain the time of observation for each path. The number of observed vehicles and the observation time of each path The method for observing the flow of the path within is:

[0020] Select a specific OD pair, corresponding to the path , calculate the number of vehicle samples with the same OD pair, that is, the OD pair at the observation time Number of observed vehicles in ;

[0021] Calculate Path The observation path flow is calculated as follows:

[0022]

[0023] In the formula, For path At observation time Observation path flow within; For path At observation time The number of observed vehicles within; is the observation time, in seconds;

[0024] Calculate the remaining paths in turn at the observation time The number of observed vehicles within the time period of the remaining paths is obtained. The observed path traffic within, the observed path traffic is the electric police data identification traffic;

[0025] The corrected path flow is calculated based on the electric police vehicle recognition rate, where the electric police vehicle recognition rate is one of the performance parameters of the electric police product. The calculation formula for the corrected path flow is:

[0026]

[0027] in, Indicates observation period Internal Path The corrected path flow; It indicates the probability of a vehicle being identified when passing through the area covered by the electric police, that is, the electric police vehicle recognition rate; Observation period Internal Path The electric police data identifies traffic.

[0028] In combination with the first aspect, further, the calculation method for obtaining the average travel time of the path in the target trunk road based on the historical electric police data is:

[0029] Extract vehicles based on historical electronic police data The starting position in the target road Time and reach the final position Time ;

[0030] Calculating vehicles Travel time , the vehicle Travel time The calculation formula is:

[0031]

[0032] in, Indicates vehicle The starting position in the target road time, Indicates vehicle Arrive at the destination location on the target road time;

[0033] Calculate Path Average travel time for all vehicles , the path Average travel time for all vehicles on The calculation formula is:

[0034]

[0035] in, Indicates the path The average travel time of all vehicles on the Indicates the path On The travel time of the vehicle; Indicates the path The number of vehicles on the path, Respectively represent the path The first car, the second car, ..., the Car.

[0036] In combination with the first aspect, further, the path information includes a flow sharing rate of each path and a travel time sharing rate of each path, and the specific method for identifying the key path in the target trunk road based on the path information is:

[0037] The calculation formula of the traffic sharing rate of each path is as follows:

[0038]

[0039] in, Pointing path Traffic sharing ratio;

[0040] The calculation formula of the travel time sharing rate of each path is as follows:

[0041]

[0042] in, Pointing path The travel time share ratio, Pointing path The average travel time of all vehicles on the

[0043] Path-based Traffic sharing ratio and path Calculate the travel time share of the path The importance of the path The calculation formula of importance is as follows:

[0044]

[0045] in, Pointing path The importance of Refers to the traffic weight coefficient; Refers to the travel time weight coefficient;

[0046] The top five paths in terms of importance are selected as critical paths.

[0047] In combination with the first aspect, further, the objective function of the optimization model is for:

[0048]

[0049] in, Upward critical path The flow weight coefficient of Downward critical path The flow weight coefficient of Upward critical path In the sub-area The number of road segments that the sub-path needs to pass through; Downward critical path In the sub-area The number of road segments that the sub-path needs to pass through; Upward critical path In the sub-area Green wave bandwidth within Downward critical path In the sub-area Green wave bandwidth within Represents an intersection sub-area.

[0050] The intersection grouping constraint is expressed as:

[0051] ;

[0052] ;

[0053] ;

[0054] in, is a binary variable representing the intersection Is it a sub-area? , 1 means yes, 0 means no; It means that intersection 1 belongs to sub-area 1; represents a sub-area set; For intersections; Represents the critical path The set of intersections passed.

[0055] The bandwidth constraint is expressed as:

[0056]

[0057]

[0058] in, Upward critical path At the intersection Green band offset at ; Downward critical path At the intersection Green band offset at ; is a binary variable representing the critical path Is it possible to Phase Get the green light, 1 for yes, 0 for no; Indicates intersection Phase Green light duration; Refers to the set of upstream critical paths; Refers to the set of downstream critical paths; Represents a sufficiently large positive number, with a lower limit of 10000.

[0059] The loop integer constraint is expressed as:

[0060]

[0061]

[0062] in, Point to the intersection The phase difference; Critical Path At the intersection The length of the red light on the left side of the green wave band at; Critical Path At the intersection The duration of the red light on the right side of the green wave band; Refers to vehicles running at green wave speed from the intersection The travel time required to reach the downstream intersection; Represents the critical path Upper intersection The multiple of the period is a positive integer; Critical Path At the intersection The queue clearing time.

[0063] The phase order constraint is expressed as:

[0064] ;

[0065] ;

[0066] ;

[0067] ;

[0068] ;

[0069] ;

[0070] ;

[0071] in, is a binary variable, indicating the intersection Phase and Phase The position relationship, 1 represents the phase exist Previously, 0 represented the phase exist after; , , Both represent phase; Indicates intersection Phase and Phase The position relationship, 1 represents the phase exist Previously, 0 represented the phase exist After that; by the same token , , , The meaning of the characters will not be repeated here; Indicates intersection Phase Green light duration; is a binary variable representing the critical path Is it possible to Phase Get the green light, 1 means yes, 0 means no, similarly, , The definition is not repeated here.

[0072] In combination with the first aspect, further, a solver is used to solve the optimization model.

[0073] In combination with the first aspect, further, the signal control parameters include the phase difference of each intersection (such as the intersection Phase difference ), phase order (e.g., , indicating an intersection Phase and Phase The position relationship, 1 represents the phase exist Previously, 0 represented the phase exist After that) and the green wave speed displayed on the display device. ) and phase sequence ( ) is the model decision variable, and the green wave speed is the model parameter, which is set according to experience and actual scenarios. To adjust the intersection phase difference of the actual road section, according to the output result of the optimization model To adjust the signal phase sequence of the intersection signal on the actual road section. The public green wave speed is the green wave speed of the optimization model, which can be adjusted according to Get, .

[0074] In a second aspect, the present invention provides a long trunk road multi-path coordinated green wave optimization system based on electric police data, comprising:

[0075] A data acquisition module is configured to acquire real-time long trunk road structure, intersection signal timing parameters and electric alarm data;

[0076] The optimization module is configured to input the real-time long trunk road structure, intersection signal timing parameters and electric alarm data into the pre-built optimization model, solve the optimization model, and output the optimized signal control parameters; adjust the signal control parameters of the actual road section according to the optimized signal control parameters to obtain the optimization result of the multi-path coordinated green wave of the long trunk road;

[0077] Wherein, the construction method of the optimization model is:

[0078] Obtain historical long-distance road structure, intersection signal timing parameters and electric alarm data;

[0079] Obtain the path flow and average path travel time in the target trunk road based on historical electronic police data;

[0080] Identify the critical path in the target trunk road based on the path information;

[0081] The optimization model includes an objective function and constraints; the objective function of the optimization model is obtained by maximizing the weighted sum of the green wave bandwidth of the critical path; the constraints of the optimization model include intersection grouping constraints, bandwidth constraints, cyclic integer constraints and phase order constraints.

[0082] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned long trunk road multi-path coordinated green wave optimization method based on electric police data.

[0083] In a fourth aspect, the present invention provides a computer device, comprising:

[0084] Memory for storing computer programs;

[0085] A processor is used to execute the computer program to implement the steps of the above-mentioned long trunk road multi-path coordinated green wave optimization method based on electric police data.

[0086] In a fifth aspect, the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned steps of multi-path coordinated green wave optimization of long trunk roads based on electric police data.

[0087] Compared with the prior art, the present invention provides a method and system for long trunk road multi-path coordinated green wave optimization based on electric police data, which has the following beneficial effects:

[0088] (1) The present invention takes long-distance urban trunk roads as the research object, uses electric police data to obtain key traffic information, takes the maximum weighted bandwidth of the key path as the optimization goal, considers constraints such as sub-area division, green wave bandwidth, cyclic integers, and phase order, and establishes an integrated optimization model that considers sub-area division and sub-area internal coordination control. The model can be applied to the scenario of long urban trunk roads, providing independent green waves for multiple paths, and improving the traffic efficiency of urban trunk roads.

[0089] (2) The present invention uses vehicle electric alarm data to obtain path information and identify key traffic flows on the main road, constructs a sub-area division and coordinated control optimization model, and realizes the sub-area division of long main roads and the coordinated control of multiple key paths. Compared with traditional green wave optimization technology, the present invention can provide green wave bands for multiple identified key paths at the same time. Compared with traditional sub-area division technology, the present invention takes into account the green wave loss cost of the partition, and incorporates the two steps of sub-area division and coordinated control into the same model, so as to obtain the ideal coordinated green wave bandwidth. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] Figure 1 It is a flowchart of a long trunk road multi-path coordinated green wave optimization method according to Embodiment 1 of the present invention;

[0091] Figure 2 This is a schematic diagram of the geometric layout of a long trunk road in Example 1 of the present invention;

[0092] Figure 3 This is a schematic diagram of the green wave bandwidth result in Example 1 of the present invention. DETAILED DESCRIPTION

[0093] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0094] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0095] Example 1

[0096] like Figure 1 As shown, this embodiment proposes a long trunk road multi-path coordinated green wave optimization method based on electric police data, and the method includes the following steps:

[0097] Step S1, obtaining historical long trunk road structure, intersection signal timing parameters and electric alarm data.

[0098] In a specific implementation of this embodiment, the road structure of the long trunk road includes the number of intersections, the distance between adjacent intersections, and the type and number of lanes at each intersection. The intersection signal timing parameters include the period of each intersection, the green-to-signal ratio, the phase structure, the phase sequence, and the phase difference. The phase structure includes the signal phase and the control pace. The electric alarm data includes the starting position, the end position, the time when the vehicle passes the starting position, and the time when the vehicle arrives at the end position of all vehicles in the long trunk road. Table 1 is an example of the electric alarm data field.

[0099]

[0100] In this embodiment, there are 15 intersections in total. (like Figure 2 Intersection 1, intersection 2, ..., intersection 15, The value range is 1 to 15. ), the 15 intersections and the spacing between adjacent intersections and intersection signal timing parameters are shown in Table 2.

[0101]

[0102] Step S2, obtaining the path flow and average path travel time in the target trunk road based on historical electronic alarm data.

[0103] Step S21, according to the electric police data, based on the historical electric police data, extract the starting position and the end position of each vehicle in the target trunk road, that is, obtain the vehicle OD data of each vehicle, such as Figure 2 As shown in the figure, the entrance and exit roads of the target trunk road intersection are numbered (the numbers are Figure 2 According to the electric police data, the vehicle OD data of each vehicle is obtained, as shown in Table 3.

[0104]

[0105] Step S211: Summarize all vehicle OD data to obtain the OD data of each path at the observation time. The number of observed vehicles and the observation time of each path Observation path flow within.

[0106] Get the observation time of each path The number of observed vehicles and the observation time of each path The method for observing the flow of the path within is:

[0107] Select a specific OD pair, corresponding to the path , calculate the number of vehicle samples with the same OD pair, that is, the OD pair at the observation time Number of observed vehicles in ;

[0108] Calculate Path The observation path flow is calculated as follows:

[0109]

[0110] In the formula, For path At observation time Observation path flow within; For path At observation time The number of observed vehicles within; is the observation time, in seconds;

[0111] Calculate the remaining paths in turn at the observation time The number of observed vehicles within the time period of the remaining paths is obtained. The observation path traffic within is the traffic identified by the electric police data.

[0112] Step S211, calculate the corrected path flow rate according to the electric police vehicle recognition rate. The electric police vehicle recognition rate is one of the performance parameters of the electric police product. The calculation formula of the corrected path flow rate is:

[0113]

[0114] in, Indicates observation period Internal Path The corrected path flow; It indicates the probability of a vehicle being identified when passing through the area covered by the electric police, that is, the electric police vehicle recognition rate; Observation period Internal Path The electric police data identifies traffic.

[0115] The corrected path flow is the path flow that is ultimately required in step S2, as shown in Table 4 below.

[0116]

[0117] Step 22, based on the historical electronic police data, the average travel time of the path in the target trunk road is obtained. The specific calculation method is:

[0118] Step S221, extracting vehicles based on historical electronic police data The starting position in the target road Time and reach the final position Time .

[0119] Step S222, calculate vehicle Travel time ,vehicle Travel time The calculation formula is:

[0120]

[0121] in, Indicates vehicle The starting position in the target road time, Indicates vehicle Arrive at the destination location on the target road time.

[0122] Step S223, calculate the path Average travel time for all vehicles , the path Average travel time for all vehicles on The calculation formula is:

[0123]

[0124] in, Indicates the path The average travel time of all vehicles on the Indicates the path On The travel time of the vehicle; Indicates the path The number of vehicles on the path, Respectively represent the path The first car, the second car, ..., the Car.

[0125] Step S3, identifying the key paths in the trunk road based on the path information. The path information includes the flow sharing rate of each path and the travel time sharing rate of each path.

[0126] In step S31, the flow sharing ratio of each path is calculated as follows:

[0127]

[0128] in, Pointing path traffic sharing ratio.

[0129] Step S32: The calculation formula of the travel time sharing rate of each path is as follows:

[0130]

[0131] in, Pointing path The travel time share ratio, Pointing path The average travel time of all vehicles on the

[0132] Step S33, based on the path Traffic sharing ratio and path Calculate the travel time share of the path The importance of the path The calculation formula of importance is as follows:

[0133]

[0134] in, Pointing path The importance of Refers to the traffic weight coefficient; Refers to the travel time weight coefficient.

[0135] The top five paths in importance of each path are taken as the critical paths, and the final critical path identification results are shown in Table 5:

[0136]

[0137] Step S4, constructing and solving an optimization model with the goal of maximizing the weighted sum of the green wave bandwidth of the critical path.

[0138] The optimization model includes an objective function and constraints. The constraints of the optimization model include intersection grouping constraints, bandwidth constraints, cyclic integer constraints and phase order constraints.

[0139] The objective function of the optimization model for:

[0140]

[0141] in, Upward critical path The flow weight coefficient of Downward critical path The flow weight coefficient of Upward critical path In the sub-area The number of road segments that the sub-path needs to pass through; Downward critical path In the sub-area The number of road segments that the sub-path needs to pass through; Upward critical path In the sub-area Green wave bandwidth within Downward critical path In the sub-area Green wave bandwidth within Represents an intersection sub-area.

[0142] The intersection grouping constraint is expressed as:

[0143] ;

[0144] ;

[0145] ;

[0146] in, is a binary variable representing the intersection Is it a sub-area? , 1 means yes, 0 means no; It means that intersection 1 belongs to sub-area 1; represents a sub-area set; For intersections; Represents the critical path The set of intersections passed.

[0147] The bandwidth constraint is expressed as:

[0148] ;

[0149] ;

[0150] in, Upward critical path At the intersection Green band offset at ; Downward critical path At the intersection Green band offset at ; is a binary variable representing the critical path Is it possible to Phase Get the green light, 1 for yes, 0 for no; Indicates intersection Phase Green light duration; Refers to the set of upstream critical paths; Refers to the set of downstream critical paths; Represents a sufficiently large positive number, with a lower limit of 10000.

[0151] The loop integer constraint is expressed as:

[0152] ;

[0153] ;

[0154] in, Point to the intersection The phase difference; Critical Path At the intersection The length of the red light on the left side of the green wave band at; Critical Path At the intersection The duration of the red light on the right side of the green wave band; Refers to vehicles running at green wave speed from the intersection The travel time required to reach the downstream intersection; Represents the critical path Upper intersection The multiple of the period is a positive integer; Critical Path At the intersection The queue clearing time.

[0155] The phase order constraint is expressed as:

[0156] ;

[0157] ;

[0158] ;

[0159] ;

[0160] ;

[0161] ;

[0162] ;

[0163] in, is a binary variable, indicating the intersection Phase and Phase The position relationship, 1 represents the phase exist Previously, 0 represented the phase exist after; , , Both represent phase; Indicates intersection Phase and Phase The position relationship, 1 represents the phase exist Previously, 0 represented the phase exist Afterwards; by the same token , , , The meaning of the characters will not be repeated here; Indicates intersection Phase Green light duration; is a binary variable representing the critical path Is it possible to Phase Get the green light, 1 means yes, 0 means no, similarly, , The definition is not repeated here.

[0164] In a specific embodiment of the present embodiment, Python is used to call a solver to solve the optimization model, and output a long trunk road intersection sub-area division scheme, a phase difference, and a phase sequence scheme.

[0165] like Figure 3 As shown in the figure, Python is used to call the solver to solve the optimization model. It takes 17 minutes to solve the long trunk road intersection sub-area division scheme, phase difference and phase sequence scheme. A total of 4 sub-areas are divided, of which sub-area 1 contains 5 intersections, sub-area 2 contains 4 intersections, sub-area 3 contains 4 intersections, and sub-area 4 contains 3 intersections. The key path coordination scheme and green wave bandwidth are shown in Figure 3 shown.

[0166] In order to verify the superiority of the optimization model proposed in the present invention, two comparative models are used, wherein comparative model 1 is MP-P, which is an improved multi-path model that can only coordinate part of the critical paths, and comparative model 2 is MP-F, which refers to the use of a fixed sub-area division scheme. Table 6 shows the green wave bandwidth results of the critical paths under the three models. The optimization model proposed in the present invention has obvious advantages over the MP-P model and the MP-F model in increasing the green wave bandwidth of the critical path. On paths 1 to 5, the optimization model of the present invention achieves green wave bandwidths of 38 seconds, 59 seconds, 48 ​​seconds, 32 seconds and 33 seconds, respectively. Compared with the MP-P model (green wave bandwidths of 43 seconds, 15 seconds, 43 seconds, 0 seconds, and 0 seconds) and the MP-F model (green wave bandwidths of 23 seconds, 28 seconds, 40 seconds, 22 seconds, and 22 seconds), the optimization model of the present invention provides longer continuous green light time on most paths. The weighted sum of the green wave bandwidth of each path is calculated, and the total weighted sum of the optimization model of the present invention is 438 seconds, which is much higher than 257 seconds of the MP-P model and 261 seconds of the MP-F model. This shows that the optimization model of the present invention is significantly better than the other two models in providing continuous green light time.

[0167]

[0168] As shown in Table 7, the optimization model of the present invention is superior to the MP-P and MP-F models. Specifically, under the optimization model of the present invention, the average delay of the vehicle is reduced by 21.45% and 17.13% compared with the MP-P and MP-F models, respectively. In terms of the average number of stops, the optimization model of the present invention achieves a lower number of stops (3.61 times), compared with 3.94 times for the MP-P model and 3.87 times for the MP-F model. In addition, the effectiveness of the optimization model of the present invention is further verified by comparing the average speed. In summary, the optimization model of the present invention is superior to the MP-P model and the MP-F model in reducing the average path flow delay, reducing the average number of stops, and increasing the average driving speed.

[0169]

[0170] Step S5: adjusting the signal control parameters of the actual road section according to the output result of the optimization model of this embodiment.

[0171] Signal control parameters include the phase difference of each intersection (such as Phase difference ), phase order (e.g., , indicating an intersection Phase and Phase The position relationship, 1 represents the phase exist Previously, 0 represented the phase exist After that) and the green wave speed displayed on the display device. ) and phase sequence ( ) is the model decision variable, and the green wave speed is the model parameter, which is set according to experience and actual scenarios. According to the output results of the optimization model To adjust the intersection phase difference of the actual road section, according to the output results of the optimization model To adjust the signal phase sequence of the intersection signal on the actual road section. The public green wave speed is the green wave speed of the optimization model, which can be adjusted according to Get, .

[0172] The present invention utilizes vehicle electric alarm data to identify target trunk road path flow information, constructs a sub-area division and coordinated control optimization model, and realizes long trunk line sub-area division and coordinated control of multiple key paths.

[0173] Example 2

[0174] Based on the same inventive concept as Example 1, this example introduces a long trunk road multi-path coordinated green wave optimization system based on electric police data, including:

[0175] A data acquisition module is configured to acquire real-time long trunk road structure, intersection signal timing parameters and electric alarm data;

[0176] The optimization module is configured to input the real-time long trunk road structure, intersection signal timing parameters and electric alarm data into the pre-built optimization model, solve the optimization model, and output the optimized signal control parameters; adjust the signal control parameters of the actual road section according to the optimized signal control parameters to obtain the optimization result of the multi-path coordinated green wave of the long trunk road;

[0177] Among them, the construction method of the optimization model is:

[0178] Obtain historical long-distance road structure, intersection signal timing parameters and electric alarm data;

[0179] Obtain the path flow and average path travel time in the target trunk road based on historical electronic police data;

[0180] Identify the critical path in the target trunk road based on the path information;

[0181] The optimization model includes an objective function and constraints. The objective function of the optimization model is obtained by maximizing the weighted sum of the green wave bandwidth of the critical path. The constraints of the optimization model include intersection grouping constraints, bandwidth constraints, cyclic integer constraints and phase order constraints.

[0182] Example 3

[0183] Based on the same inventive concept as other embodiments, this embodiment introduces a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned long trunk road multi-path coordinated green wave optimization method based on electric police data are implemented.

[0184] Example 4

[0185] Based on the same inventive concept as other embodiments, this embodiment introduces a computer device, including: a memory for storing a computer program; a processor for executing the computer program to implement the steps of the above-mentioned long trunk road multi-path coordinated green wave optimization method based on electric police data.

[0186] Example 5

[0187] Based on the same inventive concept as other embodiments, this embodiment introduces a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned long trunk road multi-path coordinated green wave optimization method based on electric police data.

[0188] 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.

[0189] 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.

[0190] 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 comprising 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.

[0191] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0192] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms under the guidance of the present invention, which all fall within the protection of the present invention.

Claims

1. A long trunk road multi-path coordinated green wave optimization method based on electric police data, characterized in that: include: Obtain real-time long trunk road structure, intersection signal timing parameters and electric alarm data; The real-time long trunk road structure, intersection signal timing parameters and electric alarm data are input into the pre-built optimization model, the optimization model is solved, and the optimized signal control parameters are output; the signal control parameters of the actual road section are adjusted according to the optimized signal control parameters to obtain the optimization result of the multi-path coordinated green wave of the long trunk road; Wherein, the construction method of the optimization model is: Obtain historical long-distance road structure, intersection signal timing parameters and electric alarm data; Obtain the path flow and average path travel time in the target trunk road based on historical electronic police data; Identify the critical path in the target trunk road based on the path information; The optimization model includes an objective function and constraints; the objective function of the optimization model is obtained by maximizing the weighted sum of the green wave bandwidth of the critical path; the constraints of the optimization model include intersection grouping constraints, bandwidth constraints, cyclic integer constraints and phase order constraints.

2. The long trunk road multi-path coordinated green wave optimization method based on electric police data according to claim 1 is characterized by: The road structure of the long trunk road includes the number of intersections, the distance between adjacent intersections, the type and number of lanes at each intersection; the intersection signal timing parameters include the cycle of each intersection, the green-to-signal ratio, the phase structure, the phase sequence and the phase difference; the phase structure includes the signal phase; the electric alarm data includes the starting position, the end position, the time when the vehicle passes the starting position and the time when the vehicle arrives at the end position of all vehicles in the long trunk road.

3. The long trunk road multi-path coordinated green wave optimization method based on electric police data according to claim 1 is characterized by: The method for obtaining the path flow in the target trunk road based on the historical electric police data is: Based on the historical electric police data, the starting position and the end position of each vehicle in the target trunk road are extracted, that is, the vehicle OD data of each vehicle is obtained; Summarize all vehicle OD data to obtain the path at the observation time The number of observed vehicles and the observation time of each path Observation path flow within; The OD data of all vehicles are summarized to obtain the time of observation for each path. The number of observed vehicles and the observation time of each path The method for observing the flow of the path within is: Select a specific OD pair, corresponding to the path , calculate the number of vehicle samples with the same OD pair, that is, the OD pair at the observation time Number of observed vehicles in ; Calculate Path The observation path flow is calculated as follows: ； In the formula, For path At observation time Observation path flow within; For path At observation time The number of observed vehicles within; is the observation time, in seconds; Calculate the remaining paths in turn at the observation time The number of observed vehicles within the time period of the remaining paths is obtained. The observed path traffic within, the observed path traffic is the electric police data identification traffic; The corrected path flow is calculated based on the electric police vehicle recognition rate, where the electric police vehicle recognition rate is one of the performance parameters of the electric police product. The calculation formula for the corrected path flow is: ； in, Indicates observation period Internal Path The corrected path flow; It indicates the probability of a vehicle being identified when passing through the area covered by the electric police, that is, the electric police vehicle recognition rate; For observation period Internal Path The electric police data identifies traffic.

4. The long trunk road multi-path coordinated green wave optimization method based on electric police data according to claim 1 is characterized by: The calculation method for obtaining the average travel time of the path in the target trunk road based on the historical electric police data is: Extract vehicles based on historical electronic police data The starting position in the target road Time and reach the final position Time ; Calculating vehicles Travel time , the vehicle Travel time The calculation formula is: ； in, Indicates vehicle The starting position in the target road time, Indicates vehicle Arrive at the destination location on the target road time; Calculate Path Average travel time for all vehicles , the path Average travel time for all vehicles on The calculation formula is: ； in, Indicates the path The average travel time of all vehicles on the Indicates the path On The travel time of the vehicle; Indicates the path The number of vehicles on the path, Respectively represent the path The first car, the second car, ..., the Car.

5. The long trunk road multi-path coordinated green wave optimization method based on electric police data according to claim 1 is characterized in that: The path information includes the flow sharing rate of each path and the travel time sharing rate of each path. The specific method of identifying the key path in the target trunk road based on the path information is: The calculation formula of the traffic sharing rate of each path is as follows: ； in, Pointing path Traffic sharing ratio; The calculation formula of the travel time sharing rate of each path is as follows: ； in, Pointing path The travel time share ratio, Pointing path The average travel time of all vehicles on the Path-based Traffic sharing ratio and path Calculate the travel time share of the path The importance of the path The calculation formula of importance is as follows: ； in, Pointing path The importance of Refers to the traffic weight coefficient; Refers to the travel time weight coefficient; The top five paths in terms of importance are selected as critical paths.

6. The long trunk road multi-path coordinated green wave optimization method based on electric police data according to claim 1 is characterized in that: The objective function of the optimization model for: ； in, Upward critical path The traffic weight coefficient of Downward critical path The traffic weight coefficient of Upward critical path In the sub-area The number of road segments that the sub-path needs to pass through; Downward critical path In the sub-area The number of road segments that the sub-path needs to pass through; Upward critical path In the sub-area Green wave bandwidth within Downward critical path In the sub-area Green wave bandwidth within represents the intersection sub-area; The intersection grouping constraint is expressed as: ； ； ； in, is a binary variable representing the intersection Is it a sub-area? , 1 means yes, 0 means no; It means that intersection 1 belongs to sub-area 1; represents a sub-area set; For intersections; Represents the critical path The set of intersections passed; The bandwidth constraint is expressed as: ； ； in, Upward critical path At the intersection Green band offset at ; Downward critical path At the intersection Green band offset at ; is a binary variable representing the critical path Is it possible to Phase Get the green light, 1 for yes, 0 for no; Indicates intersection Phase Green light duration; Refers to the set of upstream critical paths; Refers to the set of downstream critical paths; Represents a sufficiently large positive number, with a lower limit of 10000; The loop integer constraint is expressed as: ； ； in, Point to the intersection The phase difference; Critical Path At the intersection The length of the red light on the left side of the green wave band at; Critical Path At the intersection The duration of the red light on the right side of the green wave band; Refers to vehicles running at green wave speed from the intersection The travel time required to reach the downstream intersection; Represents the critical path Upper intersection The multiple of the period is a positive integer; Critical Path At the intersection The queue clearing time; The phase order constraint is expressed as: ； ； ； ； ； ； ； in, is a binary variable, indicating the intersection Phase and Phase The position relationship, 1 represents the phase exist Previously, 0 represented the phase exist after; , , Both represent phase; Indicates intersection Phase and Phase The position relationship, 1 represents the phase exist Previously, 0 represented the phase exist Afterwards; by the same token , , , The meaning of the characters will not be repeated here; Indicates intersection Phase Green light duration; is a binary variable representing the critical path Is it possible to Phase Get the green light, 1 means yes, 0 means no, similarly, , The definition is not repeated here.

7. A long trunk road multi-path coordinated green wave optimization system based on electric police data, characterized in that: include: A data acquisition module is configured to acquire real-time long trunk road structure, intersection signal timing parameters and electric alarm data; The optimization module is configured to input the real-time long trunk road structure, intersection signal timing parameters and electric alarm data into the pre-built optimization model, solve the optimization model, and output the optimized signal control parameters; adjust the signal control parameters of the actual road section according to the optimized signal control parameters to obtain the optimization result of the multi-path coordinated green wave of the long trunk road; Wherein, the construction method of the optimization model is: Obtain historical long-distance road structure, intersection signal timing parameters and electric alarm data; Obtain the path flow and average path travel time in the target trunk road based on historical electronic police data; Identify the critical path in the target trunk road based on the path information; The optimization model includes an objective function and constraints; the objective function of the optimization model is obtained by maximizing the weighted sum of the green wave bandwidth of the critical path; the constraints of the optimization model include intersection grouping constraints, bandwidth constraints, cyclic integer constraints and phase order constraints.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the long trunk road multi-path coordinated green wave optimization method based on electric police data described in any one of claims 1 to 6 are implemented.

9. A computer device, characterized in that: include: Memory for storing computer programs; A processor is used to execute the computer program to implement the steps of the long trunk road multi-path coordinated green wave optimization method based on electric police data according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of the long trunk road multi-path coordinated green wave optimization method based on electric police data described in any one of claims 1 to 6 are implemented.

Images