CN115440033B - Main line coordination control method, system, device and medium based on macroscopic basic diagram - Google Patents

Main line coordination control method, system, device and medium based on macroscopic basic diagram Download PDF

Info

Publication number
CN115440033B
CN115440033B CN202210980172.4A CN202210980172A CN115440033B CN 115440033 B CN115440033 B CN 115440033B CN 202210980172 A CN202210980172 A CN 202210980172A CN 115440033 B CN115440033 B CN 115440033B
Authority
CN
China
Prior art keywords
road network
particle
mfd
trunk
macroscopic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210980172.4A
Other languages
Chinese (zh)
Other versions
CN115440033A (en
Inventor
林炫华
林晓辉
谭超健
曹成涛
龙庆文
陈林俊
刘俊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Communications Polytechnic
Original Assignee
Guangdong Communications Polytechnic
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Communications Polytechnic filed Critical Guangdong Communications Polytechnic
Priority to CN202210980172.4A priority Critical patent/CN115440033B/en
Publication of CN115440033A publication Critical patent/CN115440033A/en
Application granted granted Critical
Publication of CN115440033B publication Critical patent/CN115440033B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G08G1/081—Plural intersections under common control
    • G08G1/083—Controlling the allocation of time between phases of a cycle
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Chemical & Material Sciences (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Analytical Chemistry (AREA)
  • Molecular Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Genetics & Genomics (AREA)
  • Physiology (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a trunk line coordination control method, a system, a device and a medium based on a macroscopic basic diagram, wherein the method comprises the following steps: constructing a multi-objective optimization model of trunk coordination control, wherein the multi-objective optimization model takes the maximum gradient of an MFD ascending section, the maximum road network bearing capacity, the minimum average delay of road network vehicles and the minimum road network queuing coefficient as optimization targets, and takes the public period of the trunk, the effective green light duration of the phase and the phase difference of an intersection as parameters to be optimized; acquiring traffic flow data of a trunk line to be optimized, and optimizing a multi-target optimization model through a multi-target particle swarm algorithm and a genetic algorithm according to the traffic flow data to obtain an optimal parameter combination of parameters to be optimized; and carrying out trunk coordination control on the trunk to be optimized according to the optimal parameter combination. The invention ensures that the trunk line coordination control can give consideration to macroscopic and microscopic traffic efficiency, improves the control effect and the vehicle passing efficiency of the trunk line coordination control, and can be applied to the technical field of road traffic signal control.

Description

Main line coordination control method, system, device and medium based on macroscopic basic diagram
Technical Field
The invention relates to the technical field of road traffic signal control, in particular to a trunk line coordination control method, a trunk line coordination control system, a trunk line coordination control device and a trunk line coordination control medium based on a macroscopic basic diagram.
Background
In the aspect of trunk coordination control, morgan firstly proposes a bidirectional green wave coordination control model, and the green wave concept is widely applied; LITTLE et al developed a trunk signal design optimization program MAXBOAND, a numerical solution, using a maximum green band phase difference optimization method which was considered to be the most cost-effective trunk control strategy to date, but basically assumed that all intersections had the same pass bandwidth; zhang Yiyuan and the like insert the superposition phase according to the design speed of the green wave band so as to better match the arrival time of the traffic flow; pan Yuan and the like increase the speed fluctuation interval constraint and establish a trunk coordination control model considering the speed fluctuation interval; wang Chenwei and the like aim at the minimum total delay of the trunk area, and a double-layer delay model is built for solving. At present, most trunk coordination control strategies are modeled from the ideas of delay minimization, green wave band maximization, multi-objective model and the like, and are solved through an intelligent optimization algorithm.
In general, existing methods are more focused on optimizing several traditional evaluation indexes or considering specific application scenarios. The urban trunk line and the communication road thereof are used as local road networks, the global running state of the network is difficult to be represented only by microscopic collection meter indexes such as delay, stop times and the like, and the numerical difference is small when saturated traffic flows by taking traffic capacity, road network output flow, running speed and the like as evaluation indexes, so that the control effect of the trunk line and the running efficiency of vehicles are influenced.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art to a certain extent.
Therefore, an object of the embodiment of the present invention is to provide a trunk coordination control method based on a macroscopic basic diagram, which improves the control effect and the vehicle passing efficiency of the trunk coordination control.
It is a further object of embodiments of the present invention to provide a trunk coordination control system based on a macroscopic base map.
In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the invention comprises the following steps:
in a first aspect, an embodiment of the present invention provides a trunk coordination control method based on a macroscopic basic graph, including the following steps:
constructing a multi-objective optimization model of trunk coordination control, wherein the multi-objective optimization model takes the maximum gradient of an MFD ascending section, the maximum road network bearing capacity, the minimum average delay of road network vehicles and the minimum road network queuing coefficient as optimization targets, and takes the public period of the trunk, the effective green light duration of the phase and the phase difference of an intersection as parameters to be optimized;
acquiring traffic flow data of a trunk line to be optimized, and optimizing the multi-objective optimization model through a multi-objective particle swarm algorithm and a genetic algorithm according to the traffic flow data to obtain an optimal parameter combination of the parameters to be optimized;
Carrying out trunk coordination control on the trunk to be optimized according to the optimal parameter combination;
in the optimization process of the multi-objective optimization model, the average delay of road network vehicles and the queuing coefficient of the road network corresponding to each particle are determined through simulation, and the gradient of the MFD ascending section and the bearing capacity of the road network corresponding to each particle are determined through a macroscopic basic diagram obtained through clustering fitting.
Further, in one embodiment of the present invention, the objective function of the multi-objective optimization model is:
wherein F (C, G, offset) represents an objective function,indicating road network vehicle average delay +.>Representing the queuing coefficient of the road network, A 1 Represents the slope, q of the rising section of the MFD max Representing road network bearing capacity;
constraint conditions of the multi-objective optimization model are as follows:
wherein the queue i Indicating the queuing length of the ith lane, L i Represents the lane length of the i-th lane, C represents the trunk common period, C min And C max The upper and lower limits of C are indicated respectively,indicating the effective green light duration of the jth phase of the ith intersection,/for the phase of the ith intersection>And->Respectively indicate->Upper and lower limit of (2), offset i Indicating the phase difference of the i-th intersection with the first intersection.
Further, in an embodiment of the present invention, the step of optimizing the multi-objective optimization model according to the traffic flow data by a multi-objective particle swarm algorithm in combination with a genetic algorithm to obtain an optimal parameter combination of the parameters to be optimized specifically includes:
Determining initial values of positions and speeds of various particles in the particle swarm, initial solution sets of the particle swarm and convergence conditions;
simulating according to the traffic flow data and the positions and speeds of all particles in the initial particle group to obtain road network vehicle average delay, road network queuing coefficients and MFD data point sets corresponding to all particles, wherein the abscissa and ordinate of the data points in the MFD data point sets are road network weighted density and road network weighted flow respectively;
performing cluster fitting on the MFD data point set to obtain a macroscopic basic diagram, and determining the gradient of the MFD ascending section and the road network bearing capacity corresponding to each particle according to the macroscopic basic diagram;
the method comprises the steps of performing non-dominant sorting on each particle to determine an individual optimal position of each particle, and performing non-dominant sorting on a particle group to determine a group optimal position of the particle group;
updating the position and the speed of each particle according to the individual optimal position and the group optimal position;
selecting, crossing and mutating the particle swarm to obtain an optimized particle swarm;
and if the convergence condition is met, taking a parameter value combination of the optimal position of the historical group of the particle swarm as an optimal parameter combination, and if the convergence condition is not met, returning to the step of simulating according to the vehicle flow data and the position and the speed of each particle in the initial particle swarm.
Further, in one embodiment of the present invention, the step of performing cluster fitting on the MFD data point set to obtain a macroscopic basic map, and determining, according to the macroscopic basic map, a slope of an MFD rising segment and a road network bearing capacity corresponding to each particle, includes:
performing boundary searching on the MFD data point set by a groined boundary extraction method, and generating an initial MFD graph according to the searched boundary points;
clustering the initial MFD graphs to obtain two or three types of data sample sets;
performing piecewise linear fitting on each data sample set to obtain a macroscopic basic diagram, wherein the macroscopic basic diagram at least comprises a rising section structure and a stable section structure;
determining the slope of the MFD ascending segment corresponding to the current particle according to the ratio of the road network weighted flow of the ascending segment structure to the road network weighted density;
and determining the road network bearing capacity corresponding to the current particles according to the road network weighted flow of the stable segment structure.
Further, in one embodiment of the present invention, the step of clustering the initial MFD map to obtain two or three types of data sample sets specifically includes:
clustering the initial MFD images by taking 3 as a clustering number to obtain three classes of undetermined sample sets;
Determining the center point of each undetermined sample set from left to right as a first center point, a second center point and a third center point respectively;
and when the road network weighted flow of the first center point and the road network weighted flow of the third center point are smaller than the road network weighted flow of the second center point, determining that the initial MFD image is a three-section closed type MFD image, outputting the to-be-determined sample set as a data sample set, otherwise, determining that the initial MFD image is a two-section non-closed type MFD image, and clustering the initial MFD image again by taking 2 as a clustering number to obtain two kinds of data sample sets.
Further, in an embodiment of the present invention, in the step of updating the position and the velocity of each particle according to the individual optimum position and the population optimum position, the position and the velocity of each particle are updated by:
V 1 ＝V 0 ×w+S×r×(pbest-x 0 )+S×r×(gbest-x 0 )
x 1 ＝x 0 +V 1
wherein V is 0 And V 1 Indicating the velocity, x, of the particle before and after updating, respectively 0 And x 1 The speeds of the particles before and after updating are represented respectively, w represents an inertia factor, S represents a learning factor, and r represents [0,1 ]]Random numbers within the range, pbest represents the individual optimal position, gbest represents the population optimal position.
Further, in one embodiment of the present invention, the step of selecting, intersecting and mutating the particle swarm to obtain an optimized particle swarm specifically includes:
selecting one of the population of particles in a roulette manner to reassign the particle parameters;
the two particles with the rearmost ordering in the particle swarm are subjected to cross treatment by a real number cross method, so that two new particles are obtained and added into the particle swarm;
traversing the particle swarm, and carrying out mutation operation on particles in the particle swarm according to the preset mutation probability to obtain an optimized particle swarm.
In a second aspect, an embodiment of the present invention provides a trunk coordination control system based on a macroscopic base map, including:
the multi-objective optimization model construction module is used for constructing a multi-objective optimization model of trunk coordination control, wherein the multi-objective optimization model takes the maximum gradient of an MFD ascending section, the maximum road network bearing capacity, the minimum road network vehicle average delay and the minimum road network queuing coefficient as optimization targets, and takes the public period of the trunk, the effective green light duration of the phase and the phase difference of an intersection as parameters to be optimized;
the model optimization module is used for acquiring traffic flow data of a trunk line to be optimized, and optimizing the multi-target optimization model through a multi-target particle swarm algorithm and a genetic algorithm according to the traffic flow data to obtain an optimal parameter combination of the parameters to be optimized;
The coordination control module is used for carrying out trunk coordination control on the trunk line to be optimized according to the optimal parameter combination;
in the optimization process of the multi-objective optimization model, the average delay of road network vehicles and the queuing coefficient of the road network corresponding to each particle are determined through simulation, and the gradient of the MFD ascending section and the bearing capacity of the road network corresponding to each particle are determined through a macroscopic basic diagram obtained through clustering fitting.
In a third aspect, an embodiment of the present invention provides a trunk coordination control device based on a macroscopic basic diagram, including:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement a macro base graph-based trunk coordination control method as described above.
In a fourth aspect, embodiments of the present invention also provide a computer readable storage medium having stored therein a processor executable program which when executed by a processor is configured to perform a macroscopic base map based trunk coordination control method as described above.
The advantages and benefits of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
According to the embodiment of the invention, the macro evaluation index based on the macro basic diagram is considered, a multi-target optimization model of the trunk coordination control is constructed, and the optimal parameter combination is obtained by optimizing a multi-target particle swarm optimization algorithm and a genetic algorithm, so that the trunk coordination control can be performed according to the optimal parameter combination. According to the embodiment of the invention, the macro evaluation index based on the macro basic diagram is incorporated into the main line coordination control optimization, so that the main line coordination control can give consideration to macroscopic and microscopic traffic efficiency, and the model optimization is carried out through the multi-target particle swarm optimization algorithm and the genetic algorithm, so that the control effect of the main line coordination control and the vehicle passing efficiency are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will refer to the drawings that are needed in the embodiments of the present invention, and it should be understood that the drawings in the following description are only for convenience and clarity to describe some embodiments in the technical solutions of the present invention, and other drawings may be obtained according to these drawings without any inventive effort for those skilled in the art.
FIG. 1 is a flow chart of steps of a trunk coordination control method based on a macroscopic basic diagram provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of an optimization flow of a multi-objective optimization model according to an embodiment of the present invention;
FIG. 3 is a schematic representation of a typical macroscopic basic diagram provided by an embodiment of the present invention;
FIG. 4 is a schematic diagram of boundary searching by a groined boundary extraction method according to an embodiment of the present invention;
FIG. 5 (a) is a schematic diagram of a fitted three-segment closed MFD plot provided by an embodiment of the present invention;
FIG. 5 (b) is a schematic illustration of a fitted two-segment non-closed MFD plot provided by an embodiment of the present invention;
fig. 6 (a) is a schematic diagram of a macroscopic basic diagram obtained by a simulation experiment of a trunk coordination control method according to an embodiment of the present invention;
fig. 6 (b) is a schematic diagram of a macroscopic basic diagram obtained by a simulation experiment of a first control experiment set according to an embodiment of the present invention;
FIG. 6 (c) is a schematic diagram of a macroscopic basic diagram obtained by simulation experiment of a second control experiment set according to the embodiment of the present invention;
fig. 6 (d) is a schematic diagram of a macroscopic basic diagram obtained by a simulation experiment of a third control experiment set according to an embodiment of the present invention;
FIG. 7 is a system block diagram of a trunk coordination control device based on a macroscopic basic diagram according to an embodiment of the present invention;
Fig. 8 is a block diagram of a trunk coordination control device based on a macroscopic basic diagram according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
In the description of the present invention, the plurality means two or more, and if the description is made to the first and second for the purpose of distinguishing technical features, it should not be construed as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the precedence of the indicated technical features. Furthermore, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.
The macroscopic fundamental diagram (Macroscopic Fundamental Diagram, MFD) analyzes the road network at the macroscopic level with road network detection data, reflecting the general relationship and inherent objective rules between traffic, density, total traffic in the road network. Xu Feifei and the like prove that road network traffic control strategies such as bus lanes, forbidden measures and the like have great influence on the MFD form through simulation experiments; hui Yanyan et al analyze the effect of the trunk control strategy on MFD and found that there is an optimal common period to maximize the trunk network traffic efficiency; sun Qiuxia and the like propose a road network key road section identification method by identifying the MFD shape change after the road section is missing. As described above, in recent years, the application of MFDs has focused on evaluation indexes using the MFD form as a control strategy, research on influence factors of MFDs, road network sub-division and boundary control based on MFDs, and the like, and it is rarely involved how MFDs are one of optimization targets to guide road network signal control strategy optimization.
According to the invention, from the MFD characteristics, an MFD modeling method under a simulation platform is utilized, macroscopic efficacy evaluation indexes based on the road network operation efficiency of the MFD are provided, an MFD multi-target trunk control strategy optimization model is established and considered in combination with the traditional evaluation indexes, and parameter solving is carried out on the model by combining a genetic algorithm with a multi-target particle swarm algorithm (GA-MOPSO), so that the solving performance is further improved. The invention aims to overcome the defect that the existing trunk line coordination control method only considers microscopic evaluation indexes, brings macroscopic basic graph characteristics and indexes into trunk line coordination control optimization, constructs a road network macroscopic evaluation index and an extraction method thereof based on macroscopic basic graph characteristics, and solves a trunk line coordination control strategy by taking the macroscopic index as an optimization target to obtain a better trunk line control effect.
Referring to fig. 1, an embodiment of the present invention provides a trunk coordination control method based on a macroscopic basic diagram, which specifically includes the following steps:
s101, constructing a multi-objective optimization model of trunk coordination control, wherein the multi-objective optimization model takes the maximum gradient of an MFD ascending segment, the maximum road network bearing capacity, the minimum average delay of road network vehicles and the minimum road network queuing coefficient as optimization targets, and takes the public period of the trunk, the effective green light duration of the phase and the phase difference of an intersection as parameters to be optimized.
Specifically, the slope of the MFD ascending section and the road network bearing capacity are introduced as road network macroscopic efficiency indexes to carry out optimization solution, and the slope and the road network macroscopic efficiency indexes are obtained through MFD morphological clustering and fitting solution output by a simulation experiment; the road network queuing coefficients are used instead of the traditional road network queuing lengths, which are defined as the sum of all lane queuing lengths and the ratio of lane lengths. The effective green light time length of the phase is the green light time length of each phase of each intersection; the intersection phase difference is the phase difference between each intersection and the first intersection.
Further as an alternative embodiment, the objective function of the multi-objective optimization model is:
wherein F (C, G, offset) represents an objective function, Indicating road network vehicle average delay +.>Representing the queuing coefficient of the road network, A 1 Represents the slope, q of the rising section of the MFD max Representing road network bearing capacity;
constraint conditions of the multi-objective optimization model are as follows:
wherein the queue i Indicating the queuing length of the ith lane, L i Represents the lane length of the i-th lane, C represents the trunk common period, C min And C max The upper and lower limits of C are indicated respectively,indicating the effective green light duration of the jth phase of the ith intersection,/for the phase of the ith intersection>And->Respectively indicate->Upper and lower limit of (2), offset i Indicating the phase difference of the i-th intersection with the first intersection. In the embodiment of the invention, the phase difference of the first intersection is set to be 0.
S102, acquiring traffic flow data of a trunk line to be optimized, and optimizing a multi-target optimization model through a multi-target particle swarm algorithm and a genetic algorithm according to the traffic flow data to obtain an optimal parameter combination of parameters to be optimized;
in the optimization process of the multi-objective optimization model, the average delay of road network vehicles and the queuing coefficient of the road network corresponding to each particle are determined through simulation, and the gradient of the MFD ascending section and the bearing capacity of the road network corresponding to each particle are determined through a macroscopic basic diagram obtained through clustering fitting.
Specifically, the embodiment of the invention operates by combining a Multi-objective particle swarm algorithm MOPSO (Multi-Objective Particle Swarm Optimization) with a genetic algorithm, namely, based on the original particle swarm algorithm, a Multi-objective optimization algorithm with rapid non-dominant and parto solution-based selection, intersection and variation strategies is adopted, and finally, the most advantageous solution set in the Multi-objective is determined.
Further as an optional implementation manner, the step of optimizing the multi-objective optimization model by combining a multi-objective particle swarm algorithm with a genetic algorithm according to the traffic flow data to obtain an optimal parameter combination of parameters to be optimized specifically includes:
a1, determining initial values of positions and speeds of various particles in a particle swarm, and initial solution sets and convergence conditions of the particle swarm;
a2, simulating according to the vehicle flow data and the positions and speeds of all particles in the initial particle group to obtain road network vehicle average delay, road network queuing coefficients and MFD data point sets corresponding to all particles, wherein the abscissa and ordinate of the data points in the MFD data point sets are road network weighted density and road network weighted flow respectively;
a3, carrying out cluster fitting on the MFD data point set to obtain a macroscopic basic diagram, and determining the gradient of the MFD ascending section and the road network bearing capacity corresponding to each particle according to the macroscopic basic diagram;
a4, performing non-dominant sorting on each particle to determine the individual optimal position of each particle, and performing non-dominant sorting on the particle group to determine the group optimal position of the particle group;
a5, updating the position and the speed of each particle according to the individual optimal position and the group optimal position;
A6, selecting, crossing and mutating the particle swarm to obtain an optimized particle swarm;
and A7, if the convergence condition is met, taking the parameter value combination of the optimal position of the historical group of the particle swarm as the optimal parameter combination, and if the convergence condition is not met, returning to the step of simulating according to the vehicle flow data and the position and the speed of each particle in the initial particle swarm.
Further as an alternative embodiment, in the step of updating the position and velocity of each particle according to the individual optimum position and the population optimum position, the position and velocity of each particle are updated by:
V 1 ＝V 0 ×w+S×r×(pbest-x 0 )+S×r×(gbest-x 0 )
x 1 ＝x 0 +V 1
wherein V is 0 And V 1 Indicating the velocity, x, of the particle before and after updating, respectively 0 And x 1 The speeds of the particles before and after updating are represented respectively, w represents an inertia factor, S represents a learning factor, and r represents [0,1 ]]Random numbers within the range, pbest represents the individual optimal position, gbest represents the population optimal position.
Further as an optional embodiment, step A6 of selecting, intersecting and mutating the particle swarm to obtain an optimized particle swarm specifically includes:
a61, selecting one particle in the particle group in a roulette manner to reappear the particle parameters;
A62, performing cross treatment on two particles with the rearmost sequence in the particle swarm by a real number cross method to obtain two new particles, and adding the two new particles into the particle swarm;
and A63, traversing the particle swarm, and carrying out mutation operation on particles in the particle swarm according to the preset mutation probability to obtain an optimized particle swarm.
Fig. 2 is a schematic diagram of an optimization flow of a multi-objective optimization model according to an embodiment of the present invention, which is specifically as follows:
step1: initializing the scale (e.g. m=15) of the particle swarm and an initial solution set, namely, a trunk public period, effective green light duration of each intersection phase, intersection phase difference and the like, and setting convergence conditions (e.g. maximum iteration times);
step2: the particle swarm changes the signal control parameters of each intersection through a com interface, and invokes Vissim to simulate to obtain the output road network weighted density and flow, and the slope A of the MFD ascending segment is obtained through clustering and fitting 1 Road network bearing capacity q max Meanwhile, the average delay of the road network vehicle and the road network queuing coefficient are obtained through the detector;
step3: non-dominant sorting is carried out on the historical solutions of each particle, the solution set (namely the optimal position of an individual) of the forefront of each particle is marked as pbest, and the solution set (namely the optimal position of a group) of all the particles with the forefront of the historical sorting is marked as gbest;
Step4: the position and velocity of each particle is updated as follows:
V 1 ＝V 0 ×w+S×r×(pbest-x 0 )+S×r×(gbest-x 0 )
x 1 ＝x 0 +V 1
wherein V is 0 And V 1 Indicating the velocity, x, of the particle before and after updating, respectively 0 And x 1 The speeds of the particles before and after updating are represented respectively, w represents an inertia factor, S represents a learning factor, and r represents [0,1]]Random numbers within the range, pbest representing the individual optimal position, gbest representing the population optimal position, both updated in each cycle;
step5: a selecting operation of selecting one of the particle reassignment parameters in a roulette manner;
step6: the crossover operation, the real number crossover method is selected, the method refers to that the timing parameter combination of two chromosomes generates two new individuals through linear combination, for example, the crossover operation method of the mth particle am and the nth particle an in the jth phase is as follows:
am j ＝(1-M)am j +Man j
an j ＝(1-M)an j +Mam j
where M is a random number between intervals [0,1 ]. Crossing the two particles with the rearmost ordering in the parent population;
step7: the mutation operation is carried out, the group is traversed, and values are randomly allocated to the particles again according to the mutation probability Pm;
step8: and repeating the steps 2-7, checking whether constraint is met in each iteration, and ending solving when convergence conditions are met, wherein the parameter value combination with the forefront corresponding ordering is the optimal parameter combination.
Further as an optional implementation manner, the step A3 of performing cluster fitting on the MFD data point set to obtain a macroscopic basic diagram, and determining the slope of the MFD rising section and the road network bearing capacity corresponding to each particle according to the macroscopic basic diagram specifically includes:
a31, performing boundary search on the MFD data point set by a groined boundary extraction method, and generating an initial MFD diagram according to the searched boundary points;
a32, clustering the initial MFD graphs to obtain two or three types of data sample sets;
a33, performing piecewise linear fitting on each data sample set to obtain a macroscopic basic diagram, wherein the macroscopic basic diagram at least comprises a rising section structure and a stable section structure;
a34, determining the slope of the MFD ascending segment corresponding to the current particle according to the ratio of the road network weighted flow of the ascending segment structure to the road network weighted density;
a35, determining the road network bearing capacity corresponding to the current particles according to the road network weighted flow of the stable segment structure.
Specifically, the macroscopic basic diagram is used as a basic attribute of the road network, and corresponding macroscopic basic diagrams exist in any road network form. Fig. 3 is a schematic view of a typical macroscopic basic diagram according to an embodiment of the present invention, where the typical macroscopic basic diagram includes a three-stage structure: the linear function expressions corresponding to the ascending section, the stable section and the descending section are as follows:
Clustering the collected and drawn MFDs is a common means for dividing road network states, and the invention needs to identify and divide ascending segments, stable segments and descending segments in the MFDs through clustering, and the invention uses Gaussian mixture clustering (Gaussian Mixture Model, GMM) for state division.
The characterization of the macroscopic efficacy of the road network by the MFD is mainly characterized by the maximum flow q of the road network max Slope A of rising section 1 The two respectively describe the initial running efficiency of the road network under free flow and the upper limit of the bearing capacity of the road network under saturated flow. In view of both characterization of efficiency and spatial "upper bound", the MFD morphology should be focused on preserving the upper boundary point of the MFD profile. The problem is how to extract the boundary points close to the upper part of the data set in the two-dimensional plane, and the invention is completed by a groined boundary point extraction method which is introduced into the image processing technology.
As shown in the figureFig. 4 is a schematic diagram of boundary searching by a groined boundary extraction method according to an embodiment of the present invention. Searching and extracting boundary points in a discrete point set through a 'groined' area in fig. 4, wherein the center of circle i (k) i ,q i ) Taking R as a radius as a search range for the current data point, taking the value as the average Euclidean distance between each point in the data set, and taking R as the average Euclidean distance 1 、r 2 For the horizontal and vertical search distances, the values are respectively the average horizontal and vertical distances between the points, 8 areas are divided from the search area around the current data point, the embodiment of the invention defines that when 2 continuous blank areas exist in the area around 8 points i, the point i is the boundary point, and the embodiment of the invention focuses on searching the boundary point of the trapezoid three-section structure, so that the area right below in fig. 4 is not listed in the blank area search. R, r 1 R 2 Calculated by the following formula:
by processing, MFD morphology that retains only boundary points can be obtained.
Further as an alternative embodiment, the step a32 of clustering the initial MFD map to obtain two or three types of data sample sets specifically includes:
a321, clustering the initial MFD graph by taking 3 as a clustering number to obtain three classes of undetermined sample sets;
a322, determining the central point of each undetermined sample set from left to right as a first central point, a second central point and a third central point respectively;
a333, when the road network weighted flow of the first center point and the road network weighted flow of the third center point are smaller than the road network weighted flow of the second center point, determining that the initial MFD image is a three-section closed type MFD image, outputting a sample set to be determined as a data sample set, otherwise, determining that the initial MFD image is a two-section non-closed type MFD image, and clustering the initial MFD image again by taking 2 as a clustering number to obtain two kinds of data sample sets.
Specifically, the GMM cluster number may be set to 3, that is, to a three-segment structure in the MFD, and a linear equation set corresponding to the three-segment sample set is fitted by the least square method. However, in practical applications, due to the non-uniformity of the road network requirements in space and time, or the road network is far from reaching a supersaturated state, the drawn MFD shape is often not an ideal three-section closed trapezoid, but is an unclosed approximately parabolic structure (which can be fitted into a two-section unclosed MFD graph), i.e. only a rising section and a stationary section. Considering the effect of the MFD on the improvement of the road network operation efficiency, the supersaturation congestion state corresponding to the descending section is not considered, so that 3 sample sets obtained by clustering are compared, and the number of GMM clusters is changed into 2 for clustering for the non-closed MFD. The steps of MFD acquisition, clustering and fitting are as follows:
step1: simulation, obtaining result k w Is of abscissa, q w Generating an MFD data set scatter diagram for the ordinate, traversing all data by using a 'groined' boundary searching method, and only reserving boundary points to obtain a preliminary MFD diagram;
step2: using GMM to cluster the obtained MFD graphs, wherein the cluster number is 3, and obtaining a cluster corresponding sample set D= { D 1 ,D 2 ,D 3 }；
Step3: determining the location of a center point in a sample set of three categories from left to right { (k) 1 ,q 1 ),(k 2 ,q 2 ),(k 3 ,q 3 ) Determining MFD morphology from the spatial location of the center point when q is satisfied 1 <q 2 And q 3 <q 2 At this point, the MFD morphology is typically three-segment closed trapezoids; when the above condition is not satisfied, e.g. q 3 >q 2 The MFD is in a two-section non-closed structure with only an ascending section and a stable section, the clustering number is changed to 2, and GMM clustering is performed again;
step4: and performing piecewise linear fitting on the finally generated sample set to obtain a final MFD map.
Fig. 5 (a) is a schematic diagram of a three-segment closed MFD graph obtained by fitting according to an embodiment of the present invention, and fig. 5 (b) is a schematic diagram of a two-segment non-closed MFD graph obtained by fitting according to an embodiment of the present invention. From the MFD characteristics, the following macroscopic efficiency indicators are determined:
(1) MFD rising segment slope: i.e. the ratio of the flow rate to the density of the ascending segment, is an index describing the time operation efficiency of the road network.
Slope A 1 The expression is as follows, wherein k 1 The rising and plateau inflection points are plotted on the abscissa for fig. 5 (a) or 5 (b).
(2) Road network bearing capacity: the prior study defines the road network bearing capacity as the traffic quantity which can be borne when the road network keeps a good running state under certain road conditions and traffic control conditions, and is an index for describing the road network traffic supply capacity. q max The maximum value of the road network traffic under the current control scheme is reflected and is defined as the road network bearing capacity.
And S103, carrying out trunk coordination control on the trunk line to be optimized according to the optimal parameter combination.
Specifically, the main line coordination control is performed according to the optimized optimal parameter combination, namely the optimal combination of the main line public period, the phase effective green light duration and the intersection phase difference.
The method flow of the embodiment of the invention is described above. The embodiment of the invention provides two forms of closed type and two-section type (ascending section, stable section and non-closed type) of a three-section type (ascending section, stable section and descending section) of a macroscopic basic diagram, which are represented by an ascending section slope A 1 Maximum bearing capacity q of road network in stationary section max The method is used as a road network macroscopic operation efficiency index to be incorporated into a main line coordination control optimization process; extracting key points of the macroscopic basic map by using a 'groined' image processing method, and using the key points for data point clustering and linear fitting; and (3) taking a public period, a green-signal ratio of each phase and a phase difference of each intersection in a dry line network as parameters to be solved, and taking four targets of maximum gradient of an MFD ascending section, maximum road network bearing capacity, minimum average delay of road network vehicles and minimum road network queuing coefficient as optimal building a multi-target optimization model, and carrying out model solving by using a GA-MOPSO algorithm. Compared with the prior art, the embodiment of the invention has the following advantages:
1) The optimization target of the macro basic map index is considered, so that the main line coordination control effect can better consider the macro and micro traffic efficiency, and the road network macro basic map form has stronger stability and controllability;
2) The method can quickly and accurately divide the state of the macroscopic basic diagram and obtain related indexes by combining a 'groined' image processing method with Gaussian mixture clustering, and the mode can be popularized to various road networks;
3) The GA-MOPSO is used for carrying out model solving, the algorithm combines a genetic algorithm with a multi-target particle swarm algorithm, and the result shows that the solving efficiency and the obtained scheme are better.
The trunk coordination control method of the embodiment of the invention is further described below in connection with simulation experiments.
Taking Dongguan city continuous lifting trunk line network as an example, manually collecting traffic flow and signal control parameters as experimental input, and simultaneously using other three methods as a comparison experimental group to compare the optimization effect with the trunk line coordination control method in the embodiment of the invention.
The optimization model used by the trunk coordination control method of the embodiment of the invention is marked as a model F0, and the model is solved by GA-MOPSO; the method comprises the steps that a first comparison experiment set is used for establishing an optimization model with minimized average delay of road network vehicles, minimized queuing coefficient of the road network and maximized system traffic capacity, the optimization model is marked as a model F1, and a GA-MOPSO solution model is also used, wherein the system traffic capacity is the sum of output flow in unit time of a road network intersection; the third control experiment group builds an optimization model F2 according to the traditional numerical method and optimizes; the fourth control experiment group also constructs an optimization model F3 by using the optimization targets of maximum gradient of the MFD ascending section, maximum road network bearing capacity, minimum average delay of road network vehicles and minimum road network queuing coefficient, but uses MOPSO which is not improved to perform model optimization. The characteristics of each scheme are shown in table 1 below.
TABLE 1
The morphological diagrams of the macroscopic basic diagrams of the respective schemes obtained by simulation experiments are shown in fig. 6 (a) to 6 (d). In order to comprehensively evaluate the advantages and disadvantages of the four models in the optimizing effect, delay, queuing length, MFD morphological parameters and system traffic capacity are respectively used as evaluation indexes, and comparison results are shown in the following table 2.
TABLE 2
From experimental results, the method provided by the embodiment of the invention has the best effect in indexes such as delay, queuing coefficient and the like, and the total MFD bearing capacity of the road network is slightly lower than that of the model F1; the maximum flow contained by the lower road network of the model F0 control scheme is 1664veh/h, and the gradient of the MFD ascending section is maximum, which indicates that the bearing capacity is reached fastest in the three schemes, the lower density has higher flow, and the running efficiency of the free-flow lower road network is highest. The total delay, the average delay and the queuing coefficient of the model F1 are higher than those of the model F0, and the carrying capacity and the traffic capacity index are slightly higher than those of the model F0 because the traffic capacity is used as an optimization target, so that the model F1 has higher output capacity in a saturated state. The model F2 and the model F3 are poor in evaluation indexes, and the model F3 is good in MFD index due to consideration of the MFD parameters, but is easy to fall into a local optimal solution due to limitation of an MOPSO algorithm. The model F2 takes the main line green wave bandwidth as the priority, so that the main line green signal ratio is too high, the period is too long, and the delay is huge.
From the MFD morphology and stability results, the four schemes MFD were two-stage, unsealed, indicating that no four schemes reached supersaturation or congestion under existing traffic demand and supply conditions. The corresponding scheme of the model F0 considers the MFD parameter, the rising section slope is the largest, which shows that the efficiency is the highest in the free flow state, the data points are more concentrated in the form of the MFD, the obvious rising and stable section states are presented, the RMSE is the smallest no matter the non-boundary points are considered or excluded, the fitting effect is the best, and the MFD stability is the best; the model F3 also considers the MFD parameter, but the MOPSO algorithm is easy to fall into the characteristic of local optimization, so that the optimization effect is not ideal, the data discreteness is large, and the bearing capacity of a stable section is maximum; the corresponding scheme of the model F2 is a traditional numerical method, the period value is maximum under the saturated traffic flow, each index is not ideal in performance, the free flow state of the ascending section has higher efficiency, but the smooth section under the saturated flow is most discrete and has the phenomenon of 'hysteresis', which indicates that the traffic flow is suddenly increased or reduced under the scheme, and the road network is extremely unstable; the corresponding scheme of the model F1 does not consider the MFD parameters, but delay and queuing length are traffic efficiency consideration indexes, so that each evaluation index is closer to the scheme of the embodiment of the invention, but the MFD stability of the scheme is worse than that of the scheme of the embodiment of the invention, and the total delay is larger.
According to the experimental results, the trunk coordination control method provided by the embodiment of the invention can better consider macroscopic and microscopic traffic efficiency in a trunk area road network and saturated traffic flow scene, the MFD form has stronger stability and controllability, the improved GA-MOPSO algorithm effect is far better than that of MOPSO, and the effectiveness of the model and algorithm in the invention is verified.
Referring to fig. 7, an embodiment of the present invention provides a trunk coordination control system based on a macroscopic base diagram, including:
the multi-objective optimization model construction module is used for constructing a multi-objective optimization model of trunk coordination control, wherein the multi-objective optimization model takes the maximum gradient of an MFD ascending section, the maximum road network bearing capacity, the minimum average delay of road network vehicles and the minimum road network queuing coefficient as optimization targets, and takes the public period of the trunk, the effective green light duration of the phase and the phase difference of an intersection as parameters to be optimized;
the model optimization module is used for acquiring traffic flow data of a trunk line to be optimized, and optimizing the multi-target optimization model through a multi-target particle swarm algorithm and a genetic algorithm according to the traffic flow data to obtain an optimal parameter combination of parameters to be optimized;
the coordination control module is used for carrying out main line coordination control on the main line to be optimized according to the optimal parameter combination;
In the optimization process of the multi-objective optimization model, the average delay of road network vehicles and the queuing coefficient of the road network corresponding to each particle are determined through simulation, and the gradient of the MFD ascending section and the bearing capacity of the road network corresponding to each particle are determined through a macroscopic basic diagram obtained through clustering fitting.
The content in the method embodiment is applicable to the system embodiment, the functions specifically realized by the system embodiment are the same as those of the method embodiment, and the achieved beneficial effects are the same as those of the method embodiment.
Referring to fig. 8, an embodiment of the present invention provides a trunk coordination control device based on a macroscopic basic diagram, including:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement a macro base graph-based trunk coordination control method as described above.
The content in the method embodiment is applicable to the embodiment of the device, and the functions specifically realized by the embodiment of the device are the same as those of the method embodiment, and the obtained beneficial effects are the same as those of the method embodiment.
The embodiment of the invention also provides a computer readable storage medium, in which a processor executable program is stored, which when executed by a processor is used to perform a macroscopic base map based trunk coordination control method as described above.
The computer readable storage medium of the embodiment of the invention can execute the trunk line coordination control method based on the macroscopic basic diagram, can execute any combination implementation steps of the embodiment of the method, and has the corresponding functions and beneficial effects of the method.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the method shown in fig. 1.
In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.
Furthermore, while the present invention has been described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the functions and/or features described above may be integrated in a single physical device and/or software module or one or more of the functions and/or features may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the invention, which is to be defined in the appended claims and their full scope of equivalents.
The above functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or a part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above-described method of the various embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium upon which the program described above is printed, as the program described above may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the foregoing description of the present specification, reference has been made to the terms "one embodiment/example", "another embodiment/example", "certain embodiments/examples", and the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the application, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present application has been described in detail, the present application is not limited to the above embodiments, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present application, and these equivalent modifications and substitutions are intended to be included in the scope of the present application as defined in the appended claims.

Claims (9)

1. The trunk line coordination control method based on the macroscopic basic diagram is characterized by comprising the following steps of:
constructing a multi-objective optimization model of trunk coordination control, wherein the multi-objective optimization model takes the maximum gradient of an MFD ascending section, the maximum road network bearing capacity, the minimum average delay of road network vehicles and the minimum road network queuing coefficient as optimization targets, and takes the public period of the trunk, the effective green light duration of the phase and the phase difference of an intersection as parameters to be optimized;
acquiring traffic flow data of a trunk line to be optimized, and optimizing the multi-objective optimization model through a multi-objective particle swarm algorithm and a genetic algorithm according to the traffic flow data to obtain an optimal parameter combination of the parameters to be optimized;
Carrying out trunk coordination control on the trunk to be optimized according to the optimal parameter combination;
in the optimization process of the multi-objective optimization model, the average delay of road network vehicles and the queuing coefficient of the road network corresponding to each particle are determined through simulation, and the gradient of the MFD ascending section and the bearing capacity of the road network corresponding to each particle are determined through a macroscopic basic diagram obtained through clustering fitting;
the step of optimizing the multi-objective optimization model by combining a genetic algorithm with a multi-objective particle swarm algorithm according to the traffic flow data to obtain an optimal parameter combination of the parameters to be optimized specifically comprises the following steps:
determining initial values of positions and speeds of various particles in the particle swarm, initial solution sets of the particle swarm and convergence conditions;
simulating according to the traffic flow data and the positions and speeds of all particles in the initial particle group to obtain road network vehicle average delay, road network queuing coefficients and MFD data point sets corresponding to all particles, wherein the abscissa and ordinate of the data points in the MFD data point sets are road network weighted density and road network weighted flow respectively;
performing cluster fitting on the MFD data point set to obtain a macroscopic basic diagram, and determining the gradient of the MFD ascending section and the road network bearing capacity corresponding to each particle according to the macroscopic basic diagram;
The method comprises the steps of performing non-dominant sorting on each particle to determine an individual optimal position of each particle, and performing non-dominant sorting on a particle group to determine a group optimal position of the particle group;
updating the position and the speed of each particle according to the individual optimal position and the group optimal position;
selecting, crossing and mutating the particle swarm to obtain an optimized particle swarm;
and if the convergence condition is met, taking a parameter value combination of the optimal position of the historical group of the particle swarm as an optimal parameter combination, and if the convergence condition is not met, returning to the step of simulating according to the vehicle flow data and the position and the speed of each particle in the initial particle swarm.
2. The trunk coordination control method based on a macroscopic basic graph according to claim 1, wherein the objective function of the multi-objective optimization model is:
wherein F (C, G, offset) represents an objective function,indicating road network vehicle average delay +.>Representing the queuing coefficient of the road network, A 1 Represents the slope, q of the rising section of the MFD max Representing road network bearing capacity;
constraint conditions of the multi-objective optimization model are as follows:
wherein the queue i Indicating the queuing length of the ith lane, L i Represent the firsti lanes of lane length, C represents the trunk common period, C min And C max The upper and lower limits of C are indicated respectively,indicating the effective green light duration of the jth phase of the ith intersection,and->Respectively indicate->Upper and lower limit of (2), offset i Indicating the phase difference of the i-th intersection with the first intersection.
3. The trunk coordination control method based on a macroscopic basic diagram according to claim 1, wherein the step of performing cluster fitting on the MFD data point set to obtain a macroscopic basic diagram, and determining the slope of the MFD rising segment and the road network bearing capacity corresponding to each particle according to the macroscopic basic diagram specifically comprises:
performing boundary searching on the MFD data point set by a groined boundary extraction method, and generating an initial MFD graph according to the searched boundary points;
clustering the initial MFD graphs to obtain two or three types of data sample sets;
performing piecewise linear fitting on each data sample set to obtain a macroscopic basic diagram, wherein the macroscopic basic diagram at least comprises a rising section structure and a stable section structure;
determining the slope of the MFD ascending segment corresponding to the current particle according to the ratio of the road network weighted flow of the ascending segment structure to the road network weighted density;
And determining the road network bearing capacity corresponding to the current particles according to the road network weighted flow of the stable segment structure.
4. A method of coordinated control of trunks based on macroscopic fundamental graphs according to claim 3, characterised in that the step of clustering the initial MFD-graphs to obtain two or three classes of data sample sets comprises:
clustering the initial MFD images by taking 3 as a clustering number to obtain three classes of undetermined sample sets;
determining the center point of each undetermined sample set from left to right as a first center point, a second center point and a third center point respectively;
and when the road network weighted flow of the first center point and the road network weighted flow of the third center point are smaller than the road network weighted flow of the second center point, determining that the initial MFD image is a three-section closed type MFD image, outputting the to-be-determined sample set as a data sample set, otherwise, determining that the initial MFD image is a two-section non-closed type MFD image, and clustering the initial MFD image again by taking 2 as a clustering number to obtain two kinds of data sample sets.
5. A macroscopic-base-graph-based trunk line coordinated control method according to claim 1, wherein in the step of updating the position and speed of each particle based on the individual optimum position and the group optimum position, the position and speed of each particle are updated by:
V 1 ＝V 0 ×w+S×r×(pbest-x 0 )+S×r×(gbest-x 0 )
x 1 ＝x 0 +V 1
Wherein V is 0 And V 1 Indicating the velocity, x, of the particle before and after updating, respectively 0 And x 1 The speeds of the particles before and after updating are represented respectively, w represents an inertia factor, S represents a learning factor, and r represents [0,1 ]]Random numbers within the range, pbest represents the individual optimal position, gbest represents the population optimal position.
6. The method for coordinated control of a trunk line based on a macroscopic basic diagram according to claim 1, wherein the step of selecting, crossing and mutating the particle swarm to obtain an optimized particle swarm comprises the following steps:
selecting one of the population of particles in a roulette manner to reassign the particle parameters;
the two particles with the rearmost ordering in the particle swarm are subjected to cross treatment by a real number cross method, so that two new particles are obtained and added into the particle swarm;
traversing the particle swarm, and carrying out mutation operation on particles in the particle swarm according to the preset mutation probability to obtain an optimized particle swarm.
7. A macroscopic-base-graph-based trunk coordination control system, comprising:
the multi-objective optimization model construction module is used for constructing a multi-objective optimization model of trunk coordination control, wherein the multi-objective optimization model takes the maximum gradient of an MFD ascending section, the maximum road network bearing capacity, the minimum road network vehicle average delay and the minimum road network queuing coefficient as optimization targets, and takes the public period of the trunk, the effective green light duration of the phase and the phase difference of an intersection as parameters to be optimized;
The model optimization module is used for acquiring traffic flow data of a trunk line to be optimized, and optimizing the multi-target optimization model through a multi-target particle swarm algorithm and a genetic algorithm according to the traffic flow data to obtain an optimal parameter combination of the parameters to be optimized;
the coordination control module is used for carrying out trunk coordination control on the trunk line to be optimized according to the optimal parameter combination;
in the optimization process of the multi-objective optimization model, the average delay of road network vehicles and the queuing coefficient of the road network corresponding to each particle are determined through simulation, and the gradient of the MFD ascending section and the bearing capacity of the road network corresponding to each particle are determined through a macroscopic basic diagram obtained through clustering fitting;
the step of optimizing the multi-objective optimization model by combining a genetic algorithm with a multi-objective particle swarm algorithm according to the traffic flow data to obtain an optimal parameter combination of the parameters to be optimized specifically comprises the following steps:
determining initial values of positions and speeds of various particles in the particle swarm, initial solution sets of the particle swarm and convergence conditions;
simulating according to the traffic flow data and the positions and speeds of all particles in the initial particle group to obtain road network vehicle average delay, road network queuing coefficients and MFD data point sets corresponding to all particles, wherein the abscissa and ordinate of the data points in the MFD data point sets are road network weighted density and road network weighted flow respectively;
Performing cluster fitting on the MFD data point set to obtain a macroscopic basic diagram, and determining the gradient of the MFD ascending section and the road network bearing capacity corresponding to each particle according to the macroscopic basic diagram;
the method comprises the steps of performing non-dominant sorting on each particle to determine an individual optimal position of each particle, and performing non-dominant sorting on a particle group to determine a group optimal position of the particle group;
updating the position and the speed of each particle according to the individual optimal position and the group optimal position;
selecting, crossing and mutating the particle swarm to obtain an optimized particle swarm;
and if the convergence condition is met, taking a parameter value combination of the optimal position of the historical group of the particle swarm as an optimal parameter combination, and if the convergence condition is not met, returning to the step of simulating according to the vehicle flow data and the position and the speed of each particle in the initial particle swarm.
8. A macroscopic basic diagram-based trunk coordination control device, comprising:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor is caused to implement a macroscopic base graph based trunk coordination control method as claimed in any of claims 1 to 6.
9. A computer readable storage medium, in which a processor executable program is stored, characterized in that the processor executable program, when being executed by a processor, is for performing a macro base graph based trunk coordination control method according to any of claims 1 to 6.
CN202210980172.4A 2022-08-16 2022-08-16 Main line coordination control method, system, device and medium based on macroscopic basic diagram Active CN115440033B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210980172.4A CN115440033B (en) 2022-08-16 2022-08-16 Main line coordination control method, system, device and medium based on macroscopic basic diagram

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210980172.4A CN115440033B (en) 2022-08-16 2022-08-16 Main line coordination control method, system, device and medium based on macroscopic basic diagram

Publications (2)

Publication Number Publication Date
CN115440033A CN115440033A (en) 2022-12-06
CN115440033B true CN115440033B (en) 2023-08-29

Family

ID=84241686

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210980172.4A Active CN115440033B (en) 2022-08-16 2022-08-16 Main line coordination control method, system, device and medium based on macroscopic basic diagram

Country Status (1)

Country Link
CN (1) CN115440033B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2506237A1 (en) * 2011-04-01 2012-10-03 Honeywell International, Inc. System for presenting taxi instructions and reducing runway incursions
CN106297334A (en) * 2016-10-27 2017-01-04 东南大学 Main line section division methods under Philodendron ‘ Emerald Queen'
CN109872531A (en) * 2019-01-28 2019-06-11 许凌 Road traffic signal controls system-wide net optimized control objective function construction method
WO2019109561A1 (en) * 2017-12-06 2019-06-13 广东交通职业技术学院 Mfd-based method for dynamically creating multiple control boundaries in over-saturated street network in internet of vehicles environment
CN111429733A (en) * 2020-03-24 2020-07-17 浙江工业大学 Road network traffic signal control method based on macroscopic basic graph
CN113327436A (en) * 2021-01-18 2021-08-31 兆边(上海)科技有限公司 Main line coordination control optimization method based on track data
CN113851006A (en) * 2021-09-01 2021-12-28 中山大学 Intersection real-time traffic state estimation method and system based on multi-source data fusion
EP4030376A1 (en) * 2021-01-16 2022-07-20 Bayerische Motoren Werke Aktiengesellschaft Method for determining an impact of ride pooling on a traffic situation

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2506237A1 (en) * 2011-04-01 2012-10-03 Honeywell International, Inc. System for presenting taxi instructions and reducing runway incursions
CN106297334A (en) * 2016-10-27 2017-01-04 东南大学 Main line section division methods under Philodendron ‘ Emerald Queen'
WO2019109561A1 (en) * 2017-12-06 2019-06-13 广东交通职业技术学院 Mfd-based method for dynamically creating multiple control boundaries in over-saturated street network in internet of vehicles environment
CN109872531A (en) * 2019-01-28 2019-06-11 许凌 Road traffic signal controls system-wide net optimized control objective function construction method
CN111429733A (en) * 2020-03-24 2020-07-17 浙江工业大学 Road network traffic signal control method based on macroscopic basic graph
EP4030376A1 (en) * 2021-01-16 2022-07-20 Bayerische Motoren Werke Aktiengesellschaft Method for determining an impact of ride pooling on a traffic situation
CN113327436A (en) * 2021-01-18 2021-08-31 兆边(上海)科技有限公司 Main line coordination control optimization method based on track data
CN113851006A (en) * 2021-09-01 2021-12-28 中山大学 Intersection real-time traffic state estimation method and system based on multi-source data fusion

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
城市交通信号的迭代学习控制及其对路网宏观基本图的影响;闫飞;田福礼;史忠科;;控制理论与应用(第05期);全文 *

Also Published As

Publication number Publication date
CN115440033A (en) 2022-12-06

Similar Documents

Publication Publication Date Title
WO2020220439A1 (en) Highway traffic flow state recognition method based on deep neural network
CN109243172B (en) Traffic flow prediction method for optimizing LSTM neural network based on genetic algorithm
CN100444210C (en) Mixed controlling method of single dot signal controlling crossing
CN109785618B (en) Short-term traffic flow prediction method based on combinational logic
Xu et al. Short-term traffic volume prediction using classification and regression trees
CN110276966B (en) Intersection signal control time interval dividing method
CN111243271A (en) Single-point intersection signal control method based on deep cycle Q learning
CN105551239B (en) travel time prediction method and device
CN111462485A (en) Traffic intersection congestion prediction method based on machine learning
CN113012449B (en) Smart city signal lamp timing optimization method based on multi-sample learning particle swarm
CN104268546A (en) Dynamic scene classification method based on topic model
CN116050672B (en) Urban management method and system based on artificial intelligence
CN116524712A (en) Highway congestion prediction method, system and device integrating space-time associated data
CN110428608A (en) A kind of road passage capability extracting method based on traffic big data
CN102521402B (en) Text filtering system and method
CN115903485A (en) Adaptive DQN model optimization method and application
CN110287995B (en) Multi-feature learning network model method for grading all-day overhead traffic jam conditions
Zheng et al. A deep learning–based approach for moving vehicle counting and short-term traffic prediction from video images
CN108256923A (en) A kind of ETC customer segmentation methods based on vehicle pass-through feature
CN115440033B (en) Main line coordination control method, system, device and medium based on macroscopic basic diagram
CN114694382A (en) Dynamic one-way traffic control system based on Internet of vehicles environment
CN113392577A (en) Regional boundary main intersection signal control method based on deep reinforcement learning
Behura et al. Road accident prediction and feature analysis by using deep learning
CN114463978B (en) Data monitoring method based on track traffic information processing terminal
CN116205356A (en) Novel urban road network dynamic subarea division method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant