CN112133086B - Regional traffic signal data driving control method based on multi-agent network - Google Patents

Regional traffic signal data driving control method based on multi-agent network Download PDF

Info

Publication number
CN112133086B
CN112133086B CN202010798063.1A CN202010798063A CN112133086B CN 112133086 B CN112133086 B CN 112133086B CN 202010798063 A CN202010798063 A CN 202010798063A CN 112133086 B CN112133086 B CN 112133086B
Authority
CN
China
Prior art keywords
intersection
space occupancy
state
error
matrix
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
CN202010798063.1A
Other languages
Chinese (zh)
Other versions
CN112133086A (en
Inventor
张海波
王力
吉鸿海
潘彦斌
李丹阳
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.)
North China University of Technology
Original Assignee
North China University of Technology
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 North China University of Technology filed Critical North China University of Technology
Priority to CN202010798063.1A priority Critical patent/CN112133086B/en
Publication of CN112133086A publication Critical patent/CN112133086A/en
Application granted granted Critical
Publication of CN112133086B publication Critical patent/CN112133086B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • 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
    • 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

Abstract

The invention relates toA regional traffic signal data driving control method based on a multi-agent network is characterized in that a storage forwarding model is established, constraint conditions for green light time of an intersection are adjusted, a time-varying control signal period C (k) is introduced, and a brand-new green light time constraint condition is obtained, so that green light time waste is avoided, the constraint conditions for breaking a fixed period are considered, and the space occupancy rate is guaranteed to meet x all the timeiAnd (k +1) is not less than 0, and the established regional traffic signal control model can describe three traffic state forms of undersaturation, critical saturation and supersaturation at the intersection at the same time, so that the applicability is stronger. The control algorithm is a dynamic feedback control algorithm, can respond to the change of periodic traffic flow, estimates and dynamically adjusts a periodic timing scheme based on the number of vehicles in the current period, and realizes the balance of space occupancy in each direction. The method has the advantages that the saturation degree in all directions is balanced, so that the possibility of supersaturation in certain directions is reduced, the traffic fairness is ensured, and the overall traffic operation efficiency is improved.

Description

Regional traffic signal data driving control method based on multi-agent network
Technical Field
The invention relates to the technical field of intelligent traffic signal control, in particular to a regional traffic signal data driving control method based on a multi-agent network.
Background
The method comprises the steps of obtaining intersection flow parameters through an estimation method on the basis of floating car data (typical mobile detection data sources), constructing a periodic vehicle number estimation model on the basis of a storage-forwarding modeling method, and constructing a regional traffic signal data driving control model which aims at space occupancy balance on the basis of a multi-agent network.
In the traditional analysis of a store-and-forward model, generally, only the traffic signal timing problem in the oversaturated traffic state is considered, more green light time is allocated to a certain direction and a certain period of an undersaturated intersection, and the problem of green light time waste, namely the idle discharge phenomenon, exists; in fact, at this time, the traffic capacity can be guaranteed only by allocating less green light time. However, most traffic signal controls are periodic control, and the constraint of the maximum and minimum green time of the phase is also required to be met, so the adjustable range of the green time in the traditional signal control is limited, and the control problems of three traffic states of undersaturation, critical saturation and oversaturation cannot be perfectly compatible.
In order to solve the problem, in the establishment of a store-and-forward model, constraint conditions for green light time of an intersection are adjusted, a time-varying control signal period C (k) is introduced, and a brand-new green light time constraint condition is obtained, so that green light time waste is avoided, the constraint conditions for breaking a fixed period are considered, and the space occupancy rate is guaranteed to meet x all the timeiAnd (k +1) is not less than 0, and the established regional traffic signal control model can describe three traffic state forms of undersaturation, critical saturation and supersaturation at the intersection at the same time, so that the applicability is stronger.
The invention content is as follows:
the method is based on the practical problems of urban regional traffic detection and signal control, high-precision low-occupancy-ratio floating car data are used as data sources, intersection flow parameters are obtained through an estimation method, a multi-intersection multi-directional vehicle conservation equation is established by combining the networking property, the expansibility and the reproducibility of distributed single-intersection multi-directional space occupancy balance control with a positive system model, and a regional traffic signal data driving control method based on a multi-agent network and aiming at space occupancy balance is provided.
With the rapid development of intelligent vehicles and internet traffic and communication technologies, the scale, quality, accuracy, instantaneity and the like of mobile detection data are greatly improved. The signal control method of the invention is based on floating car data (typical mobile detection data source), does not depend on any model information and fixed detector input, and can provide a better theoretical and application basis for the optimization design of a novel traffic control system under the future road environment. The invention adopts the following technical scheme:
a regional traffic signal data driving control method based on a multi-agent network comprises the following steps:
(1) creating a component-positive system model
Figure GDA0003409792740000021
Wherein x ism(k) N represents the state of the component system element m at the time k, wherein m is equal to or more than 0, and m is equal to 1; a ismnM ≠ n denotes the state quantity transfer proportionality coefficient of the component system element m to the component system element n in the sampling period T > 0; i ism(k) Not less than 0 and Om(k) ≧ 0 represents input and output of Compartment System element m within the sampling period, respectively, and ammThe proportional coefficient is output for the state quantity of more than or equal to 0;
describing the component system model into a vector form:
x(k+1)＝Ax(k)+I(k)
in the formula: x (k) ═ x1(k)，...，xN(k)]T∈RNIs a system state vector;
I(k)＝[I1(k)，...，IN(k)]T∈RNinputting for the outside of the system; a is an element of RN×NIs a system state matrix and has
Figure GDA0003409792740000022
Assuming that the current state quantity of any component is greater than or equal to the total quantity of state transitions in the sampling period, diagonal elements of the state matrix A are all non-negative, and the column sum satisfies:
Figure GDA0003409792740000023
(2) establishing a traffic area multi-intersection variable-period multi-direction space occupancy model with green light time constraint
Figure GDA0003409792740000024
The global balanced dynamic model of its space occupancy can be described as:
Figure GDA0003409792740000025
wherein the global space occupancy state vector is x ═ x1，...，xM]T∈RM，xi∈RNThe global nonlinear dynamic vector is f ═ f1，...，fM]T∈RM，fi∈RNControlling the input green time to
Figure GDA0003409792740000026
Figure GDA0003409792740000027
ui∈RNM represents the number of urban regional intersections, and N represents the number of each direction of a single intersection;
the distributed consistency coordination error for defining the space occupancy rate of the ith direction of the mth intersection is as follows:
Figure GDA0003409792740000031
wherein the content of the first and second substances,
Figure GDA0003409792740000032
representing a connection matrix of a multi-agent system formed by a single cross port and multiple directions,
Figure GDA0003409792740000033
connection matrix representing multi-intersection constituting multi-agent system, biThe connection coefficient between the space occupancy of the ith direction of the mth intersection and the mean value of the expected space occupancy is represented;
the distributed global consistency coordination error of the space occupancy of each direction of the single intersection is described as follows:
Figure GDA0003409792740000034
wherein e ═ e1，...，eN]T∈RN，
Figure GDA0003409792740000035
B＝diag(bi)∈RN×NRepresenting a diagonal matrix;
according to the distributed consistency coordination error, a consistency coordination control item v in the following form is selectedm，i(k)，
Figure GDA0003409792740000036
Or
Figure GDA0003409792740000037
Wherein c > 0 represents an error learning gain,
distributed green light time coordination control strategy for each direction of mth intersection
Figure GDA0003409792740000038
The design is as follows,
Figure GDA0003409792740000039
or
Figure GDA00034097927400000310
Where μ > 0 denotes the coordinated control gain, pm，i> 0, and the parameter learning rate is designed as follows:
Figure GDA00034097927400000311
or
Figure GDA0003409792740000041
Wherein, Fi＝ΠiIs greater than 0; κ > 0 represents the parameter learning gain;
the control and learning gains satisfy the following conditions:
Figure GDA0003409792740000042
Figure GDA0003409792740000043
Figure GDA0003409792740000044
wherein P ═ PT∈RN×N＞0，Q＝QT∈RN×N> 0 is a positive definite matrix;
wherein the global consistency coordination error vector e (k) e RNThe consistency converges to a bounded neighborhood near the zero value, and the neighborhood upper bound of the consistency coordination error is reduced by increasing the error learning gain c.
Drawings
FIG. 1 is a schematic diagram of the component model.
Detailed Description
A positive system with n ≧ 2 components is shown in FIG. 1, in which xm(k) N represents the state of the component system element m at the time k, wherein m is equal to or more than 0, and m is equal to 1; a ismnM ≠ n denotes the state quantity transfer proportionality coefficient of the component system element m to the component system element n in the sampling period T > 0; i ism(k) Not less than 0 and Om(k) ≧ 0 represents input and output of Compartment System element m within the sampling period, respectively, and ammAnd more than or equal to 0 is a state quantity output proportional coefficient. Thus, the state of the component system element m satisfies the following conservation equation:
Figure GDA0003409792740000045
further, equation (4-93) is written in vector form:
x(k+1)＝Ax(k)+I(k)
in the formula: x (k) ═ x1(k)，...，xN(k)]T∈RNIs a system state vector;
I(k)＝[I1(k)，...，IN(k)]T∈RNinputting for the outside of the system; a is an element of RN×NIs a system state matrix and has
Figure GDA0003409792740000051
Assuming that the current state quantity of any component is greater than or equal to the total quantity of state transitions in the sampling period, diagonal elements of the state matrix A are all non-negative, and the column sum satisfies:
Figure GDA0003409792740000052
thus, the state matrix A is a non-negative matrix, so that the component system is a type of positive system, and the matrix A is referred to as the component matrix.
The traffic area multi-intersection variable-period multi-direction space occupancy model considering the green light time constraint is as follows:
Figure GDA0003409792740000053
the global balanced dynamic model of its space occupancy can be described as:
Figure GDA00034097927400000511
wherein the global space occupancy state vector is x ═ x1，...，xM]T∈RM，xi∈RNThe global nonlinear dynamic vector is f ═ f1，...，fM]T∈RM，fi∈RNControlling the input green time to
Figure GDA0003409792740000054
Figure GDA0003409792740000055
ui∈RNM represents the number of urban regional intersections, and N represents the number of each direction of a single intersection.
The control target of the space occupancy equilibrium control is to make the distribution consistency coordination error of the space occupancy of each intersection in each direction zero. The distributed consistency coordination error for defining the space occupancy rate of the ith direction of the mth intersection is as follows:
Figure GDA0003409792740000056
wherein the content of the first and second substances,
Figure GDA0003409792740000057
representing a connection matrix of a multi-agent system formed by a single cross port and multiple directions,
Figure GDA0003409792740000058
connection matrix representing multi-intersection constituting multi-agent system, biAnd the connection coefficient between the space occupancy of the ith direction of the mth intersection and the mean value of the expected space occupancy is shown.
The distributed global consistency coordination error of the space occupancy of each direction of the single intersection can be described as follows:
Figure GDA0003409792740000059
wherein e ═ e1，...，eN]T∈RN，
Figure GDA00034097927400000510
B＝diag(bi)∈RN×NA diagonal matrix is represented.
Considering a multi-agent multi-intersection multidirectional space occupancy network system, all direction communication directed graphs at each intersection are strongly connected, and at least one b existsiNot equal to 0, and selecting a consistency coordination control item v in the following form according to the distributed consistency coordination errorm，i(k)，
Figure GDA0003409792740000061
Or
Figure GDA0003409792740000062
Wherein c > 0 represents an error learning gain,
distributed green light time coordination control strategy for each direction of mth intersection
Figure GDA00034097927400000610
The design is as follows,
Figure GDA0003409792740000063
or
Figure GDA0003409792740000064
Where μ > 0 denotes the coordinated control gain, pm，i> 0, and the parameter learning rate is designed as follows:
Figure GDA0003409792740000065
or
Figure GDA0003409792740000066
Wherein, Fi＝ΠiIs greater than 0; κ > 0 represents the parameter learning gain.
The control and learning gains satisfy the following conditions:
Figure GDA0003409792740000067
Figure GDA0003409792740000068
Figure GDA0003409792740000069
wherein P ═ PT∈RN×N＞0，Q＝QT∈RN×N> 0 is a positive definite matrix;
then there is a global consistency coordination error vector e (k) e RNThe method is characterized in that the method is uniformly converged in a bounded neighborhood near a zero value, the space occupancy of each direction of a single intersection is uniformly converged to a desired space occupancy, and the upper boundary of the neighborhood of the consistency coordination error can be reduced by increasing the error learning gain c.

Claims (1)

1. A regional traffic signal data driving control method based on a multi-agent network is characterized by comprising the following steps:
(1) creating a component-positive system model
Figure FDA0003409792730000011
Wherein x ism(k) N represents the state of the component system element m at the time k, wherein m is equal to or more than 0, and m is equal to 1; a ismnAnd m ≠ n denotes Compertent System elements m through CompaThe state quantity of the moment system element n in the sampling period T is greater than 0 and is transferred to a proportionality coefficient; i ism(k) Not less than 0 and Om(k) More than or equal to 0 respectively represents the input and the output of the component system element m in the sampling period;
describing the component system model into a vector form:
x(k+1)＝Ax(k)+I(k)
in the formula: x (k) ═ x1(k)，...，xN(k)]T∈RNIs a system state vector;
I(k)＝[I1(k)，...，IN(k)]T∈RNinputting for the outside of the system; a is an element of RN×NIs a system state matrix and has
Figure FDA0003409792730000012
Assuming that the current state quantity of any component is greater than or equal to the total quantity of state transitions in the sampling period, diagonal elements of the state matrix A are all non-negative, and the column sum satisfies:
Figure FDA0003409792730000013
(2) establishing a traffic area multi-intersection variable-period multi-direction space occupancy model with green light time constraint
Figure FDA0003409792730000014
The global balanced dynamic model of its space occupancy can be described as:
Figure FDA0003409792730000015
wherein the global space occupancy state vector is x ═ x1，...，xM]T∈RM，xi∈RNGlobal non-linear dynamicsThe vector is f ═ f1，...，fM]T∈RM，fi∈RNControlling the input green time to
Figure FDA0003409792730000016
Figure FDA0003409792730000017
ui∈RNM represents the number of urban regional intersections, and N represents the number of each direction of a single intersection;
the distributed consistency coordination error for defining the space occupancy rate of the ith direction of the mth intersection is as follows:
Figure FDA0003409792730000021
wherein the content of the first and second substances,
Figure FDA0003409792730000022
representing a connection matrix of a multi-agent system formed by a single cross port and multiple directions,
Figure FDA0003409792730000023
connection matrix representing multi-intersection constituting multi-agent system, bm，iThe connection coefficient between the space occupancy of the ith direction of the mth intersection and the mean value of the expected space occupancy is represented;
the distributed global consistency coordination error of the space occupancy of each direction of the single intersection is described as follows:
Figure FDA0003409792730000024
wherein e ═ e1，...，eN]T∈RN，
Figure FDA0003409792730000025
B＝diag(bm，i)∈RN×NRepresenting a diagonal matrix;
according to the distributed consistency coordination error, a consistency coordination control item v in the following form is selectedm，i(k)，
Figure FDA0003409792730000026
Or
Figure FDA0003409792730000027
Wherein c > 0 represents an error learning gain,
distributed green light time coordination control strategy for each direction of mth intersection
Figure FDA0003409792730000028
The design is as follows,
Figure FDA0003409792730000029
or
Figure FDA00034097927300000210
Where μ > 0 denotes the coordinated control gain, pm，i> 0, and the parameter learning rate is designed as follows:
Figure FDA00034097927300000211
or
Figure FDA0003409792730000031
Wherein, Fi＝ΠiIs greater than 0; κ > 0 represents the parameter learning gain;
the control and learning gains satisfy the following conditions:
Figure FDA0003409792730000032
Figure FDA0003409792730000033
Figure FDA0003409792730000034
wherein P ═ PT∈RN×N＞0，Q＝QT∈RN×N> 0 is a positive definite matrix;
wherein the global consistency coordination error vector e (k) e RNThe consistency converges to a bounded neighborhood near the zero value, and the neighborhood upper bound of the consistency coordination error is reduced by increasing the error learning gain c.
CN202010798063.1A 2020-08-10 2020-08-10 Regional traffic signal data driving control method based on multi-agent network Active CN112133086B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010798063.1A CN112133086B (en) 2020-08-10 2020-08-10 Regional traffic signal data driving control method based on multi-agent network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010798063.1A CN112133086B (en) 2020-08-10 2020-08-10 Regional traffic signal data driving control method based on multi-agent network

Publications (2)

Publication Number Publication Date
CN112133086A CN112133086A (en) 2020-12-25
CN112133086B true CN112133086B (en) 2022-01-18

Family

ID=73851759

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010798063.1A Active CN112133086B (en) 2020-08-10 2020-08-10 Regional traffic signal data driving control method based on multi-agent network

Country Status (1)

Country Link
CN (1) CN112133086B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112698634B (en) * 2020-12-28 2021-09-21 南京邮电大学 Event trigger-based traffic intelligent system fixed time dichotomy consistency method
CN113192318B (en) * 2021-01-29 2022-09-02 安徽科力信息产业有限责任公司 Data drive control regional traffic signal dynamic optimization method and system
CN113284354B (en) * 2021-06-18 2022-01-14 北京航空航天大学 Traffic elasticity regulation and control method and system based on reinforcement learning

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101281685A (en) * 2008-01-30 2008-10-08 吉林大学 Coordination control method for area mixed traffic self-adaption signal
CN102110371A (en) * 2011-03-04 2011-06-29 哈尔滨工业大学 Hierarchical multi-agent framework based traffic signal control system
CN105931474A (en) * 2016-02-29 2016-09-07 南京航空航天大学 City road intersection group local overflow control method with quantum decision

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7742845B2 (en) * 2002-07-22 2010-06-22 California Institute Of Technology Multi-agent autonomous system and method
TWI326859B (en) * 2007-03-30 2010-07-01 Ind Tech Res Inst System and method for intelligent traffic control using wireless sensor and actuator networks
CN101650877A (en) * 2009-08-31 2010-02-17 吉林大学 Method for setting crossing self-adapting changeable driveway
KR101601958B1 (en) * 2014-10-14 2016-03-09 공주대학교 산학협력단 Roundabout signal metering operation apparatus and method by considering approach lane's degree of saturation
CN108648446B (en) * 2018-04-24 2020-08-21 浙江工业大学 Road network traffic signal iterative learning control method based on MFD
CN109785619B (en) * 2019-01-21 2021-06-22 南京邮电大学 Regional traffic signal coordination optimization control system and control method thereof

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101281685A (en) * 2008-01-30 2008-10-08 吉林大学 Coordination control method for area mixed traffic self-adaption signal
CN102110371A (en) * 2011-03-04 2011-06-29 哈尔滨工业大学 Hierarchical multi-agent framework based traffic signal control system
CN105931474A (en) * 2016-02-29 2016-09-07 南京航空航天大学 City road intersection group local overflow control method with quantum decision

Also Published As

Publication number Publication date
CN112133086A (en) 2020-12-25

Similar Documents

Publication Publication Date Title
CN112133086B (en) Regional traffic signal data driving control method based on multi-agent network
CN110347155B (en) Intelligent vehicle automatic driving control method and system
Cong et al. Ant colony routing algorithm for freeway networks
CN104010863A (en) Method and module for controlling vehicle speed based on rules and/or costs
CN110111562A (en) A kind of urban transportation macro-regions boundary control method
Aslani et al. Continuous residual reinforcement learning for traffic signal control optimization
Nilsson et al. A micro-simulation study of the generalized proportional allocation traffic signal control
Wang et al. Optimal control design for connected cruise control with edge computing, caching, and control
CN112258856B (en) Method for establishing regional traffic signal data drive control model
Han et al. An extended linear quadratic model predictive control approach for multi-destination urban traffic networks
CN114937366A (en) Traffic flow calculation method based on multi-scale traffic demand and supply conversion
Chen et al. Duality between density function and value function with applications in constrained optimal control and markov decision process
CN110456790B (en) Intelligent networking electric automobile queue optimization control method based on adaptive weight
CN109886126B (en) Regional vehicle density estimation method based on dynamic sampling mechanism and RBF neural network
CN113870588B (en) Traffic light control method based on deep Q network, terminal and storage medium
Lu et al. Stability and fuel economy of nonlinear vehicle platoons: A distributed economic MPC approach
CN110011929B (en) Distributed predictive control method for improving network congestion phenomenon
Como et al. On the well-posedness of deterministic queuing networks with feedback control
Pettersson et al. Stability of hybrid systems using LMIs—a gear-box application
CN112258855A (en) Single-intersection multi-direction space occupancy balance control method
Como et al. On the well-posedness of dynamical flow networks with feedback-controlled outflows
Ying et al. Infrastructure-Assisted cooperative driving and intersection management in mixed traffic conditions
CN114137831B (en) Longitudinal control method and device in intelligent network automobile queue system
Ji et al. Data-driven adaptive cooperative control for urban traffic signal timing in multi-intersections
Chen et al. Heterogeneous Vehicle Platoon Control Based on Predictive Constant Time Headway Strategy

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