CN107591011A - Consider the intersection traffic signal adaptive control method of supply side constraint - Google Patents
Consider the intersection traffic signal adaptive control method of supply side constraint Download PDFInfo
- Publication number
- CN107591011A CN107591011A CN201711047657.3A CN201711047657A CN107591011A CN 107591011 A CN107591011 A CN 107591011A CN 201711047657 A CN201711047657 A CN 201711047657A CN 107591011 A CN107591011 A CN 107591011A
- Authority
- CN
- China
- Prior art keywords
- intersection
- traffic
- vehicles
- lane
- supply
- 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.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention belongs to intelligent transportation research field, is related to a kind of intersection traffic signal adaptive control method for considering supply side constraint.The problem of lacking the consideration to intersection exit road transportation supplies amount in existing signals control system and research is overcome, is comprised the following steps：1st, by the detection and processing to intersection traffic information, the transport need amount in crossing inlet road and the transportation supplies amount of exit ramp are obtained；2nd, the time-varying relation of intersection traffic supply and demand amount is established, builds intersection supply and demand matrix；3rd, based on intelligent planning, problem description, original state, dbjective state, behavior aggregate, the intersection signal signal timing optimization model of knowledge rule five-tuple description are established；4th, dbjective state is scanned for using the method for decision tree, generates corresponding timing scheme.Compared with prior art, the present invention realizes the active control of intersection, while can prevent intersection lower exit road is lined up to overflow, and avoids intersection " deadlock ".
Description
Technical Field
The invention relates to an intersection traffic signal control method in the field of intelligent traffic research, in particular to an intersection traffic signal self-adaptive control method considering supply side constraint.
Background
At present, serious traffic jam problems are generally encountered all over the country, signalized intersections serve as basic units for urban traffic control, and control strategies of the signalized intersections have great significance for solving the traffic jam problems, such as TRANSYT, SCATS, SCOOT, OPAC, RHODES and other signal control systems are applied, so that the traffic efficiency of a road network is effectively improved. However, these systems are all based on the assumption that the queuing capacity of the exit lane at the intersection is infinite, which is true in the unsaturated state of the intersection, and when the intersection is in the saturated or oversaturated state, the assumption will be invalid, so that the phenomenon that the vehicle stays inside the intersection often occurs, and in severe cases, the intersection is "dead locked" or local road network paralysis can be caused.
In recent years, in order to avoid deadlock of intersections and meet control of traffic flow full states, a large number of related researches are carried out at home and abroad, and the achievements mainly concentrate on: 1. the method avoids the situation that the intersection queues up to the upstream intersection through coordination of adjacent intersections, is characterized by passive control of the intersection, and is difficult to accurately control the intersection to queue up to the upstream intersection. 2. In the method, timing optimization is performed by taking the traffic efficiency (delay, traffic capacity and the like) of the intersection as a target, but the consideration of the queuing capacity of an exit lane is lacked, so that the control effect of the method in a saturated or supersaturated state of the intersection is difficult to verify.
In summary, existing control systems and research are based on the premise that vehicles at an intersection are completely released, and the consideration of supply amount at the downstream of the intersection is lacked, so that a traffic signal control method considering supply side constraint is urgently needed to be established.
Disclosure of Invention
The invention aims to overcome the problem that the existing signal control system and research lack of consideration on the traffic supply quantity of an intersection exit road, and provides an intersection traffic signal self-adaptive control method considering supply side constraint.
In order to realize the purpose, the following technical scheme is provided:
an intersection traffic signal adaptive control method considering supply side constraint comprises the following steps:
the method comprises the following steps: detecting and processing intersection traffic information;
step two: constructing a supply and demand matrix at the intersection;
step three: an intersection signal timing optimization model based on intelligent planning;
step four: and optimizing intersection signal timing based on the decision tree.
The intersection traffic information detection and processing in the first step comprises the following specific steps:
(1) Optimizing the layout of the detectors of the inlet channel and the outlet channel of the intersection;
determining control parameter expression, value, detection range and detector layout under constraint control by using knowledge of multi-sensor fusion, traffic control theory and traffic flow theory;
(2) Acquiring and analyzing video information of an inlet channel and an outlet channel of the intersection;
the queuing length of the vehicles at the entrance lane is the main basis for estimating the demand, the vehicles on the foreground lane are directly learned through a background model and foreground acquisition by utilizing a deep learning and image processing method to acquire the queuing length of the vehicles on the lane, and the queuing length of the vehicles is converted into the number of the vehicles and recorded as the number of the vehicles
The vacant space of the outlet channel is an estimation basis of the supply amount of the outlet channel, the video image processing and deep learning algorithm is still utilized, the space of the foreground not occupied by the vehicle is learned through the background model and the foreground acquisition, the vacant space length is acquired and converted into the number of the supply vehicles, and the number of the supply vehicles is recorded as
The construction of the supply and demand matrix of the intersection in the second step comprises the following specific steps:
(1) Predicting future delta t by using the arrival and release rule of traffic flow, probability theory and relevant knowledge of prediction theory 1 Number of vehicles expected to arrive at the intersection entrance lane iAnd number of vehicles expected to be released from exit lane j
(2) Combining the detection results of the supply and demand of the inlet and outlet roads, establishing a time-varying relational expression of the traffic supply and demand of the intersection, and acquiring the supply and demand:
will be Δ t in the future 1 The traffic demand of the intersection entrance lane i during the period is recorded as S i Then:
will be Δ t in the future 1 The traffic supply quantity of the exit lane j at the intersection during the period is recorded as D j Then:
(3) And (3) intersection supply and demand matrix description: if the number of traffic flow directions of the intersection entrance lane is M and the number of exit lanes is N, the traffic demand of each traffic flow of the intersection entrance lane is as follows: s. the 1 ,S 2 ,……,S M The traffic supply amount of each exit lane at the intersection is as follows: d 1 ,D 2 ,……D N (ii) a Therefore, the traffic demand and supply of each inlet and outlet road of the intersection respectively form a demand matrix S = [ S ] 1 ,S 2 ,……,S M ]And supply matrix D = [ D = 1 ,D 2 ,……D N ]。
The intersection signal timing optimization model based on intelligent planning in the third step comprises the following specific steps:
(1) Constructing a traffic flow intelligent planning model framework: the method comprises the steps of enabling a traffic flow signal control problem protocol to be a traffic flow uncertainty intelligent planning fast solving problem considering supply side constraint, and expressing an intelligent planning model of the traffic flow into a quintuple form (Q, I, G, A and R) by utilizing the traffic flow running characteristic, time constraint, road canalization organization and explicit and implicit related knowledge in the traffic control field of traffic flow phase and phase sequence grading, wherein Q represents problem description, I represents the initial state of the problem, G represents the target state of the problem, A represents an action set, and R represents a rule set;
(2) Taking the releasing efficiency of vehicles at the intersection and the fairness of traffic flow scheduling as solving targets, and establishing an intersection signal timing optimization model based on intelligent planning;
on the basis of considering the waiting time and queue length parameters of the traffic flow, a fair penalty function eta (t) of the traffic flow is constructed w Q, … …) where t is w Representing the waiting time, and Q representing the queuing length; the traffic flow intelligent planning model considering the supply side constraint is expressed as:
optimization target max φ:
s.t.
basic action set: act = < a1, a2, a3, … … >
a1= merging traffic flow phases of the entrance lane i and k;
a2= yellow lamp insertion time;
a3= switching to the next traffic flow;
basic rule set: r = < R1, R2, R3, … … >
r1= if the traffic flows of the entrance lane i and k are in a merged relationship, executing a1;
r2= if the traffic flow i is finished, executing a2;
r3= if the yellow light time is over, a3 is executed;
an initial state: the state of the intersection at the initial moment;
target state: the intersection state corresponding to the optimal timing scheme;
wherein:
c-optimization period;
λ i -the weight of the inlet lane i;
η i -in order to avoid that the traffic flow of the entrance lane i is not released for a plurality of times, constructing a fair penalty function of the traffic flow;
S i (C) -traffic demand at entrance lane i during cycle C;
Tr i ' (C) -vehicle transfer ratio of entry lane i during cycle C;
Tr' M×N reachable transition matrix, tr' ij Indicating a vehicle transfer ratio from the entrance lane i to the exit lane j;
d' -the traffic volume released by the inlet channel to the outlet channel;
Tr M×N -a transfer matrix, tr ij Indicating the proportion of vehicle transfer from the entrance lane i to the exit lane j;
Λ -logical and operation;
A M×N -a static reachable matrix between the entrance and exit of the intersection, reflecting the spatial OD direction of the traffic flow, a ij Indicating accessibility between the inlet i and outlet j lanes, a ij =0 denotes unreachable, a ij =1 means reachable;
AM M×N -dynamic reachable matrix between crossing entrances and exits, am ij Indicating reachability, am, between entry lane i and exit lane j ij Am if not reachable by 0 ij Am, =1 denotes reachable, am ij The change of the state of the system is realized by an action set and a rule set, reflects the actual running direction of a space OD of the traffic flow and is influenced by the conditions of road canalization organization, traffic control, traffic events, special police affairs, 0 demand and 0 supply;
g i the green time of the entrance lane i;
E i (t) — vehicle release rate of the entrance lane i;
the minimum green time and the maximum green time of the entrance lane i;
the constraint condition D' is less than or equal to D, so that the number of vehicles released by an inlet passage is limited, and queuing overflow of the outlet passage is avoided;reflecting the demand constraint and avoiding the occurrence of optimal value in the planning and solving processNegative or greater than 1;and realizing the constraint of the maximum green light time and the minimum green light time of the traffic flow i.
The decision tree-based intersection signal timing optimization in the fourth step comprises the following specific steps:
and optimizing the signal timing of the intersection by adopting a decision tree method according to the intersection signal timing optimization model established in the step three, wherein the method comprises the following specific steps of:
(1) Searching of target state:
dividing the optimization period into m periods of time Deltat 2 Interval of (2), referred to as stage; for each stage, the current state and decision variables of the intersection are used as input, and the state of the intersection comprises the traffic supply demand of an entrance road and an exit road of the intersection, the vehicle arrival and departure characteristics, the signal state and the like; outputting the running indexes and the traffic state of the intersection after the stage is finished; and the output of the previous stage is used as the input of the next stage;
wherein, the definition of decision variables in the nth stage is as follows:
when each stage starts, a decision is made according to the action set and the rule set, and the following state information of the intersection is updated:
(1) number of vehicles released at the nth stage entrance lane i:
wherein: s is i Represents the saturation flow rate of the flow in the inlet duct i in units of (pcu/Δ t) 2 )；
C i (n) is the number of vehicles arriving at the entrance lane i at the nth stage;
S i (n) the number of vehicles in line at the entrance lane i at the nth stage;
(2) the number of vehicles in queue on the entrance lane i in the (n + 1) th stage is as follows:
S i (n+1)＝S i (n)+C i (n)-R i (n) (7)
(3) the total number of vehicles on the exit way j at the n +1 stage is as follows:
Q j (n+1)＝Q j (n)+R(n)×A j -L j (n) (8)
wherein: r (n) is the number of vehicles transferred at each entrance lane in the nth stage;
A j is the reachable matrix between each inlet channel and the j outlet channel;
L j (n) is the number of vehicles driven away from the exit lane at the nth stage j;
(4) remaining queuing capacity on the n-th stage exit lane j:
D j (n)＝N j -Q j (n) (9)
wherein: n is a radical of j Represents the total queuing capacity of j exit lanes;
(5) optimization time of the n +1 stage:
T(0)＝0 (10)
wherein: gmin represents the minimum green time;
(6) green time of traffic flow at the n +1 th stage:
(7) signal state of stage n inlet lane i:
(8) node designation of stage n + 1:
p(0)＝1(13)
(9) the operation indexes of the n +1 stage are as follows:
delaying:
traffic capacity:
when the optimization time T of the nodes reaches the optimization period C, the nodes become termination nodes, F/C values corresponding to the termination nodes are compared, and intersection state information stored by the node with the maximum value is the target state of the intersection;
(2) Generating a timing scheme;
for each node generated in the searching process, unique position information exists, namely a node label corresponds to the node label; after the target state is obtained, reversely pushing back to the initial state according to the corresponding node label and the following formula to obtain an optimal decision sequence;
according to the definition of the decision variable DM, DM (n) =1 indicates that the next phase is switched to, DM (n) =0 indicates that the current phase is maintained, and after the optimal decision sequence is obtained, the corresponding timing scheme can be obtained.
Compared with the prior art, the beneficial effects of the invention are embodied in the following aspects:
1. the intersection traffic signal self-adaptive control method considering supply side constraint comprehensively considers the traffic demand of an entrance lane and the traffic supply of an exit lane of an intersection to carry out signal timing optimization, can prevent downstream exit lanes of the intersection from queuing and overflowing, and avoids deadlock of the intersection.
2. The intersection traffic signal self-adaptive control method considering supply side constraint overcomes the problem of passively adapting to traffic demand in the existing signal timing method, is represented as active control of an intersection, realizes global optimization of time and space resources of the intersection, and greatly improves the running efficiency of the intersection.
Drawings
FIG. 1 is a block flow diagram of an intersection traffic signal adaptive control method of the present invention that takes into account supply side constraints;
FIG. 2 is a schematic diagram of an intersection entrance and exit in an intersection traffic signal adaptive control method considering supply side constraints according to the invention;
FIG. 3 is a block diagram of the intersection signaling control concept of the present invention taking into account supply side constraints;
FIG. 4 is a supply and demand representation of an intersection in the intersection signal timing optimization model of the present invention taking into account supply side constraints;
FIG. 5 is a schematic diagram of input and output of a stage n in the decision tree-based intersection signal timing optimization algorithm of the present invention;
FIG. 6 is a channelized diagram of an intersection of a Xikang road and a Homing street when model verification is performed in the intersection traffic signal adaptive control method considering supply side constraints according to the present invention;
FIG. 7 is a signal phase sequence diagram of a Xikang road and a Liangjie street intersection during model verification in the intersection traffic signal adaptive control method considering supply side constraints according to the present invention;
FIG. 8 is a diagram of average vehicle delays before and after optimization during model verification in the supply and demand constrained intersection signal timing optimization method of the present invention;
fig. 9 is a cumulative number of vehicles passing through the intersection before and after optimization during model verification in the supply and demand constrained intersection signal timing optimization method.
Detailed Description
The invention is described in detail below with reference to the attached drawing figures:
referring to fig. 2 and 3, the concept of intersection signal control in consideration of supply-side constraints according to the present invention will be described. The description will be given by taking as an example the inlet channel i and its corresponding outlet channel j shown in fig. 2. The traffic arriving at the entrance lane i during the period t to t + Δ t is recorded as the demand S i (t + Δ t); the maximum amount of traffic that the exit lane j allows to divert to the entrance lane during the period t to t + Δ t is recorded as the supply amount D j (t + Δ t), the supply is limited by the remaining queuing capacity of the outlet lane. The control of the traffic flow at the entrance lane i is essentially given its allowable traffic volume to be released to the exit lane j, which is limited by the supply volume at the exit lane of the intersection.
Referring to the block diagram of the intersection signal control concept in consideration of supply side constraints shown in fig. 3, wherein:
f 1 -the proportion of the transfer of vehicles at the entry lane i during the period t to t + Δ t is related to the duration of green light at the entry lane i;
S′ i (t + Δ t) -the number of vehicles, S ', transferred downstream by the approach i during t to t + Δ t' i ＝S i *f 1 ；
D' j (t + Δ t) -the remaining queuing capacity of the exit lane j at time t + Δ t;
for entry lane i, given a green time, the transfer ratio for the corresponding vehicle is f 1 The number of vehicles transferred to the exit lane j is S' i (t + Δ t), then the remaining queuing capacity of the outlet channel j at time t + Δ t is D' j (t+Δt)，D' j The greater (t + Δ t) indicates the greater number of vehicles that can be released downstream. Thus D' j And (t + delta t) constitutes positive feedback of a signal control system, and closed-loop control of the intersection is realized. The maximum number of vehicles released downstream during green lights at the entrance lane i is limited by both the vehicles queued at the entrance lane and the remaining queuing capacity at the exit lane, max S' i (t+Δt)＝min(D j (t+Δt),S i (t + delta t)), therefore, the control method realizes active control of the intersection, can prevent vehicles at the downstream exit lane from queuing and overflowing, and avoids deadlock of the intersection.
The intersection traffic signal self-adaptive control method considering supply side constraint comprises the following specific steps:
1. intersection traffic information detection and processing
The arriving traffic volume of the entrance road and the residual queuing capacity of the exit road at the intersection, namely the supply and demand amount, are the information basis for traffic flow control. The method comprises the following specific steps:
(1) Optimized layout of intersection inlet and outlet channel detectors
Determining control parameter expression, value, detection range and detector layout under constraint control by using knowledge of multi-sensor fusion, traffic control theory and traffic flow theory;
(2) Intersection inlet and outlet channel video information acquisition and analysis
The queuing length of the vehicles at the entrance lane is the main basis for estimating the demand, the vehicles on the foreground lane are directly learned through a background model and foreground acquisition by using methods such as deep learning and image processing, the queuing length of the vehicles on the lane is acquired, the queuing length of the vehicles is converted into the number of the vehicles, and the number is recorded asThe vacant space of the outlet channel is an estimation basis of the supply amount of the outlet channel, the space of the foreground not occupied by the vehicle is learned through a background model and foreground acquisition by still utilizing video image processing, a deep learning algorithm and the like, the vacant space length is acquired and converted into the number of the supplied vehicles, and the number of the supplied vehicles is recorded as
2. Intersection supply and demand matrix construction
(1) Predicting future delta t by using the arrival and release rule of traffic flow, probability theory and relevant knowledge of prediction theory 1 Number of vehicles expected to arrive at the entryway i during the periodAnd number of vehicles expected to be released from exit lane j
(2) Combining the detection results of the supply and demand of the inlet and outlet roads, establishing a time-varying relational expression of the traffic supply and demand of the intersection, and acquiring the supply and demand:
will be Δ t in the future 1 The traffic demand of the intersection entrance lane i during the period is recorded as S i Then:
will be Δ t in the future 1 The traffic supply quantity of the exit lane j at the intersection during the period is recorded as D j Then:
(3) Referring to the supply and demand description for a conventional four-way intersection shown in FIG. 4 (numbered in a counter-clockwise direction); if the number of the traffic flow directions of the intersection entrance road is M and the number of the exit roads is N, the traffic demand of each traffic flow of the intersection entrance road is as follows: s 1 ,S 2 ,……,S M The traffic supply amount of each exit lane at the intersection is as follows: d 1 ,D 2 ,……D N (ii) a Therefore, the traffic demand and supply of each inlet and outlet road of the intersection respectively form a demand matrix S = [ S ] 1 ,S 2 ,……,S M ]And supply matrix D = [ D = 1 ,D 2 ,……D N ]。
3. Intersection signal timing optimization model based on intelligent planning
(1) The invention relates to a traffic flow intelligent planning model framework construction, which is characterized in that a traffic flow signal control problem protocol is used for solving a problem quickly for traffic flow uncertainty intelligent planning considering supply side constraint, and the traffic flow intelligent planning model is expressed into a quintuple form (Q, I, G, A and R) by utilizing explicit and implicit related knowledge in the traffic control field such as traffic flow operation characteristics, time constraint, road canalization organization, traffic flow phase sequence grading and the like, wherein Q represents problem description, I represents the initial state of a problem, G represents the target state of the problem, A represents an action set, and R represents a rule set.
(2) The method takes the releasing efficiency of vehicles at the intersection and the fairness of traffic flow scheduling as solving targets, and establishes an intersection signal timing optimization model based on intelligent planning. The efficiency ensures that the number of vehicles passing through the intersection in unit time is the largest. Because the switching of the phase position can cause time loss and influence the passing efficiency of the intersection, the traffic flow with less queued vehicles can not be released for multiple cycles on the premise of ensuring the vehicle releasing efficiency of the intersection. Therefore, the invention constructs a fair penalty function eta (t) of the traffic flow on the basis of considering the waiting time, the queuing length and other parameters of the traffic flow w Q, … …) where t is w Indicating latency and Q the queue length. Then the traffic flow intelligent planning model taking into account the supply side constraints can be expressed as:
optimization target max φ:
s.t.
basic action set: act = < a1, a2, a3, … … >
a1= merging traffic flow phases of the entrance lane i and k;
a2= yellow lamp insertion time;
a3= switching to the next traffic flow;
basic rule set: r = < R1, R2, R3, … … >
r1= if the traffic flows of the entrance lane i and k are in a merged relationship, executing a1;
r2= if the traffic flow i is finished, executing a2;
r3= if the yellow light time is over, a3 is executed;
initial state: the state of the intersection at the initial moment;
target state: and the intersection state corresponding to the optimal timing scheme.
Wherein:
c-optimization period;
λ i -the weight of the inlet lane i;
η i -in order to avoid that the traffic flow of the entrance lane i is not released many times, constructing a fair penalty function of the traffic flow;
S i (C) -traffic demand at entrance lane i during cycle C;
Tr i ' (C) -vehicle transfer ratio of entry lane i during cycle C;
Tr' M×N reachable transition matrix, tr' ij Indicating a vehicle transfer ratio from the entrance lane i to the exit lane j;
d' -the traffic volume released by the inlet channel to the outlet channel;
Tr M×N -transfer momentArray tr ij Indicating the proportion of vehicle transfer from the entrance lane i to the exit lane j;
Λ -logical and operation;
A M×N -a static reachable matrix between the entrance and exit of the intersection, reflecting the spatial OD direction of the traffic flow, a ij Indicating accessibility between the inlet i and outlet j lanes, a ij =0 denotes unreachable, a ij =1 means reachable;
AM M×N -dynamic reachable matrix between crossing entrances and exits, am ij Indicating reachability, am, between entry lane i and exit lane j ij Am if not reachable by 0 ij =1 means reachable, am ij The change of the state of the system is realized by an action set and a rule set, reflects the actual running direction of a space OD of the traffic flow and is influenced by the conditions of road canalization organization, traffic control, traffic events, special police affairs, 0 demand, 0 supply and the like;
g i the green time of the entrance lane i;
E i (t) — vehicle release rate of the entrance lane i;
the minimum green time and the maximum green time of the entrance lane i.
The constraint condition D' is less than or equal to D, so that the number of vehicles released by an inlet passage is limited, and queuing overflow of the outlet passage is avoided;reflecting the demand constraint and avoiding the occurrence of optimal value in the planning and solving processNegative or greater than 1;constraints on the maximum green time and the minimum green time of the entrance lane i are achieved.
4. Decision tree-based intersection signal timing optimization
The invention optimizes the signal timing of the intersection by adopting a decision tree method according to the intersection signal timing optimization model established in the step 3, and the method comprises the following specific steps:
(1) Searching for target states
See the phase n input-output diagram shown in fig. 5. The invention divides the optimization period into m time lengths delta t 2 Is used (herein referred to as a phase). For each stage, there are inputs (intersection status information, vehicle arrival, departure characteristics, and decision variables), outputs (operation index, status information of the intersection after the stage is finished), and the output of the previous stage is used as the input of the next stage.
Wherein, the definition of decision variables in the nth stage is as follows:
when each stage starts, making a decision according to the action set and the rule set, and updating the following state information of the intersection:
(1) number of vehicles released in the nth stage entrance lane i:
wherein: s i Represents the saturation flow rate of the flow i in units of (pcu/Δ t) 2 )；
C i (n) is the number of vehicles arriving at the entrance lane of the nth stage i;
S i (n) is the number of vehicles in line at the entrance lane at stage n.
(2) The number of vehicles in queue on the entrance lane i in the (n + 1) th stage is as follows:
S i (n+1)＝S i (n)+C i (n)-R i (n) (7)
(3) the total number of vehicles on the exit way j at the n +1 stage is as follows:
Q j (n+1)＝Q j (n)+R(n)×A j -L j (n) (8)
wherein: r (n) is the number of vehicles transferred by each entrance lane in the nth stage;
A j is the reachable matrix between each inlet channel and the j outlet channel;
L j and (n) is the number of vehicles driven away from the exit lane at the nth stage j.
(4) Remaining queuing capacity on stage n exit lane j:
D j (n)＝N j -Q j (n) (9)
wherein: n is a radical of j Representing the total queued capacity of j exit lanes.
(5) Optimization time of the n +1 stage:
T(0)＝0(10)
wherein: gmin represents the minimum green time.
(6) Green time of traffic flow at the n +1 th stage:
(7) signal state of the inlet lane i at stage n + 1:
(8) node designation of stage n + 1:
p(0)＝1 (13)
(9) the operation indexes of the n +1 stage are as follows:
delaying:
traffic capacity:
when the optimization time T of the nodes reaches the optimization period C, the nodes become termination nodes, the F/C values (the number of vehicles passing through the intersection in unit time) corresponding to the termination nodes are compared, and the intersection state information stored by the node with the maximum value is the target state of the intersection.
(3) Generating timing schemes
As can be seen from equation 13, for each node generated in the search process, there is unique location information, i.e., a node number corresponds to it. Therefore, after the target state is obtained, the method can reversely push back to the initial state according to the corresponding position information and the following formula, and obtain the optimal decision sequence.
According to the definition of the decision variable DM, DM (n) =1 indicates switching to the next phase, and DM (n) =0 indicates maintaining the current phase, and after the optimal decision sequence is obtained, the corresponding timing scheme can be obtained.
Examples
In order to verify the effectiveness of the invention, the experiment is completed by specially carrying out field investigation on the west Kang Lu of Changchun city and the intersection of the same street.
Referring to fig. 6 and 7, a crossing channelized graph and a crossing phase sequence graph are respectively shown. The current signal period of the intersection is 96s, wherein the phase 1 is green light time 51s, yellow light time 3s and red light time 42s; phase 2 green light time 33s, yellow light time 3s, red light time 60s. Survey time was 7 days earlier on weekdays: 30-7:50. and (4) surveying to obtain the state of the intersection at the initial moment, the arrival rule of vehicles at an entrance lane and the departure rule of vehicles at an exit lane at the intersection in the optimization period, the saturation release rate of the vehicles during the green light period and the queuing capacity of the exit lane. During the investigation time, the vehicles in line during the red light on the exit lane 4 often overflow and go up to the entrance lane 5, which seriously affects the traffic on the entrance lane 8.
In order to simplify the solving process, the running conditions of the vehicles at the intersection are simplified as follows: the flow of right-turn vehicles of the west Kang Lu is very small and is ignored; in addition, the vehicles are less queued during the red light period of the north exit lane and the west Kang Lu exit lane of the street, so that the right-turn traffic flow of the street and the left-turn traffic flow of the west Kang Lu are counted according to the straight-going mode. Through simplification, the intersection becomes a two-phase intersection which only allows straight running.
According to the state information of the intersection at the initial moment, the arrival rule of the vehicles at the entrance lane, the release rule of the vehicles at the exit lane and other data obtained by investigation, the running condition of the vehicles at the intersection in the future for 20min is simulated, and the following assumptions are made in the simulation process:
(1) Fixing the phase sequence of the intersection, and performing timing optimization according to the existing phase sequence condition of the intersection;
(2) Adjusting the phase green time by taking 3s as a small step pitch;
(3) The lost time when the green light is turned on is not considered, and after the green light is turned on, the queued vehicles are released at the saturated flow rate;
(4) After the yellow phase, the full red phase is not considered for insertion;
(5) The yellow light time is 3s, the vehicle cannot pass through the intersection during the specified yellow light period, and the yellow light phase must be inserted after the green light phase is finished;
(6) The minimum green time is 6s, the maximum green time is 60s, and the optimization period is 96s;
and (5) searching the target state by adopting c language programming according to the method for updating the intersection state information in the step (4), and generating a corresponding timing scheme according to the method in the step (5). The simulation results were analyzed from 3 aspects as follows:
(1) Queuing overflow condition at intersection
The remaining queuing capacity of the outlet channel 4 before and after optimization was counted at 1min intervals, and the results are shown in the table below. Wherein, the negative number represents that the outlet channel queue has overflowed, and the corresponding numerical value is the number of overflowed vehicles; 0 indicates that the exit track queue is full at this time.
TABLE 1 optimization of front and rear Outlet 4 remaining queuing Capacity
| Time interval | Before optimization (pcu) | After optimization (pcu) | Time interval | Before optimization (pcu) | After optimization (pcu) |
| 1 | -4 | 2 | 11 | 13 | 4 |
| 2 | -4 | 2 | 12 | -4 | 1 |
| 3 | 13 | 0 | 13 | -4 | 1 |
| 4 | -4 | 0 | 14 | -4 | 1 |
| 5 | -4 | 0 | 15 | -1 | 4 |
| 6 | -4 | 0 | 16 | -3 | 2 |
| 7 | -1 | 1 | 17 | -4 | 2 |
| 8 | -3 | 1 | 18 | -4 | 2 |
| 9 | -4 | 1 | 19 | 13 | 2 |
| 10 | -4 | 1 | 20 | -4 | 2 |
As can be seen from table 1, the optimized front exit lane 4 is often in an overflow state and blocks the intersection (4 vehicles can be accommodated inside the intersection, and when the remaining capacity is-4, the intersection will be blocked); after optimization, the outlet channel cannot be queued and overflowed, and intersection deadlock is avoided.
(2) Average delay of vehicles at intersection
Referring to fig. 8, the average delay of vehicles at the intersections before and after optimization is counted at intervals of 1 min. As can be seen from FIG. 8, the average delay of the vehicle in the optimized solution is much smaller than that before the optimization. During the 20min of the simulation, the mean delay of the planned vehicle before optimization was 51.5s, and the mean delay of the planned vehicle after optimization was 38.2s, which was reduced by 13.3s.
(3) Traffic capacity of intersection
Referring to fig. 9, the cumulative number of vehicles passing through the intersection before and after optimization is counted at 1min intervals. As can be seen from fig. 9, the cumulative number of vehicles passing through the intersection after optimization is always equal to or greater than that before optimization. However, due to the small flow of the west Kang Luche, once the vehicles on the exit lane 4 begin to dissipate, the vehicles arriving at the west Kang Lu can pass through the intersection, so the total number of vehicles passing through the intersection within 20min before and after optimization is equivalent. However, in the optimized scheme, the queuing vehicles at the exit lane 4 cannot overflow, the vehicles at the entrance lane 8 can smoothly pass through the intersection during the green light period, the utilization rate of the green light time of the intersection is greatly improved, and the average delay of the vehicles is far less than that before optimization.
In conclusion, the intersection traffic signal self-adaptive control method considering the supply side constraint, which is established by the invention, comprehensively considers the traffic demand of the entrance lane and the traffic supply of the exit lane of the intersection and carries out signal timing optimization. On one hand, the downstream outlet channel of the intersection can be prevented from queuing and overflowing, and the intersection is prevented from being deadlocked; on the other hand, the global optimization of the time-space resources of the intersection is realized, and the running efficiency of the intersection is greatly improved. Therefore, the invention has better application prospect.
Claims (5)
1. An intersection traffic signal adaptive control method considering supply side constraint is characterized by comprising the following steps:
the method comprises the following steps: detecting and processing intersection traffic information;
step two: constructing a supply and demand matrix at the intersection;
step three: an intersection signal timing optimization model based on intelligent planning;
step four: and optimizing intersection signal timing based on the decision tree.
2. The intersection traffic signal adaptive control method considering supply-side constraints as claimed in claim 1, characterized in that:
the intersection traffic information detection and processing in the first step comprises the following specific steps:
(1) Optimizing the layout of the detectors of the inlet channel and the outlet channel of the intersection;
determining control parameter expression, value, detection range and detector layout methods under constraint control by using knowledge of multi-sensor fusion, traffic control theory and traffic flow theory;
(2) Acquiring and analyzing video information of an inlet channel and an outlet channel of the intersection;
the queuing length of the vehicles at the entrance lane is the main basis for estimating the demand, the vehicles on the foreground lane are directly learned through a background model and foreground acquisition by utilizing a deep learning and image processing method to acquire the queuing length of the vehicles on the lane, and the queuing length of the vehicles is converted into the number of the vehicles and recorded as the number of the vehicles
The vacant space of the outlet channel is an estimation basis of the supply amount of the outlet channel, the video image processing and deep learning algorithm is still utilized, the space of the foreground not occupied by the vehicle is learned through the background model and the foreground acquisition, the vacant space length is acquired and converted into the number of the supply vehicles, and the number of the supply vehicles is recorded as
3. The intersection traffic signal adaptive control method considering supply-side constraints as claimed in claim 1, characterized in that:
the construction of the supply and demand matrix of the intersection in the second step comprises the following specific steps:
(1) Predicting future delta t by using the arrival and release rule of traffic flow, probability theory and relevant knowledge of prediction theory 1 Number of vehicles expected to arrive at the intersection entrance lane iAnd number of vehicles expected to be released from exit lane j
(2) Combining the detection results of the supply and demand of the inlet and outlet roads, establishing a time-varying relational expression of the traffic supply and demand of the intersection, and acquiring the supply and demand:
will be Δ t in the future 1 The traffic demand of the intersection entrance lane i during the period is recorded as S i Then:
will be Δ t in the future 1 The traffic supply quantity of the exit lane j of the intersection during the period is recorded as D j Then:
(3) And (3) intersection supply and demand matrix description: if the number of traffic flow directions of the intersection entrance lane is M and the number of exit lanes is N, the traffic demand of each traffic flow of the intersection entrance lane is as follows: s 1 ,S 2 ,……,S M The traffic supply amount of each exit lane at the intersection is as follows: d 1 ,D 2 ,……D N (ii) a Therefore, the traffic demand and supply of each inlet and outlet road of the intersection respectively form a demand matrix S = [ S ] 1 ,S 2 ,……,S M ]And supply matrix D = [ D = 1 ,D 2 ,……D N ]。
4. The intersection traffic signal adaptive control method considering supply-side constraints as claimed in claim 1, characterized in that:
the intersection signal timing optimization model based on intelligent planning in the third step comprises the following specific steps:
(1) Constructing a traffic flow intelligent planning model framework: the method comprises the steps of enabling a traffic flow signal control problem protocol to be a traffic flow uncertainty intelligent planning fast solving problem considering supply side constraint, and expressing an intelligent planning model of the traffic flow into a quintuple form (Q, I, G, A and R) by utilizing the traffic flow running characteristic, time constraint, road canalization organization and explicit and implicit related knowledge in the traffic control field of traffic flow phase and phase sequence grading, wherein Q represents problem description, I represents the initial state of the problem, G represents the target state of the problem, A represents an action set, and R represents a rule set;
(2) Establishing an intersection signal timing optimization model based on intelligent planning by taking the release efficiency of vehicles at an intersection and the fairness of traffic flow scheduling as solving targets;
on the basis of considering the waiting time and queue length parameters of the traffic flow, a fair penalty function eta (t) of the traffic flow is constructed w Q, … …) where t is w Representing the waiting time, and Q representing the queuing length; the traffic flow intelligent planning model considering the supply side constraint is expressed as:
optimization target max φ:
s.t.
wherein:
c-optimization period;
λ i -the weight of the inlet lane i;
η i -in order to avoid that the traffic flow of the entrance lane i is not released many times, constructing a fair penalty function of the traffic flow;
S i (C) -traffic demand at entrance lane i during cycle C;
Tr i ' (C) -vehicle transfer ratio for Inlet lane i during cycle C;
Tr' M×N reachable transition matrix, tr' ij Indicating the proportion of vehicle transfer from the entrance lane i to the exit lane j;
d' -the traffic volume released by the inlet channel to the outlet channel;
Tr M×N -a transfer matrix, tr ij Indicating the proportion of vehicle transfer from the entrance lane i to the exit lane j;
Λ -logical and operation;
A M×N -a static reachable matrix between the entrance and exit of the intersection, reflecting the spatial OD direction of the traffic flow, a ij Indicating accessibility between the inlet i and outlet j lanes, a ij =0 denotes unreachable, a ij =1 means reachable;
AM M×N -dynamic reachable matrix between crossing entrances and exits, am ij Indicating reachability, am, between entry lane i and exit lane j ij Am if not reachable by 0 ij Am, =1 denotes reachable, am ij The change of the state of the system is realized by an action set and a rule set, reflects the actual running direction of a space OD of the traffic flow and is influenced by the conditions of road canalization organization, traffic control, traffic events, special police affairs, 0 demand and 0 supply;
g i the green time of the entrance lane i;
E i (t) — vehicle release rate of the entrance lane i;
-the minimum green time and the maximum green time of the entrance lane i;
the constraint condition D' is less than or equal to D, so that the number of vehicles released by the inlet channel is limited, and the outlet channel is prevented from queuing and overflowing;reaction needConstraint solving, and avoiding the occurrence of optimal value in the planning solving processNegative or greater than 1;and realizing the constraint of the maximum green light time and the minimum green light time of the traffic flow i.
5. The intersection traffic signal adaptive control method considering supply-side constraints as claimed in claim 1, characterized in that:
the decision tree-based intersection signal timing optimization in the fourth step comprises the following specific steps:
and optimizing the signal timing of the intersection by adopting a decision tree method according to the intersection signal timing optimization model established in the step three, wherein the method comprises the following specific steps of:
(1) Searching of target state:
dividing the optimization period into m periods of time Deltat 2 Interval of (2), referred to as stage; for each stage, the current state and decision variables of the intersection are used as input, and the state of the intersection comprises the traffic supply demand of an entrance road and an exit road of the intersection, the vehicle arrival and departure characteristics, the signal state and the like; outputting the running indexes and the traffic state of the intersection after the stage is finished; and the output of the previous stage is used as the input of the next stage;
wherein, the definition of the decision variable in the nth stage is as follows:
when each stage starts, making a decision according to the action set and the rule set, and updating the following state information of the intersection:
(1) number of vehicles released in the nth stage entrance lane i:
wherein: s i Represents the saturation flow rate of the flow in the inlet duct i in units of (pcu/Δ t) 2 )；
C i (n) is the number of vehicles arriving at the entrance lane i at the nth stage;
S i (n) the number of vehicles in line at the entrance lane i at the nth stage;
(2) the number of vehicles in queue on the entrance lane i in the (n + 1) th stage is as follows:
S i (n+1)＝S i (n)+C i (n)-R i (n) (7)
(3) the total number of vehicles on the exit way j at the n +1 stage is as follows:
Q j (n+1)＝Q j (n)+R(n)×A j -L j (n) (8)
wherein: r (n) is the number of vehicles transferred by each entrance lane in the nth stage;
A j is the reachable matrix between each inlet channel and the j outlet channel;
L j (n) is the number of vehicles driven away from the exit lane at the nth stage j;
(4) remaining queuing capacity on stage n exit lane j:
D j (n)＝N j -Q j (n) (9)
wherein: n is a radical of j Represents the total queued capacity of j exit lanes;
(5) optimization time of the n +1 stage:
T(0)＝0 (10)
wherein: gmin represents the minimum green time;
(6) green time of traffic flow at the n +1 th stage:
(7) signal state of stage n inlet lane i:
(8) node designation of stage n + 1:
p(0)＝1 (13)
(9) the operation indexes of the n +1 stage are as follows:
delaying:
traffic capacity:
when the optimization time T of the nodes reaches the optimization period C, the nodes become termination nodes, F/C values corresponding to the termination nodes are compared, and intersection state information stored by the node with the maximum value is the target state of the intersection;
(2) Generating a timing scheme:
for each node generated in the searching process, unique position information exists, namely a node label corresponds to the node label; after the target state is obtained, reversely pushing back to the initial state according to the corresponding node label and the following formula to obtain an optimal decision sequence;
according to the definition of the decision variable DM, DM (n) =1 indicates switching to the next phase, and DM (n) =0 indicates maintaining the current phase, and after the optimal decision sequence is obtained, the corresponding timing scheme can be obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711047657.3A CN107591011B (en) | 2017-10-31 | 2017-10-31 | Intersection traffic signal self-adaptive control method considering supply side constraint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711047657.3A CN107591011B (en) | 2017-10-31 | 2017-10-31 | Intersection traffic signal self-adaptive control method considering supply side constraint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107591011A true CN107591011A (en) | 2018-01-16 |
| CN107591011B CN107591011B (en) | 2020-09-22 |
Family
ID=61045619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711047657.3A Active CN107591011B (en) | 2017-10-31 | 2017-10-31 | Intersection traffic signal self-adaptive control method considering supply side constraint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107591011B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710979A (en) * | 2018-03-31 | 2018-10-26 | 西安电子科技大学 | A kind of Internet of Things yard craft dispatching method based on decision tree |
| CN109003444A (en) * | 2018-07-02 | 2018-12-14 | 北方工业大学 | Urban intersection overflow control method based on wide area radar microwave detector |
| CN109935079A (en) * | 2019-03-19 | 2019-06-25 | 吉林大学 | Intersection supply and demand cooperates with optimal control method |
| CN110363997A (en) * | 2019-07-05 | 2019-10-22 | 西南交通大学 | One kind having construction area intersection signal timing designing method |
| CN110379180A (en) * | 2019-07-05 | 2019-10-25 | 平安国际智慧城市科技股份有限公司 | A kind of traffic signal control method, traffic-control unit and terminal device |
| CN110491145A (en) * | 2018-10-29 | 2019-11-22 | 魏天舒 | A kind of traffic signal optimization control method and device |
| CN111882878A (en) * | 2020-09-02 | 2020-11-03 | 烟台大学 | Method for maximizing traffic capacity of key roads based on traffic flow prediction |
| CN112037508A (en) * | 2020-08-13 | 2020-12-04 | 山东理工大学 | Intersection signal timing optimization method based on dynamic saturation flow rate |
| CN112258856A (en) * | 2020-08-10 | 2021-01-22 | 北方工业大学 | Method for establishing regional traffic signal data drive control model |
| CN113470390A (en) * | 2021-07-09 | 2021-10-01 | 公安部交通管理科学研究所 | Multiphase dynamic coordination control method for short-link intersection edge node fusion |
| CN114519931A (en) * | 2020-11-17 | 2022-05-20 | 郑州宇通客车股份有限公司 | Method and device for predicting behavior of target vehicle in intersection environment |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005071292A (en) * | 2003-08-28 | 2005-03-17 | Omron Corp | Signal control unit |
| CN101025862A (en) * | 2007-02-12 | 2007-08-29 | 吉林大学 | Video based mixed traffic flow parameter detecting method |
| US20070208492A1 (en) * | 2006-03-03 | 2007-09-06 | Inrix, Inc. | Dynamic time series prediction of future traffic conditions |
| JP2008059615A (en) * | 2007-11-21 | 2008-03-13 | Omron Corp | Traffic signal controller |
| JP2009003699A (en) * | 2007-06-21 | 2009-01-08 | Kyosan Electric Mfg Co Ltd | Traffic signal control device and traffic signal control method |
| CN102411847A (en) * | 2011-08-02 | 2012-04-11 | 清华大学 | Traffic signal optimization method |
| CN102855759A (en) * | 2012-07-05 | 2013-01-02 | 中国科学院遥感应用研究所 | Automatic collecting method of high-resolution satellite remote sensing traffic flow information |
| CN103021192A (en) * | 2012-12-27 | 2013-04-03 | 南京洛普股份有限公司 | Self-adaptive traffic intersection signal light control method capable of realizing whole-course countdown and no time hopping |
| CN103208197A (en) * | 2013-04-23 | 2013-07-17 | 成都希盟科技有限公司 | Traffic signal timing method |
| CN103927890A (en) * | 2014-04-29 | 2014-07-16 | 北京建筑大学 | Artery coordination signal control method based on dynamic O-D matrix estimation |
| CN104021682A (en) * | 2014-05-06 | 2014-09-03 | 东南大学 | Oversaturated intersection self-repairing control method |
| CN104123848A (en) * | 2014-07-14 | 2014-10-29 | 昆明理工大学 | Single intersection oversaturation signal timing method in consideration of widening segment length |
| CN104966402A (en) * | 2015-06-05 | 2015-10-07 | 吉林大学 | Supersaturated traffic flow intersection queue overflow prevention and control method |
| CN106128103A (en) * | 2016-07-26 | 2016-11-16 | 北京市市政工程设计研究总院有限公司 | A kind of intersection Turning movement distribution method based on recursion control step by step and device |
| CN106251655A (en) * | 2016-09-30 | 2016-12-21 | 哈尔滨工业大学 | A kind of intersection signal control method based on outlet residual capacity constraint |
| CN106530763A (en) * | 2016-12-28 | 2017-03-22 | 东南大学 | Supersaturation traffic adaptive signal control method with coupling of inlet flow and outlet flow |
| CN106650913A (en) * | 2016-12-31 | 2017-05-10 | 中国科学技术大学 | Deep convolution neural network-based traffic flow density estimation method |
| CN106652480A (en) * | 2016-12-28 | 2017-05-10 | 山东理工大学 | Intersection maximum queuing length calculation method based on microwave and terrestrial magnetism data |
-
2017
- 2017-10-31 CN CN201711047657.3A patent/CN107591011B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005071292A (en) * | 2003-08-28 | 2005-03-17 | Omron Corp | Signal control unit |
| US20070208492A1 (en) * | 2006-03-03 | 2007-09-06 | Inrix, Inc. | Dynamic time series prediction of future traffic conditions |
| CN101025862A (en) * | 2007-02-12 | 2007-08-29 | 吉林大学 | Video based mixed traffic flow parameter detecting method |
| JP2009003699A (en) * | 2007-06-21 | 2009-01-08 | Kyosan Electric Mfg Co Ltd | Traffic signal control device and traffic signal control method |
| JP2008059615A (en) * | 2007-11-21 | 2008-03-13 | Omron Corp | Traffic signal controller |
| CN102411847A (en) * | 2011-08-02 | 2012-04-11 | 清华大学 | Traffic signal optimization method |
| CN102855759A (en) * | 2012-07-05 | 2013-01-02 | 中国科学院遥感应用研究所 | Automatic collecting method of high-resolution satellite remote sensing traffic flow information |
| CN103021192A (en) * | 2012-12-27 | 2013-04-03 | 南京洛普股份有限公司 | Self-adaptive traffic intersection signal light control method capable of realizing whole-course countdown and no time hopping |
| CN103208197A (en) * | 2013-04-23 | 2013-07-17 | 成都希盟科技有限公司 | Traffic signal timing method |
| CN103927890A (en) * | 2014-04-29 | 2014-07-16 | 北京建筑大学 | Artery coordination signal control method based on dynamic O-D matrix estimation |
| CN104021682A (en) * | 2014-05-06 | 2014-09-03 | 东南大学 | Oversaturated intersection self-repairing control method |
| CN104123848A (en) * | 2014-07-14 | 2014-10-29 | 昆明理工大学 | Single intersection oversaturation signal timing method in consideration of widening segment length |
| CN104966402A (en) * | 2015-06-05 | 2015-10-07 | 吉林大学 | Supersaturated traffic flow intersection queue overflow prevention and control method |
| CN106128103A (en) * | 2016-07-26 | 2016-11-16 | 北京市市政工程设计研究总院有限公司 | A kind of intersection Turning movement distribution method based on recursion control step by step and device |
| CN106251655A (en) * | 2016-09-30 | 2016-12-21 | 哈尔滨工业大学 | A kind of intersection signal control method based on outlet residual capacity constraint |
| CN106530763A (en) * | 2016-12-28 | 2017-03-22 | 东南大学 | Supersaturation traffic adaptive signal control method with coupling of inlet flow and outlet flow |
| CN106652480A (en) * | 2016-12-28 | 2017-05-10 | 山东理工大学 | Intersection maximum queuing length calculation method based on microwave and terrestrial magnetism data |
| CN106650913A (en) * | 2016-12-31 | 2017-05-10 | 中国科学技术大学 | Deep convolution neural network-based traffic flow density estimation method |
Non-Patent Citations (4)
| Title |
|---|
| BIAO YIN: "Forward search algorithm based on dynamic programming for real-time adaptive traffic signal control", 《IET INTELLIGENT TRANSPORT SYSTEMS》 * |
| 李海涛: "预防"死锁"的最大绿灯时间计算方法", 《交通科技》 * |
| 李萌萌: "预防交叉口排队溢出的交通信号控制方法研究", 《中国优秀硕士学位论文工程科技Ⅱ辑》 * |
| 郭海锋: "窗口流量控制的干线动态协调控制方法", 《智能交通控制理论与应用》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710979B (en) * | 2018-03-31 | 2022-02-18 | 西安电子科技大学 | Internet of things port ship scheduling method based on decision tree |
| CN108710979A (en) * | 2018-03-31 | 2018-10-26 | 西安电子科技大学 | A kind of Internet of Things yard craft dispatching method based on decision tree |
| CN109003444A (en) * | 2018-07-02 | 2018-12-14 | 北方工业大学 | Urban intersection overflow control method based on wide area radar microwave detector |
| CN109003444B (en) * | 2018-07-02 | 2020-09-18 | 北方工业大学 | Urban intersection overflow control method based on wide area radar microwave detector |
| CN110491145A (en) * | 2018-10-29 | 2019-11-22 | 魏天舒 | A kind of traffic signal optimization control method and device |
| CN109935079A (en) * | 2019-03-19 | 2019-06-25 | 吉林大学 | Intersection supply and demand cooperates with optimal control method |
| CN110379180B (en) * | 2019-07-05 | 2021-08-13 | 平安国际智慧城市科技股份有限公司 | Traffic signal control method, traffic signal control device and terminal equipment |
| CN110363997A (en) * | 2019-07-05 | 2019-10-22 | 西南交通大学 | One kind having construction area intersection signal timing designing method |
| CN110379180A (en) * | 2019-07-05 | 2019-10-25 | 平安国际智慧城市科技股份有限公司 | A kind of traffic signal control method, traffic-control unit and terminal device |
| CN112258856A (en) * | 2020-08-10 | 2021-01-22 | 北方工业大学 | Method for establishing regional traffic signal data drive control model |
| CN112037508A (en) * | 2020-08-13 | 2020-12-04 | 山东理工大学 | Intersection signal timing optimization method based on dynamic saturation flow rate |
| CN112037508B (en) * | 2020-08-13 | 2022-06-17 | 山东理工大学 | Intersection signal timing optimization method based on dynamic saturation flow rate |
| CN111882878B (en) * | 2020-09-02 | 2021-07-02 | 烟台大学 | Method for maximizing traffic capacity of key roads based on traffic flow prediction |
| CN111882878A (en) * | 2020-09-02 | 2020-11-03 | 烟台大学 | Method for maximizing traffic capacity of key roads based on traffic flow prediction |
| CN114519931A (en) * | 2020-11-17 | 2022-05-20 | 郑州宇通客车股份有限公司 | Method and device for predicting behavior of target vehicle in intersection environment |
| CN113470390A (en) * | 2021-07-09 | 2021-10-01 | 公安部交通管理科学研究所 | Multiphase dynamic coordination control method for short-link intersection edge node fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107591011B (en) | 2020-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107591011B (en) | Intersection traffic signal self-adaptive control method considering supply side constraint | |
| Chen et al. | An improved adaptive signal control method for isolated signalized intersection based on dynamic programming | |
| Jayakrishnan et al. | An evaluation tool for advanced traffic information and management systems in urban networks | |
| Ma et al. | Trajectory planning for connected and automated vehicles at isolated signalized intersections under mixed traffic environment | |
| CN109785619B (en) | Regional traffic signal coordination optimization control system and control method thereof | |
| Yao et al. | A dynamic predictive traffic signal control framework in a cross-sectional vehicle infrastructure integration environment | |
| Babicheva | The use of queuing theory at research and optimization of traffic on the signal-controlled road intersections | |
| CN104464310B (en) | Urban area multi-intersection signal works in coordination with optimal control method and system | |
| CN103996289B (en) | A kind of flow-speeds match model and Travel Time Estimation Method and system | |
| Li et al. | Traffic signal timing optimization in connected vehicles environment | |
| CN109949604A (en) | A kind of large parking lot scheduling air navigation aid, system and application method | |
| Ma et al. | Multi-stage stochastic program to optimize signal timings under coordinated adaptive control | |
| CN114241751B (en) | Multi-entrance dynamic and static traffic coordination optimization method for large parking lot | |
| Geng et al. | Multi-intersection traffic light control with blocking | |
| Kamran et al. | Traffic light signal timing using simulation | |
| Wang et al. | TLB-VTL: 3-level buffer based virtual traffic light scheme for intelligent collaborative intersections | |
| CN116524715A (en) | Rolling double-layer planning method combining trunk line green wave coordination and emergency path decision | |
| Solovyev et al. | Optimal Synthesis Method for Signalized Intersection of Urban Highways with Route Branching | |
| Ishak et al. | Improvement and evaluation of cell-transmission model for operational analysis of traffic networks: Freeway case study | |
| Soh et al. | Modeling of a multilane-multiple intersection based on queue theory and standard approach techniques | |
| Lin et al. | Study on fast model predictive controllers for large urban traffic networks | |
| Igbinosun et al. | Traffic flow model at fixed control signals with discrete service time distribution | |
| Obsu et al. | Modelling pedestrians’ impact on the performance of a roundabout | |
| Song et al. | Catching up with traffic lights for data delivery in vehicular ad hoc networks | |
| Sutarto et al. | Developing a stochastic model of queue length at a signalized intersection |
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 |