CN109448402A - Ramp metering rate method and device - Google Patents
Ramp metering rate method and device Download PDFInfo
- Publication number
- CN109448402A CN109448402A CN201811583233.3A CN201811583233A CN109448402A CN 109448402 A CN109448402 A CN 109448402A CN 201811583233 A CN201811583233 A CN 201811583233A CN 109448402 A CN109448402 A CN 109448402A
- Authority
- CN
- China
- Prior art keywords
- traffic
- metering rate
- ramp metering
- traffic flow
- ramp
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/075—Ramp control
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the present application provides a kind of ramp metering rate method and device, the traffic flow data detected by obtaining each Traffic flow detecting device, and traffic flow data is analyzed according to preset ramp metering rate slip condition database, divide main stem traffic flow modes and ring road traffic flow modes, then using the ramp metering rate strategy under ramp metering rate strategy prediction matrix selection main stem traffic flow modes trained in advance and ring road traffic flow modes, finally corresponding ramp metering rate is generated according to target ramp metering amount to instruct, and ramp metering rate instruction is sent to control signal lamp so that control signal lamp is controlled according to the corresponding signal of ramp metering rate instruction execution.Thus, by ramp metering rate strategy prediction matrix objective analysis can be carried out to the different ramp metering rate effects under Different Traffic Flows state, so that it is determined that with the ramp metering rate strategy of optimal control results under Different Traffic Flows state, the effect and reasonability of ramp metering rate are effectively improved, the transit time in ramp segment is reduced.
Description
Technical field
This application involves technical field of traffic control, in particular to a kind of ramp metering rate method and device.
Background technique
Currently, urban traffic blocking can be divided into two classes: one kind is normal hair property traffic congestion from the origin cause of formation of congestion,
I.e. in peak period festivals or holidays on and off duty, uprushed by flow and can not evacuate in time and the traffic bottle that is formed in road or intersection
Neck;Another kind of is sporadic traffic congestion, i.e., causes road traffic capacity to reduce or due to large-scale activity by road emergency event
Etc. events attract the volume of traffic excessively caused by traffic gather around training.For the traffic congestion that different reasons are formed, need using different
Leading method.It is to restore or improve road and intersection from the angle of road supply and flow control that urban traffic blocking, which is dredged,
The traffic capacity, or by management means influence traveler decision, dredge purpose to reach.
In the active field of traffic control of highway, one of the main means that ramp metering rate is used as, with highway master
The traffic flow on drawing lines road be it is preferential, to being adjusted and controlling into vehicle, to ensure main line the coast is clear, reduce vehicle travel
Time, alleviate the conflict of merging part, to realize the steady of highway main line road traffic flow.However, being studied through inventor
Lack it was found that being imported in mouth congestion dispersal ramp metering rate strategy for ring road at present to ring road controls different under Different Traffic Flows state
The objective analysis of effect processed lacks the digging of information between different ramp metering values and its control effect under Different Traffic Flows state
Pick causes the determination process of ramp metering value to lack theoretical property.
Summary of the invention
In order to overcome above-mentioned deficiency in the prior art, the application's is designed to provide a kind of ramp metering rate method and dress
It sets, to solve or improve the above problem.
To achieve the goals above, the embodiment of the present application the technical solution adopted is as follows:
In a first aspect, the embodiment of the present application provides a kind of ramp metering rate method, it is applied to server, the server and public affairs
Road ring road imports the control that each Traffic flow detecting device and highway ramp remittance node are arranged on section and ramp metering rate section
Signal lamp communication connection, which comprises
Obtain the traffic flow data that each Traffic flow detecting device detects;
The traffic flow data is analyzed according to preset ramp metering rate slip condition database, divides main stem traffic flow shape
State and ring road traffic flow modes;
The main stem traffic flow modes and the ring road are selected to hand over using ramp metering rate strategy prediction matrix trained in advance
Ramp metering rate strategy under open position, the ramp metering rate strategy include target ramp metering amount;
Corresponding ramp metering rate instruction is generated according to the target ramp metering amount, and the ramp metering rate is instructed and is sent
To the control signal lamp so that the control signal lamp is controlled according to the corresponding signal of the ramp metering rate instruction execution.
In a kind of possible embodiment, the method also includes:
The ramp metering rate strategy prediction matrix is trained in advance.
In a kind of possible embodiment, described the step of training the ramp metering rate strategy prediction matrix in advance, packet
It includes:
Obtain the traffic flow data that the highway ramp within a preset period of time imports section;
Determine the ramp metering rate slip condition database for training the ramp metering rate strategy prediction matrix, the ramp metering rate
Slip condition database includes traffic flow modes collection and traffic flow behavior aggregate, and the traffic flow modes collection includes for describing each traffic
The variable information of state, the traffic flow modes collection include the interwoven region traffic between the main stem upstream volume of traffic, main stem and ring road
Amount, ring road flow into the volume of traffic, the main stem downstream volume of traffic, main stem upstream density, ring road density, main stem upstream average speed and circle
Road average speed, the traffic flow behavior aggregate include the ramp metering amount under different conditions;
Determine that main stem upstream main line enters the volume of traffic of interwoven region, each control according to the ramp metering rate slip condition database
Period enters the volume of traffic of ring road, main stem downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of ring road
The volume of traffic;
According to main stem upstream main line enter interwoven region the volume of traffic, it is each control the period enter ring road the volume of traffic,
The volume of traffic that main stem downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of ring road calculates under each state
State behavior Reward Program value;
According to the training of the state behavior Reward Program value, the traffic flow data and the ramp metering rate slip condition database
The ramp metering rate strategy prediction matrix.
In a kind of possible embodiment, the volume of traffic, every that interwoven region is entered according to main stem upstream main line
A control period enters the volume of traffic of ring road, main stem downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of
The volume of traffic of ring road calculates the step of state behavior Reward Program value under each state, comprising:
According to main stem upstream main line enter interwoven region the volume of traffic, it is each control the period enter ring road the volume of traffic,
The volume of traffic that main stem downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of ring road determines current traffic
Congestion status;
Corresponding reward value or penalty value are determined according to the current traffic congestion state;
Enter the volume of traffic, each of interwoven region according to determining reward value or penalty value and main stem upstream main line
Period enters the volume of traffic of ring road, main stem downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of circle for control
The state behavior Reward Program value under each state is calculated in the volume of traffic in road.
In a kind of possible embodiment, the volume of traffic, every that interwoven region is entered according to main stem upstream main line
A control period enters the volume of traffic of ring road, main stem downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of
The calculation formula that the volume of traffic of ring road calculates the state behavior Reward Program value under each state includes:
R (t)=- [(qin (t)+din (t))-(qout (t)+dout (t))]
Wherein, r (t) is state behavior Reward Program value, and qin (t) is the friendship that main stem upstream main line enters interwoven region
Flux, din (t) are the volume of traffic for entering ring road in the t control period, and qout (t) is the traffic that main stem downstream main line sails out of interwoven region
Amount, dout (t) are the volume of traffic for sailing out of ring road in the t control period.
It is described according to the state behavior Reward Program value, the traffic flow data in a kind of possible embodiment
The step of with the ramp metering rate slip condition database training ramp metering rate strategy prediction matrix, comprising:
The kernel matrix Q value in initial ramp metering rate strategy prediction matrix is initialized, the kernel matrix Q value is for characterizing
The return rate of different ramp metering rate strategies is selected under Different Traffic Flows state, wherein the ramp metering rate strategy includes ring road tune
Section amount;
It is adjusted according to Entrance ramp of the kernel matrix Q value under the corresponding each traffic behavior of the traffic flow data
It measures in adjustment process, is calculated using softmax movement selection strategy and select each ramp metering rate strategy under Current traffic stream mode
Probability;
Each ramp metering rate strategy is executed, and calculates the state behavior Reward Program value after executing each ramp metering rate strategy
And the traffic flow modes updated after executing;
According to the traffic updated after the ramp metering rate strategy of execution, the state behavior Reward Program value and the execution
Stream mode updates the kernel matrix Q value under each traffic behavior, and returns according to the kernel matrix Q value in the traffic fluxion
According in the Entrance ramp regulated quantity adjustment process under corresponding each traffic behavior, calculated using softmax movement selection strategy
The step of probability of each ramp metering rate strategy is selected under Current traffic stream mode judge whether to reach trained termination condition, and
Determining to judge whether the kernel matrix Q value restrains when meeting training termination condition;
If it is determined that the kernel matrix Q value convergence, then corresponding by the maximum kernel matrix Q value under each traffic flow modes
Ramp metering rate strategy obtains the prediction of ramp metering rate strategy as the optimal ramp metering rate strategy under each traffic flow modes, with training
Matrix, the ramp metering rate strategy prediction matrix include the ramp metering rate strategy under each traffic flow modes.
It is described that Current traffic stream mode is calculated using softmax movement selection strategy in a kind of possible embodiment
The calculation formula of the probability of each ramp metering rate strategy of lower selection includes:
Wherein, (s is a) probability that ramp metering rate strategy a is selected at traffic flow modes s to P, and T is annealing temperature, Qt(s,
It a) is the corresponding kernel matrix Q value of current time state behavior.
It is described that letter is returned according to the ramp metering rate strategy of execution, the state behavior in a kind of possible embodiment
The traffic flow modes updated after numerical value and the execution update the calculation formula of the kernel matrix Q value under each traffic behavior,
Include:
Qt(st,at)=r(t)+0.8*Qt(st',at')
Wherein, Qt(s a) is the corresponding kernel matrix Q value of t moment, r(t)For the corresponding state behavior Reward Program of t moment
Value, atIndicate the traffic flow reduction amount of the traffic flow modes updated after the execution of t moment with traffic flow modes before.
It is described to be referred to according to the corresponding ramp metering rate of target ramp metering amount generation in a kind of possible embodiment
It enables, and ramp metering rate instruction is sent to the control signal lamp so that the control signal lamp is according to the ramp metering rate
After the step of corresponding signal of instruction execution controls, the method also includes:
It is corresponding according to the ramp metering rate instruction execution according to the target ramp metering amount and the control signal lamp
Signal control after the traffic flow data that detects of each Traffic flow detecting device return according to the kernel matrix Q value
It is dynamic using softmax in the Entrance ramp regulated quantity adjustment process under the corresponding each traffic behavior of the traffic flow data
The step of probability of each ramp metering rate strategy is selected under the policy calculation that elects Current traffic stream mode continues to train the circle
Road control strategy prediction matrix.
Second aspect, the embodiment of the present application also provide a kind of ramp metering rate device, be applied to server, the server with
Highway ramp imports the control that each Traffic flow detecting device and highway ramp remittance node are arranged on section and ramp metering rate section
Signal lamp communication connection processed, described device include:
Data acquisition module, the traffic flow data detected for obtaining each Traffic flow detecting device;
State demarcation module, for being divided according to preset ramp metering rate slip condition database the traffic flow data
Analysis divides main stem traffic flow modes and ring road traffic flow modes;
Strategy selection module, for selecting the main stem traffic flow using ramp metering rate strategy prediction matrix trained in advance
Ramp metering rate strategy under state and the ring road traffic flow modes, the ramp metering rate strategy include target ramp metering amount;
Instruction sending module is instructed for generating corresponding ramp metering rate according to the target ramp metering amount, and by institute
It states ramp metering rate instruction and is sent to the control signal lamp so that the control signal lamp is according to the ramp metering rate instruction execution
Corresponding signal control.
The third aspect, the embodiment of the present application also provide a kind of readable storage medium storing program for executing, are stored thereon with computer program, described
Computer program, which is performed, realizes above-mentioned ramp metering rate method.
In terms of existing technologies, the application has the advantages that
The embodiment of the present application provides a kind of ramp metering rate method and device, is detected by obtaining each Traffic flow detecting device
The traffic flow data arrived, and traffic flow data is analyzed according to preset ramp metering rate slip condition database, it divides main stem and hands over
Open position and ring road traffic flow modes then select main stem traffic flow using ramp metering rate strategy prediction matrix trained in advance
Ramp metering rate strategy under state and ring road traffic flow modes finally generates corresponding ramp metering rate according to target ramp metering amount
Instruction, and ramp metering rate instruction is sent to control signal lamp so that control signal lamp is corresponding according to ramp metering rate instruction execution
Signal control.The different ramp metering rates under Different Traffic Flows state can be imitated by ramp metering rate strategy prediction matrix as a result,
Fruit carries out objective analysis, so that it is determined that effectively mentioning under Different Traffic Flows state with the ramp metering rate strategy of optimal control results
The effect and reasonability of ramp metering rate have been risen, the transit time in ramp segment is reduced.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the application scenarios schematic diagram of ramp metering rate method provided by the embodiments of the present application;
Fig. 2 is the flow diagram of ramp metering rate method provided by the embodiments of the present application;
Fig. 3 is the section schematic diagram that crosses of a kind of main stem and ring road;
Fig. 4 is the functional block diagram of ramp metering rate device provided by the embodiments of the present application;
Fig. 5 is the structural representation frame of the server provided by the embodiments of the present application for realizing above-mentioned ramp metering rate method
Figure.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Usually herein
The component of the embodiment of the present application described and illustrated in place's attached drawing can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiments herein provided in the accompanying drawings is not intended to limit below claimed
Scope of the present application, but be merely representative of the selected embodiment of the application.Based on the embodiment in the application, this field is common
Technical staff's all other embodiment obtained without creative labor belongs to the application protection
Range.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
Referring to Fig. 1, before being illustrated to ramp metering rate method provided in this embodiment, first below to this implementation
The application scenarios for the ramp metering rate method that example provides are illustrated.As shown in Figure 1, the application scenarios may include server 100 with
And each Traffic flow detecting device 300 and control signal lamp 500 communicated to connect with server 100.In detail, each traffic
Flow detection device 300 can be set to be imported on section and ramp metering rate section in highway ramp, for converging to by highway ramp
The traffic flow for entering section and ramp metering rate section is detected.Control signal lamp 500, which can be set, imports node in highway ramp,
Traffic flow for process controlled.
In the present embodiment, the server 100 should be understood the service point of offer processing, data bank, communications service.It lifts
For example, server 100 can refer to the single physical processor with related communication and data storage and document library facility, or
It can refer to the aggregate of networking or the processor gathered, related network and storing unit, and to software and one or more
The application software serviced provided by document library system and support server 100 is operated.Server 100 can configuration or
It is widely different in performance, but server 100 generally may include one or more central processing unit and storage unit.Service
Device 100 can also include one or more large-scale storage area equipment, one or more power supplys, one or more wired or wireless nets
Network component, one or more input output assemblies or one or more operating systems, such as, Windows Server, Mac
OS X, Unix, Linux, FreeBSD etc..
Referring to Fig. 2, being a kind of flow diagram of ramp metering rate method provided by the embodiments of the present application, the ring road control
Method processed can the server 100 as shown in Fig. 1 execute.It should be noted that ramp metering rate provided by the embodiments of the present application
Method is not limitation with Fig. 2 and specific order below.The detailed process of this method is as follows:
Step S210 obtains the traffic flow data that each Traffic flow detecting device 300 detects.
In the present embodiment, traffic flow data may include that the interwoven region between the main stem upstream volume of traffic, main stem and ring road is handed over
Flux, ring road flow into the volume of traffic, the main stem downstream volume of traffic, main stem upstream density, ring road density, main stem upstream average speed and
Ring road average speed etc., the present embodiment is not intended to be limited in any this.
The relationship of above-mentioned main stem and ring road referring to figure 3. shown in application scenarios, qin be main stem upstream, qout is main stem
Downstream, din are ring road inflow, interwoven region of the dout between main stem and ring road.
Step S220 analyzes the traffic flow data according to preset ramp metering rate slip condition database, divides master
Road traffic flow modes and ring road traffic flow modes.
In the present embodiment, preset ramp metering rate slip condition database may include traffic flow modes collection and traffic flow movement
Collection, the traffic flow modes collection includes the variable information for describing each traffic behavior, such as the traffic flow modes Ji Bao
Include the interwoven region volume of traffic between the main stem upstream volume of traffic, main stem and the ring road of each traffic behavior, ring road flows into the volume of traffic, master
The road downstream volume of traffic, main stem upstream density, ring road density, main stem upstream average speed and ring road average speed, the traffic
Stream behavior aggregate may include the ramp metering amount under different conditions, and the codomain of the ramp metering amount should allow most in current road segment
Between high section value and minimum regulated value.For example, being started to walk initial stage in vehicle by stop line, first car can be set and pass through stop line
Time be 2 seconds, reach control effect by adjusting red light and green time.The range of Expressway Traffic Flow Density is
0veh/m~100veh/m is divided into free flow, synchronous stream and congestion stream.The range of free flow density is 0veh/m~30veh/
M, the range of synchronous current density are 30veh/m~60veh/m, and the range of congestion current density is 60veh/m~100veh/m.At a high speed
The range of highway ramp phase identification is 0veh/m~45veh/m, divides traffic flow modes by step-length of 5veh/m.Circle
Road, which adjusts quantity space, can choose the action space of discretization, and range is 0veh/m~40veh/m, divide by step-length of 4veh/m
Action space.
The traffic flow data is analyzed according to above-mentioned preset ramp metering rate slip condition database as a result, Ke Yihua
Divide main stem traffic flow modes and ring road traffic flow modes.
Step S230 selects the main stem traffic flow modes and institute using ramp metering rate strategy prediction matrix trained in advance
State the ramp metering rate strategy under ring road traffic flow modes.
Before this step S230 is further elaborated, first below to the training of ramp metering rate strategy prediction matrix
Process is illustrated.
Firstly, obtaining the highway ramp within a preset period of time imports the traffic flow data in section, and determine for instructing
The ramp metering rate slip condition database namely above-mentioned traffic flow modes collection of the white silk ramp metering rate strategy prediction matrix and traffic flow
Behavior aggregate.
Then, determine that main stem upstream main line enters the volume of traffic, every of interwoven region according to the ramp metering rate slip condition database
A control period enters the volume of traffic of ring road, main stem downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of
The volume of traffic of ring road.
Then, the volume of traffic of interwoven region is entered according to main stem upstream main line, each control period enters the friendship of ring road
The volume of traffic that flux, main stem downstream main line sail out of the volume of traffic of interwoven region and each control period sails out of ring road calculates each shape
State behavior Reward Program value under state.
Wherein, the volume of traffic of interwoven region is entered according to main stem upstream main line, each control period enters the friendship of ring road
The volume of traffic that flux, main stem downstream main line sail out of the volume of traffic of interwoven region and each control period sails out of ring road calculates each shape
The calculation formula of state behavior Reward Program value under state may include:
R (t)=- [(qin (t)+din (t))-(qout (t)+dout (t))]
Wherein, r (t) is state behavior Reward Program value, and qin (t) is the friendship that main stem upstream main line enters interwoven region
Flux, din (t) are the volume of traffic for entering ring road in the t control period, and qout (t) is the traffic that main stem downstream main line sails out of interwoven region
Amount, dout (t) are the volume of traffic for sailing out of ring road in the t control period.
In a kind of possible embodiment, in order to accelerate subsequent intensified learning convergence rate, state can be being determined
To the bonus prize values of the traffic flow modes setting corresponding proportion near crucial density state when behavior Reward Program value, to serious
The additional penalty value of congestion status setting corresponding proportion.For example, the friendship of interwoven region can be entered according to main stem upstream main line
Flux, it is each control the period enter the volume of traffic of ring road, main stem downstream main line sail out of interwoven region the volume of traffic and each control
The volume of traffic that period sails out of ring road determines current traffic congestion state, and according to determining pair of the current traffic congestion state
The reward value or penalty value answered.Finally, being entered according to determining reward value or penalty value and main stem upstream main line
The volume of traffic of interwoven region, each control period enter the volume of traffic of ring road, main stem downstream main line sail out of the volume of traffic of interwoven region with
And each control period sails out of the volume of traffic of ring road, and the state behavior Reward Program value under each state is calculated.For example, can
With the bonus prize values to the traffic flow modes setting 10% near crucial density state, to heavy congestion state setting 10%
Additional penalty value, namely while computationally stating the state behavior Reward Program value under each state, increase by 10% bonus prize values
Or the additional penalty value of deduction 10%.
Finally, according to the state behavior Reward Program value, the traffic flow data and the ramp metering rate status data
The library training ramp metering rate strategy prediction matrix.
In a kind of possible embodiment, the kernel matrix in initial ramp metering rate strategy prediction matrix is initialized first
Q value, the kernel matrix Q value is for characterizing the return rate for selecting different ramp metering rate strategies under Different Traffic Flows state, wherein
The ramp metering rate strategy includes ramp metering amount.
Then, the entrance circle according to the kernel matrix Q value under the corresponding each traffic behavior of the traffic flow data
In road regulated quantity adjustment process, is calculated using softmax movement selection strategy and select each ring road control under Current traffic stream mode
Make the probability of strategy.
The above-mentioned Entrance ramp according to the kernel matrix Q value under the corresponding each traffic behavior of the traffic flow data
In regulated quantity adjustment process, is calculated using softmax movement selection strategy and select each ramp metering rate under Current traffic stream mode
The calculation formula of probability of strategy may include:
Wherein, (s is a) probability that ramp metering rate strategy a is selected at traffic flow modes s to P, and T is annealing temperature, Qt(s,
It a) is the corresponding kernel matrix Q value of current time state behavior.
On the basis of the above, each ramp metering rate strategy is executed, and calculates the state after executing each ramp metering rate strategy
The traffic flow modes updated after behavior Reward Program value and execution.
Then, according to being updated after the ramp metering rate strategy of execution, the state behavior Reward Program value and the execution
Traffic flow modes update the kernel matrix Q value under each traffic behavior, and return according to the kernel matrix Q value in the friendship
In Entrance ramp regulated quantity adjustment process under the corresponding each traffic behavior of through-flow data, selection plan is acted using softmax
Approximation calculates the step of selecting the probability of each ramp metering rate strategy under Current traffic stream mode.In the whole process, judge whether
Reach trained termination condition, such as judges whether to have executed the kernel matrix under preset times (such as 20 times) each traffic behavior
The state of Q value updates, if so, determining to reach trained termination condition, and when determining to meet training termination condition described in judgement
Whether kernel matrix Q value restrains.
Wherein, according to being updated after the ramp metering rate strategy of execution, the state behavior Reward Program value and the execution
Traffic flow modes update the calculation formula of the kernel matrix Q value under each traffic behavior and may include:
Qt(st,at)=r(t)+0.8*Qt(st',at')
Wherein, Qt(s a) is the corresponding kernel matrix Q value of t moment, r(t)For the corresponding state behavior Reward Program of t moment
Value, atIndicate the traffic flow reduction amount of the traffic flow modes updated after the execution of t moment with traffic flow modes before.
If it is determined that the kernel matrix Q value convergence, then corresponding by the maximum kernel matrix Q value under each traffic flow modes
Ramp metering rate strategy obtains the prediction of ramp metering rate strategy as the optimal ramp metering rate strategy under each traffic flow modes, with training
Matrix, the ramp metering rate strategy prediction matrix include the ramp metering rate strategy under each traffic flow modes.
The rule that the present embodiment improves traffic efficiency by learning ramp metering rate strategy as a result, determines Different Traffic Flows
With the ramp metering rate strategy of optimal control results under state.The mistake of ramp metering rate strategy in the case where learning each traffic flow modes
Cheng Zhong selects each ramp metering rate strategy according to Current traffic stream mode, calculates state caused by each ramp metering rate strategy and turns
The state behavior Reward Program value of shifting, and traverse the state behavior Reward Program of the transfer of state caused by all ramp metering rate strategies
Value, the state behavior Reward Program value convergence of the transfer of the state caused by all ramp metering rate strategies, to realize to difference
Under traffic flow modes between different ramp metering values and its control effect information excavation, mentioned for the determination process of ramp metering value
For objective theoretical foundation, it is right between traffic flow modes and ramp metering under expressway ramp in the prior art controls to compensate for
It should be related to determining randomness, improve the stability during traffic control.
On the basis of the above, the main stem traffic flow modes and the ring road are selected by ramp metering rate strategy prediction matrix
Ramp metering rate strategy under traffic flow modes independently selects the main stem traffic flow modes and the ring road traffic flow to realize
Corresponding optimal ramp metering rate regulated quantity under state, and using optimal ramp metering rate regulated quantity as the target in ramp metering rate strategy
Ramp metering amount.
Step S240 generates corresponding ramp metering rate according to the target ramp metering amount and instructs, and by the ring road control
System instruction is sent to the control signal lamp 500 so that the control signal lamp 500 is according to the ramp metering rate instruction execution pair
The signal control answered.
The present embodiment can be to the different ramp metering rates under Different Traffic Flows state by ramp metering rate strategy prediction matrix
Effect carries out objective analysis, so that it is determined that with the ramp metering rate strategy of optimal control results under Different Traffic Flows state, effectively
The effect and reasonability of ramp metering rate are improved, the transit time in ramp segment is reduced, improves traffic traffic efficiency.
Further, in a kind of possible embodiment, the present embodiment can also be according to the target ramp metering amount
And the control signal lamp 500 is according to each traffic flow after the corresponding signal control of the ramp metering rate instruction execution
The traffic flow data that detection device 300 detects returns corresponding every in the traffic flow data according to the kernel matrix Q value
In Entrance ramp regulated quantity adjustment process under a traffic behavior, current flows are calculated using softmax movement selection strategy
The step of probability of each ramp metering rate strategy is selected under state continues to train the ramp metering rate strategy prediction matrix.
Traffic flow data and target circle by being detected based on each Traffic flow detecting device 300 after control as a result,
Road regulated quantity carries out Continuous optimization to ramp metering rate strategy prediction matrix, and continual analysis ramp metering amount improves traffic efficiency
Affecting laws, so that ramp metering rate strategy prediction matrix may be implemented to carry out anti-ramp metering amount according to real-time traffic flow data
Feedback is adjusted, the traffic efficiency of further Improving Expressway.
Further, referring to Fig. 4, the embodiment of the present application also provides a kind of ramp metering rate device 200, ramp metering rate dress
The function of setting 200 realizations can correspond to the step of above method executes.The ramp metering rate device 200 can be understood as above-mentioned service
The processor of device 100 or server 100, it is understood that for independently of servicing except above-mentioned server 100 or processor
The lower component for realizing the application function of the control of device 100, as shown in figure 4, the ramp metering rate device 200 may include data acquisition mould
Block 210, state demarcation module 220, strategy selection module 230 and instruction sending module 240, the ramp metering rate fills separately below
The function of setting 200 each functional module is described in detail.
Data acquisition module 210, the traffic flow data detected for obtaining each Traffic flow detecting device 300.
State demarcation module 220, for being carried out according to preset ramp metering rate slip condition database to the traffic flow data
Analysis divides main stem traffic flow modes and ring road traffic flow modes.
Strategy selection module 230, for selecting the main stem to hand over using ramp metering rate strategy prediction matrix trained in advance
Ramp metering rate strategy under open position and the ring road traffic flow modes, the ramp metering rate strategy include target ramp metering
Amount.
Instruction sending module 240 is instructed for generating corresponding ramp metering rate according to the target ramp metering amount, and will
The ramp metering rate instruction is sent to the control signal lamp 500 so that the control signal lamp 500 is according to the ramp metering rate
The corresponding signal control of instruction execution.
It is understood that the concrete operation method of each functional module in the present embodiment can refer to above method embodiment
The detailed description of middle corresponding steps, it is no longer repeated herein.
Further, referring to Fig. 5, being the server provided by the embodiments of the present application for above-mentioned ramp metering rate method
100100 structural schematic block diagram.In the present embodiment, the server 100100 can be made general total wire body by bus 110
Architecture is realized.According to the concrete application of server 100100 and overall design constraints condition, bus 110 may include any
The interconnection bus and bridge joint of quantity.Together by various circuit connections, these circuits include processor 120, storage Jie to bus 110
Matter 130 and bus interface 140.Optionally, server 100100 can be used bus interface 140 and pass through network adapter 150 Deng
It is connected by bus 110.Network adapter 150 can be used for realizing the signal processing function of physical layer in server 100100, and lead to
It crosses antenna and realizes sending and receiving for radiofrequency signal.User interface 160 can connect external equipment, such as: keyboard, display,
Mouse or control stick etc..Bus 110 can also connect various other circuits, as timing source, peripheral equipment, voltage regulator or
Person's management circuit etc., these circuits are known in the art, therefore are no longer described in detail.
It can replace, server 100100 may also be configured to generic processing system, such as be commonly referred to as chip, the general place
Reason system includes: to provide the one or more microprocessors of processing function, and provide at least part of of storage medium 130
External memory, it is all these all to be linked together by external bus architecture and other support circuits.
Alternatively, following realize can be used in server 100100: having processor 120, bus interface 140, uses
The ASIC (specific integrated circuit) of family interface 160;And it is integrated at least part of the storage medium 130 in one single chip,
Alternatively, following realize can be used in server 100100: one or more FPGA (field programmable gate array), PLD (can compile
Journey logical device), controller, state machine, gate logic, discrete hardware components, any other suitable circuit or be able to carry out
Any combination of the application circuit of described various functions in the whole text.
Wherein, processor 120 is responsible for management bus 110 and general processing (is stored on storage medium 130 including executing
Software).One or more general processors and/or application specific processor can be used to realize in processor 120.Processor 120
Example includes microprocessor, microcontroller, dsp processor and the other circuits for being able to carry out software.It should be by software broadly
It is construed to indicate instruction, data or any combination thereof, regardless of being called it as software, firmware, middleware, microcode, hard
Part description language or other.
Storage medium 130 is illustrated as separating with processor 120 in Fig. 5, however, those skilled in the art be easy to it is bright
White, storage medium 130 or its arbitrary portion can be located at except server 100100.For example, storage medium 130 may include
Transmission line, the carrier waveform modulated with data, and/or the computer product that separates with radio node, these media can be with
It is accessed by processor 120 by bus interface 140.Alternatively, storage medium 130 or its arbitrary portion can integrate everywhere
It manages in device 120, for example, it may be cache and/or general register.
Above-described embodiment can be performed in the processor 120, specifically, can store in the storage medium 130 described
Ramp metering rate device 200, the processor 120 can be used for executing the ramp metering rate device 200.
Further, the embodiment of the present application also provides a kind of nonvolatile computer storage media, the computer is deposited
Storage media is stored with computer executable instructions, which can be performed the circle in above-mentioned any means embodiment
Channel control method.
In conclusion the embodiment of the present application provides a kind of ramp metering rate method and device, examined by obtaining each traffic flow
The traffic flow data that device detects is surveyed, and traffic flow data is analyzed according to preset ramp metering rate slip condition database,
Main stem traffic flow modes and ring road traffic flow modes are divided, then using ramp metering rate strategy prediction matrix selection trained in advance
Ramp metering rate strategy under main stem traffic flow modes and ring road traffic flow modes is finally generated according to target ramp metering amount and is corresponded to
Ramp metering rate instruction, and ramp metering rate instruction is sent to control signal lamp so that control signal lamp is instructed according to ramp metering rate
Execute corresponding signal control.It as a result, can be to the difference under Different Traffic Flows state by ramp metering rate strategy prediction matrix
Ramp metering rate effect carries out objective analysis, so that it is determined that with the ramp metering rate plan of optimal control results under Different Traffic Flows state
Slightly, the effect and reasonability of ramp metering rate are effectively improved, the transit time in ramp segment is reduced.
In embodiment provided herein, it should be understood that disclosed device and method, it can also be by other
Mode realize.Device and method embodiment described above is only schematical, for example, flow chart and frame in attached drawing
Figure shows the system frame in the cards of the system of multiple embodiments according to the application, method and computer program product
Structure, function and operation.In this regard, each box in flowchart or block diagram can represent a module, section or code
A part, a part of the module, section or code includes one or more for implementing the specified logical function
Executable instruction.It should also be noted that function marked in the box can also be with not in some implementations as replacement
It is same as the sequence marked in attached drawing generation.For example, two continuous boxes can actually be basically executed in parallel, they have
When can also execute in the opposite order, this depends on the function involved.It is also noted that in block diagram and or flow chart
Each box and the box in block diagram and or flow chart combination, can function or movement as defined in executing it is dedicated
Hardware based system realize, or can realize using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the application can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It can replace, can be realized wholly or partly by software, hardware, firmware or any combination thereof.When
When using software realization, can entirely or partly it realize in the form of a computer program product.The computer program product
Including one or more computer instructions.It is all or part of when loading on computers and executing the computer program instructions
Ground is generated according to process or function described in the embodiment of the present application.The computer can be general purpose computer, special purpose computer,
Computer network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or
Person is transmitted from a computer readable storage medium to another computer readable storage medium, for example, the computer instruction
Wired (such as coaxial cable, optical fiber, digital subscriber can be passed through from a web-site, computer, server or data center
Line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or data
It is transmitted at center.The computer readable storage medium can be any usable medium that computer can access and either wrap
The data storage devices such as electronic equipment, server, the data center integrated containing one or more usable mediums.The usable medium
It can be magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid-state
Hard disk Solid State Disk (SSD)) etc..
It should be noted that, in this document, term " including ", " including " or its any other variant are intended to non-row
Its property includes, so that the process, method, article or equipment for including a series of elements not only includes those elements, and
And further include the other elements being not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence " including one ... ", it is not excluded that including institute
State in the process, method, article or equipment of element that there is also other identical elements.
It is obvious to a person skilled in the art that the application is not limited to the details of above-mentioned exemplary embodiment, Er Qie
In the case where without departing substantially from spirit herein or essential characteristic, the application can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and scope of the present application is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the application.Any reference signs in the claims should not be construed as limiting the involved claims.
Claims (10)
1. a kind of ramp metering rate method, which is characterized in that be applied to server, the server and highway ramp import section and
Each Traffic flow detecting device is set on ramp metering rate section and highway ramp imports the control signal lamp communication connection of node, institute
The method of stating includes:
Obtain the traffic flow data that each Traffic flow detecting device detects;
The traffic flow data is analyzed according to preset ramp metering rate slip condition database, divide main stem traffic flow modes and
Ring road traffic flow modes;
The main stem traffic flow modes and the ring road traffic flow are selected using ramp metering rate strategy prediction matrix trained in advance
Ramp metering rate strategy under state, the ramp metering rate strategy include target ramp metering amount;
Corresponding ramp metering rate instruction is generated according to the target ramp metering amount, and ramp metering rate instruction is sent to institute
Control signal lamp is stated so that the control signal lamp is controlled according to the corresponding signal of the ramp metering rate instruction execution.
2. ramp metering rate method according to claim 1, which is characterized in that the method also includes:
The ramp metering rate strategy prediction matrix is trained in advance.
3. ramp metering rate method according to claim 2, which is characterized in that described to train the ramp metering rate strategy in advance
The step of prediction matrix, comprising:
Obtain the traffic flow data that the highway ramp within a preset period of time imports section;
Determine the ramp metering rate slip condition database for training the ramp metering rate strategy prediction matrix, the ramp metering rate state
Database includes traffic flow modes collection and traffic flow behavior aggregate, and the traffic flow modes collection includes for describing each traffic behavior
Variable information, the traffic flow modes collection includes the interwoven region volume of traffic, the circle between the main stem upstream volume of traffic, main stem and ring road
It is flat that road flows into the volume of traffic, the main stem downstream volume of traffic, main stem upstream density, ring road density, main stem upstream average speed and ring road
Equal speed, the traffic flow behavior aggregate include the ramp metering amount under different conditions;
Determine that main stem upstream main line enters the volume of traffic of interwoven region, each control period according to the ramp metering rate slip condition database
The volume of traffic, main stem downstream main line into ring road sail out of the volume of traffic of interwoven region and each control period sails out of the traffic of ring road
Amount;
Enter the volume of traffic of interwoven region according to main stem upstream main line, each control period enters the volume of traffic of ring road, main stem
The volume of traffic that downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of ring road calculates the shape under each state
State behavior Reward Program value;
According to the training of the state behavior Reward Program value, the traffic flow data and the ramp metering rate slip condition database
Ramp metering rate strategy prediction matrix.
4. ramp metering rate method according to claim 3, which is characterized in that described to be entered according to main stem upstream main line
The volume of traffic of interwoven region, each control period enter the volume of traffic of ring road, main stem downstream main line sail out of the volume of traffic of interwoven region with
And each control period sails out of the step of volume of traffic of ring road calculates the state behavior Reward Program value under each state, comprising:
Enter the volume of traffic of interwoven region according to main stem upstream main line, each control period enters the volume of traffic of ring road, main stem
The volume of traffic that downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of ring road determines current traffic congestion
State;
Corresponding reward value or penalty value are determined according to the current traffic congestion state;
Enter the volume of traffic of interwoven region, each control according to determining reward value or penalty value and main stem upstream main line
Period enters the volume of traffic of ring road, main stem downstream main line sails out of the volume of traffic of interwoven region and each control period sails out of ring road
The state behavior Reward Program value under each state is calculated in the volume of traffic.
5. ramp metering rate method according to claim 3, which is characterized in that described to be entered according to main stem upstream main line
The volume of traffic of interwoven region, each control period enter the volume of traffic of ring road, main stem downstream main line sail out of the volume of traffic of interwoven region with
And the volume of traffic that each control period sails out of ring road calculates the calculation formula packet of the state behavior Reward Program value under each state
It includes:
R (t)=- [(qin (t)+din (t))-(qout (t)+dout (t))]
Wherein, r (t) is state behavior Reward Program value, and qin (t) is the volume of traffic that main stem upstream main line enters interwoven region,
Din (t) is the volume of traffic for entering ring road in the t control period, and qout (t) is the volume of traffic that main stem downstream main line sails out of interwoven region,
Dout (t) is the volume of traffic for sailing out of ring road in the t control period.
6. ramp metering rate method according to claim 3, which is characterized in that described according to the state behavior Reward Program
The step of value, the traffic flow data and ramp metering rate slip condition database training ramp metering rate strategy prediction matrix,
Include:
The kernel matrix Q value in initial ramp metering rate strategy prediction matrix is initialized, the kernel matrix Q value is for characterizing difference
The return rate of different ramp metering rate strategies is selected under traffic flow modes, wherein the ramp metering rate strategy includes ramp metering amount;
According to Entrance ramp regulated quantity tune of the kernel matrix Q value under the corresponding each traffic behavior of the traffic flow data
During section, is calculated using softmax movement selection strategy and select the general of each ramp metering rate strategy under Current traffic stream mode
Rate;
Execute each ramp metering rate strategy, and calculate the state behavior Reward Program value after executing each ramp metering rate strategy and
The traffic flow modes updated after execution;
According to the traffic flow shape updated after the ramp metering rate strategy of execution, the state behavior Reward Program value and the execution
State updates the kernel matrix Q value under each traffic behavior, and returns according to the kernel matrix Q value in the traffic flow data pair
In Entrance ramp regulated quantity adjustment process under each traffic behavior answered, calculated using softmax movement selection strategy current
The step of probability of each ramp metering rate strategy is selected under traffic flow modes judges whether to reach trained termination condition, and is sentencing
Judge whether the kernel matrix Q value restrains when fixed satisfaction training termination condition;
If it is determined that the kernel matrix Q value convergence, then by the corresponding ring road of maximum kernel matrix Q value under each traffic flow modes
Control strategy obtains ramp metering rate strategy prediction square as the optimal ramp metering rate strategy under each traffic flow modes, with training
Battle array, the ramp metering rate strategy prediction matrix includes the ramp metering rate strategy under each traffic flow modes.
7. ramp metering rate method according to claim 6, which is characterized in that described to act selection strategy using softmax
It calculates and selects the calculation formula of the probability of each ramp metering rate strategy to include: under Current traffic stream mode
Wherein, (s is a) probability that ramp metering rate strategy a is selected at traffic flow modes s to P, and T is annealing temperature, Qt(s a) is
The corresponding kernel matrix Q value of current time state behavior.
8. ramp metering rate method according to claim 6, which is characterized in that the ramp metering rate strategy according to execution,
The traffic flow modes updated after the state behavior Reward Program value and the execution update the core under each traffic behavior
The calculation formula of matrix Q value, comprising:
Qt(st,at)=r(t)+0.8*Qt(st',at')
Wherein, Qt(s a) is the corresponding kernel matrix Q value of t moment, r(t)For the corresponding state behavior Reward Program value of t moment, at
Indicate the traffic flow reduction amount of the traffic flow modes updated after the execution of t moment with traffic flow modes before.
9. ramp metering rate method according to claim 6, which is characterized in that described raw according to the target ramp metering amount
It is instructed at corresponding ramp metering rate, and ramp metering rate instruction is sent to the control signal lamp so that the control signal
After the step of lamp is controlled according to the corresponding signal of the ramp metering rate instruction execution, the method also includes:
According to the target ramp metering amount and the control signal lamp according to the corresponding letter of the ramp metering rate instruction execution
The traffic flow data that detects of each Traffic flow detecting device is returned according to the kernel matrix Q value in institute after number control
It states in the Entrance ramp regulated quantity adjustment process under the corresponding each traffic behavior of traffic flow data, is acted and selected using softmax
The step of selecting the probability that each ramp metering rate strategy is selected under policy calculation Current traffic stream mode continues to train the ring road control
Make tactful prediction matrix.
10. a kind of ramp metering rate device, which is characterized in that be applied to server, the server and highway ramp import section
And the control signal lamp communication connection of each Traffic flow detecting device and highway ramp remittance node is set on ramp metering rate section,
Described device includes:
Data acquisition module, the traffic flow data detected for obtaining each Traffic flow detecting device;
State demarcation module is drawn for being analyzed according to preset ramp metering rate slip condition database the traffic flow data
Divide main stem traffic flow modes and ring road traffic flow modes;
Strategy selection module, for selecting the main stem traffic flow modes using ramp metering rate strategy prediction matrix trained in advance
With the ramp metering rate strategy under the ring road traffic flow modes, the ramp metering rate strategy includes target ramp metering amount;
Instruction sending module is instructed for generating corresponding ramp metering rate according to the target ramp metering amount, and by the circle
Road control instruction is sent to the control signal lamp so that the control signal lamp is corresponding according to the ramp metering rate instruction execution
Signal control.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811583233.3A CN109448402B (en) | 2018-12-24 | 2018-12-24 | Ramp control method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811583233.3A CN109448402B (en) | 2018-12-24 | 2018-12-24 | Ramp control method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109448402A true CN109448402A (en) | 2019-03-08 |
CN109448402B CN109448402B (en) | 2021-02-09 |
Family
ID=65535125
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811583233.3A Active CN109448402B (en) | 2018-12-24 | 2018-12-24 | Ramp control method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109448402B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110299008A (en) * | 2019-07-19 | 2019-10-01 | 浙江工业大学 | A kind of traffic flow multistep forecasting method based on intensified learning |
CN111028504A (en) * | 2019-11-27 | 2020-04-17 | 天津易华录信息技术有限公司 | Urban expressway intelligent traffic control method and system |
CN112669600A (en) * | 2020-12-15 | 2021-04-16 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Method for predicting intersection traffic flow by using automobile electronic identification information |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101789183A (en) * | 2010-02-10 | 2010-07-28 | 北方工业大学 | Self-adaptive control system and method for entrance ramp |
CN101958049A (en) * | 2010-09-21 | 2011-01-26 | 隋亚刚 | Signal light linkage control system of express way ramp outlet and adjacent intersection in city |
CN104103180A (en) * | 2014-07-15 | 2014-10-15 | 同济大学 | Urban expressway on-ramp and main line collaborative signal control system and method |
CN104240521A (en) * | 2014-09-30 | 2014-12-24 | 天津通翔智能交通***有限公司 | Intelligent ramp traffic control machine, system and method |
CN106128123A (en) * | 2016-07-11 | 2016-11-16 | 东南大学 | A kind of traffic control algorithm optimization algorithm promoted towards different traffic bottlenecks sections traffic efficiency |
CN106157650A (en) * | 2016-07-11 | 2016-11-23 | 东南大学 | A kind of through street traffic efficiency ameliorative way controlled based on intensified learning variable speed-limit |
WO2018013269A1 (en) * | 2016-07-12 | 2018-01-18 | Siemens Industry, Inc. | A connected vehicle traffic safety system and a method of warning drivers of a wrong-way travel |
CN107765551A (en) * | 2017-10-25 | 2018-03-06 | 河南理工大学 | A kind of city expressway On-ramp Control method |
CN108109398A (en) * | 2017-12-28 | 2018-06-01 | 山东易构软件技术股份有限公司 | A kind of overhead expressway Coordinated Ramp Control System and control method |
CN108122418A (en) * | 2017-12-19 | 2018-06-05 | 公安部交通管理科学研究所 | City expressway main line and ring road cooperative control method and system |
CN108320535A (en) * | 2018-04-10 | 2018-07-24 | 哈尔滨工业大学 | A kind of passing control method of road merging area weaving vehicles |
CN108510758A (en) * | 2018-05-24 | 2018-09-07 | 金陵科技学院 | City expressway Entrance ramp signal control method based on video real time information |
CN108898854A (en) * | 2018-07-06 | 2018-11-27 | 广州交通信息化建设投资营运有限公司 | A kind of Ramp cooperative control method based on Model Predictive Control |
-
2018
- 2018-12-24 CN CN201811583233.3A patent/CN109448402B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101789183A (en) * | 2010-02-10 | 2010-07-28 | 北方工业大学 | Self-adaptive control system and method for entrance ramp |
CN101958049A (en) * | 2010-09-21 | 2011-01-26 | 隋亚刚 | Signal light linkage control system of express way ramp outlet and adjacent intersection in city |
CN104103180A (en) * | 2014-07-15 | 2014-10-15 | 同济大学 | Urban expressway on-ramp and main line collaborative signal control system and method |
CN104240521A (en) * | 2014-09-30 | 2014-12-24 | 天津通翔智能交通***有限公司 | Intelligent ramp traffic control machine, system and method |
CN106128123A (en) * | 2016-07-11 | 2016-11-16 | 东南大学 | A kind of traffic control algorithm optimization algorithm promoted towards different traffic bottlenecks sections traffic efficiency |
CN106157650A (en) * | 2016-07-11 | 2016-11-23 | 东南大学 | A kind of through street traffic efficiency ameliorative way controlled based on intensified learning variable speed-limit |
WO2018013269A1 (en) * | 2016-07-12 | 2018-01-18 | Siemens Industry, Inc. | A connected vehicle traffic safety system and a method of warning drivers of a wrong-way travel |
CN107765551A (en) * | 2017-10-25 | 2018-03-06 | 河南理工大学 | A kind of city expressway On-ramp Control method |
CN108122418A (en) * | 2017-12-19 | 2018-06-05 | 公安部交通管理科学研究所 | City expressway main line and ring road cooperative control method and system |
CN108109398A (en) * | 2017-12-28 | 2018-06-01 | 山东易构软件技术股份有限公司 | A kind of overhead expressway Coordinated Ramp Control System and control method |
CN108320535A (en) * | 2018-04-10 | 2018-07-24 | 哈尔滨工业大学 | A kind of passing control method of road merging area weaving vehicles |
CN108510758A (en) * | 2018-05-24 | 2018-09-07 | 金陵科技学院 | City expressway Entrance ramp signal control method based on video real time information |
CN108898854A (en) * | 2018-07-06 | 2018-11-27 | 广州交通信息化建设投资营运有限公司 | A kind of Ramp cooperative control method based on Model Predictive Control |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110299008A (en) * | 2019-07-19 | 2019-10-01 | 浙江工业大学 | A kind of traffic flow multistep forecasting method based on intensified learning |
CN110299008B (en) * | 2019-07-19 | 2020-11-13 | 浙江工业大学 | Traffic flow multi-step prediction method based on reinforcement learning |
CN111028504A (en) * | 2019-11-27 | 2020-04-17 | 天津易华录信息技术有限公司 | Urban expressway intelligent traffic control method and system |
CN112669600A (en) * | 2020-12-15 | 2021-04-16 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Method for predicting intersection traffic flow by using automobile electronic identification information |
Also Published As
Publication number | Publication date |
---|---|
CN109448402B (en) | 2021-02-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105046987B (en) | Road traffic signal lamp coordination control method based on reinforcement learning | |
Ma et al. | Feudal multi-agent deep reinforcement learning for traffic signal control | |
CN109448402A (en) | Ramp metering rate method and device | |
CN110136455A (en) | A kind of traffic lights timing method | |
Ault et al. | Reinforcement learning benchmarks for traffic signal control | |
CN100444210C (en) | Mixed controlling method of single dot signal controlling crossing | |
CN106355885A (en) | Traffic signal dynamic control method and system based on big data analysis platform | |
CN109544945A (en) | Region based on lane saturation degree controls multiphase traffic time allocation optimization method | |
CN106846842A (en) | Urban arterial road coordinate control optimization method based on multi-period control program | |
CN106205156A (en) | A kind of crossing self-healing control method for the sudden change of part lane flow | |
CN104183119A (en) | Real-time traffic flow distribution prediction system based on road section OD backstepping | |
CN113257016B (en) | Traffic signal control method and device and readable storage medium | |
CN109035808A (en) | A kind of traffic lights switching method and system based on deep learning | |
CN108171998A (en) | A kind of crossing self-adapting traffic signal control system and its method of work based on the alert data of electricity | |
CN109902864A (en) | A kind of construction area Traffic Organization design method considering network prestowage equilibrium | |
CN105447116B (en) | Parking guidance decision-making technique based on Mamdani algorithm | |
Guerrero-Ibanez et al. | A policy-based multi-agent management approach for intelligent traffic-light control | |
CN105743783B (en) | Car networking network node screening technique based on BS-TS and autoencoder network | |
CN115311868B (en) | Main line coordination control method and device based on bus priority | |
CN112365713A (en) | Main branch intersection signal timing optimization method | |
CN113537626A (en) | Neural network combined time sequence prediction method for aggregating information difference | |
Beauchamp-Baez et al. | A fuzzy logic based phase controller for traffic control | |
Hussain et al. | Optimizing traffic lights with multi-agent deep reinforcement learning and v2x communication | |
Teng et al. | A hybrid algorithm based on GWO and GOA for cycle traffic light timing optimization | |
Zeng et al. | Halight: Hierarchical deep reinforcement learning for cooperative arterial traffic signal control with cycle 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 |