CN109544929A - A kind of control of vehicle low-carbon and abductive approach, system, equipment and storage medium based on big data - Google Patents
A kind of control of vehicle low-carbon and abductive approach, system, equipment and storage medium based on big data Download PDFInfo
- Publication number
- CN109544929A CN109544929A CN201811534976.1A CN201811534976A CN109544929A CN 109544929 A CN109544929 A CN 109544929A CN 201811534976 A CN201811534976 A CN 201811534976A CN 109544929 A CN109544929 A CN 109544929A
- Authority
- CN
- China
- Prior art keywords
- data
- intersection
- traffic
- algorithm
- signal
- 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
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/081—Plural intersections under common control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The control of vehicle low-carbon and abductive approach that the invention discloses a kind of based on big data include the following steps: that S100. passes through the various approach acquisition traffic data including different detection devices, mobile device, network including；S200. the traffic data collected according to S100 is proposed to be accelerated the algorithm of data processing speed based on cloud computing technology and be handled data；S300. on-line data analysis is carried out according to S200 treated data, analysis obtains crossing, the road section traffic volume situation of different times；S400. according to arterial highway signal coordination methodology, the online traffic signals of real-time control realize arterial highway signal coordination and optimization；S500. final that driver is induced to select optimal path trip by the optimal trip route of traffic guidance algorithmic rule.By carrying out arterial highway signal coordination and optimization and optimum path planning, induction driver selects optimal path trip, to reduce stop frequency and congestion time of the vehicle in intersection, reduces the problem of vehicle exhaust emissions amount caused by intersection increases.
Description
Technical field
The present invention relates to traffic coordinated control fields, control more particularly, to a kind of vehicle low-carbon based on big data
With abductive approach, system, equipment and storage medium.
Background technique
As the economic condition of people becomes to become better and better, trip requirements become increasing, possess so as to cause automobile
Amount significantly improves.Vehicle ownership increases so that traffic is more crowded, and clogging is more and more obvious, and energy source of car consumption accounts for
The ratio of total energy increases.What it is due to automobile consumption is the oil and gasoline extracted inside petroleum, in recent years, whole society's traffic
It transports and increases by 9.74% fossil energy consumption year, Chinese year increases by 10.8%.In contrast, the whole of China's communications and transportation consumes
Oil amount has been more than the whole society 1.06%, and under the situation of energy globalization, China is either all in consumption or discharge
Major country, especially traffic become main use direction and discharge source.
In urban road, inevitable complex crossing is the hub site of traffic.Correctly, reasonably processing traffic flow it
Between traffic conflict, to improve traffic efficiency, and solve the problems, such as that Serious conflicts are the key that solutions to a certain extent.Intersect
Mouthful traffic signalization it is reasonable whether direct decision vehicle operation conditions, or even the entirely operational efficiency of road network.Current
In off-the-shelf item, primary concern is that next pair of traffic circulation index, including vehicle delay, queue length etc. when research signal controls
The problem of intersection carries out signal timing dial, but vehicle exhaust discharge quantity caused by often ignoring because of intersection increases, thus it is existing
Technology could be improved and improve.
Summary of the invention
The present invention is to solve to ignore the increasing of vehicle exhaust discharge quantity caused by intersection in existing traffic coordinated control technology
More problems, provide it is a kind of based on big data vehicle low-carbon control with abductive approach, system, equipment and storage medium.
To realize the above goal of the invention, and the technological means used is:
A kind of control of vehicle low-carbon and abductive approach based on big data, includes the following steps:
S100. traffic data is acquired by the various approach including different detection devices, mobile device, network；
S200. the traffic data collected according to S100 proposes to accelerate data processing speed based on cloud computing technology
Algorithm is simultaneously handled data；
S300. on-line data analysis is carried out according to S200 treated data, analysis obtains crossing, the section of different times
Traffic condition；
S400. according to arterial highway signal coordination methodology, the online traffic signals of real-time control realize arterial highway signal coordination and optimization；
S500. final that driver is induced to select optimal path trip by the optimal trip route of traffic guidance algorithmic rule.
Above scheme is analyzed by the integrated treatment to traffic data, calculates and predict the traffic condition in each section of road network,
And the online traffic signals of real-time control, realize arterial highway signal coordination and optimization, while planning optimal trip route for driver, from
And stop frequency and delay time at stop of the vehicle in intersection are reduced, reduce vehicle energy consumption and exhaust emissions.
Preferably, acquisition data described in step S100 are by including earth magnetism, coil, video, RFID, internet and shifting
Detector including dynamic equipment carries out one or more data acquisition；For different acquisition approach, need to only be arranged corresponding
Longitude and latitude.The traffic data of acquisition includes traffic behavior, traffic index, the magnitude of traffic flow, average speed, queue length, stops
Train number number, delay time at stop, saturation degree, hourage and record time etc., more perfect to analysis and the prediction offer of traffic behavior,
Accurate information.
Preferably, step S200 is specifically included:
S210. the characteristic that the traffic data that S100 is acquired is calculated using Canopy clustering algorithm, it is same wherein having
The traffic data set of one characteristic is put into a subset, referred to as Canopy, and each Canopy regards a cluster as, is denoted as V, and will
They are put into set S；
S211. two points of clusters are carried out using K-means clustering algorithm in each Canopy: from the set S in S210
Each cluster is extracted in order, and the cluster of extraction will match with limit point criterion, then carry out two points with K-means clustering algorithm
Cluster, the smallest two clusters of error sum of squares in cluster is put back in set S, and circulation is executed until obtaining K cluster；
Data are carried out quickening processing by the data processing algorithm for S212. passing through S210 and S211.
Preferably, on-line data analysis described in step S300 includes:
S310. it is based on that hour built-up pattern is divided to carry out mid-term traffic flow forecasting:
Step 1: being screened according to Lay spy's criterion to the data；
Step 2: the data to screening carry out correlation analysis；
Step 3: carrying out Time segments division according to flow distribution, being divided into 24 periods for 24 hours one day；For each
Period studies the relationship of its flow and speed, i.e. Q-V model, is then predicted using ARIMA model the discharge in period of time；
Step 4: prediction result is combined by certain weight with the result of Q-V model, according to mean absolute error,
Three indexs of average absolute percentage error and mean square error compare final calculated result and actual flow.
S311. the expanded Kalman filtration algorithm based on expectation optimization estimates traffic state information；
Wherein expectation optimization algorithm is a kind of iterative solution algorithm for estimating model parameter α and known variables Y
Step 1: Y is sought, and α | X；Y is found out first | the accurate solution of X, α, and point out the limitation accurately solved, Accurate Reasoning is
It is realized by the Bayesian Estimation of recursion, expands posterior probability density, and calculate in a recursive manner；Then propose that one kind makes
Use expansible Kalman filtering algorithm as a kind of substitution approximate solution；Hypothetic observation is x, and hidden state is y, shape
State transform distribution such as formula p (y(t)y(t-1)), and observational networks such as formula p (x(t)|y(t)).Reasoning behind hidden state y are as follows:
Use p (y(t-1)|x(1:t-1)) recursive resolve formula are as follows:
p(y(t)|x(1:t-1))=∫ p (y(t)|y(t-1)p(y(t-1)|x(1:t-1))dy(t-1)；
Similarly, p (y(t)|x(1:t)) can be by such as formula p (y(t)|x(1:t))=Cp (x(t)|y(t))p(y(t)|x(1:t-1)) and C=
(∫p(x(t)|y(t))p(y(t)|x(1:t-1)dy(t))-1It finds out.
Step 2: seeking α | Y, X；Determine optimal model parameter α first, it is assumed that all traffic behaviors be it is known, this
It can be implemented as one simply to minimize the error；From parent map and link queue model, observation function h () and pseudo- sight are obtained
It surveys, calculation formula X-=h (Y)；Then, observation X and pseudo- observation X are reduced to the maximum extent+Between difference, obtain it is expected
The iteration of a new model parameter α, formula defined in optimization algorithm areWherein α+It indicates
A new iteration of α,Indicate that square of euclideam norm, α here include that traffic events adapt to.Any event inspection
It surveys, as the quantization of capacity reduction, the additional constraint that can be used as α is added in equation.
Preferably, arterial highway signal coordination methodology described in step S400 includes unsaturated signal coordination methodology and supersaturation
Signal coordination methodology；
Wherein, unsaturated signal coordination methodology includes:
Situation and actual traffic situation is canalized according to the lane in each intersection arterial highway direction in step 1., determines its signal phase
Position allows set-up mode；
Step 2. allows set-up mode for the unlike signal phase of each intersection, logical meeting non-coordinating direction wagon flow
It is according to the principle that the intersection arterial highway total split of direction signal phase is constant, split more than needed is whole on row Demand Base
Distribute to coordination phase；
Step 3. principle constant according to link travel time makes this by converting some travel speed for coordinating direction
The spacing of equal value in direction is equal with opposite intersection spacing；
Step 4. takes its intersection as the common signal period according to the signal period value range of intersection each on arterial highway
Value optimize space；
Step 5. is derived for the unlike signal phase combination between benchmark intersection and other intersections using time space graph
Corresponding ideal intersection spacing out；
Step 6. determines the optimum signal phase set-up mode in arterial highway best common signal period and each intersection, makes to manage
Think that intersection position matches the most with practical intersection position；According to the signal phase set-up mode of each intersection, recently reason
Think intersection position and coordinate the split of direction clearance phase, determines the absolute phase difference of each intersection；
Step 7. is for some driving direction, according to the offset split of each intersection, calculates its green light center respectively
The top of time line and lower section split, therefrom select the minimum split of top with lower section, and addition obtains in the driving direction
Green wave band width.
Preferably, supersaturated signal coordination methodology step includes:
Step 1., which defines queue length according to different situations, influences coefficient:
Wherein it is divided into three kinds of situations:
(1) road environment locating for section uplink and downlink direction is to queue length without particular/special requirement；
(2) easily there is overflow phenomena in the downstream road section in section direction, and the queue length of the direction suitably increases will be advantageous
Overflow in downstream controls；
(3) section direction is equipped with the entrance of an important place, when the queuing vehicle of the direction is more than entrance position
When setting, entering and leaving vehicle need to be waited for parking until at queue clearance to entrance；
Therefore define section uplink and downlink and weight overall length Δ L, uplink and downlink total delay D has:
In formula:Dividing indicates uplink and downlink maximum queue length；
αu、αdRespectively indicate uplink and downlink queue length weighing factor, value rule are as follows: 1 is taken under situation (1), situation (2)
Lower combination is practical to be taken greater than 1 value, is combined and is actually taken less than 1 value under situation (3)；Du、DdRespectively indicate uplink and downlink delay；
Step 2. successively establishes offset optimization process using min Δ L and minD as target, carries out layering to phase difference and asks
Solution:
Step1 inputs upstream and downstream intersection signal parameter, traffic flow parameter, and according to section environmental characteristic, determines upper and lower
Row queue length weighing factor αu、αd；
Step2 enables phase differenceSentence a section initial period arrival wagon flow ownership, successively establishes queue length model, delay
Model；
Step3 is traversed using 1s as step-length using enumerative techniqueIt calculates simultaneously and stores Δ L, D under respective phase difference；
Step4 finds corresponding phase difference value range using min Δ L as first layer optimization aim, obtains effectively solving empty
Between；
Step5 is using minD as second layer optimization aim, and to obtain optimum angle poor in effective solution space for optimizing from upper one layer.
Preferably, traffic guidance algorithm described in step S500 includes:
The S510.MAP stage: Map function is by the Link Travel Time of corresponding subnet and intersection delay data and meter
Evaluation time range traverses the structure of figure according to level according to the principle of breadth First as input；Map function is according to each
The journey time and intersection delay data of period calculates the time for reaching next intersection, finally generates key/value shape
The median of formula；The key of median is the time for reaching intersection, and value is respectively intersection ID, forerunner intersection ID, arrives
Up to the time of forerunner intersection；
The S511.Reduce stage: all value with identical key value are gathered together and are passed to by HaLoop
Reduce function, Reduce function handle the value value set of the intersection with identical arrival time, generate new
Bucket；
The iteration of S512.HaLoop MapReduce: the output in each Reduce stage is again as the next round Map stage
Input, Job Server constantly start operation Map-Reduce task, complete all friendships that path is included by successive ignition
The calculating of prong；In an iterative process, the Master node machine of HaLoop is responsible for the loop control in Job, until iteration meter
Terminate.
A kind of control of vehicle low-carbon and inducible system based on big data comprising:
Data acquisition module, for being adopted by the various approach including different detection devices, mobile device, network
Collect traffic data；
Data processing module, the traffic data for being collected according to data acquisition module propose to be based on cloud computing skill
Art is accelerated the algorithm of data processing speed and is handled data；
Traffic circulation state module, for carrying out on-line data analysis according to data processing module treated data, point
Analysis obtains crossing, the road section traffic volume situation of different times；
Module is coordinated and optimized, for according to arterial highway signal coordination methodology, the online traffic signals of real-time control to realize arterial highway letter
Number coordination optimization.
Paths chosen module, for passing through the optimal trip route of traffic guidance algorithmic rule, final induction driver selection
Optimal path trip.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes approach described above of the present invention when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of approach described above of the present invention is realized when row.
Compared with prior art, the beneficial effect of technical solution of the present invention is:
The present invention acquires traffic data by approach such as different detection devices, mobile device, networks；According to collecting
Traffic data, propose based on cloud computing technology accelerate data processing speed algorithm simultaneously data are handled；To traffic number
According to on-line data analysis is carried out, crossing, the road section traffic volume situation of different times are analyzed；Arterial highway signal coordination and optimization is carried out, is realized
It is secondary to reduce parking in nearly saturation or saturation state by the traffic flow colleague that blocks by nothing when the flock-mate of road network arterial highway is through-flow unsaturated
The several and congestion time；And optimum path planning is carried out, induction driver selects optimal path trip, is intersecting to reduce vehicle
It the stop frequency of mouth and congestion time, solves the problems, such as that vehicle exhaust emissions amount caused by intersection increases, reduces vehicle
Energy consumption improves urban life environment and humanistic environment.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention.
Fig. 2 is the schematic diagram of mono- embodiment data of step S100 of the present invention acquisition.
Fig. 3 is the speed and discharge relation figure a of mono- embodiment of step S310 of the present invention.
Fig. 4 is the speed and discharge relation figure b of mono- embodiment of step S310 of the present invention.
Fig. 5 is mono- embodiment mean absolute error of step S310 of the present invention and actual flow comparison diagram a.
Fig. 6 is mono- embodiment mean absolute error of step S310 of the present invention and actual flow comparison diagram b.
Fig. 7 is mono- embodiment mean absolute error of step S310 of the present invention and actual flow comparison diagram c.
Fig. 8 is step S311 traffic state information estimation method schematic diagram of the present invention.
Fig. 9 is unsaturated signal coordination methodology flow chart in step S400 of the present invention.
Figure 10 is supersaturated signal coordination methodology flow chart in step S400 of the present invention.
Figure 11 is that traffic route induces algorithmic procedure a figure in step S500 of the present invention.
Figure 12 is that traffic route induces algorithmic procedure b figure in step S500 of the present invention.
Figure 13 is that traffic route induces algorithmic procedure c figure in step S500 of the present invention.
Figure 14 is the schematic diagram of one embodiment of the invention paths chosen.
Figure 15 is the structural block diagram of present system.
Figure 16 is computer installation structure chart block diagram of the present invention.
Specific embodiment
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent；
In order to better illustrate this embodiment, the certain components of attached drawing have omission, zoom in or out, and do not represent actual product
Size；
To those skilled in the art, it is to be understood that certain known features and its explanation, which may be omitted, in attached drawing
's.
The following further describes the technical solution of the present invention with reference to the accompanying drawings and examples.
The control of vehicle low-carbon and abductive approach that the present invention is to provide a kind of based on big data, include the following steps:
S100. traffic data is acquired by the various approach including different detection devices, mobile device, network；
S200. the traffic data collected according to S100 proposes to accelerate data processing speed based on cloud computing technology
Algorithm is simultaneously handled data；
S300. on-line data analysis is carried out according to S200 treated data, analysis obtains crossing, the section of different times
Traffic condition；
S400. according to arterial highway signal coordination methodology, the online traffic signals of real-time control realize arterial highway signal coordination and optimization；
S500. final that driver is induced to select optimal path trip by the optimal trip route of traffic guidance algorithmic rule.
Wherein, acquisition data described in step S100 are by including earth magnetism, coil, video, RFID, internet and movement
Detector including equipment carries out one or more data acquisition；For different acquisition approach, corresponding warp need to be only set
Degree and latitude.
As shown in Fig. 2, choosing Zhongshan city, the Guangdong province, China crossing Xing Zhongdao-Song Yuanlu in this example northing mouth 2017 years 1
Month 1~November 30, totally 334 days vehicle flowrate data, were divided into 1h between sample collection.Speed data comes from Amap, acquisition
Period is similarly on 1 day~November of January in 2017 30, and sample collection interval is also 1h, amounts to 8016 groups of data.
Wherein, step S200 is specifically included:
S210. the characteristic that the traffic data that S100 is acquired is calculated using Canopy clustering algorithm, it is same wherein having
The traffic data set of one characteristic is put into a subset, referred to as Canopy, and each Canopy regards a cluster as, is denoted as V, and will
They are put into set S；
S211. two points of clusters are carried out using K-means clustering algorithm in each Canopy: from the set S in S210
Each cluster is extracted in order, and the cluster of extraction will match with limit point criterion, then carry out two points with K-means clustering algorithm
Cluster, the smallest two clusters of error sum of squares in cluster is put back in set S, and circulation is executed until obtaining K cluster；Wherein K-
Means clustering algorithm is the classic algorithm of Data Clustering Algorithm, its core concept is: concentrating random take out from initial data first
It takes k number according to central point, and regards these points as initial cluster center；Secondly, calculating surrounding point around cluster centre arrives center
The distance of point.Finally, assigning data to cluster according to apart from the optimal cluster of this parameter selection, then distributing data point
To cluster, and repeat the process.It has used K-means algorithm to analyze S210 data in the present embodiment, and has utilized as follows
1 is defined, define 2 and defines 3 pairs of clusters and is analyzed；Wherein:
Define 1 (Canopy definition): data-oriented set U=ui| i=1,2,3 ... n, whereinMeetThen set xi, that is, it is classified as Canopy collection, T1Indicate Canopy diameter of a set, cjTable
Show Canopy central point.
Define 2 (SSEi): cluster CiSquare error and indicate that whole points in this cluster arrive the quadratic sums of the cluster centre distance,
Formula isciIt is cluster CiMass center.
Define 3 (limit point criterion): given clusterSo thatThen xp,xqIt is the limit point of cluster C, with xp,xqTwo o'clock is that cluster C initially gathers
Class center is limit point principle, dist (x in formulap,xq) indicate critical distance.
Data are carried out quickening processing by the data processing algorithm for S212. passing through S210 and S211.
Wherein, on-line data analysis described in step S300 includes:
S310. based on the carry out mid-term traffic flow forecasting for dividing hour built-up pattern:
Step 1: being screened according to Lay spy's criterion to the data；
Step 2: the data to screening carry out correlation analysis；As a whole, nearest a moment (2 hours with history
It is interior) demand positive correlation it is relatively high, more than 66%；
Step 3: carrying out Time segments division according to flow distribution, being divided into 24 periods for 24 hours one day；For each
Period studies the relationship of its flow and speed, i.e. Q-V model, is then predicted using ARIMA model the discharge in period of time；
Step 4: prediction result is combined by certain weight with the result of Q-V model, according to mean absolute error,
Three indexs of average absolute percentage error and mean square error compare final calculated result and actual flow.
Wherein, Lay spy criterion (i.e. 3 σ criterion) is that the method for exceptional value is differentiated in the case of a kind of normal distribution.Particular content
It is as follows: assuming that in a column equal precision measurement result, residual error corresponding to ith measurement valueAbsolute value meetThen the error is rough error, corresponding measured value xiFor abnormal numerical value, it should pick out and not have to.Wherein standard deviation
Estimation:
According to acquisition data as shown in Figure 2, correlation analysis is carried out, correlation analysis refers to be had to two or more
The variable element of correlation is analyzed, to measure the related intimate degree of two Variable Factors.Carry out the element of correlation
Between need that there are certain connection or probability can just carry out correlation analysis.As shown in table 1 below, d (w, m) represents w
The trip requirements total amount at its m-th of moment.If table 1 is data dependence analysis on 1 day~November 30 January in 2017 as a result, can
To find out:
Table 1
Within on the same day, flow and the historical time at current time are inversely proportional, and such as table 1, last is arranged, as a whole, with
The flow positive correlation of the nearest moment (in 1 hour) of history is relatively high, more than 0.8；And it is significant with data dependence earlier
Weaken, especially the correlation with the 5th hour drops to 0.112.
| Related coefficient | d(w,m) | d(w+1,m) | d(w+2,m) | d(w+3,m) | d(w+4,m) | d(w+5,m) | d(w+6,m) |
| d(w,m) | 1 | 0.906 | 0.875 | 0.869 | 0.866 | 0.865 | 0.788 |
| d(w+1,m) | 0.906 | 1 | 0.906 | 0.875 | 0.869 | 0.867 | 0.780 |
| d(w+2,m) | 0.875 | 0.906 | 1 | 0.906 | 0.875 | 0.869 | 0.780 |
| d(w+3,m) | 0.869 | 0.875 | 0.906 | 1 | 0.906 | 0.875 | 0.784 |
| d(w+4,m) | 0.866 | 0.869 | 0.875 | 0.906 | 1 | 0.906 | 0.788 |
| d(w+5,m) | 0.865 | 0.867 | 0.869 | 0.875 | 0.906 | 1 | 0.811 |
| d(w+6,m) | 0.788 | 0.780 | 0.780 | 0.784 | 0.788 | 0.811 | 1 |
Table 2
From Table 2, it can be seen that a phase in the same time in, it is workaday on the whole for the flow of history day in the same time
Flow phase relation is higher, minimum with Sunday correlation.But Saturday is more special, is higher than Sunday with workaday correlation, main
It is related for business unit's working more near the crossing.
Wherein, annual speed and data on flows are counted, the fast relational graph of stream-close-is as shown in Figure 3.Matched curve are as follows: Q=-
2.8324V2+148.88V-704.44R2=0.766；
24 periods were divided by whole day 24 hours, for each period, count the relationship of its average flow rate and speed.
Regulation " 0 point " represents 0:00:00~0:59:59, and " 1 point " represents 1:00:00~1:59:59, as shown in Figure 4.
According to variable correlation analysis it is found that the input variable of trip of taxi Demand Forecast Model should not be confined to work as
The demand at heavenly calendar prehistory several moment, and it is closer with the relationship of history day in the same time, and the present embodiment uses input parameter are as follows: 1.
Current date w；2. the period；3. nearest four historical juncture flows.
By taking 6 o'clock as an example, its rule is described.It is found that the relationship of speed and flow is as follows at 6 o'clock:
Q=0.1878V3-24.18V2+1036V-14529；
Prediction result index is as illustrated in figs. 5-7.It can be found that at 6 points, with the increase of weight coefficient α, wavelet neural
Combination of network model and BP neural network Combined model forecast precision improve, and ARIMA built-up pattern and Grey Combinatorial Model Method
Precision of prediction reduces, when α=1, i.e., only with Q-V model when, precision of prediction is between BP neural network built-up pattern and grey colour cell
Molding type.When α is identical, the precision of prediction of combination forecasting has high to Low are as follows: ARIMA (1,0,1) built-up pattern, grey colour cell
Molding type, BP neural network built-up pattern, wavelet neural network built-up pattern.
As described above, the model prediction accuracy of each period is ranked up in the α of equal weight,
A represents ARMIA combination forecasting, and B represents BP neural network combination forecasting, and G represents Grey Combination Forecast, W generation
Table wavelet neural network combination forecasting.Wherein precision of prediction from left to right successively reduces, model expression and front in bracket
Model prediction accuracy it is same or similar, can substitute.The results are shown in Table 3.
| Time | Preference pattern sequence | Time | Preference pattern sequence |
| 0 point | 1A(G)>2W>3B | 12 points | 1A>2W>3G>4B |
| 1 point | 1A>2G>3W>4B | 13 points | 1A>2W(G)>3B |
| 2 points | 1A(G)>2W>3B | 14 points | 1A(G/B)>2W |
| 3 points | 1B>2A(W)>3G | 15 points | 1A>2G>3B>4W |
| 4 points | 1A(G/B)>2W | 16 points | 1A>2G>3B>4W |
| 5 points | 1W>2A(G)>3B | 17 points | 1A>2G(B/W) |
| 6 points | 1A>2G>3B>4W | 18 points | 1A(W)>2G>3B |
| 7 points | 1A>2W>3B>4G | 19 points | 1A>2W>3G>4B |
| 8 points | 1A>2B>3G(W) | 20 points | 1A>2W>3G>4B |
| 9 points | 1G>2B(A)>3W | 21 points | 1A(W)>2G>3B |
| 10 points | 1A>2G>3B>4W | 22 points | 1A>2W>3G>4B |
| 11 points | 1A(B)>2G>3W | 23 points | 1A(G/W)>2B |
Table 3
By table 3 it can be found that in 24 periods, ARMIA combination forecasting achieves 21 first choices, and (13 unique first
Choosing plus 8 first choices arranged side by side), Grey Combination Forecast achieves 6 first choices (1 unique preferred plus 5 first choice arranged side by side), BP mind
4 first choices (1 unique preferred plus 3 first choice arranged side by side) are achieved through combination of network prediction model, wavelet neural network combination is pre-
Survey 4 first choices of model (1 unique preferred plus 3 first choice arranged side by side).And sort in terms of precision of prediction is worst, BP neural network
Combination forecasting 13 periods it is worst (including 12 it is worst and 1 side by side it is worst), wavelet neural network combined prediction mould
Type 10 periods it is worst (including 8 it is worst and 2 side by side it is worst), Grey Combination Forecast 3 periods it is worst (including
2 it is worst and 1 side by side it is worst), ARMIA combination forecasting is worst in 0 period.It can be seen that ARMIA combined prediction mould
The precision of type is higher, can be used for 87.5% prediction period, and the precision of prediction of two kinds of neural network ensemble models is lower.
Wherein, S311. estimates traffic state information based on the expanded Kalman filtration algorithm of expectation optimization；
Wherein expectation optimization algorithm is a kind of iterative solution algorithm for estimating model parameter α and known variables
Step 1: Y is sought, and α | X.Assuming that all model parameters are to estimate the traffic shape not observed in known situation
State solves Y | X, α, followed by Y to be found out | the accurate solution of X, α, and point out the limitation accurately solved, Accurate Reasoning is logical
The Bayesian Estimation realization of recursion is crossed, expands posterior probability density, and calculate in a recursive manner.Hypothetic observation is x, and
Hidden state is y, and state transformation is distributed such as formula p (y(t)y(t-1)), and observational networks such as formula p (x(t)|y(t)).After hidden state y
Face reasoning are as follows:
Use p (y(t-1)|x(1:t-1)) recursive resolve formula are as follows:
p(y(t)|x(1:t-1))=∫ p (y(t)|y(t-1)p(y(t-1)|x(1:t-1)))dy(t-1)；
Similarly, p (y(t)|x(1:t)) can be by such as formula p (y(t)|x(1:t))=Cp (x(t)|y(t))p(y(t)|x(1:t-1)) and C=
(∫p(x(t)|y(t))p(y(t)|x(1:t-1)dy(t))-1It finds out.
Step 2: seeking α | Y, X；Determine optimal model parameter α first, it is assumed that all traffic behaviors be it is known, this
It can be implemented as one simply to minimize the error；From parent map and link queue model, observation function h () and pseudo- sight are obtained
It surveys, calculation formula X-=h (Y)；Then, observation X and pseudo- observation X are reduced to the maximum extent+Between difference, obtain it is expected
The iteration of a new model parameter α, formula defined in optimization algorithm areWherein α+It indicates
A new iteration of α,Indicate that square of euclideam norm, α here include that traffic events adapt to.Any event inspection
It surveys, as the quantization of capacity reduction, the additional constraint that can be used as α is added in equation.
As shown in figure 8, all links are disposed as sky when starting, emulate duration T=1.05 (hour), between the time
Every Δ t=1.75 × 10-4(hour).Boundary condition is constant: the demand of origin is constant Do(t)=7020vph, and eventually
Point supply is also constant Sd(t)=2340vph.In addition, the parent map of link is free-stream velocity Ff=70mph, every road
The congestion index on road is J=125v/km, critical density dc=25v/km.Each of the links length Li=[1,1,1,1] km,
The number of track-lines of each of the links is ni=[3,1,2,1] km.Link 1 becomes link 2 and link 3 in intersection.In addition, in link 3
On have parking lot along the street, it can be increased or decreased by random number z~N (0,500) vph pours in link 3 flow.
In an initial condition, all links are empty.In link queue model, in a specific time step i, entirely
Road network has 4 traffic flow status variables.
Wherein, arterial highway signal coordination methodology described in step S400 includes unsaturated signal coordination methodology and supersaturation letter
Number coordination approach；
As shown in figure 9, unsaturated signal coordination methodology includes:
Situation and actual traffic situation is canalized according to the lane in each intersection arterial highway direction in step 1., determines its signal phase
Position allows set-up mode；
Step 2. allows set-up mode for the unlike signal phase of each intersection, logical meeting non-coordinating direction wagon flow
It is according to the principle that the intersection arterial highway total split of direction signal phase is constant, split more than needed is whole on row Demand Base
Distribute to coordination phase；
Step 3. principle constant according to link travel time makes this by converting some travel speed for coordinating direction
The spacing of equal value in direction is equal with opposite intersection spacing；
Step 4. takes its intersection as the common signal period according to the signal period value range of intersection each on arterial highway
Value optimize space；
Step 5. is derived for the unlike signal phase combination between benchmark intersection and other intersections using time space graph
Corresponding ideal intersection spacing out；
Step 6. determines the optimum signal phase set-up mode in arterial highway best common signal period and each intersection, makes to manage
Think that intersection position matches the most with practical intersection position；According to the signal phase set-up mode of each intersection, recently reason
Think intersection position and coordinate the split of direction clearance phase, determines the absolute phase difference of each intersection；
Step 7. is for some driving direction, according to the offset split of each intersection, calculates its green light center respectively
The top of time line and lower section split, therefrom select the minimum split of top with lower section, and addition obtains in the driving direction
Green wave band width.
Wherein, as shown in Figure 10, supersaturated signal coordination methodology step includes:
Step 1., which defines queue length according to different situations, influences coefficient:
Wherein it is divided into three kinds of situations:
(1) road environment locating for section uplink and downlink direction is to queue length without particular/special requirement；
(2) easily there is overflow phenomena in the downstream road section in section direction, and the queue length of the direction suitably increases will be advantageous
Overflow in downstream controls；
(3) section direction is equipped with the entrance of an important place, when the queuing vehicle of the direction is more than entrance position
When setting, entering and leaving vehicle need to be waited for parking until at queue clearance to entrance；
Therefore define section uplink and downlink and weight overall length Δ L, uplink and downlink total delay D has:
In formula:Dividing indicates uplink and downlink maximum queue length；
αu、αdRespectively indicate uplink and downlink queue length weighing factor, value rule are as follows: 1 is taken under situation (1), situation (2)
Lower combination is practical to be taken greater than 1 value, is combined and is actually taken less than 1 value under situation (3)；Du、DdRespectively indicate uplink and downlink delay；
Step 2. successively establishes offset optimization process using min Δ L and minD as target, carries out layering to phase difference and asks
Solution:
Step1 inputs upstream and downstream intersection signal parameter, traffic flow parameter, and according to section environmental characteristic, determines upper and lower
Row queue length weighing factor αu、αd；
Step2 enables phase differenceSentence a section initial period arrival wagon flow ownership, successively establishes queue length model, delay
Model；
Step3 is traversed using 1s as step-length using enumerative techniqueIt calculates simultaneously and stores Δ L, D under respective phase difference；
Step4 finds corresponding phase difference value range using min Δ L as first layer optimization aim, obtains effectively solving empty
Between；
Step5 is using minD as second layer optimization aim, and to obtain optimum angle poor in effective solution space for optimizing from upper one layer.
Wherein, traffic guidance algorithm described in step S500 includes:
The S510.MAP stage is as shown in figure 11: the Link Travel Time of corresponding subnet and intersection are delayed by Map function
Data and calculating time range traverse the structure of figure according to level according to the principle of breadth First as input；Map
Function calculates the time for reaching next intersection, finally generates according to the journey time and intersection delay data of each period
The median of key/value form；The key of median is the time for reaching intersection, and value is respectively intersection ID, forerunner
Intersection ID, the time for reaching forerunner intersection.
The S511.Reduce stage is as shown in figure 12: HaLoop gathers together all value with identical key value
Reduce function is passed to, Reduce function handles the value value set of the intersection with identical arrival time, produces
Raw new bucket, bucket list B are used to store intersection node to be accessed in different time nodes.
The iteration of S512.HaLoop MapReduce is as shown in figure 13: the output in each Reduce stage is again as next
The input in Map stage is taken turns, Job Server (JobTracker) constantly starting operation Map-Reduce task passes through successive ignition
Complete the calculating for all intersections that path is included；In an iterative process, the Master node machine of HaLoop is responsible in Job
Loop control, until iterative calculation terminate.
As shown in figure 14, this paths chosen embodiment is the conditions such as setting starting point, terminal, route, through the above steps
S500 method plans optimal trip route, realizes the paths chosen scheme from Guangzhou to Zhongshan city.
The present invention also provides a kind of systems applied to the method for the present invention, as shown in figure 15, comprising:
Data acquisition module 1, for passing through the various approach including different detection devices, mobile device, network
Acquire traffic data；The traffic data of acquisition include traffic behavior, traffic index, the magnitude of traffic flow, average speed, queue length,
Stop frequency, delay time at stop, saturation degree, hourage and record time etc. provide analysis and the prediction of traffic behavior completeer
Kind, accurate information；
Data processing module 2, for propose based on cloud computing technology accelerate data processing speed algorithm and to data into
Row processing.
Traffic circulation state module 3, for carrying out on-line data analysis according to treated the data of data processing module 2,
Analysis obtains crossing, the road section traffic volume situation of different times.It is different according to period of selection analysis, respectively with when, day, week, the moon,
The period in year carries out traffic state analysis, index analysis, flow analysis, velocity analysis, row to crossing, section, area data
Statistical chart is analyzed in the generations such as team's length analysis, stop frequency analysis, delay time at stop analysis, saturation analysis, hourage analysis,
The traffic condition of different times is intuitively shown to graphically.
Module 4 is coordinated and optimized, for realizing arterial highway letter by the online traffic signals of arterial highway signal coordination methodology real-time control
Number coordination optimization.Interface Controller crossing traffic signal controlling machine is issued by scheme, realizes that traffic flow is logical in the flock-mate of road network arterial highway
Block by nothing passage when stream unsaturation, in nearly saturation or saturation state, reduces stop frequency, shortens the congestion time.
Paths chosen module 5, for passing through the optimal trip route of traffic guidance algorithmic rule, final induction driver selection
Optimal path trip.
The present invention also provides a kind of computer equipment, computer equipment can be mobile terminal, desktop PC, notes
Originally, the computer equipments such as palm PC and server.It as shown in figure 16, is processor 10, the memory 20 in computer equipment
And display 30.Figure 16 illustrates only the members of computer equipment, it should be understood that being not required for implementing all show
Component out, the implementation that can be substituted is more or less component.
The memory 20 can be the internal storage unit of the computer equipment in some embodiments, such as calculate
The hard disk or memory of machine equipment.It deposits the outside that the memory 20 is also possible to the computer equipment in further embodiments
The plug-in type hard disk being equipped in storage equipment, such as the computer equipment, intelligent memory card (Smart Media Card, SMC),
Secure digital (Secure Digital, SD) card, flash card (Flash Card) etc..Further, the memory 20 may be used also
With the internal storage unit both including computer equipment or including External memory equipment.The memory 20 is installed on for storing
The application software and Various types of data of the computer equipment, such as the program code etc. of the installation computer equipment.It is described to deposit
Reservoir 20 can be also used for temporarily storing the data that has exported or will export.In one embodiment, on memory 20
The vehicle low-carbon control based on big data and induction program 40 are stored, the control of vehicle low-carbon and induction program based on big data are somebody's turn to do
40 can be performed by processor 10, to realize the list of videos switching method based on educational system of each embodiment of the application.
The processor 10 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), microprocessor or other data processing chips, for running the program code stored in the memory 20 or processing number
According to, such as execute the list of videos switching method etc. based on educational system.
The display 30 can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display in some embodiments
And OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) touches device etc..The display 30 is used
In the information for being shown in the computer equipment and for showing visual user interface.The component of the computer equipment
10-30 is in communication with each other by system bus.
The realization when processor 10 executes the control of the vehicle low-carbon in the memory 20 based on big data with induction program
Following steps:
S100. traffic data is acquired by the various approach including different detection devices, mobile device, network；
S200. the traffic data collected according to S100 proposes to accelerate data processing speed based on cloud computing technology
Algorithm is simultaneously handled data；
S300. on-line data analysis is carried out according to S200 treated data, analysis obtains crossing, the section of different times
Traffic condition；
S400. according to arterial highway signal coordination methodology, the online traffic signals of real-time control realize arterial highway signal coordination and optimization；
S500. final that driver is induced to select optimal path trip by the optimal trip route of traffic guidance algorithmic rule.
The present invention also provides a kind of computer readable storage medium, it is stored thereon with computer program described in computer program
The step of control of vehicle low-carbon and the abductive approach based on big data are realized when being executed by processor.
The terms describing the positional relationship in the drawings are only for illustration, should not be understood as the limitation to this patent；
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Made any modifications, equivalent replacements, and improvements etc., should be included in the claims in the present invention within the spirit and principle of invention
Protection scope within.
Claims (10)
1. a kind of control of vehicle low-carbon and abductive approach based on big data, which comprises the steps of:
S100. traffic data is acquired by the various approach including different detection devices, mobile device, network；
S200. the traffic data collected according to S100 proposes the algorithm for accelerating data processing speed based on cloud computing technology
And data are handled；
S300. on-line data analysis is carried out according to S200 treated data, analysis obtains crossing, the road section traffic volume of different times
Situation；
S400. according to arterial highway signal coordination methodology, the online traffic signals of real-time control realize arterial highway signal coordination and optimization；
S500. final that driver is induced to select optimal path trip by the optimal trip route of traffic guidance algorithmic rule.
2. the control of vehicle low-carbon and abductive approach according to claim 1 based on big data, which is characterized in that step
Acquisition data described in S100 pass through the detector including earth magnetism, coil, video, RFID, internet and mobile device
Carry out one or more data acquisition；For different acquisition approach, corresponding longitude and latitude need to be only set.
3. the control of vehicle low-carbon and abductive approach according to claim 1 based on big data, which is characterized in that step
S200 is specifically included:
S210. the characteristic that the traffic data that S100 is acquired is calculated using Canopy clustering algorithm, wherein with same spy
The traffic data set of property is put into a subset, and referred to as Canopy, each Canopy regard a cluster as, is denoted as V, and by they
It is put into set S；
S211. two points of clusters are carried out using K-means clustering algorithm in each Canopy: by suitable from the set S in S210
Sequence extracts each cluster, and the cluster of extraction will match with limit point criterion, then carries out two points with K-means clustering algorithm and gathers
Class is put back to the smallest two clusters of error sum of squares in cluster in set S, and circulation is executed until obtaining K cluster；
Data are carried out quickening processing by the data processing algorithm for S212. passing through S210 and S211.
4. the control of vehicle low-carbon and abductive approach according to claim 1 based on big data, which is characterized in that step
On-line data analysis described in S300 includes:
S310. it is based on that hour built-up pattern is divided to carry out mid-term traffic flow forecasting:
Step 1: being screened according to Lay spy's criterion to the data；
Step 2: the data to screening carry out correlation analysis；
Step 3: carrying out Time segments division according to flow distribution, being divided into 24 periods for 24 hours one day；For each period,
The relationship of its flow and speed, i.e. Q-V model are studied, then the discharge in period of time is predicted using ARIMA model；
Step 4: prediction result is combined by certain weight with the result of Q-V model, it is average according to mean absolute error
Three indexs of absolute percent error and mean square error compare final calculated result and actual flow；
S311. the expanded Kalman filtration algorithm based on expectation optimization estimates traffic state information:
Wherein expectation optimization algorithm is a kind of iterative solution algorithm for estimating model parameter α and known variables Y
Step 1: Y is sought, and α | X；Y is found out first | the accurate solution of X, α, and point out the limitation accurately solved, Accurate Reasoning is by passing
The Bayesian Estimation pushed away is realized, expands posterior probability density, and calculate in a recursive manner；Then it proposes a kind of using expansible
Kalman filtering algorithm is as a kind of substitution approximate solution；
Step 2: seeking α | Y, X；Determine optimal model parameter α first, it is assumed that all traffic behaviors be it is known, this can be with
It is embodied as one simply to minimize the error；From parent map and link queue model, observation function h () and pseudo- observation, meter are obtained
Calculation formula is X-=h (Y)；Then, observation X and pseudo- observation X are reduced to the maximum extent+Between difference, obtain expectation optimize calculate
The iteration of a new model parameter α, formula defined in method areWherein α+Indicate the one of α
A new iteration,Indicate that square of euclideam norm, α here include that traffic events adapt to.
5. the control of vehicle low-carbon and abductive approach according to claim 1 based on big data, which is characterized in that step
Arterial highway signal coordination methodology described in S400 includes unsaturated signal coordination methodology and supersaturated signal coordination methodology；
Wherein, unsaturated signal coordination methodology includes:
Situation and actual traffic situation is canalized according to the lane in each intersection arterial highway direction in step 1., determines that its signal phase is permitted
Perhaps set-up mode；
Step 2. allows set-up mode for the unlike signal phase of each intersection, is meeting the current need of non-coordinating direction wagon flow
On the basis of asking, according to the principle that the intersection arterial highway total split of direction signal phase is constant, split more than needed is all distributed
Give coordination phase；
Step 3. principle constant according to link travel time makes the direction by converting some travel speed for coordinating direction
Spacing of equal value it is equal with opposite intersection spacing；
Step 4. takes its intersection taking as the common signal period according to the signal period value range of intersection each on arterial highway
Value optimization space；
Step 5. derives phase using time space graph for the unlike signal phase combination between benchmark intersection and other intersections
The ideal intersection spacing answered；
Step 6. determines the optimum signal phase set-up mode in arterial highway best common signal period and each intersection, makes intersection of ideals
Prong position matches the most with practical intersection position；According to the signal phase set-up mode of each intersection, nearest intersection of ideals
Prong position and the split for coordinating direction clearance phase, determine the absolute phase difference of each intersection；
Step 7. is for some driving direction, according to the offset split of each intersection, calculates its green light central instant respectively
The top of line and lower section split, therefrom select the minimum split of top with lower section, and addition obtains green in the driving direction
Wavestrip width.
6. the control of vehicle low-carbon and abductive approach according to claim 5 based on big data, which is characterized in that supersaturation
Signal coordination methodology step includes:
Step 1., which defines queue length according to different situations, influences coefficient:
Wherein it is divided into three kinds of situations:
(1) road environment locating for section uplink and downlink direction is to queue length without particular/special requirement；
(2) easily there is overflow phenomena in the downstream road section in section direction, and the queue length of the direction, which suitably increases, to be beneficial to down
The overflow of trip controls；
(3) section direction is equipped with the entrance of an important place, when the queuing vehicle of the direction is more than entrance,
Entering and leaving vehicle need to wait for parking until at queue clearance to entrance；
Therefore define section uplink and downlink and weight overall length Δ L, uplink and downlink total delay D has:
In formula:Dividing indicates uplink and downlink maximum queue length；αu、αdRespectively indicating uplink and downlink queue length influences power
Weight, value rule are as follows: take 1 under situation (1), combine and actually taken greater than 1 value under situation (2), combined under situation (3) actually take it is small
In 1 value；Du、DdRespectively indicate uplink and downlink delay；
Step 2. successively establishes offset optimization process using min Δ L and minD as target, carries out hierarchical solving to phase difference:
Step1 inputs upstream and downstream intersection signal parameter, traffic flow parameter, and according to section environmental characteristic, determines that uplink and downlink are arranged
Team leader's degree weighing factor αu、αd；
Step2 enables phase differenceSentence a section initial period arrival wagon flow ownership, successively establishes queue length model, Delay Model；
Step3 is traversed using 1s as step-length using enumerative techniqueIt calculates simultaneously and stores Δ L, D under respective phase difference；
Step4 finds corresponding phase difference value range, obtains effective solution space using min Δ L as first layer optimization aim；
Step5 is using minD as second layer optimization aim, and to obtain optimum angle poor in effective solution space for optimizing from upper one layer.
7. the control of vehicle low-carbon and abductive approach according to claim 1 based on big data, which is characterized in that step
Traffic guidance algorithm described in S500 includes:
The S510.MAP stage: when Map function is by the Link Travel Time of corresponding subnet and intersection delay data and calculating
Between range as input, the structure of figure is traversed according to level according to the principle of breadth First；Map function is according to each time
The journey time and intersection delay data of section calculate the time for reaching next intersection, finally generate key/value form
Median；The key of median is the time for reaching intersection, before value is respectively intersection ID, forerunner intersection ID, arrival
Drive the time of intersection；
The S511.Reduce stage: all value with identical key value are gathered together and pass to Reduce letter by HaLoop
Number, Reduce function handle the value value set of the intersection with identical arrival time, generate new bucket；
The iteration of S512.HaLoop MapReduce: the output in each Reduce stage is again defeated as the next round Map stage
Enter, Job Server constantly starts operation Map-Reduce task, completes all intersections that path is included by successive ignition
The calculating of mouth；In an iterative process, the Master node machine of HaLoop is responsible for the loop control in Job, until iterative calculation
Terminate.
8. a kind of control of vehicle low-carbon and inducible system based on big data characterized by comprising
Data acquisition module is handed over for being acquired by the various approach including different detection devices, mobile device, network
Logical data；
Data processing module, the traffic data for being collected according to data acquisition module, proposition are added based on cloud computing technology
The algorithm of fast data processing speed is simultaneously handled data；
Traffic circulation state module is analyzed for carrying out on-line data analysis according to data processing module treated data
The crossing of different times, road section traffic volume situation out；
Module is coordinated and optimized, for according to arterial highway signal coordination methodology, the online traffic signals of real-time control to realize arterial highway signal association
Tuning；
Paths chosen module, for by the optimal trip route of traffic guidance algorithmic rule, final induction driver selection to be optimal
Path trip.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534976.1A CN109544929B (en) | 2018-12-14 | 2018-12-14 | Vehicle low-carbon control and induction method, system, equipment and storage medium based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534976.1A CN109544929B (en) | 2018-12-14 | 2018-12-14 | Vehicle low-carbon control and induction method, system, equipment and storage medium based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109544929A true CN109544929A (en) | 2019-03-29 |
| CN109544929B CN109544929B (en) | 2020-12-15 |
Family
ID=65856396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811534976.1A Active CN109544929B (en) | 2018-12-14 | 2018-12-14 | Vehicle low-carbon control and induction method, system, equipment and storage medium based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109544929B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517492A (en) * | 2019-08-27 | 2019-11-29 | 中国科学院自动化研究所 | Based on the traffic route recommended method of parallel integrated study, system, device |
| CN110634287A (en) * | 2019-08-26 | 2019-12-31 | 上海电科智能系统股份有限公司 | Urban traffic state refined discrimination method based on edge calculation |
| CN110969845A (en) * | 2019-11-19 | 2020-04-07 | 武汉理工大学 | Intelligent vehicle speed control method and system based on vehicle-road cooperation |
| CN111179586A (en) * | 2019-10-24 | 2020-05-19 | 广州市高科通信技术股份有限公司 | Traffic guidance method, equipment and storage medium based on big data analysis |
| CN111915887A (en) * | 2020-07-10 | 2020-11-10 | 广州运星科技有限公司 | Integration and processing system and method based on multi-source heterogeneous traffic data |
| CN111968383A (en) * | 2020-08-24 | 2020-11-20 | 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 realizing speed guidance of intersection by using electronic identification information of automobile |
| CN112233445A (en) * | 2020-09-28 | 2021-01-15 | 上海思寒环保科技有限公司 | Intelligent roadblock avoiding method and system |
| CN113299088A (en) * | 2021-05-06 | 2021-08-24 | 东南大学 | Regional multi-directional green wave design and driving speed guiding method based on Internet of vehicles |
| CN113411758A (en) * | 2020-03-16 | 2021-09-17 | 成都鼎桥通信技术有限公司 | Method and device for determining group call key event of private network cluster terminal |
| CN114333335A (en) * | 2022-03-15 | 2022-04-12 | 成都交大大数据科技有限公司 | Lane-level traffic state estimation method, device and system based on track data |
| CN116721545A (en) * | 2023-06-28 | 2023-09-08 | 东南大学 | Network-connected time-varying path control method based on traffic carbon emission reduction |
| CN117455087A (en) * | 2023-10-25 | 2024-01-26 | 南京迅集科技有限公司 | Logistics energy-saving control method and system based on Internet of things |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101383091A (en) * | 2008-10-14 | 2009-03-11 | 北京交通大学 | Network control system for traffic induction outdoor screen |
| US20090167562A1 (en) * | 2007-12-26 | 2009-07-02 | Aochengtongli S&T Development ( Beijing ) Co., Ltd | Traffic light control system for a high flow intersection |
| CN101571997A (en) * | 2009-05-31 | 2009-11-04 | 上海宝康电子控制工程有限公司 | Method and device for fusion processing of multi-source traffic information |
| CN102509470A (en) * | 2011-10-14 | 2012-06-20 | 北京掌城科技有限公司 | System and method for realizing energy conservation and emission reduction of vehicle based on dynamic path planning |
| CN103559797A (en) * | 2013-10-21 | 2014-02-05 | 华南理工大学 | Universal phase position type artery two-way green wave coordination control method |
| CN104157151A (en) * | 2014-06-13 | 2014-11-19 | 东南大学 | Method and system for cooperation of city traffic guidance and signal control |
| CN105206053A (en) * | 2015-09-21 | 2015-12-30 | 河海大学常州校区 | Road comprehensive information processing system and method based on technology of Internet of vehicles |
| CN105702029A (en) * | 2016-02-22 | 2016-06-22 | 北京航空航天大学 | Express way traffic state prediction method taking spatial-temporal correlation into account at different times |
| CN105865476A (en) * | 2016-06-21 | 2016-08-17 | 北京航空航天大学 | Method for searching lowest carbon path of automobile under dynamic traffic environment |
| CN107742420A (en) * | 2017-09-22 | 2018-02-27 | 北京交通大学 | It is a kind of to be used for the method that road traffic flow is predicted under emergent traffic incident |
| CN108269401A (en) * | 2018-01-30 | 2018-07-10 | 银江股份有限公司 | A kind of overpass traffic congestion Forecasting Methodology based on data-driven |
-
2018
- 2018-12-14 CN CN201811534976.1A patent/CN109544929B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090167562A1 (en) * | 2007-12-26 | 2009-07-02 | Aochengtongli S&T Development ( Beijing ) Co., Ltd | Traffic light control system for a high flow intersection |
| CN101383091A (en) * | 2008-10-14 | 2009-03-11 | 北京交通大学 | Network control system for traffic induction outdoor screen |
| CN101571997A (en) * | 2009-05-31 | 2009-11-04 | 上海宝康电子控制工程有限公司 | Method and device for fusion processing of multi-source traffic information |
| CN102509470A (en) * | 2011-10-14 | 2012-06-20 | 北京掌城科技有限公司 | System and method for realizing energy conservation and emission reduction of vehicle based on dynamic path planning |
| CN103559797A (en) * | 2013-10-21 | 2014-02-05 | 华南理工大学 | Universal phase position type artery two-way green wave coordination control method |
| CN104157151A (en) * | 2014-06-13 | 2014-11-19 | 东南大学 | Method and system for cooperation of city traffic guidance and signal control |
| CN105206053A (en) * | 2015-09-21 | 2015-12-30 | 河海大学常州校区 | Road comprehensive information processing system and method based on technology of Internet of vehicles |
| CN105702029A (en) * | 2016-02-22 | 2016-06-22 | 北京航空航天大学 | Express way traffic state prediction method taking spatial-temporal correlation into account at different times |
| CN105865476A (en) * | 2016-06-21 | 2016-08-17 | 北京航空航天大学 | Method for searching lowest carbon path of automobile under dynamic traffic environment |
| CN107742420A (en) * | 2017-09-22 | 2018-02-27 | 北京交通大学 | It is a kind of to be used for the method that road traffic flow is predicted under emergent traffic incident |
| CN108269401A (en) * | 2018-01-30 | 2018-07-10 | 银江股份有限公司 | A kind of overpass traffic congestion Forecasting Methodology based on data-driven |
Non-Patent Citations (6)
| Title |
|---|
| FIAMMAPEREZ-PRADA: "Ex-post environmental and traffic assessment of a speed reduction strategy in Madrid"s inner ring-road", 《JOURNAL OF TRANSPORT GEOGRAPHY》 * |
| 张亚茹: "基于车联网大数据分析的实时路况信息系统关键技术研究", 《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》 * |
| 徐建闽、王钰、林培群: "大数据环境下的动态最短路径算法", 《华南理工大学学报(自然科学版)》 * |
| 李应安: "基于MapReduce的聚类算法的并行化研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 邱荣太: "基于Hadoop平台的Map_Reduce应用研究", 《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》 * |
| 马旭辉: "城市道路交通网络过饱和状态信号控制方法研究", 《中国博士学位论文全文数据库（工程科技Ⅱ辑）》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021036278A1 (en) * | 2019-08-26 | 2021-03-04 | 上海电科智能系统股份有限公司 | Edge computing-based fine determination method for urban traffic state |
| CN110634287A (en) * | 2019-08-26 | 2019-12-31 | 上海电科智能系统股份有限公司 | Urban traffic state refined discrimination method based on edge calculation |
| US11361658B1 (en) | 2019-08-26 | 2022-06-14 | Shanghai Seari Intelligent System Co., Ltd. | Edge computing-based method for fine determination of urban traffic state |
| CN110634287B (en) * | 2019-08-26 | 2021-08-17 | 上海电科智能系统股份有限公司 | Urban traffic state refined discrimination method based on edge calculation |
| CN110517492A (en) * | 2019-08-27 | 2019-11-29 | 中国科学院自动化研究所 | Based on the traffic route recommended method of parallel integrated study, system, device |
| CN111179586A (en) * | 2019-10-24 | 2020-05-19 | 广州市高科通信技术股份有限公司 | Traffic guidance method, equipment and storage medium based on big data analysis |
| CN110969845A (en) * | 2019-11-19 | 2020-04-07 | 武汉理工大学 | Intelligent vehicle speed control method and system based on vehicle-road cooperation |
| CN113411758B (en) * | 2020-03-16 | 2022-08-09 | 成都鼎桥通信技术有限公司 | Method and device for determining group call key event of private network cluster terminal |
| CN113411758A (en) * | 2020-03-16 | 2021-09-17 | 成都鼎桥通信技术有限公司 | Method and device for determining group call key event of private network cluster terminal |
| CN111915887A (en) * | 2020-07-10 | 2020-11-10 | 广州运星科技有限公司 | Integration and processing system and method based on multi-source heterogeneous traffic data |
| CN111968383A (en) * | 2020-08-24 | 2020-11-20 | 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 realizing speed guidance of intersection by using electronic identification information of automobile |
| CN112233445A (en) * | 2020-09-28 | 2021-01-15 | 上海思寒环保科技有限公司 | Intelligent roadblock avoiding method and system |
| CN112233445B (en) * | 2020-09-28 | 2022-03-01 | 上海思寒环保科技有限公司 | Intelligent roadblock avoiding method and system |
| CN113299088A (en) * | 2021-05-06 | 2021-08-24 | 东南大学 | Regional multi-directional green wave design and driving speed guiding method based on Internet of vehicles |
| CN113299088B (en) * | 2021-05-06 | 2022-03-11 | 东南大学 | Regional multi-directional green wave design and driving speed guiding method based on Internet of vehicles |
| CN114333335A (en) * | 2022-03-15 | 2022-04-12 | 成都交大大数据科技有限公司 | Lane-level traffic state estimation method, device and system based on track data |
| CN116721545A (en) * | 2023-06-28 | 2023-09-08 | 东南大学 | Network-connected time-varying path control method based on traffic carbon emission reduction |
| CN116721545B (en) * | 2023-06-28 | 2024-05-28 | 东南大学 | Network-connected time-varying path control method based on traffic carbon emission reduction |
| CN117455087A (en) * | 2023-10-25 | 2024-01-26 | 南京迅集科技有限公司 | Logistics energy-saving control method and system based on Internet of things |
| CN117455087B (en) * | 2023-10-25 | 2024-04-12 | 南京迅集科技有限公司 | Logistics energy-saving control method and system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109544929B (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544929A (en) | A kind of control of vehicle low-carbon and abductive approach, system, equipment and storage medium based on big data | |
| Yao et al. | Short‐term traffic speed prediction for an urban corridor | |
| Wu et al. | Simulation-based robust optimization of limited-stop bus service with vehicle overtaking and dynamics: A response surface methodology | |
| Jindal et al. | Optimizing taxi carpool policies via reinforcement learning and spatio-temporal mining | |
| CN104183119B (en) | Based on the anti-arithmetic for real-time traffic flow distribution forecasting method pushed away of section OD | |
| Gong et al. | Train timetabling with dynamic and random passenger demand: A stochastic optimization method | |
| CN101325004B (en) | Method for compensating real time traffic information data | |
| CN104157139B (en) | A kind of traffic congestion Forecasting Methodology and method for visualizing | |
| Zhou et al. | Optimizing taxi driver profit efficiency: A spatial network-based markov decision process approach | |
| CN100444210C (en) | Mixed controlling method of single dot signal controlling crossing | |
| CN107919014B (en) | Taxi running route optimization method for multiple passenger mileage | |
| Ding et al. | Hunts: A trajectory recommendation system for effective and efficient hunting of taxi passengers | |
| He et al. | Vehicle scheduling under stochastic trip times: An approximate dynamic programming approach | |
| CN110390349A (en) | Bus passenger flow volume based on XGBoost model predicts modeling method | |
| Ionita et al. | Where to park? predicting free parking spots in unmonitored city areas | |
| CN112489426A (en) | Urban traffic flow space-time prediction scheme based on graph convolution neural network | |
| Tang et al. | Online operations of automated electric taxi fleets: An advisor-student reinforcement learning framework | |
| Wu et al. | Predicting peak load of bus routes with supply optimization and scaled Shepard interpolation: A newsvendor model | |
| CN115409256A (en) | Route recommendation method for congestion area avoidance based on travel time prediction | |
| Chang et al. | A cooperative strategy for optimizing vehicle relocations and staff movements in cities where several carsharing companies operate simultaneously | |
| Banerjee et al. | An intelligent hybrid scheme for optimizing parking space: A Tabu metaphor and rough set based approach | |
| Zhang et al. | Travel time prediction of urban public transportation based on detection of single routes | |
| CN110490365B (en) | Method for predicting network car booking order quantity based on multi-source data fusion | |
| Zheng et al. | A novel approach to coordinating green wave system with adaptation evolutionary strategy | |
| Xia et al. | A distributed EMDN-GRU model on Spark for passenger waiting time forecasting |
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 |