CN107153896A - Traffic network path prediction method and system based on node pair entropy - Google Patents
Traffic network path prediction method and system based on node pair entropy Download PDFInfo
- Publication number
- CN107153896A CN107153896A CN201710535258.5A CN201710535258A CN107153896A CN 107153896 A CN107153896 A CN 107153896A CN 201710535258 A CN201710535258 A CN 201710535258A CN 107153896 A CN107153896 A CN 107153896A
- Authority
- CN
- China
- Prior art keywords
- node
- value
- flow
- surveyed
- probability
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000005540 biological transmission Effects 0.000 claims abstract description 32
- 238000011144 upstream manufacturing Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000002834 transmittance Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000007717 exclusion Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G06Q50/40—
-
- 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
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- 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
Abstract
The invention provides a method and a system for predicting paths in a traffic network, wherein the method determines the uncertainty of each node and the uncertainty of the flow transmission of each path by measuring and calculating the influence caused by the layer-by-layer propagation of the flow between any node pair in the traffic network. Meanwhile, the invention also introduces the physical quantity of the information entropy, and further determines the degree of influence of the uncertainty of the traffic information transmission on the nodes, namely the node pair entropy. By applying the method, all node pair entropies of the whole traffic network can form a completely connected network, thereby realizing the prediction of paths in the traffic network and providing a basis for further realizing a more optimized traffic network.
Description
Technical field
Field, more particularly to a kind of traffic based on node to entropy are predicted the present invention relates to urban road traffic network path
Networking footpath Forecasting Methodology.
Background technology
Path prediction in transportation network suffers from the status that can not ignore in the planning and management and control of municipal road network, with
It is that probabilistic model is set up according to historical data mostly into traffic route forecasting research.Short distance is divided into according to Prediction distance difference
Predicted from prediction and long range, the prediction of its short-distance and medium-distance can be influenceed by road direction;The prediction of long range travel route is difficult to solve
Variation route problem, the path Forecasting Methodology based on correlation rule is had also been proposed based on this theoretical foundation in recent years.These methods
It can more or less be limited by scale, more systematic method is not suggested yet.
The content of the invention
Instant invention overcomes the shadow that the urban highway traffic path Forecasting Methodology of current generally existing is limited by road network scale
Ring there is provided a kind of based on path Forecasting Methodology of the network of communication lines node to entropy, this method passes through to arbitrary node in transportation network
The measuring and calculating of influence caused by flow is successively propagated between, to determine the uncertain and each paths flow of each node
The uncertainty of transmission.Simultaneously present invention further introduces this physical quantity of comentropy, flow information transmission further determined that
Uncertainty node is brought effect --- node is to entropy.Using all nodes pair of the whole transportation network of this method
Entropy can be formed by a network being fully connected, it is achieved thereby that in transportation network path prediction, be further realize more
The transportation network of optimization provides basis.
The present invention specifically uses following technical scheme:
The system includes dynamic road network modeling module, according to traffic sub-district road network topology data and real-time dynamic traffic fluxion
According to it is point, road as the Model of dynamic transportation network of side, flow for weights to set up using crossing;Path flow indeterminacy of calculation module,
Extract with all nodes of flow transmission and corresponding side occur between required node pair, a new subnet is constituted, to node
Original state assignment, and by calculate downstream node each layer transmission flow value, calculate each layer of middle and upper reaches node
Flow is transmitted to the probability of downstream node and the contribution probability of node, start node is finally calculated to all roads of destination node
Transmit the probability of flow value in footpath;Node enters walking along the street with node to entropy to entropy and path prediction module, calculate node to the value of entropy
Predict in footpath;If node is bigger to entropy, path is more unimpeded between two nodes, if node is smaller to entropy, path between two nodes
It is more crowded.
This method takes following steps successively:
1) the original state assignment of start node is given, the state value of start node exports weights sum for its downstream, other
The state value of node is 0, and then start node carries out flow transmission toward downstream;
2) when flow is delivered to surveyed node, judge whether the weights sum on the surveyed all sides in node downstream is not more than institute
The output weights of node are surveyed, if being not more than, downstream side is equal to the power on all sides in downstream in the flow value that surveyed node layer is transmitted
It is worth sum;If being more than, maximum side right is cut successively with all side right value sums in surveyed node downstream and is worth to correction value, when repairing
Stop calculating when being not more than and surveying the output weights of node, then downstream side is equal to most in the flow value that surveyed node layer is transmitted
The correction value once obtained afterwards;
3) judgment step 2) in the downstream node that calculates in the flow value that surveyed node layer is transmitted whether be 0;If not 0,
Then enter step 4);If 0, then into step 9);
4) calculate upstream node and survey value of feedback of the node in the presence of the transmission of surveyed node layer flow;Upstream node
Value of feedback subtract the state value of loss for the state value of upstream node, survey the value of feedback of node by survey node state value
Plus the state value of the loss;Using the value of feedback of upstream node as the new state value of upstream node, by the feedback of surveyed node
Value is used as the new state value of surveyed node;
5) probability of the upstream node transmission flow to downstream node is calculated;
If 6) surveyed node is present in single-pathway, into step 7);If surveyed node is present in different branch paths
In footpath, then into step 8);
7) probability that path flows through surveyed node is:Each upstream node is delivered to the product of downstream node probability;Into
Step 9);
8) probability that path flows through surveyed node is:Each upstream node is delivered to downstream node probability in one paths
Product flows through the probability to surveyed node plus other individual paths;Into step 9);
9) represent to judge whether surveyed node is terminal node, if not then continuation return to step 2) next layer general of calculating
Rate;If so, then outgoing route flow to the probability of terminal node;Into step 10);
10) according to H (vivj)=- ∑ Plln PlCalculate node is to entropy, wherein H (vivj) represent node to entropy, PlRepresent road
Footpath l flow to the probability of terminal node.
The node is described as follows to entropy and path prediction module:
The process that the present invention can to downstream node transmit node weights is depicted as the process that primary information is interacted, and also may be used
Great influence is applied with downstream node to be interpreted as upstream node, in order to which the influence present invention for quantifying this transmission is proposed
The concept of entropy.Comentropy is used for the uncertainty degree for representing information source transmission, and this is with being consistent herein, and node is used to represent to entropy
The uncertainty degree that transmittance process interior joint is transmitted to other nodes each time.For any two node in road network,
It is uncertain bigger if their node is bigger to entropy, then illustrate the easier transmission for occurring information between them, therefore can
To understand that path is more crowded between 2 points, entropy is smaller, more unimpeded, and entropy is bigger.This method neither by direction influenceed and also by
The influence of newly-increased route.
The present invention has the advantages that:
(1) present invention is not influenceed by road network scale;
(2) present invention is on the uncertain method for calculating each path transmission flow, and application traffic is transmitted to node step by step
Influence additive calculating, taken into full account percentage contribution of each node to downstream node;
(3) each paths indeterminacy of calculation of the invention can effectively and accurately reflect shadow of each paths to whole subnet
The degree of sound;
(4) present invention has taken into full account whole road network structure characteristic, eliminate with want calculate node to unrelated node and
Respective stretch, makes result more accurate;
(5) invention introduces node to entropy, each paths transmit flow between more precisely illustrating node pair
Ability is to node to the effect brought.
Brief description of the drawings:
Fig. 1 is the inventive method broad flow diagram.
Fig. 2 is flow rate calculation flow chart.
Fig. 3 is each paths indeterminacy of calculation flow chart between node.
Embodiment:
The present invention is described in further detail with embodiment below in conjunction with the accompanying drawings.
Reference picture 1, based on network of communication lines path Forecasting Methodology of the node to entropy, is broadly divided into three levels:Dynamic road network is built
Mould module 102, node are to the indeterminacy of calculation modules 103 of each paths, node to entropy and path prediction module 104.Three
Part provides platform for node with supporting relation, i.e. Model of dynamic transportation network step by step to the indeterminacy of calculation of each paths, saves
Point predicts the data that provide the foundation for node to the uncertainty of each paths to entropy and path.
Dynamic road network modeling module, according to traffic sub-district road network topology data and real-time dynamic traffic flow data, set up with
Crossing is point, the Model of dynamic transportation network that road is side, flow is weights;Each paths flow through flow uncertainty between node pair
Computing module, extracts with all nodes of flow transmission and corresponding side occur between required node pair, constitutes a new son
Net, to the original state assignment of node, then by calculating flow value of the downstream node in each layer of transmission, is released in each layer
Upstream node transmits probability of the corresponding discharge to downstream node, and node contribution probability, and then draw start node to end
Transmit the probability of respective streams value in all paths of node;Node is to entropy and path prediction module, according to the thing of shannon entropy
Reason meaning infers the required node of the present invention to entropy, and path prediction is carried out to the value of entropy with node.
The dynamic road network modeling module is described as follows:
Any one urban road traffic network may be described as following form:
TN=(N, E, W),
Wherein, TN is the transportation network to be modeled, N={ n1,n2,…,npIt is that (p is node to the set of transportation network interior joint
Number), E={ e1,e2,…,eqBe side in transportation network set (q is road way), weights W is defined as the flow on section.
Interior joint of the present invention is entropy for the correlation statistics network interior joint.Due to nodes and node it
Between have information transmission, this make it that downstream node is bound to receive at any one time the influence of its upstream node, even if therefore not
Certain correlation is also had between two adjacent nodes.
It is to be noted that the path of the present invention is the process that a flow spreads.
The node of the present invention is to entropy:
H(vivj)=- ∑ Plln Pl
Wherein H (vivj) represent node to entropy, PlRepresent path l in node to the percentage contribution in flow transmittance process, i.e.,
Each paths flow through flow probability between node pair in the present invention.
Each paths flow through the uncertain module of flow and are described as follows between the node pair:
Mi(v):State value of the v points at i layers
Ni(e):The flow that e is crossed in i laminar flows
Wi(e):Weights of the e sides at i-th layer
(1) the original state assignment of node is given.
For the state value M of start node0(v) it is its downstream side right Wi (e) summation, the state value of remaining each node is
It is empty.
(2) flow value of the downstream node in each layer of transmission is calculated.
From the off, Ni (e) weights are transmitted to its downstream node successively.
1. when downstream side right is met:∑w(e)≤Mi-1(Va) when, Ni(e)=w (e)
2. be unsatisfactory for, ∑ w (e) subtracts the w (e) of maximum successively, until ∑ w (e)≤Mi-1(Va), Ni(e)=w (e);
3. when the critical edge in 2 includes the node of upstream node each other, preferentially distribute to such side.
If not including, the equal any a line of minimum value in the side being subtracted, the flow that this edge passes through are randomly selected
It is expressed as Ni(e)=Mi-1(Va)-∑ w (e), remaining side is 0.
4. often transmitting once, the state value of upstream node accordingly reduces loss value, and the state value of downstream node is accordingly added
This loss value, transfer mode is parallel transmission.
The state value of remaining non-present search node is its state value in previous step
(3) probability of each layer of middle and upper reaches node transmission corresponding discharge to downstream node.
(4) the contribution probability of node.
The influence of same layer transmission is separate, and the influence of the same node transmission in different layers is mutual exclusion, because
And if node has transmission on upper strata, the influence to surveyed node layer is cumulative
(5) start node transmits the probability of respective streams value to each path of destination node.
According to the superposition for the product that the l probability transmitted is each layer probability transmitted along the chain.Decision node is upper in transmittance process
Whether other branches of layer are searched, if be searched, due to being mutual exclusion between each branch, then be delivered to this node
Probability should be other branches on upper strata and search the probability of the point and this branch searches the probability sum of the point.
Reference picture 2, flow rate calculation flow chart is the downstream side in each paths indeterminacy of calculation flow chart between Fig. 3 nodes
The refinement of the flow 302 transmitted in surveyed node layer.301 after original state assignment, first have to judge that initial point downstream owns
Whether the weights sum on side is not more than the initial state value 201 of initial point, if being not more than, downstream side is transmitted in surveyed node layer
Flow value be equal to the weights 203 on side;If being more than, need with all side right values and cut maximum side right successively and be worth to amendment
Value, untill this result is not more than the state value of start node, this part of the state value for being not more than start node
The present invention carrys out assignment according to 203, is then assigned to last time with initial state value and the difference of the last maximum cut successively
The correction value 205 that the side cut is obtained.Therefore 203 and 205 be exactly the of the invention downstream node finally wanted in surveyed node layer
The flow value 206 of transmission.
The uncertain probability calculation flow of each paths between reference picture 3, node, 301 are represented to surveyed node to initial shape
State assignment, wherein the node to be surveyed is start node or terminal node, the state value of start node for its downstream output weights it
It is 0 with, other nodes;The flow that 302 expression downstream nodes are transmitted in surveyed node layer, is described in detail in figure two;
303 represent to judge whether flow value is 0;If not 0, then need calculating 304,304 to represent upstream and downstream node in surveyed node laminar flow
Value of feedback in the presence of amount transmission;The ratio that each branch flow of node layer and upstream node state value are surveyed by calculating is drawn
Probability of the downstream in this layer of transmission is swum in 305,305 one branch of expression;This hair before the probability of a paths is calculated
Bright to need to calculate the probability for flowing through this node, 306 represent decision node with the presence or absence of (i.e. node is upper in single-pathway
Whether other branches of layer are searched), because the transmission of each paths is transmitted parallel, therefore it is separate each other
, but being transmitted each time for node is once influenceed in application, therefore the shadow that same node is subject in different branches
Sound is mutual exclusive.If therefore node is existed only in single-pathway and (is not searched), 307 are calculated, i.e. the paths
The probability 309 for flowing through this node is the continued product in each stage, is 307 and 308 result;If node is also present in other roads
(be searched) in footpath, then the paths flow through this node probability 307 also needed on the basis of 308 plus upper strata its
His branch flows through the probability of this node.3010 represent judge whether it is start node or terminal node, if not then continuing
Return to 302 probability for calculating next layer;If so, then exporting the probability of the paths, and return to start node progress next round
301 are calculated, until all downstream flows are 0, process exports the probability 3012 in all paths untill not gone down, and leads to
Computational methods of the node to entropy are crossed, final uncertainty degree is calculated.
It is uncertain bigger if their node is bigger to entropy for any two node in road network, then say
The bright transmission for occurring information easier between them, it is therefore to be understood that path is more crowded between 2 points, entropy is smaller, more smooth
Logical, entropy is bigger.This method is neither influenceed by direction nor influenceed by newly-increased route.Using the whole transportation network of this method
All nodes can be formed by a network being fully connected to entropy, it is achieved thereby that in transportation network path prediction, to enter
One step realizes that the transportation network more optimized provides basis.
Claims (2)
1. it is a kind of based on network of communication lines path forecasting system of the node to entropy, it is characterised in that the system includes
Dynamic road network modeling module, according to traffic sub-district road network topology data and real-time dynamic traffic flow data, sets up with crossing
For the Model of dynamic transportation network that point, road are side, flow is weights;
Path flow indeterminacy of calculation module, is extracted to all nodes and corresponding of flow transmission occur between required node pair
Side, constitute a new subnet, to the original state assignment of node, and by calculate downstream node each layer transmission stream
Value, calculates each layer of middle and upper reaches node and transmits flow to the probability of downstream node and the contribution probability of node, finally count
Calculate the probability that start node transmits flow value to all paths of destination node;
Node carries out path prediction with node to entropy to entropy and path prediction module, calculate node to the value of entropy;If node pair
Entropy is bigger, then path is more unimpeded between two nodes, if node is smaller to entropy, and path is more crowded between two nodes.
2. a kind of application is as claimed in claim 2 based on method of the node to the network of communication lines path forecasting system of entropy, its feature
It is, this method takes following steps successively:
1) the original state assignment of start node is given, the state value of start node exports weights sum, other nodes for its downstream
State value be 0, then start node toward downstream carry out flow transmission;
2) when flow is delivered to surveyed node, judge whether the weights sum on the surveyed all sides in node downstream is not more than and survey section
The output weights of point, if being not more than, the flow value that downstream side is transmitted in surveyed node layer equal to all sides in downstream weights it
With;If being more than, maximum side right is cut successively with all side right value sums in surveyed node downstream and is worth to correction value, works as correction value
Stop calculating during the output weights of no more than surveyed node, then downstream side is equal to last in the flow value that surveyed node layer is transmitted
Secondary obtained correction value;
3) judgment step 2) in the downstream node that calculates in the flow value that surveyed node layer is transmitted whether be 0;If not 0, then enter
Enter step 4);If 0, then into step 9);
4) calculate upstream node and survey value of feedback of the node in the presence of the transmission of surveyed node layer flow;Upstream node it is anti-
Feedback value subtracts the state value of loss for the state value of upstream node, survey the value of feedback of node by the state value of survey node add
The state value of the loss;Using the value of feedback of upstream node as the new state value of upstream node, by the value of feedback of surveyed node
It is used as the new state value of surveyed node;
5) probability of the upstream node transmission flow to downstream node is calculated;
If 6) surveyed node is present in single-pathway, into step 7);If surveyed node is present in different individual paths,
Then enter step 8);
7) probability that path flows through surveyed node is:Each upstream node is delivered to the product of downstream node probability;Into step
9);
8) probability that path flows through surveyed node is:Each upstream node is delivered to the product of downstream node probability in one paths
The probability to surveyed node is flowed through plus other individual paths;Into step 9);
9) represent to judge whether surveyed node is terminal node, if not then continuation return to step 2) next layer of probability of calculating;
If so, then outgoing route flow to the probability of terminal node;Into step 10);
10) according to H (vivj)=- ∑ PllnPlCalculate node is to entropy, wherein H (vivj) represent node to entropy, PlRepresent path l streams
To the probability of terminal node.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710535258.5A CN107153896A (en) | 2017-07-03 | 2017-07-03 | Traffic network path prediction method and system based on node pair entropy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710535258.5A CN107153896A (en) | 2017-07-03 | 2017-07-03 | Traffic network path prediction method and system based on node pair entropy |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107153896A true CN107153896A (en) | 2017-09-12 |
Family
ID=59795474
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710535258.5A Pending CN107153896A (en) | 2017-07-03 | 2017-07-03 | Traffic network path prediction method and system based on node pair entropy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107153896A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109064750A (en) * | 2018-09-28 | 2018-12-21 | 深圳大学 | Urban road network traffic estimation method and system |
CN110444009A (en) * | 2018-05-02 | 2019-11-12 | 芝麻开门网络信息股份有限公司 | A kind of expressway wagon flow forecasting system based on Internet of Things |
CN110444010A (en) * | 2018-05-02 | 2019-11-12 | 芝麻开门网络信息股份有限公司 | A kind of expressway wagon flow prediction technique based on Internet of Things |
CN111814605A (en) * | 2020-06-23 | 2020-10-23 | 浙江大华技术股份有限公司 | Main road identification method, main road identification device and main road storage device based on topological map |
CN113903171A (en) * | 2021-09-27 | 2022-01-07 | 北京航空航天大学 | Vehicle crowd sensing node optimization method based on spatial-temporal characteristics of highway network |
CN114639235A (en) * | 2020-12-16 | 2022-06-17 | 华为技术有限公司 | Method and related device for acquiring traffic data |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103699785A (en) * | 2013-12-13 | 2014-04-02 | 北京交通大学 | Urban rail traffic system safety identifying method based on emergence and entropy |
CN104616507A (en) * | 2014-12-11 | 2015-05-13 | 北方工业大学 | Coordination control method and system for signal period of traffic sub-area |
CN105303839A (en) * | 2015-12-04 | 2016-02-03 | 中国科学院遥感与数字地球研究所 | Latent congested road intersection prediction method and device |
-
2017
- 2017-07-03 CN CN201710535258.5A patent/CN107153896A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103699785A (en) * | 2013-12-13 | 2014-04-02 | 北京交通大学 | Urban rail traffic system safety identifying method based on emergence and entropy |
CN104616507A (en) * | 2014-12-11 | 2015-05-13 | 北方工业大学 | Coordination control method and system for signal period of traffic sub-area |
CN105303839A (en) * | 2015-12-04 | 2016-02-03 | 中国科学院遥感与数字地球研究所 | Latent congested road intersection prediction method and device |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110444009A (en) * | 2018-05-02 | 2019-11-12 | 芝麻开门网络信息股份有限公司 | A kind of expressway wagon flow forecasting system based on Internet of Things |
CN110444010A (en) * | 2018-05-02 | 2019-11-12 | 芝麻开门网络信息股份有限公司 | A kind of expressway wagon flow prediction technique based on Internet of Things |
CN110444010B (en) * | 2018-05-02 | 2022-01-21 | 广州智丰设计研发有限公司 | Expressway traffic flow prediction method based on Internet of things |
CN109064750A (en) * | 2018-09-28 | 2018-12-21 | 深圳大学 | Urban road network traffic estimation method and system |
CN109064750B (en) * | 2018-09-28 | 2021-09-24 | 深圳大学 | Urban road network traffic estimation method and system |
CN111814605A (en) * | 2020-06-23 | 2020-10-23 | 浙江大华技术股份有限公司 | Main road identification method, main road identification device and main road storage device based on topological map |
CN111814605B (en) * | 2020-06-23 | 2024-01-19 | 浙江华睿科技股份有限公司 | Main road identification method, main road identification device and storage device based on topological map |
CN114639235A (en) * | 2020-12-16 | 2022-06-17 | 华为技术有限公司 | Method and related device for acquiring traffic data |
CN113903171A (en) * | 2021-09-27 | 2022-01-07 | 北京航空航天大学 | Vehicle crowd sensing node optimization method based on spatial-temporal characteristics of highway network |
CN113903171B (en) * | 2021-09-27 | 2022-07-15 | 北京航空航天大学 | Vehicle crowd sensing node optimization method based on spatial-temporal characteristics of highway network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107153896A (en) | Traffic network path prediction method and system based on node pair entropy | |
Aland et al. | Exact price of anarchy for polynomial congestion games | |
Thai et al. | Negative externalities of GPS-enabled routing applications: A game theoretical approach | |
Ma et al. | Integrated traffic and communication performance evaluation of an intelligent vehicle infrastructure integration (VII) system for online travel-time prediction | |
Guo et al. | Day-to-day flow dynamics and congestion control | |
CN102708698B (en) | Vehicle optimal-path navigation method based on vehicle internet | |
CN103471603B (en) | The matching process of a kind of public bus network and road network and device | |
CN108151756A (en) | The travel time computation method and device of a kind of urban public tranlport system | |
CN103854072A (en) | Processing method and system for path selection | |
CN106971535B (en) | A kind of urban traffic blocking index computing platform based on Floating Car GPS real time data | |
CN103903430A (en) | Dynamic fusion type travel time predicting method with multi-source and isomorphic data adopted | |
CN105976048A (en) | Power transmission network extension planning method based on improved artificial bee colony algorithm | |
CN105656771A (en) | Service path determining method, device and system | |
CN104318793B (en) | A kind of road water logging event is promptly dredged and is joined stream generating method | |
CN108830401B (en) | Dynamic congestion charging optimal rate calculation method based on cellular transmission model | |
CN104091460A (en) | Evacuation control method and system for tree structural network | |
CN116167533A (en) | Station emergency evacuation method and device suitable for urban rail transit | |
CN105095613A (en) | Method and device for prediction based on sequential data | |
CN116153117A (en) | Traffic guiding method, device, electronic equipment and storage medium | |
Afandizadeh et al. | Simultaneous determination of optimal toll locations and toll levels in cordon-based congestion pricing problem (case study of Mashhad city) | |
CN105427581B (en) | traffic simulation method and system based on floating car data | |
Elbery et al. | A novel stochastic linear programming feedback eco-routing traffic assignment system | |
Sun et al. | A global and dynamitic route planning application for smart transportation | |
CN103139212A (en) | Security service method of complex network | |
Lo et al. | A new dynamic traffic control system: performance of adaptive control strategies for over-saturated traffic |
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 | ||
AD01 | Patent right deemed abandoned | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20211203 |