CN109448381A - A kind of traffic prediction technique based on car networking big data - Google Patents
A kind of traffic prediction technique based on car networking big data Download PDFInfo
- Publication number
- CN109448381A CN109448381A CN201811554221.8A CN201811554221A CN109448381A CN 109448381 A CN109448381 A CN 109448381A CN 201811554221 A CN201811554221 A CN 201811554221A CN 109448381 A CN109448381 A CN 109448381A
- Authority
- CN
- China
- Prior art keywords
- section
- speed
- vehicle
- big data
- studied
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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"
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to the KNN estimation method under function type nonparametric model and the model, traffic prediction is effective application of car networking big data, it provides effective reference by power-assisted urban traffic control, for car owner's choice for traveling travel route.Non parametric regression is as a kind of printenv, high-precision algorithm, and prediction effect is more superior than parametric regression, and error is smaller；The velocity amplitude in a period of time is regarded as continuous function curve simultaneously, goes to analyze from the angle of function type data；The estimation method for using K- neighbour herein, need to only determine the parameters such as optimal bandwidth, so that it may predict vehicle flow in real time.
Description
Technical field
The invention belongs to intelligent networks to join technical field, particularly relate to a kind of traffic prediction based on car networking big data
Method.
Background technique
Car networking is the important intersection of Internet of Things and the big field of intelligent vehicle two in strategic emerging industries, is city intelligence
The key components of intelligent traffic.The concept of car networking is derived from Internet of Things, is using sensor, communication network, system integration etc.
Technology realizes the network interconnection between people and vehicle, Che Yuche, Che Yulu and information mutual communication, is managed by the intelligence on people, vehicle, road,
To realize that intelligent traffic administration system, car networking are that this macroscopic concept is embodied in vehicle and Modern Traffic by technology of Internet of things
In.Big data analysis, which refers to, analyzes huge data, can be with by big data technical application in car networking environment
The big data that car networking is collected is analyzed to reach and relieve traffic congestion, optimize the operation of traffic system, improves traffic information clothes
Business is horizontal.
Traffic system is someone's participation, a dynamic, complicated nonlinear system, its distinguishing feature is exactly to have
The time variation and uncertainty of height, this uncertainty not only have the reason of nature (season and weather etc.), also come from
Artificial reason (such as traffic accident, emergency event, driver psychological condition).
Accomplish that real-time, accurate forecasting traffic flow may be implemented traffic control, induction and provide Real-time Traffic Information service,
Great help is brought to traffic congestion is solved.But short-term traffic flow forecast is relative to medium- and long-term forecasting, by random disturbances because
Element influence is bigger, and uncertain stronger, regularity is less obvious, therefore the difficulty predicted is also bigger.
In current main short-term traffic flow forecasting model, it is mainly based upon parametric regression method, such as history is averaged mould
Type, time series models, neural network model etc..But since the uncertainty of traffic condition is compared with parameter model, nonparametric
Regression model is more in line with reality, and prediction effect is more preferable.It is not limited in any way data nonparametric Regression Model, independent of
Fixed model, does not need any priori knowledge, needs historical data only to establish model with Selecting All Parameters, real time data is substituted into
Model is to obtain prediction result.1987, Yakowit is proposed earliest was applied to time series forecasting for k nearest neighbor method；1991
Year, distribution-free regression procedure is applied in traffic forecast by Davis and Nihan for the first time.Zhang Xiaoli (2009) proposes a kind of base
In the prediction of short-term traffic volume method of K- neighbour's non parametric regression of balanced binary tree；Zhang Xiaoli, Lu Huapu (2009) are anti-using having
The distribution-free regression procedure of feedback adjustment mechanism is predicted；Zhang Tao (2010) is based on K- neighbour nonparametric Regression Model, using not
With state vector and prediction algorithm to short-time traffic flow forecast.
Summary of the invention
The object of the present invention is to provide one kind based on car networking big data and using non parametric regression algorithm to traffic
Prediction technique, to solve the problems, such as that the prior art is big to the impacted factor of short-term traffic flow forecast, predictablity rate is poor.
The present invention is achieved by the following technical solutions:
A kind of traffic prediction technique based on car networking big data, comprising:
1) it determines studied section and influences the networking section quantity in the studied section；
2) count all vehicles it is described enter network segment real-time speed and the vehicle after entering the studied section
Speed, be based on function type nonparametric Regression Model, the relationship of available vehicle speed under two sections of routes, the model is such as
Under: Yi=r (xi)+εi,1≤i≤n,n∈N+, wherein YiIndicate the speed of studied i-th vehicle in section, xiIndicate networking section
The rate curve of i-th vehicle, ε are random error；
3) KNN estimation method is utilized, model is estimated, obtain the optimized parameter of model, estimation method is as follows:
Wherein, K is asymmetric nuclear function；
Setting B (x, h)=x ' ∈ H | d (x, x ')≤h }, wherein it is the small of h that wherein B (x, h), which is distance center x radius,
Ball, the quantity of neighbour k are smoothing parameter, then Hn,k(x) it is defined as follows:
4) by the speed of predetermined speed come the vehicle flowrate of response prediction period road.
In single intersection, variable is the flow with studied section relevant road segments, the as flow in networking section.
The networking section and the studied section are adjacent segments.
The rate curve of the vehicle in the networking section is real-time speed curve in the set period of time of the vehicle.
The beneficial effects of the present invention are:
The traffic prediction of the technical program is effective application of car networking big data, it is by power-assisted urban transportation pipe
Reason, provides effective reference for car owner's choice for traveling travel route.Non parametric regression as a kind of printenv, high-precision algorithm,
Its error is smaller；The estimation method for using K- neighbour herein, need to only determine the parameters such as optimal bandwidth, so that it may predict road in real time
Flow.
Detailed description of the invention
Fig. 1 is studied section relevant road segments schematic diagram in the case of single intersection.
Specific embodiment
Carry out the technical solution that the present invention will be described in detail below by way of embodiment, embodiment below is merely exemplary,
It is only capable of for explanation and illustration technical solution of the present invention, and is not to be construed as the limitation to technical solution of the present invention.
The application provides one kind based on car networking big data, is predicted using nonparametric Regression Model traffic.
There are many factor for influencing traffic condition, such as weather conditions, vehicle fleet size, traffic accident etc., but finally all show
In speed, the information content that speed is forgiven is enough.
Prediction of speed is exactly feelings most like in historical data using non parametric regression predicted method, core concept
Condition, to be predicted.This method and k neighbour, that is, some are similar for KNN method, the thought of KNN algorithm is k feature
Most of sample of arest neighbors belongs to a classification, and non-parametric thought is the speed curves of arest neighbors here, future time instance
Variation may also be similar.And since speed index is continuous curve, if going to analyze from certain single time point or average speed,
The inaccuracy of prediction can be brought, so the speed index in a period of time is regarded as continuous function curve, from function type data
Angle go to analyze, the effect of prediction will be more superior.In order to study the traffic condition of certain road, we select intuitive and can obtain
Index --- the speed obtained, for reflecting that road crowded state, the i.e. faster road of speed are more unimpeded.
A kind of traffic prediction technique based on car networking big data, comprising:
1) it determines studied section and influences the networking section quantity in the studied section；In single intersection, become
Amount is the flow with studied section relevant road segments, the as flow in networking section.The networking section and the studied road
Section is adjacent segments.
2) vehicle is in the real-time speed in the networking section and the vehicle after entering the studied section
Speed obtains the relationship of vehicle speed after networking section speed and studied section, the function by Function Estimation model
Estimate model are as follows:
Wherein, K is asymmetric nuclear function；
Setting B (x, h)=x ' ∈ H | d (x, x ')≤h }, wherein it is the small of h that wherein B (x, h), which is distance center x radius,
Ball, the quantity of neighbour k are smoothing parameter, then Hn,k(x) it is defined as follows:
3) when needing to some period speed prediction, all vehicle networkings section rate curve is acquired by car networking
(i.e. continuous, intensive data value can be fitted to curve) and enter the studied single velocity amplitude in section, data value is substituted into model
In, it can be deduced that unknown operator and optimized parameter in the model, to obtain the relationship of two section speed.In actual prediction
When, only networking section velocity amplitude need to be acquired as independent variable and substitutes into the above-mentioned model estimated, obtain dependent variable as a result, the value
Speed after as entering studied section.
4) by the speed of predetermined speed come the vehicle flowrate of response prediction period road.
In single intersection, variable be usually with studied section relevant road segments flow, as shown in Figure 1, a1,a2,a3For
Networking section is related to studied section b, it is assumed that it is equiprobable that networking section vehicle, which enters studied section,.
In prediction of short-term traffic volume, the vehicle flowrate in section after we wonder a few minutes or dozens of minutes, we
Real-time networking section Vehicle Speed can be first obtained respectively and the vehicle enters the speed behind studied section, by data generation
Enter to estimate model, obtains optimal bandwidth；The vehicle real-time speed of prediction period is substituted into model again later, pre- test the speed can be obtained
Degree, the flow of road is reflected with the speed of speed.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And deformation, the scope of the present invention is by appended claims and its equivalent limits.
Claims (4)
1. a kind of traffic prediction technique based on car networking big data characterized by comprising
1) it determines studied section and influences the networking section quantity in the studied section；
2) count all vehicles it is described enter network segment speed after entering the studied section of real-time speed and the vehicle
Degree, based on function type nonparametric Regression Model, the relationship of available vehicle speed under two sections of routes, the model is as follows:
Yi=r (xi)+εi,1≤i≤n,n∈N+, wherein YiIndicate the speed of studied i-th vehicle in section, xiIndicate networking section i-th
The rate curve of vehicle, ε is random error；
3) KNN estimation method is utilized, model is estimated, obtain the optimized parameter of model, estimation method is as follows:
Wherein, K is asymmetric nuclear function；
Setting B (x, h)=x ' ∈ H | d (x, x ')≤h }, wherein wherein B (x, h) is the bead that distance center x radius is h, closely
The quantity of adjacent k is smoothing parameter, then Hn,k(x) it is defined as follows:
4) by the speed of predetermined speed come the vehicle flowrate of response prediction period road.
2. the traffic prediction technique according to claim 1 based on car networking big data, which is characterized in that in single channel
In the case of mouthful, variable is the flow with studied section relevant road segments, the as flow in networking section.
3. the traffic prediction technique according to claim 1 based on car networking big data, which is characterized in that it is described enter
Network section is adjacent segments with the studied section.
4. the traffic prediction technique according to claim 1 based on car networking big data, which is characterized in that it is described enter
The rate curve of the vehicle of network section is real-time speed curve in the set period of time of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811554221.8A CN109448381A (en) | 2018-12-19 | 2018-12-19 | A kind of traffic prediction technique based on car networking big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811554221.8A CN109448381A (en) | 2018-12-19 | 2018-12-19 | A kind of traffic prediction technique based on car networking big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109448381A true CN109448381A (en) | 2019-03-08 |
Family
ID=65559287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811554221.8A Pending CN109448381A (en) | 2018-12-19 | 2018-12-19 | A kind of traffic prediction technique based on car networking big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109448381A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110111563A (en) * | 2019-04-08 | 2019-08-09 | 东南大学 | A kind of real-time traffic states estimation method of city expressway |
| 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 |
| CN113140108A (en) * | 2021-04-16 | 2021-07-20 | 西北工业大学 | Cloud traffic situation prediction method in internet-connected intelligent traffic system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9129449B2 (en) * | 2011-03-31 | 2015-09-08 | United Parcel Service Of America, Inc. | Calculating speed and travel times with travel delays |
| CN105139656A (en) * | 2015-09-28 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Road state prediction method and device |
| CN106128100A (en) * | 2016-06-30 | 2016-11-16 | 华南理工大学 | A kind of short-term traffic flow forecast method based on Spark platform |
| CN108364463A (en) * | 2018-01-30 | 2018-08-03 | 重庆交通大学 | A kind of prediction technique and system of the magnitude of traffic flow |
-
2018
- 2018-12-19 CN CN201811554221.8A patent/CN109448381A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9129449B2 (en) * | 2011-03-31 | 2015-09-08 | United Parcel Service Of America, Inc. | Calculating speed and travel times with travel delays |
| CN105139656A (en) * | 2015-09-28 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Road state prediction method and device |
| CN106128100A (en) * | 2016-06-30 | 2016-11-16 | 华南理工大学 | A kind of short-term traffic flow forecast method based on Spark platform |
| CN108364463A (en) * | 2018-01-30 | 2018-08-03 | 重庆交通大学 | A kind of prediction technique and system of the magnitude of traffic flow |
Non-Patent Citations (2)
| Title |
|---|
| 张晓利，等: "基于K-邻域非参数回归短时交通流预测方法", 《系统工程学报》 * |
| 陆晓恒，等: "固定设计函数型非参数回归模型的估计", 《应用数学》 * |
Cited By (3)
| 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 |
| CN110111563A (en) * | 2019-04-08 | 2019-08-09 | 东南大学 | A kind of real-time traffic states estimation method of city expressway |
| CN113140108A (en) * | 2021-04-16 | 2021-07-20 | 西北工业大学 | Cloud traffic situation prediction method in internet-connected intelligent traffic system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yao et al. | Short‐term traffic speed prediction for an urban corridor | |
| CN105118294B (en) | A kind of Short-time Traffic Flow Forecasting Methods based on state model | |
| CN109215350B (en) | Short-term traffic state prediction method based on RFID electronic license plate data | |
| US8606727B2 (en) | Method and system for traffic prediction based on space-time relation | |
| CN109191849B (en) | Traffic jam duration prediction method based on multi-source data feature extraction | |
| CN109448381A (en) | A kind of traffic prediction technique based on car networking big data | |
| Jin et al. | Short-term traffic safety forecasting using Gaussian mixture model and Kalman filter | |
| US20140278052A1 (en) | Lane-level vehicle navigation for vehicle routing and traffic management | |
| CN106251642B (en) | A kind of public transport road chain speed calculation method based on real-time bus GPS data | |
| CN105913661A (en) | Highway road section traffic state discrimination method based on charging data | |
| CN106373390B (en) | Traffic state evaluation method based on Adaptive Neuro-fuzzy Inference | |
| CN101593424A (en) | A kind of intelligent combination forecasting method for short-term traffic flow | |
| Chen et al. | A multiscale-grid-based stacked bidirectional GRU neural network model for predicting traffic speeds of urban expressways | |
| CN109003453B (en) | Floating car section average speed short-term prediction method based on support vector machine | |
| CN105551250A (en) | Method for discriminating urban road intersection operation state on the basis of interval clustering | |
| CN110796876A (en) | Road section vehicle total number estimation method based on Kalman filtering | |
| Li et al. | Cloud aided safety-based route planning | |
| CN117546218A (en) | Distributed multitasking machine learning for traffic prediction | |
| Gao et al. | Traffic speed forecast in adjacent region between highway and urban expressway: based on MFD and GRU model | |
| Fu et al. | Estimation of route travel time distribution with information fusion from automatic number plate recognition data | |
| Zou et al. | City-level traffic flow prediction via LSTM networks | |
| Zhu | A spatial decision-making model of smart transportation and urban planning based on coupling principle and Internet of Things | |
| CN106571034A (en) | City expressway traffic state rolling prediction method based on fusion data | |
| Shen | Freeway travel time estimation and prediction using dynamic neural networks | |
| Sheu | A fuzzy clustering approach to real-time demand-responsive bus dispatching control |
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 | ||
| CB02 | Change of applicant information |
Address after: 230601 No. 99 Ziyun Road, Hefei Economic and Technological Development Zone, Anhui Province Applicant after: Anhui Jianghuai Automobile Group Limited by Share Ltd Address before: 230601 No. 669 Shixin Road, Taohua Industrial Park, Hefei City, Anhui Province Applicant before: Anhui Jianghuai Automobile Group Limited by Share Ltd |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |
|
| RJ01 | Rejection of invention patent application after publication |