CN111145544A - Travel time and route prediction method based on congestion spreading dissipation model - Google Patents
Travel time and route prediction method based on congestion spreading dissipation model Download PDFInfo
- Publication number
- CN111145544A CN111145544A CN201911359987.5A CN201911359987A CN111145544A CN 111145544 A CN111145544 A CN 111145544A CN 201911359987 A CN201911359987 A CN 201911359987A CN 111145544 A CN111145544 A CN 111145544A
- Authority
- CN
- China
- Prior art keywords
- congestion
- road section
- dissipation
- road
- spreading
- 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
Images
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
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
-
- 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
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method for predicting travel time and a route based on a congestion spreading dissipation model, which comprises the steps of establishing a common congestion and special event congestion spreading superposition model and a common congestion and special event congestion dissipation superposition model by considering the influence of special events, obtaining congestion spreading speed, a congestion spreading boundary, congestion duration time, a traffic capacity loss value, congestion dissipation speed and congestion dissipation form, establishing a method for predicting travel time based on the congestion spreading dissipation model, and predicting the time-space relationship between the running position of each road section and the congestion spreading boundary, the travel time increment value caused by congestion spreading and the predicted travel time value of each road section in real time; and finally, establishing a predictive path navigation optimization method, and outputting and predicting to obtain the optimal path, the alternative path and the corresponding travel time. The embodiment of the invention can more accurately provide travel time prediction and an optimal travel path for the traveler, and is convenient for the traveler to make a travel decision.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a travel time and route prediction method based on a congestion spreading dissipation model.
Background
ETA (Estimated Time of Arrival, travel Time prediction) is a prediction of travel Time for roads based on traffic data collected by various traffic detection methods such as video detection systems, floating cars, stationary loop detectors, and the like. The travel time prediction can provide timely and reliable time information for travelers, so that the travelers can make travel decisions conveniently, and the travel time prediction plays an important role in travel induction; the method is also an important part of intelligent traffic and is one of effective means for relieving traffic jam.
With the continuous improvement of road information acquisition means and technology, the method for predicting the travel time is also continuously and deeply researched. Currently, there are many methods for studying travel time prediction, such as: historical trend methods, Markov chain models, exponential smoothing methods, time series methods, Kalman filtering models, and the like. However, the models and the methods are almost based on historical data under the condition of frequent congestion at the same time, so that the predicted road section travel time cannot be dynamically updated along with time, and the difference from the actual situation often exists. In recent years, although research has begun to consider sporadic congestion factors (mainly special events), travel time prediction is made more practical, and the problem of vehicle dynamic routing is optimized. However, these studies do not consider the duration of the emergency event, and do not consider the travel time prediction in the case where the emergency event occurs and the congestion generated after the occurrence dissipates, so that the travel time prediction and the optimal travel route cannot be accurately provided for the travelers. However, in real life, the occurrence of an emergency is objective, and the generated congestion dissipates with the resolution of the event, which is often ignored by current research and application.
Disclosure of Invention
The embodiment of the invention provides a travel time and path prediction method based on a congestion propagation dissipation model, which aims to overcome the defects of the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme.
A travel time and path prediction method based on a congestion propagation dissipation model comprises the following steps:
s1, acquiring data related to road sections based on floating car speed data, flow data collected by flow collection equipment, check line survey data and GIS road network attribute table data, and establishing a frequent traffic congestion feature library and a feature model;
s2, on the basis of the frequent traffic congestion feature library and the feature model, considering the influence of the special event, establishing a superposition model of the frequent congestion and the special event congestion spreading according to the congestion record information under the special event, and calculating the congestion spreading speed, the congestion spreading boundary, the congestion duration and the traffic capacity loss value;
s3, establishing a demand reduction type congestion dissipation model based on data related to a road section, establishing an event relief type congestion dissipation model based on the data related to the road section and congestion record information under a special event, establishing a superposition model of frequent congestion and special event congestion dissipation based on the demand reduction type congestion dissipation model and the event relief type congestion dissipation model, and calculating congestion dissipation speed and congestion dissipation form;
s4, predicting the space-time relation between the running position of each road section and the congestion spreading boundary, the travel time increment value caused by congestion spreading and the travel time predicted value of each road section in real time based on the acquired congestion spreading speed, the congestion spreading boundary, the congestion duration, the congestion dispersion speed, the congestion dispersion form, the traffic capacity loss value parameter, the determination of the road section weight and the input of the user travel parameter;
and S5, determining the key road sections according to the travel time predicted values of the road sections, establishing a predictive path navigation optimization method, performing weight comparison on all the determined multiple paths to determine the final optimal path, and outputting the predicted optimal path, the predicted alternative path and the corresponding travel time predicted values.
Preferably, the S1 includes:
acquiring data related to road sections from floating vehicle speed data, flow data acquired from flow acquisition equipment, check line survey data and GIS road network attribute table data;
judging whether the speed of the road section is lower than v according to the data related to the road sectioncWhen the congestion occurs, the method determines whether the road section is a frequently congested road section according to the frequency and the occurrence time of congestion, and comprises the following steps: setting congestion days in the same time period to be more than alpha% of total days as a frequent congestion road section, establishing a frequent traffic congestion feature library and a feature library model, and storing road section names, road section numbers, driving directions, congestion time periods, congestion duration, traffic and speed information;
wherein v iscTo distinguish congestion from non-congestion, α ∈ (0, 100) is the congestion days ratio.
Preferably, the S2 includes:
(1) speed u of spreading of congestionw(tk) The calculation formula of (2) is as follows:
wherein, the model formula adopted by the f function is as follows:
the model formula adopted by the F function is as follows:
wherein the final number of vehicles passing downstream q2(tk) The calculation formula is as follows:
final number of vehicles passing upstream Qo(tk) The calculation formula is as follows:
wherein u isw(tk) To speed of spread of congestion, Qo(tk) Is the upstream flow in the k time period, Vo(tk) Is the original speed of the upstream road section in the k time period, q2(tk) Is the downstream flow in the k time period, ufFor free flow velocity, ucIs the critical speed, u is the road speed, kjTo plug density, qcTo capacity, c1,c2,c3Is an intermediate variable, N is the total number of lanes, N is the number of blocked lanes, QnlcNumber of vehicles needing to be changed, pnlc(b) For changing bus lane proportion, qoIs the downstream saturation flow rate, QoFor main road primary traffic flow, pmr(b) In proportion to the bus, V0Is main road original speed, V'0For the post-accident main road speed, V1To assist the road in the original speed, DaoiIs the exit ramp density, uwIs the wave velocity of traffic waves, tjFor the duration of the congestion period, tintBeing time intervals, CrFor the traffic capacity of the ramps, C1For auxiliary road capacity, Q1For the auxiliary road original traffic, psr(b) As a side road bus ratio, DaiiFor the entry ramp density, α1、α2、α4For the parameter to be determined, /)maxRepresents the maximum length of the congested road section that the driver can tolerate, delta is the road condition information acceptance ratio, α3、α5The parameter is an undetermined parameter, and theta is the vehicle proportion for mastering the congestion information;
(2) congestion spread boundary smaxThe calculation formula of (2) is as follows:
smax=min[s(tk)]
wherein s ismaxAs a congestion spread boundary, s (t)k) For queue length, tintervalIs a time interval;
(3) duration tLThe calculation formula of (2) is as follows:
tL=Lauw(tk)
wherein, tLFor a duration of time, LaIs the road segment length;
(4) after a special event occurs, the road traffic capacity is correspondingly reduced under the influence of the number of blocked lanes and the number of lane-changing vehicles, and the calculation formula of the traffic capacity loss value delta q is as follows:
Δq=qc-qd
qd=λqc
where Δ q is the traffic capacity loss value, qcTraffic capacity of the road section before the bottleneck is generated, qdFor the traffic capacity after the reduction, λ ∈ (0,1) is a reduction coefficient, and is related to the total number of lanes and the number of blocked lanes.
Preferably, the S3 includes:
congestion dissipation speed u of demand reduction type1dThe calculation formula of (2) is as follows:
wherein u is1dTo reduce the congestion dissipation speed for demand, u1lIs the space average speed of the vehicle upstream of the bottleneck, q1(tk) The upstream flow in the k time period is defined as a, b and c, and the a, b and c are three constants;
event-resolved congestion dissipation velocity u2dThe calculation formula of (2) is as follows:
wherein u is2dFor speed of congestion dissipation at a particular event, u2lIs the space average speed of the vehicles downstream of the bottleneck;
establishing a superposition model of frequent congestion and special event congestion dissipation based on a demand reduction type congestion dissipation model and an event relief type congestion dissipation model, wherein the superposition model comprises the following steps:
dissipation patterns are divided into five types: the method comprises the following steps of reducing a demand type I and a demand type II mainly by reducing demand, and removing the type I, the type II and the type III mainly by removing events;
dissipation speed u under dissipation superposition of frequent congestion and special event congestiondThe calculation formula is as follows:
wherein u isdCongestion dissipation speed k is superimposed on congestion dissipation of frequent congestion and special events1、k2Is a variable of 0 and 1.
Preferably, the S4 includes:
suppose that n paths from the starting point to the special event point can be selected, that is, the path set is: { l1,…,li,…,lnThe corresponding weights, i.e. travel time sets, are: { T1,…,Ti,…,Tn}; n paths are available between the starting place and the common node, namely the path set is as follows: { ln+1,…,ln+i,…,ln+NThe corresponding weights, i.e. travel time sets, are: { Tn+1,…,Tn+i,…,Tn+N};
Predicting the space-time relationship between the driving position of each road section and the congestion spreading boundary, which comprises the following specific steps:
dividing the congestion spreading between the user and the special event into a group by taking the accident occurrence point as the origin of coordinates and the propagation direction of the congestion spreading wave as the positive directionThe following three cases: the situation is that the user meets the congestion spreading wave, and the meeting point happens to be on the congestion spreading boundary, namely sitec=smax(ii) a Second, the user meets the congestion spreading wave, and the junction point is in the congestion spreading boundary, namely sitec<smax(ii) a The third situation is that the special event is completed, and the user does not meet the congestion spreading wave, namely, no junction exists; wherein sitecIs the position of the intersection point;
inputting user travel parameters based on a superposition model for spreading the frequent congestion and the special event congestion and a superposition model for dissipating the frequent congestion and the special event congestion, and performing a certain iteration period delta TfixAnd predicting and updating the meeting time { T) of the running position of each road section and the congestion spreading boundary in real timec1,…,Tci,…,Tcn,Tcn+1,…,TcNAnd the intersection location { site }c1,…,siteci,…,sitecn,sitecn+1,…,sitecN};
Taking the road section travel time as a road weight index, the calculation formula is as follows:
T=Ta+ta
wherein T is the road section travel time, TaTime of flight, t, for non-congested road sectionsaIs the travel time of the congested road segment,the running time of the section of the free stream of the upstream traffic is d, and the delay time of the vehicle at the intersection is d;
the travel time increase value delta T caused by congestion spreading dissipation is calculated according to the following formula:
ΔT=T-Td
wherein, the delta T is a road section travel time increment value caused by congestion spreading dissipation, TdThe road section travel time under the normal condition;
there are two possibilities for a user to reach a destination from a starting location: the method comprises the following steps that one is to pass through a special event point, the other is to pass through a common node without passing through the special event point, and the shortest travel time is judged in real time, and the method specifically comprises the following steps:
based on a superposition model for spreading the congestion of the frequent congestion and the special event congestion and a superposition model for dissipating the congestion of the frequent congestion and the special event congestion, a certain iteration period delta T is usedfixTo predict and output the travel time increment { Delta T ] caused by congestion propagation dissipation1,…,ΔTi,…,ΔTn,ΔTn+1,…,ΔTn+i,…,ΔTn+NAnd outputting predicted values of the travel time of each road section, namely updating a road section travel time set (T) in real time1,…,Ti,…,Tn,Tn+1,…,Tn+i,…,Tn+N}。
Preferably, the S5 includes:
s51, inputting a starting point and an end point of a user, determining road section weight and updating a time interval T;
s52, determining a key road section set according to the road section weight change rule;
s53, under the condition that the key road section is not considered, determining the optimal path and the time consumption t of the vehicle from the current node to the next node by applying a Dijkstra algorithm;
s54, judging whether the next node is an end point, if so, directly ending the circulation;
s55, if not, taking the current node as a new starting point;
s56, if T is less than or equal to T, driving along the original path until the next node, and recording the required time as T1; if T > T, updating the road segment weight and returning to the step S54;
s57, continuously judging whether the current node is a terminal point, and if so, outputting a path; if not, updating the time consumption t to t + t1, and returning to the step S55;
s58, judging whether all the key road sections have been accessed, if so, outputting the path with the minimum weight, and ending the circulation; otherwise, considering the key road section, determining a corresponding initial optimal path and the time t required by the vehicle from the current node to the next node, and returning to the step S54;
all paths and corresponding travel time predicted values are obtained through the calculation, the path with the shortest travel time is selected as the optimal path, and other paths are used as alternative paths.
Preferably, the S62 includes:
s521, calculating the weight of each road section, namely the travel time predicted value of each road section at the current moment, sorting the road sections from big to small, and taking i% as a boundary line;
s522, judging whether the road section weight is higher than an i% boundary, and if not, forming a non-key road section set;
s523, if yes, a potential key road section set is formed;
s524, calculating the weights of the road sections of the potential key road sections in the future time period, sequencing the predicted weight values of the road sections in the future time period, and taking the j% quantile as a boundary line;
s525, judging whether the weight of the potential key road section in the future time period is lower than j% quantile or the descending amplitude is larger than k%, if not, forming a non-key road section;
s526, if yes, forming a key road section set, and ending the process;
wherein i, j, k ∈ (0, 100).
Preferably, the method further comprises: based on a superposition model for spreading the frequent congestion and the special event congestion and a superposition model for dissipating the frequent congestion and the special event congestion, an algorithm solving model is designed to obtain congestion spreading speed, congestion spreading boundary, congestion duration and traffic capacity loss value parameters, which are as follows:
s31, initializing fixed parameters of the model, and inputting congestion information data of the special event;
s32, inputting flow data provided by the flow acquisition equipment and speed data provided by floating vehicle speed data;
s33, based on frequent congestionCalculating and outputting congestion spreading speed u in specific time period by using a superposition model of special event congestion dissipation and a superposition model of frequent congestion and special event congestion dissipationw(tk) Congestion propagation boundary smaxDuration of congestion tLCongestion dissipation velocity udCongestion dissipation form and traffic capacity loss value delta q;
s34, updating time and spatial position to predict the congestion propagation speed and boundary in a future time period, and if the congestion propagation distance is greater than the road section length, updating the background traffic flow and the historical speed; otherwise, the calculation continues to be performed with the original value, and the step returns to the step S32 until the congestion is completely dissipated.
Preferably, the flow rate collecting device includes: RTMS or coil or toll station or ETC gantry;
the data relating to the road segment includes: road section name, serial number, driving direction, speed, flow and time;
the special events include: traffic accidents, service controls and inclement weather.
According to the technical scheme provided by the embodiment of the invention, the method for predicting the travel time and the route based on the congestion propagation dissipation model is provided, and the travel time prediction and the optimal travel route are provided for travelers by considering the occurrence of an emergency and the prediction of the travel time under the condition of congestion propagation dissipation generated after the occurrence of the emergency on the basis of the congestion propagation dissipation model, so that the travelers can make travel decisions conveniently and the travel decisions are more suitable for the actual life needs.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a travel time and route prediction method based on a congestion propagation dissipation model according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of five dissipation patterns under the superposition of frequent congestion and special event congestion dissipation provided by an embodiment of the present invention;
fig. 3 is a schematic flowchart of a superposition algorithm for dissipation of congestion spreading between frequent congestion and special event congestion according to an embodiment of the present invention;
FIG. 4 is a simplified diagram of a user's path from an origin to a destination according to an embodiment of the present invention;
fig. 5 shows three location situations between a user trip and a special event congestion spreading boundary according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an algorithm flow of a key road segment according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating an algorithm of a predictive path navigation optimization method according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
The method for predicting the travel time and the route based on the congestion spreading dissipation model provided by the embodiment of the invention can consider the situations of special events occurring under the frequently congested road section and the known special event duration, and can more accurately provide travel time prediction and an optimal travel route for travelers, as shown in fig. 1, the method for predicting the travel time and the route based on the congestion spreading dissipation model specifically comprises the following steps:
s1, acquiring data (such as road section name, serial number, driving direction, speed, flow, time data and the like) related to road sections from flow data, check line survey data, GIS road network attribute table data and congestion record information under special events such as traffic accidents, service control and severe weather collected from floating vehicle speed data and flow collection equipment (such as RTMS or coils or toll stations or ETC gantries), and establishing a frequently-occurring traffic congestion feature library and a feature model through the acquired data information, wherein the data comprises the following specific steps:
judging the current road according to the data related to the road sectionSegment velocity below vcWhen the congestion occurs, the method determines whether the road section is a frequently congested road section according to the frequency and the occurrence time of congestion, and comprises the following steps: setting the proportion of the congestion days in the same time period to more than alpha% of the total days as a frequent congestion road section, establishing a frequent traffic congestion feature library and a feature library model, and storing the road section name, the road section number, the driving direction, the congestion time period, the congestion time, the traffic and the speed information. Wherein v iscTo distinguish congestion from non-congestion, α ∈ (0, 100) is the congestion days ratio.
S2, on the basis of the frequent traffic congestion feature library and the feature model, considering the influence of special events, establishing a superposition model of frequent congestion and special event congestion spreading according to congestion recording information under special events such as traffic accidents, service control and severe weather, and calculating congestion spreading speed, congestion spreading boundary, congestion duration and traffic capacity loss value, wherein the superposition model comprises the following steps:
(1) speed u of spreading of congestionw(tk) The calculation formula of (2) is as follows:
the model formula adopted by the f function is as follows:
the model formula adopted by the F function is as follows:
wherein the final number of vehicles passing downstream q2(tk) The calculation formula is as follows:
final number of vehicles passing upstream Qo(tk) The calculation formula is as follows:
wherein u isw(tk) To speed of spread of congestion, Qo(tk) Is the upstream flow in the k time period, Vo(tk) Is the original speed of the upstream road section in the k time period, q2(tk) Is the downstream flow in the k time period, ufFor free flow velocity, ucIs the critical speed, u is the road speed, kjTo plug density, qcTo capacity, c1,c2,c3Is an intermediate variable, N is the total number of lanes, N is the number of blocked lanes, QnlcNumber of vehicles needing to be changed, pnlc(b) For changing bus lane proportion, qoIs the downstream saturation flow rate, QoFor main road primary traffic flow, pmr(b) In proportion to the bus, V0Is main road original speed, V'0For the post-accident main road speed, V1To assist the road in the original speed, DaoiIs the exit ramp density, uwIs the wave velocity of traffic waves, tjFor the duration of the congestion period, tintBeing time intervals, CrFor the traffic capacity of the ramps, C1For auxiliary road capacity, Q1For the auxiliary road original traffic, psr(b) As a side road bus ratio, DaiiFor the entry ramp density, α1、α2、α4For the parameter to be determined, /)maxRepresents the maximum length of the congested road section that the driver can tolerate, delta is the road condition information acceptance ratio, α3、α5The parameter is an undetermined parameter, and theta is the vehicle proportion for mastering the congestion information;
(2) congestion spread boundary smaxThe calculation formula of (2) is as follows:
smax=min[s(tk)]
wherein s ismaxAs a congestion spread boundary, s (t)k) For queue length, tintervalIs a time interval;
(3) duration tLThe calculation formula of (2) is as follows:
tL=La/uw(tk)
wherein, tLFor a duration of time, LaIs the road segment length;
(4) after a special event occurs, the road traffic capacity is correspondingly reduced under the influence of the number of blocked lanes and the number of lane-changing vehicles, and the calculation formula of the traffic capacity loss value delta q is as follows:
Δq=qc-qd
qd=λqc
where Δ q is the traffic capacity loss value, qcThe traffic capacity of a road section before bottleneck generation, qd and lambda epsilon (0,1) are respectively the traffic capacity after reduction, and are related to the total number of lanes, the number of blocked lanes and the like.
S3, establishing a demand reduction type congestion dissipation model based on data related to a road section, establishing an event relief type congestion dissipation model based on the data related to the road section and congestion record information under a special event, establishing a superposition model of frequent congestion and special event congestion dissipation based on the demand reduction type congestion dissipation model and the event relief type congestion dissipation model, and calculating congestion dissipation speed and congestion dissipation form, wherein the congestion dissipation model comprises the following steps:
congestion dissipation speed u of demand reduction type1dThe calculation formula of (2) is as follows:
wherein u is1dTo reduce the congestion dissipation speed for demand, u1lThe spatial average speed q of the vehicle upstream of the bottleneck1(tk) The upstream flow in the k time period is a, b and c are three constants.
Event-resolved congestion dissipation velocity u2dThe calculation formula of (2) is as follows:
wherein u is2dFor speed of congestion dissipation at a particular event, u2lIs the space average speed of vehicles downstream of the bottleneck.
According to a demand reduction type congestion dissipation model and an event relief type congestion dissipation model, a superposition model of frequent congestion and special event congestion dissipation is established, and the superposition model comprises the following steps:
the dissipation pattern is divided into five types, as shown in fig. 2:
the method comprises the following steps of reducing a demand type I and a demand type II mainly by reducing demand, and removing the type I, the type II and the type III mainly by removing events;
dissipation speed u under dissipation superposition of frequent congestion and special event congestiondThe calculation formula is as follows:
wherein u isdCongestion dissipation speed k is superimposed on congestion dissipation of frequent congestion and special events1、k2Is a variable of 0 and 1.
According to the established superposition model for spreading the frequent congestion and the special event congestion and the superposition model for dissipating the frequent congestion and the special event congestion, an algorithm solving model is designed, and congestion spreading speed, congestion spreading boundary, congestion duration and traffic capacity loss value parameters are obtained, as shown in fig. 3, the method specifically comprises the following steps:
s31, initializing fixed parameters of the model, and inputting congestion information data of the special event;
s32, inputting flow data provided by the flow acquisition equipment and speed data provided by floating vehicle speed data;
s33, calculating and outputting the congestion spreading speed u in a specific time period based on the superposition model of the frequent congestion and the special event congestion dissipation and the superposition model of the frequent congestion and the special event congestion dissipationw(tk) Congestion propagation boundary smaxDuration of congestion tLCongestion dissipation velocity udCongestion dissipation form and traffic capacity loss value delta q;
s34, updating the time and the space position of the congestion spreading wave to predict the congestion propagation speed and the boundary in the future time period, and if the congestion spreading distance is greater than the road section length, updating the background traffic flow and the historical speed; otherwise, the next calculation is continued with the original values (the last calculated background traffic flow and the historical speed value) being maintained, and the flow returns to S32 until the congestion is completely dissipated.
S4, predicting the time-space relationship between the driving location of each road segment and the congestion spreading boundary, the travel time increment value caused by congestion spreading, and the predicted travel time value of each road segment in real time based on the acquired congestion spreading speed, congestion spreading boundary, congestion duration, congestion dispersion speed, congestion dispersion form, traffic capacity loss value parameter and determination of road segment weight, and user input travel parameters (such as departure location, departure time, and destination), specifically including:
fig. 4 shows a schematic diagram of a path from a departure point to a destination, but the following description shall be made in application based on actual situations:
suppose that n paths from the starting point to the special event point can be selected, that is, the path set is: { l1,…,li,…,lnThe corresponding weights, i.e. travel time sets, are: { T1,…,Ti,…,Tn}; n paths are available between the starting place and the common node, namely the path set is as follows: { ln+1,…ln+i,…ln+NThe corresponding weights, i.e. travel time sets, are: { Tn+1,…Tn+i,…Tn+N}。
Predicting the space-time relationship between the driving position of each road section and the congestion spreading boundary, which comprises the following specific steps:
by taking the accident occurrence point as the origin of coordinates and the propagation direction of the congestion propagation wave as the positive direction, the congestion propagation between the user and the special event can be divided into the following three cases, as shown in fig. 5: the situation is that the user meets the congestion spreading wave, and the meeting point happens to be on the congestion spreading boundary, namely sitec=smax(ii) a Second, the user meets the congestion spreading wave, and the junction point is in the congestion spreading boundary, namely sitec<smax(ii) a The third situation is that the special event is completed, and the user does not meet the congestion spreading wave, namely, no junction exists; wherein sitecIs the position of the intersection point.
According to the superposition algorithm of the frequent congestion and special event congestion spreading dissipation and the user input travel parameters, a certain iteration period delta T is adoptedfixAnd predicting and updating the meeting time { T) of the running position of each road section and the congestion spreading boundary in real timec1,…,Tci,…,Tcn,Tcn+1,…,TcNAnd the intersection location { site }c1,…,siteci,…,sitecn,sitecn+1,…,sitecN};
Taking the road section travel time as a road weight index, the calculation formula is as follows:
T=Ta+ta
wherein T is the road section travel time, TaTime of flight, t, for non-congested road sectionsaIs the travel time of the congested road segment,the running time of the section of the free stream of the upstream traffic is d, and the delay time of the vehicle at the intersection is d;
the travel time increase value delta T caused by congestion spreading dissipation is calculated according to the following formula:
ΔT=T-Td
wherein, the delta T is a road section travel time increment value caused by congestion spreading dissipation, TdThe road section travel time under the normal condition;
there are two possibilities for a user to reach a destination from a starting location: one is to pass through a special event point, and the other is not to pass through the special event point, namely to pass through a common node. However, which travel time is the shortest can be determined only by real-time judgment according to the actual situation, which is specifically as follows:
according to the superposition algorithm for spreading and dissipating the frequent congestion and the special event congestion, a certain iteration period delta T is adoptedfixTo predict and output the travel time increment { Delta T ] caused by congestion propagation dissipation1,…,ΔTi,…,ΔTn,ΔTn+1,…,ΔTn+i,…,ΔTn+NAnd outputting the predicted value of the travel time of each road section, namely updating the travel time set of the road section { T } in real time1,…,Ti,…,Tn,Tn+1,…,Tn+i,…,Tn+N}。
S5, determining a key road section according to the travel time predicted value of each road section, establishing a predictive path navigation optimization method, determining a final optimal path by performing weight comparison on all determined multiple paths, and outputting the predicted optimal path, alternative path and corresponding travel time predicted value, wherein the method specifically comprises the following steps:
through the travel time prediction section of step S4, the spatiotemporal relationship between the travel position of each link and the congestion propagation boundary can be predicted in real time, that is, the traffic state in the future period can be known. When a special event occurs, the weight of the road section can be increased sharply, the weight of the road section can be decreased after the generated congestion is dissipated, and the travel time of a path passing through the special event point is possibly even shorter than that of a path passing through a common node. Therefore, the problem needs to be solved by determining the key link according to the variation rule of the predicted value of the link weight. The key road section considers two factors of the weight of the initial road section and the large change range of the weight of the road section, and adopts a weight quantile method to determine whether the road section is the key road section, wherein a key road section algorithm flow is shown in fig. 6 and comprises the following specific steps:
step 521: calculating the weight of each road section, namely the travel time predicted value of each road section at the current moment, sequencing the road sections from big to small, and taking i% as a boundary line;
step 522: judging whether the road section weight is higher than an i% boundary, and if not, forming a non-key road section set;
step 523: if yes, forming a potential key road section set;
step 524: calculating the weights of the road sections of potential future time periods (namely the next updating time T) of the key road sections, sequencing the predicted weight values of the road sections in the future time periods, and taking j% quantiles as boundary lines;
step 525: judging whether the weight of the potential key road section in the future time period is lower than j% quantile or the reduction amplitude is larger than k%, if not, forming a non-key road section;
step 526: if so, forming a key road section set and finishing the process;
wherein i, j and k are preset values, and i, j and k are belonged to (0, 100).
By introducing the definition of the key road sections and identifying the key road sections, a predictive path navigation optimization method is designed. The initial path obtained before optimization is only based on travel time prediction under contemporaneous historical data, and has no real-time property and predictability; because the travel time prediction part can predict the time-space relationship between the driving position of each road section and the congestion spreading boundary and the travel time of each road section in real time, namely can know the traffic state in the future time period, the predictive path navigation optimization method is provided, and comprises the following steps:
optimal path transformation caused by rapid weight change is avoided through optimization, and the determined optimal paths are compared in weight, so that the final optimal path is determined, as shown in fig. 7, the specific steps are as follows:
step 51: inputting a starting point and a terminal point of a user, determining road section weight and updating a time interval T;
step 52: determining a key road section set according to a road section weight change rule;
step 53: under the condition of not considering the key road section, determining an optimal path and the time consumption t of the vehicle from the current node to the next node by applying a Dijkstra algorithm;
step 54: and judging whether the next node is an end point. If yes, directly ending the circulation;
step 55: if not, taking the current node as a new starting point;
step 56: if T is less than or equal to T, driving along the original path until the next node, and recording the required time as T1; if T > T, updating the road segment weight and returning to the step S54;
and 57: continuously judging whether the current node is an end point, and if so, outputting a path; if not, updating the time consumption t to t + t1, and returning to the step S55;
step 58: judging whether all the key road sections are completely accessed, if so, outputting the path with the minimum weight, and finishing the circulation; otherwise, considering the key road section, determining a corresponding initial optimal path and the time t required by the vehicle from the current node to the next node, and returning to the step S54;
the algorithm can obtain all possible paths and corresponding travel time predicted values, the path with the shortest travel time is selected from the possible paths and is the optimal path, and other paths are used as alternative paths for reference of a user.
In summary, embodiments of the present invention provide a travel time and route prediction method based on a congestion spreading dissipation model, and on the basis of establishing a frequent congestion and special event congestion spreading dissipation model and algorithm, the travel time prediction method is established, a route navigation algorithm is optimized, and conditions of occurrence of a special event and known duration of the special event in a frequently congested road section can be considered, so that travel time prediction and an optimal travel route can be more accurately provided for travelers, thereby facilitating the travelers to make travel decisions and better fit actual living needs.
The embodiment of the invention effectively solves the problems that in the prior art, the travel time can be obtained without considering the duration of the special event, and the travel time prediction of the condition that the special event occurs and the generated congestion is spread and dissipated after the special event occurs are not considered, so that the travel time prediction of a traveler is inaccurate and the provided path is not excellent.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. A travel time and path prediction method based on a congestion propagation dissipation model is characterized by comprising the following steps:
s1, acquiring data related to road sections based on floating car speed data, flow data collected by flow collection equipment, check line survey data and GIS road network attribute table data, and establishing a frequent traffic congestion feature library and a feature model;
s2, on the basis of the frequent traffic congestion feature library and the feature model, considering the influence of the special event, establishing a superposition model of the frequent congestion and the special event congestion spreading according to the congestion record information under the special event, and calculating the congestion spreading speed, the congestion spreading boundary, the congestion duration and the traffic capacity loss value;
s3, establishing a demand reduction type congestion dissipation model based on data related to a road section, establishing an event relief type congestion dissipation model based on the data related to the road section and congestion record information under a special event, establishing a superposition model of frequent congestion and special event congestion dissipation based on the demand reduction type congestion dissipation model and the event relief type congestion dissipation model, and calculating congestion dissipation speed and congestion dissipation form;
s4, predicting the space-time relation between the running position of each road section and the congestion spreading boundary, the travel time increment value caused by congestion spreading and the travel time predicted value of each road section in real time based on the acquired congestion spreading speed, the congestion spreading boundary, the congestion duration, the congestion dispersion speed, the congestion dispersion form, the traffic capacity loss value parameter, the determination of the road section weight and the input of the user travel parameter;
and S5, determining the key road sections according to the travel time predicted values of the road sections, establishing a predictive path navigation optimization method, performing weight comparison on all the determined multiple paths to determine the final optimal path, and outputting the predicted optimal path, the predicted alternative path and the corresponding travel time predicted values.
2. The method according to claim 1, wherein the S1 includes:
acquiring data related to road sections from floating vehicle speed data, flow data acquired from flow acquisition equipment, check line survey data and GIS road network attribute table data;
judging whether the speed of the road section is lower than v according to the data related to the road sectioncWhen the congestion occurs, the method determines whether the road section is a frequently congested road section according to the frequency and the occurrence time of congestion, and comprises the following steps: setting congestion days in the same time period to be more than alpha% of total days as a frequent congestion road section, establishing a frequent traffic congestion feature library and a feature library model, and storing road section names, road section numbers, driving directions, congestion time periods, congestion duration, traffic and speed information;
wherein v iscTo distinguish congestion from non-congestion, α ∈ (0, 100) is the congestion days ratio.
3. The method according to claim 1, wherein the S2 includes:
(1) speed u of spreading of congestionw(tk) The calculation formula of (2) is as follows:
wherein, the model formula adopted by the f function is as follows:
the model formula adopted by the F function is as follows:
wherein the final number of vehicles passing downstream q2(tk) The calculation formula is as follows:
final number of vehicles passing upstream Qo(tk) The calculation formula is as follows:
wherein u isw(tk) To speed of spread of congestion, Qo(tk) Is the upstream flow in the k time period, Vo(tk) Is the original speed of the upstream road section in the k time period, q2(tk) Is the downstream flow in the k time period, ufFor free flow velocity, ucIs the critical speed, u is the road speed, kjTo plug density, qcTo capacity, c1,c2,c3Is an intermediate variable, N is the total number of lanes, N is the number of blocked lanes, QnlcNumber of vehicles needing to be changed, pnlc(b) For changing bus lane proportion, qoIs the downstream saturation flow rate, QoFor main road primary traffic flow, pmr(b) In proportion to the bus, V0Is main road original speed, V'0For the post-accident main road speed, V1To assist the road in the original speed, DaoiIs the exit ramp density, uwIs the wave velocity of traffic waves, tjFor the duration of the congestion period, tintBeing time intervals, CrFor the traffic capacity of the ramps, C1For auxiliary road capacity, Q1For the auxiliary road original traffic, psr(b) As a side road bus ratio, DaiiFor the entry ramp density, α1、α2、α4For the parameter to be determined, /)maxRepresents the maximum length of the congested road section that the driver can tolerate, delta is the road condition information acceptance ratio, α3、α5The parameter is an undetermined parameter, and theta is the vehicle proportion for mastering the congestion information;
(2) congestion spread boundary smaxThe calculation formula of (2) is as follows:
smax=min[s(tk)]
wherein s ismaxAs a congestion spread boundary, s (t)k) For queue length, tintervalIs a time interval;
(3) duration tLThe calculation formula of (2) is as follows:
tL=La/uw(tk)
wherein, tLFor a duration of time, LaIs the road segment length;
(4) after a special event occurs, the road traffic capacity is correspondingly reduced under the influence of the number of blocked lanes and the number of lane-changing vehicles, and the calculation formula of the traffic capacity loss value delta q is as follows:
Δq=qc-qd
qd=λqc
where Δ q is the traffic capacity loss value, qcTraffic capacity of the road section before the bottleneck is generated, qdFor the traffic capacity after the reduction, λ ∈ (0,1) is a reduction coefficient, and is related to the total number of lanes and the number of blocked lanes.
4. The method according to claim 1, wherein the S3 includes:
congestion dissipation speed u of demand reduction type1dThe calculation formula of (2) is as follows:
wherein u is1dTo reduce the congestion dissipation speed for demand, u1lIs the space average speed of the vehicle upstream of the bottleneck, q1(tk) The upstream flow in the k time period is defined as a, b and c, and the a, b and c are three constants;
event-resolved congestion dissipation velocity u2dThe calculation formula of (2) is as follows:
wherein u is2dFor speed of congestion dissipation at a particular event, u2lIs the space average speed of the vehicles downstream of the bottleneck;
establishing a superposition model of frequent congestion and special event congestion dissipation based on a demand reduction type congestion dissipation model and an event relief type congestion dissipation model, wherein the superposition model comprises the following steps:
dissipation patterns are divided into five types: the method comprises the following steps of reducing a demand type I and a demand type II mainly by reducing demand, and removing the type I, the type II and the type III mainly by removing events;
dissipation speed u under dissipation superposition of frequent congestion and special event congestiondThe calculation formula is as follows:
wherein u isdCongestion dissipation speed k is superimposed on congestion dissipation of frequent congestion and special events1、k2Is a variable of 0 and 1.
5. The method according to claim 1, wherein the S4 includes:
suppose that n paths from the starting point to the special event point can be selected, that is, the path set is: { l1,…,li,…,lnThe corresponding weights, i.e. travel time sets, are: { T1,…,Ti,…,Tn}; n paths are available between the starting place and the common node, namely the path set is as follows: { ln+1,…,ln+i,…,ln+NThe corresponding weights, i.e. travel time sets, are: { Tn+1,…,Tn+i,…,Tn+N};
Predicting the space-time relationship between the driving position of each road section and the congestion spreading boundary, which comprises the following specific steps:
taking an accident occurrence point as a coordinate origin and a congestion spreading wave propagation direction as a positive direction, dividing congestion spreading between a user and a special event into the following three conditions: the situation is that the user meets the congestion spreading wave, and the meeting point happens to be on the congestion spreading boundary, namely sitec=smax(ii) a Second, the user meets the congestion spreading wave, and the junction point is in the congestion spreading boundary, namely sitec<smax(ii) a The third situation is that the special event is completed, and the user does not meet the congestion spreading wave, namely, no junction exists; wherein sitecIs the position of the intersection point;
inputting user travel parameters based on a superposition model for spreading the frequent congestion and the special event congestion and a superposition model for dissipating the frequent congestion and the special event congestion, and performing a certain iteration period delta TfixAnd predicting and updating the meeting time { T) of the running position of each road section and the congestion spreading boundary in real timec1,…,Tci,…,Tcn,Tcn+1,…,TcNAnd the intersection location { site }c1,…,siteci,…,sitecn,sitecn+1,…,sitecN};
Taking the road section travel time as a road weight index, the calculation formula is as follows:
T=Ta+ta
wherein T is the road section travel time, TaTime of flight, t, for non-congested road sectionsaIs the travel time of the congested road segment,the running time of the section of the free stream of the upstream traffic is d, and the delay time of the vehicle at the intersection is d;
the travel time increase value delta T caused by congestion spreading dissipation is calculated according to the following formula:
ΔT=T-Td
wherein, the delta T is a road section travel time increment value caused by congestion spreading dissipation, TdThe road section travel time under the normal condition;
there are two possibilities for a user to reach a destination from a starting location: the method comprises the following steps that one is to pass through a special event point, the other is to pass through a common node without passing through the special event point, and the shortest travel time is judged in real time, and the method specifically comprises the following steps:
based on a superposition model for spreading the congestion of the frequent congestion and the special event congestion and a superposition model for dissipating the congestion of the frequent congestion and the special event congestion, a certain iteration period delta T is usedfixTo predict and output the travel time increment { Delta T ] caused by congestion propagation dissipation1,…,ΔTi,…,ΔTn,ΔTn+1,…,ΔTn+i,…,ΔTn+NAnd outputting predicted values of the travel time of each road section, namely updating a road section travel time set (T) in real time1,…,Ti,…,Tn,Tn+1,…,Tn+i,…,Tn+N}。
6. The method according to claim 1, wherein the S5 includes:
s51, inputting a starting point and an end point of a user, determining road section weight and updating a time interval T;
s52, determining a key road section set according to the road section weight change rule;
s53, under the condition that the key road section is not considered, determining the optimal path and the time consumption t of the vehicle from the current node to the next node by applying a Dijkstra algorithm;
s54, judging whether the next node is an end point, if so, directly ending the circulation;
s55, if not, taking the current node as a new starting point;
s56, if T is less than or equal to T, driving along the original path until the next node, and recording the required time as T1; if T > T, updating the road segment weight and returning to the step S54;
s57, continuously judging whether the current node is a terminal point, and if so, outputting a path; if not, updating the time consumption t to t + t1, and returning to the step S55;
s58, judging whether all the key road sections have been accessed, if so, outputting the path with the minimum weight, and ending the circulation; otherwise, considering the key road section, determining a corresponding initial optimal path and the time t required by the vehicle from the current node to the next node, and returning to the step S54;
all paths and corresponding travel time predicted values are obtained through the calculation, the path with the shortest travel time is selected as the optimal path, and other paths are used as alternative paths.
7. The method of claim 6, the S62 comprising:
s521, calculating the weight of each road section, namely the travel time predicted value of each road section at the current moment, sorting the road sections from big to small, and taking i% as a boundary line;
s522, judging whether the road section weight is higher than an i% boundary, and if not, forming a non-key road section set;
s523, if yes, a potential key road section set is formed;
s524, calculating the weights of the road sections of the potential key road sections in the future time period, sequencing the predicted weight values of the road sections in the future time period, and taking the j% quantile as a boundary line;
s525, judging whether the weight of the potential key road section in the future time period is lower than j% quantile or the descending amplitude is larger than k%, if not, forming a non-key road section;
s526, if yes, forming a key road section set, and ending the process;
wherein i, j, k ∈ (0, 100).
8. The method of claim 1, further comprising: based on a superposition model for spreading the frequent congestion and the special event congestion and a superposition model for dissipating the frequent congestion and the special event congestion, an algorithm solving model is designed to obtain congestion spreading speed, congestion spreading boundary, congestion duration and traffic capacity loss value parameters, which are as follows:
s31, initializing fixed parameters of the model, and inputting congestion information data of the special event;
s32, inputting flow data provided by the flow acquisition equipment and speed data provided by floating vehicle speed data;
s33, calculating and outputting the congestion spreading speed u in a specific time period based on the superposition model of the frequent congestion and the special event congestion dissipation and the superposition model of the frequent congestion and the special event congestion dissipationw(tk) Congestion propagation boundary smaxDuration of congestion tLCongestion dissipation velocity udCongestion dissipation form and traffic capacity loss value delta q;
s34, updating time and spatial position to predict the congestion propagation speed and boundary in a future time period, and if the congestion propagation distance is greater than the road section length, updating the background traffic flow and the historical speed; otherwise, the calculation continues to be performed with the original value, and the step returns to the step S32 until the congestion is completely dissipated.
9. The method of claim 1, wherein the flow collection device comprises: RTMS or coil or toll station or ETC gantry;
the data relating to the road segment includes: road section name, serial number, driving direction, speed, flow and time;
the special events include: traffic accidents, service controls and inclement weather.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911359987.5A CN111145544B (en) | 2019-12-25 | 2019-12-25 | Travel time and route prediction method based on congestion spreading dissipation model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911359987.5A CN111145544B (en) | 2019-12-25 | 2019-12-25 | Travel time and route prediction method based on congestion spreading dissipation model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111145544A true CN111145544A (en) | 2020-05-12 |
CN111145544B CN111145544B (en) | 2021-05-25 |
Family
ID=70520190
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911359987.5A Active CN111145544B (en) | 2019-12-25 | 2019-12-25 | Travel time and route prediction method based on congestion spreading dissipation model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111145544B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112312082A (en) * | 2020-09-14 | 2021-02-02 | 上海商汤智能科技有限公司 | Road operation condition determining method and device, equipment and storage medium |
CN114170803A (en) * | 2021-12-15 | 2022-03-11 | 阿波罗智联(北京)科技有限公司 | Roadside sensing system and traffic control method |
CN114419876A (en) * | 2021-12-13 | 2022-04-29 | 北京百度网讯科技有限公司 | Road saturation evaluation method and device, electronic equipment and storage medium |
EP4002322A1 (en) * | 2020-11-24 | 2022-05-25 | HERE Global B.V. | System and method for determining dynamic road capacity data for traffic condition |
CN116935655A (en) * | 2023-09-15 | 2023-10-24 | 武汉市规划研究院 | Traffic state judging method and system for complex urban road network |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1637383A (en) * | 2003-12-26 | 2005-07-13 | 爱信艾达株式会社 | Systems, methods, and data structures for smoothing link travel time |
CN101046391A (en) * | 2006-03-31 | 2007-10-03 | 爱信艾达株式会社 | Navigation system |
CN102081857A (en) * | 2009-12-01 | 2011-06-01 | 华东师范大学第一附属中学 | Intelligent urban traffic control system |
CN103065468A (en) * | 2012-12-14 | 2013-04-24 | 中国航天系统工程有限公司 | Assessment method of traffic information and device |
CN103198681A (en) * | 2013-03-20 | 2013-07-10 | 东南大学 | Intersection signal control method based on public transport priority |
CN103488893A (en) * | 2013-09-23 | 2014-01-01 | 北京交通发展研究中心 | Forecasting technical scheme for traffic congestion spreading caused by waterlogging under bridge |
CN104392614A (en) * | 2014-08-28 | 2015-03-04 | 邓荣峰 | Jammed intersection signal timing method and traffic signal lamp control system |
CN105788256A (en) * | 2016-03-30 | 2016-07-20 | 北京交通大学 | Road condition information sensing method based on Internet of vehicles |
CN107704957A (en) * | 2017-09-28 | 2018-02-16 | 京东方科技集团股份有限公司 | A kind of congested link passes through optimization method and device |
CN107945507A (en) * | 2016-10-13 | 2018-04-20 | 腾讯科技(深圳)有限公司 | Travel Time Estimation Method and device |
US20190164419A1 (en) * | 2017-11-27 | 2019-05-30 | International Business Machines Corporation | Traffic control for autonomous vehicles |
US20190329770A1 (en) * | 2018-04-27 | 2019-10-31 | Honda Motor Co., Ltd. | System and method for lane level hazard prediction |
-
2019
- 2019-12-25 CN CN201911359987.5A patent/CN111145544B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1637383A (en) * | 2003-12-26 | 2005-07-13 | 爱信艾达株式会社 | Systems, methods, and data structures for smoothing link travel time |
CN101046391A (en) * | 2006-03-31 | 2007-10-03 | 爱信艾达株式会社 | Navigation system |
CN102081857A (en) * | 2009-12-01 | 2011-06-01 | 华东师范大学第一附属中学 | Intelligent urban traffic control system |
CN103065468A (en) * | 2012-12-14 | 2013-04-24 | 中国航天系统工程有限公司 | Assessment method of traffic information and device |
CN103198681A (en) * | 2013-03-20 | 2013-07-10 | 东南大学 | Intersection signal control method based on public transport priority |
CN103488893A (en) * | 2013-09-23 | 2014-01-01 | 北京交通发展研究中心 | Forecasting technical scheme for traffic congestion spreading caused by waterlogging under bridge |
CN104392614A (en) * | 2014-08-28 | 2015-03-04 | 邓荣峰 | Jammed intersection signal timing method and traffic signal lamp control system |
CN105788256A (en) * | 2016-03-30 | 2016-07-20 | 北京交通大学 | Road condition information sensing method based on Internet of vehicles |
CN107945507A (en) * | 2016-10-13 | 2018-04-20 | 腾讯科技(深圳)有限公司 | Travel Time Estimation Method and device |
CN107704957A (en) * | 2017-09-28 | 2018-02-16 | 京东方科技集团股份有限公司 | A kind of congested link passes through optimization method and device |
US20190164419A1 (en) * | 2017-11-27 | 2019-05-30 | International Business Machines Corporation | Traffic control for autonomous vehicles |
US20190329770A1 (en) * | 2018-04-27 | 2019-10-31 | Honda Motor Co., Ltd. | System and method for lane level hazard prediction |
Non-Patent Citations (4)
Title |
---|
FEI WEN-PENG 等: "Practical approach to determining traffic congestion propagation boundary due to traffic incidents", 《JOURNAL OF CENTRAL SOUTH UNIVERSITY》 * |
中国全球定位系统技术应用协会: "《卫星导航技术进步与创新》", 31 December 2008 * |
张晓燕: "基于交通波理论的典型交通事件下拥堵蔓延消散模型", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
藏金蕊,宋国华等: "交通事件下快速路拥堵蔓延消散时空范围模型", 《交通运输系统工程与信息》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112312082A (en) * | 2020-09-14 | 2021-02-02 | 上海商汤智能科技有限公司 | Road operation condition determining method and device, equipment and storage medium |
CN112312082B (en) * | 2020-09-14 | 2021-11-30 | 上海商汤智能科技有限公司 | Road operation condition determining method and device, equipment and storage medium |
EP4002322A1 (en) * | 2020-11-24 | 2022-05-25 | HERE Global B.V. | System and method for determining dynamic road capacity data for traffic condition |
CN114419876A (en) * | 2021-12-13 | 2022-04-29 | 北京百度网讯科技有限公司 | Road saturation evaluation method and device, electronic equipment and storage medium |
CN114419876B (en) * | 2021-12-13 | 2023-04-25 | 北京百度网讯科技有限公司 | Road saturation evaluation method and device, electronic equipment and storage medium |
CN114170803A (en) * | 2021-12-15 | 2022-03-11 | 阿波罗智联(北京)科技有限公司 | Roadside sensing system and traffic control method |
CN114170803B (en) * | 2021-12-15 | 2023-06-16 | 阿波罗智联(北京)科技有限公司 | Road side sensing system and traffic control method |
CN116935655A (en) * | 2023-09-15 | 2023-10-24 | 武汉市规划研究院 | Traffic state judging method and system for complex urban road network |
CN116935655B (en) * | 2023-09-15 | 2023-12-05 | 武汉市规划研究院 | Traffic state judging method and system for complex urban road network |
Also Published As
Publication number | Publication date |
---|---|
CN111145544B (en) | 2021-05-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111145544B (en) | Travel time and route prediction method based on congestion spreading dissipation model | |
He et al. | PAMSCOD: Platoon-based arterial multi-modal signal control with online data | |
CN105023433B (en) | A kind of traffic abnormal events of expressway coverage predictor method | |
CN104778834B (en) | Urban road traffic jam judging method based on vehicle GPS data | |
CN109215350B (en) | Short-term traffic state prediction method based on RFID electronic license plate data | |
CN104157139B (en) | A kind of traffic congestion Forecasting Methodology and method for visualizing | |
CN100444210C (en) | Mixed controlling method of single dot signal controlling crossing | |
CN104778835B (en) | High-grade road multi-bottleneck-point congestion evolution space-time range identification method | |
JP2002008183A (en) | Method of determining traffic situation based on reported vehicle data for traffic network including traffic-controlled network nodes | |
CN102346964A (en) | Real-time jam prediction and intelligent management system for road traffic network area | |
CN111161537B (en) | Road congestion situation prediction method considering congestion superposition effect | |
CN111915887A (en) | Integration and processing system and method based on multi-source heterogeneous traffic data | |
CN110634299B (en) | Urban traffic state fine division and identification method based on multi-source track data | |
He et al. | PAMSCOD: Platoon-based arterial multi-modal signal control with online data | |
CN111882858B (en) | Multi-source data-based method for predicting queuing length of highway abnormal event | |
Oh et al. | Real-time inductive-signature-based level of service for signalized intersections | |
CN106297296B (en) | A kind of fine granularity hourage distribution method based on sparse track point data | |
CN105654720A (en) | Detector laying method based on urban road jam identification | |
CN110766940A (en) | Method for evaluating running condition of road signalized intersection | |
CN112926768A (en) | Ground road lane-level traffic flow prediction method based on space-time attention mechanism | |
CN109859475B (en) | Intersection signal control method, device and system based on DBSCAN density clustering | |
CN112785859B (en) | System and method for controlling uniform timing of signal lamps in urban area | |
Gaur et al. | Method for real-time recognition of vehicle platoons | |
CN110097757B (en) | Intersection group critical path identification method based on depth-first search | |
CN112785840A (en) | Urban intelligent traffic computer control system and method |
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 |