CN114049770A - Flow prediction method and system after circuit break of multi-mode traffic system - Google Patents
Flow prediction method and system after circuit break of multi-mode traffic system Download PDFInfo
- Publication number
- CN114049770A CN114049770A CN202111458041.1A CN202111458041A CN114049770A CN 114049770 A CN114049770 A CN 114049770A CN 202111458041 A CN202111458041 A CN 202111458041A CN 114049770 A CN114049770 A CN 114049770A
- Authority
- CN
- China
- Prior art keywords
- bus
- traffic
- flow
- road section
- road
- 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
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method and a system for predicting the flow of a multi-mode traffic system after circuit breaking, which belong to the technical field of traffic system flow prediction and are used for estimating the public transport traffic volume before and after circuit breaking; counting the track quantity of the floating car between the traffic districts to obtain a floating car sample OD matrix; estimating travel demands of non-public transport between traffic districts; carrying out traffic flow distribution on the estimated time-interval non-public traffic demand matrix; adjusting the estimated OD to obtain a calibrated time-interval non-bus trip OD matrix; obtaining a full-quantity multi-mode travel matrix; and adjusting the road network and the bus route. The invention adopts a traffic flow distribution method under the principle of user balance, the travel demand before the open circuit occurs is subjected to flow distribution again according to the changed road network structure, a multi-mode traffic system containing public buses is introduced, and the influence of public bus flow and line adjustment after the open circuit is considered in the flow prediction; the problem that travel demands are difficult to obtain in traffic flow distribution is solved by applying the track data of the commercial vehicles.
Description
Technical Field
The invention relates to the technical field of traffic system flow prediction, in particular to a multi-source data-based multi-mode traffic system flow prediction method and system after circuit breaking.
Background
The economic development drives the acceleration of the urbanization process, the increase of the urban road coverage area and the increase of the holding capacity of the passenger car. Along with the increase of the traffic pressure on the main roads of the city, higher requirements are put forward on urban traffic dispersion and planning control measures. Particularly for a road-closing construction scene, the traffic flow on the original road is dispersed on the peripheral road, which may exceed the traffic bearing capacity when the peripheral road is designed, further resulting in the diffusion and spreading of congestion.
The flow prediction method after road sealing construction commonly used in engineering practice is a pressure test, and is relatively easy to operate when the condition after road sealing is previewed in advance, but congestion can be really caused in the test stage, and only the condition after road sealing can be presented as a reference, and direct strategy guidance cannot be given. With the development of technologies such as sensing, communication, computers and the like, the basic capability of an Intelligent Traffic System (ITS) is greatly improved, and the development of research directions such as road condition prediction, route navigation, diversion and dispersion measures, congestion spreading early warning and the like is rapidly stimulated by richer road data and Intelligent algorithms. Therefore, the method provides possibility for traffic flow prediction and measure simulation after the road network interruption in advance.
However, the existing traffic prediction methods rely on historical data to simulate the short-term traffic conditions in the future, for example, statistical methods such as autoregressive moving average (ARIMA) and the like or system machine learning methods such as bayesian network algorithm and the like are adopted to capture the relation between the historical road conditions and the space-time characteristics and realize prediction. However, for the construction scene of the open circuit, no corresponding historical information can be used as a reference for the situation after the open circuit, and the timeliness is poor. In addition, the existing traffic prediction method rarely considers a multi-mode traffic system, namely, the condition that buses and small motor vehicles are mixed on the road, and the route adjustment of the buses can cause great influence on the road condition change after the circuit is broken, so that the traffic prediction method needs to be considered.
In a word, the traditional flow prediction method relies on historical traffic conditions to predict the flow in the next time interval. However, for the scenes of open circuit construction and the like, the traffic condition changes, and no proper historical data can be relied on during prediction. Private cars and buses are mixed on public roads, and the buses can cause larger influence on the road passing condition due to factors such as station entering and exiting and the like, so that the congestion is aggravated. When the circuit break occurs, the bus line can be correspondingly adjusted, and the driving of other vehicles is influenced. The traditional traffic distribution four-stage model is carried out by means of a large amount of traffic investigation and field analysis when the overall travel demand is acquired, and is often only applied to long-term and large-scale traffic planning. The method is poor in applicability for projects with road sealing construction periods of only a few months.
Disclosure of Invention
The present invention is directed to a method and a system for predicting a flow rate of a multi-mode traffic system after a circuit is broken, so as to solve at least one technical problem in the background art.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the invention provides a method for predicting flow after a circuit break of a multi-mode traffic system, which comprises the following steps:
step 1: dividing the research time period according to the traffic variation of the gate, the travel activity type and the dynamic pricing rule of the commercial vehicle;
step 2: counting the number of buses with stop stations on each road section before and after the circuit break, and estimating the bus traffic before and after the circuit break according to the bus departure frequency in different time periods;
and step 3: dividing a research area into traffic cells;
and 4, step 4: counting the track quantity of the floating car between traffic districts in all time periods all day before the occurrence of the open circuit to obtain a floating car sample OD matrix;
and 5: calculating traffic flow ratio of each mode of the sampling road section, carrying out sample expansion on the track quantity of the floating vehicles, and estimating the travel demand of non-public transport between traffic districts;
step 6: preloading the bus flow to a road network before interruption according to the departure frequency of the bus in different time periods, and then carrying out traffic flow distribution on the estimated time-period non-bus demand matrix;
and 7: the difference between the simulated flow and the actual observed flow on the minimized target road section is taken as a target, the estimated OD is adjusted, and a calibrated time-interval non-bus travel OD matrix is obtained;
and 8: correspondingly summing a non-bus travel matrix obtained by calibration based on the observation data and a bus travel matrix obtained by statistics to obtain a full-quantity multi-mode travel matrix;
and step 9: adjusting a road network and a bus line according to the open circuit construction condition of an actual scene;
step 10: repeating the traffic flow distribution step in the open circuit scene according to the step 6; on the road network preloaded with the adjusted bus flow, traffic flow distribution is carried out on the non-bus traffic flow among all the ODs to obtain the simulation flow of each road section after the circuit is broken in a balanced state; and then adding the sum with the adjusted statistical value of the public traffic throughput of each road section to obtain the multi-mode traffic flow prediction result after the road network is interrupted.
Preferably, the step 4 comprises: the floating car data is dotting positioning track data returned by vehicle-mounted equipment of the commercial vehicle; firstly, cutting a track into small sections of strokes from order dimensions; taking out a travel track of the order starting time within the research time period range; and counting the number of the travel tracks with the cell o as a starting point and the cell d as a terminal point by pair-by-pair OD to form a floating car sample matrix.
Preferably, the step 5 comprises: collecting a total flow observed value of a road section communicated with a broken circuit position by using a bayonet device arranged near an intersection; the bus flow is obtained by indirectly calculating the number of road sections and bus departure frequency, wherein the number of the road sections and the bus lines can be obtained by matching bus stop coordinates to the road sections; the floating car flow is to count the track quantity passing through the road section in a target time period; and calculating to obtain the proportion of the floating vehicles in the non-public vehicles, and expanding the magnitude of the floating vehicle sample matrix according to the average value of the proportion of each target road section to obtain an estimated OD matrix of the non-public vehicles in a certain time period.
Preferably, the step 6 includes: according to the departure frequency of the buses in different periods, the bus flow is preloaded on a road network before interruption, and then traffic flow distribution is carried out on the estimated time-period non-bus demand matrix, namely the road section passing time is simultaneously influenced by the bus and the non-bus trip flow on the road section, and the non-bus trip simulation flow on the target road section can be obtained after the non-bus flow reaches a balanced state.
Preferably, the step 9 includes: deleting the road sections which are influenced by construction and can not pass through from the road section set before the circuit break to obtain a road section set under a new road network; the bus route is usually adjusted according to the construction influence range, a new route is matched to a corresponding road section in a road network, and the influence of the bus route projected on the road section is depicted by the number of bus stop stations and bus route and bus number on the road section.
Preferably, the multi-mode traffic flow prediction result after the road network on the target link is disconnected is compared with the actual flow observed value after the road network is disconnected, and the result is used as the evaluation of the prediction effect of the model method.
Preferably, in step 6, the method for acquiring the road section simulation flow rate includes the following steps:
loading the bus flow on each road section; distributing traffic flow to the estimated non-public traffic OD on the road network before the open circuit loaded with the public traffic flow; and solving the traffic flow distribution condition in the balanced state to finally obtain the flow distribution result on each road section in the balanced state.
Preferably, based on the above technical solution, in step 7, the calibrating the estimated OD includes the following steps: constructing a loss function as the difference between the estimated flow and the actual observed flow, and calculating the error condition under the current estimated OD; and selecting an optimization algorithm, adjusting the preset OD according to an optimization target, and finally obtaining a non-bus travel OD matrix after the real observation value is calibrated.
In a second aspect, the present invention provides a computer device comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, the processor invoking the program instructions to perform the method for post-outage traffic prediction for a multi-mode traffic system as described above.
In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, the processor invoking the program instructions to perform the method for post-outage traffic prediction for a multi-mode transportation system as described above.
In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the method for post-outage traffic prediction for a multi-mode traffic system as described above.
The invention has the beneficial effects that:
adopting a traffic flow distribution method under the principle of user balance, and carrying out flow distribution again on travel demands before the occurrence of the open circuit according to the changed road network structure, namely, carrying out path selection again by an original traffic traveler according to the situation after the open circuit, so that the problem that the traffic flow after the partial open circuit of the road network is difficult to predict by relying on historical data is solved; a multi-mode traffic system comprising buses is introduced, the influence of bus flow and line adjustment after disconnection is considered in flow prediction, and the prediction accuracy is improved; a convenient method for restoring travel demands is provided by utilizing the track data of the commercial vehicles, the total travel demands are estimated and calibrated according to the demands of the commercial vehicles, and the problem that the travel demands are difficult to obtain in traffic flow distribution is solved by applying the track data of the commercial vehicles.
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 flowchart of a flow prediction method after a circuit break of a multi-mode transportation system 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 or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below by way of the drawings are illustrative only and are not to be construed as limiting the invention.
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.
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.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
For the purpose of facilitating an understanding of the present invention, the present invention will be further explained by way of specific embodiments with reference to the accompanying drawings, which are not intended to limit the present invention.
It should be understood by those skilled in the art that the drawings are merely schematic representations of embodiments and that the elements shown in the drawings are not necessarily required to practice the invention.
Example 1
As shown in fig. 1, the present embodiment 1 provides a method for predicting a flow rate after a circuit break in a multi-mode transportation system, which includes the following steps:
step 1: dividing the research time period according to the traffic variation of the gate, the travel activity type and the dynamic pricing rule of the commercial vehicle;
step 2: counting the number of buses with stop stations on each road section before and after the circuit break, and estimating the bus traffic before and after the circuit break according to the bus departure frequency in different time periods;
and step 3: dividing a research area into traffic cells;
and 4, step 4: counting the track quantity of the floating car between traffic districts in all time periods all day before the occurrence of the open circuit to obtain a floating car sample OD matrix;
and 5: calculating traffic flow ratio of each mode of the sampling road section, carrying out sample expansion on the track quantity of the floating vehicles, and estimating the travel demand of non-public transport between traffic districts;
step 6: preloading the bus flow to a road network before interruption according to the departure frequency of the bus in different time periods, and then carrying out traffic flow distribution on the estimated time-period non-bus demand matrix;
and 7: the difference between the simulated flow and the actual observed flow on the minimized target road section is taken as a target, the estimated OD is adjusted, and a calibrated time-interval non-bus travel OD matrix is obtained;
and 8: correspondingly summing a non-bus travel matrix obtained by calibration based on the observation data and a bus travel matrix obtained by statistics to obtain a full-quantity multi-mode travel matrix;
and step 9: adjusting a road network and a bus line according to the open circuit construction condition of an actual scene;
step 10: repeating the traffic flow distribution step in the open circuit scene according to the step 6; on the road network preloaded with the adjusted bus flow, traffic flow distribution is carried out on the non-bus traffic flow among all the ODs to obtain the simulation flow of each road section after the circuit is broken in a balanced state; and then adding the sum with the adjusted statistical value of the public traffic throughput of each road section to obtain the multi-mode traffic flow prediction result after the road network is interrupted.
Specifically, step 1: and dividing the research time period by referring to the traffic variation of the gate, the type of the trip activities and the dynamic pricing rule of the commercial vehicle. Because the travel demands at different times in a day have obvious peak-peak flat changes, the travel characteristics at different time intervals may have differences, such as the influence of the dynamic price of a commercial vehicle on the taxi taking demand, and the like, the traffic flow prediction after demand restoration and disconnection is carried out at different time intervals, the consistency of the track quantity of the commercial vehicle and the traffic quantity relation of the small cars in each time interval is ensured, and the demand back-pushing and prediction accuracy is improved. The divided time period set of one day is denoted as T.
Step 2: and counting the number of buses with stop stations on each road section before and after the circuit break, and estimating the bus traffic before and after the circuit break according to the departure frequency of the buses in different time periods.
And step 3: the study area is divided into traffic cells according to geographical conditions, population distributions, etc. The set of traffic cells is denoted S, each cell may be considered as a start or end point of demand, i.e. any set of travel demands OD may be represented as
The traffic demand from o to d generated during time t can be recorded as
And 4, step 4: counting the track quantity of floating cars between traffic districts in each period of time all day before the occurrence of open circuit
Obtaining a floating car sample OD matrix ODfloat,t；
The floating car data is dotting positioning track data returned by vehicle-mounted equipment of the commercial vehicle. Firstly, cutting a track into small sections of strokes from order dimensions; then taking out the travel track of the order starting time within the research time interval range; finally, counting the number of travel tracks with the cell o as a starting point and the cell d as a terminal point by pairs of OD to form a floating car sample matrix ODfloat,t；
And 5: calculating traffic flow ratio of each mode of the sampling road section, carrying out sample expansion on the track quantity of the floating vehicles, and estimating the travel demand of non-public transport between traffic districts;
the sampled road segments are typically several major segments near the open circuit location, and for segment l, the total flow observations are collected by a gate device installed near the intersection and recorded as Vs,l(ii) a The bus flow is obtained by indirectly calculating the number of road sections and bus departure frequency and is recorded as Vb,lThe number of the bus lines on the road section can be obtained by matching the coordinates of the bus stops to the road section; the flow of the floating car is the statistics of the track quantity passing through the road section in the target time period and is recorded as Vc,l. Then the proportion of the floating vehicles to the non-public vehicles can be calculated
Expanding the magnitude of the floating car sample matrix according to the average value of the proportion of each target road section to obtain an estimated OD matrix OD of the non-public transport vehicle in the time period tE,t；
Step 6: preloading the bus flow to the road network before interruption according to the departure frequency of the bus in different time periods, and then carrying out prediction on the estimated time-period non-bus demand matrix ODE,tThe traffic flow distribution is carried out, namely the passing time of the road section is simultaneously influenced by the traffic flow and the non-public traffic travel flow on the road section, and the simulation flow of the non-public traffic travel on the target road section can be obtained after the non-public traffic flow reaches the balanced state
And 7: to minimise simulated and actual observed flows over a target sectionThe difference is taken as a target, the estimated OD is adjusted to obtain a calibrated time-interval non-public transport trip OD matrix
And 8: non-public transport travel matrix obtained based on observation data calibration
And a bus travel matrix OD obtained through statisticsB,tCorrespondingly summing to obtain a full-quantity multi-mode travel matrix ODM,t；
And step 9: adjusting a road network and a bus line according to the open circuit construction condition of an actual scene;
deleting the road sections which are influenced by construction and can not pass through from the road section set N before the circuit break to obtain the road section set N under the new road networknew(ii) a The bus route is usually adjusted according to the construction influence range, so that a new route is also required to be matched to a corresponding road section in a road network, and the influence of the bus route projected on the road section is depicted by the number of bus stop stations, bus route and bus order and the like on the road section because the coordinates of the whole route of the bus are not easy to obtain;
step 10: repeating the traffic flow distribution step in the open circuit scene according to the step 6; on the road network preloaded with the adjusted bus flow, the non-bus traffic volume among all the ODs
Distributing traffic flow to obtain the simulation flow of each broken road section in balanced state
Then the statistical value V of the adjusted public traffic throughput of each road section is calculatedb′,lAdding to obtain a multi-mode traffic flow prediction result V after the road network is interruptedM′,lI.e. by
Step 11: multi-mode traffic flow prediction result V after road network on target road section is interruptedM′,lAnd comparing the actual flow observed value after the circuit is disconnected as the evaluation of the prediction effect of the model method, wherein the error calculation formula is as follows:
wherein, VS′,lFor bayonet flow observations on the target section l after a circuit break, VM′,lFor multi-mode flow prediction results, NsAlso a set of target road segments; and selecting the integral error index as the effect evaluation of the model because the basic flow of different target road sections possibly has difference.
In step 5, the calculation method of the estimated OD matrix of the non-public transport vehicle is shown as a formula:
wherein, ODfloatA floating car sample OD matrix between traffic cells,
the proportion of the floating vehicles in the non-public vehicles on the target road section l,
average proportion of floating cars for N target road sections, NsIs a set of target road segments;
the proportion calculation formula of the floating vehicles in the non-public vehicles on the road section l is as follows:
wherein VS,lIs a road section total flow observed value; vb,lThe traffic flow is obtained by indirectly calculating the number of road sections and traffic routes by the bus departure frequency; vc,lIs the floating traffic flow.
In step 6, the method for acquiring the road section simulation flow comprises the following steps:
step 1: loading the bus flow on each road section; firstly, counting the number of bus stops falling on a road section and the line number in different directions one by one; then according to the line BSiDeparture frequency information f in a target time periodBSiCollecting; finally, calculating the bus traffic V on each road section according to a formulab,l，BSlIs a set of bus stops on directed road section l:
step 2: distributing traffic flow to the estimated non-public traffic OD on the road network before the open circuit loaded with the public traffic flow; according to the principle of user balance, for any pair of ODs, traffic is required to be distributed only on one or more paths with the minimum travel cost, that is, no traveler will change path selection; the balanced flow distribution under the above-mentioned path selection rule can be converted into solving the following convex programming equation:
u (x) is the overall passage cost, flFor allocated non-public traffic flow on road section l, tlFor the passage time of the road section l, the non-public traffic flow distributed on the road section and the pre-loaded public traffic flow Vb,lIn connection with this, the present invention is,
flow allocated to the mth path among the ods, FodIs the estimated total quantity of non-public transportation demand between od, Fod∈ODC，
In order to characterize whether the road section l is a 0-1 coefficient on the mth path with flow distribution from o to d, N is a road section set in the whole road network.
The transit time of the section l is determined according to the form of the BPR function given by the us highway administration:
wherein t isl0The time is the free flow time of the road section and is obtained by dividing the length of the road section by the speed limit; f. oflFor non-public traffic flow, V, allocated on road sectionsb,lFor calculated traffic flow, eta, on the road section lbThe method is characterized in that the method is a public transport adjustment coefficient, and because the public transport has the characteristics of longer vehicle body, larger passenger carrying capacity and the like, according to the regulations of relevant departments, one public transport is generally considered to be equivalent to 2 passenger cars; c is the link capacity, and α, β are adjustment coefficients related to the level of the link itself, and are determined with reference to the natural level of the road.
Step 3: solving the traffic flow distribution condition in the balanced state, wherein common methods include but are not limited to FW algorithm and the like, and finally obtaining the flow distribution result on each road section in the balanced state
In step 7, the calibration of the estimated OD comprises the following steps:
step 1: constructing a loss function as the difference between the estimated flow and the actual observed flow, and calculating the error condition under the current estimated OD, wherein the loss function has the following form:
NSis a collection of target road sections, VS,l-Vb,lIn order to remove the observed value of the residual traffic after the bus traffic is removed from the total traffic on the target road section l,
the method is a non-public traffic flow simulation result based on the estimated OD, and the optimization target is to minimize the difference between the simulation flow and the observed flow of each road section.
Step 2: and (3) selecting an optimization algorithm, adjusting the preset OD according to the optimization target defined in the previous step, wherein the algorithm can select a traditional random gradient descent method or a synchronous disturbance random approximation algorithm SPSA and the like. Finally obtaining a non-public transport travel OD matrix OD after the real observation value is calibratedE *。
In this embodiment 1, the multi-mode transportation system refers to a transportation system in which a private car and a bus run in a mixed manner; the open circuit means a partial interruption of the road network due to road closure work or the like.
Example 2
The embodiment 2 of the present invention provides an electronic device, including a memory and a processor, where the processor and the memory are in communication with each other, the memory stores a program instruction executable by the processor, and the processor calls the program instruction to execute a method for predicting a flow rate after a multi-mode traffic system is disconnected, where the method includes the following steps:
step 1: dividing the research time period according to the traffic variation of the gate, the travel activity type and the dynamic pricing rule of the commercial vehicle;
step 2: counting the number of buses with stop stations on each road section before and after the circuit break, and estimating the bus traffic before and after the circuit break according to the bus departure frequency in different time periods;
and step 3: dividing a research area into traffic cells;
and 4, step 4: counting the track quantity of the floating car between traffic districts in all time periods all day before the occurrence of the open circuit to obtain a floating car sample OD matrix;
and 5: calculating traffic flow ratio of each mode of the sampling road section, carrying out sample expansion on the track quantity of the floating vehicles, and estimating the travel demand of non-public transport between traffic districts;
step 6: preloading the bus flow to a road network before interruption according to the departure frequency of the bus in different time periods, and then carrying out traffic flow distribution on the estimated time-period non-bus demand matrix;
and 7: the difference between the simulated flow and the actual observed flow on the minimized target road section is taken as a target, the estimated OD is adjusted, and a calibrated time-interval non-bus travel OD matrix is obtained;
and 8: correspondingly summing a non-bus travel matrix obtained by calibration based on the observation data and a bus travel matrix obtained by statistics to obtain a full-quantity multi-mode travel matrix;
and step 9: adjusting a road network and a bus line according to the open circuit construction condition of an actual scene;
step 10: repeating the traffic flow distribution step in the open circuit scene according to the step 6; on the road network preloaded with the adjusted bus flow, traffic flow distribution is carried out on the non-bus traffic flow among all the ODs to obtain the simulation flow of each road section after the circuit is broken in a balanced state; and then adding the sum with the adjusted statistical value of the public traffic throughput of each road section to obtain the multi-mode traffic flow prediction result after the road network is interrupted.
Example 3
An embodiment 3 of the present invention provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the method for predicting a flow rate of a multi-mode traffic system after a shutdown is implemented, where the method includes the following steps:
step 1: dividing the research time period according to the traffic variation of the gate, the travel activity type and the dynamic pricing rule of the commercial vehicle;
step 2: counting the number of buses with stop stations on each road section before and after the circuit break, and estimating the bus traffic before and after the circuit break according to the bus departure frequency in different time periods;
and step 3: dividing a research area into traffic cells;
and 4, step 4: counting the track quantity of the floating car between traffic districts in all time periods all day before the occurrence of the open circuit to obtain a floating car sample OD matrix;
and 5: calculating traffic flow ratio of each mode of the sampling road section, carrying out sample expansion on the track quantity of the floating vehicles, and estimating the travel demand of non-public transport between traffic districts;
step 6: preloading the bus flow to a road network before interruption according to the departure frequency of the bus in different time periods, and then carrying out traffic flow distribution on the estimated time-period non-bus demand matrix;
and 7: the difference between the simulated flow and the actual observed flow on the minimized target road section is taken as a target, the estimated OD is adjusted, and a calibrated time-interval non-bus travel OD matrix is obtained;
and 8: correspondingly summing a non-bus travel matrix obtained by calibration based on the observation data and a bus travel matrix obtained by statistics to obtain a full-quantity multi-mode travel matrix;
and step 9: adjusting a road network and a bus line according to the open circuit construction condition of an actual scene;
step 10: repeating the traffic flow distribution step in the open circuit scene according to the step 6; on the road network preloaded with the adjusted bus flow, traffic flow distribution is carried out on the non-bus traffic flow among all the ODs to obtain the simulation flow of each road section after the circuit is broken in a balanced state; and then adding the sum with the adjusted statistical value of the public traffic throughput of each road section to obtain the multi-mode traffic flow prediction result after the road network is interrupted.
In summary, the method and the system for predicting the flow of the multi-mode traffic system after the circuit is broken in the embodiment of the invention select the traffic flow distribution method for modeling aiming at the problem that the traffic condition after the circuit breaking scene such as the road closing construction is difficult to predict by relying on historical data, and consider the influence of the multi-mode traffic system (bus), thereby more finely predicting the flow after the circuit is broken; meanwhile, travel demands are restored by taking track data of the commercial vehicles as a reference, and the problem that the total travel demands are difficult to obtain in a traffic flow distribution method is solved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts based on the technical solutions disclosed in the present invention.
Claims (10)
1. A method for predicting flow after a circuit break of a multi-mode traffic system is characterized by comprising the following steps:
step 1: dividing the research time period according to the traffic variation of the gate, the travel activity type and the dynamic pricing rule of the commercial vehicle;
step 2: counting the number of buses with stop stations on each road section before and after the circuit break, and estimating the bus traffic before and after the circuit break according to the bus departure frequency in different time periods;
and step 3: dividing a research area into traffic cells;
and 4, step 4: counting the track quantity of the floating car between traffic districts in all time periods all day before the occurrence of the open circuit to obtain a floating car sample OD matrix;
and 5: calculating traffic flow ratio of each mode of the sampling road section, carrying out sample expansion on the track quantity of the floating vehicles, and estimating the travel demand of non-public transport between traffic districts;
step 6: preloading the bus flow to a road network before interruption according to the departure frequency of the bus in different time periods, and then carrying out traffic flow distribution on the estimated time-period non-bus demand matrix;
and 7: the difference between the simulated flow and the actual observed flow on the minimized target road section is taken as a target, the estimated OD is adjusted, and a calibrated time-interval non-bus travel OD matrix is obtained;
and 8: correspondingly summing a non-bus travel matrix obtained by calibration based on the observation data and a bus travel matrix obtained by statistics to obtain a full-quantity multi-mode travel matrix;
and step 9: adjusting a road network and a bus line according to the open circuit construction condition of an actual scene;
step 10: repeating the traffic flow distribution step in the open circuit scene according to the step 6; on the road network preloaded with the adjusted bus flow, traffic flow distribution is carried out on the non-bus traffic flow among all the ODs to obtain the simulation flow of each road section after the circuit is broken in a balanced state; and then adding the sum with the adjusted statistical value of the public traffic throughput of each road section to obtain the multi-mode traffic flow prediction result after the road network is interrupted.
2. The method according to claim 1, wherein the step 4 comprises: the floating car data is dotting positioning track data returned by vehicle-mounted equipment of the commercial vehicle; firstly, cutting a track into small sections of strokes from order dimensions; taking out a travel track of the order starting time within the research time period range; and counting the number of the travel tracks with the cell o as a starting point and the cell d as a terminal point by pair-by-pair OD to form a floating car sample matrix.
3. The method according to claim 1, wherein the step 5 comprises: collecting a total flow observed value of a road section communicated with a broken circuit position by using a bayonet device arranged near an intersection; the bus flow is obtained by indirectly calculating the number of road sections and bus departure frequency, wherein the number of the road sections and the bus lines can be obtained by matching bus stop coordinates to the road sections; the floating car flow is to count the track quantity passing through the road section in a target time period; and calculating to obtain the proportion of the floating vehicles in the non-public vehicles, and expanding the magnitude of the floating vehicle sample matrix according to the average value of the proportion of each target road section to obtain an estimated OD matrix of the non-public vehicles in a certain time period.
4. The method of claim 1, wherein the step 6 comprises: according to the departure frequency of the buses in different periods, the bus flow is preloaded on a road network before interruption, and then traffic flow distribution is carried out on the estimated time-period non-bus demand matrix, namely the road section passing time is simultaneously influenced by the bus and the non-bus trip flow on the road section, and the non-bus trip simulation flow on the target road section can be obtained after the non-bus flow reaches a balanced state.
5. The method of claim 1, wherein the step 9 comprises: deleting the road sections which are influenced by construction and can not pass through from the road section set before the circuit break to obtain a road section set under a new road network; the bus route is usually adjusted according to the construction influence range, a new route is matched to a corresponding road section in a road network, and the influence of the bus route projected on the road section is depicted by the number of bus stop stations and bus route and bus number on the road section.
6. The method of claim 1, wherein the predicted multi-mode traffic flow is compared with an observed value of actual flow after a cut in a road network on a target road segment to evaluate the predicted effect of the model method.
7. The method according to claim 1, wherein the step 6 of obtaining the road section simulation flow comprises the following steps:
loading the bus flow on each road section; distributing traffic flow to the estimated non-public traffic OD on the road network before the open circuit loaded with the public traffic flow; and solving the traffic flow distribution condition in the balanced state to finally obtain the flow distribution result on each road section in the balanced state.
8. The method of claim 1, wherein the step 7 of calibrating the estimated OD comprises the following steps: constructing a loss function as the difference between the estimated flow and the actual observed flow, and calculating the error condition under the current estimated OD; and selecting an optimization algorithm, adjusting the preset OD according to an optimization target, and finally obtaining a non-bus travel OD matrix after the real observation value is calibrated.
9. An electronic device comprising a memory and a processor, the processor and the memory in communication with one another, the memory storing program instructions executable by the processor, the processor invoking the program instructions to perform the multi-mode transportation system post-outage traffic prediction method of any of claims 1-8.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method for post-outage traffic prediction according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111458041.1A CN114049770B (en) | 2021-12-01 | 2021-12-01 | Flow prediction method and system after circuit break of multi-mode traffic system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111458041.1A CN114049770B (en) | 2021-12-01 | 2021-12-01 | Flow prediction method and system after circuit break of multi-mode traffic system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114049770A true CN114049770A (en) | 2022-02-15 |
| CN114049770B CN114049770B (en) | 2023-03-21 |
Family
ID=80211952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111458041.1A Active CN114049770B (en) | 2021-12-01 | 2021-12-01 | Flow prediction method and system after circuit break of multi-mode traffic system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114049770B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002163748A (en) * | 2000-11-27 | 2002-06-07 | Natl Inst For Land & Infrastructure Management Mlit | Traffic flow prediction and control system by traffic flow simulating device |
| KR20030014552A (en) * | 2001-08-11 | 2003-02-19 | 명지대학교 | Method for traffic flow simulation of large scale network based origin and destination point |
| JP2013025545A (en) * | 2011-07-20 | 2013-02-04 | Sumitomo Electric Ind Ltd | Traffic evaluation device, computer program and traffic evaluation method |
| US20180174449A1 (en) * | 2016-12-19 | 2018-06-21 | ThruGreen, LLC | Connected and adaptive vehicle traffic management system with digital prioritization |
| CN109559512A (en) * | 2018-12-05 | 2019-04-02 | 北京掌行通信息技术有限公司 | A kind of regional traffic flow prediction technique and device |
| CN110599760A (en) * | 2019-10-17 | 2019-12-20 | 东南大学 | Travel behavior simulation method under multi-mode traffic network |
| US10810883B1 (en) * | 2016-06-03 | 2020-10-20 | Uber Technologies, Inc. | Travel time estimation |
| CN111915464A (en) * | 2020-07-04 | 2020-11-10 | 西南交通大学 | Passenger connection model and method for subway interruption interval considering conventional bus network |
| CN113053103A (en) * | 2021-02-19 | 2021-06-29 | 北京嘀嘀无限科技发展有限公司 | Traffic simulation model generation method, traffic flow prediction method and related device |
| CN113096404A (en) * | 2021-04-23 | 2021-07-09 | 中南大学 | Road blockade oriented quantitative calculation method for change of traffic flow of road network |
| CN113409576A (en) * | 2021-06-24 | 2021-09-17 | 北京航空航天大学 | Bayesian network-based traffic network dynamic prediction method and system |
-
2021
- 2021-12-01 CN CN202111458041.1A patent/CN114049770B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002163748A (en) * | 2000-11-27 | 2002-06-07 | Natl Inst For Land & Infrastructure Management Mlit | Traffic flow prediction and control system by traffic flow simulating device |
| KR20030014552A (en) * | 2001-08-11 | 2003-02-19 | 명지대학교 | Method for traffic flow simulation of large scale network based origin and destination point |
| JP2013025545A (en) * | 2011-07-20 | 2013-02-04 | Sumitomo Electric Ind Ltd | Traffic evaluation device, computer program and traffic evaluation method |
| US10810883B1 (en) * | 2016-06-03 | 2020-10-20 | Uber Technologies, Inc. | Travel time estimation |
| US20180174449A1 (en) * | 2016-12-19 | 2018-06-21 | ThruGreen, LLC | Connected and adaptive vehicle traffic management system with digital prioritization |
| CN109559512A (en) * | 2018-12-05 | 2019-04-02 | 北京掌行通信息技术有限公司 | A kind of regional traffic flow prediction technique and device |
| CN110599760A (en) * | 2019-10-17 | 2019-12-20 | 东南大学 | Travel behavior simulation method under multi-mode traffic network |
| CN111915464A (en) * | 2020-07-04 | 2020-11-10 | 西南交通大学 | Passenger connection model and method for subway interruption interval considering conventional bus network |
| CN113053103A (en) * | 2021-02-19 | 2021-06-29 | 北京嘀嘀无限科技发展有限公司 | Traffic simulation model generation method, traffic flow prediction method and related device |
| CN113096404A (en) * | 2021-04-23 | 2021-07-09 | 中南大学 | Road blockade oriented quantitative calculation method for change of traffic flow of road network |
| CN113409576A (en) * | 2021-06-24 | 2021-09-17 | 北京航空航天大学 | Bayesian network-based traffic network dynamic prediction method and system |
Non-Patent Citations (4)
| Title |
|---|
| HALI PANG ET AL: "Simulation of Urban Macro-Traffic Flow Based on Cellular Automata", 《2019 CHINESE CONTROL AND DECISION CONFERENCE (CCDC)》 * |
| JIAN-XUN DING ET. AL: "A Mixed Traffic Flow Model Based on a Modified Cellular Automaton in Two-Lane System", 《2009 INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL SCIENCES AND OPTIMIZATION》 * |
| 王志建: "基于EMD-GRU循环神经网络的转向交通流量组合预测", 《工业控制计算机》 * |
| 陈丹等: "基于贝叶斯估计的短时空域扇区交通流量预测", 《西南交通大学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114049770B (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112818497B (en) | Traffic simulation method, traffic simulation device, computer equipment and storage medium | |
| Hellinga et al. | Assessing expected accuracy of probe vehicle travel time reports | |
| JP7163099B2 (en) | ENERGY MANAGEMENT DEVICE, MODEL MANAGEMENT METHOD AND COMPUTER PROGRAM | |
| Li et al. | A dynamic simulation model of passenger flow distribution on schedule-based rail transit networks with train delays | |
| US11847907B2 (en) | Traffic flow simulator, simulation method of traffic flow, and computer program | |
| Yan et al. | Performance evaluation of bus routes using automatic vehicle location data | |
| JP7062553B2 (en) | Information processing equipment, information processing methods and computer programs | |
| CN114049770B (en) | Flow prediction method and system after circuit break of multi-mode traffic system | |
| Yelchuru et al. | Analysis, modeling, and simulation (AMS) testbed development and evaluation to support dynamic mobility applications (DMA) and active transportation and demand management (ATDM) programs-Chicago testbed analysis plan. | |
| Kim | Simultaneous calibration of a microscopic traffic simulation model and OD matrix | |
| Henderson | A planning model for optimizing locations of changeable message signs | |
| Hadi et al. | Application of dynamic traffic assignment to advanced managed lane modeling. | |
| Hernández‐Moreno et al. | Transient traffic energy‐use analysis employing video‐tracking and microscopic modeling techniques: A case study using electric and combustion engine vehicles | |
| Hossain et al. | Development of a real-time crash prediction model for urban expressway | |
| Mahmassani et al. | Implementation of a weather responsive traffic estimation and prediction system (TrEPS) for signal timing at Utah DOT. | |
| Memon et al. | Calibration of a rule-based intelligent network simulation model | |
| Hu | Measuring the effectiveness of advanced traveler information systems (ATIS) | |
| Thilakshan et al. | An Approach to Identify Bottlenecks in Road Networks using Travel Time Variations: A Case Study in the City of Colombo and Suburbs | |
| Khan et al. | Hybrid Data Implementation: Final Report for Task Number 3643 | |
| Gardes et al. | Bay Area Simulation and Ramp Metering Study | |
| Kanteti | Effect of Vehicle Connectivity on the Safety Performance of Freeway Acceleration Speed Change Lanes | |
| Abd-Elazeem et al. | Constructing Route Choice Mobile Application Using the Real-Time Traffic Information | |
| Oghoyafedo et al. | Capacity Evaluation Along Benin-Lagos Expressway by Traffic Flow and Time Headway Approach | |
| Mamdoohi | Optimization and Machine Learning Methods Toward Improved Traffic Network Performance in Disrupted Environments | |
| Kabir | Data Driven Method to Assess Safety and Energy on Freeway and Intersection Performance Using Probe Vehicle |
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 |