Home
Dynamic traffic assignment is an increasingly concerned tool for traffic analysis and evaluation. Its implementation attracts practitioners’ great interest meanwhile facing several big challenges. This document is aimed at providing the procedure of applying DTA method into practical projects with approaches for those challenges. The specific tools are DLSim (Deep Learning Based Traffic Simulation) and NeXTA (a visualization tool).
The process of dynamic traffic assignment program can be described according to the following Figure 1. The basic data input for a dynamic network loading program (f) includes time-dependent origin-destination demand (a) and the traffic network (b) with road capacity constraints on links and nodes. However, it is a challenge to obtain accurate dynamic demand and real-world network data required for practical application. Through calculating the dynamic travel time (c) of all links (free-flow travel time is used at first iteration), the route choice model (d) embeds a standard time-dependent least-cost path algorithm (e) to generate paths for all agents. The combination between least cost and the behavior of traveler’s choice is also still one challenging issue. The core dynamic network loading program (f) loads previously generated agents on the traffic network for the entire planning horizon, which produces link-based traffic states (h) that describes time-varying traffic states at the link level using traffic flow model (g) and updates the dynamic travel time database (c). At the following step within an iterative assignment process, the route choice module (d) will again re-compute the route selection for each agent using updated travel times (c), for another iteration of dynamic network loading (f), until the model is converged or reaches the maximum number of iterations.
Figure 1: Procedure of Dynamic Traffic Assignment
The DTA model usually relies on the estimates from Regional Travel Demand Model that can provide peak-period demand used for static traffic assignment. However, the peak-period demand is a fixed value and cannot satisfy the requirements for DTA implementation, 24 hour simulation for all day to capture the time-dependent congestion, so a temporal component have to be considered to obtain the dynamic demand. In NeXTA, the temporal component is a “time-slicing ratio” that divides the total demands into individual 15-minute interval.
In NeXTA, the input of “time-slicing ratio” is in input_demand_meta_data.csv file, and it defines loading period and the departure time for all vehicles. Table 1 is a departure time profile example:
Table 1 One Example of Departure Time Profile
| File_name | Format_ type | Start_time | End_time | 14:00 | 14:15 | 14:30 | 14:45 |
|---|---|---|---|---|---|---|---|
| Demand_Data\SOV_14_15.csv | matrix | 840 | 900 | 0.2 | 0.2 | 0.3 | 0.3 |
| Demand_Data\HOV_14_15.csv | matrix | 840 | 900 | 0.1 | 0.3 | 0.3 | 0.3 |
| Demand_Data\HPCE_14_15.csv | matrix | 840 | 900 | 0.2 | 0.2 | 0.3 | 0.3 |
| Demand_Data\MPCE_14_15.csv | matrix | 840 | 900 | 0.2 | 0.2 | 0.3 | 0.3 |
Project manager can estimate the time-slicing ratio according to his/her project experience or observed counts, the result of which should be consistent with existing traffic data (count, speed, ect.) as much as possible.
What needs to be done for time-dependent OD demand in NeXTA can be summarized in Table 2.
Table 2 Summary for time-dependent OD demand in NeXTA
| How to prepare | Input data | Output data | |
|---|---|---|---|
| Demand | Static Regional Travel Demand | Input_demand.csv | Time-dependent traffic demand |
| Departure time | Experience or observed time-dependent traffic count | Input_demand_meta_data.csv |
The network for DTA model is usually from Regional Travel Demand Model. Through the settings in import_GIS_settings.csv file, those various GIS network shape files from Regional Travel Demand Model can be imported into NeXTA and read by DTALite.
However, the lane capacity from macroscopic travel model is relative lower than its real value, because for static traffic assignment, reduced capacity can make up those lost travel time, to some extent, like the real stop time at intersections.
Therefore, it needs to adjust the lane capacity for different link types. In NeXTA, there is one column called “capacity_adjustment_factor” in input_link_type.csv. Project manager can estimate the factor value based on observed traffic data or his/her experience for different link type. Table 3 is the link type table for Atlanta network.
Table 3 Capacity Adjustment Factor in Input_Link_Type_csv
In DTALite, four traffic flow models are applied for traffic state calculation.
Table 4 Application of Traffic Flow Models in DLSIM
| Traffic flow model | Lane capacity | K** jam ** | ** Shock wave propagation through K **jam and backward wave _ w _ |
|---|---|---|---|
| BPR | Considered through volume/delay funciton, but allow V/C >1 | No | No |
| Point queue | Yes(its inflow capacity is infinite, and its outflow capacity is lane capacity ) | No | No |
| Spatial queue | Yes(its inflow capacity is infinite, and its outflow capacity is lane capacity and storage capacity of next lane) | Yes | No |
| Newell's simplified KW model | Yes(its inflow capacity is equal to its outflow capacity under free-flow traffic state for each lane) | Yes | Yes, applied on freeway only |
For detailed illustration about link capacity considered by different traffic flow models, please refer to the DTALite white paper (https://docs.google.com/file/d/0B7B_ItZxmow6TkNxRVA3Nk1kMVk/edit).
Since jam density is a key parameter for spatial queue model and Newell's KW model, it needs to calibrate this value for the base traffic flow model.
The process is called traffic flow model sensitivity analysis based on various jam density values. Through building the connection between simulated results (MOE) with different jam density values, users can compare the simulated data with observed data.
Finally, obtain the ideal jam density to reduce the difference between simulated MOE and observed MOE.
Figure 2 is an example of traffic flow model sensitivity analysis.
Usually the congestion location is the ideal place to calibrate traffic flow model. Where vehicles merge/diverge belongs to such place, so it is necessary to notice this topic. For on-ramp location: when the demand of mainline link and ramp link is more than the inflow capacity of downstream link, as shown in Figure 3. It needs to calibrate the distribution of the available inflow capacity for further traffic analysis. For off-ramp location: as the mesoscopic DNL model moves agents/vehicles with OD and path information, the proportions of vehicles moving out of a link to individual outgoing links are in fact determined directly by the paths (downstream node sequences) associated with vehicles at this link, as shown in Figure 4, so it becomes one part of OD demand matrix calibration.
Figure 3 Illustration of Merge.
Figure 4 Illustration of Diverge.
In DTALite, the route choice is based on generalized travel cost, so the parameters regarding the travel cost should be calibrated. Generalized travel cost = generalized travel time + toll /VOT+ operation cost/VOT Generalized travel time = arterial travel time + coeff * freeway travel time Operation cost = operation cost of distance unit * distance Here, the coefficient is based on the link reliability. Generally, travelers would like to choose freeway compared with arterial links in their trips, so we can define it as 0.881. The reference for this coefficient is Network Knowledge and Route Choice (Table 5-13, M. Ramming, Dissertation at MIT). In NeXTA, there is one column called “travel_time_bias_factor” in input_link_type.csv. This factor is indeed the coefficient of choice preference for different link type. The following is the link type table for Atlanta network.
Table 4 Illustration of Travel Time Bias Factor in Input_Link_Type.csv
In addition to coefficient for different link types, the parameters of generalized travel cost also include Value of Time (or distribution of value of time for different demand type) and operation unit cost. In NeXTA, the value of time is defined in input_VOT.csv, and the operation unit cost is defined in input_pricing_type.csv. Based on the given toll values in Scenario_Link_Based_Toll.csv, the parameters, such as, VOT and operation unit cost for different demand type, can be calibrated so as to match with observed data.
Data files node.csv link.csv demand and setings.csv video about the use of QGIS for visualizing network file Rachel's video link.
link_performance.csv
TD_link_performance.csv
path.csv
agent.csv
trajectory.csv