Calibration of Vehicle and Driver Characteristics for Vissim Model, Ann-Based Sensitivity Analysis, Traffic Management, and Signal Design Using Ga for Mangalore City

Abstract

The field of traffic flow modeling has emerged as an important multi-disciplinary area with contributions from traffic-engineers, city-planners, mathematicians, and specialists in the field of computer sciences. Traffic engineers and planners constantly strive to alleviate problems that arise due to bottlenecks in traffic movement. One of the major challenges to traffic management lies in minimizing congestion and facilitating efficient traffic flow. The study of traffic congestion requires a proper understanding of the relationship between vehicle characteristics and driver characteristics to mimic existing traffic flows on urban streets.Simulation approaches permit traffic engineers of developing countries to evolve reliable models to investigate the influence of various factors related to roadways, and driver and vehicle characteristics on traffic flow on urban roads characterized by heterogeneous traffic conditions. These modeling techniques assist in gaining insight into the underlying relationships between the above factors involved. The primary scope of this study is focused on performing investigations using micro- simulation on understanding the traffic characteristics of Mangalore city in India, for heterogeneous traffic composition using VISSIM. A very important traffic circuit of the city connecting Hampankatta Circle, Navbharat Circle, PVS Circle, Bunts Hostel Circle, and Jyothi Circle, was considered for analysis, in addition to the nearby important locations such as Bendoorwell Junction, Balmatta Junction, and St. Theresa’s School Junction. In the initial phase of the study, the links and connectors representing the road network of the city were assigned in the VISSIM modeling environment on a template comprising a 1:5000 high- resolution base-map of the city overlaid with the layout of the roads and junctions using AutoCAD. Data on turning movements of traffic at various junctions was collected for 80 minutes during the peak-hour between 17:00 - 18.30 hours on Tuesday 10th March 2015 as part of this study. In this phase of the study, a number of simulation experiments were performed using the above data for default vehicle and driver characteristics, and the best random seed to be used for simulation was identified as 25, and 42 from among the random seeds from 1-50s tested. In the calibration exercise, the driver and vehicle parameters were fine-tuned in fourteen major stages to minimize errors between the observed data and the simulated results. 75% of the video-graphic data was used for performing testing and calibration, while the remaining 25% of the data was used for validation studies. An ANN-based sensitivity analysis was then performed to identify the relative importance of various vehicle and driver characteristics. A modified Garson’s approach was adopted in this study for the computation of relative sensitivity based on connection weights between the input layer, the three hidden layers, and the output layer for the optimized ANN configuration. Based on the results of the sensitivity analysis, the predictive capability of the simulation model was further enhanced by performing a multi-level extended calibration procedure that provided reliable results as per prescribed standards for traffic simulation. This finalized model was again validated successfully. The fully calibrated VISSIM model was the used inthe later phase of the study, to study the effect of implementing short-term strategies such as widening of existing road-widths, and long-term improvement strategies such as introduction of flyovers at selected critical locations in the city. Additionally, studies were performed using the genetic algorithm (GA) based approach in the design of traffic signal timings for streamlining traffic flows across four important junctions in the city. The objective function in the GA module was formulated based on the HCM average delay model (TRB 2000). The overall approach towards performing calibration studies evolved through the present study is expected to provide the basic framework for calibration and fine-tuning of vehicle and driver characteristics in the development of micro-simulation models. The findings of this study are expected to assist transport planners in developing innovative solutions to urban traffic management, analysis, design, and operation of vehicles on roadways.