Nan Zou

Simulation-based emergency evacuation system for Ocean City, Maryland, during hurricanes

This paper presents a simulation-based system for Ocean City, Maryland, evacuation during hurricanes. The proposed model features integration of optimization and simulation that allows potential users to revise the optimized plan for both planning and real-time operations. Since it is difficult to capture all network operational constraints and driver responses fully with mathematical formulations, six evacuation plans for Ocean City were investigated. Each was optimized initially with the optimization module and then revised on the basis of the results of simulation evaluation. To address potential incidents during the evacuation, the study presents a real-time operation plan with a developed system that allows the responsible operators to concurrently evaluate all candidate responsive strategies and to track the performance over time of the implemented strategy.

Real-Time Bus Arrival Time Prediction: Case Study for Jinan, China

Providing real-time bus arrival information can help to improve the service quality of a transit system and enhance its competitiveness among other transportation modes. Taking the city of Jinan, China, as an example, this study proposes two artificial neural network (ANN) models to predict the real-time bus arrivals, based on historical global positioning system (GPS) data and automatic fare collection (AFC) system data. Also, to contend with the difficulty in capturing the traffic fluctuations over different time periods and account for the impact of signalized intersections, this study also subdivides the collected dataset into a bunch of clusters. Sub-ANN models are then developed for each cluster and further integrated into a hierarchical ANN model. To validate the proposed models, six scenarios with respect to different time periods and route lengths are tested. The results reveal that both proposed ANN models can outperform the Kalman filter model. Particularly, with several selected performance indices, it has been found that the hierarchical ANN model clearly outperforms the other two models in most scenarios.

Application of Advanced Traffic Information Systems: Field Test of a Travel-Time Prediction System with Widely Spaced Detectors

With increased congestion in most urban networks, providing reliable trip times to commuters has emerged as a critical challenge for all existing advanced traffic information systems. This paper presents the development and evaluation of a hybrid travel-time prediction model in a demonstration system sponsored by the Maryland State Highway Administration. The automated real-time travel-time prediction system is located on a 25-mi stretch of I-70 eastbound from MD-27 to I-695, which includes seven interchanges and 10 traffic detectors. To contend with the resource constraints of more than 1 mi in detector spacing, the proposed prediction model consists of two components: a multitopology neural network model with a clustering function as the main model and an enhanced k nearest neighbor model as the supplemental model. The evaluation results based on estimated travel times and field data collected by a third party indicate that the proposed hybrid model can provide reliable predictions of travel times in real-time operations in uncongested, congested, and transition traffic conditions.

Transit Priority Strategies for Multiple Routes Under Headway-Based Operations

This paper presents a transit signal priority (TSP) model designed to consider the benefits both to bus riders and to intersection passenger car users. The proposed strategy, which is mainly for headway-based bus operations, offers the responsible agency a reliable way to determine the optimal green extension or red truncation duration in response to multiple bus priority requests from different routes. The control objective is to minimize bus passenger waiting time at the downstream bus stop while ensuring that the delays for all passengers are not increased. In tests that used field data from Jinan, China, the proposed strategy showed promise in reducing bus passenger waiting time and total intersection delay. Further exploration with simulation experiments for sensitivity analysis found that TSP is most effective if the ratio between bus and passenger volumes exceeds a threshold of 2%.

A Reliable Hybrid Prediction Model for Real-time Travel Time Prediction with Widely Spaced Detectors

This paper presents a travel time prediction model that employs a small number of traffic detectors to perform real-time prediction under recurrent traffic conditions. The proposed model that consists of mainly a multi-topology Neural Network model and a supplemental component of an enhanced k-Nearest Neighbor model is capable of using various types of available information and contending with the potential detection errors and missing data. The evaluation results from field data have indicated that the developed hybrid model is capable of generating reliable prediction of travel times under various types of traffic conditions, and offers the potential for its application in a large freeway network.

Travel Time Prediction: Empirical Analysis of Missing Data Issues for Advanced Traveler Information System Applications

As reported in the literature for the applications of intelligent transportation systems with traffic detectors, various missing data patterns are frequently observed in such systems and may dramatically degrade their performance. This study presents two imputation approaches for contending with the missing data issues in travel time prediction. The first model is based on the concept of multiple imputation technique to predict directly the travel times under various missing data patterns. The second model that serves as the supplemental component is to estimate the missing detector values using neighboring detector data and historical traffic patterns. Both models have been incorporated with reliability indicators so as to assess the quality of imputed data and its applicability for use in prediction. The numerical example based on 10 roadside detectors on I-70 in Maryland has demonstrated that both developed models outperformed existing methods and offer the potential for field implementation.

An integrated emergency evacuation system for real-time operations - a case study of Ocean City, Maryland under hurricane attacks

The consecutive hurricane attacks to US coastline have drawn significant attentions to evacuation operations related issues. To better prepare the state of Maryland for potential hurricanes, this study presents an emergency evacuation system that integrates both optimization and microscopic simulation methods. The optimization module applies a two-level process to generate the preliminary optimal control plans, which is based on a revised cell transmission formulation for large-scale network applications. Using the optimized results as the initial input, the simulation module takes into account various operational constraints and driver responses that are difficult to be captured realistically with mathematical formulations. The proposed system also features its flexibility for potential users to adjust the optimized plans in both the planning phase and real-time operations based on the results of simulation evaluation. The case study with the data from Ocean City, Maryland during hurricane attacks has demonstrated the potential of the proposed system for evacuation of traffic flows in large-scale networks within a given time window.

Designing a Flexible Feeder Transit System Serving Irregularly Shaped and Gated Communities: Determining Service Area and Feeder Route Planning

This paper presents a mathematical model to design the appropriate service area and routing plans for a flexible feeder transit system serving irregularly shaped and gated communities. Given the fleet size and travel times between demand collection nodes, a mixed integer linear programming (MILP) model is developed to optimize the service area and transit route planning concurrently. The proposed model features a two-level structure with an upper level to maximize the number of served passengers by the feeder transit system and a lower level to minimize the operational cost for transit operators. This paper further presents a heuristic approach to yield acceptable solutions to the model in a reasonable amount of time. Case study results have demonstrated the effectiveness of the proposed model as well as the heuristic solution approach.

A bi-level multi-objective programming model for bus crew and vehicle scheduling

This paper focuses on the analysis of bus crew and vehicle scheduling under the management system commonly-seen in China. With considerations of management rules in practice and related regulations in China, this study proposes a bi-level multi-objective programming model for optimizing the crew and vehicle scheduling for the operation of public bus system. The developed model first estimates the lower bound of the global minimum number of drivers and buses needed in each week. The upper-level model minimizes the difference between the solution and the estimated lower bound and determine the number of vehicles needed; and then the lower-level model tries to minimize the number of drivers needed in each day. A branch and bound solution method has been developed to solve the proposed NP-Hard model, and has been programmed to achieve the computer aided crew and vehicle scheduling. A case study based on four different timetables demonstrated that the estimated lower bounds are with 13% of the global optimization that can ben achieved by the proposed approach. The implementation of the developed method can efficiently reduce the operation cost and support the automated intelligent scheduling for the Advanced Public Transportation System.

Average travel speed estimation using multi-type floating car data

Average travel speed is one of the most important indexes for traffic status identification. This paper presents a model to estimate average travel speed based on the data from multi-types floating cars (i.e., taxis, buses, and logistic vehicles). The concept of dynamic road section integration has been proposed to contend with critical issues such as small sample size and large sampling interval. To evaluate the effectiveness of the proposed approach, this paper has also tested the model performance with simulated data from the microscopic simulator VISSIM. Intensive numerical experiments revealed that the average errors of the estimated average speed are less than 7%, which indicates the proposed approach could improve the estimation accuracy significantly.