[서평]「The Unified Modeling Language User Guide」

Short-term traffic forecast is one of the essential issues in intelligent transportation system. Accurate forecast result enables commuters make appropriate travel modes, travel routes, and departure time, which is meaningful in traffic management. To promote the forecast accuracy, a feasible way is to develop a more effective approach for traffic data analysis. The availability of abundant traffic data and computation power emerge in recent years, which motivates us to improve the accuracy of short-term traffic forecast via deep learning approaches. A novel traffic forecast model based on long short-term memory (LSTM) network is proposed. Different from conventional forecast models, the proposed LSTM network considers temporal-spatial correlation in traffic system via a two-dimensional network which is composed of many memory units. A comparison with other representative forecast models validates that the proposed LSTM network can achieve a better performance.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-its.2016.0208

LSTM network: a deep learning approach for short-term traffic forecast

Dynamic Traffic Assignment (DTA) has evolved substantially since the pioneering work of Merchant and Nemhauser. Numerous formulations and solutions approaches have been introduced ranging from mathematical programming, to variational inequality, optimal control, and simulation-based. The aim of this special issue is to document the main existing DTA approaches for future reference. This opening paper will summarize the current understanding of DTA, review the existing literature, make the connection to the approaches presented in this special issue, and attempt to hypothesize about the future.

Foundations of dynamic traffic assignment : the past, the present and the future

The vehicle routing problem

A MIcroscopic Traffic SIMulator (MITSIM) has been developed for modeling traffic networks with advanced traffic control, route guidance and surveillance systems. MITSIM represents networks in detail and simulates individual vehicle movements using car following, lane changing, and traffic signal responding logic. A probabilistic route choice model is used to capture drivers' route choice decisions in the presence of real time traffic information provided by route guidance systems. The simulator is a component of a larger system for evaluating traffic management systems and interacts with a surveillance module that can represent a wide variety of sensors (e.g. loop detectors, area sensors, probe vehicles, etc.) and a traffic management module which sets traffic signals and signs, routing recommendations, etc. MITSIM is coded in C+ + using object-oriented design and supports distributed implementation. It includes a graphical user interface for animating vehicle movements in the network and displaying aggregate traffic information such as speed and density.

A microscopic traffic simulator for evaluation of dynamic traffic management systems

Tools for evaluating traffic networks under information supply are a crucial necessity in view of the ATMS/ATIS systems being proposed and implemented around the world as part of Intelligent Vehicle-Highway Systems of the future. This paper presents an evaluation model that incorporates the driver response to information, the traffic flow behavior, and the resulting changes in the characteristics of network paths, into an integrated simulation framework. The model is based on simulating individual vehicle movements according to macroscopic flow principles, the driver path selection behavior under information being explicitly modelled. Detailed modelling of intersection delays as well as a variety of traffic control options for both freeways and arterials are performed. The path-processing component is designed for efficient application of the framework to large and realistic networks. The model can be effectively used for studying alternative information supply and traffic control strategies under various levels of market penetration of in-vehicle ATIS hardware. The paper also discusses its application to candidate networks.

An evaluation tool for advanced traffic information and management systems in urban networks

A day-to-day dynamic framework, in which the DYnamic Network Assignment Simulation Model for Advanced Road Telematics (DYNASMART) simulation-assignment model is applied to evaluate the performance of traffic networks, is developed to study network dynamics under real-time information and responsive signal control systems. The focus in this paper is primarily on commuter trips from home to work in a general network. Two levels of tripmaker decision-making processes are incorporated: (1) day-to-day dynamics and (2) real-time dynamics. Day-to-day dynamics consider the choices of departure time and route according to indifference bands of tolerable ‘schedule delay’, defined as the difference between the user's actual and preferred arrival times, and are thus governed by tripmakers' daily learning processes. Real-time dynamics consider en-route switching decisions in response to real-time information on prevailing traffic conditions. The resulting flows could be used in updating the supplied real-time information as well as the traffic control parameters. Two types of traffic control responsiveness are evaluated: (1) daily adjustment of signal timing parameters to reflect the preceding day's traffic patterns; and (2) real-time traffic-responsive signal control driven by prevailing flow patterns. The framework is illustrated through numerical experiments to investigate the day-to-day evolution of network flows under real-time information and responsive signal control, and assess the effectiveness of such information in a proper dynamic perspective.

Day-to-day evolution of network flows under real-time information and reactive signal control

Natural and/or man-made disasters have caused serious problems in transportation systems due to their unpredictable and destructive characteristics. Under disasters, transportation infrastructure plays an important role in emergency management; however, this infrastructure is also vulnerable because of disasters. One way to describe the vulnerable is through resilience. Resilience refers to the ability to recover from a disruption under unexpected conditions, such as natural and/or man-made disasters. How to enhance resilience of transportation infrastructure under disasters is an important issue when facing natural or man-made disasters. This study aims to measure and optimize transportation resilience under disasters. An optimization model for resilience under the constraints of budget and traversal time is proposed. One special feature is that preparedness and recovery activities are implicitly considered and incorporated within the optimization model. The mathematical model provides a good connection between preparedness/recovery activities and network-level resilience. In order to illustrate the proposed model, a real city network and assumptions on activities of emergency management are used in a series of numerical experiments. Traffic conditions before and after disasters are evaluated by the simulation-assignment model, DynaTAIWAN. Experiments and results illustrate advantages for network-level transportation resilience assessment and also prioritize preparedness and recovery activities under budget constraints.

A resilience optimization model for transportation networks under disasters

The dynamic vehicle routing problems (DVRP) is an extension of vehicle routing problems (VRP) in order to consider possible variations of travel times in the network. In this research, a two-stage framework for solving dynamic vehicle routing problem is proposed. In the first stage, the sweep method is adopted in vehicle assignment. In the second stage, a tabu search algorithm is implemented to improve routes under real-time information. The framework is implemented in an object-oriented approach and possible benefit from real-time information is illustrated through numerical simulation. The simulation-assignment model, DynaTAIWAN is applied in numerical simulation to evaluate real-time routing strategies in a traffic network. Numerical experiments are conducted in a 50 Nodes Network and a Taichung City. The results show that positive benefits could be achieved through utilization of real-time information with careful design.

An object-oriented evaluation framework for dynamic vehicle routing problems under real-time information

Travel time prediction in Advanced Traveler Information Systems is an important issue, because travel time is a major factor in motorists' decisions to avoid congestion and incidents. A simulation-assignment-based travel time prediction model for traffic corridors is constructed in this paper. Based on the concept of simulation-assignment models, two algorithms-the flowand the vehicle-based models-are proposed for travel time prediction. One of the critical issues in simulation-assignment models is how reliable time-dependent origin-destination (O-D) trip tables are generated. A dynamic O-D estimation and prediction procedure is developed to generate time-dependent O-D demand data for simulating vehicle movements using DynaTAIWAN: a simulation-assignment model. The empirical travel time data that were collected from electronic toll stations are used to validate the travel times that were predicted by the proposed models. The mean absolute percentage errors (RMSPEs) and root-mean-square percentage errors are less than 20% and 26% for the vehicle-based model and less than 10% and 12% for the flow-based model, respectively. The results show that the proposed algorithms predict reasonable travel times for traffic corridors.

Ta-Yin Hu

Papers

An evaluation tool for advanced traffic information and management systems in urban networks

Day-to-day evolution of network flows under real-time information and reactive signal control

A resilience optimization model for transportation networks under disasters

An object-oriented evaluation framework for dynamic vehicle routing problems under real-time information

Simulation-Assignment-Based Travel Time Prediction Model for Traffic Corridors