Traffic Operations and Management

Region-Wide Congestion Prediction and Control Using Deep Learning

Mohanty, Sudatta
Pozdnukhov, Alexey
Cassidy, Michael
2020

Traffic congestion is forecast for neighborhoods within a region using a deep learning model. The model is based on Long Short-Term Memory (LSTM) neural network architecture. It forecasts a congestion score, defined as the ratio of the vehicle accumulation inside a neighborhood to its trip completion rate. Inputs include congestion scores measured at earlier times in neighborhoods within a region, and three other real-time measures of regional traffic. The ideas are tested using Newell’s simplified theory of kinematic waves. Simplified street networks are featured first. Initial tests...

Synergies of Combining Demand- and Supply-Side Measures to Manage Congested Streets

Itani, Ibrahim
Cassidy, Michael J.
Daganzo, Carlos
2021

An agent-based, multichannel simulation of a downtown area reveals the impacts of both time-shifting traffic demand with congestion pricing, and supplying extra capacity by banning left turns. The downtown street network was idealized, and loosely resembles central Los Angeles. On the demand-side, prices were set based on time-of-day and distance traveled. On the supply side, left-turn maneuvers were prohibited at all intersections on the network. Although both traffic management measures reduced travel costs when used alone, the left-turn ban was much less effective than pricing. When...

Traffic Signal Plans to Decongest Street Grids

Sadek, Bassel
Doig Godier, Jean
Cassidy, Michael J.
Daganzo, Carlos F.
2022

Two new synchronization strategies are developed for signalized grids of two-directional streets. Both strategies are found to reduce congestion significantly more than do other approaches. One of the strategies is static and the other adaptive. Both use a common timing pattern for all signals on the grid but use a different offset for each. The static strategy serves the morning rush by providing perfect forward progression on all streets in the directions that point toward a reference intersection, one that is located near the center of gravity of all workplaces. For the evening rush,...

Traffic Signal Plans to Decongest Street Grids

Sadek, Bassel
Doig Godier, Jean
Cassidy, Michael J.
Daganzo, Carlos F.
2022

Two new synchronization strategies are developed for signalized grids of two-directional streets. Both strategies are found to reduce congestion significantly more than do other approaches. One of the strategies is static and the other adaptive. Both use a common timing pattern for all signals on the grid but use a different offset for each. The static strategy serves the morning rush by providing perfect forward progression on all streets in the directions that point toward a reference intersection, one that is located near the center of gravity of all workplaces. For the evening rush,...

How and When Cordon Metering Can Reduce Travel Times

Doig, Jean
Daganzo, Carlos F.
Cassidy, Michael J.
2024
The paper addresses two questions regarding cordon metering that have until now gone unanswered. The first of these pertains to how and where a metered cordon ought to be placed in a city to be of greatest benefit. A simple 3-step rule is proposed that can be readily applied in real settings, and that we call the cordon layout conjecture, or CLC. Its use is shown to minimize the overall travel time...

An Analysis of HOT Lanes in North Carolina

Benjamin, JM
Sakano, R
McKinney, B
Khattak, AJ
Rodriguez, DA
Gaskin, C
2007

Many medium and small-size metropolitan areas in the U.S. face increasing traffic problems similar to large metropolitan areas. These metropolitan areas have responded primarily by expanding their road network and capacity. This paper explores the possibility of using a HOT lane in a medium-size metropolitan area for the same purpose. A detailed analysis and a suggested HOT lane solution are prepared for Greensboro-Winston-Salem-High Point metropolitan area. While high congestion are not widespread in the region now, a highway corridor is identified based on forecasted high...

The Market for Traffic Information-Study of Industry Structure and Prospects

Chan, Shirley
Malchow, Matthew
Kanafani, Adib
1999

The market for traffic information has grown considerably in the past 10 years. Traffic information is different from other goods because the cost to users is negligible and the product is indirectly priced. As a result of these unique characteristics, the classic economic model can not be applied to determine the price or the amount of information which would be produced and consumed under competitive equilibrium. Examination of the history of traffic information as a marketable good and the structure of the market indicate that traffic information providers are experiencing significant...

Evaluation of the Anaheim Advanced Traffic Control System Field Operational Test: Final Report Task B; Assessment of Institutional Issues

McNally, M.G.
Moore, James E., II
MacCarley, C. Arthur
Jayakrishnan, R.
1999

This report provides an overview of the technical and institutional issues associated with the evaluation of the federally-sponsored Anaheim Advanced Traffic Control System Field Operations Test. The primary FOT objective was the implementation and performance evaluation of adaptive traffic signal control technologies including an existing second generation approach, SCOOT, and a 1.5 generation control (1.5GC) approach under development. Also selected for implementation was a video traffic detection system (VTDS). The SCOOT evaluation was defined relative to existing, first generation UTCS...

Neural Network Models For Automated Detection Of Non-recurring Congestion

Ritchie, Stephen G.
Cheu, Ruey L.
1993

This research addressed the first year of a proposed multi-year research effort that would investigate, assess, and develop neural network models from the field of artificial intelligence for automated detection of non- recurring congestion in integrated freeway and signalized surface street networks. In this research, spatial and temporal traffic patterns are recognized and classified by an artificial neural network.

Estimating ATIS Benefits For The Smart Corridor

Sengupta, Raja
Hongola, Bruce
1998

This report studies the effects of Advanced Traveler Information Systems (ATIS) on traffic congestion in the Smart Corridor of the Santa Monica Freeway. Simulation modeling is used to estimate the potential travel time savings to divert traffic from the Smart Corridor to arterial roads when incidents occur. The study attempts to establish relationships between traffic management variables, such as incident detection time, incident duration, capacity reduction, percentage of traffic diversion, and duration of traffic diversion.