A Planning Model for Optimizing Locations of Changeable Message Signs

Abstract

Changeable Message Signs (CMS) are commonly utilized by transportation agencies to inform motorists of traffic, roadway, and environmental conditions. They may be used to provide information, such as delay and alternate route guidance, in the event of an incident, construction or a roadway closure. The effectiveness of CMS in managing freeway traffic, however, is a function of many factors including the number of CMS installations, the location of CMS, the messages displayed, varied traffic network characteristics, and drivers' response to incident conditions and CMS information. The objective of this thesis is to develop a CMS location planning model that can be used by transportation agencies to develop a CMS location plan that could achieve the largest long-term benefit to the system. This research is mainly motivated by the lack of systematic, robust and practical methods for locating CMS. State-of-practice methods rely mostly on the practitioner's experience and judgement. Other methods fail to incorporate reasonable driver behaviour models, consider time-varying demand, allow for computational efficiency on large networks, or consider the spatial variation of incidents on a traffic network. A new CMS location optimization model has been developed that is unique in both model realism and computational efficiency. The model incorporates several components to estimate incident delay, predict driver response, estimate network-wide benefit, and choose those CMS locations that would provide the most benefit. Deterministic queuing methods are used in conjunction with historic incident characteristics to approximate the delay impact of an incident with and without CMS. A discrete choice model is used to predict the rate at which drivers would switch from the incident route to a less congested alternative under CMS information. A network traffic assignment model is then incorporated in an attempt to estimate the resulting traffic induced by incidents. Genetic algorithms are utilized as an optimization technique to choose a set of CMS that would provide the most benefit. An extensive computational analysis was performed on both a hypothetical network and a segment of Highway 401 through Toronto. A sensitivity analysis was performed to test the model's response to parameter and data estimation errors. The model was found to be most sensitive to the diversion model parameters. The model produced reasonable results with locations selected upstream of major freeway interchange diversion points. Considering the additional components included in the proposed model, and its ability to consider more location schemes, the proposed model may be considered superior to previous CMS location models.