An Integrated Forecasting and Regularization Framework for Light Rail Transit Systems

In recent years, with half the world's population living in towns and cities and most of them relying heavily on public transport to meet their mobility needs, efficient and effective public transport operations have become critical to sustainable economic and social development. Nowadays, Light Rail Transit Systems (LRTSs) are considered to be the most promising technological approach to satisfy these needs, i.e. to ensure efficient and reliable urban mobility. However, LRTSs are subject to frequent minor disrupted transit operations, often caused by stochastic variations of passenger demand at stations and traffic conditions on the service routes, which increase passenger waiting times discouraging them from using the transit system. Although these minor disruptions usually last no longer than a few minutes, they can degrade the level of service significantly on a short headway service. In this paper the authors propose a real-time disruption control model for LRTSs based on an integrated quantitative forecasting and regularization approach. The forecasting component relies on Artificial Neural Networks, a non-parametric computational model that has proved to be particularly efficient for the forecasting task in several applicative domains. The regularization engine involves the formulation of a constrained mathematical programming problem which can be solved quickly and, therefore, is well suited for real-time disruption control. The conceptual model is applied to a case study concerning the transit line number 7 operating in the urban area of Milan. To validate the proposed forecasting and regularization framework an experimental plan has been designed and performed under different traffic and passengers demand fluctuation conditions. The results of the simulation study witness the efficacy of the overall approach to forecast and regularize the considered LRTSs.

Keywords:

• Intelligent Light Rail Train
• Feed-Forward Neural Networks
• Headway Variance Minimization
• Real-Time Regularization
• Discrete Event Dynamic Simulation

This work is part of the “iLRT—intelligent Light Rail Train” Research Project (Bogni et al., 2000) coordinated by Project Automation S.p.A. and cofunded by the Italian Ministry of Research (MIUR) within the framework of the Law n° 46/82.

The authors acknowledge the precious contribution of Dr. Andrea Sanchini (Sanchini, 2003), who designed and implemented the DEDS simulation model of transit line number 7 as well as the precious help of Matteo Cecchinello (Cecchinello, 2003) who performed the planned numerical experiment. The authors are grateful to the anonymous referees whose comments and criticisms significantly contributed to improve the quality of the article. The authors are indebted to Professor Hickman for his precious help and assistance during the referring process.