Toward real-time decision making for bus service reliability

This paper addresses real-time decision making for a transit system based on a Bayesian network. It addresses issues associated with real-time control of bus operations to improve headway and minimize passenger wait time. The randomness of passenger arrivals at bus stops and external factors, such as traffic congestion and weather, in high frequency transit operations often cause highly irregular headway that can result in decreased service reliability. The approach proposed in this paper, which has the capability of handling the uncertainty of transit operations, applies holding control strategies to forestall bus unreliability and, where unreliability is evident, restore reliability. A real-life bus route operating in Wollongong, Australia together with its passenger load data are used in the simulation analysis to verify and evaluate the proposed approach.