Reliability and Delay Distributions of Train Connections

A review of train delay prediction approaches

“…Büker and Seybold (2012) propose a probability distribution convolution model for large railway networks, assuming exponentially distributed process times. Keyhani et al (2012) and Lemnian et al (2014) present stochastic graph approaches to predict the expected reliability of a scheduled train connection. Kecman and Goverde (2015b) use a microscopic TEG model to predict train events with dynamic edge weights.…”

“…The prediction horizon lasts from a few minutes up to a few hours. Predictions lead to a psychologic reduction of discomfort due to known delay against unknown delay; in case of connections, the predicted probability of catching the connecting train creates awareness (see Keyhani et al (2012). Effects can be changes in route choice resulting in a potential replanning of transport chains (e.g., transfers, different trains).…”