IMPROVING RAIL NETWORK SIMULATIONS WITH DISCRETE DISTRIBUTIONS IN ONTIME

Abstract

To analyse a rail network’s punctuality and the operational quality of a timetable on a network-wide scale an advanced simulation is needed. Whereas most simulations use a Monte Carlo approach, we calculate delay distributions analytically and thus need only a single calculation run. Previously we used exponential distribution functions as they map the status in railway operations well and are suited for efficient calculation of delays. The resulting delay distributions due to primary delays along a train’s itinerary as well as delay propagation from other trains is handled by convolution of these distribution functions. However, as the resulting distributions become more complex, a simplification step is needed from time to time to keep calculation times reasonable. Increased requirements for the accuracy of the simulation model and improvements in the computational potential led us to remodel the delays with discrete distributions. This has two main advantages. First, restrictions on the possible form of primary delays are much smaller compared to the previous exponential distributions and second, the simplification step is no longer needed, which increases accuracy considerably. We discuss the different options of distribution modelling and their use in railway applications.