Frequency Data Compression for Public Transportation Network Algorithms (Extended Abstract)

Timetable information in public transportation networks exhibit a large degree of redundancy; e.g. consider a bus going from station A to station B at 6:00, 6:15, 6:30, 6:45, 7:00, 7:15, 7:30, . . . , 20:00, the very same data can be provided by a frequency-based representation as ’6:00-20:00, every 15 minutes’ in considerably less space. Nevertheless a common graph model for routing in public transportation networks is the time-expanded representation where for each arrival/departure event a single node is created. We will introduce a frequency-based graph model which allows for a significantly more compact representation of the network, resulting also in a speed-up for station-to-station queries. Moreover we will describe a new variant of Dijkstra’s algorithm, where also the labels are frequency-based. This approach allows for accelerating profile queries in public transportation networks. Introduction Buses, trains, subways etc. often depart at fixed intervals from the respective stations. Hence the compressibility of timetable information is high as we can represent a list of such departure events, e.g. 7:00, 7:05, 7:10, . . . , 12:00, also as triple (7:00, 12:00, 5min) containing the start and end time of the service and the frequency. In the following we will describe ways to improve the computation of fastest routes in public transportation networks based on this compressed representation. Modelling a Frequency-Based Graph A standard way to model timetable information into a graph is the time-expanded representation (as used e.g. in (Bast et al. 2010)). Here for every arrival/departure event at a station a node needs to be created, which results in a huge amount of data. In the time-dependent model the number of nodes/edges is significantly smaller, but the complexity of the departure events is now shifted into edge cost functions, which are costly to store and evaluate. Therefore both models are comparable in terms of space consumption and query times. We will now introduce an alternative graph model based on frequency-compression. Here we only create a node for each route per station (e.g. Bus 80 at main Copyright c © 2013, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. S205 S314