Authors:
Syed Muhammad Zeeshan Iqbal
;
Håkan Grahn
and
Johanna Törnquist Krasemann
Affiliation:
Blekinge Institute of Technology, Sweden
Keyword(s):
Railway traffic, Disturbance management, Optimization, Re-scheduling, Parallel computing, Multiprocessor.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Methodologies and Technologies
;
Operational Research
;
Optimization
;
Pattern Recognition
;
Scheduling
;
Software Engineering
;
Symbolic Systems
Abstract:
Railways are an important part of the infrastructure in most countries. As the railway networks become more
and more saturated, even small traffic disturbances can propagate and have severe consequences. Therefore, efficient
re-scheduling support for the traffic managers is needed. In this paper, the train real-time re-scheduling
problem is studied in order to minimize the total delay, subject to a set of safety and operational constraints.
We propose a parallel greedy algorithm based on a depth-first branch-and-bound search strategy. A number of
comprehensive numerical experiments are conducted to compare the parallel implementation to the sequential
implementation of the same algorithm in terms of the quality of the solution and the number of nodes evaluated.
The comparison is based on 20 disturbance scenarios from three different types of disturbances. Our
results show that the parallel algorithm; (i) efficiently covers a larger portion of the search space by exchanging
informatio
n about improvements, and (ii) finds better solutions for more complicated disturbances such as
infrastructure problems. Our results show that the parallel implementation significantly improves the solution
for 5 out of 20 disturbance scenarios, as compared to the sequential algorithm.
(More)