masdima - multi-agent system for disruption management

 

1. doctoral research project - abstract

Airline companies make a huge effort to maximize their revenue while keeping their costs at a minimum. This is not an easy task and, because of that, airline companies invest in tools that allow to optimize their operational schedule. Unfortunately, any operational plan has a strong probability of being affected, not only by large disruptions like the one that happened in April 2010 due to the eruption of the Iceland Eyjafjallajökull volcano but, more frequently, by smaller daily disruptions caused by bad weather, aircraft malfunctions and crew absenteeism, for example. These disruptions affect the original schedule plan, delaying the flights, and cause what is called an Irregular Operation. Studies have estimated that irregular operations can cost between 2% and 3% of the airlines annual revenues and that a better recovery process could result in cost reductions of at least 20% of its irregular operations. Considering the above, the Airline Operations Control Centre (AOCC) tries to manage disruptions by trying to find a solution with a minimum impact to the airline schedule and with the minimum cost. Usually, the AOCC solves the disruptions in a sequential process, i.e., first solving the aircraft part of the problem, then the crew part and, finally, the passenger part. Most of the process is done manually by experienced operators with the help of some computer-based tools.
MASDIMA is capable of monitoring the operational plan and deciding if an event requires or not an action. It is autonomous with decision making capabilities and automates the repetitive tasks; it is adaptive to changes on the environment (includes learning capabilities); it is dynamic and provides solutions in almost real-time and allows the inclusion of a human-in-the-loop to improve the user acceptance of the solutions found automatically by reacting and learning the preferences of this user.

2. list of publications

"Towards an Autonomous and Intelligent Airline Operations Control",, Antonio J.M. Castro, Ana Paula Rocha and Eugenio Oliveira, Proceedings of the 2012 15th IEEE Conference on Intelligent Transportation Systems (ITSC 2012), pp. 1429-1434, Anchorage, Alaska, USA, September 16-19.

"A New Concept for Disruption Management in Airline Operations Control", Antonio J. M. Castro and Eugenio Oliveira, Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, Vol. 225, N. 3 (March 2011), pp. 269-290. DOI: 10.1243/09544100JAERO864

Disruption Management in Airline Operations Control - An Intelligent Agent-Based Approach”, Antonio J.M. Castro and Eugenio Oliveira,
Web Intelligence and Intelligent Agents, edited by Zeeshan Usmani, ISBN 978-953-7619-85-4, IN-TECH 2010.

"Minimizing Airport Peaks Problem by Improving Airline Operations Performance through an Agent Based System", Antonio J.M. Castro, Antonio Mota, Luis Paulo Reis and Eugenio Oliveira, New Trends in Artificial Intelligence, Local Proceedings of the 14th Portuguese Conference on Artificial Intelligence (EPIA2009), pp. 3-14, ISBN: 978-972-96895-4-3, Universidade de Aveiro, Portugal, October 12-15, 2009.

"Recovering from Airline Operational Problems with a Multi-Agent System: a Case Study", Antonio Mota, Antonio J. M. Castro and Luis Paulo Reis,  Lecture Notes in Artificial Intelligence (LNAI 5816), Springer, Progress in Artificial Intelligence, 14th Portuguese Conference on Artificial Intelligence (EPIA2009), pp. 461-472, ISBN: 978-3-642-04685-8, Universidade de Aveiro, Portugal, October 12-15, 2009.

Quantifying Quality Operational Costs in a Multi-Agent System for Airline Operations Recovery”, Antonio J.M. Castro and Eugenio Oliveira, International Review on Computers and Software (I.RE.CO.S), Vol. 4, No. 4, pp. 504-516, ISSN 1828-6003, July 2009.

A Multi-Agent System for Airline Operations Control”, Antonio J.M. Castro and Eugenio Oliveira, 7th International Conference on PAAMS’09, Advances in Intelligent and Soft Computing 55, pp. 159-168, Springer-Verlag Berlin Heidelberg 2009. ISBN: 978-3-642-00486-5

Solving Airline Operations Problems using Specialized Agents in a Distributed Multi-Agent System”, Antonio J.M. Castro and Eugenio Oliveira
LNBIP 12 (ICEIS 2007), pp. 173-184, Springer-Verlag Berlin Heidelberg 2008, ISBN: 978-3-540-88709-6

The Rationale behind Development of an Airline Operations Control Centre using GAIA based Methodology", Antonio Castro and Eugenio Oliveira, Int. J. Agent-Oriented Software Engineering, Vol. 2, No. 3, pp.350-377, 2008

3. list of presentations

MASDIMA - Presentation in the Fraunhofer Portugal Challenge 2013
This is the advanced prototype I have developed during my PhD work to prove my hypotheses. It is a Distributed and Autonomous System that represents the Airline Operational Control Center with capacity to provided an Integrated solution to the problems in real-time and with adaptive characteristics.

A Multi-Agent System for Airline Operations Control
Presented at PAAMS 2009 in March, 26th 2009. Salamanca, Spain.

Using Specialized Agents in a Distributed MAS to Solve Airline Operations Problems: a Case Study
Presented at IAT 2007 in December 2007. Silicon Valley, USA.


4. list of research applications and demos

MASDIMA - Multi-Agent System for Disruption Management VIDEO DEMO
This is the advanced prototype I have developed during my PhD work to prove my hypotheses. It is a Distributed and Autonomous System that represents the Airline Operational Control Center with capacity to provided an Integrated solution to the problems in real-time and with adaptive characteristics.
e