A Multi-agent System for Intelligent Monotoring of Airline Operations

There are quite a few solutions for crew scheduling, including some commercial applications. The same happens for aircraft scheduling and for flight scheduling including revenue management. However, the airline operations problem did not receive the same attention as the other airline scheduling problems. In this paper we introduce this problem and report the work we are doing in the development of a Distributed Multi-Agent System that will encompass tasks like crew and aircraft recovery among others that are typical of airline operations control. The MAS deals with different operational bases and all bases cooperate to find the solutions to the local problems. Robustness is a key feature and we achieve that through redundancy in finding the possible solutions to the problem, using agents that compete in finding for the best solution to be applied. To be an “Intelligent System” some kind of learning must be available. We are using learning to define the crew member’s profile, to learn the use of stand by crew members and include this learning in future crew scheduling and in suggesting new solutions based on previous decisions. Finally, we would like to explore the possibility of having a “kind of electronic market” for available crew members/aircrafts among airline companies, to be used in crew and aircraft recovery. This would work as a “market” of solutions to specific local problems and these solutions would compete with the recommended local solutions. To develop the system the latest MAS methodologies, frameworks, tools and technologies will be used. This includes GAIA, JADE, Agent-web services and IBM Rational suite of tools.