Seite - 385 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

fly-in a replacement crew from PCF into BOM. Here, both the delayed crew and replacement crew were able to operate in one tour of crew duty time. This solution was chosen instead of using crew from other aircraft based on the transcript data from the expert panel simulations in [7]. In comparison to policies P1 and P2, policy P3 is much better from both the airline and the passenger’s perspectives. Regarding the minimum time required for managing the disruption policy, P3 takes more time than P1 and P2. Under policy P4, it was assumed that AOC agents make level 3 decisions similar to P3. Under P3, the crew controller agent can either consider various crew deadheading possibilities or user alternative crew from other aircraft. If the latter policy is followed, policy P4 is able to identify a possibility that had not been identified by the expert panel. The flight crew that had landed the aircraft at CDG had received sufficient rest to fly the delayed aircraft directly to PCF instead of enjoying their scheduled day-off in Paris. Passengers had a minimum delay compared to the previous policies (P1-P3) as they only had to wait for the aircraft to be fixed. If the assumption regarding AOC agents under policy P4 was changed to decision level 1 or 2 similar to P1 and P2, the crew problem would not have been resolved. Table 2. Simulation Results. P: Policy; FL: Flight; MP: Mechanical Problem; CP: Crew Problem; PAX: Passengers Problem; MDT: Minimum Disruption Management Time; OC: Operation Costs; TL: Time Lost for passengers. P FL MP CP PAX MDT OC PAXC TL P1 Cancelled Fixed Not resolved Distressed 26 min 326kEUR 168kEUR 24 P2 Cancelled Fixed Not resolved Distressed 30 min 326kEUR 168kEUR 24 P3 Diverted Fixed Resolved Delayed 33 min 360kEUR 126kEUR 8 P4 Delayed Fixed Resolved Delayed 29 min 326kEUR 0kEUR 3 6. Conclusion Efficient handling of disruptions by airlines requires advanced coordination and communication means employed by socio-technical teams, in which human operators are supported by intelligent technology. Human operators often demonstrate ingenuity and creativity in problem solving, particularly necessary for handing previously unknown disruptions. By combining these human abilities with the computational power and analysis capabilities of machines, diverse disruptions could be handled efficiently. It is worth noting that the final decision will be made by a human decision maker. The proposed system is supposed to support human controllers by recommending mutually agreeable solutions. In this paper, we investigated four policies for handling disruptions by a socio-technical team of the AOC, based on agent-based coordination and negotiation models. The policies varied in the level of performance in terms of reasoning and coordination capabilities of the involved agents. The effects of the policies were studied by simulation in the context of a realistic scenario involving a mechanical failure disruption. The results demonstrated that the effectiveness and efficiency of the policies were in direct relation to the capabilities of the agents: richer reasoning and coordination abilities resulted in more efficient and sophisticated solutions, generated within limited time. Another important contribution of the paper is the formal specification of the policies in an agent-based model using LEADSTO and TTL languages, which enabled simulation S.Bouarfaetal. /AMulti-AgentNegotiationApproach forAirlineOperationControl 385