Page - 384 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

∀t1,t2 ∀x:AIRCRAFT_PROBLEM ∀y:CREW_PROBLEM at(Observation(AOS, Aircraft_problem(x))), t1) & at(Observation(AOS, Crew_problem(y))), t2) & ∃t3,t4 t3 < t1 & t4 < t2 & at(Communicate_from_to(AMS, ACo, inform, Aircraft_problem(x)), t3) & at(Communicate_from_to(AMS, CCo, inform, Crew_problem(y)), t4) ⇒ ∃t’,t’’ t’ > t1 & t’ > t2 & t’’ > t1 & t’’ > t2 ∃s: INTEGRATED_SOLUTION & at(Communicate_from_to(AOS, ACo, inform, integrated_solution(s)),t’) & at(Communicate_from_to(AOS, CCo, inform, integrated_solution(s)), t’’) This property is checked to ensure that the specialist agents provide solutions to the AOS before he announces offers to solve the problem. • Policy P4 - Property 2: If AOS announces an integrated disruption management solution, he should obtain within 5 minutes the vote results (approval/rejection) from both ACo and CCo on the AMS. Formally: ∀t1,t2 ∀s: INTEGRATED_SOLUTION & at(Communicate_from_to(AOS, ACo, inform, integrated_solution(s)),t1) & at(Communicate_from_to(AOS, CCo, inform, integrated_solution(s)), t2) ⇒ ∃t’, t’’, t3, t4 t’ < t1+5 & t’’ < t2+5 & t3 < t1+5 & t4 < t2+5 ∃z1,z2: VOTE_RESULT & at(Communicate_from_to(AOS, ACo, reply, vote_for(s, z1)), t’) & at(Communicate_from_to (AOS, CCo, reply, vote_for(s, z2)), t’’) & at(Observation(AOS, vote_for(s, z2)), t3) & at(Observation(AOS, vote_for(s, z2)), t4) This property is checked to ensure that the AOS obtain the vote results after he announces a solution to solve the problem. All the identified properties were verified as true for the developed agent-based model. 5. Simulation Results The four AOC policies introduced in Section 3 have been implemented and simulated in the presented agent-based model. For each of these four policies various results have been collected such as related to aircraft, crew, passengers, and the minimum time needed to manage the disruption. Table 2 presents the simulation results obtained for the four AOC policies. The outcome of policy P3 concurs with the best solution identified by the expert panel. However, the outcomes of P1 and P2 are significantly worse, and the outcome of P4 even outperforms the expert panel result. In order to understand the background of these differences, the agent-based simulation results have carefully been analyzed. Under policies P1 and P2, AOC operators make decisions based on limited coordination, as a result of which the disruption considered is not efficiently managed. The aircraft mechanical problem was eventually fixed, however the flight was cancelled. As a result, the 420 passengers were accommodated in hotels (i.e. greatly inconvenienced). This unfavorable outcome can be explained as a result of the possible actions identified by the crew controller i.e. “await crew from inbound aircraft” and “seek extensions to crew duty time.” Crew controllers mainly considered crew sign-on time and duty time limitations and tried to work within these constraints. In this scenario, none of the possible actions solves the crew problem. Under policy P3, AOC controllers consider complex crewing alternatives and can either choose to deadhead replacement crew from another airport or use crew from other aircraft. Therefore, under P3 the decision was made to reroute the flight via BOM and S.Bouarfaetal. /AMulti-AgentNegotiationApproach forAirlineOperationControl384