Page - 378 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

evaluating a new coordination approach based on multi-agent negotiation and comparing it with existing strategies in the context of a realistic operational scenario. Multi-agent negotiation, negotiation among more than two agents, has taken the attention of the AI research community in recent years. In the AOC domain, this has only been explored by one researcher [1]. There is a variety of negotiation protocols proposed in the literature. For instance, the Stacked Alternating Offers Protocol (SAOP) [2] governs the interaction among agents in a turn-taking fashion. One of the agents initiates the negotiation by making an offer. The next agent in line can accept this offer or make a counteroffer by overriding the previous offer, or end the negotiation. This process continues until reaching a mutual consensus or reaching a deadline. In the Single Text Mediated Protocol [3], there is an unbiased mediator searching for an agreement without knowing each agent’s preferences. The mediator initiates the negotiations by making a random bid and asks each agent to vote to accept or reject this offer. When all agents accept the given offer, the mediator keeps this offer as “most recently accepted bid”. In the next round, it only changes the value of one of the issues and asks agents to vote accept or reject this modified offer. Other protocols include the Feedback based Protocol [4], and the Intra-team negotiation protocol [5]. While some of these protocols involve an unbiased mediator, which aims to help negotiating agents to find a consensus; others focus on the interaction among only negotiating agents. In order to model negotiation in AOC, the authors developed a new approach similar to the single text mediated protocol. In the proposed policy, a team representative acts like a mediator to reach a unanimous agreement by making offers according to his preferences and asking other agents to vote for or against the given offers. This protocol is compatible with AOC in which the supervisor makes the final decision upon feedback from other experts. This paper proposes developing and evaluating a new multi-agent negotiation policy for airline disruption management. This was motivated by the need to improve coordination processes in AOC. The paper is organized as follows. Section 2 presents the simulated policies. Section 3 explains the development of the agent-based model and the case study. Section 4 explains how the model is verified. Section 5 provides the simulation results, and finally section 6 provides key conclusions of this work. Appendix A includes the ontology used for developing the agent-based model. 2. AOC disruption management policies 2.1. Current AOC Policies P1-P3 In order to select representative AOC policies and make a clear distinction between them, a critical element is the understanding of how AOC operators make their decisions in relation to various aspects during disruption management. Bruce [6] has systematically studied the decision-making processes of 52 controllers in six AOC centers and found out that airline controllers use policies with three different levels of performance. These policies are shown in table 1. S.Bouarfaetal. /AMulti-AgentNegotiationApproach forAirlineOperationControl378