Cooperative self Organization of agents for optimization : the electrical wiring example

Stéphanie Combettes (1, 2) , Pierre Glize (1) , Thomas Sontheimer (3) , Sylvain Rougemaille (3)

1 IRIT-SMAC - Systèmes Multi-Agents Coopératifs
2 UT3 - Université Toulouse III - Paul Sabatier
3 Upetec (Ramonville-Saint-Agne, France)

In aircrafts, densifying electrical systems and oversizing cables in order to respect constraints induce a useless increase in cable weight. This increase leads to additional costs of operation and to an unnecessary pollution during the plane operating life. In this paper we address optimization of harness weight which is a mono-objective problem with manifold and interdependent constraints. To solve this problem, we use a multi-agent approach based on the cooperative self-organization of agents. Performances obtained by the 'Smart Harness Optimizer' software that we have developed are promising for problems considered by the experts as being very difficult. In this article, we expose the method used to solve this Constraint Optimization Problem. Then we apply it to the addressed problem and finally we give results on typical cases and analyze them.

Mots clés: Emergent optimization; Cooperative self-organization; Autonomous local decision

Domaines: Intelligence artificielle [cs.AI]

Stéphanie Combettes, Pierre Glize, Thomas Sontheimer, Sylvain Rougemaille. Cooperative self Organization of agents for optimization : the electrical wiring example. 5th International Conference on Agents and Artificial Intelligence (ICAART 2013), Feb 2013, Barcelona, Spain. pp. 482-485. ⟨hal-01282035⟩