Decentralized approaches for self-adaptation in agent organizations

• Published in: ACM transactions on autonomous and adaptive systems 2012-04, Vol.7 (1), p.1-28
• Main Authors: Kota, Ramachandra, Gibbins, Nicholas, Jennings, Nicholas R.
• Format: Article
• Language: English
• Subjects: Agents (artificial intelligence)
• ISSN: 1556-4665; 1556-4703
• DOI: 10.1145/2168260.2168261

Self-organizing multi-agent systems provide a suitable paradigm for developing autonomic computing systems that manage themselves. Towards this goal, we demonstrate a robust, decentralized approach for structural adaptation in explicitly modeled problem solving agent organizations. Based on self-organization principles, our method enables the autonomous agents to modify their structural relations to achieve a better allocation of tasks in a simulated task-solving environment. Specifically, the agents reason about when and how to adapt using only their history of interactions as guidance. We empirically show that, in a wide range of closed, open, static, and dynamic scenarios, the performance of organizations using our method is close (70–90%) to that of an idealized centralized allocation method and is considerably better (10–60%) than the current state-of-the-art decentralized approaches.