Decentralised metacognition in context-aware autonomic systems: some key challenges
Catriona M Kennedy · National Conference on Artificial Intelligence · 2010
A distributed non-hierarchical metacognitive architecture is one in which all meta-level reasoning components are subject to meta-level monitoring and management by other components. Such metacognitive distribution can support the robustness of distributed IT systems in which humans and artificial agents are participants. However, robust metacognition also needs to be context-aware and use diversity in its reasoning and analysis methods. Both these requirements mean that an agent evaluates its reasoning within a bigger and that it can monitor this global picture from multiple perspectives. In particular, social context-awareness involves understanding the goals and concerns of users and organisations. In this paper, we first present a conceptual architecture for distributed metacognition with context-awareness and diversity. We then consider the challenges of applying this architecture to autonomic management systems in scenarios where agents must collectively diagnose and respond to errors and intrusions. Such autonomic systems need rich semantic knowledge and diverse data sources in order to provide the necessary context for their metacognitive evaluations and decisions.