Methodological design and comparative evaluation of a MAS providing AmI

Researches on Ambient Intelligent and Ubiquitous Computing using wireless technologies have increased in the last years. In this work, we review several scenarios to define a multi-agent architecture that support the information needs of these new technologies, for heterogeneous domain. Our contribution consists of designing in a methodological way a Context Aware System (involving location services) using agents that can be used in very different domains. We describe all the steps followed in the design of the agent system. We apply a hybridizing methodology between GAIA and AUML. Additionally we propose a way to compare different agent architectures for Context Aware System using agent interactions. So, in this paper, we describe the assignment of weight values to agents interaction in two different MAS architectures for Context Aware problems solving different scenarios inspired in FIPA standard negotiation protocols.

► Designing in a methodological way a Context Aware System using Agents that can be applied to very different domains. ► We applied a hybridizing methodology between GAIA and AUML. ► We compared two (one is our proposal) agent architectures of context aware systems weighting exchanged messages. ► This evaluation was applied to FIPA-protocols inspired scenarios. ► We included an adhoc recommendation scenario involving users asking about the reputation of agent providers.