Software agent reasoning supporting non-intrusive building space usage monitoring

•ZigBee based sensor network and underlying multi-agent software (MAS) have been integrated.•Several types of sensors were assembled with ZigBee host devices to produce compact multi-functional sensor units.•The agents can conduct belief-desire-intention (BDI) reasoning through real time ontology model query.•The agents can conduct resource negotiation, battery usage optimisation, and non-intrusive building space monitoring.

Conventional facility management (FM) software tools, lacking automatic synchronisation with the domain and rich semantic modelling, are limited to the simpler querying of manually maintained models. A software system that monitors and interprets temporally changing (internal) building environments and generates related knowledge can better assist in facility management decision making. This paper introduces a non-intrusive building monitoring framework that includes ZigBee sensor network and supporting software agents to provide better building space usage monitoring through software agents based on the belief-desire-intention (BDI) abstraction, exploiting ontology based reasoning to direct behaviour. The non-intrusive method is particularly useful and more amenable than the use of cameras for example when building monitoring involves human behaviours. The use of the multi agent paradigm renders a system that delivers demonstrable rationality and is robust within the dynamic environment that it operates. Agent behaviour directed at working towards goals is rendered intelligent with semantic web technologies. The capture of semantics through formal expression to model the environment adds a richness that the agents exploit to intelligently determine behaviours to satisfy goals that are flexible and adaptable. The agent goals are currently used to generate knowledge about building space usage as well as environmental conditions by elaborating and combining near real time sensor data and information from conventional building models. The deployed and tested sensor based monitoring framework exhibits intelligence that will find application in the better support of decision making by integration with existing FM tools.