A Bayesian network approach to energy-aware distributed sensing

This paper presents a strategy for the design and implementation of an energy-efficient multi-sensor network, based on the structure of sectioned Bayesian networks. A key issue in the design of Bayesian networks for monitoring engineering systems is to ensure that a reliable inference scheme about the health of the system can be made by combining information acquired from each sensor in the system into a single Bayesian network. However, as the size of the network rapidly grows, aggregating information made by all the sensors becomes computationally intractable. Hence, sectioning of the Bayesian network based on functional or logical constraints allows for improved computational efficiency in aggregating information while reducing the overall communication requirements. This ultimately leads to a reduction of the energy cost which is critical to effective operation of the sensor network.