Abstract
Wireless sensor networks usually operate in dynamic, stochastic environments. While the behaviour of individual nodes is important, they are better seen as contributors to a larger mission, and managing the sensing quality and performance of these missions requires a range of online decisions to adapt to changing conditions. In this paper we propose an self-adaptive, self-managing and self-optimising sensing framework grounded in Bayesian dynamic linear models. Experimental results show that this solution can make sound scheduling decisions while also minimising energy usage.