Distributed Self-Monitoring Sensor Networks Via Markov Switching Dynamic Linear Models

Abstract

Wireless sensor networks empowered with low-cost sensing devices and wireless communications present an opportunity to enable continuous, fine-grained data collection over a wide environment. However, the quality of data collected is susceptible to the hardware conditions and also adversarial external factors such as high variance in temperature and humidity. Over time, the sensors report erroneous readings, which deviate from true readings. To tackle the problem, we propose an efficient self-monitoring, self-managing and self-adaptive sensing framework based on a dynamic hybrid Bayesian network that combines Hidden Markov Model and Dynamic Linear Model. The framework does not only enable automatic on-line inference of true readings robustly but also monitor the working status of sensor nodes at the same time, which can uncover important insights on hardware management. The whole process also benefits from the derived approximation algorithm and thus supports on-line one-pass computation with minimum human intervention, which make the accurate formal inference affordable for distributed edge processing.