An Online Anomaly Learning and Forecasting Model for Large-Scale Service of Internet of Things

The online anomaly detection has been propounded as the the key idea of monitoring fault of large-scale sensor nodes in Internet of Things. Although the exciting progresses of research have been made in online anomaly detection area, the highly dynamic distribution makes the anomaly detection scheme difficult to be used in online manner. This paper presents an online anomaly learning and forecasting mechanism for large-scale service of Internet of Thing. Firstly, our model uses the reversible-jump MCMC learning to online learn anomaly-free of dynamics network and service data. Next, we perform a structural analysis of IoT-based service topology by Network Utility Maximization(NUM) theory. The result of experiment demonstrates the method accuracy in forecasting dynamics network and service structures from synthetic data.