TRIGGERING REROUTES USING EARLY LEARNING MACHINE-BASED PREDICTION OF FAILURES

摘要

Network metrics are collected and analyzed. It is predicted by using machine learning whether a network element failure is relatively likely to occur based on the collected and analyzed network metrics. In response to predicting that a network element failure is relatively likely to occur, traffic in the network is rerouted in order to avoid the network element failure. Application to Low Power and Lossy Network (LLN).