A detection model for anomalies in smart grid with sensor network

Abstract

In this paper, we present a model to monitor the smart grid for any anomalous/malicious activity or attack. The model uses machine learning techniques to detect and classify anomalies from the sensory observations. It is helpful for ensuring the security and stability of the smart grid. The model relies on the real time data collected using wireless sensor networks as an overlay network on the power distribution grid. The overlay network of wireless sensors /devices uses a cluster topology at each tower to collect local information about the tower that is augmented by the linear chain topology to connect to the base station (usually at the substation). Preliminary results show that our classification mechanism is promising and is able to detect anomalous events that may cause a threat to the smart grid.