Investigating a Raspberry Pi Cluster for Detecting Anomalies in the Smart Grid

Document Type

Conference Proceeding

Publication Date

Winter 2-2017


Smart Grid Technology is an integral part of ensuring the security of the power grid. To provide situational awareness to grid operators, a smart grid system must be able to detect alarm events (such as sudden voltage fluctuations or drops in current) in close to real-time. In this paper, we propose the use of a low energy Raspberry Pi cluster to detect anomalies in the Smart Grid. We build a prototype cluster and test our approach on a real data set of approximately 1 million measurements derived from 8 PMUS from a 1000:1 scale emulation of a working power grid. Our results show that a cluster of 12 Raspberry Pis is capable of achieving better performance than a more power-hungry multicore server at lower cost and a significant reduction in power consumption.

USMA Center/Institute Affiliation

Cyber Research Center