Investigating a Raspberry Pi cluster for detecting anomalies in the smart grid
No Thumbnail Available
Authors
Candelario, Kasey
Booth, Chris
Ledger, Aaron St.
Matthews, Suzanne J.
Issue Date
2017-11
Type
proceedings-article
Language
Keywords
Multicore processing , Current measurement , Anomaly detection , Phasor measurement units , Workstations , Smart grids
Alternative Title
Abstract
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.
Description
Citation
K. Candelario, C. Booth, A. St.Leger and S. J. Matthews, "Investigating a Raspberry Pi cluster for detecting anomalies in the smart grid," 2017 IEEE MIT Undergraduate Research Technology Conference (URTC), Cambridge, MA, USA, 2017, pp. 1-4, doi: 10.1109/URTC.2017.8284197.
Publisher
IEEE