TY - GEN
T1 - Cluster-based Module to Manage Smart Grid Data for an Enhanced Situation Awareness
T2 - 2019 Resilience Week, RWS 2019
AU - Sundararajan, Aditya
AU - Riggs, Hugo
AU - Jeewani, Avinash
AU - Sarwat, Arif I.
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Under an imminent or ongoing cyberattack, utility network and security operation control center (NOC/SOC) analysts lack access to relevant, timely data, thus reducing their speeds of incident response and decision-making. To enhance their situation awareness, this paper proposes a Data Module (DM) that uses computer clusters to ingest, process, and store data from heterogeneous sources of smart grids and utility enterprise, and derive contextual relationships across attributes to infer meaningful trends. The goal of DM is to enhance situation awareness of its users in a time-constrained environment. The paper describes DM's architecture, presents three functions (correlation, classification and regression trees, and K-means clustering), and validates them using weather and smart meter data from a real Florida neighborhood for the years 2013 to 2015. In doing so, this paper demonstrates the use of an independent module that can be readily customized and integrated into utility NOC/SOC for effective data ingestion and contextualization for well-informed decision-making.
AB - Under an imminent or ongoing cyberattack, utility network and security operation control center (NOC/SOC) analysts lack access to relevant, timely data, thus reducing their speeds of incident response and decision-making. To enhance their situation awareness, this paper proposes a Data Module (DM) that uses computer clusters to ingest, process, and store data from heterogeneous sources of smart grids and utility enterprise, and derive contextual relationships across attributes to infer meaningful trends. The goal of DM is to enhance situation awareness of its users in a time-constrained environment. The paper describes DM's architecture, presents three functions (correlation, classification and regression trees, and K-means clustering), and validates them using weather and smart meter data from a real Florida neighborhood for the years 2013 to 2015. In doing so, this paper demonstrates the use of an independent module that can be readily customized and integrated into utility NOC/SOC for effective data ingestion and contextualization for well-informed decision-making.
KW - Apache Hadoop
KW - ELK
KW - computer cluster
KW - data management
KW - regression
KW - situation awareness
UR - http://www.scopus.com/inward/record.url?scp=85079326677&partnerID=8YFLogxK
U2 - 10.1109/RWS47064.2019.8971817
DO - 10.1109/RWS47064.2019.8971817
M3 - Conference contribution
AN - SCOPUS:85079326677
T3 - Proceedings - 2019 Resilience Week, RWS 2019
SP - 81
EP - 87
BT - Proceedings - 2019 Resilience Week, RWS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 November 2019 through 7 November 2019
ER -