Publication Type:

Conference Paper

Source:

2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT) (2016)

URL:

http://ieeexplore.ieee.org/abstract/document/7530186/

Keywords:

Anomaly detection, Clustering algorithms, computer network security, Computers, cyber security threats, Denial of Service, floods, Home area network, home computing, home networks, Intrusion detection, k-Means algorithm, K-means clustering, pattern clustering, Smart grid, smart grid functionalities, smart grid networks, smart grid traffic data clustering, Smart grids, Smart homes, Smart meters, Smart power grids, utility centre

Abstract:

Strengthening of Smart Grid functionalities has become the need of the 21st Century. Security evolves to be the primary concern at the deployment level of Smart Grids. Cyber security threats and vulnerabilities in Smart grid Network needs to be addressed before the deployment of the Smart Grid. Our proposed intrusion detection scheme identifies anomalies in the Smart Grid traffic and detects attacks like flooding which causes Denial of Service in Smart Grid Networks. This paper applies k-Means algorithm for clustering of traffic data and outlier detection for the data transmitted between utility Centre and the Smart Homes. Performance of the algorithm has been compared with other clustering algorithms and the results were found to have higher percentage in anomaly detection.

Cite this Research Publication

D. M. Menon and Dr. Radhika N., “Anomaly detection in smart grid traffic data for home area network”, in 2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT), 2016.