Detection o f Cyber Attack i n Broad Scale Smart Grids u sing Deep a nd Scalable Unsupervised Machine Learning System

Abstract

The increase in the reliability, efficiency and security of the electrical grids was credited to the innovation of the smart grid. It is also a fact that the smart grids a very dependable on the digital communication technology that in turn gives rise to undiscovered weaknesses which have to be reconsidered for dependable and coherent power distribution. In this paper, we propose an unsupervised anomaly detection which is mainly focused the statistical correlation among the data. The main aim is to create a scalable anomaly detection system suitable for huge-scale smart grids, which are capable to denote a difference between a real fault from a disruption and an intelligent cyber-attack. We have presented a methodology that applies the concept of attribute extraction by the use of Symbolic Dynamic Filtering (SDF) to decrease compilation drift whilst uncovering usual interactions among subsystems. Results of simulation obtained on IEEE 39, 118 and 2848 bus systems confirm the execution of the method, proposed in this paper, under various working conditions. The results depict a precision of almost 99 percent, along with 98 percent of true positive rate and less than 2 percent of false positive rate.