A Realistic Machine Learning-based Model for Failure Prediction and Propagation in Smart Grid Networks

Cyber-Physical Systems (CPS) combine communication and information technology functions to the physical components of a system for purposes of monitoring, controlling, and automation. The power grid is becoming one of the largest CPS, where grid components are controlled based on the synergies in the cyberspace. CPS hold a great promise to improve the efficiency and productivity of numerous sectors in Canada and around the world. However, cyber-security is a major concern in CPS including the smart grid where an intrusion in one part of the system can cause a failure in the entire network if not detected and dealt with in a timely fashion. The main objective of this research project is to develop a realistic model to enable the implementation of machine learning-based algorithms to detect cyber-attacks in a smart grid environment.

Faculty Supervisor:

Irfan Al-Anbagi;Kin-Choong Yow

Student:

Aliasghar Salehpourbarough

Partner:

Ericsson Canada

Discipline:

Engineering

Sector:

University:

University of Regina

Program: