Machine & Deep Learning on Protecting Smart Grid

 

G. Efstathopoulos, P. Radoglou Grammatikis, P. Sarigiannidis, V. Argyriou, A. Sarigiannidis, K. Stamatakis, M. Angelopoulos and S. Athanasopoulos, “Operational Data Based Intrusion Detection System for Smart Grid”, in IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks, Limassol, Cyprus, 2019, pp. 1-6. [Online] Available: https://zenodo.org/record/3834769



In the era of hyper-connected digital economies, the smart technologies play a vital role in the operation of the electrical grid, transforming it into a new paradigm. This new reality introduces severe cybersecurity issues due to insecure, legacy protocols. Our latest work entitled "Operational Data Based Intrusion Detection System for Smart Grid" proposed a novel approach for protecting modern smart grids by timely detecting cyberthreats and indications of attacks. This work was presented at the IEEE International Workshop on Computer Aided Modelling and Design of Communication Links and Networks and won the best paper award.

A Novel Cybersecurity Approach

  • Anomaly-based IDS especially designed for the smart grid, utilising operational data from a real power plant
  • Evaluation of multiple machine learning and deep learning models, introducing novel parameters and feature representations in a comparative study
  • The evaluation analysis demonstrates the efficacy of the proposed IDS and the improvement due to the suggested complex data representation

An Accurate & Efficient Tool for Energy Stakeholders

  • Metrics: Accuracy, F1, AUC
  • Evaluation Environment: Power plant of PPC S.A., in Greece
  • Via the proposed complex representation, the overall average Accuracy was increased by 29%, the F1 score by 22% and the AUC by 8%.

Paving the Way to a New Energy Market

The new solution introduced by this work paves the way for more accurate IDS, capable to detect a variety of threats in modern smart grids, thus, enabling the operators to timely respond to security incidents and rendering smart grids more secure and trusted. Moreover, the proposed solution opens new market opportunities in the energy domain, including: