Machine Learning Methods for Attack Detection in the Smart Grid

Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used to classify measurements as being either secure or attacked. An attack detection framework is provided to exploit any available prior knowledge about the system and surmount constraints arising from the sparse structure of the problem in the proposed approach. Well-known batch and online learning algorithms (supervised and semisupervised) are employed with decision- and feature-level fusion to model the attack detection problem. The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods. The proposed algorithms are examined on various IEEE test systems. Experimental analyses show that machine learning algorithms can detect attacks with performances higher than attack detection algorithms that employ state vector estimation methods in the proposed attack detection framework.

I. Introduction

Machine learning methods have been widely proposed in the smart grid literature for monitoring and control of power systems [1]–[4]. Rudin et al. [1] suggest an intelligent framework for the system design, in which machine learning algorithms are employed to predict the failures of the system components. Anderson et al. [2] employ machine learning algorithms for the energy management of loads and sources in smart grid networks. Malicious activity prediction and intrusion detection problems have been analyzed using machine learning techniques at the network layer of smart grid communication systems [3], [4].