Semantic Scholar Open Access 2015 540 sitasi

Machine Learning Methods for Attack Detection in the Smart Grid

M. Ozay I. Esnaola Fatos Tunay Yarman Vural S. Kulkarni +1 lainnya

Lihat Sumber DOI

Abstrak

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.

Topik & Kata Kunci

Computer Science Medicine

Penulis (6)

M. Ozay

I. Esnaola

Fatos Tunay

Yarman Vural

S. Kulkarni

H. Vincent Poor

Format Sitasi

APA MLA BibTeX

Ozay, M., Esnaola, I., Tunay, F., Vural, Y., Kulkarni, S., Poor, H.V. (2015). Machine Learning Methods for Attack Detection in the Smart Grid. https://doi.org/10.1109/TNNLS.2015.2404803

Akses Cepat

Lihat di Sumber doi.org/10.1109/TNNLS.2015.2404803

Informasi Jurnal

Tahun Terbit: 2015
Bahasa: en
Total Sitasi: 540×
Sumber Database: Semantic Scholar
DOI: 10.1109/TNNLS.2015.2404803
Akses: Open Access ✓