Cyber Spoofing Detection for Grid Distributed Synchrophasor Using Dynamic dual-Kernel SVM

Journal Article · Thu Nov 19 00:00:00 EST 2020 · IEEE Transactions on Smart Grid

DOI:https://doi.org/10.1109/tsg.2020.3039411· OSTI ID:1767849

Qiu, Wei ^[1]; Tang, Qiu ^[2]; Zhu, Kunzhi ^[2]; Yao, Wenxuan ^[3]; Ma, Jun ^[2]; Liu, Yilu ^[4]

---

1. Hunan Univ., Changsha (China); Univ. of Tennessee, Knoxville, TN (United States)
2. Hunan Univ., Changsha (China)
3. Hunan Univ., Changsha (China); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
4. Univ. of Tennessee, Knoxville, TN (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Cyber spoofing with distributed synchrophasor adversely affects the decision-making and situational awareness of the power grid. To detect the spoofing trail, this letter proposes a composite signature-based cyber spoofing detection methodology. The intrinsic principal modes are first extracted from the distributed synchrophasor data. Then, multiple signatures of different intrinsic model components are derived to quantify the spoofing. Thereafter, the dynamic dual-kernel support vector machine is proposed to identify cyber spoofing using multiple signatures. Multiple experimental results using six spoofing methods have verified the validity of the methodology.

• Research Organization: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE; National Science Foundation (NSF)
• Grant/Contract Number: AC05-00OR22725; EEC-1041877
• OSTI ID: 1767849
• Journal Information: IEEE Transactions on Smart Grid, Vol. 12, Issue 3; ISSN 1949-3053
• Publisher: IEEE
• Country of Publication: United States
• Language: English

Related Subjects

24 POWER TRANSMISSION AND DISTRIBUTION
cyber spoofing
distributed synchrophasor
dynamic dual-kernel support vector machine