Summary
Energy Internet drives power systems into highly integrated cyber-physical infrastructures, raising severe cybersecurity challenges. Vulnerability severity assessment is critical for defense, yet widely used CVSS faces three key drawbacks in power scenarios: insufficient modeling of power business impacts, heavy dependence on manual interpretation, and discrete levels failing fine-grained management. This paper proposes an adaptive, finegrained assessment method for power systems. Innovatively, knowledge graph and cascaded fuzzy logic are integrated to achieve three objectives: automatic feature extraction from vulnerability texts, continuous fine-grained severity scores instead of discrete grades, and adaptive matching to dynamic operational scenarios. Validated on CVE industrial control vulnerabilities, the proposed method outperforms CVSS in business relevance, critical risk discrimination and expert consistency, supporting refined and intelligent cybersecurity governance for power systems.
Additional informations
| Publication type | Session Materials |
|---|---|
| Reference | D2_11575_2026 |
| Publication year | |
| Publisher | CIGRE |
| Country | China, People's Republic of |
| Study committees | |
| File size | 1 MB |
| Price for non member | 30 € |
| Price for member | 30 € |
Authors
BI Leyu - Electric Power Research Institute, China Southern Power Grid; LIANG Zhihong - Electric Power Research Institute, China Southern Power Grid; YANG Yiwei - Electric Power Research Institute, China Southern Power Grid; HONG Chao - Electric Power Research Institute, China Southern Power Grid; JIANG Yixin - Electric Power Research Institute, China Southern Power Grid; XU Wenqian - Electric Power Research Institute, China Southern Power Grid; LI Pandeng - Electric Power Research Institute, China Southern Power Grid; CHEN Lin - Electric Power Research Institute, China Southern Power Grid
Keywords
