An Adaptive Penalized Weighted Least Squared Approach for Detecting and Mitigating Cyberattacks on Dynamic State Estimation
Bibliographic record
Abstract
Leveraging measurements from phasor measurement units (PMUs) within wide-area measurement systems (WAMSs) has empowered dynamic state estimation (DSE) to assume a crucial role in power system control and real-time contingency analysis. Yet, the susceptibility of WAMSs and PMUs to exploitation by attackers poses a significant threat. This vulnerability is underscored by the potential impact of false data injection attacks (FDIAs), where malicious data infiltrate DSE, compromising its accuracy and reliability. To address this concern, this article introduces an approach to detect and mitigate cyberattacks on DSE in power systems. The proposed method enhances the extended Kalman filter (EKF), commonly used for DSE, by incorporating a machine learning-based penalized weighted least squared (MLPWLS) approach. This augmentation ensures the accurate assignment of weights to measurements through an optimization process. Higher weight indicates greater trust in measurements, while lower weight signals vulnerability to cyberattacks. Consequently, measurements with lower weights are excluded to mitigate the impacts of cyberattacks. In fact, incorporating machine learning into the classic penalized weighted least square (CPWLS) method enhances its adaptability across a spectrum of operating conditions and in the face of diverse FDIAs. The performance of the proposed approach is evaluated on the IEEE 14-Bus and IEEE 39-Bus test systems under various attack scenarios.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".