Real-Time Evaluation of Cyberattack-Resilient Control for Secure Large-Scale Power Networks
Bibliographic record
Abstract
This paper studies the load frequency control (LFC) performance of a multi-area power network targeted by false data injection attacks (FDIAs). To this end, a cyberattack-resilient defense strategy consisting of the model and learning-based methods is proposed to improve the network frequency response. A strategy based on comparing the state estimation performed by the model-based observer with a threshold value is used in the presented mechanism to detect attacks. After detecting an attack, an artificial intelligence (AI) observer predicts the control signals and compares them with the observed ones. When there is a significant deviation, an event-trigger strategy blocks the observed signal and sends the predicted signal to the physical network. In the presented strategy, a model-free nonsingular terminal sliding mode control (MFNTSMC) scheme based on the ultra-local model (ULM) principle is also developed as the secondary controller to regulate the network frequency response under FDIAs. Also, a sliding mode observer is designed to estimate the unknown terms related to the ULM. The presented controller improves the finite-time convergence of the system states to the origin and inherits the intrinsic robustness of sliding mode methods. Moreover, it provides high-precision tracking under disturbances and uncertainties. An auxiliary deep policy gradient method with actor and critic neural networks is designed to enhance the controller’s dynamic efficiency. The practical implementation of the suggested strategy is assessed utilizing the Speedgoat-based real-time platform and compared with the other methods under physical limitations and FDIAs.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".