Deep Learning Detection and Robust MPC Mitigation for EV-Based Load-Altering Attacks on Wind-Integrated Power Grids
Bibliographic record
Abstract
Large-scale deployment of electric vehicles (EVs) provides power grid operators with several opportunities, such as bidirectional energy transfers and frequency and voltage ancillary services. To fully realize these advantages, information and communication technologies (ICTs) between EV ecosystems and smart power grids have been developed, making power grids an appealing target for cyber attacks. On this basis, this paper studies the impact of a new family of EV-based load-altering attacks (EV-LAAs) against the subsynchronous control interaction (SSCI) of the wind-integrated power grid. First, the cyber-physical connections between the EV ecosystem and the power grid are discussed in detail to represent a threat model for coordinated EV-LAAs that can excite the SSCI modes of the system. Then, a convolutional neural network (CNN) is trained based on data from phasor measurement units (PMUs) at wind farm substations for detecting this attack, separating it from benign events, e.g., fault or line disconnection, and estimating attack vectors. The developed CNN detection model may neglect a few EV-LAAs due to the huge number of attack vectors with different combinations of amplitudes and frequencies during uncertainties in wind speeds and the number of WTG outages, leading to generating false negatives. As such, a robust model predictive controller (RMPC) is developed as a supplementary solution for mitigation purposes based on linear-matrix inequalities (LMIs). Possible uncertainties in wind speed and wind turbine generator (WTG) outages during different amplitudes of EV-LAAs are investigated when defining these LMIs. The performance of mitigation schemes is evaluated and compared with recent wide-area damping controllers, e.g., the two-degree freedom (2DOF), linear quadratic regulator (LQR), and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$H_{\infty }$</tex-math></inline-formula> under the co-simulation of EMTP-RV and MATLAB/Simulink.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".