Wavelet-Facilitated Resonance Attack Detection in Inverter-Based Resources
Bibliographic record
Abstract
Following the rapid integration of inverter-based resources (IBRs) in the power grids, IEEE standards, e.g., IEEE 1547.1-2020, have been widely adopted to regulate their operation. Such an adoption, which often necessitates communication between IBRs and the utility control center, makes the power grid prone to cyber threats targeting the grid's harmonic stability. On this basis, this paper (i) investigates the existing attack surfaces in the grids with IBR integration, (ii) proposes a new type of resonance-based attack that aims to excite harmonic conditions of IBRs, and (iii) develops a tailor-made attack detection method for developed attacks. First, we show that adversaries can target the harmonic stability of the grid by injecting false data in the communication layers of IBRs. Then, a well-crafted attack, that injects a signal with the resonance frequency of IBRs, is designed using either impedance-based modeling of IBRs, or signal processing of available measurements. Subsequently, an optimized wide neural network (OWNN) with a Bayesian optimizer is developed as a detection method to effectively detect such attacks. The proposed OWNN model uses the discrete wavelet transform (DWT) as a time-frequency domain analysis tool to extract problem-specific features. Finally, the impact of the attack, the effectiveness of the detection method, and the superior accuracy of the OWNN compared to existing data-driven techniques are demonstrated using an IBR connected to an infinite bus, an IBR-integrated IEEE 30-bus, and a high-voltage direct current (HVDC)-based bulk power grid test system.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.003 |
| 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; both teacher heads agree on what is shown here.
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".