Denial-of-Service Attack Detection and Mitigation Strategy for Synchrophasor Data Flowing in Power Transmission System
Bibliographic record
Abstract
The coupling of the legacy power infrastructure with complex computer networks and the integration of communication devices has led to the problem of cyberattacks, which in turn may induce partial/full blackouts. In this regard, an approach based on a Decision Tree for the detection and mitigation of Denial-of-Service (DoS) attacks is proposed in this paper. Based on the patterns and effects observed during DoS attacks on the Synchrophasor data flowing from the Phasor Measurement Unit (PMU) to the Phasor Data Concentrator (PDC), various supervised machine learning models are employed, which classify healthy and attack data and detect DoS attacks. Thereafter, a recurrent deep learning network employing Gated Recurrent Unit (GRU) architecture is utilized to reconstruct the lost data, which in turn is helpful in mitigating the impacts of a DoS attack. The suggested algorithms are validated using a real-world scenario of a communication dataflow between multiple PMUs placed at different buses of a power transmission network and a PDC present at a control center, representing a wide-area network, and are incorporated using Real Time Digital Simulator and openPDC. By comparing various metrics of ML classification, the results indicate that the decision tree based model gives better accuracy along with the least detection time compared to other machine learning-based models. The suggested GRU-based mitigation algorithm can reconstruct the DoS-impacted lost data from the available pre-attack phasors.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 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 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".