An artificial insurance framework for a hydrogen-based microgrid to detect the advanced cyberattack model
Bibliographic record
Abstract
Microgrid systems have evolved based on renewable energies including wind, solar, and hydrogen to make the satisfaction of loads far from the main grid more flexible and controllable using both island- and grid-connected modes. Albeit microgrids can gain beneficial results in cost and energy schedules once operating in grid-connected mode, such systems are vulnerable to malicious attacks from the viewpoint of cybersecurity. With this in mind, this paper explores a novel advanced attack model named the false transferred data injection (FTDI) attack aiming to manipulatively alter the power flowing from the microgrid to the upstream grid to raise voltage usability probability. One crucial piece of information that the model uses to change the system and cause the greatest amount of damage while concealing the attacker's view is the voltage stability index. Saying that the power transaction between the microgrid and the upstream grid is within the broad scope of bilateral exchange at any given moment is noteworthy. Put otherwise, with respect to the FTDI assault, the microgrid's power direction is just as significant to the detection system as the transferred power value. Therefore, once the microgrid is running in the grid-connected mode, the false data detector needs to concurrently detect changes in the value and direction of power. To overcome this problem, the paper presents a learning generative network model, based on the generative adversarial network (GAN) paradigm, to recognize the change in probability values that is maliciously aimed. To this end, a studied microgrid system including the wind turbine, photovoltaic, storage, tidal turbine, and fuel cell units is performed on the tested 24-bus IEEE grid to satisfy the local load demands. Comparative analysis indicates notable gains, such as scores of 0.95%, 0.92%, 0.7%, and 10% for the Hit rate, C.R. rate, F.A. rate, and Miss rate in order to evaluate the GAN-based detection model within the microgrid.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".