A Deep Convolutional Neural Network-Based Approach to Detect False Data Injection Attacks on PV-Integrated Distribution Systems
Bibliographic record
Abstract
The integration of photovoltaic (PV) panels has allowed power distribution systems (PDSs) to regulate their voltage through the injection/absorption of reactive power. The deployment of information and communication technologies (ICTs), which is required for this scheme, has made the PDS prone to various cyber threats, e.g., false data injection (FDI) attacks. To counter these attacks, this paper proposes a data-driven framework to detect FDI attacks against voltage regulation of PV-integrated PDS. Initially, an attack-free system is modeled along with its voltage regulation scheme, where the grid measurements are sent to a centralized controller and the control signals are transmitted back to PVs to be used by their local controllers. Then, a convolutional neural network (CNN) framework is proposed to detect FDI attacks. To train this framework—which should be able to distinguish between normal grid behaviors and attacks—a complete and realistic dataset is formed to cover all normal conditions and unpredictable changes of a PDS during a year. Since normal variations and fluctuations in power consumption lead to changes in the voltage profile, this dataset is enriched using features such as season, weekdays, weekends, load conditions, and PV generation power. The performance of the trained framework has been compared with other supervised Machine Learning-based and deep-learning techniques for FDI attacks against modified IEEE 33- and 141-bus PDSs. Simulation results demonstrate the superior performance of the proposed framework in detecting FDI attacks.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".