Real-Time Detection of False Readings in Smart Grid AMI Using Deep and Ensemble Learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
In the advanced metering infrastructure, smart meters are deployed at the consumers’ side to regularly transmit fine-grained electricity consumption readings to the system operator (SO) for billing and real-time load monitoring and energy management. However, fraudulent consumers may compromise their meters to launch electricity-theft cyberattacks by reporting low-consumption readings to reduce their bills. These false readings not only cause financial losses but also degrade the grid’s performance because they are used for energy management and load estimate. The existing solutions in the literature focus only on securing the billing, so they are not designed to detect the attacks in real time, and thus the SO may use false readings for a long period of time in load monitoring and energy management until they are identified. In this paper, we propose a general ensemble-based deep-learning detector that enables the SO to detect false readings in real time. To do that, we first train several deep learning models on samples generated from a sliding window of the readings. Then, we use the best-performing model to train several models on different ratios of false readings and use them in our ensemble-based detector. Extensive experiments are conducted, and the results indicate that comparing to the literature, our detector can detect the false readings after sending a few false readings (around 15) comparing to the existing daily and weekly detection approaches that need 144 and 1,008 readings, respectively.
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.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it