A novel two‐stage method to detect non‐technical losses in smart grids
Bibliographic record
Abstract
Abstract Numerous strategies have been proposed for the detection and prevention of non‐technical electricity losses due to fraudulent activities. Among these, machine learning algorithms and data‐driven techniques have gained prominence over traditional methodologies due to their superior performance, leading to a trend of increasing adoption in recent years. A novel two‐step process is presented for detecting fraudulent Non‐technical losses (NTLs) in smart grids. The first step involves transforming the time‐series data with additional extracted features derived from the publicly available State Grid Corporation of China (SGCC) dataset. The features are extracted after identifying abrupt changes in electricity consumption patterns using the sum of finite differences, the Auto‐Regressive Integrated Moving Average model, and the Holt‐Winters model. Following this, five distinct classification models are used to train and evaluate a fraud detection model using the SGCC dataset. The evaluation results indicate that the most effective model among the five is the Gradient Boosting Machine. This two‐step approach enables the classification models to surpass previously reported high‐performing methods in terms of accuracy, F1‐score, and other relevant metrics for non‐technical loss detection.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".