Anomaly Detection in Load Forecasting for Electric Vehicles Using Image Processing Techniques
Bibliographic record
Abstract
The incorporation of electric vehicles (EVs) into the power grid presents significant challenges, particularly in meeting the electricity requirements of EVs through effective distribution strategies, efficient energy allocation, and optimal charging station placement. Accurate forecasting of load demand is critical for both the operational and planning aspects of energy systems, particularly due to the influence of EV travel behavior. This study introduces a hybrid approach to EV load forecasting using deep learning models to tackle this challenge. The proposed CLSTM model integrates convolutional neural network (CNN) and long short-term memory (LSTM) algorithms. Furthermore, the study introduces and applies an anomaly detection model based on image processing. The forecasting process initially uses clean data and then advances to a scenario involving a simulated cyber-attack by manipulating certain input data, which is referred to as a false data injection attack. After analyzing the data using various evaluation metrics and confirming anomalies, the image processing model identifies these anomalies through data visualization. In conclusion, a thorough evaluation of the results under both clean and compromised forecasting conditions unequivocally demonstrates that the CLSTM model not only surpasses the performance of traditional models but also exhibits greater robustness and accuracy. This superior performance highlights the CLSTM model's potential as a more reliable and effective solution for forecasting in scenarios impacted by data integrity issues.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 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".