Prediction of Traction Power Consumption for Rail Transit Based on Ensemble Learning Hybrid Time Series Models
Bibliographic record
Abstract
Against the backdrop of electricity market reform, accurate forecasting of train traction energy consumption can help operating enterprises set energy‐saving targets and implement precise energy management. Traction energy consumption prediction models based on traditional influencing factors are prone to uncertainties in future factors and often overlook the seasonal variations inherent in traction energy consumption. This paper proposes a sliding window stacking method that integrates random forest with Holt–Winters, ARIMA, and Prophet models. The method is experimentally validated using 14 years of per‐car‐kilometer traction energy consumption data from a metro line in a certain city. Experimental results show that the random forest stacking model achieves a mean absolute error (MAE) of 0.037609 kWh/car‐km, which represents reductions of 17%, 26%, and 32% compared with using Holt–Winters, ARIMA, and Prophet models alone, respectively. The mean squared error (MSE) reaches 0.002264 kWh/car‐km, corresponding to reductions of 33%, 28%, and 46% compared with the individual models. The results demonstrate that the random forest stacking hybrid model can effectively improve the accuracy of train traction energy consumption forecasting.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| 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".