Forecasting electric vehicle charging loads using random forest and gene expression programming ensemble models
Bibliographic record
Abstract
The adoption of Electric Vehicles (EVs) is steadily increasing worldwide, aimed at reducing carbon emissions. Accurate forecasting of charging loads at EV charging stations is essential for effective energy allocation and infrastructure planning. This paper proposes ensemble machine learning models to forecast charging loads using Random Forest (RF) and Gene Expression Programming (GEP) techniques. These ensemble models integrate forecasts from Prophet, TBATS, and Long Short-Term Memory (LSTM) models. An outlier detection approach is introduced by employing feature engineering and Isolation Forest to identify abnormal data. The proposed ensemble models are designed to handle the complexities of time series data by incorporating diverse methodologies. Each ensemble model integrates trigonometric seasonality and holiday effects as modeled by Prophet, Box-Cox transformations, and auto-regressive moving average (ARMA) components from TBATS, and short-term as well as long-term variability captured by LSTM’s deep learning capabilities. The ensemble models also use time-context features and recent performance metrics of base forecasters, enabling them to capture temporal patterns and adjust each forecaster’s influence dynamically. This comprehensive approach ensures robust performance in modeling the complex nature of EV charging load time se data. While the RF ensemble model provides better forecasts than the GEP ensemble model, the GEP model presents an interpretable model that reveals the individual contributions of Prophet, TBATS, and LSTM forecasts to the predicted charging loads without requiring additional postprocessing. A benchmarking study compares the performance of the proposed ensemble models versus Chronos, a framework for pretrained probabilistic time series forecasting. Using various time series data from an open-source EV dataset, results demonstrate that the proposed ensemble models are superior, outperforming the Chronos framework in forecasting accuracy. Furthermore, statistical analysis has shown the significance of the RF and GEP results over the results of their base forecasters.
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 | 0.001 |
| 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 | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 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".