A data-driven framework for medium-term electric vehicle charging demand forecasting
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
The rapid phase-in of electric vehicles (EV) will cause unprecedented issues with managing the supply of electricity and charging stations. It is in the interest of utility providers and everyday consumers to be able to plan for peak charging times, and related congestion. While past work has been done for localized, short-term forecasting, it has not included longer term forecasting, or considered the relationships between multiple stations. Importantly, past work has also not offered a framework for dataset construction and evaluated different dataset features. We propose a methodology to forecast demand at public EV charging stations, and use it to explore the potential of data-driven models to predict demand up to one week in advance. Our strategy includes selecting parameters for formatting a dataset given a list of charging events, a way to consider flexible prediction horizons, and deployment of deep and supervised learning-based models. To the best of our knowledge, ours is the first study to propose machine learning to forecast medium-term public EV charging demand, to exploit weather and other features at public charging stations, and to forecast demand at multiple stations and the entire network. We validated our approach using data from eleven stations over three years from Scotland, UK. Our method outperforms the benchmark time series method, and predicts network demand with a symmetric mean absolute percentage error (SMAPE) of 5.9% and a mean absolute error (MAE) of 124.7 kWh, or less than twelve percent of average daily demand.
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 | 0.000 |
| 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