Medium-Term Electric Load Forecasting: A Benchmark Study of Transformer-Based and Linear-Based Methods
Bibliographic record
Abstract
Accurate electric load forecasting is essential to support the stable operation of power systems in the face of growing system complexities. Current studies on load forecasting mainly focus on short-term load forecasting. However, mediumterm forecasting, which plays a key role in efficient operation planning, is underexplored. In this work, we develop a comprehensive empirical study for medium-term load forecasting on linear models and transformer-based models. The results indicate that model performance varies with the data characteristics: linear models perform well on data sets with clear seasonal trends, while transformer-based models show advantages in more complex patterns. We evaluate a compound data augmentation strategy and find that augmentation yields limited improvements on large datasets with stable periodicity, but enhances robustness on smaller datasets with less regular trends by increasing data variability. Finally, the computational complexity of the six forecasting models is analyzed both theoretically and empirically. Linear models are preferable in resource-constrained environments, whereas with sufficient resources, model selection should be guided primarily by the complexity and structure of the data. This work reveals the strengths and limitations of each model in medium-term forecasting scenarios, providing valuable insights for future research and real-world applications.
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 | 0.004 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".