An Attention-Based Deep Learning Approach for Forecasting Electricity Prices in Real-Time Electricity Markets
Bibliographic record
Abstract
Real-time electricity markets are characterized by irregular and sudden price swings, leading to high price volatility and significant uncertainties for market participants. Accurate and informative electricity price forecasts are essential to reduce these uncertainties and enable more effective decision-making in energy generation, consumption, strategy planning, and risk management. This thesis presents a new forecasting framework for electricity prices in real-time markets, leveraging the capabilities of deep learning and advanced feature engineering. The proposed methodology integrates the Temporal Fusion Transformer (TFT), a deep learning model applied to time series forecasting, with dynamic clustering techniques to enhance forecasting accuracy. This is done by combining Hierarchical Density-Based Spatial Clustering of Applications with Noise and Dynamic Time Warping to cluster generators based on attributes such as geographical location, fuel type, installed capacity, and generation patterns. These clusters provide new covariates for forecasting models, enabling the method to adapt to the unique characteristics of any electricity market. The effectiveness of the proposed framework is demonstrated through a case study of the Ontario electricity market, where the methodology outperforms the forecasts of the system operator in terms of average error, accuracy, precision, and recall across a six-hour forecast horizon. This study underlines the framework's versatility and offers valuable insights into electricity price behavior, aiding market participants in mitigating risks and optimizing energy strategies.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".