Short-term Electricity Price Forecasting in Highly Volatile Real-time Markets: The Case of Alberta
Bibliographic record
Abstract
Accurate short-term electricity price forecasting is a key input in the operational scheduling decisions made by electricity market participants. Thus, there has been a board body of models and techniques presented in the literature to forecast these prices. However, when it comes to real-time markets, they are significantly more volatile than day-ahead markets. This is because they are affected by unforeseen real-time grid events that may lead prices to jump to unusual high/low levels. This high volatility makes accurate forecasting of electricity prices a very challenging task. In this thesis, a volatility analysis of the Alberta electricity market is carried out to demonstrate significant intra-day fluctuations in the price patterns. Relevant publicly available data from the Alberta electricity market is investigated to select a set of explanatory real-time variables that might help predict some of these fluctuations. The Long Short-Term Memory network combined with the XGBoost decision tree algorithm is applied in a multi-stage forecasting mechanism to generate forecasts up to 96 hours ahead. Experimental results demonstrated that the proposed model provides a better performance for short-term electricity price forecasting relative to existing models. Two economic applications of the developed forecasting model are carried out to demonstrate its usefulness to the market players of the Alberta electricity market. The results obtained from these applications show that, compared with other approaches, the deployment of the developed forecasting model can increase significantly the revenues of several market players of the Alberta electricity market.
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 | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".