BOL-LPP: A Bayesian-Optimized LSTM Model for Day-Ahead Load Price Forecasting in the ERCOT Market
Bibliographic record
Abstract
Precise short-term load price forecasting is critical for uninterrupted and efficient power-system operation and energy-market performance. Although machine-learning techniques have been widely employed to predict market prices, achieving reliable day-ahead load price forecasts remains challenging in practice, especially in the Electric Reliability Council of Texas (ERCOT) energy-only market. This paper targets sufficiently accurate day-ahead load price prediction for ERCOT's zonal markets by modeling historical load, price, and weather data with a Long Short-Term Memory (LSTM) network whose hyperparameters are tuned via Bayesian Optimization (BO). The resulting Bayesian-Optimized LSTM for load price Prediction (BOL-LPP) is evaluated against classical statistical and deep-learning baselines. On the North-zone test set, BOL-LPP attains a Mean Absolute Error (MAE) of${\$}$0.0044/MWh, cutting the MAE by 32% relative to the strongest deep baseline (BiLSTM, MAE of${\$}$0.0065/MWh) and by over 99% compared with SARIMAX. Its MAE remains below${\$}$0.006/MWh on the Coast and South zones, confirming robust generalization. These numerical results, along with the reported Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE), validate the performance gains delivered by the proposed model. BOL-LPP therefore promises markedly improved short-term load price forecasts, supporting informed decision-making and enhanced operational efficiency in the ERCOT 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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".