Hybrid Long Short-Term Memory (LSTM) and Exponentially Weighted Moving Average (EWMA) Model for Accurate and Scalable Electricity Price Forecasting
Bibliographic record
Abstract
Accurate electricity price forecasting is critical for market participants seeking to optimize bids and manage risk in increasingly volatile energy markets. This paper proposes a hybrid machine learning framework that integrates Long ShortTerm Memory (LSTM) networks with Exponentially Weighted Moving Average (EWMA) volatility smoothing. The framework optimizes bid strategy formulation for Battery Energy Storage System (BESS) operators in electricity markets, thereby enhancing market participation efficiency. The model was trained and validated on historical Austrian market data including wholesale electricity price, frequency containment reserve price, electrical load, gas price, radiation, temperature, and wind speed. This approach directly supports more informed decision-making for local traders and operators. Model training was accomplished through 64,500 iterations over 6.1 hours, utilizing a variable learning rate and MATLAB’s Deep Learning Toolbox to accelerate convergence. The computational process was executed on a dedicated Intel Core i9-14900HX/NVIDIA RTX 4060 platform, demonstrating that the approach is both scalable and suitable for real-time deployment scenarios with intra-day retraining requirements. The hybrid model achieves a root mean square error (RMSE) of 1.2207 €/MWhe, outperforming several established benchmarks while providing year-forward price forecasts with hourly resolution.
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 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| 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 | 0.001 |
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".