Optimization of Deep Reservoir Computing with Binary Genetic Algorithm for Multi-Time Horizon Forecasting of Power Consumption
Bibliographic record
Abstract
The roll of consumption energy forecasting is very important to make planning of time-horizon strategy, and to mitigate a great energy management. As a result, improving the sustainability of energy, and creating a clean environment. Aiming to develop the forecasting of consumption energy in different time horizons, this work gives the results of a new hybrid method, which combine deep echo state network (DeepESN), with Binary genetic algorithm (BGA). DeepESN is an extension of Echo state network (ESN), which integrates the strong nonlinear time series processing capability (of ESN) with the advanced learning characteristic of the deep learning models. BGA is another version of genetic algorithm optimization methods that can be applied to find the best values of architecture hyperparameters of deep learning models, basesd on binary decoding of his chromosoms. In this work, we compared the accuracy and performance of proposed model DeepESN-BGA with other deep learning methods. It is found that DeepESN-BGA have a fast processing compared with other models. In addition, it gives best results based on error metrics, compared with DeepESN without BGA, and other deep learning models, in different time horizon forecasting. Proposed model has been compared also with DeepESN-DE, DeepESN-GA, and DeepESN-PSO aiming to evaluate the performance of BGA in term of deep learning optimization. DeepESN-BGA gives statistically good result compared with other hybrid models.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| 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".