Deep Learning-Based Models for Wind and Solar Curtailment Forecasting
Bibliographic record
Abstract
Renewable Energy Resources (RESs) power curtailments, mainly wind and solar, have become a significant problem in many countries due to the rapid rise in renewable energy capacity and a sharp reduction in the cost of their power plants.These curtailments lead to the deteriorating economic viability of renewable energy.Modelling and predicting RES power curtailments are essential to better managing and can provide more apparent perspectives to increase the efficiency of future RES performance.However, the prediction of RES power curtailments is a complex problem because it is not only influenced by the volatile renewable power generation but also by the power generation of other units, imports, load demand and power exchange.In this study, using different Machine Learning (ML) and Deep Learning (DL) approaches, we aimed to predict wind and solar curtailments employing historical training data on power generation.A comprehensive learning-based data analysis was performed based on time-series renewable power curtailment reports obtained from California ISO (CAISO).The prediction models are trained based on ten input features for nine years, including load demand, imports, the output power of nuclear units, thermal power plants, small and large hydro units, biomass and geothermal, solar farms, wind turbines, and historical wind and solar curtailments.To find the best possible prediction methodology, different ML-based models, including Stochastic Gradient Descent (SGD), K-Nearest Neighbours algorithm (KNN), Support Vector Machines (SVR), Regression Trees (RT), and Random Forest (RF), are employed.Also, among the several deep learning methods, we utilize Deep Neural Network (DNN) as a fundamental deep learning model and Long Short-Term Memory (LSTM), and the Gated Recurrent Unit (GRU) to consider the time-series characteristics of the data.The learning results demonstrated that the GRU method outperformed all utilized models and could achieve a better forecasting performance.The results indicated the effectiveness of the proposed approach in predicting wind and solar curtailments.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".