Evaluating Solar Power Forecasting Robustness: A Comparative Analysis of XGBoost, RNN, KNN, RF, and LSTM with emphasis on Lagged Steps, Sensitivity, and Cross-Validation Techniques
Bibliographic record
Abstract
The transition towards renewable energies is inevitable in the face of global warming conditions and the increasing scarcity of fossil fuels, alongside their harmful impacts on the environment. Solar power, considered as a clean and its availability energy source, plays a vital role in this matter. However, due to the unpredictability nature of solar, influenced by environmental and temporal factors, energy production has faced significant challenges for its integration into microgrids. The present study works on addressing these obstacles by implementing advanced machine learning techniques to empower the predictability of solar energy. Utilizing one-month datasets of two power plants in India, Gandikota, Andhra, and Nasik, Maharashtra. This work focuses on various predictive models, including Support Vector Regression (SVR), Recurrent Neural Networks (RNN), eXtreme Gradient Boosting (XGBoost)m K-Nearest Neighbors (KNN), and Random Forest. These models are evaluated under different conditions, like incorporating lagged steps, and dynamics capturing. For the evaluation, a range of metrics is used. Mean Squared Log Error (MSLE), Mean Absolute Error (MAE), Mean Percentage Error (MPE), and R2, for the identification of the most effective algorithm are used. The final goal of this work is not only to improve the forecasting accuracy of solar power generation, by advantageous model modification but also to contribute to the efficient management and optimization of renewable energy integrations. Overall, XGBoost emerges as the preferred method for forecasting, offering a balance of high accuracy and robustness across different forecasting scenarios.
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 | 0.007 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 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".