Cooling Load Prediction in Residential Buildings: Machine Learning Approaches and Comparative Analysis
Bibliographic record
Abstract
Accurate estimation of Cooling Loads (CLs) in Residential Buildings (RBs) is crucial for ensuring energy-efficient HVAC system design and maintaining indoor comfort. This research explores advanced Machine Learning (ML) approaches to forecast cooling demand by considering critical factors such as building envelope characteristics, solar exposure, and internal heat sources. A novel ensemble framework, Voting Regression (VR), is proposed and further enhanced through integration with two recently developed metaheuristic optimization algorithms: Weevil Damage Optimization (WDO) and Dandelion Sowing Optimization (DSO). These optimizers are applied to fine-tune model hyperparameters, thereby improving predictive accuracy and robustness. Among the evaluated models, the hybrid VR-WDO (Voting Regression + WDO) achieved the most outstanding performance, recording an R² of 0.988 and RMSE of 1.034 on the training dataset, and an R² of 0.983 with RMSE of 1.209 on the test dataset. In comparison, the CatBoost Regression (CATR) model yielded the weakest performance across the evaluation metrics, highlighting the superiority of the proposed hybrid approach. The novelty of this study lies in integrating emerging metaheuristic algorithms with ensemble learning to establish a high-accuracy, interpretable framework for residential Cooling Load Prediction (CLP). By combining ensemble methods with optimization-driven parameter tuning, the proposed approach addresses limitations in conventional models and offers practical insights for energy-efficient building design. The results demonstrate that the developed hybrid framework provides a reliable decision-support tool for engineers, architects, and urban planners seeking to enhance energy planning and optimize HVAC system performance in residential environments.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| 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) | 0.001 | 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".