XML Print


Chandigarh University
Abstract:   (77 Views)
Evaluating the energy efficiency of energy-efficient constructions relies heavily on accurately anticipating their thermal loads. Current results have demonstrated that stochastic algorithms effectively tackle the abovementioned problem. In light of these issues, this research aims to evaluate a novel hybrid technique for estimating dwellings' cooling load (CL). The multilayer perceptron and the Whale Optimization Algorithm (WOA-MLP) are both suggested components of the model. The nonlinear analysis of the impact of eight freestanding parameters on the cooling load was performed through the best structure of every model. The assessment for this investigation was carried out in two stages. During the first stage, the population size that yielded the highest coefficient of determination (R2) value and the lowest root mean square error (RMSE) amount was selected as the optimal one. During the second stage, the experiment’ findings with a swarm size of 500 (R2 =0.95155 and 0.95021, RMSE =0.07973 and 0.07737 for training and validation, correspondingly) were put through a series of tests using several various p values (between 0.5-1.4). According to the findings, the p-value of 1.3 is the one that provides the most reliable results. This amount has an R2 equal to 0.95212 and 0.94792 and an RMSE equal to 0.07926 and 0.07909.
Full-Text [PDF 2389 kb]   (36 Downloads)    
Type of Study: Research | Subject: General
Received: 2025/07/7 | Accepted: 2025/09/1
* Corresponding Author Address: Mechanical Engineering Department

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2025 CC BY-NC 4.0 | AI in Sustainable Energy and Environment

Designed & Developed by : Yektaweb