Optimasi Catboost Dengan Algoritma Self Adaptive Emperor Penguin Optimizer (Sa-Epo) Untuk Prediksi Konsumsi Energi Pendinginan Bangunan

Fadhilatuzzahro, Mutiara (2026) Optimasi Catboost Dengan Algoritma Self Adaptive Emperor Penguin Optimizer (Sa-Epo) Untuk Prediksi Konsumsi Energi Pendinginan Bangunan. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21081010205.-cover.pdf Download (1MB)
	Text (bab 1) 21081010205.-bab1.pdf Download (43kB)
	Text (bab 2) 21081010205.-bab2.pdf Restricted to Repository staff only until 23 January 2029. Download (749kB)
	Text (bab 3) 21081010205.-bab3.pdf Restricted to Repository staff only until 23 January 2029. Download (1MB)
	Text (bab 4) 21081010205.-bab4.pdf Restricted to Repository staff only until 23 January 2029. Download (1MB)
	Text (bab 5) 21081010205.-bab5.pdf Download (17kB)
	Text (Daftar pustaka) 21081010205.-daftarpustaka.pdf Download (253kB)
	Text (Lampiran) 21081010205.lampiran.pdf Restricted to Repository staff only until 23 January 2029. Download (71kB)

Abstract

The building sector is currently one of the largest contributors to global energy consumption, with cooling energy use in buildings showing a much faster growth rate compared to other types of energy consumption. This study aims to develop a predictive model for building cooling energy consumption using a CatBoost model optimized with the Self-Adaptive Emperor Penguin Optimizer (SA-EPO) algorithm to support long-term energy reduction efforts. The research stages include data preprocessing, CatBoost model development, and hyperparameter optimization. The model was evaluated using two validation techniques Hold Out and Time Series Split Cross-Validation employing RMSE, MAE, MSE, and R² as performance metrics. The results show that SA-EPO consistently improves CatBoost performance. In the Hold-Out validation, SA-EPO reduced the RMSE from 0.2957 to 0.2858 and increased the R² from 0.9350 to 0.9393. Meanwhile, in the Time Series Split CV, SA-EPO achieved the lowest RMSE of 0.2659 and the highest R² of 0.9492, outperforming both the standard model and other comparative optimization algorithms. It can be concluded that SA-EPO is effective in optimizing CatBoost hyperparameters and is capable of enhancing the accuracy of building cooling energy consumption predictions.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Rahmat, Basuki	NIDN196907232021211002	basukirahmat.if@upnjatim.ac.id
Thesis advisor	Mumpuni, Retno	NIDN198707162025212045	retnomumpuni.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Unnamed user with email 21081010205@student.upnjatim.ac.id

Date Deposited:

27 Jan 2026 08:04

Last Modified:

27 Jan 2026 08:04

URI:

https://repository.upnjatim.ac.id/id/eprint/49060