Integrasi Teaching-Learning-Based Optimization dan K-Nearest Neighbors untuk Prediksi Konsumsi Energi Listrik

Retno Wahyusari, Aris Rakhmadi, Lastoni Wibowo

Abstract


Konsumsi energi listrik merupakan salah satu aspek krusial dalam manajemen energi, terutama di era modern di mana kebutuhan energi terus meningkat seiring dengan perkembangan teknologi dan pertumbuhan populasi.  Maka perlu adanya prediksi konsumsi energy listrik yang akurat. Salah satu metode yang populer untuk prediksi adalah K-Nearest Neighbors (KNN).Berdasarkan hal tersebut maka  penelitian ini bertujuan untuk meningkatkan kinerja prediksi konsumsi energi listrik dengan mengintegrasikan algoritma Teaching-Learning-Based Optimization (TLBO) dalam proses seleksi fitur dan algoritma K-Nearest Neighbors (KNN) sebagai model prediksi. Data yang digunakan merupakan dataset konsumsi energi publik dari Kaggle dengan total 1000 data. Data terlebih dahulu diproses melalui normalisasi Min-Max Scaling sebelum dilakukan seleksi fitur. TLBO digunakan untuk memilih subset fitur yang paling relevan, yaitu Temperature, SquareFootage, HVACUsage, dan Holiday. Model KNN kemudian dilatih menggunakan fitur terpilih tersebut. Evaluasi kinerja dilakukan menggunakan dua metrik utama: Root Mean Square Error (RMSE) dan Mean Absolute Percentage Error (MAPE). Hasil menunjukkan bahwa model dengan fitur hasil TLBO menghasilkan MAPE sebesar 23.15% dan RMSE sebesar 0.1125, lebih baik dibandingkan model dengan seluruh fitur (MAPE 27.62%, RMSE 0.1297). Ini menunjukkan bahwa seleksi fitur dengan TLBO mampu menyederhanakan model sekaligus meningkatkan performa prediksi.

Keywords


KNN, Min-Max Scalingkomponen, Prediksi Konsumsi Energi, Seleksi Fitur, TLBO.

Full Text:

PDF

References


A. Yang, W. Li, and X. Yang, “Short-term electricity load forecasting based on feature selection and Least Squares Support Vector Machines,” Knowledge-Based Syst., vol. 163, pp. 159–173, 2019, doi: https://doi.org/10.1016/j.knosys.2018.08.027.

L. Pan, S. Wang, J. Wang, M. Xiao, and Z. Tan, “Research on Central Air Conditioning Systems and an Intelligent Prediction Model of Building Energy Load,” Energies, vol. 15, no. 24, 2022, doi: 10.3390/en15249295.

S. R. Bhatnagar et al., “An analytic approach for interpretable predictive models in high-dimensional data in the presence of interactions with exposures,” Genet. Epidemiol., vol. 42, no. 3, pp. 233–249, 2018, doi: 10.1002/gepi.22112.

X. Liu, D. Lu, A. Zhang, Q. Liu, and G. Jiang, “Data-Driven Machine Learning in Environmental Pollution: Gains and Problems,” Environ. Sci. Technol., vol. 56, no. 4, pp. 2124–2133, Feb. 2022, doi: 10.1021/acs.est.1c06157.

N. Pudjihartono, T. Fadason, A. W. Kempa-Liehr, and J. M. O’Sullivan, “A Review of Feature Selection Methods for Machine Learning-Based Disease Risk Prediction,” Front. Bioinforma., vol. 2, no. June, pp. 1–17, 2022, doi: 10.3389/fbinf.2022.927312.

P. Ray, S. S. Reddy, and T. Banerjee, “Various dimension reduction techniques for high dimensional data analysis: a review,” Artif. Intell. Rev., vol. 54, no. 5, pp. 3473–3515, 2021, doi: 10.1007/s10462-020-09928-0.

D. Eko Waluyo et al., “Implementasi Algoritma Regresi pada Machine Learning untuk Prediksi Indeks Harga Saham Gabungan,” J. Inform. J. Pengemb. IT, vol. 9, no. 1, pp. 12–17, 2024.

O. H. Kombo, S. Kumaran, Y. H. Sheikh, A. Bovim, and K. Jayavel, “Long-term groundwater level prediction model based on hybrid KNN-RF technique,” Hydrology, vol. 7, no. 3, pp. 1–24, 2020, doi: 10.3390/HYDROLOGY7030059.

F. Li and G. Jin, “Research on power energy load forecasting method based on KNN,” Int. J. Ambient Energy, vol. 43, no. 1, pp. 946–951, 2022, doi: 10.1080/01430750.2019.1682041.

L. Abualigah et al., “5 - Teaching–learning-based optimization algorithm: analysis study and its application,” L. B. T.-M. O. A. Abualigah, Ed., Morgan Kaufmann, 2024, pp. 59–71. doi: https://doi.org/10.1016/B978-0-443-13925-3.00016-9.

E. Akbari, G. Mojtaba, G. Milad, R. Abolfazl, and S. and Andrew Gadsden, “Optimal Power Flow via Teaching-Learning-Studying-Based Optimization Algorithm,” Electr. Power Components Syst., vol. 49, no. 6–7, pp. 584–601, Feb. 2022, doi: 10.1080/15325008.2021.1971331.

M. A. Eirgash, “Optimization of time–cost–quality-CO2 emission trade-off problems via super oppositional TLBO algorithm,” Asian J. Civ. Eng., vol. 26, no. 4, pp. 1743–1755, 2025, doi: 10.1007/s42107-025-01282-2.

R. Venkata Rao, “Review of applications of tlbo algorithm and a tutorial for beginners to solve the unconstrained and constrained optimization problems,” Decis. Sci. Lett., vol. 5, no. 1, pp. 1–30, 2016, doi: 10.5267/j.dsl.2015.9.003.

Z. Zhai, Y. Dai, and Y. Xue, “A Novel Teaching-Learning-Based Optimization with Laplace Distribution and Experience Exchange,” Math. Probl. Eng., vol. 2022, 2022, doi: 10.1155/2022/4177405.

L. B. Becker, M. Gergeleit, S. Schemmer, and E. Nett, “Using a flexible real-time scheduling strategy in a distributed embedded application,” in IEEE International Conference on Emerging Technologies and Factory Automation, ETFA, Apr. 2003, pp. 652–657. doi: 10.1109/ETFA.2003.1248760.


Refbacks

  • There are currently no refbacks.


Editorial Office :

Prosiding SENDIKO (Seminar Nasional Hasil Penelitian & Pengabdian Masyarakat Bidang Ilmu Komputer)
Published by Universitas PGRI Madiun
Managed by Program Studi Sistem Informasi Fakultas Teknik Universitas PGRI Madiun
Address Jl. Auri 14-16 Kota Madiun Kampus III Universitas PGRI Madiun 63118
Website http://prosiding.unipma.ac.id/index.php/sendiko/index
Email [email protected]

e-ISSN:  3025-4604