PERBANDINGAN K-NEAREST NEIGHBORS (KNN) DAN SUPPORT VECTOR REGRESSION (SVR) UNTUK PREDIKSI KONSUMSI ENERGI LISTRIK
DOI:
https://doi.org/10.34151/prosidingsnast.v1i1.5034Keywords:
prediksi energi listrik, KNN, MAPE, RMSE, SVR.Abstract
Kebutuhan prediksi konsumsi energi listrik penting dalam manajemen energi seiring peningkatan kebutuhan energi akibat pertumbuhan penduduk dan perkembangan teknologi. Prediksi yang akurat membantu optimalisasi distribusi energi, pengurangan biaya operasional, dan mendukung kebijakan berkelanjutan. Penelitian ini menggunakan algoritma K-Nearest Neighbors (KNN) dan Support Vector Regression (SVR) untuk memprediksi konsumsi energi listrik pada dataset Tetuan City Power Consumption dengan tujuan mengukur performa kedua model berdasarkan Root Mean Squared Error (RMSE) dan Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan bahwa model KNN memiliki performa yang lebih baik dengan RMSE sebesar 0,14 dan MAPE sebesar 0,23 (atau 23%), sedangkan model SVR memiliki RMSE sebesar 0,16 dan MAPE sebesar 0,31 (atau 31%). Hal ini menunjukkan bahwa KNN lebih akurat dan andal dalam memprediksi konsumsi energi listrik dibandingkan SVR. Penelitian lebih lanjut dapat mempertimbangkan penggunaan model lain yang mampu menangani fluktuasi data yang lebih ekstrem atau menggabungkan beberapa algoritma agar dapat memberikan prediksi yang lebih akurat. Selain itu, penggunaan dataset dengan variabel tambahan atau penyempurnaan proses prapengolahan data dapat meningkatkan kinerja model.
References
Antolak, E., & Pułka, A. (2024). Power Consumption Prediction in Real-Time Multitasking Systems. Electronics (Switzerland), 13(7). https://doi.org/10.3390/electronics13071347
Ariyani, V., Putri, P., Prasetijo, A. B., & Eridani, D. (2022). Perbandingan Kinerja Algoritme Naïve Bayes Dan K-Nearest Neighbor (Knn) Untuk Prediksi Harga Rumah. Jurnal Ilmiah Teknik Elektro, 24(2), 162–171. https://ejournal.undip.ac.id/index.php/transmisi
da Silva, D. G., & Meneses, A. A. de M. (2023). Comparing Long Short-Term Memory (LSTM) and bidirectional LSTM deep neural networks for power consumption prediction. Energy Reports, 10(October), 3315–3334. https://doi.org/10.1016/j.egyr.2023.09.175
Drucker, H., Surges, C. J. C., Kaufman, L., Smola, A., & Vapnik, V. (1997). Support vector regression machines. Advances in Neural Information Processing Systems, 1, 155–161.
Gadi Ana Amas, A., Kopong Pati, G., Ema Ose Sanga, F., Informatika, T., & Stella Maris Sumba, S. (2024). JESCE (Journal of Electrical and System Control Engineering) Penerapan K-Optimal Pada Algoritma KNN Untuk Prediksi Kelulusan Tepat Waktu Mahasiswa Program Studi Teknik Informatika Application of K-Optimal in the KNN Algorithm to Predict Timely Graduation . Jesce, 7(2), 92–97. https://doi.org/10.31289/jesce.v6i2.10536
Hasan, M. Y., Kadhim, D. J., & Humaidi, A. J. (2024). Prediction of electricity-consumption and residential bills based on artificial neural network. International Review of Applied Sciences and Engineering. https://doi.org/10.1556/1848.2024.00856
Hora, S. K., Poongodan, R., de Prado, R. P., Wozniak, M., & Divakarachari, P. B. (2021). Long short-term memory network-based metaheuristic for effective electric energy consumption prediction. Applied Sciences (Switzerland), 11(23). https://doi.org/10.3390/app112311263
Karamizadeh, S., Abdullah, S. M., Halimi, M., Shayan, J., & Rajabi, M. J. (2014). Advantage and drawback of support vector machine functionality. I4CT 2014 - 1st International Conference on Computer, Communications, and Control Technology, Proceedings, I4ct, 63–65. https://doi.org/10.1109/I4CT.2014.6914146
Lewis, C. D. (1982). Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting. Butterworth Scientific. https://books.google.co.id/books?id=t8W4AAAAIAAJ
Memarzadeh, G., & Keynia, F. (2021). Short-term electricity load and price forecasting by a new optimal LSTM-NN based prediction algorithm. Electric Power Systems Research, 192(July 2020), 106995. https://doi.org/10.1016/j.epsr.2020.106995
Muhammad Ali, P. J. (2022). Investigating the Impact of Min-Max Data Normalization on the Regression Performance of K-Nearest Neighbor with Different Similarity Measurements. Aro-the Scientific Journal of Koya University, 10(1), 85–91. https://doi.org/10.14500/aro.10955
Muthiah, H., Sa, U., & Efendi, A. (2021). Support Vector Regression (SVR) Model for Seasonal Time Series Data. Proceedings of the Second Asia Pacific International Conference on Industrial Engineering and Operations Management, September 14-16, 2021, 3191–3200.
Olu-Ajayi, R., Alaka, H., Owolabi, H., Akanbi, L., & Ganiyu, S. (2023). Data-Driven Tools for Building Energy Consumption Prediction: A Review. Energies, 16(6), 1–20. https://doi.org/10.3390/en16062574
Rasyid, M. F., Djafar, I., & Mahersatillah, A. A. (2022). Prediksi penyebaran Sub Varian omicron di Indonesia menggunakan Machine Learning. Prosiding Seminar Ilmiah Sistem Informasi Dan Teknologi Informasi, XI(1), 1–7.
Saadah, S., Z, F. Z., & Z, H. H. (2021). Support Vector Regression (SVR) Dalam Memprediksi Harga Minyak Kelapa Sawit di Indonesia dan Nilai Tukar Mata Uang EUR/USD. Journal of Computer Science and Informatics Engineering (J-Cosine), 5(1), 85–92. https://doi.org/10.29303/jcosine.v5i1.403
Salam, A., & Hibaoui, A. El. (2018). Comparison of Machine Learning Algorithms for the Power Consumption Prediction - Case Study of Tetouan city –. International Renewable and Sustainable Energy Conference (IRSEC), 1–5. https://doi.org/10.1109/IRSEC.2018.8703007
Smola, A. J., & Scholkopf, B. (2004). Identification of TRACs (T3 receptor-associating cofactors), a family of cofactors that associate with, and modulate the activity of, nuclear hormone receptors. Molecular Endocrinology, 10(7), 813–825. https://doi.org/10.1210/me.10.7.813
Son, N., & Shin, Y. (2023). Short- and Medium-Term Electricity Consumption Forecasting Using Prophet and GRU. Sustainability (Switzerland), 15(22). https://doi.org/10.3390/su152215860
Tang, J., Saga, R., Cai, H., Ma, Z., & Yu, S. (2024). Advanced Integration of Forecasting Models for Sustainable Load Prediction in Large-Scale Power Systems. Sustainability (Switzerland), 16(4). https://doi.org/10.3390/su16041710
Wahyudi, A., Setiawan, W., Dwi, Y., & Negara, P. (2024). PREDIKSI KURS MATA UANG RIYAL KE RUPIAH MENGGUNAKAN METODE SUPPORT VECTOR REGRESSION ( SVR ). 10(2).
Yasmin, N. S. A., Wahab, N. A., Ismail, F. S., Musa, M. J., Halim, M. H. A., & Anuar, A. N. (2021). Support vector regression modelling of an aerobic granular sludge in sequential batch reactor. Membranes, 11(8). https://doi.org/10.3390/membranes11080554
Yunus, M., & Pratiwi, N. K. A. (2023). Prediksi Status Gizi Balita Dengan Algoritma K-Nearest Neighbor (KNN) di Puskemas Cakranegara. JTIM : Jurnal Teknologi Informasi dan Multimedia, 4(4), 221–231. https://doi.org/10.35746/jtim.v4i4.328
Zhang, S., & Li, J. (2023). KNN Classification With One-Step Computation. IEEE Transactions on Knowledge and Data Engineering, 35(3), 2711–2723. https://doi.org/10.1109/TKDE.2021.3119140
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
