Prediksi Kecepatan Angin di Kabupaten Kupang Menggunakan Metode Support Vector Regression (SVR)

Khofifah Auliyatuz Zahroh; Dian Candra Rini Novitasari; Wika Dianita Utami; Puteri Permata Sani

doi:10.15575/telka.v10n3.193-203

Prediksi Kecepatan Angin di Kabupaten Kupang Menggunakan Metode Support Vector Regression (SVR)

Khofifah Auliyatuz Zahroh, Dian Candra Rini Novitasari, Wika Dianita Utami, Puteri Permata Sani

Sari

Energi angin menjadi salah satu energi alternatif yang dapat dimanfaatkan sebagai sumber energi listrik dikarenakan ramah lingkungan dan ketersediaannya yang tidak terbatas. Akan tetapi, kinerja Pembangkit Listrik Tenaga Bayu (PLTB) sangat bergantung dengan kecepatan angin pada suatu daerah. Kecepatan angin yang berubah-ubah dapat menyebabkan kualitas daya menjadi tidak stabil, sehingga tujuan penelitian ini yaitu untuk melakukan prediksi kecepatan angin agar dapat dimanfaatkan oleh PLTB untuk menghasilkan energi listrik. Pada penelitian ini, metode yang digunakan untuk prediksi yaitu metode Support Vector Regression (SVR) dengan melakukan pengujian menggunakan tiga jenis kernel yaitu linear, polynomial, dan gaussian. Berdasarkan model SVR terbaik diperoleh dengan menggunakan kernel gaussian yang menunjukkan nilai MAPE sebesar 20,703 dengan epsilon 0,010 dan bias 0,284. Hasil prediksi kecepatan angin pada bulan September 2022 menunjukkan kecepatan angin tertinggi terjadi pada tanggal 30 September 2022 dengan kecepatan sebesar 3,591 m/s dan kecepatan angin yang terendah terjadi pada tanggal 01 September 2022 dengan kecepatan sebesar 3,439 m/s.

Wind energy is an alternative energy that can be used as a source of electrical energy because it is environmentally friendly and has unlimited availability. However, the performance of wind power plants is highly dependent on wind speed in an area. Changes in wind speed can cause power quality to become unstable, so the purpose of this study is to predict wind speed so that it can be used by wind power plants to generate electricity. In this study the method used for prediction is the Support Vector Regression (SVR) method by conducting tests using three types of kernels, namely linear, polynomial, and gaussian. Based on the best SVR model obtained using a gaussian kernel which shows a MAPE value of 20.703 with an epsilon of 0.010 and a bias of 0.284. The results of the September 2022 wind speed prediction show that the highest wind speed will occur on September 30, 2022 with a speed of 3,591 m/s and the lowest wind speed will occur on September 1, 2022 with a speed of 3,439 m/s.

Kata Kunci

Kecepatan Angin; Prediksi; Support Vector Regression

Teks Lengkap:

PDF

Dilihat:

Sari 39 kali

PDF 13 kali

Referensi

A. F. N. Arif dan N. Nurwati, “Pengaruh Konsentrasi Penduduk Indonesia Di Pulau Jawa Terhadap Kesejahteraan Masyarakat,” J. Ilmu Kesejaht. Sos. “Humanitas” Fisip Unpas, vol. IV, no. 1, hal. 54–70, 2022.

Mahdawi et al., “The effect of population growth on economic growth: An evidence from Indonesia,” Proc. Int. Conf. Ind. Eng. Oper. Manag., no. July, hal. 141–148, 2021.

K. Handayani, Y. Krozer, dan T. Filatova, “From fossil fuels to renewables: An analysis of long-term scenarios considering technological learning,” Energy Policy, vol. 127, no. January 2018, hal. 134–146, 2019, doi: 10.1016/j.enpol.2018.11.045.

R. A. Diantari et al., “Sosialisasi Energi Baru Terbarukan dan Lingkungan Hidup Untuk Masyarakat Desa Sukawali KAB. Tangerang, Banten,” Terang, vol. 2, no. 1, hal. 53–59, 2019, doi: 10.33322/terang.v2i1.538.

A. P. Supriyadi, Adelia Rachmaniar, Aris Mustriadhi, dan Hasyimi Pradana, “Novel Renewable Energy as Resources for Environmentally Friendly National Energy Security: The Existence and the Readiness of the Regulatory Framework,” Indones. J. Soc. Environ. Issues, vol. 2, no. 1, hal. 59–67, 2021, doi: 10.47540/ijsei.v2i1.128.

J. Sih Setyono, F. Hari Mardiansjah, dan M. Febrina Kusumo Astuti, “Potensi Pengembangan Energi Baru Dan Energi Terbarukan Di Kota Semarang,” J. Riptek, vol. 13, no. 2, hal. 177–186, 2019, [Daring]. Tersedia pada: http://riptek.semarangkota.go.id

V. Sebestyén, “Renewable and Sustainable Energy Reviews: Environmental impact networks of renewable energy power plants,” Renew. Sustain. Energy Rev., vol. 151, no. September, hal. 111626, 2021, doi: 10.1016/j.rser.2021.111626.

J. Ugwu, K. C. Odo, L. O. Oluka, dan K. O. Salami, “A Systematic Review on the Renewable Energy Development, Policies and Challenges in Nigeria with an International Perspective and Public Opinions,” Int. J. Renew. Energy Dev., vol. 11, no. 1, hal. 287–308, 2022, doi: 10.14710/IJRED.2022.40359.

S. A. Solarin dan M. O. Bello, “Wind energy and sustainable electricity generation: evidence from Germany,” Environ. Dev. Sustain., vol. 24, no. 7, hal. 9185–9198, 2022, doi: 10.1007/s10668-021-01818-x.

S. Rochman dan M. Taufiq Irvan Efendy, “Arduino Based Design of Horizontal Wind Power Generator for Coastal Road Lighting,” BEST J. Appl. Electr. Sci. Technol., vol. 3, no. 1, hal. 30–33, 2021, doi: 10.36456/best.vol3.no1.3540.

I. Suprapto dan U. Hasanah, “Ekonomi dan Kebijakan Publik Indonesia Dekomposisi Pertumbuhan Produktivitas Industri Manufaktur Indonesia,” vol. 9, no. 2, hal. 1–17, 2022.

M. Q. Andiyantama, I. Zahira, dan A. Irawan, “Prediksi Energi Listrik Kincir Angin Berdasarkan Data Kecepatan Angin Menggunakan LSTM,” JITCE (Journal Inf. Technol. Comput. Eng., vol. 5, no. 01, hal. 1–7, 2021, doi: 10.25077/jitce.5.01.1-7.2021.

A. Malek, S. Suriadi, dan K. Saddami, “Prediksi Kecepatan Angin Jangka Menengah dengan Artificial Neural Network untuk Estimasi Daya Listrik Tenaga Angin (Studi Kasus: Kota Sabang),” J. Serambi Eng., vol. 8, no. 3, hal. 6078–6087, 2023, doi: 10.32672/jse.v8i3.6010.

S. Nurjanah, Y. Purbolingga, D. M. Putri, dan A. Rahmawati, “Prediksi Kecepatan Angin untuk Mengetahui Potensi Sumber Energi Alternatif menggunakan Model Regresi Lasso : Studi Kasus Kota Makassar pada Tahun 2024,” vol. 3, no. 1, 2024.

N. S. A. Yasmin, N. A. Wahab, F. S. Ismail, M. J. Musa, M. H. A. Halim, dan A. N. Anuar, “Support vector regression modelling of an aerobic granular sludge in sequential batch reactor,” Membranes (Basel)., vol. 11, no. 8, 2021, doi: 10.3390/membranes11080554.

F. Yulianto, W. F. Mahmudy, dan A. A. Soebroto, “Comparison of Regression, Support Vector Regression (SVR), and SVR-Particle Swarm Optimization (PSO) for Rainfall Forecasting,” J. Inf. Technol. Comput. Sci., vol. 5, no. 3, hal. 235–247, 2020, doi: 10.25126/jitecs.20205374.

R. A. Putri, W. S. Winahju, dan M. Mashuri, “Penerapan Metode Ridge Regression dan Support Vector Regression (SVR) untuk Prediksi Indeks Batubara di PT XYZ,” J. Sains dan Seni ITS, vol. 9, no. 1, hal. 64–71, 2020, doi: 10.12962/j23373520.v9i1.51021.

A. Mirarabi, H. R. Nassery, M. Nakhaei, J. Adamowski, A. H. Akbarzadeh, dan F. Alijani, “Evaluation of data-driven models (SVR and ANN) for groundwater-level prediction in confined and unconfined systems,” Environ. Earth Sci., vol. 78, no. 15, 2019, doi: 10.1007/s12665-019-8474-y.

M. S. Zaghloul, R. A. Hamza, O. T. Iorhemen, dan J. H. Tay, “Comparison of adaptive neuro-fuzzy inference systems (ANFIS) and support vector regression (SVR) for data-driven modelling of aerobic granular sludge reactors,” J. Environ. Chem. Eng., vol. 8, no. 3, hal. 103742, 2020, doi: 10.1016/j.jece.2020.103742.

P. Aji, K. Wakamori, dan H. Mineno, Short-term solar power forecasting using svr on hybrid pv power plant in indonesia, vol. 1035. Springer International Publishing, 2020. doi: 10.1007/978-3-030-29035-1_23.

T. M. N. Utami, D. C. R. Novitasari, F. Setiawan, N. Ulinnuha, dan Y. Farida, “Tide Prediction in Prigi Beach using Support Vector Regression (SVR) Method,” Sci. J. Informatics, vol. 8, no. 2, hal. 194–201, 2021, doi: 10.15294/sji.v8i2.28906.

E. A. Kusnanti, D. C. R. Novitasari, F. Setiawan, A. Fanani, M. Hafiyusholeh, dan G. I. Permata Sari, “Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method,” J. Inf. Syst. Eng. Bus. Intell., vol. 8, no. 1, hal. 21–30, 2022, doi: 10.20473/jisebi.8.1.21-30.

D. Z. Haq et al., “Long Short-Term Memory Algorithm for Rainfall Prediction Based on El-Nino and IOD Data,” Procedia Comput. Sci., vol. 179, no. 2019, hal. 829–837, 2021, doi: 10.1016/j.procs.2021.01.071.

D. Singh dan B. Singh, “Investigating the impact of data normalization on classification performance,” Appl. Soft Comput., vol. 97, no. xxxx, hal. 105524, 2020, doi: 10.1016/j.asoc.2019.105524.

U. I. Arfianti, D. C. R. Novitasari, N. Widodo, M. Hafiyusholeh, dan W. D. Utami, “Sunspot Number Prediction Using Gated Recurrent Unit (GRU) Algorithm,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 15, no. 2, hal. 141, 2021, doi: 10.22146/ijccs.63676.

D. A. Nasution, H. H. Khotimah, dan N. Chamidah, “Perbandingan Normalisasi Data untuk Klasifikasi Wine Menggunakan Algoritma K-NN,” Comput. Eng. Sci. Syst. J., vol. 4, no. 1, hal. 78, 2019, doi: 10.24114/cess.v4i1.11458.

U. A. Yakubu dan M. P. A. Saputra, “Time Series Model Analysis Using Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) for E-wallet Transactions during a Pandemic,” Int. J. Glob. Oper. Res., vol. 3, no. 3, hal. 80–85, 2022, doi: 10.47194/ijgor.v3i3.168.

C. Clarabelle dan J. Gatc, “Prediction Number of Passenger Ships from Port X to the Kepulauan Seribu Using SARIMA,” 2022 9th Int. Conf. Inf. Technol. Comput. Electr. Eng., vol. pp. 201-20, 2022, doi: 10.1109/ICITACEE55701.2022.9924116.

F. Zhang dan L. J. O’Donnell, Support vector regression. Elsevier Inc., 2019. doi: 10.1016/B978-0-12-815739-8.00007-9.

D. Faatihah, R. Putri, I. Arianti, J. W. Nugroho, dan K. Kunci, “Analysis of Using Support Vector Regression ( SVR ) Algorithm to Predict The Occurrence of Sea Tides in Tanjung Medang , Riau by Saas Storage in Cloud Computing,” vol. 11, no. 1, hal. 34–40, 2022.

M. El-Morshedy, Z. Almaspoor, G. Srinivasa Rao, M. Ilyas, dan A. Al-Bossly, “On Predictive Modeling for the Al2O3Data Using a New Statistical Model and Machine Learning Approach,” Adv. Civ. Eng., vol. 2022, no. ii, 2022, doi: 10.1155/2022/9348980.

R. Bárcenas, R. Fuentes-García, dan L. Naranjo, “Mixed kernel SVR addressing Parkinson’s progression from voice features,” PLoS One, vol. 17, no. 10, hal. e0275721, 2022, doi: 10.1371/journal.pone.0275721.

Y. Sun, S. Ding, Z. Zhang, dan W. Jia, “An improved grid search algorithm to optimize SVR for prediction,” Soft Comput., vol. 25, no. 7, hal. 5633–5644, 2021, doi: 10.1007/s00500-020-05560-w.

H. Muthiah, U. Sa, dan A. Efendi, “Support Vector Regression (SVR) Model for Seasonal Time Series Data,” Proc. Second Asia Pacific Int. Conf. Ind. Eng. Oper. Manag., no. September 14-16, 2021, hal. 3191–3200, 2021.

D. C. R. Novitasari et al., “Weather Parameters Forecasting as Variables for Rainfall Prediction using Adaptive Neuro Fuzzy Inference System (ANFIS) and Support Vector Regression (SVR),” J. Phys. Conf. Ser., vol. 1501, no. 1, 2020, doi: 10.1088/1742-6596/1501/1/012012.

Y. Yang et al., “A support vector regression model to predict nitrate-nitrogen isotopic composition using hydro-chemical variables,” J. Environ. Manage., vol. 290, 2021, doi: 10.1016/j.jenvman.2021.112674.

A. Rafati, M. Joorabian, E. Mashhour, dan H. R. Shaker, “High dimensional very short-term solar power forecasting based on a data-driven heuristic method,” Energy, vol. 219, hal. 119647, 2021, doi: 10.1016/j.energy.2020.119647.

J. S. P. Fong dan K. W. T. Yan, “Data Normalization,” Inf. Syst. Reengineering, Integr. Norm., 2021, doi: 10.1007/978-3-030-79584-9_8.

L. Wiranda dan M. Sadikin, “Penerapan Long Short Term Memory Pada Data Time Series Untuk Memprediksi Penjualan Produk Pt. Metiska Farma,” J. Nas. Pendidik. Tek. Inform., vol. 8, no. 3, hal. 184–196, 2019.

P. Nehra dan A. Nagaraju, “Host utilization prediction using hybrid kernel based support vector regression in cloud data centers,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 8, hal. 6481–6490, 2022, doi: 10.1016/j.jksuci.2021.04.011.

F. Novianti, N. Ulinnuha, M. Hafiyusholeh, dan A. Arianto, “Prediksi Penggunaan Bahan Bakar pada PLTGU menggunakan Metode Support Vector Regression (SVR),” Techno.Com, vol. 21, no. 2, hal. 249–255, 2022, doi: 10.33633/tc.v21i2.5712.

DOI: https://doi.org/10.15575/telka.v10n3.193-203