PERAMALAN PENYINARAN MATAHARI PER JAM SATU HARI KE DEPAN MENGGUNAKAN MODEL LONG SHORT-TERM MEMORY (LSTM)
DOI:
https://doi.org/10.23960/jitet.v13i3S1.7883Abstract Views: 44 File Views: 31
Keywords:
peramalan iradiasi matahari, LSTM, K-means, Bayesian Optimization, one-day aheadAbstract
Energi surya merupakan sumber energi terbarukan yang potensial, namun variabilitas penyinaran matahari akibat kondisi cuaca menimbulkan tantangan dalam integrasi ke sistem tenaga listrik. Oleh karena itu, peramalan iradiasi matahari dengan akurasi tinggi menjadi penting untuk mendukung stabilitas dan efisiensi operasi jaringan. Penelitian ini mengusulkan model Long Short-Term Memory (LSTM) untuk peramalan iradiasi per jam satu hari ke depan dengan hanya menggunakan data historis Global Horizontal Irradiance (GHI) sebagai input. Proses penelitian meliputi pra-pemrosesan data, rekayasa fitur melalui klasterisasi K-Means untuk identifikasi pola cuaca, pemanfaatan data historis beberapa hari sebelumnya, serta transformasi waktu siklikal. Optimasi hyperparameter dilakukan menggunakan Bayesian Optimization untuk memperoleh konfigurasi model terbaik. Hasil evaluasi menunjukkan model mencapai R² sebesar 0,7937, RMSE 87,71 W/m², MAE 59,34 W/m², dan MAPE 28,75%. Analisis visual juga memperlihatkan kemampuan model mengikuti pola siklus harian dan berkorelasi kuat dengan data aktual. Temuan ini menegaskan bahwa data GHI historis saja sudah cukup menghasilkan prediksi yang reliabel, khususnya di wilayah dengan keterbatasan infrastruktur, serta dapat menjadi dasar pengembangan metode prediksi yang lebih efisien.
Downloads
References
Renewable Energy Policy Network for the 21st Century, “Renewables 2023 Global Status Report Collection,” REN21, 2023. [Online]. Available: https://www.ren21.net/gsr-2023/
IEA, “Renewables 2023,” IEA, Paris, 2024. [Online]. Available: https://www.iea.org/reports/renewables-2023
H. N. Amer, N. Y. Dahlan, A. M. Azmi, M. F. A. Latip, M. S. Onn, and A. Tumian, “Solar power prediction based on Artificial Neural Network guided by feature selection for Large-scale Solar Photovoltaic Plant,” Energy Reports, vol. 9, pp. 262–266, Nov. 2023, doi: 10.1016/j.egyr.2023.09.141.
F. M. Guangul and G. T. Chala, “Solar Energy as Renewable Energy Source: SWOT Analysis,” in 2019 4th MEC International Conference on Big Data and Smart City (ICBDSC), Muscat, Oman: IEEE, Jan. 2019, pp. 1–5. doi: 10.1109/ICBDSC.2019.8645580.
U. K. Das et al., “Forecasting of photovoltaic power generation and model optimization: A review,” Renewable and Sustainable Energy Reviews, vol. 81, pp. 912–928, Jan. 2018, doi: 10.1016/j.rser.2017.08.017.
D. Rowe, S. Sayeef, and G. Platt, “Intermittency: It’s the Short-Term That Matters,” in Future of Utilities Utilities of the Future, Elsevier, 2016, pp. 129–150. doi: 10.1016/B978-0-12-804249-6.00007-5.
J. Ramirez-Vergara, L. B. Bosman, E. Wollega, and W. D. Leon-Salas, “Review of forecasting methods to support photovoltaic predictive maintenance,” Cleaner Engineering and Technology, vol. 8, p. 100460, June 2022, doi: 10.1016/j.clet.2022.100460.
S. S. Refaat, H. Abu‐Rub, A. P. Sanfilippo, and A. Mohamed, “Impact of grid‐tied large‐scale photovoltaic system on dynamic voltage stability of electric power grids,” IET Renewable Power Gen, vol. 12, no. 2, pp. 157–164, Feb. 2018, doi: 10.1049/iet-rpg.2017.0219.
H. Liu, N. Nikitas, Y. Li, and R. Yang, “Big Data Analysis of Energy Economics in Photovoltaic Power Generation Market,” in Big Data in Energy Economics, in Management for Professionals. , Singapore: Springer Singapore, 2022, pp. 117–136. doi: 10.1007/978-981-16-8965-9_5.
K. Sereja and P. Miller, “Forecasting and evaluation of voltage conditions in a low-voltage power grid with a large share of prosumer installations,” in Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2019, R. S. Romaniuk and M. Linczuk, Eds., Wilga, Poland: SPIE, Nov. 2019, p. 188. doi: 10.1117/12.2536975.
N. Y. Hendrikx et al., “All sky imaging-based short-term solar irradiance forecasting with Long Short-Term Memory networks,” Sol. Energy, vol. 272, 2024, doi: 10.1016/j.solener.2024.112463.
M. Ansong, T. N. Nyang’onda, R. J. Musembi, and B. S. Richards, “Very Short-Term Solar Irradiance Forecasting for Photovoltaic Power Integration with the Grid: Potentials and Challenges for Africa,” in IEEE PES/IAS PowerAfrica, PowerAfrica, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/PowerAfrica61624.2024.10759405.
N. Omar, H. Aly, and T. Little, “LSTM and RBFNN Based Univariate and Multivariate Forecasting of Day-ahead Solar Irradiance for Atlantic Region in Canada and Mediterranean Region in Libya,” in Int. Conf. Energy, Electr. Power Eng., CEEPE, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 1130–1135. doi: 10.1109/CEEPE51765.2021.9475652.
M. AlShafeey and C. Csáki, “Evaluating neural network and linear regression photovoltaic power forecasting models based on different input methods,” Energy Rep., vol. 7, pp. 7601–7614, 2021, doi: 10.1016/j.egyr.2021.10.125.
H. Wang, P. Wang, Y. Zhang, and X. Sun, “Short-term Prediction of Solar Irradiance Based on EEMD-Lasso-MLP,” in Proc. - Int. Conf. Mach. Learn. Knowl. Eng., MLKE, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 164–168. doi: 10.1109/MLKE55170.2022.00038.
S. J. Abdulkadir, H. Alhussian, M. Nazmi, and A. A. Elsheikh, “Long short term memory recurrent network for standard and Poor’s 500 index modelling,” Int. J. Eng. Technol., vol. 7, no. 4, pp. 25–29, 2018, doi: 10.14419/ijet.v7i4.15.21365.
A. N. A. Mazmee, N. Zaini, and M. F. A. Latip, “Enhancing Solar Energy Forecasting Accuracy Using LSTM Networks for Global Horizontal Irradiance,” in Int. Conf. Sys. Eng. Technol., ICSET - Proceeding, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 174–179. doi: 10.1109/ICSET63729.2024.10774732.
P. S. Kumar, V. A. G. Raju, Ch. Ramesh, P. Prasad, T. Soniya, and A. Yaswanth, “Enhancement of Solar Energy Forecasting with LSTM Model: A Deep Dive into Accuracy and Performance Metrics,” in IEEE Int. Conf. Adv. Inf. Technol., ICAIT - Proc., Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ICAIT61638.2024.10690374.
R. A. Rajagukguk, R. A. A. Ramadhan, and H.-J. Lee, “A review on deep learning models for forecasting time series data of solar irradiance and photovoltaic power,” Energies, vol. 13, no. 24, 2020, doi: 10.3390/en13246623.
M. Lim and T. Handhayani, “PENERAPAN LSTM DAN GRU UNTUK PREDIKSI HARGA CABAI MERAH DI KOTA JAWA TIMUR,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 2, Apr. 2025, doi: 10.23960/jitet.v13i2.6467.
W. Maseri Binti Wan Mohd, A. H. Beg, T. Herawan, A. Noraziah, and K. F. Rabbi, “Improved parameterless K-means: Auto-generation centroids and distance data point clusters,” in Information Retrieval Methods for Multidisciplinary Applications, Z. Lu, Ed., IGI Global, 2013, pp. 156–168. doi: 10.4018/978-1-4666-3898-3.ch010.
A. Zharova and A. Scherz, “Multistep Multiappliance Load Prediction,” Dec. 19, 2022, arXiv: arXiv:2212.09426. doi: 10.48550/arXiv.2212.09426.
N. Sultana, S. M. Z. Hossain, S. H. Almuhaini, and D. Düştegör, “Bayesian Optimization Algorithm-Based Statistical and Machine Learning Approaches for Forecasting Short-Term Electricity Demand,” Energies, vol. 15, no. 9, p. 3425, Jan. 2022, doi: 10.3390/en15093425.
E. T. Habtemariam, K. Kekeba, M. Martínez-Ballesteros, and F. Martínez-Álvarez, “A Bayesian Optimization-Based LSTM Model for Wind Power Forecasting in the Adama District, Ethiopia,” Energies, vol. 16, no. 5, p. 2317, Jan. 2023, doi: 10.3390/en16052317.
AESI, “Indonesia Solar Map.” Accessed: Aug. 08, 2025. [Online]. Available: https://indonesiasolarmap.com/methodology
D. Pandya, A. Jadeja, S. Gour, S. B. Trivedi, H. H. Patel, and P. U. Jadeja, “An Analytical Perspective of Missing Values in Machine Learning,” in Lect. Notes Networks Syst., Springer Science and Business Media Deutschland GmbH, 2024, pp. 285–294. doi: 10.1007/978-981-97-3991-2_24.
S. Urolagin, N. Sharma, and T. K. Datta, “A combined architecture of multivariate LSTM with Mahalanobis and Z-Score transformations for oil price forecasting,” Energy, vol. 231, 2021, doi: 10.1016/j.energy.2021.120963.
A. Pranolo et al., “Enhanced Multivariate Time Series Analysis Using LSTM: A Comparative Study of Min-Max and Z-Score Normalization Techniques,” Ilk. J. Ilm., vol. 16, no. 2, pp. 210–220, Aug. 2024, doi: 10.33096/ilkom.v16i2.2333.210-220.
A. Katrompas and V. Metsis, “Enhancing LSTM Models with Self-attention and Stateful Training,” in Lect. Notes Networks Syst., Springer Science and Business Media Deutschland GmbH, 2022, pp. 217–235. doi: 10.1007/978-3-030-82193-7_14.
A. M. Ikotun, A. E. Ezugwu, L. Abualigah, B. Abuhaija, and J. Heming, “K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data,” Information Sciences, vol. 622, pp. 178–210, Apr. 2023, doi: 10.1016/j.ins.2022.11.139.
Y. Yu, J. Cao, and J. Zhu, “An LSTM Short-Term Solar Irradiance Forecasting Under Complicated Weather Conditions,” IEEE Access, vol. 7, pp. 145651–145666, 2019, doi: 10.1109/ACCESS.2019.2946057.
J. Mielke, F. Innerbichler, M. Schiestl, N. M. Ballarini, and B. Jones, “The Assessment of Quality Attributes for Biosimilars: a Statistical Perspective on Current Practice and a Proposal,” AAPS J., vol. 21, no. 1, 2019, doi: 10.1208/s12248-018-0275-9.
S. A. Mousavian Anaraki, A. Haeri, and F. Moslehi, “A hybrid reciprocal model of PCA and K-means with an innovative approach of considering sub-datasets for the improvement of K-means initialization and step-by-step labeling to create clusters with high interpretability,” Pattern Anal. Appl., vol. 24, no. 3, pp. 1387–1402, 2021, doi: 10.1007/s10044-021-00977-x.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jurnal Informatika dan Teknik Elektro Terapan
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
