Comparative Analysis of ARIMA and LSTM for Forecasting Maximum Wind Speed in Kupang City, East Nusa Tenggara

Indah Magfirrah; Meisyatul Ilma; Khairil Anwar Notodiputro; Yenni Angraini; Laily Nissa Atul Mualifah

doi:10.37905/jjom.v6i2.25834

Comparative Analysis of ARIMA and LSTM for Forecasting Maximum Wind Speed in Kupang City, East Nusa Tenggara

Indah Magfirrah, Meisyatul Ilma, Khairil Anwar Notodiputro, Yenni Angraini, Laily Nissa Atul Mualifah

Abstract

This study compares the Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) models for predicting maximum wind speed based on accuracy measured by Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Based on the results of the research, the LSTM model is better than the ARIMA model in predicting maximum wind speed in Kupang City, East Nusa Tenggara Province. The best LSTM model has hyperparameters of 200 epochs; batch size of 32; learning rate of 0,001; and 8 neurons. Based on the evaluation results of predicted data against actual data, the MAPE value of the LSTM model is 19,40%. The benefit of this research is that it can contribute to the literature on the development of wind utilization as a basis for building power plants on small islands as a renewable resource, particularly in Kupang City, East Nusa Tenggara.

Keywords

Wind Speed; ARIMA; LSTM; Grid Search

Full Text:

PDF

References

R. J. Hyndman and G. Athanasopoulos, “Forecasting: Principles and Practice (3rd ed),” Monash University: OTexts. Accessed: Jul. 02, 2024. [Online]. Available: https://otexts.com/fpp3/

J. Patterson and A. Gibson, “Deep Learning: A Practitioner’s Approach.” Sebastopol, CA: O’Reilly Media, Inc., 2017.

O. Al Qasem, M. Akour, and M. Alenezi, “The Influence of Deep Learning Algorithms Factors in Software Fault Prediction,” IEEE Access, vol. 8, pp. 63945–63960, 2020, doi: 10.1109/ACCESS.2020.2985290.

H. Abbasimehr, M. Shabani, and M. Yousefi, “An optimized model using LSTM network for demand forecasting,” Comput Ind Eng, vol. 143, p. 106435, May 2020, doi: 10.1016/j.cie.2020.106435.

J. N. Van Rijn and F. Hutter, “Hyperparameter importance across datasets,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Jul. 2018, pp. 2367–2376. doi: 10.1145/3219819.3220058.

Z. Liu and X. Yang, “Cross validation for uncertain autoregressive model,” Commun Stat Simul Comput, vol. 51, no. 8, pp. 4715–4726, Aug. 2022, doi: 10.1080/03610918.2020.1747077.

E. S. Putri and M. Sadikin, “Prediksi Penjualan Produk Untuk Mengestimasi Kebutuhan Bahan Baku Menggunakan Perbandingan Algoritma LSTM dan ARIMA,” Format Jurnal Ilmiah Teknik Informatika, vol. 10, no. 2, p. 162, 2021, doi: 10.22441/format.2021.v10.i2.007.

M. Elsaraiti and A. Merabet, “A comparative analysis of the arima and lstm predictive models and their effectiveness for predicting wind speed,” Energies (Basel), vol. 14, no. 20, 2021, doi: 10.3390/en14206782.

A. D. Milniadi and N. O. Adiwijaya, “Analisis Perbandingan Model Arima Dan Lstm Dalam Peramalan Harga Penutupan Saham (Studi Kasus : 6 Kriteria Kategori Saham Menurut Peter Lynch),” SIBATIK JOURNAL: Jurnal Ilmiah Bidang Sosial, Ekonomi, Budaya, Teknologi, dan Pendidikan, vol. 2, no. 6, pp. 1683–1692, 2023, doi: 10.54443/sibatik.v2i6.798.

K. Umam and Ardiansyah, “Perbandingan Metode ARIMA dan LSTM pada Prediksi Jumlah Pengunjung Perpustakaan,” MIND (Multimedia Artificial Intelligent Networking Database) Journal, vol. 8, no. 2, pp. 119–129, 2023.

F. K. Lutgens and E. J. Tarbuck, The Atmosphere: An Introduction to Meteorology (13th Ed.). London: Pearson, 2018.

T. Prasetyo et al., “Perbandingan Kinerja Metode Arima, Multi-Layer Perceptron, dan Random Forest dalam Peramalan Harga Logam Mulia Berjangka yang Mengandung Pencilan,” vol. 11, no. 2, pp. 265–274, 2024, doi: 10.25126/jtiik.2024117392.

D. C. Montgomery, C. L. Jennings, and M. Kulahci, “Introduction to Time Series Analysis and Forecasting”. New Jesrey: John Wiley & Sons, 2015.

M. Yohansa, K. A. Notodiputro, and E. Erfiani, “Dynamic Time Warping Techniques for Time Series Clustering of Covid-19 Cases in DKI Jakarta,” ComTech: Computer, Mathematics and Engineering Applications, vol. 13, no. 2, pp. 63–73, Nov. 2022, doi: 10.21512/comtech.v13i2.7413.

M. Abror Gustiansyah et al., “Aplikasi Model ARIMA dalam Peramalan Data Harga Emas Dunia Tahun 2010-2022,” Jurnal Statistika dan Aplikasinya, vol. 7, no. 1, 2023, doi: 10.21009/JSA.07108.

S. Novel Lase, M. Turnip, and E. Indra, “Application of Data Mining to Predicate Stock Price using Long Short Term Memory

Method,” Jurnal Infokum, vol. 10, no. 2, 2022, [Online]. Available:

http://infor.seaninstitute.org/index.php/infokum/index.

S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” 1997, Accessed: Jul. 03, 2024. [Online]. Available:

http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.51.3117.

N. Kalchbrenner, I. Danihelka, and A. Graves, “Grid Long Short-Term Memory,” Jul. 2015, [Online]. Available: http://arxiv.org/abs/1507.01526.

K. Zhang, W.-L. Chao, F. Sha, and K. Grauman, “Video Summarization with Long Short-term Memory,” May 2016, [Online]. Available: http://arxiv.org/abs/1605.08110.

B. Karlik and A. V. Olgac, “Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks.” Accessed: Jul. 03, 2024. [Online]. Available:

https://www.cscjournals.org/manuscript/Journals/IJAE/Volume1/Issue4/IJAE-26.pdf

S. K. Sachin Kumar, A. D. Sachin Kumar, A. K. Agam Damaraju, S. K. Aditya Kumar, and C.-M. C. Saru Kumari, “LSTM Network for Transportation Mode Detection,” Journal of Internet Technology, vol. 22, no. 4, pp. 891–902, Jul. 2021, doi: 10.53106/160792642021072204016.

E. F. de S. Soares, C. A. V. Campos, and S. C. de Lucena, “Online travel mode detection method using automated machine learning and feature engineering,” Future Generation Computer Systems, vol. 101, pp. 1201–1212, Dec. 2019, doi: 10.1016/j.future.2019.07.056.

A. L. Schaffer, T. A. Dobbins, and S. A. Pearson, “Interrupted time series analysis using autoregressive integrated moving average (ARIMA) models: a guide for evaluating large-scale health interventions,” BMC Med Res Methodol, vol. 21, no. 1, Dec. 2021, doi: 10.1186/s12874-021-01235-8.

J. Brownlee, “Long short-term memory networks with python: develop sequence prediction models with deep learning.” Machine Learning Mastery, 2017.

J. D. Williams and G. Zweig, “End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning,” Jun. 2016, [Online]. Available: http://arxiv.org/abs/1606.01269.

T. Phaladisailoed and T. Numnonda, “Machine Learning Models Comparison for Bitcoin Price Prediction,” in 2018 10th International Conference on Information Technology and Electrical Engineering (ICITEE), IEEE, Jul. 2018, pp. 506–511. doi: 10.1109/ICITEED.2018.8534911.

M. Naeem and S. A. Maged, “Linear Time Invariant State Space System Identification Using Adam Optimization,” in 2020 International Conference on Innovative Trends in Communication and Computer Engineering (ITCE), IEEE, Feb. 2020, pp. 196–204. doi: 10.1109/ITCE48509.2020.9047808.

K. Greff, R. K. Srivastava, J. Koutnik, B. R. Steunebrink, and J. Schmidhuber, “LSTM: A Search Space Odyssey,” IEEE Trans Neural Netw Learn Syst, vol. 28, no. 10, pp. 2222–2232, Oct. 2017, doi: 10.1109/TNNLS.2016.2582924.

N. Bakhashwain and A. Sagheer, “Online Tuning of Hyperparameters in Deep LSTM for Time Series Applications,” International Journal of Intelligent Engineering and Systems, vol. 14, no. 1, pp. 212–220, Feb. 2021, doi: 10.22266/ijies2021.0228.21.

P. M. Radiuk, “Impact of Training Set Batch Size on the Performance of Convolutional Neural Networks for Diverse Datasets,” Information Technology and Management Science, vol. 20, no. 1, Jan. 2017, doi: 10.1515/itms-2017-0003.

N. Rochmawati et al., “Analisa Learning rate dan Batch size Pada Klasifikasi Covid Menggunakan Deep learning dengan Optimizer Adam,” 2021. doi: 10.26740/jieet.v5n2.p44-48.

S. Siami-Namini, N. Tavakoli, and A. Siami Namin, “A Comparison of ARIMA and LSTM in Forecasting Time Series,” in 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, Dec. 2018, pp. 1394–1401. doi: 10.1109/ICMLA.2018.00227.

D. Fan, H. Sun, J. Yao, K. Zhang, X. Yan, and Z. Sun, “Well production forecasting based on ARIMA-LSTM model considering manual operations,” Energy, vol. 220, p. 119708, Apr. 2021, doi: 10.1016/j.energy.2020.119708.

G. N. Ahmad, H. Fatima, S. Ullah, A. Salah Saidi, and Imdadullah, “Efficient Medical Diagnosis of Human Heart Diseases Using Machine Learning Techniques With and Without GridSearchCV,” IEEE Access, vol. 10, pp. 80151–80173, 2022, doi: 10.1109/ACCESS.2022.3165792.

B. Wang, The Asian Monsoon. Berlin: Springer, 2006.

DOI: https://doi.org/10.37905/jjom.v6i2.25834