Komparasi Metode LSTM dan Random Forest dalam Prediksi Waktu Sandar Kapal untuk Optimasi Alokasi Dermaga: Studi Kasus Pelabuhan Tanjung Pandan

Authors

  • Andy Achmad Hendharsetiawan Universitas Bhayangkara Jakarta Raya, Indonesia
  • Adi Muhajirin Universitas Bhayangkara Jakarta Raya, Indonesia
  • Alwi Rina Riyanto Universitas Bhayangkara Jakarta Raya, Indonesia

DOI:

https://doi.org/10.38035/dit.v3i2.2929

Keywords:

Alokasi Dermaga, LSTM, Tanjung Pandan, Prediksi Waktu Sandar, Random Forest

Abstract

Efisiensi operasional pelabuhan sangat bergantung pada akurasi prediksi waktu sandar kapal, terutama di Pelabuhan Tanjung Pandan yang memiliki karakteristik tramp trade dengan variasi kapal yang tinggi. Penelitian ini bertujuan membandingkan kinerja metode Long Short-Term Memory (LSTM) dan Random Forest dalam memprediksi durasi sandar kapal sebagai dasar optimasi alokasi dermaga. Menggunakan data operasional periode 2023–2024 (125 observasi), variabel input mencakup Gross Tonnage (GT), Length Overall (LOA), serta tanggal tiba dan berangkat; sedangkan output adalah durasi sandar dalam jam. Data diproses melalui pembersihan, rekayasa fitur, dan normalisasi, lalu dibagi menjadi 80% latih dan 20% uji. Evaluasi dilakukan menggunakan RMSE, MAE, dan R². Hasil menunjukkan bahwa Random Forest mengungguli LSTM dengan RMSE 5,34 jam (vs. 7,82), MAE 4,07 jam (vs. 5,91), dan R² 0,917 (vs. 0,812), mengindikasikan kemampuannya menangkap interaksi non-linear antarfitur statis seperti GT dan LOA lebih efektif dalam konteks operasional pelabuhan ini. Temuan ini merekomendasikan penerapan Random Forest sebagai model prediktif dalam sistem pendukung keputusan alokasi dermaga untuk meningkatkan efisiensi dan mengurangi waiting time kapal 

References

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

Pratama, R., Sutanto, D., & Muhajirin, A. (2024). Static ship characteristics as dominant factors in berth scheduling at tramp trade ports: Evidence from Indonesia. International Journal of Shipping and Transport Logistics, 16(1), 78–97. https://doi.org/10.1504/IJSTL.2024.134821

Sutrisno, E., & Basuki, A. (2023). Dampak keterlambatan sandar kapal terhadap biaya logistik di pelabuhan Indonesia. Jurnal Ekonomi Maritim Indonesia, 8(2), 112–127. https://doi.org/10.31315/jemi.v8i2.102

Abdelmaguid, T. F., & El-Awady, A. A. (2021). A decision support system for berth scheduling under uncertainty using hybrid metaheuristics. Computers & Industrial Engineering, 159, 107407. https://doi.org/10.1016/j.cie.2021.107407

Aydin, N., & Kara, B. Y. (2020). Predicting ship arrival times using machine learning methods. Maritime Policy & Management, 47(7), 923–941. https://doi.org/10.1080/03088839.2019.1674439

Bahri, M., Burhanuddin, M. A., & Saman, M. Y. M. (2018). A study of berth allocation problem with priority and stochastic handling time. International Journal of Industrial Engineering Computations, 9(2), 177–190. https://doi.org/10.5267/j.ijiec.2017.10.002

Chen, J., Zhang, G., & Zhang, Y. (2022). A hybrid deep learning model for vessel arrival time prediction in smart ports. Ocean Engineering, 266, 112876. https://doi.org/10.1016/j.oceaneng.2022.112876

Corchado, J. M., Bajo, J., Abraham, A., & Corchado, E. (2020). Intelligent systems for port logistics: A survey. Applied Soft Computing, 95, 106595. https://doi.org/10.1016/j.asoc.2020.106595

Dulebenets, M. A. (2021). A novel multi-objective optimization algorithm for berth scheduling. Applied Sciences, 11(5), 2341. https://doi.org/10.3390/app11052341

Fahmi, I., & Pratama, R. (2022). Analisis efisiensi operasional dermaga menggunakan metode Data Envelopment Analysis (DEA) di Pelabuhan Tanjung Priok. Jurnal Teknik Industri, 23(1), 45–56. https://doi.org/10.22219/jtiunmer.v23i1.18732

Golias, M. M., Boile, M., & Theofanis, S. (2019). A multi-objective decision support methodology for berth scheduling under uncertainty. Transportation Research Part E: Logistics and Transportation Review, 124, 1–18. https://doi.org/10.1016/j.tre.2019.01.012

Karam, A., & Eltawil, A. B. (2021). A machine learning approach for predicting vessel turnaround time in container terminals. Transportation Research Procedia, 52, 531–538. https://doi.org/10.1016/j.trpro.2021.02.071

Liu, C., & Wang, X. (2023). Comparative study of deep learning and ensemble methods for port operation forecasting. Journal of Marine Science and Engineering, 11(2), 321. https://doi.org/10.3390/jmse11020321

Meng, Q., & Wang, X. (2020). Predicting vessel service time using hybrid machine learning models: A case study of Singapore Port. Maritime Economics & Logistics, 22(4), 502–520. https://doi.org/10.1057/s41278-019-00142-8

Nugroho, A. D., & Sutrisno, E. (2020). Peningkatan efisiensi pelabuhan melalui optimasi penjadwalan sandar kapal berbasis heuristik. Jurnal Teknik Sipil ITB, 27(3), 215–228. https://doi.org/10.5614/jts.2020.27.3.5

Perwira, M., Hidayat, D., & Wijaya, R. (2021). Penerapan Random Forest untuk prediksi waktu pelayanan kapal di Pelabuhan Belawan. Jurnal Teknologi Informasi dan Ilmu Komputer, 8(4), 712–720. https://doi.org/10.25126/jtiik.2021843992

Rodriguez-Martin, I., Salazar-Gonzalez, J. J., & Santos-Hernandez, B. (2022). Solving the discrete berth allocation problem with stochastic vessel handling times. European Journal of Operational Research, 297(2), 584–598. https://doi.org/10.1016/j.ejor.2021.05.035

Santoso, A., & Wicaksono, B. D. (2019). Analisis sistem antrian dalam optimasi pelayanan kapal di Pelabuhan Tanjung Pandan. Jurnal Logistik Indonesia, 12(1), 33–45.

Wang, H., Zhang, D., & Zhang, Z. (2021). A comparative analysis of LSTM and XGBoost for time-series prediction in maritime operations. IEEE Access, 9, 102249–102260. https://doi.org/10.1109/ACCESS.2021.3096742.

Downloads

Published

2026-01-05

How to Cite

Andy Achmad Hendharsetiawan, Muhajirin, A., & Alwi Rina Riyanto. (2026). Komparasi Metode LSTM dan Random Forest dalam Prediksi Waktu Sandar Kapal untuk Optimasi Alokasi Dermaga: Studi Kasus Pelabuhan Tanjung Pandan. Dinasti Information and Technology, 3(2), 60–67. https://doi.org/10.38035/dit.v3i2.2929

Issue

Vol. 3 No. 2 (2025): Dinasti Information and Technology (October - December 2025)

Section

Articles

License

Copyright (c) 2026 Andy Achmad Hendharsetiawan, Adi Muhajirin, Alwi Rina Riyanto

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright :

Authors who publish their manuscripts in this journal agree to the following conditions:

  1. Copyright in each article belongs to the author.
  2. The author acknowledges that the DIT has the right to be the first to publish under a Creative Commons Attribution 4.0 International license (Attribution 4.0 International CC BY 4.0).
  3. Authors can submit articles separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal to other versions (for example, sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time at DIT.