Peramalan Volume Arus Peti Kemas dan Evaluasi Sistem Antrian Menggunakan Time Series dan Queuing Theory di Terminal XYZ

Hartanti, Hanni Putria (2026) Peramalan Volume Arus Peti Kemas dan Evaluasi Sistem Antrian Menggunakan Time Series dan Queuing Theory di Terminal XYZ. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043221019-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Terminal peti kemas memiliki peran penting dalam menjaga kelancaran rantai pasok dan efisiensi logistik nasional. Fluktuasi volume arus peti kemas menuntut kemampuan peramalan dan pengelolaan kapasitas yang tepat agar fasilitas bongkar muat dapat beroperasi secara optimal. Penelitian ini mengintegrasikan metode deret waktu dan teori antrian untuk meramalkan volume arus peti kemas serta mengevaluasi kapasitas pelayanan Terminal XYZ. Data periode Januari 2023 hingga Maret 2025 menunjukkan pola musiman tahunan,dengan peningkatan pada pertengahan tahun dan penurunan pada awal tahun berikutnya. Model terbaik yang diperoleh adalah SARIMA(0,1,1)(0,1,1)[12] dengan RMSE sebesar 5.698,057 TEUs, menunjukkan besarnya deviasi hasil peramalan dalam satuan asli data, serta MAPE sebesar 4,280%, yang berarti hasil peramalan rata-rata menyimpang sebesar 4,280% dari nilai aktual. Hasil peramalan periode April 2025 hingga April 2026 menunjukkan volume tertinggi pada Juli 2025 sebesar 79.736,05 TEUs dan volume terendah pada April 2026 sebesar 52.808,38 TEUs.
Hasil peramalan kemudian dikonversi menjadi laju kedatangan dan dianalisis menggunakan model antrian M/M/10, yang menggambarkan pelayanan peti kemas oleh 10 unit crane yang bekerja secara paralel, untuk mengevaluasi kemampuan kapasitas sistem dalam menangani beban kedatangan dengan laju pelayanan sebesar 27,5 TEUs/jam/crane. Analisis dilakukan melalui skenario Baseline berdasarkan laju kedatangan hasil peramalan, skenario Optimis dengan peningkatan laju kedatangan sebesar 20%, dan skenario Pesimis dengan penurunan laju kedatangan sebesar 20%. Pada skenario Baseline, utilisasi rata-rata sebesar 0,343 dan maksimum sebesar 0,403. Skenario Optimis menghasilkan utilisasi rata-rata sebesar 0,412 dan maksimum sebesar 0,483, yang berarti pada beban tertinggi sekitar 48,3% kapasitas pelayanan. Skenario Pesimis menghasilkan utilisasi rata-rata sebesar 0,274 dan maksimum sebesar 0,322. Seluruh skenario tetap stabil karena utilisasi berada di bawah satu. Hasil stress test menunjukkan bahwa sistem masih stabil ketika laju kedatangan meningkat hingga dua kali kondisi puncak Baseline, meskipun waktu tunggu meningkat secara nonlinier. Dengan demikian, kapasitas pelayanan Terminal XYZ masih memadai pada rentang beban yang dianalisis, tetapi pemantauan kapasitas tetap diperlukan pada periode puncak.
=====================================================================================================================================
Container terminals play a vital role in maintaining supply chain continuity and national logistics efficiency. Fluctuations in container throughput demand accurate forecasting and capacity management capabilities to ensure cargo handling facilities operate at an optimal level. This study integrates time series methodology and queuing theory to forecast container throughput volume and evaluate the service capacity of Terminal XYZ. Data spanning from January 2023 to March 2025 exhibits an annual seasonal pattern, characterized by mid-year increases and declines early in the following year. The best-performing model obtained is SARIMA(0,1,1)(0,1,1)[12] with a Root Mean Square Error (RMSE) of 5,698.057 TEUs, reflecting the deviation in the original unit of measurement, and a Mean Absolute Percentage Error (MAPE) of 4.280%, indicating that the forecast deviates by an average of 4.280% from actual values. Forecasting results for the period of April 2025 to April 2026 project a peak volume in July 2025 reaching 79,736.05 TEUs and a lowest volume in April 2026 at 52,808.38 TEUs. The forecasted volumes were then converted into arrival rates and analyzed using an M/M/10 queuing model, which represents container handling by 10 crane units operating in parallel, to evaluate the system's capacity performance in handling arrival loads at a service rate of 27.5 TEUs/hour/crane. The analysis was conducted through a Baseline scenario based on the forecasted arrival rates, an Optimistic scenario with a 20% increase in arrival rates, and a Pessimistic scenario with a 20% decrease in arrival rates. Under the Baseline scenario, the average utilization rate was 0.343 with a maximum of 0.403. The Optimistic scenario yielded an average utilization rate of 0.412 and a maximum of 0.483, meaning that during peak load, the system operates at approximately 48.3% of its service capacity. The Pessimistic scenario resulted in an average utilization rate of 0.274 and a maximum of 0.322. All scenarios remained stable as utilization rates stayed below one. Stress testing results demonstrated that the system remains stable even when arrival rates increase up to double the peak Baseline condition, despite a non-linear increase in waiting time. Consequently, the service capacity at Terminal XYZ remains adequate within the analyzed load range, though capacity monitoring remains necessary during peak periods.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Logistik Maritim, Peti Kemas, SARIMA, Terminal XYZ, Teori Antrian, Containers , Maritime Logistics, SARIMA, Terminal XYZ, Queuing Theory
Subjects:	H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA30.3 Time-series analysis Q Science > QA Mathematics > QA274.8 Queuing theory
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Hanni Putria Hartanti
Date Deposited:	29 Jul 2026 02:14
Last Modified:	29 Jul 2026 02:16
URI:	http://repository.its.ac.id/id/eprint/137339

Actions (login required)

View Item