Rully Tri Cahyono’s research while affiliated with Bandung Institute of Technology and other places

Background: Accurate inventory management of intermittent spare parts requires precise demand forecasting. The sporadic and irregular nature of demand, characterized by long intervals between occurrences, results in a significant data imbalance, where demand events are vastly outnumbered by zero-demand periods. This challenge has been largely overlooked in forecasting research for intermittent spare parts. Methods: The proposed model incorporates the Synthetic Minority Oversampling Technique (SMOTE) to balance the dataset and uses focal loss to enhance the sensitivity of deep learning models to rare demand events. The approach was empirically validated by comparing the model’s Mean Squared Error (MSE) performance and Area Under the Curve (AUC). Results: The ensemble model achieved a 47% reduction in MSE and a 32% increase in AUC, demonstrating substantial improvements in forecasting accuracy. Conclusions: The findings highlight the effectiveness of the proposed method in addressing data imbalance and improving the prediction of intermittent spare part demand, providing a valuable tool for inventory management.

Background: Container terminal congestion is often measured by the average turnaround time for external trucks. Reducing the average turnaround time can be resolved by controlling the yard crane operation and the arrival times of external trucks (truck appointment system). Because the truck appointment system and yard crane scheduling problem are closely interconnected, this research investigates synchronization between the approaches used in truck appointment systems and yard crane scheduling strategies. Rubber-tired gantry (RTG) operators for yard crane scheduling operations strive to reduce RTG movement time as part of the container retrieval service. However, there is a conflict between individual agent goals. While seeking to minimize truck turnaround time, RTGs may travel long distances, ultimately slowing down the RTG service. Methods: We address a method that balances individual agent goals while also considering the collective objective, thereby minimizing turnaround time. An agent-based simulation is proposed to simulate scenarios for yard crane scheduling strategies and truck appointment system approaches, which are centralized and decentralized. This study explores the combined effects of different yard scheduling strategies and truck appointment procedures on performance indicators. Various configurations of the truck appointment system and yard scheduling strategies are modeled to investigate how those factors affect the average turnaround time, yard crane utilization, and CO2 emissions. Results: At all levels of truck arrival rates, the nearest-truck-first-served (NTFS) scenario tends to provide lower external truck turnaround times than the first-come-first-served (FCFS) and nearest-truck longest-waiting-time first-served (NLFS) scenario. Conclusions: The decentralized truck appointment system (DTAS) generally shows slightly higher efficiency in emission reduction compared with centralized truck appointment system (CTAS), especially at moderate to high truck arrival rates. The decentralized approach of the truck appointment system should be accompanied by the yard scheduling strategy to obtain better performance indicators.

This research aims to provide the best strategic supply chain network design decisions for e-groceries to accommodate growing demand at the minimum cost. The decisions include supply chain network configuration, facility location, and facility capacity at each year in the period of analysis. We use combination approach of k-means clustering and linear programming to cater big dataset of historical demand and number of customers. We use a real case from an Indonesian e-grocery provider. A computer-based mathematical model is built using CPLEX Python API. By optimizing the program, this study concludes the recommendation for the company is to operate facilities at certain capacity level for year 2023–2025, along with the service configuration.

Makalah ini membahas model penjadwalan dinamis dari operasi tangki bahan bakar umum dan pompa. Modelnya bersifat dinamis karena waktu kedatangan kapal diperbolehkan bervariasi. Tujuan dari studi ini adalah untuk menentukan alokasi/penjadwalan dermaga yang optimal dan rekomendasi kebijakan yang meminimalkan total waktu tunggu kapal, rasio hunian dermaga, dan biaya sewa kapal. Pemodelan Discrete-event Systems (DES) dipilih karena aperiodisitas dalam waktu kedatangan kapal dan waktu operasi asinkron di antara posisi berlabuh yang berbeda. Dua model DES dikembangkan, yaitu: (1) masalah alokasi biaya berganda (MBAP) untuk dermaga suplai dan (2) masalah alokasi dermaga sederhana (SBAP) untuk dermaga konsinyasi. Selanjutnya, digunakan model predictive control (MPC) untuk mengoptimalkan model DES, dan juga disediakan analisis matematis dari algoritma yang diusulkan. Contoh numerik memeriksa dua kasus (pasang surut dan non-pasang surut) di masing-masing model disajikan untuk menggambarkan solusi optimal. Masalah yang dihadapi adalah alokasi tambatan saat ini tidak bekerja secara efisien, yang ditunjukkan dengan rata-rata waktu tunggu kapal di dermaga pemasok (dermaga 1 dan 2) yang di atas standar (14 jam), sedangkan dermaga konsinyasi (dermaga 3) berada jauh di bawah standar.

We present a dynamical modeling of integrated (end-to-end) container terminal operations using finite state machine (FSM) framework where each state machine is represented by a discrete-event system (DES) formulation. The hybrid model incorporates the operations of quay cranes (QC), internal trucks (IT), and yard cranes (YC) and also the selection of storage positions in container yard (CY) and vessel bays. The QC and YC are connected by the IT in our models. As opposed to the commonly adapted modeling in container terminal operations, in which the entire information/inputs to the systems are known for a defined planning horizon, in this research we use real-time trucks, crane, and container storage operations information, which are always updated as the time evolves. The dynamical model shows that the predicted state variables closely follow the actual field data from a container terminal in Tanjung Priuk, Jakarta, Indonesia. Subsequently, using the integrated container terminal hybrid model, we proposed a model predictive algorithm (MPA) to obtain the near-optimal solution of the integrated terminal operations problem, namely the simultaneous allocation and scheduling of QC, IT, and YC, as well as selecting the storage location for the inbound and outbound containers in the CY and vessel. The numerical experiment based on the extensive Monte Carlo simulation and real dataset show that the MPA outperforms by 3-6% both of the policies currently implemented by the terminal operator and the state-of-the-art method from the current literature.

In this paper, we study the problem of integrated berth and quay crane allocation (I-BCAP) in general seaport container terminals and propose the model predictive allocation (MPA) algorithm and preconditioning methods for solving the I-BCAP. First, we propose a dynamical modeling framework based on discrete-event systems (DESs), which describes the operation of a berthing process with multiple discrete berthing positions and multiple quay cranes. Second, based on the discrete-event model, we propose the MPA algorithm for solving the I-BCAP using the model predictive control (MPC) principle with a rolling event horizon. The validation and performance evaluation of the proposed modeling framework and allocation method are done using: 1) extensive Monte Carlo simulations with realistically generated datasets; 2) real dataset from a container terminal in Tanjung Priuk port, located in Jakarta, Indonesia; and 3) real life field experiment at the aforementioned container terminal. The numerical simulation results show that our proposed MPA algorithm can improve the efficiency of the process where the total handling and waiting cost is reduced by approximately 6%-9% in comparison with the commonly adapted method of first-come first-served (FCFS) (for the berthing process) combined with the density-based quay cranes allocation (DBQA) strategy. Moreover, the proposed method outperforms the state-of-the-art hybrid particle swarm optimization (HPSO)-based and genetic algorithm (GA)-based method proposed in the recent literature. The real life field experiment shows an improvement of about 6% in comparison with the existing allocation method used in the terminal.

We study in this paper a dynamic berth and quay cranes allocation strategy in general seaport container terminals. We develop a dynamical model that describes the operation of berthing process with multiple discrete berthing positions and multiple quay cranes. Based on the proposed model, we develop a dynamic allocation strategy using the model predictive control (MPC) paradigm. The proposed strategy is evaluated using real data from a container terminal in Indonesia. The simulation results show that the MPC-based allocation strategy can improve the efficiency of the process where the total handling and waiting cost is reduced by approximately 20% in comparison to the commonly adapted method of first-come first-served (FCFS) (for the berthing process) combined with the density-based quay cranes allocation strategy.