Optimization of Bulk Cargo Terminal Unloading and Outbound Operations Based on a Deep Reinforcement Learning Framework DOI Creative Commons
Haijiang Li, Jiapeng Zhao, Peng Jia

и другие.

Journal of Marine Science and Engineering, Год журнала: 2025, Номер 13(1), С. 105 - 105

Опубликована: Янв. 8, 2025

This study addresses the integrated scheduling problem of dry bulk cargo terminal yards, which includes three components: transportation planning, yard selection optimization, and equipment scheduling. Additionally, research integrates safety considerations complexities dynamic planning. work presents two innovations. Firstly, this develops a sophisticated modeling framework that graph structures for precise mapping with mixed-integer programming to enforce operational constraints. approach facilitates more accurate comprehensive representation operations, capturing diverse aspects while maintaining model clarity computational efficiency. Secondly, proposes an advanced solution methodology employs reinforcement learning technique integrating Dueling Deep Q-Network Double Q-Network. hybrid algorithm significantly enhances optimization performance accelerates process, thereby improving efficiency solutions. The experimental results demonstrate proposed effectively manages material ingress, storage, egress within yard. plans generated by outperform traditional first-come, first-served strategies, showcasing substantial improvements in port reliability. underscores potential significant advancements overall management ports.

Язык: Английский

Optimization of Bulk Cargo Terminal Unloading and Outbound Operations Based on a Deep Reinforcement Learning Framework DOI Creative Commons
Haijiang Li, Jiapeng Zhao, Peng Jia

и другие.

Journal of Marine Science and Engineering, Год журнала: 2025, Номер 13(1), С. 105 - 105

Опубликована: Янв. 8, 2025

This study addresses the integrated scheduling problem of dry bulk cargo terminal yards, which includes three components: transportation planning, yard selection optimization, and equipment scheduling. Additionally, research integrates safety considerations complexities dynamic planning. work presents two innovations. Firstly, this develops a sophisticated modeling framework that graph structures for precise mapping with mixed-integer programming to enforce operational constraints. approach facilitates more accurate comprehensive representation operations, capturing diverse aspects while maintaining model clarity computational efficiency. Secondly, proposes an advanced solution methodology employs reinforcement learning technique integrating Dueling Deep Q-Network Double Q-Network. hybrid algorithm significantly enhances optimization performance accelerates process, thereby improving efficiency solutions. The experimental results demonstrate proposed effectively manages material ingress, storage, egress within yard. plans generated by outperform traditional first-come, first-served strategies, showcasing substantial improvements in port reliability. underscores potential significant advancements overall management ports.

Язык: Английский

Процитировано

1