風を考慮したパレート多目的強化学習による港湾進入水路の低炭素船舶交通整理
Wind-constrained Pareto multi-objective reinforcement learning for low-carbon vessel traffic organization in port approach channels (原題)
Zhengjiao Qi, Yukuan Wang, Jingxian Liu, Jing Qu
🤖 gxceed AI 要約
日本語
港湾進入水路での船舶交通整理に、風を考慮したパレート多目的強化学習（Pareto MO-PPO）を適用。風速を排出要因かつスケジューリング制約として組み込み、効率と排出のトレードオフを学習。曹妃甸港のシナリオで、FCFS比で排出11.41%削減、システム時間7.49%増加を実現し、運航者に明示的な選択肢を提供する。
English
This study applies a wind-constrained Pareto multi-objective reinforcement learning (Pareto MO-PPO) to vessel traffic organization in port approach channels, incorporating wind as both an emission driver and scheduling constraint. In a Caofeidian Port scenario, the balanced policy reduced emissions by 11.41% while increasing system time by 7.49% compared to FCFS, offering port operators explicit trade-off choices.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本の港湾・海運業界では、IMOのGHG削減戦略や国内のカーボンニュートラルポート（CNP）構想が進む中、港湾運航の効率化と排出削減は重要課題。本手法は、風況を考慮したリアルタイムの運航最適化により、港湾の省エネと排出削減に寄与し、CNP政策や港湾管理者の取り組みに示唆を与える。
In the global GX context
Globally, ports face pressure to reduce emissions under IMO and national decarbonization targets. This study demonstrates how AI-driven scheduling can optimize vessel traffic for both efficiency and emissions, providing a scalable approach for ports worldwide to meet sustainability goals while maintaining operational performance.
👥 読者別の含意
🔬研究者:Provides a novel application of multi-objective RL to port vessel scheduling with wind constraints, offering a methodological template for similar logistics optimization.
🏢実務担当者:Port operators can use the Pareto policy approach to make informed trade-offs between transit time and emissions, potentially reducing fuel costs and carbon footprint.
🏛政策担当者:Highlights the potential of AI-based traffic management to contribute to port decarbonization targets, informing policy on smart port initiatives and emission reduction mandates.
📄 Abstract（原文）
Port approach channels concentrate vessel conflicts, waiting, and speed adjustments that can increase fuel use and CO2 emissions, yet real-time wind is rarely represented as both an emission driver and a scheduling constraint. This study develops a wind-constrained vessel traffic organization framework and a Pareto-based multi-objective proximal policy optimization algorithm (Pareto MO-PPO). A wind-aware propulsion model links vessel speed, transit time, relative wind, and CO2 emissions, while wind-dependent engine-load limits restrict the feasible speed range. A preference-conditioned actor-critic network learns policies across the efficiency and emission trade-off, and an external archive retains non-dominated policies. The framework was evaluated in a Caofeidian Port scenario. Relative to first-come, first-served (FCFS) scheduling, the balanced policy reduced emissions by 11.41% while increasing system time by 7.49%. Detailed results show how wind-aware Pareto policy learning can provide port operators with explicit operating choices rather than a single fixed weight solution.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.3389/fmars.2026.1926689first seen 2026-08-26 04:39:23
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。