货运铁路工程师的呼叫窗口调度
Call Window Scheduling for Freight Rail Engineers
AI总结：
该研究针对货运铁路工程师调度问题，提出集合覆盖型优化模型与直接算法，经实验验证集合覆盖型模型需求未覆盖率更低、休息机会更多且延迟更少，敏感性分析显示工程师可用时间上限影响关键性能指标。
AI中文摘要：
本研究针对《工作时间（HOS）法规》下基于呼叫窗口的货运铁路工程师调度新方法展开研究。与计划行程指派不同，呼叫窗口明确规定工程师可能被要求开始工作的时间区间，这在应对不确定行程需求时提供了更大灵活性，同时为工程师提供了更可预测的休假时段。目前美国所有主要货运运营商都要求工程师在强制休息时段外保持全天候待命，引发了对员工疲劳与安全的担忧。我们将呼叫窗口调度问题形式化，并提出两种解决方案：一种是集合覆盖型优化模型，另一种是直接算法。两者均旨在最大化需求覆盖范围，同时最小化受HOS可行性约束的工程师数量。针对2城和3城实例开展的计算实验，涉及不同的呼叫窗口长度、最大延迟允许值以及是否允许空驶行程，结果显示集合覆盖型模型的需求未覆盖率（2城和3城实例分别为94.89%和91.09%）高于直接算法（93.96%和71.83%），且该模型还提供了更多休息机会并减少了延迟。敏感性分析表明，工程师可用时间的上限对所有关键性能指标有显著影响。
英文摘要：
This study investigates a new approach for scheduling freight rail engineers based on call windows under the Hours of Service (HOS) regulations. Unlike planned trip assignments, call windows specify a time interval during which an engineer may be required to start work, thus providing greater flexibility to handle uncertain trip demand while offering drivers more predictable off-duty periods. Currently in the U.S., all major freight operators require drivers to be available 24/7 outside of mandatory rest periods, raising concerns over workforce fatigue and safety. We formalize the call-window scheduling problem and propose two solution approaches: a Set-covering-type optimization model and a Direct Algorithm. Both aim to maximize demand coverage while minimizing the number of engineers subject to HOS feasibility. Computational experiments for 2-city and 3-city instances with varying call window lengths, maximum delay allowances, and whether to allow deadhead trips show that the Set-covering-type model yields higher demand undercoverage (94.89% and 91.09% for 2-city and 3-city instances, respectively) than the Direct Algorithm (93.96% and 71.83%). It also offers greater rest opportunities and reduced delays. Sensitivity analysis reveals that the upper limit on engineer availability significantly affects all key performance metrics.
