A Stochastic Goal Program for Employee Scheduling
A Stochastic Goal Program for Employee Scheduling
复制标题
员工调度的随机目标计划
DOI：
--
复制
发表时间：
1996
期刊：
影响因子：
--
通讯作者：
Donald F. Rossin
中科院分区：
文献类型：
--
作者：
Frederick Easton;Donald F. Rossin
员工调度决策的确定性目标程序试图通过将理想的员工数量分配给每个可行的调度来最小化预期的运营成本。对于计划范围内的每一段时间，经理必须首先确定应该安排值班的劳动量。这些要求通常是通过边际分析技术建立的，该技术使用对增量劳动力成本和短缺费用的估计。通常，规划范围内的每个时期都被评估为一个独立的时期。一个隐含的假设是，单个员工可以被分配到只有一个工作周期的时间表。如果这一假设违反了当地的工作规则，那么确定性目标计划的劳动力需求参数可能是次优的。
正如我们在这项研究中所表明的那样，这一众所周知的限制可能会导致代价高昂的人员配备和日程安排错误。我们提出了一种结合劳动力需求和调度决策的员工调度模型，克服了这一局限性。该模型使用的是所需劳动力数量的概率分布，而不是每个时期由外部决定的单一人员配备目标。该模式可以自由地为每个时期选择适当的人员配置水平，从而不需要单独的目标设定程序。在大多数情况下，这会导致更好、成本更低的决定。此外，拟议的模型很容易考虑到线性和非线性人员配置不足和超编的处罚。我们使用简单的示例来演示这些优势中的许多，并说明实现我们的模型所需的关键技术。我们还在1,700多个模拟的随机员工调度问题的研究中评估了它的性能。
Deterministic goal programs for employee scheduling decisions attempt to minimize expected operating costs by assigning the ideal number of employees to each feasible schedule. For each period in the planning horizon, managers must first determine the amount of labor that should be scheduled for duty. These requirements are often established with marginal analysis techniques, which use estimates for incremental labor costs and shortage expenses. Typically, each period in the planning horizon is evaluated as an independent epoch. An implicit assumption is that individual employees can be assigned to schedules with as little as a single period of work. If this assumption violates local work rules, the labor requirements parameters for the deterministic goal program may be suboptimal.
As we show in this research, this well-known limitation can lead to costly staffing and scheduling errors. We propose an employee scheduling model that overcomes this limitation by integrating the labor requirements and scheduling decisions. Instead of a single, externally determined staffing goal for each period, the model uses a probability distribution for the quantity of labor required. The model is free to choose an appropriate staffing level for each period, eliminating the need for a separate goal-setting procedure. In most cases this results in better, less costly decisions. In addition, the proposed model easily accommodates both linear and nonlinear under- and overstaffing penalties. We use simple examples to demonstrate many of these advantages and to illustrate the key techniques necessary to implement our model. We also assess its performance in a study of more than 1,700 simulated stochastic employee scheduling problems.