Multi-objective simulation-optimization for a distribution center resource planning
研究通过多目标仿真优化方法，在配送中心中最小化平均排队时间、工人和叉车数量，并识别出入库缓冲区为关键瓶颈，为资源调度提供策略。
This study tackles resource planning in distribution centers, aiming to enhance efficiency while minimizing the number of deployed workers and forklifts. We achieve this by optimizing resource schedules across different areas and time periods. Initially, we developed a detailed warehouse simulation model to reflect resource limitations and their impact on operations. Specifically, we define staging areas, including the receiving dock, inbound buffer area, and outbound buffer area, which serve as the start and end points of all activities and the nexus of resource allocation. Utilizing modular modeling and an event-driven discrete-event mechanism, our proposed model can accelerate the simulation process while ensuring high fidelity. We then design multi-objective simulation-optimization models, aiming for Pareto optimality, minimizing average queuing time, workforce size, and forklift fleetsize under different skill set scenarios. Using a customized multiple gradient descent-simultaneous perturbation stochastic approximation algorithm, our approach effectively handles many-objective problems and significantly reduces CPU time compared to evolutionary algorithms. A case study highlights the inbound buffer area as a key bottleneck and reveals the impact of incomplete skills on workforce deployment. Drawing insights from the results, we discuss several strategies for enhancing efficiency—including deploying part-time workers—offering new solutions to warehouse resource planning challenges.