Data-Driven Robust Optimization Model For A Sustainable Inventory Scheduling Framework

Production planning forms the backbone of global economies and supply chains, demanding a delicate balance between cost optimization and customer satisfaction. Scheduling material across interconnected production networks presents a complex analytical challenge, highlighting the need for data-driven insights to support informed decision-making. This research proposes an inventory scheduling framework that empowers decision-makers to monitor and control key production parameters, mitigating schedule risks and optimizing operational efficiency within the network. A sustainable framework of this study is to manage the work center energy consumption during Peak electricity load by prioritizing unit of flow for each work center. The inherent uncertainty in inventory scheduling, arising from factors such as work stage shortages and fluctuating order quantities, significantly impacts the ability to fulfill multi-product orders on time. To address this challenge, the framework incorporates both robust optimization and data-driven robust optimization approaches. This enables the system to adapt to fluctuations and uncertainties, ensuring operational resilience and achieving reliable fulfillment of multi-product orders while minimizing water consumption.

کلیدواژه ها:

Data-driven robust optimization ، Material requirements planning ، Robust Optimization Approach ، Material requirements planning ، Principal component analysis ، Kernel Density Estimation Introduction