Resilient Pharmaceutical Supply Chain Design Using GRU Forecasting and Grasshopper Optimization Dual Technique

One of the biggest problems facing contemporary medical care is effectively managing pharmaceutical distribution networks and hospital evacuations, especially in times of emergency. This study suggests a novel bi-objective optimization paradigm to handle these issues. The model simultaneously minimizes overall expenses and maximizes patient satisfaction by combining sophisticated artificial intelligence techniques with the Mixed-Integer Linear Programming (MILP) method. The use of Gated Recurrent Unit (GRU) Neural Network (NN) for drug demand forecasting, which permits dynamic resource allocation in emergencies, is a significant advance. To avoid medication shortages, the model also incorporates a dedicated medical supply chain. Supply chain dependability is ensured by considering probabilistic demand patterns and disruption threats to increase system robustness. The solution methodology effectively handles the problem's multi-objective character by combining the e-constraint methodology with the Grasshopper Optimization Algorithm (GOA). The model's usefulness in actual situations is demonstrated by the results in an increase in cost reduction, and it helps in resource allocation and service level. This study offers important insights for improving healthcare logistics on important occasions, improving patient welfare and operational effectiveness, and helps in investigating the current problems medical supply chain management system.