SUPPLY CHAIN PRODUCTION PLANNING AND SCHEDULING COORDINATION USING DISCRETE EVENT SIMULATION.

Effective coordination of multi-echelon supply chains is vital in dynamic markets, yet traditional methods fail to address inherent complexity and uncertainties. This study proposes a novel discrete event simulation (DES) and genetic algorithm (GA) integration to optimize production planning and scheduling. The DES model simulates real-world dynamics, including demand fluctuations and delays, while the GA optimizes critical decisions (production schedules, inventory levels) through iterative learning. A hierarchical framework combines mathematical supply chains modelling, DES-based scenario testing, and GA-driven decision refinement. Experimental results demonstrate significant improvements: 15-22 % cost reduction, 10-18 % shorter lead times, and 12-20 % higher service levels compared to conventional methods. This approach advances supply chain management by bridging dynamic simulation with metaheuristic optimization, offering enterprises a scalable tool for adaptive decision-making under uncertainty. The work underscores the value of integrating simulation and AI to tackle complex supply chain challenges. [ABSTRACT FROM AUTHOR]