Optimizing Blood Plasma Distribution in Blood Banks through Evolutionary Computation

Efficient blood plasma distribution is essential for minimizing wastage and ensuring timely availability in blood banks. This study proposes an optimized assignment framework that enhances blood plasma management by maximizing utilization before expiration and ensuring Rhesus compatibility. We implement and compare three evolutionary optimization algorithms, namely genetic algorithm (GA), particle swarm optimization (PSO), and differential evolution (DE), with enhancements to balance exploration and exploitation for optimal inventory management. Extensive experiments were conducted by varying key control parameters, such as population size and the number of generations or iterations, while maintaining consistency across all algorithms. Performance evaluation on real-world blood bank datasets demonstrates that DE outperforms GA and PSO, achieving the lowest blood importation and expiration rates. The results highlight the potential of evolutionary computation in optimizing healthcare inventory management problems, which offers practical strategies for improving blood bank efficiency, data-driven decision-making, and patient care outcomes.