Authors - Sowmini Devi Veeramachaneni Abstract - This paper addresses the challenge of balancing economic performance and environmental sustainability in supply chain optimization. We propose a bi-level hybrid optimization framework that integrates Particle SwarmOptimization (PSO) with Linear Programming (LP) for carbonaware business decision making. At the upper level, PSO dynamically optimizes the carbon penalty parameter, while at the lower level, LP ensures optimal and feasible operational decisions under supply chain constraints. The proposed framework automatically learns the trade-off between profit and emissions, eliminating the need for manual parameter tuning. Experimental results on both synthetic and real-world datasets demonstrate that the method effectively identifies Pareto-optimal solutions, achieves stable convergence, and exhibits strong robustness compared to standalone optimization approaches.
Open Zoom