Sustainable green supply chain and logistics management using adaptive fuzzy-based particle swarm optimization

Abstract

Sustainable Green Supply Chain and Logistics Management are crucial to reap environmental and economic wins in today’s complex and competitive global business environment. However, conventional optimization planning techniques can prove inadequate for green supply chain networks. This study proposes a sustainable green supply chain and logistics network that adopts a novel Adaptive Fuzzy Particle Swarm Optimization (AFPSO) method. This study presents a multi-objective mathematical model in combination with Mixed-Integer Linear Programming (MILP) and Multi-Adjacent Descent Traversal Algorithm (MADTA). AFPSO approach bases particle swarm optimization on fuzzy logic to improve efficiency in various conditions. Performance is assessed using parameters such as energy consumption, implementation cost, error values, and enabler applications. Performance assessment is carried out through MATLAB simulations, where the proposed AFPSO-MADTA is compared against Back-Propagation Neural Network (BPNN), the Traditional Particle Swarm Optimization Back-Propagation Neural Network (Traditional PSO-BPNN), and Improved Particle Swarm Optimization Back-Propagation Neural Network (IPSO-BPNN) methods. The results demonstrate that the proposed AFPSO-MADTA approach demonstrates greater energy efficiency, lower costs, higher accuracy, and better sustainability enabler stabilization than traditional optimization methodologies. These findings show the value of AFPSO-MADTA in achieving sustainable supply chain and logistics management.