Modelling and solving sustainable supply chain network design based on graph autoencoder clustering algorithm
提出一种基于图自编码器聚类算法的供应链网络模型，兼顾经济和环境可持续性，能高效求解大规模实例，为企业提供实用方案。
The modelling of Sustainable Supply Chain Network Design (SSCND) is evolving significantly with increasing problem diversity and complexity. Existing algorithms face substantial challenges in accommodating various models and effectively handling large-scale instances. To address these challenges, we propose an intercity distances supply chain network model to reflect real-world scenarios, and develop a clustering mapping algorithm based on Graph Autoencoder (GAE) to solve the model. The mathematical model incorporates both economic and environmental sustainability dimensions, while also including supply chain responsiveness metrics. The algorithm operates by abstracting attribute information of supply chain potential participants, generating sparse graphs, and applying GAE clustering to create abstract nodes. The classified abstract nodes are then processed using the simplex method to generate preliminary solutions, which are subsequently mapped back into real-world solutions through a mapping mechanism. Experimental results demonstrate the high efficiency and stability of the proposed approach. For large-scale instances, it produces high-quality solutions in substantially less time compared to commercial solvers like CPLEX, offering a novel and practical approach for enterprises addressing sustainable supply chain design challenges.