成本不确定性下面向物理互联网供应链优化的图神经网络引导遗传算法
A Graph Neural Network--Guided Genetic Algorithm for Physical Internet Supply Chain Optimization under Cost Uncertainty
浏览论文内容
中文总结 AI 辅助
针对成本不确定的物理互联网三级供应链优化问题，构建确定性与最小最大遗憾模型，提出GNN-GA算法，实验显示其在多实例上优于标准GA，学习到的初始化是主要改进来源。
中文摘要 AI 辅助
物理互联网网络中的库存与配送规划需要协调工厂-枢纽分配、工厂供应、协作枢纽间的横向转运、零售商配送及缺货管理。该问题结合了离散分配决策与相互依赖的连续流，而不确定的运营成本使鲁棒规划更具挑战性。本研究针对由工厂、枢纽和零售商构成的三级网络，构建了确定性模型与最小最大遗憾模型，并开发了图神经网络引导遗传算法（GNN-GA）用于分配决策。GNN会估计各枢纽特定的工厂选择概率，用于构建遗传算法（GA）的初始种群，并根据预测不确定性调整变异操作。每个未见过的候选分配通过求解剩余连续流问题至线性规划（LP）最优性来评估。在15个实例上，将模拟退火、标准GA与GNN-GA进行比较，采用匹配的随机种子和固定的不同分配评估次数限制。由于测试实例13-15的评估预算小于标称种群规模，这些实验主要评估学习到的初始化质量而非多代进化搜索。针对精确测试实例13的另一项400次评估实验允许完成三代完整后代和第四代部分迭代，在10次匹配运行中GNN-GA均优于GA。三个独立生成的精确可解实例提供了单独的迁移性测试。 ablation结果表明，学习到的初始化提供了大部分改进，而熵引导变异具有较小的、依赖于实例的影响。每实例的求解时间包含GNN推理与搜索，但不包含模型训练和一次性模型设置。
英文摘要
Inventory and distribution planning in Physical Internet networks requires coordinating factory-hub assignments, factory supply, lateral transshipment among collaborative hubs, retailer deliveries, and shortages. The problem combines discrete assignment decisions with interdependent continuous flows, while uncertain operating costs make robust planning more difficult. This study formulates deterministic and min-max regret models for a three-echelon network of factories, hubs, and retailers and develops a graph neural network-guided genetic algorithm (GNN-GA) for the assignment decisions. The GNN estimates hub-specific factory-selection probabilities that are used to construct the initial GA population and adapt mutation according to prediction uncertainty. Each previously unseen candidate assignment is evaluated by solving the remaining continuous-flow problem to LP optimality. Simulated annealing, a standard GA, and GNN-GA are compared on 15 instances using matched random seeds and fixed limits on distinct assignment evaluations. Because the evaluation budgets for test Instances 13-15 are smaller than the nominal population size, these experiments primarily assess the quality of learned initialization rather than multi-generation evolutionary search. A separate 400-evaluation experiment on exact test Instance 13 permits three complete offspring generations and a partial fourth pass, with GNN-GA outperforming GA in all 10 matched runs. Three independently generated exact-solvable instances provide a separate test of transfer. Ablation results show that learned initialization provides most of the improvement, while entropy-guided mutation has a smaller, instance-dependent effect. Per-instance solution times include GNN inference and search but exclude model training and one-time model setup.
发表机构
- Louisiana State University（路易斯安那州立大学）
机构由 AI 辅助整理，请以论文原文为准。
