Heterogeneous Graph Attention Networks for Scheduling in Cloud Manufacturing and Logistics

Abstract

Efficient task scheduling and resource allocation in manufacturing are vital for gaining competitive advantages in dynamic economic environments. Modern manufacturing systems must integrate logisticsconsiderations such as delivery times and costs, yet traditional scheduling methods often overlook thesefactors. To address this gap, we investigate task scheduling in cloud manufacturing systems, emphasizinglogistics integration. We propose a novel Graph Neural Network architecture for optimizing task schedulingby representing the problem on a heterogeneous graph, where nodes denote tasks and locations. Our modelminimizes both manufacturing and logistics costs, achieving significant performance improvements overgreedy algorithms and comparable results to strong genetic algorithms in large-scale scenarios with up to20 locations. This work advances the efficiency and flexibility of cloud manufacturing systems, offeringpractical solutions for dynamic, cost-sensitive environments.