Graph-Enhanced Deep Reinforcement Learning for Multi-Objective Unrelated Parallel Machine Scheduling

2025-12-07

Online World Conference on Soft Computing in Industrial Applications

AI Summary

This work addresses the unrelated parallel machine scheduling problem with release times, sequence-dependent setup times, and eligibility constraints, proposing a deep reinforcement learning framework that integrates graph neural networks (GNNs) with proximal policy optimization (PPO) to jointly optimize the conflicting objectives of total weighted tardiness and total setup time. To the best of our knowledge, this is the first approach to combine GNNs and PPO for multi-objective unrelated parallel machine scheduling, leveraging a multi-objective reward mechanism to directly learn scheduling policies while effectively capturing complex interactions between jobs and machines. Experimental results on standard benchmark instances demonstrate that the proposed method significantly outperforms conventional dispatching rules and metaheuristic algorithms, exhibiting superior performance in terms of objective balance, robustness, and scalability.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The Unrelated Parallel Machine Scheduling Problem (UPMSP) with release dates, setups, and eligibility constraints presents a significant multi-objective challenge. Traditional methods struggle to balance minimizing Total Weighted Tardiness (TWT) and Total Setup Time (TST). This paper proposes a Deep Reinforcement Learning framework using Proximal Policy Optimization (PPO) and a Graph Neural Network (GNN). The GNN effectively represents the complex state of jobs, machines, and setups, allowing the PPO agent to learn a direct scheduling policy. Guided by a multi-objective reward function, the agent simultaneously minimizes TWT and TST. Experimental results on benchmark instances demonstrate that our PPO-GNN agent significantly outperforms a standard dispatching rule and a metaheuristic, achieving a superior trade-off between both objectives. This provides a robust and scalable solution for complex manufacturing scheduling.

Problem

• Unrelated Parallel Machine Scheduling
• Multi-Objective Optimization
• Total Weighted Tardiness
• Total Setup Time
• Scheduling with Constraints

Innovation

• Graph Neural Network
• Deep Reinforcement Learning
• Multi-Objective Scheduling
• Proximal Policy Optimization
• Unrelated Parallel Machine Scheduling