Skip to content
DSML.KZ
Publications

Code · Code Ocean · August 19, 2026

LIWSA-GNN: Graph Neural Network-Based Workflow Scheduling in WorkflowSim

Mohammed Alaa Fadhil Al-hadeethi
Open via DOI

Abstract

This compute capsule implements and evaluates LIWSA-GNN, a Graph Neural Network-driven planning algorithm for scientific workflow scheduling within the WorkflowSim framework. It features a multi-seed training pipeline in Python using PyTorch Geometric and integrates exported model weights into Java-based WorkflowSim/CloudSim simulations across standard workflow benchmarks (Montage, CyberShake, Sipht, Epigenomics, Inspiral).

Distributed and Parallel Computing SystemsScientific Computing and Data ManagementCloud Computing and Resource Managementscientific workflow schedulinggraph neural networksWorkflowSim

More by Mohammed Alaa Fadhil Al-hadeethi