A Real-Time Digital Twin for Adaptive Scheduling

TL;DR

This paper introduces SchedTwin, a real-time digital twin that adaptively guides HPC cluster scheduling by predictive simulation, outperforming static policies with low overhead.

Contribution

The paper presents SchedTwin, a novel real-time digital twin system that dynamically optimizes HPC scheduling using predictive simulation and integration with existing schedulers.

Findings

SchedTwin outperforms static scheduling policies.

Maintains low overhead of a few seconds per cycle.

Demonstrates practical effectiveness for adaptive HPC scheduling.

Abstract

High-performance computing (HPC) workloads are becoming increasingly diverse, exhibiting wide variability in job characteristics, yet cluster scheduling has long relied on static, heuristic-based policies. In this work we present SchedTwin, a real-time digital twin designed to adaptively guide scheduling decisions using predictive simulation. SchedTwin periodically ingests runtime events from the physical scheduler, performs rapid what-if evaluations of multiple policies using a high-fidelity discrete-event simulator, and dynamically selects the one satisfying the administrator configured optimization goal. We implement SchedTwin as an open-source software and integrate it with the production PBS scheduler. Preliminary results show that SchedTwin consistently outperforms widely used static scheduling policies, while maintaining low overhead (a few seconds per scheduling cycle). These results demonstrate that real-time digital twins offer a practical and effective path toward adaptive HPC scheduling.