A cost effective and reliable environment monitoring system for HPC applications
Peter Bernd Otte, Dalibor Djukanovic

TL;DR
This paper introduces a cost-effective, scalable environment monitoring system for HPC applications, featuring a novel hardware device that combines Raspberry Pi, Arduino, and PoE, enhancing reliability and efficiency.
Contribution
It presents a new hardware device and system design for environment monitoring in HPC, improving cost efficiency and reliability over existing solutions.
Findings
System successfully deployed at a 2 PFLOPS HPC cluster.
Hardware device integrates Raspberry Pi, Arduino, and PoE in a compact form.
Enhanced environment monitoring improves HPC reliability.
Abstract
We present a slow control system to gather all relevant environment information necessary to effectively and reliably run an HPC (High Performance Computing) system at a high value over price ratio. The scalable and reliable overall concept is presented as well as a newly developed hardware device for sensor read out. This device incorporates a Raspberry Pi, an Arduino and PoE (Power over Ethernet) functionality in a compact form factor. The system is in use at the 2 PFLOPS cluster of the Johannes Gutenberg-University and Helmholtz-Institute in Mainz.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSmart Grid Energy Management
