arxiv: 2604.22799 · v1 · submitted 2026-04-13 · 💻 cs.HC · cs.CY· hep-ex

Recognition: unknown

Enabling users to work sustainably on shared institute computing resources

Benjamin Fischer, Jan Kelleter, Johannes Erdmann, Martin Erdmann, Niclas Eich, Paul Gilles, Tim Hauptreif

Authors on Pith no claims yet

Pith reviewed 2026-05-10 15:41 UTC · model grok-4.3

classification 💻 cs.HC cs.CYhep-ex

keywords sustainable computingenergy monitoringgreen schedulinguser behaviorcomputing clustercarbon footprintrenewable energyphysics research

0 comments

The pith

A physics computing cluster cuts emissions by letting users track their energy use and schedule jobs during renewable peaks.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows how a mid-scale shared cluster for physics data analysis addresses sustainability when major hardware upgrades are impractical due to its location in a 1970s building. Instead of technical retrofits, it deploys per-job energy monitoring, real-time grid renewable data, and voluntary user tools including personal consumption queries, weekly reports, project tagging, and memory-based resource hints. A simulation framework estimates the resulting impact on emissions. The measures rely on building user awareness rather than enforcing limits, targeting medium- to long-term greenhouse-gas reductions through changed habits in the research community.

Core claim

Recording per-job energy consumption and combining it with live renewable-share data from the German grid enables green-window scheduling, while voluntary interfaces let users query footprints, receive reports, tag jobs by project, and reuse memory records to prevent oversubscription, all evaluated through a simulation framework to support emission reductions via increased resource awareness.

What carries the argument

The per-job energy monitoring system integrated with real-time renewable-share data for green-window scheduling, plus voluntary user reports, tagging, and memory records, evaluated by a simulation framework.

If this is right

Users can check their personal energy consumption and carbon footprints at any time and receive weekly reports that highlight their usage patterns.
Jobs can be preferentially submitted during green windows when the grid's renewable share is high, directly lowering associated emissions.
Project tagging allows aggregate accounting of energy use across research groups without imposing hard limits.
Memory usage records from prior runs help users request appropriate resources and avoid oversubscription that wastes energy.
The simulation framework supplies quantitative estimates of potential greenhouse-gas savings from these combined measures.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Similar voluntary monitoring and scheduling systems could be deployed on other shared research clusters that face building retrofit constraints.
Widespread adoption might gradually shift experimental design choices in physics and data analysis toward lower-energy computing patterns.
The emphasis on cultural change through information rather than mandates offers a model for sustainability efforts in other academic computing environments.

Load-bearing premise

That voluntary user engagement with energy data, reports, and green-window scheduling will produce enough behavioral changes to achieve meaningful emission reductions.

What would settle it

A before-and-after measurement of total cluster energy consumption and emissions over multiple years, or user surveys tracking actual changes in job submission timing and resource requests.

read the original abstract

The VISPA project is a self-managed, mid-scale computing cluster that supports physics data analysis in research and teaching. Because the cluster is housed in a 1970s institute building with limited retrofit options, conventional efficiency upgrades would yield only minor energy savings. We therefore target sustainability primarily through user-centric measures. A monitoring system now records per-job energy consumption, while real-time data on the renewable share of the German power grid enable `green-window' scheduling. Users can query their individual energy consumption and carbon footprints, receive weekly reports, and tag jobs by project for aggregate accounting; memory records from previous runs help avoid oversubscription. All options are voluntary, fostering a cultural shift rather than imposing hard constraints. A simulation framework evaluates the potential impact of these measures. Together, the technological and behavioral interventions aim at medium- to long-term reductions in greenhouse-gas emissions by increasing resource awareness within the scientific community.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper describes a practical voluntary toolkit for energy awareness on a small physics cluster but supplies no usage data or measured impact to back its emission-reduction claims.

read the letter

The core of this work is a set of user-facing tools on the VISPA cluster: per-job energy logging, real-time German grid renewable data for green-window scheduling, voluntary queries and weekly reports, project tagging, and memory-history checks to reduce oversubscription. All of it stays optional to encourage cultural change rather than rules. They also built a simulation to project possible savings. That combination is a reasonable adaptation for an institute stuck with a 1970s building where hardware retrofits are limited. It pulls together existing ideas from green computing into one deployed system aimed at academic users. The description is clear on the components and how they fit the constraints. The main weakness is the missing evidence. The text gives the system design and simulation framework but no logs, no uptake numbers, no baseline comparisons, and no sensitivity checks on how many users actually need to participate for the savings to matter. The central assumption—that voluntary engagement will deliver medium-term GHG cuts—therefore stays untested. This is the sort of paper that could interest cluster admins or HCI researchers working on sustainability interfaces in research settings. It is not a new empirical result or formal derivation, so it is unlikely to change how most people cite green-computing work. Still, the concrete implementation details are worth a referee's time for feedback on design choices and on what data would be needed next. I would send it to review rather than desk-reject.

Referee Report

2 major / 0 minor

Summary. The manuscript describes the VISPA project, a self-managed mid-scale computing cluster supporting physics data analysis and teaching. Limited by its 1970s building infrastructure, the authors implement user-centric sustainability measures: a per-job energy monitoring system, real-time integration of German grid renewable-share data for green-window scheduling, and voluntary user tools including individual energy/carbon queries, weekly reports, project-based job tagging for aggregate accounting, and historical memory records to reduce oversubscription. A simulation framework is presented to evaluate potential impacts. The central claim is that these technological and behavioral interventions, by increasing resource awareness, will produce medium- to long-term greenhouse-gas emission reductions without imposing hard constraints.

Significance. If the behavioral assumptions hold and the simulation is validated, the work could meaningfully advance sustainable practices in shared research computing where hardware retrofits are infeasible. It provides a concrete, deployed example of voluntary feedback mechanisms in a real cluster and highlights the role of user awareness in HCI for sustainability. The simulation framework offers a starting point for impact modeling in similar environments, though its current lack of detail and empirical grounding limits immediate applicability.

major comments (2)

[Abstract] Abstract and simulation framework description: the central claim of medium- to long-term GHG reductions rests on the assumption that voluntary user engagement with queries, reports, and green-window scheduling will produce sufficient behavioral change, yet the manuscript supplies no usage logs, participation rates, measured emission impacts, baseline comparisons, or validation of the simulation against real data.
[Simulation framework] Simulation framework section: no details are given on the framework's methodology, key parameters (e.g., assumed participation fraction or sensitivity to voluntary uptake), input data sources, or how projections account for the absence of hard constraints, rendering the potential-impact evaluation non-reproducible and insufficient to support the emission-reduction claim.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive and detailed feedback on our manuscript. We appreciate the recognition of the potential value of voluntary, user-centric approaches to sustainability in shared computing environments where hardware upgrades are limited. We address the major comments below and indicate the changes we will make to the manuscript.

read point-by-point responses

Referee: [Abstract] Abstract and simulation framework description: the central claim of medium- to long-term GHG reductions rests on the assumption that voluntary user engagement with queries, reports, and green-window scheduling will produce sufficient behavioral change, yet the manuscript supplies no usage logs, participation rates, measured emission impacts, baseline comparisons, or validation of the simulation against real data.

Authors: We acknowledge that the current manuscript does not include empirical usage logs, participation rates, or measured emission reductions. The VISPA system has only recently been deployed, and the paper's primary contribution is the description of the implemented monitoring, scheduling, and feedback tools together with a simulation framework to explore prospective impacts. We will revise the abstract to frame the GHG-reduction claim more explicitly as a potential, medium- to long-term outcome that depends on user engagement, rather than as a demonstrated result. We agree that real-world validation would strengthen the work but cannot supply such data at present. revision: partial
Referee: [Simulation framework] Simulation framework section: no details are given on the framework's methodology, key parameters (e.g., assumed participation fraction or sensitivity to voluntary uptake), input data sources, or how projections account for the absence of hard constraints, rendering the potential-impact evaluation non-reproducible and insufficient to support the emission-reduction claim.

Authors: We agree that the simulation framework section requires substantially more detail to be reproducible. In the revised manuscript we will expand this section to describe the underlying methodology, the key parameters (including assumed participation fractions and sensitivity analyses for voluntary uptake), the sources of input data (historical cluster job logs and German grid renewable-share time series), and the modeling approach used to project impacts under voluntary rather than mandatory constraints. These additions will make the framework transparent and allow others to replicate or adapt the analysis. revision: yes

standing simulated objections not resolved

Empirical usage logs, participation rates, measured emission impacts, and baseline comparisons, which are not yet available because the VISPA monitoring and feedback features have only recently been implemented and sufficient longitudinal data have not been collected.

Circularity Check

0 steps flagged

No significant circularity; system description and simulation lack self-referential derivations or fitted predictions

full rationale

The paper describes a deployed monitoring system for per-job energy use, voluntary user tools (queries, reports, green-window scheduling), and a simulation framework to evaluate potential impact. No equations, fitted parameters, or predictions appear that reduce by construction to the paper's own inputs. The central claim is an aspirational aim for emission reductions via increased awareness, supported by external real-time grid data rather than self-defined or self-cited quantities. No load-bearing self-citations, ansatzes, or renamings of known results are evident in the provided text. This is a standard non-circular project report.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the unverified premise that voluntary information and scheduling tools will drive behavioral change sufficient for emission reductions; no free parameters or new entities are introduced.

axioms (1)

domain assumption Users will voluntarily adjust computing behavior when given personal energy consumption data, carbon footprints, and green-window options.
The paper explicitly states all options are voluntary and aim at a cultural shift rather than hard constraints.

pith-pipeline@v0.9.0 · 5471 in / 1269 out tokens · 46399 ms · 2026-05-10T15:41:12.844519+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

25 extracted references · 16 canonical work pages

[1]

https://vispa.physik

VISPA homepage. https://vispa.physik. rwth-aachen.de. [Online; Accessed: 8-Apr-2026] (2026)

2026
[2]

: Visual physics data anal- ysis in the Web browser

Brodski, M., et al. : Visual physics data anal- ysis in the Web browser. J. Phys. Conf. Ser. 331, 072056 (2011) https://doi.org/10.1088/ 1742-6596/331/7/072056

2011
[3]

: A Development Environment for Visual Physics Anal- ysis

Bretz, H.P., et al. : A Development Environment for Visual Physics Anal- ysis. JINST 7, 08005 (2012) https: //doi.org/10.1088/1748-0221/7/08/T08005 arXiv:1205.4912 [physics.data-an]

work page doi:10.1088/1748-0221/7/08/t08005 2012
[4]

: A field study of data analysis exercises in a bachelor physics course using the internet platform VISPA

Erdmann, M., et al. : A field study of data analysis exercises in a bachelor physics course using the internet platform VISPA. Eur. J. Phys. 35, 035018 (2014) https: //doi.org/10.1088/0143-0807/35/3/035018 arXiv:1402.2836 [physics.ed-ph]

work page doi:10.1088/0143-0807/35/3/035018 2014
[5]

: The VISPA internet platform for outreach, education and scien- tific research in various experiments

Asseldonk, D., et al. : The VISPA internet platform for outreach, education and scien- tific research in various experiments. J. Phys. Conf. Ser. 664(3), 032031 (2015) https://doi. org/10.1088/1742-6596/664/3/032031

work page doi:10.1088/1742-6596/664/3/032031 2015
[6]

: Evolution of the VISPA-project

Erdmann, M., et al. : Evolution of the VISPA-project. EPJ Web Conf. 214, 05021 (2019) https://doi.org/10.1051/epjconf/ 201921405021

work page doi:10.1051/epjconf/ 2019
[7]

: The VISPA internet- platform in deep learning applications

Erdmann, M., et al. : The VISPA internet- platform in deep learning applications. J. Phys. Conf. Ser. 1085(4), 042044 (2018) https://doi.org/10.1088/1742-6596/1085/4/ 042044

work page doi:10.1088/1742-6596/1085/4/ 2018
[8]

Eich, N., Erdmann, M., Fackeldey, P., Fis- cher, B., Noll, D., Rath, Y.: Fast Columnar 15 Physics Analyses of Terabyte-Scale LHC Data on a Cache-Aware Dask Cluster. Comput. Softw. Big Sci. 7(1), 3 (2023) https://doi.org/10.1007/s41781-023-00095-9 arXiv:2207.08598 [physics.data-an]

work page doi:10.1007/s41781-023-00095-9 2023
[9]

Concurrency and Computation: Practice and Experience 17(2-4), 323–356 (2005) https://doi.org/10.1002/cpe.938

Thain, D., Tannenbaum, T., Livny, M.: Dis- tributed computing in practice: the condor experience. Concurrency and Computation: Practice and Experience 17(2-4), 323–356 (2005) https://doi.org/10.1002/cpe.938

work page doi:10.1002/cpe.938 2005
[10]

: Resource-aware Research on Universe and Matter: Call- to-Action in Digital Transformation

Bruers, B., et al. : Resource-aware Research on Universe and Matter: Call- to-Action in Digital Transformation. Eur. Phys. J. Spec. Top. (2024) https: //doi.org/10.1140/epjs/s11734-024-01436-4 arXiv:2311.01169 [physics.comp-ph]

work page doi:10.1140/epjs/s11734-024-01436-4 2024
[11]

Let’s wait awhile: how temporal workload shifting can reduce carbon emissions in the cloud,

Wiesner, P., Behnke, I., Scheinert, D., Gontarska, K., Thamsen, L.: Let’s wait awhile: how temporal workload shifting can reduce carbon emissions in the cloud. In: Proceedings of the 22nd International Middleware Conference. Middleware ’21, pp. 260–272. Association for Computing Machinery, New York, NY, USA (2021). https://doi.org/10.1145/3464298.3493399 ...

work page doi:10.1145/3464298.3493399 2021
[12]

Hybrid cloud and hpc approach to high-performance dataframes,

Haghshenas, K., Setz, B., Aiello, M.: CO2 Emission Aware Scheduling for Deep Neural Network Training Workloads. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 1542–1549 (2022). https://doi. org/10.1109/BigData55660.2022.10020544

work page doi:10.1109/bigdata55660.2022.10020544 2022
[13]

1038/s44168-025-00232-7 arXiv:2403.03308 [physics.soc-ph]

Lang, V.S., Bhalla, N.K., Gurdasani, S.S., Niknejadi, P.: Know your footprint – Evalu- ation of the professional carbon footprint for individual researchers in high energy physics and related fields (2024) https://doi.org/10. 1038/s44168-025-00232-7 arXiv:2403.03308 [physics.soc-ph]

work page arXiv 2024
[14]

Burger et al.: Electric- ity traﬀic light for Germany

B. Burger et al.: Electric- ity traﬀic light for Germany. https://www.energy-charts.info/charts/ consumption_advice/chart.htm?l=en&c= DE. [Accessed: 19-Oct-2025] (2025)

2025
[15]

Instrum.11, 05018 (2016) https://doi.org/10.1088/1748-0221/ 11/05/C05018

Chatrchyan, S., et al. : The CMS Experi- ment at the CERN LHC. JINST 3, 08004 (2008) https://doi.org/10.1088/1748-0221/ 3/08/S08004

work page doi:10.1088/1748-0221/ 2008
[16]

Aab, A., et al.: The Pierre Auger Cosmic Ray Observatory. Nucl. Instrum. Meth. A 798, 172–213 (2015) https://doi.org/10.1016/j. nima.2015.06.058 arXiv:1502.01323 [astro- ph.IM]

work page doi:10.1016/j 2015
[18]

[Accessed: 8-Dec-2025] (2025)

https://gude-systems.com/produkte/ expert-power-control-8226/ . [Accessed: 8-Dec-2025] (2025)

2025
[19]

Gude Systems: Expert Power Control
[20]

[Accessed: 8-Dec-2025] (2025)

https://gude-systems.com/produkte/ expert-power-control-8035/ . [Accessed: 8-Dec-2025] (2025)

2025
[21]

https://allianz-entwicklung-klima.de/ toolbox

Stiftung Allianz für Entwicklung und Klima: CO2e und GWP. https://allianz-entwicklung-klima.de/ toolbox. [Accessed: 29-Oct-2025] (2023)

2025
[22]

In: Pro- ceedings

Raman, R., Livny, M., Solomon, M.: Match- making: distributed resource management for high throughput computing. In: Pro- ceedings. The Seventh International Sym- posium on High Performance Distributed Computing (Cat. No.98TB100244), pp. 140– 146 (1998). https://doi.org/10.1109/HPDC. 1998.709966

work page doi:10.1109/hpdc 1998
[23]

Burger et al.: Energy-Charts API: Public net electricity production for a given country for each production type

B. Burger et al.: Energy-Charts API: Public net electricity production for a given country for each production type. https://api.energy-charts.info/#/power/ public_power_public_power_get. [Accessed: 31-Mar-2026] (2026)

2026
[24]

In: IPCC Special Report on Renewable Energy Sources and Climate Change Mitigation

Moomaw, W., Burgherr, P., Heath, G., Lenzen, M., Nyboer, J., Verbruggen, A.: Annex ii: Methodology. In: IPCC Special Report on Renewable Energy Sources and Climate Change Mitigation. Cambridge Uni- versity Press, Cambridge, United Kingdom and New York, NY, USA (2011)

2011
[25]

, Gardner, R

Smith, N., et al. : Coffea: Columnar Object Framework For Effective Analysis. EPJ 16 Web Conf. 245, 06012 (2020) https: //doi.org/10.1051/epjconf/202024506012 arXiv:2008.12712 [cs.DC]

work page doi:10.1051/epjconf/202024506012 2020
[26]

Gray, L., Smith, N.: Evaluating Awkward Arrays, uproot, and coffea as a query plat- form for High Energy Physics Data. J. Phys. Conf. Ser. 2438(1), 012033 (2023) https:// doi.org/10.1088/1742-6596/2438/1/012033 17

work page doi:10.1088/1742-6596/2438/1/012033 2023