Metraipolis › archive › dc_67ebb747232b
Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction — arXiv:2609.13701
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13701
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:50:40.491Z
- SHA-256 of the archived text
8c0804d06fc406cf23224ebfd629ddd5f04b741f50a1af8de30e648db7a647cb- Stable URL of this page
https://metraipolis.com/documento/dc_67ebb747232b
How to cite
Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction — arXiv:2609.13701 — arXiv (en), https://arxiv.org/abs/2609.13701 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_67ebb747232b (Metraipolis archive dc_67ebb747232b, sha256 8c0804d06fc406cf23224ebfd629ddd5f04b741f50a1af8de30e648db7a647cb)
BibTeX
@misc{dc67ebb747232b,
title = {Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction — arXiv:2609.13701},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13701},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_67ebb747232b; sha256 8c0804d06fc406cf23224ebfd629ddd5f04b741f50a1af8de30e648db7a647cb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13701. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Accurate job runtime prediction can improve scheduling-aware resource management in grid and distributed computing environments, but prediction models must be evaluated under realistic deployment constraints. This paper revisits CPU burst time prediction on the GWA-T-4 AuverGrid workload trace and reformulates it as leakage-safe pre-execution job runtime prediction. We define the target as job-level runtime, use only submission-time attributes, exclude post-execution variables, and evaluate models under temporal and cold-start settings rather than relying only on random cross-validation. We compare standard regressors, chronological historical baselines, categorical encoding strategies, and CatBoost with native categorical handling. We further add temporal hyperparameter tuning, runtime predictability analysis, feature ablation, error analysis by job length, and a minimal scheduling simulation. After temporal-validation tuning, CatBoost achieves the strongest deployment-oriented result with R^2=0.239, MAE=27,019, RMSE=46,587, and LogMAE=2.646 on the held-out temporal test set. A single-server simulation over all 69,523 held-out temporal test jobs shows that prediction-informed SJF reduces average waiting time by 50.92% relative to FCFS. The results show that random-split evaluation overestimates performance, categorical-native boosting improves temporal generalization, and long-job underestimation remains a scheduler-relevant challenge. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.13701 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T22:29:03.539Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).