























Abstract:Service level agreements (SLAs) in data center colocation contracts define precise thresholds for power, temperature, and humidity, with tiered violation penalties expressed as credits against monthly recurring charges. Traditional reactive monitoring detects breaches only after they occur, limiting remediation opportunities. We present a framework that encodes SLA rules as structured JSON objects to generate training data without manual annotation. We train a per-customer multi-head transformer model in which each attention head specializes in one SLA rule, learning temporal dependencies that precede violations by 30 minutes. Post-training, the inference service emits structured prediction events transformed into three role-specific views: finance schemas exposing credit liability, operations schemas surfacing risk scores and recommended interventions, and compliance schemas bundling predictions with immutable telemetry signatures for audit. By aligning model architecture directly with contractual obligations, this framework enables operators to anticipate SLA breaches, prioritize corrective actions, and minimize financial penalties.
| Comments: | 6 pages, 9 figures, 46th IEEE International Conference on Distributed Computing Systems |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.05354 [cs.LG] |
| (or arXiv:2605.05354v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.05354 arXiv-issued DOI via DataCite |
From: Omanshu Thapliyal [view email]
[v1]
Wed, 6 May 2026 18:31:06 UTC (2,605 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。