Metraipolis › archive › dc_0dca99328b0e

GreenPipe: Power Modeling for Containerized DNN Inference on Kubernetes Edge Nodes — arXiv:2609.04952

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04952
License (as archived)
CC0-1.0
Archived
2026-10-16T22:41:14.648Z
SHA-256 of the archived text
3d9093f3fa6ab0871e2e41a7a875cf19deb9e955102bc0fc872d6495a0b00e22
Stable URL of this page
https://metraipolis.com/documento/dc_0dca99328b0e

How to cite

GreenPipe: Power Modeling for Containerized DNN Inference on Kubernetes Edge Nodes — arXiv:2609.04952 — arXiv (en), https://arxiv.org/abs/2609.04952 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0dca99328b0e (Metraipolis archive dc_0dca99328b0e, sha256 3d9093f3fa6ab0871e2e41a7a875cf19deb9e955102bc0fc872d6495a0b00e22)
BibTeX
@misc{dc0dca99328b0e,
  title = {GreenPipe: Power Modeling for Containerized DNN Inference on Kubernetes Edge Nodes — arXiv:2609.04952},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04952},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0dca99328b0e; sha256 3d9093f3fa6ab0871e2e41a7a875cf19deb9e955102bc0fc872d6495a0b00e22},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04952. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Distributed DNN inference is increasingly deployed in containerized edge-cloud environments, where workloads run on-device or are exposed to remote clients over the network. Accurate online power estimation on resource-constrained ARM nodes without hardware power counters such as RAPL remains a challenge, and CPU-only models fail to capture multi-resource behavior. We present GreenPipe, an automated profiling-training-validation pipeline that builds multi-resource regression models from external power meter measurements and attributes power to containers proportionally. GreenPipe is evaluated on a Raspberry Pi 4 edge node in a K3s edge-cloud testbed, covering DNN inference with three vision models, multiple precisions, thread counts, and both local and serving scenarios. System-level MAPE is 6.3-9.4%, improving over CPU-stress and utilization-only baselines by 26.9% MAPE on average. We jointly report inference latency and energy per inference, exposing performance-energy trade-offs across workload configurations.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-07 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2609.04952 — 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 2026-10-16T22:26:34.116Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).