Metraipolis › archive › dc_ec80c317cd11

PRISM: Predictive Runtime In-place Scaling and Model Selection for Edge Microservices — arXiv:2608.21910

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21910
License (as archived)
CC0-1.0
Archived
2026-10-18T07:50:10.923Z
SHA-256 of the archived text
9b19efe72377c5371941ade811d5f7d95ab222224c70760a1f77e42c9ac0faf4
Stable URL of this page
https://metraipolis.com/documento/dc_ec80c317cd11

How to cite

PRISM: Predictive Runtime In-place Scaling and Model Selection for Edge Microservices — arXiv:2608.21910 — arXiv (en), https://arxiv.org/abs/2608.21910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec80c317cd11 (Metraipolis archive dc_ec80c317cd11, sha256 9b19efe72377c5371941ade811d5f7d95ab222224c70760a1f77e42c9ac0faf4)
BibTeX
@misc{dcec80c317cd11,
  title = {PRISM: Predictive Runtime In-place Scaling and Model Selection for Edge Microservices — arXiv:2608.21910},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21910},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec80c317cd11; sha256 9b19efe72377c5371941ade811d5f7d95ab222224c70760a1f77e42c9ac0faf4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Latency-sensitive edge AI services must balance strict deadlines, output quality, and limited compute and energy budgets. However, static CPU provisioning wastes resources because inference cost varies substantially across inputs, model variants, and runtime conditions. We present PRISM, a prediction-guided runtime framework that jointly selects model variants and CPU allocations for containerized edge microservices. Using container-level energy monitoring and lightweight regression models, PRISM adapts each pipeline stage in place and minimizes predicted CPU-package energy under deadline, resource, and offline model-level Quality of Result (QoR) constraints. We evaluate PRISM on more than 52,000 requests in an Automatic License Plate Recognition (ALPR) pipeline with detection and recognition stages. For detection, PRISM reduces energy consumption by 36 % compared to the strongest static configuration while preserving a comparable success rate and using less than half of the average CPU allocation. For recognition, it reaches near-static-best performance with lower average CPU allocation. These results show that predictive in-place adaptation is a practical mechanism for making time-sensitive AI microservice pipelines more energy-efficient at the edge.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-25 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2608.21910 — 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 2026-10-18T07:47:32.945Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).