Metraipolis › archive › dc_addb9967b66e

User-Assisted Collaborative Distributed Inference for Efficient QoS-Aware Autoscaling — arXiv:2608.11840

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11840
License (as archived)
CC0-1.0
Archived
2026-10-19T05:16:14.369Z
SHA-256 of the archived text
d3267428c97a2687969f8c3aef93935f577669290f745cfa18d661d96eb82e12
Stable URL of this page
https://metraipolis.com/documento/dc_addb9967b66e

How to cite

User-Assisted Collaborative Distributed Inference for Efficient QoS-Aware Autoscaling — arXiv:2608.11840 — arXiv (en), https://arxiv.org/abs/2608.11840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_addb9967b66e (Metraipolis archive dc_addb9967b66e, sha256 d3267428c97a2687969f8c3aef93935f577669290f745cfa18d661d96eb82e12)
BibTeX
@misc{dcaddb9967b66e,
  title = {User-Assisted Collaborative Distributed Inference for Efficient QoS-Aware Autoscaling — arXiv:2608.11840},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11840},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_addb9967b66e; sha256 d3267428c97a2687969f8c3aef93935f577669290f745cfa18d661d96eb82e12},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Growing demand for artificial intelligence (AI) inference services requires scalable infrastructure, yet centralized serving costs rise with demand. We propose a collaborative distributed inference system combining dedicated infrastructure with resources contributed by service users. Dedicated resources provide baseline capacity for maintaining quality of service (QoS), while volunteered resources absorb increasing demand without proportional growth in centralized infrastructure. To capture stochastic and dynamic interactions among users, resources, tasks, and policies, we develop a high-dimensional generative Markov model with structured temporal factorization. The model supports simulation and provides a foundation for task scheduling and QoS-aware resource allocation optimization. We evaluate the system across user populations, resource capacities, and centralized and distributed scheduling policies. Simulations show that distributed scheduling becomes increasingly advantageous as the user population grows, improving request completion and P99 latency while substantially reducing dedicated resource consumption. These results demonstrate the feasibility of user-assisted collaborative inference for infrastructure-efficient autoscaling.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI); Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2608.11840 — 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 2026-10-19T05:08:46.736Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).