• Computer Science > Networking and Internet Architecture [Submitted on 17 Feb 2026 (v1), last revised 18 Feb 2026 (this version, v2)] Title:High-Fidelity Network Management for Federated AI-as-a-Service: Cross-Domain Orchestration View PDF HTML (experimental)Abstract:To support the emergence of AI-as-a-Service (AIaaS), communication service providers (CSPs) are on the verge of a radical transformation-from pure connectivity providers to AIaaS a managed network service (control-and-orchestration plane that exposes AI models). • In this model, the CSP is responsible not only for transport/communications, but also for intent-to-model resolution and joint network-compute orchestration, i.e., reliable and timely end-to-end delivery. • The resulting end-to-end AIaaS service thus becomes governed by communications impairments (delay, loss) and inference impairments (latency, error). • A central open problem is an operational AIaaS control-and-orchestration framework that enforces high fidelity, particularly under multi-domain federation. • This paper introduces an assurance-oriented AIaaS management plane based on Tail-Risk Envelopes (TREs): signed, composable per-domain descriptors that combine deterministic guardrails with stochastic rate-latency-impairment models. • Using stochastic network calculus, we derive bounds on end-to-end delay violation probabilities across tandem domains and obtain an optimization-ready risk-budget decomposition.

Article Summaries:

  • Researchers have proposed a new control‑and‑orchestration framework to support federated AI‑as‑a‑Service (AIaaS) across multiple communication domains. The approach introduces “Tail‑Risk Envelopes” (TREs), signed per‑domain descriptors that combine deterministic guardrails with stochastic models of rate, latency, and loss. Using stochastic network calculus, the authors derive end‑to‑end delay‑violation bounds and a risk‑budget decomposition that can be optimized. Tenant‑level reservations are shown to curb bursty traffic, while an auditing layer estimates extreme‑percentile performance and attributes tail risk to individual domains. Monte‑Carlo simulations demonstrate improved 99.9th‑percentile compliance under overload and robust tenant isolation.

Sources: