Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

High-Fidelity Network Management for Federated AI-as-a-Service: Cross-Domain Orchestration

Mohaned Chraiti, Ozgur Ercetin, Merve Saimler

TL;DR

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.

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. We show that tenant-level reservations prevent bursty traffic from inflating tail latency under TRE contracts. An auditing layer then uses runtime telemetry to estimate extreme-percentile performance, quantify uncertainty, and attribute tail-risk to each domain for accountability. Packet-level Monte-Carlo simulations demonstrate improved p99.9 compliance under overload via admission control and robust tenant isolation under correlated burstiness.

High-Fidelity Network Management for Federated AI-as-a-Service: Cross-Domain Orchestration

TL;DR

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.

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. We show that tenant-level reservations prevent bursty traffic from inflating tail latency under TRE contracts. An auditing layer then uses runtime telemetry to estimate extreme-percentile performance, quantify uncertainty, and attribute tail-risk to each domain for accountability. Packet-level Monte-Carlo simulations demonstrate improved p99.9 compliance under overload via admission control and robust tenant isolation under correlated burstiness.
Paper Structure (20 sections, 1 theorem, 25 equations, 4 figures, 1 table, 1 algorithm)

This paper contains 20 sections, 1 theorem, 25 equations, 4 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Motivations
  3. Related Work
  4. Problem Statement
  5. Contributions
  6. Contract Interface for Federated AIaaS
  7. Federated AIaaS execution pipeline and service contract
  8. Pipeline stages and architecture
  9. Tenant-level AI service-level objective
  10. TREs as a composable per-domain contract
  11. Compositional Tail Guarantees
  12. Single-domain tail bound under stochastic rate--latency
  13. End-to-end composition across an AIaaS pipeline: from per-domain TREs to a path-level bound
  14. Federated Provisioning and Assurance
  15. Federated provisioning under TRE contracts
  16. ...and 5 more sections

Key Result

Theorem 1

Under eq:arr_mgf and eq:neg_service_mgf, if $\Delta_{u,d}>0$, then for any deadline $\tau\ge T_d$,

Figures (4)

  • Figure 1: Federated AIaaS execution pipeline and assurance loop. The CSP AIaaS receives intents, selects model/placement, and provisions joint network--compute resources across a multi-stage path. Each administrative domain, including the Hyperscale Cloud Provider (HCP), exposes a TRE contract (signed, composable) rather than raw internal state. Telemetry feeds an audit layer for p99/p99.9 calibration.
  • Figure 2: Estimated p99.9 end-to-end delay versus normalized offered load $\rho$.
  • Figure 3: Isolation under burstiness.
  • Figure 4: Marginal tail-risk attribution under controlled degradation.

Theorems & Definitions (4)

  • Remark 1
  • Definition 1: Tail-Risk Envelope
  • Theorem 1: Single-domain delay-violation bound
  • proof