Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AWaRe-SAC: Proactive Slice Admission Control under Weather-Induced Capacity Uncertainty

Dror Jacoby, Yanzhi Li, Shuyue Yu, Nicola Di Cicco, Hagit Messer, Gil Zussman, Igor Kadota

TL;DR

A proactive slice admission control framework is developed for mmWave x-haul networks subject to rain-induced fluctuations to improve network performance, ensure QoS, and optimize revenue, thereby surpassing the limitations of standard reactive approaches.

Abstract

As emerging applications demand higher throughput and lower latencies, operators are increasingly deploying millimeter-wave (mmWave) links within x-haul transport networks, spanning fronthaul, midhaul, and backhaul segments. However, the inherent susceptibility of mmWave frequencies to weather-related attenuation, particularly rain fading, complicates the maintenance of stringent Quality of Service (QoS) requirements. This creates a critical challenge: making admission decisions under uncertainty regarding future network capacity. To address this, we develop a proactive slice admission control framework for mmWave x-haul networks subject to rain-induced fluctuations. Our objective is to improve network performance, ensure QoS, and optimize revenue, thereby surpassing the limitations of standard reactive approaches. The proposed framework integrates a deep learning predictor of future network conditions with a proactive Q-learning-based slice admission control mechanism. We validate our solution using real-world data from a mmWave x-haul deployment in a dense urban area, incorporating realistic models of link capacity attenuation and dynamic slice demands. Extensive evaluations demonstrate that our proactive solution achieves 2-3x higher long-term average revenue under dynamic link conditions, providing a scalable and resilient framework for adaptive admission control.

AWaRe-SAC: Proactive Slice Admission Control under Weather-Induced Capacity Uncertainty

TL;DR

A proactive slice admission control framework is developed for mmWave x-haul networks subject to rain-induced fluctuations to improve network performance, ensure QoS, and optimize revenue, thereby surpassing the limitations of standard reactive approaches.

Abstract

As emerging applications demand higher throughput and lower latencies, operators are increasingly deploying millimeter-wave (mmWave) links within x-haul transport networks, spanning fronthaul, midhaul, and backhaul segments. However, the inherent susceptibility of mmWave frequencies to weather-related attenuation, particularly rain fading, complicates the maintenance of stringent Quality of Service (QoS) requirements. This creates a critical challenge: making admission decisions under uncertainty regarding future network capacity. To address this, we develop a proactive slice admission control framework for mmWave x-haul networks subject to rain-induced fluctuations. Our objective is to improve network performance, ensure QoS, and optimize revenue, thereby surpassing the limitations of standard reactive approaches. The proposed framework integrates a deep learning predictor of future network conditions with a proactive Q-learning-based slice admission control mechanism. We validate our solution using real-world data from a mmWave x-haul deployment in a dense urban area, incorporating realistic models of link capacity attenuation and dynamic slice demands. Extensive evaluations demonstrate that our proactive solution achieves 2-3x higher long-term average revenue under dynamic link conditions, providing a scalable and resilient framework for adaptive admission control.
Paper Structure (24 sections, 11 equations, 7 figures, 2 tables, 1 algorithm)

This paper contains 24 sections, 11 equations, 7 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Dataset and Problem Setting
  4. mmWave Network Measurements
  5. Network Slice Modeling From User Requests
  6. Problem Formulation
  7. System Design
  8. Capacity Predictions with AttIRNN
  9. Prediction Problem Statement
  10. AttIRNN Model
  11. Discrete Probability Distribution over Capacity Levels
  12. Slice Admission Control
  13. Rate Control
  14. Locally Optimal
  15. Predictive Q-Learning
  16. ...and 9 more sections

Figures (7)

  • Figure 1: Overview of the AWaRe-SAC framework workflow.
  • Figure 2: RSL measurements and rainfall intensities, showing rain-induced attenuation and corresponding capacity levels.
  • Figure 3: AttIRNN. Seq2Seq-based predictions with temporal attention for $H$-step prediction using $T$-step history.
  • Figure 4: Time-series RSL prediction with uncertainty bounds and capacity thresholds during rainfall, alongside CV trends grouped by rainfall intensity.
  • Figure 5: AttIRNN prediction performance
  • ...and 2 more figures