A Persistence-Aware Framework for Age Violation Control in Wireless Status Update Systems

2026-05-13

AI Summary

Traditional Age of Information (AoI) metrics struggle to capture the persistence of consecutive age violations, falling short of the stringent reliability demands of safety-critical wireless applications. This work proposes a reliability assessment framework based on a Continuous Age Violation Rate (C-AVR) vector, which, for the first time, quantifies consecutive violations across multiple time windows and integrates diverse optimization objectives—such as average persistence and tail-sensitive performance—through a unified weighting mechanism. To address challenges posed by sparse rewards and temporal dependencies, the authors employ a Quantile Regression-based Dueling Double Deep Q-Network (QR-D3QN) that models the full return distribution rather than just its expectation, significantly enhancing learning capability for rare yet persistent violation sequences. Experiments demonstrate consistent superiority over expectation-based baselines across various system configurations, with pronounced gains in tail-sensitive scenarios, thereby validating the effectiveness of the C-AVR framework for multi-scale, persistence-aware reliability evaluation.

Abstract

Timely and reliable status updates are essential for emerging QoS-sensitive wireless applications. Common age of information (AoI)-based metrics, such as average AoI and age violation rate (AVR), characterize time-averaged freshness or violation frequency but do not explicitly capture the temporal persistence of consecutive age violations, which can be critical in safety-sensitive wireless applications. We develop a persistence-aware reliability framework based on the consecutive age violation rate (C-AVR) vector, whose components quantify AoI threshold violations over consecutive time windows of different lengths. Through flexible weighting schemes, the proposed framework unifies reliability objectives ranging from average persistence to tail-sensitive performance. Optimizing weighted C-AVR objectives is challenging because consecutive violations are temporally correlated, leading to sparse learning signals. To address this issue, we develop a distributional reinforcement learning approach based on a quantile regression dueling double deep Q-network (QR-D3QN). By modeling a quantile-based return distribution rather than only a scalar expected return, QR-D3QN provides richer value-estimation signals for rare but prolonged violation sequences under stochastic packet arrivals, unreliable channels, and transmission cost constraints. Simulation results show that QR-D3QN consistently outperforms expectation-based baselines across a wide range of weighting schemes and system settings, with particularly significant gains under tail-sensitive persistence objectives. Component-wise analysis further shows that distributional value learning substantially improves reliability across multiple persistence scales, especially for long consecutive violation sequences. Overall, our results establish the proposed C-AVR framework as an effective foundation for persistence-aware reliability evaluation.

Problem

• Age of Information
• Persistence
• Consecutive Age Violation
• Reliability
• Wireless Status Update

Innovation

• Consecutive Age Violation Rate (C-AVR)
• Persistence-aware reliability
• Distributional reinforcement learning
• Quantile regression D3QN
• Age of Information (AoI)