Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning

📄 arXiv: 2607.27626v1 📥 PDF

作者: Wentao Zhang, Wentao Mo

分类: cs.LG

发布日期: 2026-07-30

备注: Accepted to 2026 IEEE Real-Time Systems Symposium (RTSS)


💡 一句话要点

提出OCO-PAoI-Hard以解决IoT系统的实时安全问题

🎯 匹配领域: 支柱一:机器人控制 (Robot Control) 支柱二:RL算法与架构 (RL & Architecture)

关键词: 物联网 实时调度 安全性 在线凸优化 对抗学习 信息年龄 深度学习

📋 核心要点

  1. 现有方法在满足实时PAoI截止期限时,通常依赖于严格的假设条件,限制了其应用范围。
  2. 本文提出OCO-PAoI-Hard,通过将硬实时调度转化为时间变化的约束在线凸优化,解决了PAoI的安全性问题。
  3. 在实验中,OCO-PAoI-Hard在对抗流体模型通道上实现了零状态截止违规,而对比基线的违规率在1.65%到64.0%之间。

📝 摘要(中文)

安全关键的物联网系统(如工业闭环控制、V2X协调和远程遥操作)要求每个传感器的峰值信息年龄(PAoI)在严格的每个时隙截止期限内。现有方法在假设条件下才能满足这一要求,存在一定的局限性。本文提出的OCO-PAoI-Hard在对抗性系数下保证零每个时隙的PAoI状态违规,并通过严格因果的提议-保护-更新循环实现可行性。该方法在四个传感器的对抗流体模型通道上实现了零状态截止违规,且经验归一化后悔保持在理论范围内。

🔬 方法详解

问题定义:本文旨在解决安全关键物联网系统中传感器的峰值信息年龄(PAoI)在每个时隙内必须低于严格截止期限的问题。现有方法在假设条件下才能满足这一要求,导致其在实际应用中的局限性。

核心思路:论文的核心思路是将硬实时调度转化为时间变化的约束在线凸优化,通过将PAoI的截止期限转化为资源分配向量的仿射半空间约束,从而实现实时安全性。

技术框架:整体架构包括一个严格因果的提议-保护-更新循环,通过每个时隙的欧几里得投影来确保可行性,同时保持无后悔行为。该框架还简化了经典虚拟队列的设计。

关键创新:最重要的技术创新在于将PAoI的截止期限与资源分配的约束直接关联,使得在对抗性环境中能够实现零状态截止违规,这与现有方法的本质区别在于不再依赖于严格的假设条件。

关键设计:关键设计包括参数设置、损失函数的选择以及网络结构的简化,确保在对抗环境下的稳定性和可行性。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

在实验中,OCO-PAoI-Hard在四个传感器的对抗流体模型通道上实现了零状态截止违规,而四个代表性基线的违规率在1.65%到64.0%之间,显示出显著的性能提升。经验归一化后悔保持在理论范围内,验证了方法的有效性。

🎯 应用场景

该研究的潜在应用领域包括工业自动化、智能交通系统和远程医疗等安全关键的物联网场景。通过确保信息传递的及时性和安全性,可以显著提高系统的可靠性和效率,具有重要的实际价值和未来影响。

📄 摘要(原文)

Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Information (peak AoI, also abbreviated PAoI) to stay below a hard per-slot deadline, not merely an average bound. Existing approaches meet this requirement only under restrictive assumptions: stochastic channels for Whittle-index AoI, simulator rollouts for deep reinforcement learning, or sublinear cumulative violation for long-term constrained online convex optimization. Under adversarial coefficients, OCO-PAoI-Hard guarantees zero per-slot violation of the modeled AoI state under one-step viability and O(sqrt(T)) regret against any static safe comparator; packet-level safety requires stronger service assumptions. Our key observation is that the fractional peak-AoI deadline collapses exactly to an affine half-space constraint on the resource-allocation vector, turning hard real-time scheduling into time-varying constrained online convex optimization over a polyhedral safe set. A strictly causal proposal-shield-update loop enforces feasibility through one Euclidean projection per slot, the gradient step preserves no-regret behavior, and the classical virtual queue is reduced to an a-posteriori certificate. We establish closed-form static and dynamic regret bounds, a matching Omega(sqrt(T)) minimax lower bound, a margin-safe variant against execution noise, and a deadline-induced competitive ratio. On a four-sensor adversarial fluid-model trap channel, OCO-PAoI-Hard attains zero modeled-state deadline violations across all ten seeds, while four representative baselines miss between 1.65 percent and 64.0 percent of slots, and the empirical normalized regret stays below the theoretical envelope across two orders of magnitude in T.