Structure-Aware Online Optimization of the Age of Information with Unknown System Statistics
Abstract
Timely information dissemination is essential in modern communication systems, where low informational latency is critical for networked control, monitoring, and real-time decision-making. The Age of Information (AoI) has emerged as a fundamental metric for quantifying information freshness at the receiver. A key challenge in AoI optimization is selecting the update generation rate: infrequent updates lead to stale information, whereas overly frequent updates increase queueing delays. We develop a structure-aware, data-driven framework for adaptive AoI optimization modeled as single-server queues with unknown system statistics. Our key idea is to exploit analytical representations of the AoI gradient, which depend on a finite-dimensional collection of system quantities that can be estimated from observations collected during system operation. This reduces the online learning problem to estimating the quantities required by the gradient, rather than learning the AoI objective as a black box. We propose an online stochastic approximation algorithm that jointly estimates these quantities and optimizes the update generation rate. We prove almost sure convergence of the algorithm to the optimal update generation rate under mild regularity and moment conditions, despite the temporal dependence induced by the underlying queueing process. We demonstrate the framework in four representative incomplete-information settings, including FCFS queues with unknown service characteristics or hidden background traffic, a preemptive LCFS system with partial observations, and a generate-at-will system with threshold waiting.
Related
- Online Optimization with Unknown Time-Varying Parameters Using Noisy Gradient Measurements
- Fully Online Decentralized Learning in Stochastic Games with Unknown Independent Chains
- Accelerated Prox-Level Methods for Unknown Piecewise-Smooth Optimization II: Function-constrained Optimization
- Sequential Probability Ratio Test using Z-Statistics (SPRT-z): A Practical Approach for Online Experimentation
- Adaptive Restart under Unknown KL Geometry in Stochastic Weakly-Convex Optimization
BibTeX
@misc{inoue2026structureaware,
title = {{Structure-Aware Online Optimization of the Age of Information with Unknown System Statistics}},
author = {Yoshiaki Inoue and Michel Mandjes and Liron Ravner},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.13142},
eprint = {2610.13142},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.13142},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Structure-Aware Online Optimization of the Age of Information with Unknown System Statistics
AU - Yoshiaki Inoue
AU - Michel Mandjes
AU - Liron Ravner
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.13142
UR - https://arxiv.org/abs/2610.13142
AB - Timely information dissemination is essential in modern communication systems, where low informational latency is critical for networked control, monitoring, and real-time decision-making. The Age of Information (AoI) has emerged as a fundamental metric for quantifying information freshness at the receiver. A key challenge in AoI optimization is selecting the update generation rate: infrequent updates lead to stale information, whereas overly frequent updates increase queueing delays. We develop a structure-aware, data-driven framework for adaptive AoI optimization modeled as single-server queues with unknown system statistics. Our key idea is to exploit analytical representations of the AoI gradient, which depend on a finite-dimensional collection of system quantities that can be estimated from observations collected during system operation. This reduces the online learning problem to estimating the quantities required by the gradient, rather than learning the AoI objective as a black box. We propose an online stochastic approximation algorithm that jointly estimates these quantities and optimizes the update generation rate. We prove almost sure convergence of the algorithm to the optimal update generation rate under mild regularity and moment conditions, despite the temporal dependence induced by the underlying queueing process. We demonstrate the framework in four representative incomplete-information settings, including FCFS queues with unknown service characteristics or hidden background traffic, a preemptive LCFS system with partial observations, and a generate-at-will system with threshold waiting.
ER -