Online Learning for Optimizing AoI-Energy Tradeoff under Unknown Channel Statistics

2025-09-23

AI Summary

This paper addresses the joint optimization of transmission energy consumption at source nodes and information freshness (measured by Age of Information, AoI) at the destination in energy-constrained real-time monitoring systems under unknown channel statistics. First, we prove that the optimal scheduling policy exhibits an AoI-driven threshold structure. Leveraging this structural insight, we propose an online learning algorithm that requires no prior knowledge of channel statistics and adapts decisions solely via real-time observation feedback. To our knowledge, this is the first algorithm achieving order-optimal finite-horizon regret bound of $O(1)$ in such unknown environments—significantly improving upon conventional $O(sqrt{T})$ learning approaches. Experimental results demonstrate that the proposed algorithm closely approaches the performance of the optimal policy under known channel statistics. The work thus provides both theoretical guarantees and a practical solution for low-power, high-timeliness IoT monitoring.

Technology Category

• Machine Learning: Online Learning & Bandits
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

We consider a real-time monitoring system where a source node (with energy limitations) aims to keep the information status at a destination node as fresh as possible by scheduling status update transmissions over a set of channels. The freshness of information at the destination node is measured in terms of the Age of Information (AoI) metric. In this setting, a natural tradeoff exists between the transmission cost (or equivalently, energy consumption) of the source and the achievable AoI performance at the destination. This tradeoff has been optimized in the existing literature under the assumption of having a complete knowledge of the channel statistics. In this work, we develop online learning-based algorithms with finite-time guarantees that optimize this tradeoff in the practical scenario where the channel statistics are unknown to the scheduler. In particular, when the channel statistics are known, the optimal scheduling policy is first proven to have a threshold-based structure with respect to the value of AoI (i.e., it is optimal to drop updates when the AoI value is below some threshold). This key insight was then utilized to develop the proposed learning algorithms that surprisingly achieve an order-optimal regret (i.e., $O(1)$) with respect to the time horizon length.

Problem

• Optimizes AoI-energy tradeoff with unknown channel statistics
• Develops online learning algorithms for threshold-based scheduling
• Achieves order-optimal regret without prior channel knowledge

Innovation

• Online learning algorithms optimize AoI-energy tradeoff
• Threshold-based policy structure proven for optimal scheduling
• Achieves order-optimal regret with unknown channel statistics