Learning-augmented Online Minimization of Age of Information and Transmission Costs

2024-03-05

Conference on Computer Communications Workshops

AI Summary

This paper addresses the challenge of transmitting time-sensitive data over time-varying wireless channels using resource-constrained sensors. We jointly optimize transmission energy consumption and information freshness, quantified by Age-of-Information (AoI). To this end, we propose the first learning-enhanced online scheduling algorithm that simultaneously achieves consistency and robustness. The algorithm integrates machine learning–based channel prediction, online competitive analysis, and a threshold-based adaptive decision mechanism. We theoretically establish a strict upper bound on its competitive ratio: it asymptotically approaches the offline optimal solution when predictions are accurate (consistency), while guaranteeing worst-case performance under prediction errors (robustness). Simulation results demonstrate that our method reduces total cost by 18%–35% compared to baseline approaches. Moreover, its performance degrades significantly more gracefully than purely learning-based methods as prediction error increases, effectively bridging the gap between classical online algorithms and modern learning-driven approaches.

Technology Category

• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Machine Learning: Online Learning & Bandits
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Social networks and social learning

Abstract

We consider a discrete-time system where a resource-constrained source (e.g., a small sensor) transmits its time-sensitive data to a destination over a time-varying wireless channel. Each transmission incurs a fixed transmission cost (e.g., energy cost), and no transmission results in a staleness cost represented by the Age-of-Information. The source must balance the tradeoff between transmission and staleness costs. To address this challenge, we develop a robust online algorithm to minimize the sum of transmission and staleness costs, ensuring a worst-case performance guarantee. While online algorithms are robust, they are usually overly conservative and may have a poor average performance in typical scenarios. In contrast, by leveraging historical data and prediction models, machine learning (ML) algorithms perform well in average cases. However, they typically lack worst-case performance guarantees. To achieve the best of both worlds, we design a learning-augmented online algorithm that exhibits two desired properties: (i) consistency: closely approximating the optimal offline algorithm when the ML prediction is accurate and trusted; (ii) robustness: ensuring worst-case performance guarantee even ML predictions are inaccurate. Finally, we perform extensive simulations to show that our online algorithm performs well empirically and that our learning-auamented algorithm achieves both consistency and robustness.

Problem

• Minimize age of information and transmission costs tradeoff
• Develop robust online algorithm with worst-case guarantees
• Design learning-augmented algorithm combining consistency and robustness

Innovation

• Learning-augmented online algorithm design
• Combining ML predictions with worst-case guarantees
• Balancing transmission costs and Age-of-Information