Adaptive Requesting in Decentralized Edge Networks via Non-Stationary Bandits

2026-01-13

AI Summary

This work addresses the challenge of optimizing information freshness in decentralized edge networks, where multiple clients operate under partial observability—unable to monitor access point states or other users’ actions. The problem is formulated as a non-stationary multi-armed bandit, and the authors propose the AGING BANDIT WITH ADAPTIVE RESET algorithm, which integrates an adaptive sliding window with a periodic reset mechanism to effectively handle both abrupt and gradual changes in reward distributions. By doing so, the method overcomes key limitations of conventional bandit approaches in partially observable, history-dependent, and coupled environments, while providing near-optimal theoretical performance guarantees. Extensive simulations demonstrate that the proposed algorithm significantly enhances information freshness in dynamic edge network settings.

Technology Category

• Machine Learning: Online Learning & Bandits
• Multiagent Systems: Mechanism Design
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• 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
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

We study a decentralized collaborative requesting problem that aims to optimize the information freshness of time-sensitive clients in edge networks consisting of multiple clients, access nodes (ANs), and servers. Clients request content through ANs acting as gateways, without observing AN states or the actions of other clients. We define the reward as the age of information reduction resulting from a client's selection of an AN, and formulate the problem as a non-stationary multi-armed bandit. In this decentralized and partially observable setting, the resulting reward process is history-dependent and coupled across clients, and exhibits both abrupt and gradual changes in expected rewards, rendering classical bandit-based approaches ineffective. To address these challenges, we propose the AGING BANDIT WITH ADAPTIVE RESET algorithm, which combines adaptive windowing with periodic monitoring to track evolving reward distributions. We establish theoretical performance guarantees showing that the proposed algorithm achieves near-optimal performance, and we validate the theoretical results through simulations.

Problem

• decentralized edge networks
• information freshness
• non-stationary bandits
• age of information
• collaborative requesting

Innovation

• non-stationary bandits
• decentralized edge networks
• age of information
• adaptive windowing
• collaborative requesting