Game Theoretic Analysis of Age of Federated Information for Participatory Data Ecosystems

We investigate a scenario where multiple sources independently and voluntarily contribute status reports, which are then aggregated through a federated process. To address the challenge of partial participation in distributed systems, we introduce the age of federated information (AoFI), a novel metric that quantifies data freshness. This metric is specifically designed to bridge the gap between classical age of information, which is unsuitable for collaborative tasks, and the often impractical age of correlated information, which requires full participation. To model distributed optimization across multiple independent sources, we adopt a game-theoretic framework. In this framework, users strategically minimize their individual penalty, computed as a global-local combination of the overall AoFI on the common receiver’s side and their individual energy expenditure. We derive the worst-case Nash equilibrium of this game and compare its efficiency with the centralized optimization optimum. Our efficiency analysis reveals a critical design tradeoff for practical industrial internet of things (IIoT) deployments: while decentralized coordination is highly efficient in high-participation regimes, performance in low-participation regimes is paradoxically optimized by actively restricting the number of sources to prevent strategic inefficiencies.