Age-Optimal Power Allocation in Industrial IoT: A Risk-Sensitive Federated Learning Approach

TL;DR

This paper introduces a risk-sensitive federated learning approach for power allocation in industrial IoT, optimizing energy use while maintaining timely information delivery under stochastic constraints.

Contribution

It proposes a novel distributed power allocation method combining Lyapunov optimization, federated learning, and extreme value theory for industrial IoT environments.

Findings

Achieves 28.50% energy savings compared to centralized solutions.

Performs on par with centralized baselines in real-time monitoring tasks.

Effectively manages extreme AoI staleness using extreme value theory.

Abstract

This work studies a real-time environment monitoring scenario in the industrial Internet of things, where wireless sensors proactively collect environmental data and transmit it to the controller. We adopt the notion of risk-sensitivity in financial mathematics as the objective to jointly minimize the mean, variance, and other higher-order statistics of the network energy consumption subject to the constraints on the age of information (AoI) threshold violation probability and the AoI exceedances over a pre-defined threshold. We characterize the extreme AoI staleness using results in extreme value theory and propose a distributed power allocation approach by weaving in together principles of Lyapunov optimization and federated learning (FL). Simulation results demonstrate that the proposed FL-based distributed solution is on par with the centralized baseline while consuming 28.50% less system energy and outperforms the other baselines.