Lyapunov-guided Deep Reinforcement Learning for Semantic-aware AoI Minimization in UAV-assisted Wireless Networks

TL;DR

This paper proposes a Lyapunov-guided deep reinforcement learning approach to optimize semantic-aware age-of-information in UAV-assisted wireless networks, balancing information freshness and semantic importance for improved data transmission.

Contribution

It introduces a novel semantic-aware AoI metric and a hierarchical DRL framework to jointly optimize UAV association, semantic extraction, and trajectories.

Findings

Hierarchical DRL improves learning efficiency.

Proposed method reduces AoI while preserving data semantics.

Outperforms existing baseline methods in simulations.

Abstract

This paper investigates an unmanned aerial vehicle (UAV)-assisted semantic network where the ground users (GUs) periodically capture and upload the sensing information to a base station (BS) via UAVs' relaying. Both the GUs and the UAVs can extract semantic information from large-size raw data and transmit it to the BS for recovery. Smaller-size semantic information reduces latency and improves information freshness, while larger-size semantic information enables more accurate data reconstruction at the BS, preserving the value of original information. We introduce a novel semantic-aware age-of-information (SAoI) metric to capture both information freshness and semantic importance, and then formulate a time-averaged SAoI minimization problem by jointly optimizing the UAV-GU association, the semantic extraction, and the UAVs' trajectories. We decouple the original problem into a series of subproblems via the Lyapunov framework and then use hierarchical deep reinforcement learning (DRL) to solve each subproblem. Specifically, the UAV-GU association is determined by DRL, followed by the optimization module updating the semantic extraction strategy and UAVs' deployment. Simulation results show that the hierarchical structure improves learning efficiency. Moreover, it achieves low AoI through semantic extraction while ensuring minimal loss of original information, outperforming the existing baselines.