Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks

2025-01-24

AI Summary

To jointly optimize information freshness (Age of Information, AoI) and energy consumption in low-power UAV-enabled IoT networks, this paper co-designs UAV trajectory planning and communication scheduling to minimize a time-varying weighted sum of AoI and transmission power. We propose a novel meta-deep reinforcement learning framework that integrates model-agnostic meta-learning (MAML) with deep Q-networks (DQN), enabling rapid adaptation to dynamic AoI–power trade-off objectives. Compared to conventional deep RL approaches, the proposed method achieves a 40% faster convergence rate and reduces adaptation time to new objectives by 60%, while attaining optimal joint AoI–power performance. This significantly enhances generalization capability and real-time responsiveness in time-sensitive UAV-IoT applications.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Life-Long and Continual Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Age-of-information (AoI) and transmission power are crucial performance metrics in low energy wireless networks, where information freshness is of paramount importance. This study examines a power-limited internet of things (IoT) network supported by a flying unmanned aerial vehicle(UAV) that collects data. Our aim is to optimize the UAV flight trajectory and scheduling policy to minimize a varying AoI and transmission power combination. To tackle this variation, this paper proposes a meta-deep reinforcement learning (RL) approach that integrates deep Q-networks (DQNs) with model-agnostic meta-learning (MAML). DQNs determine optimal UAV decisions, while MAML enables scalability across varying objective functions. Numerical results indicate that the proposed algorithm converges faster and adapts to new objectives more effectively than traditional deep RL methods, achieving minimal AoI and transmission power overall.

Problem

• Energy Efficiency
• Information Freshness
• Drone Networks

Innovation

• Deep Learning
• Adaptive Learning Algorithm
• Reinforcement Learning for UAV Networks