Optimizing Energy and Data Collection in UAV-aided IoT Networks using Attention-based Multi-Objective Reinforcement Learning

TL;DR

This paper introduces an attention-based multi-objective reinforcement learning approach to optimize UAV path planning for energy-efficient data collection in IoT networks, effectively balancing multiple objectives in dynamic urban environments.

Contribution

It presents a novel MORL architecture that adapts to varying trade-offs and scenarios without retraining, improving performance and generalization in UAV-based data harvesting tasks.

Findings

Significant performance improvements over existing RL methods.

Enhanced model compactness and sample efficiency.

Strong generalization to unseen scenarios.

Abstract

Due to their adaptability and mobility, Unmanned Aerial Vehicles (UAVs) are becoming increasingly essential for wireless network services, particularly for data harvesting tasks. In this context, Artificial Intelligence (AI)-based approaches have gained significant attention for addressing UAV path planning tasks in large and complex environments, bridging the gap with real-world deployments. However, many existing algorithms suffer from limited training data, which hampers their performance in highly dynamic environments. Moreover, they often overlook the inherently multi-objective nature of the task, treating it in an overly simplistic manner. To address these limitations, we propose an attention-based Multi-Objective Reinforcement Learning (MORL) architecture that explicitly handles the trade-off between data collection and energy consumption in urban environments, even without prior knowledge of wireless channel conditions. Our method develops a single model capable of adapting to varying trade-off preferences and dynamic scenario parameters without the need for fine-tuning or retraining. Extensive simulations show that our approach achieves substantial improvements in performance, model compactness, sample efficiency, and most importantly, generalization to previously unseen scenarios, outperforming existing RL solutions.