Explainable AI for UAV Mobility Management: A Deep Q-Network Approach for Handover Minimization

2025-04-25

AI Summary

In cellular networks, UAV mobility management faces challenges due to probabilistic line-of-sight links causing frequent handovers, compounded by the poor interpretability of existing deep Q-network (DQN)-based approaches. Method: This paper proposes the first SHAP-enhanced DQN framework for UAV handover decision-making, integrating the SHAP (Shapley Additive Explanations) interpretability framework into a deep reinforcement learning architecture. Leveraging real-world flight test and signaling data—including RSRP, RSRQ, buffer status, and positional information—the method quantifies the marginal contribution of each feature to handover actions, thereby rendering the black-box policy transparent. Contribution/Results: Experimental results demonstrate that the proposed method significantly improves policy interpretability and human-AI collaboration trustworthiness while reducing handover frequency and maintaining decision robustness. It establishes a novel paradigm for trustworthy air-ground integrated network mobility management.

Technology Category

Humans and AI: Planning and Decision Support for Human-Machine TeamsMachine Learning: Calibration & Uncertainty QuantificationReasoning under Uncertainty: Sequential Decision Making

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomyUser Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalizationSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The integration of unmanned aerial vehicles (UAVs) into cellular networks presents significant mobility management challenges, primarily due to frequent handovers caused by probabilistic line-of-sight conditions with multiple ground base stations (BSs). To tackle these challenges, reinforcement learning (RL)-based methods, particularly deep Q-networks (DQN), have been employed to optimize handover decisions dynamically. However, a major drawback of these learning-based approaches is their black-box nature, which limits interpretability in the decision-making process. This paper introduces an explainable AI (XAI) framework that incorporates Shapley Additive Explanations (SHAP) to provide deeper insights into how various state parameters influence handover decisions in a DQN-based mobility management system. By quantifying the impact of key features such as reference signal received power (RSRP), reference signal received quality (RSRQ), buffer status, and UAV position, our approach enhances the interpretability and reliability of RL-based handover solutions. To validate and compare our framework, we utilize real-world network performance data collected from UAV flight trials. Simulation results show that our method provides intuitive explanations for policy decisions, effectively bridging the gap between AI-driven models and human decision-makers.

Problem

• Minimize frequent UAV handovers in cellular networks
• Enhance interpretability of DQN-based mobility management
• Quantify feature impacts on handover decisions using SHAP

Innovation

• Deep Q-Network optimizes UAV handover decisions dynamically
• Shapley Additive Explanations enhance decision interpretability
• Real-world UAV flight data validates framework performance