Handover Analysis for Vehicular Communication with Explainability on the Fly

2026-08-14

AI Summary

This study addresses the lack of interpretability and real-time responsiveness in machine learning models for handover detection in vehicular networks by proposing an fANOVA-based instant interpretability framework. Leveraging intrinsic interpretability mechanisms, the method enables real-time decision parsing with zero additional computational overhead, thereby overcoming the latency bottlenecks inherent in traditional post-hoc explanation approaches. Experimental results demonstrate that the proposed model maintains detection accuracy comparable to LSTM baselines while significantly reducing explanation latency. Furthermore, the revealed feature correlations align with established physical mechanisms. By simultaneously achieving high accuracy, low latency, and transparency, this work provides an efficient and trustworthy solution for next-generation vehicular network systems.

Abstract

Handover (HO) management in vehicular networks requires fast and reliable decision-making under highly dynamic conditions. While machine learning (ML) approaches can improve HO detection by capturing complex relationships among various key performance indicators (KPIs), their black-box nature limits interpretability and operator trust. To address this, this paper investigates HO detection from an explainability-on-the-fly perspective using inherently interpretable models based on the functional analysis of variance (fANOVA) framework. The proposed models are evaluated using two real-world operator datasets and compared against a Long Short-Term Memory baseline augmented with post-hoc SHAP explanations. Unlike post-hoc approaches, the proposed framework enables immediate interpretation of model decisions without incurring additional computational overhead. This capability is particularly critical for latency-sensitive vehicular networks. The results show that fANOVA-based models achieve competitive detection performance while providing significantly reduced explanation latency compared to conventional post-hoc methods. Furthermore, feature ranking and visualization analyses reveal physically meaningful relationships between KPIs and HO occurrences that align with standardized HO mechanisms. These results demonstrate that inherently interpretable models provide an efficient and transparent solution for HO detection in next-generation vehicular networks.

Problem

• Vehicular Handover
• Explainability-on-the-fly
• Intrinsic Interpretability
• Low Latency
• Black-box ML

Innovation

• Explainability on the Fly
• fANOVA
• Inherently Interpretable Models
• Vehicular Handover Detection
• Low-latency Explanation