AI-Driven Optimization in Mobile Industrial Wireless Networks: A Performance and Security Enhancement Framework

This study investigates integrating artificial intelligence (AI) techniques in mobile industrial wireless communication networks, focusing on enhancing network performance, reliability, and security in industrial environments. Through a comprehensive analysis of industrial testbed datasets (iV2V and iV2I+), we demonstrate the effectiveness of AI-driven approaches in optimizing network operations. We implemented multiple machine learning models, including Decision Trees, Random Forests, and LightGBM, to predict quality of service (QoS) and optimize link selection. The Decision Tree Regressor achieved excellent performance, demonstrating its effectiveness for industrial wireless applications. We introduce a DBSCAN clustering-based approach for identifying weak signal regions, enabling proactive network optimization and coverage enhancement. The study also evaluates location fingerprinting models, achieving high accuracy in source classification through feature importance analysis. Our results emphasize the practical benefits of AI integration in industrial wireless networks, particularly in predictive maintenance, real-time decision-making, and network security. The findings provide valuable information for implementing AI-driven solutions in Industry 4.0 applications. However, the study acknowledges current limitations and emphasizes the need for real-world validation in industrial operations.