Excellence in Research: AI Powered Multi-Agent System (MAS) for Real-Time QoS Anomaly Detection and Adaptive Network Optimization in 6G-Enabled Industrial IoT Environments

Sixth generation (6G) wireless networks will support emerging applications such as smart manufacturing, autonomous robotics, intelligent transportation, advanced healthcare, and critical infrastructure. These applications depend on communication networks that can quickly detect disruptions, adapt to changing conditions, and maintain reliable operation with little or no human intervention. This project develops an artificial intelligence-powered system that continuously monitors network conditions, detects anomalies in real time, and intelligently adapts network resources to sustain dependable communications. The research also explores the use of blockchain technologies and intelligent spectrum management to strengthen the security and resilience of future wireless networks. Together, these advances will enable more reliable, secure, and efficient communications for mission-critical applications while preparing a future skilled workforce through undergraduate and graduate research experiences, curriculum enhancements, open educational modules, and annual workshops in AI, cybersecurity, blockchain, and next-generation wireless communications. The project develops a decentralized Multi-Agent System for real-time Quality-of-Service (QoS) anomaly detection and adaptive network optimization in 6G-enabled Industrial Internet of Things environments. Intelligent monitoring agents collaborate with machine learning-based anomaly detection and reinforcement learning to identify network degradations and dynamically optimize resource allocation. Blockchain-based authentication, smart contract policy management, and Spectrum Access System integration enable secure coordination of network decisions and support efficient spectrum sharing. The framework will be evaluated using a programmable Firecell 5G/6G testbed under realistic industrial workloads to quantify improvements in latency, throughput, packet loss, QoS, and network resilience. The expected outcome is an AI-native framework for secure, autonomous management of next-generation wireless networks that delivers more reliable communications for mission-critical industrial systems. This project is funded by the U.S. National Science Foundation (NSF) Historically Black Colleges and Universities-Excellence in Research (HBCU-EIR) Program. HBCU-EIR supports research at public and private HBCUs to strengthen their research capacity and promote engagement with NSF. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.