BQAREM: Blockchain-Secured Quantum Adaptive Resource Management for Edge Machine Learning

Abstract

The exponential growth of IoT devices in smart city infrastructures generates vast edge data, demanding secure, low latency, energy-efficient processing. Conventional cloud-centric models face bandwidth bottlenecks, latency overhead, and single-point vulnerabilities, necessitating decentralized management. This research introduces BQAREM: Blockchain-Secured Quantum Adaptive Resource Management for Edge Machine Learning, integrating blockchain security, quantum optimization, reinforcement learning. The framework employs timestamped identity verification, multi parameter trust assessment, and a weighted Proof-of-Stake consensus for secure coordination. Quantum adaptive scheduling and smart contracts ensure efficient, tamper-proof resource allocation, achieving superior latency, energy efficiency, SLA compliance. Comprehensive performance evaluation demonstrates that BQAREM significantly enhances reliability, scalability, intelligent resource orchestration across heterogeneous edge environments. Testing in various smart city scenarios including Smart Grid Control, Traffic Management, Healthcare Monitoring, Surveillance Systems, and Emergency Response demonstrates high accuracy (> 95%), reduced latency (< 50 ms), and efficiency improvements exceeding 80%, with balanced energy use. BQAREM uniquely unifies blockchain-backed trust like timestamped identity + weighted PoS, quantum-adaptive risk-sensitive RL, and multi-resource orchestration with a new Robust Performance Index (RPI) for secure, low-latency, energy-aware Edge-ML scheduling.