TRUST-AWARE FEDERATED INTELLIGENCE ORCHESTRATION IN EDGE-CLOUD CONTINUUM FOR AUTONOMOUS DECISION-MAKING AT THE NETWORK EDGE: A LIGHTWEIGHT BLOCKCHAIN-ENABLED FRAMEWORK FOR PRIVACY-PRESERVING, LOW-LATENCY, AND SCALABLE AI MODEL DEPLOYMENT ACROSS HETER

This paper presents a novel lightweight framework for federated learning and decision-making in an edge-cloud continuum, emphasizing trust-aware orchestration for autonomous decision-making at the network edge. The proposed system leverages blockchain technology to ensure privacy-preserving mechanisms, low-latency operations, and scalable AI model deployment across heterogeneous devices. The framework aims to address the challenges of data privacy, model accuracy, and latency in real-time edge AI applications, such as autonomous vehicles and industrial IoT. By integrating federated learning with blockchain, the system offers secure, decentralized model training and inference, which is critical for ensuring privacy in sensitive applications.