Hybrid Cloud–Edge Frameworks for Real-Time Data Analytics and Decision Intelligence

Abstract

The exponential growth of data in distributed environments has intensified the need for scalable and intelligent architectures that can deliver real-time analytics and decision-making. This paper proposes a Hybrid Cloud–Edge Framework for Real-Time Data Analytics and Decision Intelligence that integrates the computational efficiency of edge computing with the global scalability and cognitive power of cloud systems. The framework introduces a multi-layer architecture comprising device, edge, communication, cloud, and orchestration layers, coordinated by an AI-driven Decision Intelligence Layer employing reinforcement learning and knowledge graphs. Experimental implementation using Kubernetes-managed microservices on NVIDIA Jetson and Google Cloud environments demonstrated a 38% reduction in latency, 21% improvement in decision accuracy, and 25% reduction in energy consumption compared to traditional cloud-centric systems. The results validate that hybrid orchestration enables adaptive workload distribution, bi-directional learning, and self-optimization under dynamic conditions. This research contributes a foundational model for developing intelligent, scalable, and context-aware distributed systems, paving the way for next-generation real-time analytics in industrial, healthcare, and smart infrastructure domains.