Hierarchical Edge-Cloud Framework for Real-Time Network Anomaly Detection and Security

The hundreds of proliferation in distributed digital infrastructures and certain latency-sensitive applications require serious real-time cybersecurity solutions for heterogeneous environments. Traditional centralized approach to monitoring systems have their own set of challenges including volume capability, high latency, and delayed response which is more significant for large-scale IoT and edge-enabled networks. This study proposes Hierarchical Edge-Cloud Framework for Real-Time Network Anomaly Detection and Security with multi-layered monitoring, collaborative intelligence and adaptive machine learning. Lightweight detection models that are deployed at edge nodes perform immediate traffic inspection while computationally intensive deep learning models in the cloud perform global pattern analysis and model optimization. A hierarchical coordination mechanism is used to achieve continuous knowledge sharing and adaptable updates at edge and cloud level. Experimental evaluation using large volume of network traffic data results show 98.6% accuracy in detection with 42% saving in response latency as compared to centralized systems and a 35% improvement in accuracy in classifying threats. Localized filtering reduces network bandwidth usage even further (28%). These results are useful in emphasizing the framework's capacity to provide scalable, resilient and efficient cybersecurity for next-generation distributed networks.