AI-POWERED DECENTRALIZED EPIDEMIOLOGICAL SURVEILLANCE: CONTAINERIZED EDGE INTELLIGENCE WITH DOCKER AND KUBERNETES ORCHESTRATION

Abstract

In the world today, effective epidemiological monitoring requires both sophisticated AI analytics and solid, scalable deployment platforms. This article introduces a new decentralized epidemiological AI system that relies on edge-based swarm intelligence as well as state-of-the-art geospatial anonymization methods, augmented with containerization using Docker and orchestration using Kubernetes (K8s). With the deployment of containerized AI models on hybrid infrastructures, edge devices, and cloud servers, our framework enables a portable, efficient, and scalable method of real-time disease surveillance and rapid outbreak response in distributed health networks. Docker enables consistent application packaging and seamless portability, and Kubernetes dynamically provisions resource and provides fault tolerance, optimizing performance on heterogeneous computing systems. Real-time simulations and preliminary field tests verify that this integrated framework significantly reduces data latency, increases predictive accuracy, and preserves strict privacy protection, a breakthrough in modern public health surveillance.