AI-Enabled Distributed Cloud Frameworks for Big Data Analytics with Privacy Preservation

Abstract

The fast rise of the Big Data and the faster adoption of Artificial Intelligence (AI) have changed the modern computational ecosystems allowing to conduct real-time analytics and automation in some of the most vital areas: healthcare, finance, and industrial IoT. Nevertheless, there are notable problems with traditional centralized cloud designs such as poor scalability, high latency, network overload, and augmented privacy and security threats in distributing sensitive information that is sensitive. To fill these gaps, this paper suggests a new AI-enabled distributed cloud framework (AIDCF) that combines federated learning, differential privacy, and homomorphic encryption to facilitate secure, privacy-preserving and scalable analytics on the Big Data without centralized sharing of data. The mixed-method research design was chosen, which involved the development of theoretical frameworks, the modeling of algorithms, and simulation of experiment, based on synthetic multi-domain data (healthcare, finance, IoT) running on distributed cloud nodes (10-100). The outcomes indicate the novelty and high-performance AIDCF, which has a high accuracy (93.7%), low latency (139 ms), high throughput (1585 MB/s) and high computational performance (89.5 percent), as well as the significant reduction in privacy loss (ε = 1.3) compared to other models such as DP-FedAvg, SecureML, and Baseline Cloud Analytics (BCA). These results confirm that the presented framework provides a feasible trade-off between analytical and confidentiality protection, which makes it be deployed in privacy-sensitive, real-time, and large-scale distributed systems. Altogether, AIDCF offers a scalable, secure, and high-performance distributed AI system, which will push the state of the art of privacy-aware Big Data processing.