Analyzing Edge AI Deployment Challenges with in Hybrid IT Systems Utilizing Containerization and Blockchain-Based Data Provenance Solutions

Abstract

The integration of Edge AI within hybrid IT systems presents significant challenges, particularly in terms of scalability, security, and data integrity. This review explores the complexities of deploying Edge AI in hybrid environments, emphasizing the role of containerization and blockchain-based data provenance solutions in mitigating these challenges. Containerization enhances the portability and scalability of AI models across diverse edge devices and cloud infrastructures, while blockchain ensures secure and verifiable data lineage, addressing concerns related to data authenticity and regulatory compliance. The paper examines key deployment barriers, including resource constraints, interoperability issues, and latency considerations, alongside strategies for optimizing AI model efficiency in distributed computing environments. Additionally, it evaluates real world use cases, technological frameworks, and best practices for integrating containerized Edge AI solutions with blockchain-driven data provenance mechanisms. By bridging gaps in security, operational efficiency, and trust, this review highlights a pathway toward resilient and transparent Edge AI deployments within hybrid IT ecosystems.