Edge and Cloud-Based AI Inference for Big Data Processing

This chapter explores a unified framework that leverages both edge computing and cloud computing for AI inference in big data environments. Edge computing enables near-source, low-latency processing and decision-making, reducing dependency on centralized infrastructure, while cloud platforms offer powerful capabilities for large-scale model training, data aggregation, and long-term storage. By combining these paradigms, a hybrid ecosystem emerges that balances efficiency, scalability, and responsiveness. The chapter discusses architectural models, deployment strategies, and real-world applications across domains such as healthcare monitoring, intelligent transportation, industrial automation, and smart cities. It also highlights key challenges including resource heterogeneity, interoperability, security, and model optimization. Ultimately, the abstraction emphasizes how edge-cloud synergy forms a foundational approach for next-generation AI-driven big data systems.