Hybrid AI Models for Real-Time lot Data Analytics on Edge-Cloud Platforms

Authors

  • Dr. S. B. Sawant Director, Department of MBA, Abhijit Kadam Institute of Management and Social Sciences, Bharati Vidyapeeth Deemed to be University, Solapur, Maharashtra Author
  • Koppula Sridhar Assistant Professor, Department Computer Science And Engineering, CMR Engineering College. Kondlakoya, Medchal Author

Keywords:

hybrid AI, edge computing, cloud computing, IoT, realtime analytics, federated learning

Abstract

The rapid growth of the Internet of Things (IoT) has led to massive volumes of distributed, high-velocity data that require low-latency, privacy-preserving, and scalable analytics. Pure cloud-based processing often fails to meet real-time constraints, while pure edge analytics struggle with limited computation and storage resources. Hybrid AI, which combines edge and cloud intelligence, has emerged as a promising paradigm for real-time IoT data analytics. This paper proposes a conceptual framework for hybrid AI models on edge–cloud platforms, where latency-sensitive inference is executed at the edge while model training, global optimization, and crossdomain analytics are offloaded to the cloud. We review recent advances in edge and hybrid architectures, discuss AI deployment patterns, and present a reference architecture with a layered data flow. A comparative table highlights key trade-offs between cloud-only, edge-only, and hybrid AI strategies. The paper concludes with open challenges in orchestration, resource management, security, and standardization.

Downloads

Published

2026-02-17

How to Cite

Dr. S. B. Sawant, & Koppula Sridhar. (2026). Hybrid AI Models for Real-Time lot Data Analytics on Edge-Cloud Platforms. Journal of Emerging Technologies and Innovative Research Development (JETIRD), 1(1), 49-54. https://jetird.com/index.php/files/article/view/8