Dynamic Federated Data Integration and Iterative Pipelines for Scalable E Commerce Analytics Using Hybrid Cloud and Edge Computing

Abstract

Background information: IoT systems create a big stream of data with exponential growth. These 
make traditional centralized systems have difficulty processing their huge streams. Decentralized, 
fault tolerant, and scalable analytics in IoT could be supported using federated learning, resilient 
workflow orchestration, and hybrid task allocation. Interlacing them guarantees real time, secure 
computing, and makes optimum resource exploitation feasible across diverse IoT scenarios. 
Objectives: This paper assesses the feasibility of federated learning, resilient workflow 
orchestration, and hybrid task allocation for IoT analytics. The goals are to reduce latency, improve 
cost-effectiveness, enhance model accuracy, and optimize resource usage. The framework is 
designed to be scalable, reliable, and adaptable to various IoT applications. 
Methods: The methodology will integrate federated learning into privacy-preserving analytics, 
resilient workflows for fault-tolerant task execution, and hybrid task allocation to support 
optimized resource management. Performance metrics such as latency, cost efficiency, model 
accuracy, and resource utilization would then be assessed across individual and combined 
configurations to validate the effectiveness of the framework. 
Results: The results for the Full Model were outstanding at 18.4 ms latency, 92.5% cost efficiency, 
94.8% model accuracy, and 95.1% resource utilization. The individual methods performed 
moderately better, and blended setups exhibit considerable synergies, establishing the soundness 
and scalability of the framework in real-time IoT analytics. 
Conclusion: The proposed methodology outperforms the traditional approaches in guaranteed 
safety, scalability, and efficiency of IoT analytics. Following enhancements will be focused on 
adaptive federated learning, advanced fault recovery, and support for emerging applications such 
as Internet of Things-based autonomous vehicles. Such enhancements will further strengthen this 
framework's applicability and scalability in dynamic environments.