Abstract :

The Rapid Deployment Of Multi-site Enterprise 5G Networks Has Increased The Demand For Intelligent Radio Access Network (RAN) Optimization While Ensuring User Privacy And Data Security. Conventional Centralized Machine Learning Approaches Require Transferring Sensitive Network Data To A Central Server, Creating Privacy Risks, Communication Overhead, And Scalability Challenges. This Paper Proposes A Federated Learning (FL)-based Privacy-preserving Framework For Optimizing RAN Performance Across Distributed Enterprise 5G Sites. Each Local Site Trains A Machine Learning Model Using Its Own Network Data, While Only Encrypted Model Parameters Are Shared With A Central Aggregator Through The Federated Averaging (FedAvg) Algorithm. The Proposed Framework Enhances Network Throughput, Minimizes Latency, Improves Resource Allocation, And Reduces Communication Costs Without Exposing Confidential Information. Experimental Analysis Demonstrates That The Proposed Approach Achieves Higher Optimization Accuracy, Faster Convergence, And Robust Privacy Preservation, Making It Suitable For Next-generation Intelligent Enterprise 5G Networks.

Published:

17-4-2023

Issue:

Vol. 23 No. 4 (2023)

Page Nos:

53-57

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite