RESOURCE-AWARE PERSONALIZED FEDERATED LEARNING FOR HETEROGENEOUS AND NON-IID EDGE
ENVIRONMENTS
Federated Learning Federated Systems Distributed Machine Learning Non-IID Data Simulation Privacy Preservation.
Federated systems, and Federated Learning (FL) systems, in particular, allow distributed clients to engage in machine learning, without necessarily sharing raw data. This paradigm deals with issues of privacy, data ownership and control as well as regulatory matters and promotes large scale intelligent applications. Federated environments have drawbacks, however, which include non-independent and identically distributed (non-IID) data, system heterogeneity, and overhead of communication. This paper gives a simulation analysis of the performance of federated learning with different populations of clients, diverse data distributions, and different participation rates. The convergence behavior, global model accuracy and communication efficiency are experimented using standard federated learning frameworks and benchmark datasets. Findings reveal that in the case of IID scenarios, federated learning approaches almost centralized performance, whereas non- IID data and the heterogeneity of clients largely influence the convergence rate and accuracy. The paper also brings out trade-offs between privacy preservation and system efficiency, which can be used in the design of practical federated systems.
Registration ID: IJVRA_701998 Published ID: IJVRA2603497
"RESOURCE-AWARE PERSONALIZED FEDERATED LEARNING FOR HETEROGENEOUS AND NON-IID EDGE
ENVIRONMENTS", IJVRA - International Journal of Versatile Research and Analysis (www.IJVRA.org), ISSN:2984-8903, Vol.4, Issue 3, page no.835-840, March-2026, Available :https://ijpub.org/ijvra/papers/IJVRA2603497.pdf
Paper Reg. ID: IJVRA_701998
Published Paper Id: IJVRA2603497
Research Area: Other area not in list
Country: Gwalior,MP, MADHYA PRADESH, India
ISSN: 2984-8903 | IMPACT FACTOR: 9.12 Calculated By Google Scholar | ESTD YEAR: 2023
An International UGC CARE JOURNAL PUBLICATION Low Cost (₹599), Scholarly Open Access, Peer-Reviewed, Refereed Journal Impact Factor 9.12 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage, Crossref DOI Member Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJVRA (IJ Publication) Janvi Wave
© 2026 - Authors hold the copyright of this article. This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition.
This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0). 🛡️ Disclaimer:
The content, data, and findings in this article are based on the authors’ research and have been peer-reviewed for academic purposes only. Readers are advised to verify all information before practical or commercial use. The journal and its editorial board are not liable for any errors, losses, or consequences arising from its use.
: Click Here to Get
About Hard Copy and Transparent Peer Review Report
