A Survey on Federated Learning and Edge Computing: Applications, Advantages, and Challenges
Open Access
- 20 July 2026
- conference paper
- Published by MDPI AG in Engineering Proceedings
- Vol. 143 (1) , 39
Abstract
Federated learning (FL) and edge computing are transformative technologies that enhance privacy, efficiency, and real-time intelligence for distributed machine learning across diverse edge device networks. FL enables devices to collaboratively train models locally, so sensitive data remains on each device, ensuring privacy and regulatory compliance (like GDPR and HIPAA). Edge computing complements FL by bringing data processing closer to sources such as IoT sensors and smartphones, which reduces latency, bandwidth use, and dependence on cloud servers. This architecture is vital for smart cities, healthcare, industry, and autonomous systems, supporting real-time decision-making. The review details challenges such as resource heterogeneity, communication constraints, security risks, and management complexity, while highlighting opportunities for scalable orchestration, decentralized architectures, and blockchain integration. Together, FL and edge computing create a robust paradigm for scalable, privacy-aware distributed intelligence across multiple domains.Keywords
This publication has 40 references indexed in Scilit:
- Dynamic analysis of a generalized attention deficit disorder model with Soboleva activation functionsChaos: An Interdisciplinary Journal of Nonlinear Science, 2025
- Adaptive federated learning for resource-constrained IoT devices through edge intelligence and multi-edge clusteringScientific Reports, 2024
- From distributed machine learning to federated learning: a surveyKnowledge and Information Systems, 2022
- Towards edge computing in intelligent manufacturing: Past, present and futureJournal of Manufacturing Systems, 2022
- Challenges and future directions of secure federated learning: a surveyFrontiers of Computer Science, 2021
- A survey on federated learning in data miningWIREs Data Mining and Knowledge Discovery, 2021
- A survey on federated learningKnowledge-Based Systems, 2021
- A review of applications in federated learningComputers & Industrial Engineering, 2020
- An Overview on Edge Computing ResearchIEEE Access, 2020
- A Survey on the Edge Computing for the Internet of ThingsIEEE Access, 2017