Aug 2026· International Journal of Electronics and Communication Engineering· 0 citations· 35 references
TL;DR
This work introduces a federated learning framework on campus that provides a resource-conscious multi-layer federating strategy that controls the number of devices taking part in the process as well as the frequency at which aggregation is done based on each device’s capability.
Abstract
The rise in the use of the Internet of Things is resulting in extensive and varied data being generated on university campuses, especially in the domain of energy consumption and management in buildings. Conventional learning algorithms will fail in this scenario because they are restricted by privacy boundaries and communication cost considerations on edge devices. Against this background, we introduce a federated learning framework on campus. In which learning will occur at the edge nodes collaboratively. This scheme provides a resource-conscious multi-layer federating strategy that controls the number of devices taking part in the process as well as the frequency at which aggregation is done based on each device’s capability. Contrary to existing federating designs that assume each edge node is similar in ability, this design considers the differences in each campus environment. The experiments conducted using the realistic smart campus test bed reveal that our approach ensures stronger convergence, reduced communication overhead, as well as more accurate predictions of energy consumption, when compared to traditional Federated Averaging as well as the fixed aggregation strategy. Moreover, the approach allows for simplicity in the preservation of privacy, without losing scalability, especially for the smart campus setting that has been projected to be rather large.
The intersection of sixth-generation (6G) communication networks, edge computing, and federated learning offers a novel occasion regarding empowering trustful and scalable collaboration throughout distributed Internet of Things (IoT) ecosystems. Conventional centralized machine learning technology is plagued by severe constraints in IoT scenes, such as privacy issues, network congestion, and network bottlenecks. The paper has presented a new 6G-integrated federated learning system which builds on the native intelligence of 6G networks to support secure, efficient, and scalable cooperative learning among heterogeneous edge-IoT devices. The suggested architecture combines terahertz frequencies to synchronize model communication in real-time at ultra-low latency, reconfigurable intelligent surfaces to improve the quality of communication, and network slicing to provide differentiated quality-of-service assurances. Another new hierarchical federated learning system integrates intra-edge aggregation and inter-edge cooperation that can reduce communication overhead by 85-percent and achieve the same accuracy in models. This framework integrates blockchain-based trust management involving zero-knowledge proofs of verifiable model update, to provide integrity and accountability without impacting on privacy. Experimental analysis of massive scale edge-IoT applications has revealed that the suggested scheme attains 97.2% model precision and lowers communication expenses by 87 percent and convergence rate by 3.4 times that of traditional federated learning techniques. The framework has high-uniform performance in adversarial environments where 99.6 percent of malicious model updates are identified with a small false positive. The results define the 6G-integrated federated learning as a framework of reliable and scalable edge-IoT cooperation.
T.Muthumanickam, D. Jayalakshmi, Sathiyamoorthy M et al.· 2026 6th International Confe...· 0 citations
The experimental results demonstrate that the proposed Trust-FedAvg framework substantially improves robustness over conventional FedAvg and remains competitive with established robust aggregation strategies, particularly under directional model-manipulation attacks and intermittent-connectivity conditions.
M. Reis, Carlos Serôdio, Frederico Branco· Applied Sciences· 0 citations
INTRODUCTION: Heterogeneous edge computing creates data islands due to privacy and environmental heterogeneity. Current solutions lack an overall approach. OBJECTIVES: This study constructs a federated learning framework for secure data element circulation, mitigating low-power node tailing, balancing communication with accuracy, and adapting to non-IID data, advancing intelligent systems and cybersecurity. METHODS: The framework fuses Dynamic Clustering, Adaptive Gradient Transmission, and Data Distribution Alignment. Validation uses simulations against existing technologies. RESULTS: The proposed method achieves 0.892±0.021 comprehensive performance, 11.1%–13.6% higher than existing technologies. Under 20% network interruption, attenuation is 3.3% vs. 8.6%–12.5%. Data flow reaches 18.6±0.7 MB/s; privacy leakage is 0.8±0.2 bit. CONCLUSION: This study provides reliable support for safe, efficient data element circulation, advancing intelligent systems and cybersecurity.
Geng Cheng, Jianbo Liu· ICST Transactions on Scalabl...· 0 citations
A lightweight edge AI framework that employs federated learning, enabling model training across distributed Internet of People and Things (IoP) devices without transferring raw data to centralised servers is proposed, enabling responsive, privacy-preserving, and resilient edge AI operations in distributed environments.
F. Philip-Kpae, A. Imoize, Lloyd Endurance Ogbondamati et al.· E3S Web of Conferences· 0 citations
An increasing number of special Internet of Things (IoT) applications are being deployed within federated and zero-trust (ZT) environments. These ad-hoc networks consist of heterogeneous, resource-constrained devices from various administrative domains, all of which are susceptible to compromise. The dynamic nature of these environments necessitates near-real-time Situational Awareness (SA), where processed data varies with its sensitivity and reliability, without dependence on a central authority. Examples include NATO and non-NATO coalitions engaged in hybrid military operations or humanitarian aid scenarios. To address the challenges of security, reliability, and context-aware data dissemination, we propose FedM, a multi-level formal model designed for context-aware and policy-driven data dissemination in federated IoT environments. This model is built upon various access control models and Denning’s research on information flow control (IFC), prioritizing the protection and reliability of data flows. A crucial element of this model is the distributed ledger, which facilitates the dynamic modification of label expressiveness, enhances resilience against disruption attacks, and separates policy logic from application functionality to mitigate risks associated with the benevolent developer. Additionally, we delineate a deterministic and history- and precedence-aware policy enforcement procedure to resolve conflicting actions and introduce processing primitives for the ongoing Data Quality Assessment (DQA) process. Our model also aligns with the concepts of Ubiquitous and Continuum Computing. Furthermore, in our paper we illustrate a policy-based dissemination pipeline, incorporating a bounded trustworthiness dimension. Additionally, we present a refined multi-layered framework that proposes the deployment of Information Flow Control (IFC) components, such as the Open Policy Agent decision engine, to facilitate policy-driven contextual data dissemination. We provide preliminary benchmarks for resource-constrained platforms, along with a formal threat model that addresses implicit flows, the benevolent developer problem, and the behavior of a distributed ledger under degraded network conditions. Finally, we conduct a formal verification of our model using the P framework.
Jakub Sychowiec, Zbigniew Zieliński· Electronics· 0 citations
This study demonstrates the efficacy of the synergy between federated learning and edge computing in IoT security contexts, providing a scalable and privacy-centric solution for anomaly detection across large-scale distributed devices.
Quan Liu, Yuanyuan Feng· Discover Artificial Intellig...· 0 citations