The results show a 15% increase in clustering metrics compared to current algorithms, showcasing how the method improves device assignment and data redistribution in hierarchical semi-synchronous federated learning, addressing issues in model accuracy and resource optimization.
Abstract
This study focuses on the important task of optimizing device clustering and assigning them to edge servers, while also implementing data redistribution in hierarchical semi-synchronous federated learning within the realm of advancing edge computing. Our research goal is to increase the performance and scalability of federated learning systems by improving resource allocation and data processing efficiency, which will in turn enhance edge computing frameworks. The current literature does not have thorough methods that can effectively combine model accuracy with optimal device clustering algorithms in hierarchical semi-synchronous federated learning, leading to below-par performance and inefficient use of resources. This difference highlights the need for creative measures that enhance not only model training accuracy but also the grouping of devices as opposed to current methods. The study utilizes a Graph Neural Network (GNN) to group IoT devices according to their hardware features and local datasets, then applies the K-means algorithm to create efficient device clusters. After that, Hybrid Data Redistribution is used to equalize local datasets in each cluster, and Proximal Policy resource allocation optimization algorithm is implemented to allocate devices to edge servers according to bandwidth usage, and energy consumption based on real-time updates, ultimately enabling hierarchical semi-synchronous federated learning to improve model training. The results show a 15% increase in clustering metrics compared to current algorithms, showcasing how our method improves device assignment and data redistribution in hierarchical semi-synchronous federated learning, addressing issues in model accuracy and resource optimization.
This paper proposes a communication-efficient adaptive federated learning algorithm for heterogeneous defect classification tasks that achieves competitive classification accuracy while reducing single-round training time by up to 70%.
Shuo He, He-Yang Wei, Congxian Bi et al.· Electronics· 0 citations
Experiments under representative Non-IID settings on benchmark datasets show that PFLS-One achieves improved accuracy and faster convergence compared with representative baseline methods, and the convergence analysis under a non-convex objective provides theoretical support for the proposed method.
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
With the rapid development of the Internet of Things (IoT) and edge computing, Federated Learning (FL) has emerged as a promising distributed framework capable of effectively leveraging distributed devices for machine learning tasks while preserving data privacy. However, in practical scenarios characterized by significant device heterogeneity and communication delays, traditional synchronous FL often suffers from inefficiency due to the straggler effect. Although Asynchronous Federated Learning (AFL) has been proposed to mitigate this, it still faces challenges regarding model staleness and training bias, which hinder convergence performance. To address these issues, this paper presents an asynchronous framework named FedQS. First, FedQS employs a multi-dimensional staleness evaluation mechanism that dynamically assesses updates by combining the similarity between local and global models with client latency metrics. Second, to resolve the coupling between training bias and model staleness, we implement a decoupling solution via a queue scheduling algorithm. This algorithm reprocesses high-staleness model parameters on selected faster helper clients using only the helpers’ local private data while preserving the provenance of the original uploading clients, thereby aiming to reduce stale-update effects in aggregation. Finally, during the aggregation phase, the framework recalibrates aggregation weights based on client contributions to reduce training bias and improve global model accuracy. Comparative experiments on Fashion-MNIST and CIFAR-10 datasets demonstrate that FedQS outperforms four evaluated representative baselines—FedAsync, FedBuff, KAFL, and CAFL—achieving an average accuracy improvement of 8.62%.
Jia-Hui Zhou, Fang Li, Tian-Yu Shi et al.· Journal of Cloud Computing· 0 citations
The Federated Green Anaconda Optimizer (FedGAO), an innovative FL framework inspired by the behavioral patterns of the Green Anaconda Optimizer (GAO), is proposed, demonstrating superior performance in terms of accuracy, convergence speed, and resource efficiency.
Elahe Eslami, S. A. Shahzadeh Fazeli, J. Abouei et al.· Cluster Computing· 0 citations
In the recent years, the Internet of Things (IoT) has transformed many areas of society and improved
human life by changing the way data is conveyed. IoT technology is now part of everyday life, transforming the way
cities use resources, provide services, and allow individuals to interact with each other. The spread of IoT has
resulted in more efficient and responsive urban systems, tailor-made services, and new ways of social interaction.
Data from sensors and smart meters are utilized in intelligent cities to enhance public services, infrastructure, and
utilities. WSNs are essential for gathering data in IoT systems over the long term. Data are delivered to the sink
node through networks, and having strong connectivity between the sensor nodes is essential in IoT systems.
Clustering techniques are popular in IoT to save power at the node level and enhance battery life. Improving the
capacity and longevity of the clustered network depends on the careful selection of Cluster Heads (CHs). Over the
past decade, studies on optimal Cluster Head selection have decreased energy consumption by a considerable
amount. The wrong Cluster Head selection not only speeds up battery drain but also prolongs the network
convergence time. To address this challenge, this research article proposes the Sandpiper Optimization Algorithmbased Energy-Conscious Cluster Head (SOA-ECCH) algorithm. It utilizes both distance constraints and residual
energy levels to improve network performance and lifespan. The enhanced SOA-ECCH effectively minimizes
energy consumption among network nodes while boosting network lifetime and throughput.
S. Mageshwaran, P. Sundareswaran· International Journal of Dru...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
