Fine-Grained Data Selection for Improved Energy Efficiency of Federated Edge Learning

• Published in: IEEE transactions on network science and engineering Vol. 9; no. 5; pp. 3258 - 3271
• Main Authors: Albaseer, Abdullatif, Abdallah, Mohamed, Al-Fuqaha, Ala, Erbad, Aiman
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Beamforming; Computational modeling; Constraints; Convergence rate; Data models; Data selection; Datasets; Edge computing; Edge Intelligence; Energy consumption; Energy efficiency; Federated Edge Learning (FEEL); Iterative algorithms; Iterative methods; Learning Algorithm; Machine learning; Performance evaluation; Resource allocation; Resource management; Servers; Training
• ISSN: 2327-4697; 2334-329X
• DOI: 10.1109/TNSE.2021.3100805

In Federated edge learning (FEEL), energy-constrained devices at the network edge consume significant energy when training and uploading their local machine learning models, leading to a decrease in their lifetime. This work proposes novel solutions for energy-efficient FEEL by jointly considering local training data, available computation, and communications resources, and deadline constraints of FEEL rounds to reduce energy consumption. This paper considers a system model where the edge server is equipped with multiple antennas employing beamforming techniques to communicate with the local users through orthogonal channels. Specifically, we consider a problem that aims to find the optimal user's resources, including the fine-grained selection of relevant training samples, bandwidth, transmission power, beamforming weights, and processing speed with the goal of minimizing the total energy consumption given a deadline constraint on the communication rounds of FEEL. Then, we devise tractable solutions by first proposing a novel fine-grained training algorithm that excludes less relevant training samples and effectively chooses only the samples that improve the model's performance. After that, we derive closed-form solutions, followed by a Golden-Section-based iterative algorithm to find the optimal computation and communication resources that minimize energy consumption. Experiments using MNIST and CIFAR-10 datasets demonstrate that our proposed algorithms considerably outperform the state-of-the-art solutions as energy consumption decreases by 79% for MNIST and 73% for CIFAR-10 datasets.