Online-Learning-Based Fast-Convergent and Energy-Efficient Device Selection in Federated Edge Learning
Online-Learning-Based Fast-Convergent and Energy-Efficient Device Selection in Federated Edge Learning
复制标题
DOI：
10.1109/jiot.2022.3222234
复制
发表时间：
2023-03-15
影响因子：
10.6
通讯作者：
Xiong, Zehui
中科院分区：
文献类型：
--
作者：
Peng, Cheng;Hu, Qin;Xiong, Zehui
随着边缘计算面临越来越严峻的边缘设备数据安全和隐私问题，最近提出了一种称为联邦边缘学习（FEL）的框架，以在边缘实现机器学习（ML）模型训练，确保边缘设备的通信效率和数据隐私保护。在这种模式中，训练效率长期以来受到通信条件、计算能力和设备上可用数据集的异质性的挑战。目前，研究人员专注于从优化能耗或收敛速度的角度通过设备选择来解决这一挑战。然而，考虑其中任何一个都不足以保证长期的系统效率和稳定性。为了填补这一差距，本文提出了一个优化问题，在训练数据量和时间消耗的约束下，同时最小化所选器件的总能耗和最大化FEL器件选择全局模型的收敛速度。为了准确计算能耗，我们采用在线学习的方法来估计每个设备的CPU周期频率可用性，并提出了一种高效的算法，称为快速收敛的节能设备选择（FCEDS）-D-2），以较低的时间复杂度来解决优化问题。通过一系列的对比实验，我们评估了所提出的（FCEDS）-D-2方案的性能，验证了其较高的训练精度和能量效率。
As edge computing faces increasingly severe data security and privacy issues of edge devices, a framework called federated edge learning (FEL) has recently been proposed to enable machine learning (ML) model training at the edge, ensuring communication efficiency and data privacy protection for edge devices. In this paradigm, the training efficiency has long been challenged by the heterogeneity of communication conditions, computing capabilities, and available data sets at devices. Currently, researchers focus on solving this challenge via device selection from the perspective of optimizing energy consumption or convergence speed. However, the consideration of any one of them is insufficient to guarantee the long-term system efficiency and stability. To fill the gap, we propose an optimization problem to simultaneously minimize the total energy consumption of selected devices and maximize the convergence speed of the global model for device selection in FEL, under the constraints of training data amount and time consumption. For the accurate calculation of energy consumption, we deploy online bandit learning to estimate the CPU-cycle frequency availability of each device, based on an efficient algorithm, named fast-convergent energy-efficient device selection ((FCEDS)-D-2), is proposed to solve the optimization problem with a low level of time complexity. Through a series of comparative experiments, we evaluate the performance of the proposed (FCEDS)-D-2 scheme, verifying its high training accuracy and energy efficiency.