Exploring Deep Reinforcement Learning-Assisted Federated Learning for Online Resource Allocation in Privacy-Preserving EdgeIoT

Authors

Jingjing Zheng, Real-Time and Embedded Computing Systems Research Centre (CISTER), 4249-015 Porto, Portugal
Kai Li, Real-Time and Embedded Computing Systems Research Centre (CISTER), 4249-015 Porto, Portugal
Naram Mhaisen, College of Electrical Engineering, Mathematics, and Computer Science (EEMCS), TU Delft, Netherlands
Wei Ni, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Sydney 2122, Australia
Eduardo Tovar, Real-Time and Embedded Computing Systems Research Centre (CISTER), 4249-015 Porto, Portugal
Mohsen Guizani, Mohamed Bin Zayed University of Artificial IntelligenceFollow

Document Type

Article

Publication Title

IEEE Internet of Things Journal

Abstract

Federated learning (FL) has been increasingly considered to preserve data training privacy from eavesdropping attacks in mobile edge computing-based Internet of Thing (EdgeIoT). On the one hand, the learning accuracy of FL can be improved by selecting the IoT devices with large datasets for training, which gives rise to a higher energy consumption. On the other hand, the energy consumption can be reduced by selecting the IoT devices with small datasets for FL, resulting in a falling learning accuracy. In this paper, we formulate a new resource allocation problem for privacypreserving EdgeIoT to balance the learning accuracy of FL and the energy consumption of the IoT device. We propose a new federated learning-enabled twin-delayed deep deterministic policy gradient (FL-DLT3) framework to achieve the optimal accuracy and energy balance in a continuous domain. Furthermore, long short term memory (LSTM) is leveraged in FL-DLT3 to predict the time-varying network state while FL-DLT3 is trained to select the IoT devices and allocate the transmit power. Numerical results demonstrate that the proposed FL-DLT3 achieves fast convergence (less than 100 iterations) while the FL accuracy-to-energy consumption ratio is improved by 51.8% compared to existing state-of-the-art benchmark. IEEE

First Page

1

Last Page

1

DOI

10.1109/JIOT.2022.3176739

Publication Date

5-20-2022

Keywords

E-learning, Entropy, Green computing, Information management, Internet of things, Long short-term memory, Mobile edge computing, Privacy-preserving techniques, Reinforcement learning, Resource allocation, Computational modelling, Energy-consumption, Federated learning, Internet of thing., Learning accuracy, Online resource allocation, Online resources, Privacy preserving, Resource management, Resources allocation, Energy utilization

Comments

IR Deposit conditions:

OA version (pathway a) Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged

Recommended Citation

J. Zheng, K. Li, N. Mhaisen, W. Ni, E. Tovar and M. Guizani, "Exploring Deep Reinforcement Learning-Assisted Federated Learning for Online Resource Allocation in Privacy-Preserving EdgeIoT," in IEEE Internet of Things Journal, May 2022, doi: 10.1109/JIOT.2022.3176739.