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

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

Zheng, Jingjing (Real-Time and Embedded Computing Systems Research Centre)
Li, Kai (Real-Time and Embedded Computing Systems Research Centre)
Mhaisen, N. (TU Delft Embedded Systems)
Ni, Wei (Commonwealth Scientific and Industrial Research Organisation)
Tovar, Eduardo (Real-Time and Embedded Computing Systems Research Centre)
Guizani, Mohsen (Mohamed Bin Zayed University of Artificial Intelligence)

2022

Federated learning (FL) has been increasingly considered to preserve data training privacy from eavesdropping attacks in mobile-edge computing-based Internet of Things (EdgeIoT). On the one hand, the learning accuracy of FL can be improved by selecting the IoT devices with large data sets 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 data sets for FL, resulting in a falling learning accuracy. In this article, we formulate a new resource allocation problem for privacy-preserving EdgeIoT to balance the learning accuracy of FL and the energy consumption of the IoT device. We propose a new FL-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 the existing state-of-the-art benchmark.

Federated learning
online resource allocation
deep reinforcement learning
mobile edge computing
Internet of Things

http://resolver.tudelft.nl/uuid:cebffd38-ce2f-4f5b-aabd-c9aa125cb99f

https://doi.org/10.1109/JIOT.2022.3176739

2023-07-01

2327-4662

IEEE Internet of Things Journal, 9 (21), 21099-21110

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2022 Jingjing Zheng, Kai Li, N. Mhaisen, Wei Ni, Eduardo Tovar, Mohsen Guizani