Federated Learning-Based Computation Offloading Optimization in Edge Computing-Supported Internet of Things

By Jianji Ren, Haichao Wang, Tingting Hou, Shuai Zheng, Chaosheng Tang. 2019

195 citations recorded by the source corpus.

Recently, smart cities, smart homes, and smart medical systems have challenged the functionality and connectivity of the large-scale Internet of Things (IoT) devices. Thus, with the idea of offloading intensive computing tasks from them to edge nodes (ENs), edge computing emerged to supplement these limited devices. Benefit from this advantage, IoT devices can save more energy and still maintain the quality of the services they should provide. However, computational offload decisions involve federation and complex resource management and should be determined in the real-time face to dynamic workloads and radio environments. Therefore, in this work, we use multiple deep reinforcement learning (DRL) agents deployed on multiple edge nodes to indicate the decisions of the IoT devices. On the other hand, with the aim of making DRL-based decisions feasible and further reducing the transmission costs between the IoT devices and edge nodes, federated learning (FL) is used to train DRL agents in a distributed fashion. The experimental results demonstrate the effectiveness of the decision scheme and federated learning in the dynamic IoT system.

Subfields: Artificial Intelligence, Computer Networks and Communications, Computer Science Applications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Computer Science Applications

Citations in the corpus

Robust Aggregation for Federated Learning (2019, background): “Recent work has looked beyond supervised learning to domains such as data analytics but also semi-, self- and un-supervised learning, transfer learning, meta learning, and reinforcement learning [46, 58, 76, 91].”
Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues (2020, background): “[38] propose a FL-based framework for largescale IoT environments with edge computing.”
Federated Learning for Internet of Things: A Comprehensive Survey (2021, methodology): “Caching: Due to the high data distribution of large-scale IoT networks, FL can provide distributed AI solutions to support intelligent data offloading and caching at the network edge [59].”
Edge Computing with Artificial Intelligence: A Machine Learning Perspective (2022, background): “propose a distributed computing offloading strategy combining federated learning and multiple DRLs [96].”
Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, background): “The authors of [42] employ federated learning to improve the offloading decision-making in Internet of Things (IoT) environments.”
Federated Learning in Edge Computing: A Systematic Survey (2022, unknown): “Ren et al. [139] demonstrated FL-enabled computation ofﬂoading by deploying multiple DRL agents in distributed IoT devices to indicate their decisions.”
FLAME: Taming Backdoors in Federated Learning (2022, methodology): “Although we evaluate FLAME’s effectiveness on several aggregation mechanisms in §7.1, we generally focus on FedAvg in this work as it is commonly applied in FL [21, 28, 39, 44, 47, 50, 54] and related work on back-door attacks [7,22,51,57,59].”
Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “…as compared to the centralized ESN algorithm proposed in [195], since a centralized approach only makes partial prediction with the incomplete data from sole base stations, whereas the federated ESN approach can make predictions based on a model learned collaboratively from more complete data.”
A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond (2021, background): “Ren et al. [9] take into account that proxy data on the edge level is less relevant to the data stored on IoT devices.”