Relay-Assisted Federated Edge Learning: Performance Analysis and System Optimization

Chen, Lunyuan; Fan, Lisheng; Lei, Xianfu; Duong, Trung Q.; Nallanathan, Arumugam; Karagiannidis, George K.

doi:10.1109/tcomm.2023.3263566

Cited by 31 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al 20 introduced a Federated Edge Learning (FEEL) system supported by relays, considering constraints related to delay and bandwidth. The evaluation of system performance involved deriving analytical and asymptotic expressions for system outage probability and conducting convergence analysis.…”

Section: Related Workmentioning

confidence: 99%

Decision tree‐based task offloading in vehicle edge computing

Tay,

Şentürk

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThere are significant developments in the Internet of Vehicles (IoV) field, and the requirements needed in this area are increasing rapidly. When these needs are examined in the near future, it appears that the demand for connected, autonomous, shared, and electric vehicles will increase. Therefore, fundamental problems such as big data flow and storage will arise in the IoV field. Another problem is the delay sensitivity of IoVs and the need to minimize data loss. The use of edge computing (EC) tools can play an important role in obtaining effective solutions to overcome these problems. Delay, bandwidth, and energy consumption rate, which are important qualities in EC systems, emerge as a problem that needs to be improved for delay‐sensitive systems. These improvements belong to the category of nonlinear challenging problems. Effective optimization or machine learning methods can be used to improve these types of problems. In this study, a two‐stage machine learning method is proposed for a more efficient task completion rate and service time. According to the proposed method, in the first stage, the decision tree algorithm is used to select the computing tool to which the task will be sent, and the decision is made on which computing tool to send it to. In the second stage, a linear regression‐based classification method is used to select a delay‐sensitive computing tool. The performance analysis of the proposed method was made using the edgeCloudSim simulation tool, and according to the results obtained, the proposed method provides better results than other algorithms in the literature.

show abstract

Section: Related Workmentioning

confidence: 99%

Decision tree‐based task offloading in vehicle edge computing

Tay,

Şentürk

2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Similar to the scenario of multi-user grouping discussed in [15], we investigate an irregular RIS-assisted NOMA downlink wireless communication system, as depicted in Fig. 1.…”

Section: System Modelmentioning

confidence: 99%

Throughput maximization for irregular reconfigurable intelligent surface assisted NOMA systems

Zhang,

Wang,

Mao

et al. 2023

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Reconfigurable intelligent surface (RIS) is an emerging technology to improve the spectral efficiency of wireless communication systems. However, the high complexity of beam design and the non-negligible overhead associated with RIS limit the number of elements that can be deployed in practice. In this paper, we investigate the downlink communications of irregularly deployed intelligent reflecting surfaces that assist non-orthogonal multiple access (NOMA) systems. To address this challenge, we propose a novel four-step resource allocation algorithm. Specifically, we first obtain a sub-optimal solution for the sparse deployment of RIS elements using a Simulated Annealing Algorithm. We then solve the power allocation problem by employing an integer optimization algorithm that continuously iterates the immobile point. To simplify and optimize the reflection coefficient matrix, we propose a construction inequality algorithm. Finally, we optimize the channel assignment using a genetic algorithm. The simulation results demonstrate that the proposed irregular RIS-assisted NOMA system outperforms the traditional RIS-assisted orthogonal multiple access system, with a maximum throughput increase of approximately 30%.

show abstract

“…Due to the data security and fast data analysis and decision-making requirements of the Industrial Internet of Things (IIoT), federated learning is expected to be applied to the IIoT scenario to train machine learning models [ 6 ]. However, there are problems of low resource availability [ 7 ] in IIoT scenarios, such as low computing power, limited bandwidth, and battery life, and the heterogeneous properties of device capabilities [ 8 ] also increase the performance gap between devices. However, most of the existing research on federated learning for IIoT does not consider issues such as limited battery energy, resulting in limited applicable scenarios [ [9] , [10] ].…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, long-term energy scheduling and energy-saving technologies for batteries are the keys to efficient federated learning for battery-powered IIoT. Existing research on federated learning based on battery-powered devices mainly uses battery life as a device selection indicator [ 7 ] or adjusts some training parameters to improve battery life [12] , 14 – 15 , such as training batch size, CPU frequency, etc. There is little overall scheduling and allocation of battery energy, and there is a lack of control over battery life from a long-term perspective.…”

Section: Introductionmentioning

confidence: 99%