Federated Learning Over Energy Harvesting Wireless Networks

Hamdi, Rami; Chen, Mingzhe; Said, Ahmed Ben; Qaraqe, Marwa; Poor, H. Vincent

doi:10.1109/jiot.2021.3089054

Cited by 57 publications

(28 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, how to allow the devices to harvest sufficient energy to train a FL model while not substantially increasing the communication round time is largely an open question. The use of energy harvesting for FL is highly novel and to the best of our knowledge, there are only three works in the literature [62], [148], [185].…”

Section: Energy Harvesting and Power Transfermentioning

confidence: 99%

Wireless for Machine Learning: A Survey

Hellström¹,

Silva²,

Amiri³

et al. 2022

Self Cite

View full text Add to dashboard Cite

As data generation increasingly takes place on devices without a wired connection, Machine Learning (ML) related traffic will be ubiquitous in wireless networks. Many studies have shown that traditional wireless protocols are highly inefficient or unsustainable to support ML, which creates the need for new wireless communication methods. In this monograph, we give a comprehensive review of the state-of-the-art wireless methods that are specifically designed to support ML services over distributed datasets. Currently, there are two clear themes within the literature, analog over-the-air computation and digital radio resource management optimized for ML. This survey gives an introduction to these methods, reviews the most important works, highlights open problems, and discusses application scenarios.

show abstract

Section: Energy Harvesting and Power Transfermentioning

confidence: 99%

Wireless for Machine Learning: A Survey

Hellström¹,

Silva²,

Amiri³

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite its potential and impact, FL in IoT networks is a difficult task as IoT devices are highly resource constrained. In particular, this paper focuses on enabling FL with energy harvesting (EH) devices [3,4], where the computation [5,6,7] and communication [8,9,10,11,12] operations of FL at an EH device depend entirely on its harvested energy. The focus CS was supported in part by the National Science Foundation (NSF) under CNS-2002902, ECCS-2029978, and ECCS-2033671.…”

Section: Introductionmentioning

confidence: 99%

On Federated Learning with Energy Harvesting Clients

Shen¹,

Yang²,

Xu³

2022

Preprint

View full text Add to dashboard Cite

Catering to the proliferation of Internet of Things devices and distributed machine learning at the edge, we propose an energy harvesting federated learning (EHFL) framework in this paper. The introduction of EH implies that a client's availability to participate in any FL round cannot be guaranteed, which complicates the theoretical analysis. We derive novel convergence bounds that capture the impact of time-varying device availabilities due to the random EH characteristics of the participating clients, for both parallel and local stochastic gradient descent (SGD) with non-convex loss functions. The results suggest that having a uniform client scheduling that maximizes the minimum number of clients throughout the FL process is desirable, which is further corroborated by the numerical experiments using a real-world FL task and a state-of-the-art EH scheduler.

show abstract

“…Energy harvesting communication devices have been previously studied in detail from different perspectives, including optimal transmission policies [21]- [23], and channel capacity computation for unit-sized battery [24]. Energy harvesting FL has also been considered where the participating MDs are energy harvesting devices [25], [26]. However, no approach considers the wireless channel effects and OTA aggregation in energy harvesting FL setups, which constitutes the basis of this work.…”

Section: Introductionmentioning

confidence: 99%

Over-the-Air Federated Learning with Energy Harvesting Devices

Aygün¹,

Kazemi²,

Gündüz³

et al. 2022

Preprint

View full text Add to dashboard Cite

We consider federated edge learning (FEEL) among mobile devices that harvest the required energy from their surroundings, and share their updates with the parameter server (PS) through a shared wireless channel. In particular, we consider energy harvesting FL with over-the-air (OTA) aggregation, where the participating devices perform local computations and wireless transmission only when they have the required energy available, and transmit the local updates simultaneously over the same channel bandwidth. In order to prevent bias among heterogeneous devices, we utilize a weighted averaging with respect to their latest energy arrivals and data cardinalities. We provide a convergence analysis and carry out numerical experiments with different energy arrival profiles, which show that even though the proposed scheme is robust against devices with heterogeneous energy arrivals in error-free scenarios, we observe a 5-10% performance loss in energy harvesting OTA FL.

show abstract

Federated Learning Over Energy Harvesting Wireless Networks

Cited by 57 publications

References 39 publications

Wireless for Machine Learning: A Survey

Wireless for Machine Learning: A Survey

On Federated Learning with Energy Harvesting Clients

Over-the-Air Federated Learning with Energy Harvesting Devices

Contact Info

Product

Resources

About