Toward Resource-Efficient Federated Learning in Mobile Edge Computing

Yu, Rong; Li, Peichun

doi:10.1109/mnet.011.2000295

Cited by 118 publications

(59 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) FL-based methods for resource management Some research efforts dealt with improving the FL steps. Authors in [38] classified some of them. These improvements have been applied on training tricks [39], client selection [16], [40], data compensation [41], hierarchical aggregation [42], model compression [43], knowledge distillation [44], and asynchronous update [45], [46].…”

Section: B Federated Learning For Resource Managementmentioning

confidence: 99%

Fast and Fair Computation Offloading Management in a Swarm of Drones Using a Rating-Based Federated Learning Approach

et al. 2021

View full text Add to dashboard Cite

Today, unmanned aerial vehicles (UAVs) or drones are increasingly used to enable and support multi-access edge computing (MEC). However, transferring data between nodes in such dynamic networks implies considerable latency and energy consumption, which are significant issues for practical real-time applications. In this paper, we consider an autonomous swarm of heterogeneous drones. This is a general architecture that can be applied for applications that need in-field computation, e.g. real-time object detection in video streams. Collaborative computing in a swarm of drones has the potential to improve resource utilization in a real-time application i.e., each drone can execute computations locally or offload them to other drones. In such an approach, drones need to compete for using each other's resources; therefore, efficient orchestration of the communication and offloading at the swarm level is essential. The main problem investigated in this work is computation offloading between drones in a swarm. To tackle this problem, we propose a novel federated learning (FL)-based fast and fair offloading strategy with a rating method. The simulation results demonstrate the effectiveness of the proposed strategy over other existing methods and architectures with average improvements of -23% in energy consumption, -15% in latency, +18% in throughput, and +9% in fairness.INDEX TERMS Swarm of drones, Multi-access edge computing, Collaborative computing, Federated learning.

show abstract

Section: B Federated Learning For Resource Managementmentioning

confidence: 99%

Fast and Fair Computation Offloading Management in a Swarm of Drones Using a Rating-Based Federated Learning Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Moreover, the adaptive quantization and specification could be applied into the FL networks, in order to compress the local models to reduce the communication cost [6]. In further, some other wireless techniques such as mobile edge computing can be incorporated into the FL networks to reduce the communication cost, in order to accelerate the convergence [7]- [10]. Recently, the effect of latency on the FL networks has been studied, where several bandwidth allocation schemes were proposed to enhance the system performance [11], [12].…”

Section: Introductionmentioning

confidence: 99%

System Optimization of Federated Learning Networks With a Constrained Latency

Zhang

Xia

Fan

et al. 2022

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

This paper investigates a wireless federated learning (FL) network with limited communication bandwidth, where multiple mobile clients train their individual models with the help of one central server. We consider the practical communication scenarios, where the clients should complete the local computation and model upload within a defined latency. By jointly exploiting the dynamic characteristics of wireless channels and computational capability at the clients, we optimize the federated learning network by maximizing the number of active clients under the constraints of both latency and bandwidth. Specifically, we propose two bandwidth allocation (BA) schemes, where scheme I is based on the instantaneous channel state information (CSI), while scheme II employs the particle swarm optimization (PSO) method, based on the statistical CSI. Simulation results on the test accuracy and convergence rate are finally provided to demonstrate the advantages of the proposed optimization schemes for the considered FL network.

show abstract

“…Consequently, edge computing (EC) systems are recently exploiting attaching these portable edge devices on low altitude platform (LAP) unmanned aerial vehicles (UAVs) or drones as aerial deployments, to execute complex resourcehungry use cases. A state-of-the-art drone technology, called Drone-in-a-box 3 , is most suitable for aerial EC deployment. A drone-in-a-box system can be deployed autonomously from a box that serves as a landing pad and charging base.…”

Section: Introductionmentioning

confidence: 99%

“…Most recently, research on EC has proposed a machine learning (ML) technique that trains an algorithm across multiple edge deployments holding local data samples, without exchanging them [2], [3]. This is called Federated or Collaborative Learning.…”

Section: Introductionmentioning

confidence: 99%

“…However, efficient orchestration of complex dependencies among tasks in such individual deployments is challenging due to constrained resource capabilities, vendor lock-in, availability factors, etc. Existing research on edge federated/collaborative learning, i.e., [2], [3] do not consider the ability of keeping edge resources running across different edge deployments in a single pool, such that these resources can be holistically managed and controlled from a single federated plane, vendor lock-in situations can be eliminated, and applications can be deployed dynamically across the resources. Note that edge FL technique produces and shares a single global inference model among participating edge through a remote/central server, while the merging of resources among participating edge, such that these resources are holistically managed and controlled from a single federated plane is refereed to as Edge Federation (EF).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation