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

Dadmehr Rahbari,Maksim Jenihhin,Yannick Le Moullec,Muhammad Mahtab Alam

doi:10.1109/access.2021.3104117

Dadmehr Rahbari, Maksim Jenihhin + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3104117

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2021
Citations: 9	License type: CC BY 4.0

Affiliation: Tallinn University of Technology

Abstract

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 used 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. Our 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.

Highlights

Autonomous swarms of unmanned aerial vehicles (UAVs) or drones have attracted significant attention in different application domains
We propose a novel distributed offloading management strategy that is based on online federated deep reinforcement learning (FDRL), which relies on drone rating
Since our problem is distributed offloading in a swarm of drones as multi-access edge computing (MEC), we present the works related to cooperative computing in the following subsections

Summary

Introduction

Autonomous swarms of unmanned aerial vehicles (UAVs) or drones have attracted significant attention in different application domains. When operating in a group, drones can process the computation tasks independently or collaboratively. A group of independent drones is subject to severe constraints such as limited battery capacity, computing resource capability, etc. Collaboration between drones, The associate editor coordinating the review of this manuscript and approving it for publication was Chi-Tsun Cheng. I.e. offloading computations between them, yields many advantages over a group of independent drones [1]. A swarm of collaborative and intelligent drones decreases the overall energy consumption and cost, and increases the throughput and quality of service (QoS) [2]. A swarm of drones can be used for many applications such as monitoring, detection, etc. A swarm of drones can be used for many applications such as monitoring, detection, etc. [3], [4]

Objectives

Results

Conclusion