Optimal Stochastic Coded Computation Offloading in Unmanned Aerial Vehicles Network

TL;DR

This paper proposes an optimal task allocation scheme for UAV networks that minimizes energy consumption during computation offloading by using stochastic integer programming, effectively handling uncertainties in task completion.

Contribution

It introduces a novel OTAS method based on stochastic integer programming for energy-efficient task offloading in UAV networks.

Findings

Energy consumption is minimized under task completion uncertainty.

The proposed scheme outperforms traditional offloading methods.

Simulation results validate the effectiveness of OTAS.

Abstract

Today, modern unmanned aerial vehicles (UAVs) are equipped with increasingly advanced capabilities that can run applications enabled by machine learning techniques, which require computationally intensive operations such as matrix multiplications. Due to computation constraints, the UAVs can offload their computation tasks to edge servers. To mitigate stragglers, coded distributed computing (CDC) based offloading can be adopted. In this paper, we propose an Optimal Task Allocation Scheme (OTAS) based on Stochastic Integer Programming with the objective to minimize energy consumption during computation offloading. The simulation results show that amid uncertainty of task completion, the energy consumption in the UAV network is minimized.