A Game Theory Based Efficient Computation Offloading in an UAV Network

Abstract

Recently, solutions based on Mobile Edge Computing (MEC) paradigm have been widely discussed in academia and industry. This paradigm offers solutions to address limitations, in terms of battery lifetime and processing power, of mobile and constrained devices. Despite the ever-increasing capabilities of these devices, resource requirements of applications can often transcend what is available within a single device. Offloading intensive computation tasks to a distant server can help applications reach their desired performances. In this work, we tackle the problem of offloading heavy computation tasks of Unmanned Aerial Vehicles (UAVs) while achieving the best possible tradeoff between energy consumption, time delay and computation cost. We focus on a scenario of a fleet of small UAVs performing an exploration mission. During their mission, these constrained devices have to carry-out highly intensive computation tasks such as pattern recognition and video preprocessing. We formulate the problem using a non-cooperative theoretical game with N players and three pure strategies. We provide a comprehensive proof for the existence of a Nash Equilibrium and implement accordingly a distributed algorithm that converges to such an equilibrium. Extensive simulations are performed in order to provide thorough results and assess the performances of the approach compared to three other models. Results show that our algorithm outperforms all the three approaches. Our approach achieved in average about 19%, 58% and 55% better results compared to local computing, offloading to the Edge Server (ES) and offloading to Base Station (BS) respectively.

New Bargaining Game Based Computation Offloading Scheme for Flying Ad-hoc Networks

“…The Game Theory based Efficient Computation (GTEC) scheme is a game theory based offloading control algorithm to decrease the execution delay while optimizing the energy overhead [1]. This scheme formulates the task offloading problem by using a non-cooperative theoretical game model with three pure strategies; i) local computing, ii) offloading to edge server, and iii) offloading to a powerful BS.…”

“…Main objective in this paper is to optimize a global utility function, which takes into account a combination of energy consumption, delay and communication cost. Therefore, the solution obtained in [1] can achieve the best possible tradeoff between execution time and energy overhead while considering communication cost [1].…”

“…Therefore, the MCC enables developers to build applications designed specifically for mobile devices without being bound by the computing or memory capacity of mobile devices. Based on the MCC technology, computation intensive tasks in UAVs can be offloaded, and most computation can be executed in the MCC server to greatly reduce the burden on UAVs [1]- [4].…”

DeepBrain: Experimental Evaluation of Cloud-Based Computation Offloading and Edge Computing in the Internet-of-Drones for Deep Learning Applications

“…Furthermore, the gain of energy saving from a computation perspective is compromised by extra energy dissipation due to communication. This topic is a typical research problem pertaining to adopting optimal computation offloading strategies in cloud robotics that were addressed with different approaches in recent works, including Game Theory [ 14 , 15 ], Markov Decision Processes [ 16 , 17 ], and computational intelligence [ 18 ].…”

Testbed for Connected Artificial Intelligence using Unmanned Aerial Vehicles and Convolutional Pose Machines

“…In [18], the UAV is used for crowd surveillance based on face recognition. In [19], the drones have to carry-out pattern recognition and video preprocessing, both considering the possibility of local processing or offloading the intensive computation tasks to a Mobile Edge Computing (MEC) node. In [9] the authors propose moving the computation to an offboard computing cloud, while keeping low-level object detection and short-term navigation onboard, comparing the Faster R-CNNs [20] algorithm with YOLOv3 [21] and SSD [22].…”