Research on Task-Oriented Computation Offloading Decision in Space-Air-Ground Integrated Network

In Space–Air–Ground Integrated Networks (SAGIN), computation offloading technology is a new way to improve the processing efficiency of node tasks and improve the limitation of computing storage resources. To solve the problem of large delay and energy consumption cost of task computation offloading...

Full description

Bibliographic Details
Main Authors: Jun Liu, Xiaohui Lian, Chang Liu
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Future Internet
Subjects:
DQN
Online Access:https://www.mdpi.com/1999-5903/13/5/128
id doaj-036016a503e5482499fea7f74381250b
record_format Article
spelling doaj-036016a503e5482499fea7f74381250b2021-05-31T23:56:16ZengMDPI AGFuture Internet1999-59032021-05-011312812810.3390/fi13050128Research on Task-Oriented Computation Offloading Decision in Space-Air-Ground Integrated NetworkJun Liu0Xiaohui Lian1Chang Liu2School of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaIn Space–Air–Ground Integrated Networks (SAGIN), computation offloading technology is a new way to improve the processing efficiency of node tasks and improve the limitation of computing storage resources. To solve the problem of large delay and energy consumption cost of task computation offloading, which caused by the complex and variable network offloading environment and a large amount of offloading tasks, a computation offloading decision scheme based on Markov and Deep Q Networks (DQN) is proposed. First, we select the optimal offloading network based on the characteristics of the movement of the task offloading process in the network. Then, the task offloading process is transformed into a Markov state transition process to build a model of the computational offloading decision process. Finally, the delay and energy consumption weights are introduced into the DQN algorithm to update the computation offloading decision process, and the optimal offloading decision under the low cost is achieved according to the task attributes. The simulation results show that compared with the traditional Lyapunov-based offloading decision scheme and the classical Q-learning algorithm, the delay and energy consumption are respectively reduced by 68.33% and 11.21%, under equal weights when the offloading task volume exceeds 500 Mbit. Moreover, compared with offloading to edge nodes or backbone nodes of the network alone, the proposed mixed offloading model can satisfy more than 100 task requests with low energy consumption and low delay. It can be seen that the computation offloading decision proposed in this paper can effectively reduce the delay and energy consumption during the task computation offloading in the Space–Air–Ground Integrated Network environment, and can select the optimal offloading sites to execute the tasks according to the characteristics of the task itself.https://www.mdpi.com/1999-5903/13/5/128Space–Air–Ground Integrated Networkcomputation offloadingMarkov decision processDQN
collection DOAJ
language English
format Article
sources DOAJ
author Jun Liu
Xiaohui Lian
Chang Liu
spellingShingle Jun Liu
Xiaohui Lian
Chang Liu
Research on Task-Oriented Computation Offloading Decision in Space-Air-Ground Integrated Network
Future Internet
Space–Air–Ground Integrated Network
computation offloading
Markov decision process
DQN
author_facet Jun Liu
Xiaohui Lian
Chang Liu
author_sort Jun Liu
title Research on Task-Oriented Computation Offloading Decision in Space-Air-Ground Integrated Network
title_short Research on Task-Oriented Computation Offloading Decision in Space-Air-Ground Integrated Network
title_full Research on Task-Oriented Computation Offloading Decision in Space-Air-Ground Integrated Network
title_fullStr Research on Task-Oriented Computation Offloading Decision in Space-Air-Ground Integrated Network
title_full_unstemmed Research on Task-Oriented Computation Offloading Decision in Space-Air-Ground Integrated Network
title_sort research on task-oriented computation offloading decision in space-air-ground integrated network
publisher MDPI AG
series Future Internet
issn 1999-5903
publishDate 2021-05-01
description In Space–Air–Ground Integrated Networks (SAGIN), computation offloading technology is a new way to improve the processing efficiency of node tasks and improve the limitation of computing storage resources. To solve the problem of large delay and energy consumption cost of task computation offloading, which caused by the complex and variable network offloading environment and a large amount of offloading tasks, a computation offloading decision scheme based on Markov and Deep Q Networks (DQN) is proposed. First, we select the optimal offloading network based on the characteristics of the movement of the task offloading process in the network. Then, the task offloading process is transformed into a Markov state transition process to build a model of the computational offloading decision process. Finally, the delay and energy consumption weights are introduced into the DQN algorithm to update the computation offloading decision process, and the optimal offloading decision under the low cost is achieved according to the task attributes. The simulation results show that compared with the traditional Lyapunov-based offloading decision scheme and the classical Q-learning algorithm, the delay and energy consumption are respectively reduced by 68.33% and 11.21%, under equal weights when the offloading task volume exceeds 500 Mbit. Moreover, compared with offloading to edge nodes or backbone nodes of the network alone, the proposed mixed offloading model can satisfy more than 100 task requests with low energy consumption and low delay. It can be seen that the computation offloading decision proposed in this paper can effectively reduce the delay and energy consumption during the task computation offloading in the Space–Air–Ground Integrated Network environment, and can select the optimal offloading sites to execute the tasks according to the characteristics of the task itself.
topic Space–Air–Ground Integrated Network
computation offloading
Markov decision process
DQN
url https://www.mdpi.com/1999-5903/13/5/128
work_keys_str_mv AT junliu researchontaskorientedcomputationoffloadingdecisioninspaceairgroundintegratednetwork
AT xiaohuilian researchontaskorientedcomputationoffloadingdecisioninspaceairgroundintegratednetwork
AT changliu researchontaskorientedcomputationoffloadingdecisioninspaceairgroundintegratednetwork
_version_ 1721416180733837312