Research on intelligent task offloading algorithm based on compressed sensing in internet of vehicles

Wenbo Zhang; Jie Zhang; Qi Liu; Shuai Li

doi:10.1117/12.2675292

25 May 2023 Research on intelligent task offloading algorithm based on compressed sensing in internet of vehicles

Wenbo Zhang, Jie Zhang, Qi Liu, Shuai Li

Proceedings Volume 12636, Third International Conference on Machine Learning and Computer Application (ICMLCA 2022); 1263657 (2023) https://doi.org/10.1117/12.2675292
Event: Third International Conference on Machine Learning and Computer Application (ICMLCA 2022), 2022, Shenyang, China

Abstract

In this paper, a vehicle-side-cloud collaborative offloading architecture for vehicular networking tasks is proposed and an optimization model is constructed to minimize the load under the conditions of computational task latency and communication link stability constraints. Secondly, a compressed sensing technique is introduced to reduce the amount of data for offloading tasks by compressing the sampling to eliminate a large amount of redundant data. Finally, a deep Q-network is introduced to solve the optimization problem, and the terminal executes different offloading strategies according to the task attributes, which can update itself in the environment under time-varying channel conditions. The simulation results show that the intelligent task offloading algorithm based on compressed sensing (CSITO) algorithm has certain superiority.

Citation Download Citation

Wenbo Zhang, Jie Zhang, Qi Liu, and Shuai Li "Research on intelligent task offloading algorithm based on compressed sensing in internet of vehicles", Proc. SPIE 12636, Third International Conference on Machine Learning and Computer Application (ICMLCA 2022), 1263657 (25 May 2023); https://doi.org/10.1117/12.2675292

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available