Energy-Aware Positioning Service Provisioning for Cloud-Edge-Vehicle Collaborative Network Based on DRL and Service Function Chain

Authors

Peiying Zhang, China University of Petroleum (East China)
Yi Zhang, China University of Petroleum (East China)
Neeraj Kumar, Thapar Institute of Engineering & Technology
Mohsen Guizani, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Ahmed Barnawi, King Abdulaziz University
Wei Zhang, Qilu University of Technology

Document Type

Article

Publication Title

IEEE Transactions on Mobile Computing

Abstract

In the collaborative intelligent transportation system, providing precise positioning services is costly. Reducing resource consumption and improving revenue are crucial to the development of positioning services. Therefore, a practical algorithm that combines cloud and edge network environments is necessary to improve the positioning services. Integrating network function virtualization and edge computing can provide users with more flexible and efficient services. Based on the above issues, we use the service function chain (SFC) to improve the positioning services provided in cloud-edge-vehicle collaborative networks (CEVCN). We propose a deep reinforcement learning-assisted SFC embedding algorithm and improve its performance through training. We construct a five-layer policy network to sense the environment of CEVCN and derive the optimal node selection strategy. Finally, we use the breadth-first search algorithm to solve the embedding scheme for virtual links. The simulation results show that our proposed algorithm has excellent performance. The long-term average revenue is improved by 21%, the long-term average revenue-cost ratio is improved by 13%, and the embedding rate is improved by 8%.

First Page

1

Last Page

12

DOI

10.1109/TMC.2023.3276314

Publication Date

5-16-2023

Keywords

Cloud computing, Cloud-Edge-Vehicle collaborative network, Costs, deep reinforcement learning, Edge computing, Heuristic algorithms, network function virtualization, positioning service, Quality of service, Roads, service function chain, Service function chaining

Comments

IR Deposit conditions:

OA version (pathway a) Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged

Recommended Citation

P. Zhang, Y. Zhang, N. Kumar, M. Guizani, A. Barnawi and W. Zhang, "Energy-Aware Positioning Service Provisioning for Cloud-Edge-Vehicle Collaborative Network Based on DRL and Service Function Chain," in IEEE Transactions on Mobile Computing, pp. 1-6, May 2023, doi: 10.1109/TMC.2023.3276314.

Additional Links

https://doi.org/10.1109/TMC.2023.3276314