On Leveraging the Computational Potential of Fog-Enabled Vehicular Networks
The advent of autonomous vehicles demands powerful processing capabilities of on-board units to handle the dramatic increase of sensor data used to make safe self-driving decisions. Those com- putational resources, being constantly available on the highways, represent valuable assets that can be lev...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , |
| Format: | conferenceObject |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10725/11624 https://doi.org/10.1145/3345838.3356009 http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.php https://dl.acm.org/citation.cfm?id=3356009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The advent of autonomous vehicles demands powerful processing capabilities of on-board units to handle the dramatic increase of sensor data used to make safe self-driving decisions. Those com- putational resources, being constantly available on the highways, represent valuable assets that can be leveraged to serve as fog computing facility to computational tasks generated from other vehicles or even from different networks. In this paper, we propose a fog-enabled system scheme that can be deployed on a road side unit (RSU) to schedule and offload requested computational tasks over the available vehicles' on-board units (OBUs). The goal is to maximize the weighted sum of the admitted tasks. We model the problem as a Mixed Integer Linear Programming (MILP), and due to NP-hardness, we propose a Dantzig-Wolfe decomposition method to provide a scalable solution. The experiment shows that our ap- proach has a sufficient effectiveness in terms of both computational complexity and tasks acceptance rate. |
|---|