Back to Search
Start Over
A Computation Offloading Game for Jointly Managing Local Pre-Processing Time-Length and Priority Selection in Edge Computing.
- Source :
- IEEE Transactions on Vehicular Technology; Sep2022, Vol. 71 Issue 9, p9868-9883, 16p
- Publication Year :
- 2022
-
Abstract
- Edge computing has been regarded as an enabling technology for supporting future smart applications, such as industrial Internet of Things. In this paper, a novel computation offloading framework for edge computing is proposed. Unlike existing studies, this work considers that end users can intentionally reserve some time for local pre-processing before requesting the computation offloading service (instead of always declaring their offloading requests immediately when heavy-duty tasks are generated). By doing so, each task’s offloading cost may decrease because of less edge resource demand, while the delay cost may increase due to the later report of its offloading request. Furthermore, end users can select their preferred priority levels in the offloading scheduling by paying premium service charges. To maximize the individual utility, each end user may strategically and jointly determine its local pre-processing time-length and priority selection in computation offloading. For characterizing strategic interactions among end users and the quality-of-service (QoS) of the scheduling system with congested nature, a computation offloading game built upon a queueing model is formulated. On top of this, a revenue maximization problem for the interest of edge operator is also investigated. Simulations evaluate the performance of the proposed solution, and shows its superiority over counterparts. [ABSTRACT FROM AUTHOR]
- Subjects :
- EDGE computing
INTERNET of things
GAMES
TASK analysis
Subjects
Details
- Language :
- English
- ISSN :
- 00189545
- Volume :
- 71
- Issue :
- 9
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Vehicular Technology
- Publication Type :
- Academic Journal
- Accession number :
- 159210981
- Full Text :
- https://doi.org/10.1109/TVT.2022.3177432