.png){kind=icon}
.png){kind=icon}
Return
Learning-Based Fast Decision for Task Execution in Next Generation Wireless Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/ICT52184.2021.9511542.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Learning-based computation of task execution in edge computing has a great potential to be a part of future cloud based next generation wireless networks. In this paper, we propose a novel intelligent computation task execution model to reduce decision latency by taking different system parameters into account including the execution deadline of the task, the battery level of mobile devices, and the channel between mobile device and edge server. In the edge computing, the number of task requests, resource constraints, mobility of users and energy consumption are main performance considerations. This study addresses the problem of a fast decision of the computing resources for the application offloaded to the edge servers by formulating it as a multi-class classification problem. The extensive simulation results demonstrate that the proposed algorithm is able to determine the decision of offloading computation tasks with more than 100 times faster than the conventional optimization method.
Keywords:
computation offloading
edge computing
Lyapunov optimization
machine learning
Journal
I
IF:
0
Papers:
9
Citations:
0