.png){kind=icon}
.png){kind=icon}
Return
Offloading Dependent Tasks in Edge Computing With Unknown System-Side Information
.png){kind=icon}
PRE
AI
DOI：10.1109/TSC.2023.3320674.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We consider the problem of dependent task offloading in edge computing with unknown system-side information (e.g., edge transmission rate and computation resources). In this problem, tasks have complicated dependency relationships and have no prior knowledge of system-side information to assist offloading decision-making. Although existing learning-based approaches can help to address unknown system-side information, the impact of inherent task dependency on such approaches has not been formally explored. To bridge the gap, we first use a breadth-first-search (BFS) method to decouple task dependency, and then leverage the Lyapunov optimization technique to transfer the long-term offloading problem to an online optimization problem. Furthermore, we employ the multi-armed bandit (MAB) theory to develop the online learning-based dependent task offloading algorithm, called OL-DTO. The algorithm can address the unknown system-side information and is augmented with task dependency awareness. We present a rigorous theoretical analysis to evaluate the performance of this algorithm in terms of application delay and UD energy consumption. Our extensive experimental results demonstrate that the OL-DTO algorithm significantly reduces application delay while satisfying the long-term energy budget constraint of the UD.
Keywords:
Unknown system-side information
task dependency
concurrent-enhanced offloading
learning-based offloading
multi-armed bandit theory
Journal
IF:
5.8
Papers:
2.1K
Citations:
6.5K
Organization
View more organizations