.png){kind=icon}
返回
Knowledge reuse in edge computing environments
.png){kind=icon}
OA
AI
DOI：10.1016/j.jnca.2022.103466.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To cope with the challenge of managing numerous computing devices, humongous data volumes and models in Internet-of-Things environments, Edge Computing (EC) has emerged to serve latency-sensitive and compute -intensive applications. Although EC paradigm significantly eliminates latency for predictive analytics tasks by deploying computation on edge nodes' vicinity, the large scale of EC infrastructure still has huge inescapable burdens on the required resources. This paper introduces a novel paradigm where edge nodes effectively reuse local completed computations (e.g., trained models) at the network edge, coined as knowledge reuse. Such paradigm releases the burden from individual nodes, where they can save resources by relying on reusing models for various predictive analytics tasks (e.g., regression and classification). We study the feasibility of our paradigm by involving pair-wise (dis)similarity metrics among datasets over nodes based on statistical learning techniques (kernel-based Maximum Mean Discrepancy and eigenspace Cosine Dissimilarity). Our paradigm is enhanced with computationally lightweight monitoring mechanisms, which rely on Holt-Winters to forecast future violations and updates of the reused models. Such mechanisms predict when 'borrowed' models are insufficient for being reused, triggering a new process of finding more appropriate models to be reused at the network edge. We provide comprehensive performance evaluation and comparative assessment of our algorithms over different experimental scenarios using real and synthetic datasets. Our findings showcase the ability and robustness of our paradigm to maintain up-to-date reused models at the edge trading off quality of analytics and resource utilization.
Keyword:
Edge Computing
Model reusability
Knowledge dissemination
Maximum Mean Discrepancy
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8
论文数:
3.6K
被引数:
1.1W
机构
引用论文
Mentor-spotting: recommending expert mentors to mentees for live trouble-shooting in Codementor
PREAI
分享收藏
Gender related differences on the EEG during a simulated mobile phone signal模拟手机信号期间脑电图上的性别相关差异.png)
NeuroReport
NeuroReportIF0
PREAI
分享收藏分享收藏Electron Backscatter Diffraction: An Important Tool for Analyses of Structure–Property Relationships in Thin-Film Solar CellsJOM
JOMIF0
PREAI
分享收藏
查看更多内容