.png){kind=icon}
返回
A Data-Driven Adaptive Sampling Method Based on Edge Computing
.png){kind=icon}
OA
AI
DOI：10.3390/s20082174.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The rise of edge computing has promoted the development of the industrial internet of things (IIoT). Supported by edge computing technology, data acquisition can also support more complex and perfect application requirements in industrial field. Most of traditional sampling methods use constant sampling frequency and ignore the impact of changes of sampling objects during the data acquisition. For the problem of sampling distortion, edge data redundancy and energy consumption caused by constant sampling frequency of sensors in the IIoT, a data-driven adaptive sampling method based on edge computing is proposed in this paper. The method uses the latest data collected by the sensors at the edge node for linear fitting and adjusts the next sampling frequency according to the linear median jitter sum and adaptive sampling strategy. An edge data acquisition platform is established to verify the validity of the method. According to the experimental results, the proposed method is more effective than other adaptive sampling methods. Compared with constant sampling frequency, the proposed method can reduce the edge data redundancy and energy consumption by more than 13.92% and 12.86%, respectively.
Keyword:
edge computing
industrial internet of things
data acquisition
adaptive sampling
linear median jitter sum
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:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
Efficient IoT-based sensor BIG Data collection-processing and analysis in smart buildings基于物联网的高效传感器大数据采集-智能建筑中的处理和分析
PREAI
分享收藏A Capillary Computing Architecture for Dynamic Internet of Things: Orchestration of Microservices from Edge Devices to Fog and Cloud Providers.png)
SENSORSOAAI
SENSORSIF3.5
OAAI分享收藏Big Data-Based Improved Data Acquisition and Storage System for Designing Industrial Data PlatformIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容