期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：12
页码：307-320
出版社：Science and Information Society (SAI)
摘要：Edge computing extends cloud computing to
enhancing network performance in terms of latency and network
traffic of many applications such as: The Internet of Things
(IoT), Cyber-Physical Systems (CPS), Machine to Machine
(M2M) technologies, Industrial Internet, and Smart Cities. This
extension aims at reducing data communication and transmission
through the network. However, data processing is the main
challenge facing edge computing. In this paper, we proposed a
data processing framework based on both edge computing and
cloud computing, that is performed by partitioning (classification
and restructuring) of data schema on the edge computing level
based on feature selection. These features are detected using
MapReduce algorithm and a proposed machine learning
subsystem built on user requirements. Our approach mainly
relies on the assumption that the data sent by edge devices can be
used in two forms, as control data (i.e. real-time analytics) and as
knowledge extraction data (i.e. historical analytics).We evaluated
the proposed framework based on the amount of transmitted,
stored data and data retrieval time, the results show that both the
amount of sending data was optimized and data retrieval time
was highly decreased. Our evaluation was applied experimentally
and theoretically on a hypothetical system in a kidney disease
center.
关键词：Edge computing; cloud computing; data
processing; data partitioning; MapReduce; machine learning;
feature selection; user requirement
