TY - JOUR
T1 - Front-End Intelligence for Large-Scale Application-Oriented Internet-of-Things
AU - Bader, Ahmed
AU - Ghazzai, Hakim
AU - Kadri, Abdullah
AU - Alouini, Mohamed-Slim
N1 - KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: The work was made possible by NPRP grant #6-001-2-001 from
the Qatar National Research Fund (a member of Qatar Foundation). The
statements made herein are solely the responsibility of the authors.
PY - 2016/6/14
Y1 - 2016/6/14
N2 - The Internet-of-things (IoT) refers to the massive integration of electronic devices, vehicles, buildings, and other objects to collect and exchange data. It is the enabling technology for a plethora of applications touching various aspects of our lives such as healthcare, wearables, surveillance, home automation, smart manufacturing, and intelligent automotive systems. Existing IoT architectures are highly centralized and heavily rely on a back-end core network for all decision-making processes. This may lead to inefficiencies in terms of latency, network traffic management, computational processing, and power consumption. In this paper, we advocate the empowerment of front-end IoT devices to support the back-end network in fulfilling end-user applications requirements mainly by means of improved connectivity and efficient network management. A novel conceptual framework is presented for a new generation of IoT devices that will enable multiple new features for both the IoT administrators as well as end users. Exploiting the recent emergence of software-defined architecture, these smart IoT devices will allow fast, reliable, and intelligent management of diverse IoT-based applications. After highlighting relevant shortcomings of the existing IoT architectures, we outline some key design perspectives to enable front-end intelligence while shedding light on promising future research directions.
AB - The Internet-of-things (IoT) refers to the massive integration of electronic devices, vehicles, buildings, and other objects to collect and exchange data. It is the enabling technology for a plethora of applications touching various aspects of our lives such as healthcare, wearables, surveillance, home automation, smart manufacturing, and intelligent automotive systems. Existing IoT architectures are highly centralized and heavily rely on a back-end core network for all decision-making processes. This may lead to inefficiencies in terms of latency, network traffic management, computational processing, and power consumption. In this paper, we advocate the empowerment of front-end IoT devices to support the back-end network in fulfilling end-user applications requirements mainly by means of improved connectivity and efficient network management. A novel conceptual framework is presented for a new generation of IoT devices that will enable multiple new features for both the IoT administrators as well as end users. Exploiting the recent emergence of software-defined architecture, these smart IoT devices will allow fast, reliable, and intelligent management of diverse IoT-based applications. After highlighting relevant shortcomings of the existing IoT architectures, we outline some key design perspectives to enable front-end intelligence while shedding light on promising future research directions.
UR - http://hdl.handle.net/10754/614417
UR - http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7491206
UR - http://www.scopus.com/inward/record.url?scp=85006216192&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2016.2580623
DO - 10.1109/ACCESS.2016.2580623
M3 - Article
SN - 2169-3536
VL - 4
SP - 3257
EP - 3272
JO - IEEE Access
JF - IEEE Access
ER -