Page 46 - European Energy Innovation - Spring 2016 publication
P. 46

46  Spring 2016 European Energy Innovation


also enhances privacy, security and         However, the existing cloud-centric          ACKNOWLEDGEMENT
reliability of the network. It will also    architecture of IoT poses serious
improve the sustainable development         challenges regarding cognitive capacity,     The author acknowledges many
of the IoT ecosystem. In order to           connectivity, safety, privacy, flexibility,  of his colleagues and students
do so, the key enabler is the smart         latency and energy-efficiency. We have       from BWRC and Telecom ParisTech
application gateway (SAG), which            proposed to develop COGNICOM,                who have contributed to the ideas
should be able to perform many tasks        a brain-inspired software-hardware           presented in this paper. In particular,
that are currently relegated to cloud       paradigm, to support IoT’s future            he would like to thank Duc-Tuyen
computing. In addition to its traditional   growth. COGNICOM brings computing            TA and Nhan NGUYEN-THANH for
functionalities, SAG will also (1)          closer to end-user and focuses on            the figures and Tuan DINH from
collect, classify, and integrate data; (2)  optimal uses of local SAG and cloud          Cogitativo for interesting discussions
interpret data to generate appropriate      computing. COGNICOM consists                 and his help.
responses; and (3) perform actions          of two key components: Cognitive
and/or generate alerts/warnings.            Engine and Smart Connectivity. CE is
The majority of data will be stored         powered by deep-learning algorithms
and processed in local databases.           integrated with game-theoretic decision
The interpretation of the data will be      analytics, implemented on low-power
performed by the CE, whose deep-            Network Multi-Processor System on
learning algorithms will be pre-trained     Chip. CE provides cognitive functions
using cloud-based computing. The            to smart objects. SC integrates neural
CE will detect abnormal activities and      network inspired designs of cognitive
emergency situations and directly           radio, transceivers and baseband
provide appropriate responses. It is        processors. SC provides flexible and
also responsible for timely response        reliable connections to IoT objects and
services and decision of which data         optimally distributes communication
should be sent to the cloud platform        resources. l
for further analytic and interpretation.
It is also capable to learn to adapt        CONTACT DETAILS
its functionalities, capabilities and
behavior to the environment and             Author's name: Van Tam Nguyen
user in order to achieve predefined         Email: or
objectives.                                 Web:
                                            BWRC, Department of EECS, University of California at Berkeley, California,
5 CONCLUSION                                94720, USA
IoT is experiencing explosive growth        LTCI, CNRS, Télécom ParisTech, Université Paris Saclay, 75013, Paris, France
in number of devices and applications.

1	 Available:
2	 H. Sundmaeker, P. Guillemin, P. Friess, and S. Woelfflé, “Vision and challenges for realising the Internet of Things,” vol. 20, no. 10. CERP-IoT – Cluster of European

    Research Projects on the Internet of Things, 2010.
3	 J. Gubbi, R. Buyya, S. Marusic, and M. Palaniswami, “Internet of Things (IoT): A vision, architectural elements, and future directions,” Future Generation Computer

    Systems, vol. 29, no. 7, pp. 1645–1660, 2013.
4	 Global e-Sustainability Initiative, “SMARTer 2020: The Role of ICT in Driving a Sustainable Future,” Climate Group, 2012.
5	 G. Cook and J. Van Horn, “How dirty is your data? A look at the energy choices that power cloud computing,” Greenpeace (April 2011), 2011.
6	 F. Bonomi, R. Milito, J. Zhu, and S. Addepalli, “Fog computing and its role in the internet of things,” in Proceedings of the first edition of the MCC workshop on

    Mobile cloud computing, 2012, pp. 13–16.
7	 S. Sarkar, S. Chatterjee, and S. Misra, “Assessment of the Suitability of Fog Computing in the Context of Internet of Things,” Cloud Computing, IEEE Transactions on,

    vol. PP, no. 99, pp. 1–1, 2015.
8	 V. T. Nguyen, F. Villain, and Y. L. Guillou, “Cognitive radio RF: overview and challenges,” VLSI Design, vol. 2012, p. 1, 2012.
9	 N. Nguyen-Thanh, T. A. Pham, and V.-T. Nguyen, “Medium access control design for cognitive radio networks: a survey,” IEICE Transactions on Communications, vol.

    97, no. 2, pp. 359–374, 2014.
10	 R. Madan, J. Borran, A. Sampath, N. Bhushan, A. Khandekar, and T. Ji, “Cell association and interference coordination in heterogeneous LTE-A cellular networks,”

    Selected Areas in Communications, IEEE Journal on, vol. 28, no. 9, pp. 1479–1489, 2010.

   41   42   43   44   45   46   47   48   49   50   51