Page 44 - European Energy Innovation - Spring 2016 publication

44 Spring 2016 European Energy Innovation
COMMUNICATION
Cognitive computation and
communication for IoT
By Van Tam Nguyen, UC Berkeley / Telecom ParisTech
1. INTRODUCTION
In the next decades, Internet of Things
(IoT), the interconnected networks
of physical objects embedded with
electronics, software, sensors, and
connectivity will revolutionize how we
work, live, exercise, entertain and travel. wireless communication and cloud
IoT is experiencing explosive growth in
both quantity (20.8 billion IoT devices
by 20201) and utility, with increasingly
important applications in healthcare,
military operations, transportation and
urban planning2. However, IoT faces
several major growing challenges. First,
incorporating appropriate intelligence
and smart connectivity into IoT objects
requires a computing paradigm
that exceeds the current computing
capabilities of smart phones and
portables3. Second, ensuring privacy,
security and safety of IoT applications is
critically important, as IoT is susceptible (DCs), resulting in massive energy
Fig. 1: COGNICOM concept
to external attacks that can cause either expenditure and emission of CO2.
leak of private information or dangers
to users. Third, many IoT applications
require a high degree of reliability,
robustness and a low degree of latency
that exceeds the current design of
computing. Fourth, since IoT requires
process of large amount of data from
numerous devices, hardware design
for IoT applications need to be not only
flexible and adaptive but also highly
energy-efficient.
In the current architecture of IoT,
cloud computing provides the virtual
infrastructure for data collection,
analysis, visualization and service
delivery³. With the growing number of
billions of IoT devices, there will be a
great demand on cloud Data Centres
Today, the DCs are already responsible
for about 2% of global greenhouse gas
emissions, a similar share to aviation4.
In 2007, the DCs consumed on the
order of 330bn kWh, equivalent to the
entire electricity demand of the UK.
This demand is projected to triple or
quadruple by 2020, and accounts for
1.5-2% of all global electricity demand,
at a growing rate of 12% per year5.
Many IoT applications, such as smart
vehicular traffic management system,
smart driving and smart grid require
real-time and low-latency services. If the
processing, computation and storage
of the enormous amount of data are
performed only within DCs, the massive
data traffic generated from IoT devices
will result in network bottlenecks,
and affect the performance of all IoT
applications. In order to better handle
the communication demand of the IoT,
and reduce the energy consumption
and the emission of CO2, Bonomi
et al. proposed the concept of Fog
computing6. Its key principle is to
bring the cloud closer to the end user
by transforming as much as possible
data into action at the network edge.
The recent work in7 showed that in the
context of high number of latency-
sensitive applications, Fog computing
outperforms cloud computing.
However, the privacy issues, the
security and reliability problems remain
unsolved.
2 COGNICOM SOLUTION
To address those four major
challenges, we propose the
development of COGNICOM, a hybrid
architecture powered by Cognitive
Engine (CE) that facilitates optimal
www.europeanenergyinnovation.eu