Page 45 - EE Times Europe Magazine | April2019

EE|Times EUROPE — Boards & Solutions Insert 45

SPECIAL REPORT: AI AT THE EDGE
Edge Intelligence Ticks Many Boxes for AI

By Dennis Goldenson

s adoption rates rise for artificial intelligence
and machine learning (ML), the ability to process
large amounts of data in the form of algorithms
A for computational purposes becomes increasingly
important.
To help make the expanding use of data applications across
billions of connected devices more efficient and valuable,
there is growing momentum to migrate the processing from
centralized third-party cloud servers to decentralized and
localized processing on-device, commonly referred to as edge
computing. According to SAR Insight & Consulting’s latest AI/
ML embedded chips database, the global number of AI-en-
abled devices with edge computing will grow at a compound
annual growth rate of 64.2% during the 2019–2024 period.

DATA COMPUTATION AT THE EDGE, NO NETWORK
NEEDED
Edge AI takes the algorithms and processes the data as close
as possible to the physical system — in this case, locally on
the hardware device. The advantage is that the processing of
data does not require a connection. The computation of data
happens near the network edge, where the data is developed,
instead of in a centralized data-processing center. Determin- Proposed reference architecture model for edge computing
ing the right balance between how much processing can and should be (Image: European Edge Computing Consortium)
done on the edge will become one of the most important decisions for
device, technology, and component providers.
Given the training and inferencing engines that produce deep- security, aerospace, automotive, smart cities, health care — in which
learning predictive models, edge processing usually requires an x86 the immediate interpretation of diagnostics and equipment perfor-
or Arm processor from suppliers such as Intel, Qualcomm, Nvidia, and mance is critical.
Google; an AI accelerator; and the ability to handle speeds of up to
2.5 GHz with 10 to 14 cores. AI EDGE DEVELOPMENTS
The ability of edge REAL-TIME RESULTS FOR Innovative organizations such as Amazon, Google, Apple, BMW,
Volkswagen, Tesla, Airbus, Fraunhofer, Vodafone, Deutsche Telekom,
computing to provide TIME-SENSITIVE APPS Ericsson, and Harting are now embracing and hedging their bets for AI
immediate and reliable Given the expanding markets at the edge. A number of these companies are forming trade associa-
and expanding service and
tions, such as the European Edge Computing Consortium (EECC), to
data for time-sensitive application demands placed help educate and motivate small, medium-sized, and large enterprises
on computational data and
to drive the adoption of edge computing within manufacturing and
needs builds confidence, power, there are several other industrial markets.
The goals of the EECC initiative include specification of a reference
increases customer factors and benefits driving architecture model for edge computing, development of reference
the growth of edge comput-
engagement, and, in ing. Because of the shifting technology stacks (EECC edge nodes), identification of gaps and recom-
many cases, saves lives. needs of reliable, adaptable, mendation of best practices by evaluating approaches within multiple
and contextual informa-
scenarios, and synchronization with related initiatives/standardization
tion, a majority of the data organizations.
is migrating locally to on-device processing, resulting in improved
performance and response time (in less than a few milliseconds), lower LOOKING OVER THE EDGE
latency, higher power efficiency, improved security because data is The advancement of AI and machine learning is providing numerous
retained on the device, and cost savings because data-center transports opportunities to create smart devices that are contextually aware of
are minimized. their environment. The demands placed on smart machines will benefit
One of the biggest benefits of edge computing is the ability to secure from the growth in multi-sensory data that can compute with greater
real-time results for time-sensitive needs. In many cases, sensor data precision and performance. Edge computing provides an opportunity
can be collected, analyzed, and communicated straightaway, without to turn AI data into real-time value across almost every industry. The
having to send the data to a time-sensitive cloud center. intelligent edge is the next stage in the evolution and success of AI
Scalability across various edge devices to help speed local technology. ■
decision-making is fundamental. The ability to provide immediate and
reliable data builds confidence, increases customer engagement, and, Dennis Goldenson is director of artificial intelligence and machine
in many cases, saves lives. Just think of all of the industries — home learning at SAR Insight & Consulting.

www.eetimes.eu | APRIL 2020