EXELON`S CHRIS CRANE:

Transcription

EXELON`S CHRIS CRANE:
MARCH/APRIL 2015
EXELON’S CHRIS CRANE:
Innovative Solutions
Drive Performance
32
WORKFORCE
DEVELOPMENT STRATEGIES
46
MANAGING
BIG DATA
equipment and machinery; transformers;
substations; distribution feeders; and
power generation and control components. Once sensored, these devices
become remotely machine addressable,
meaning information can be sent and
received across a computer network.
Taking smart meters as one example, it is clear that the smart grid is
communicate, with lasting effects on
advancing apace. As of 2014, nearly
professional and leisure activities.
400 million smart meters have been
With the genesis of the smart grid,
installed globally, according to Navigant
Bell’s predictions from four decades
Research. That number will more than
ago are having a direct impact on
double in the coming decade. Repretoday’s energy systems. The National
senting a fraction of the sensors on the
Academy of Engineers identified the
grid infrastrucelectric grid as the
ture, smart meter
most significant
As utilities adapt from
installations serve
scientific achieveas a proxy for the
ment of the 20th
managing a relatively small
penetration and
century. The smart
number of non-communicating
growth rate of
grid will be the
devices to connecting hundreds
the smart grid.
largest and most
of millions of diverse sensored
The “smart”
complex machine
devices, data volumes are
sensored devices
ever conceived
in and of themand will likely prove
expanding exponentially.
selves provide
one of the most
little utility. They
significant sciensimply provide the capability to remotely
tific achievements of the 21st century.
sense and/or change a device’s state.
It is estimated that as much as
For example, is the device operative
$2 trillion is being invested this decade
or inoperative? If operative, at what
in upgrading the power infrastructure
temperature, voltage, or amperage?
globally to add sensors to the devices
It might allow us to know the amount
throughout the grid, creating part of
of energy that the device has conwhat has come to be known as the
sumed or recorded over some period
IoT. These newly sensored things or
of time or is consuming in real time.
devices are the basis for the physical
Collectively, these devices generate
infrastructure of the smart grid and
massive amounts of information—an
include smart meters; thermostats;
increase of six orders of magnitude from
home appliances; heating, ventilation,
before the connected grid. As utilities
and air conditioning equipment; factory
information technology
The Internet of Energy
BY THOMAS M. SIEBEL
T
he “Internet of Things” (IoT) is
creating a buzz across industries.
It describes the integration of
an advanced, interconnected information backbone into the functioning
of physical devices, systems, and
infrastructures. It is the convergence
of the virtual and the physical. At a
basic level, IoT applies the Internet
as we know it to wirelessly connect
machines, devices, systems, and other
“things.” IoT will be transformational,
and Gartner predicts that, by 2020,
25 billion things will be connected
in industries ranging from automotive to food and beverage services.
In the energy industry, the momentum
of IoT is having a tremendous impact as
the grid becomes sensored, connected,
and smarter. The “Internet of Energy”
applies the premise of IoT to the infrastructure of the grid and is driving the
acceleration of the dynamic smart grid.
The Advent of the Smart Grid
Nearly 40 years ago, a Harvard sociologist predicted the advent of the Information Age. Years before the invention
of the Internet, minicomputer, personal
computer, and smart phone, Daniel Bell
authored “The Coming of Post-Industrial
Society.” He predicted that information
and communications technology would
cause a fundamental change in the
structure of the global economy—
a change as significant as the
Industrial Revolution.
The Information Age, as we know
it today, describes the free, nearly
instantaneous transfer and access of
data. It predicated the preeminence of
the “knowledge worker” and resulted in
the emergence and continued growth
of information technology (IT). It drives
ubiquitous changes in the ways we
Thomas M. Siebel is the chairman and CEO of C3 Energy. He
also was the founder, chairman, and CEO of Siebel Systems,
which became a leader in application software before merging
with Oracle Corporation in 2006.
54
ELECTRIC PERSPECTIVES
|
www.eei.org/ep
The “Internet of Energy”
is driving the
acceleration of the
dynamic
smart grid.
information technology
C3 Energy
Data analytics solutions for utilities must integrate massive amounts of disparate data, apply sophisticated multilayered
analytics, and provide highly usable portals that generate actionable real-time insights.
adapt from managing a relatively small
number of non-communicating devices
to connecting hundreds of millions of
diverse sensored devices, data volumes
are expanding exponentially. To effectively aggregate and manage this influx
of data, utilities require next-generation
technologies to integrate, process, apply
analytics, and intuitively visualize the data
and analytic results in a way that drives
business outcomes through a common
data- and intelligence-driven solution.
Next-Generation Technologies
By applying technologies and techniques commonly used by Google,
Amazon, Netflix, and Twitter in the
consumer industry, utilities can collect
and aggregate the sum of increasing
volumes of data to correlate and scientifically analyze all of the information
generated by the smart grid infrastructure in real time. Computer science
techniques, including elastic cloud
computing, machine learning, and social
human-computer interaction models,
are now being applied to challenges
utilities have faced for years, such as
56
ELECTRIC PERSPECTIVES
|
www.eei.org/ep
algorithm to refine it. As a result, over
managing the operational health of
time, it “learns” and evolves so that
advanced metering infrastructure (AMI)
the analyses generated are increasassets and preventing revenue loss
ingly accurate, reflecting real-world
due to theft and meter malfunctions.
conditions specific to the utility.
Utilities can apply the same techMachine learning is used to classify
nology concepts that Twitter uses to
assets at high risk of failure, segment
process 15 million tweets per second
customers for targeted marketing
or Netflix uses to stream more than
campaigns, identify
one billion hours
non-technical loss
of videos per
Leveraging not only machine
(which includes
month to intemeasurement
grate, aggregate,
learning but also a full stack of
errors, recording
and analyze the
tools associated with the science
errors, theft, and
massive amounts
of big data, analytics enabled by
timing differences),
of incoming data.
the smart grid provide efficiencies
and predict future
One such powerful
across the energy value chain.
load, among many
computer sciother applications.
ence technique is
For example, like a
machine learning,
credit card company can use historical
or the ability for computers to learn
spending data to flag potential fraud,
without being explicitly programmed.
utilities can use a variety of historical
Machine learning simply uses matheand real-time data to identify cases of
matical equations known as algorithms
energy theft. Baltimore Gas and Electric
that can learn from data. The algoCompany (BGE) proved this use case
rithms are trained on historical data
when it deployed the C3 Revenue
to make predictions. After predictions
Protection™ application across its full
are made, actual confirmed results
two-million-meter service territory. In
are fed back into a machine-learning
six months, the solution identified more
than 8,000 new cases of potential
theft, higher than its original goal.
Leveraging not only machine learning
but also a full stack of tools associated with the science of big data,
analytics enabled by the smart grid
provide efficiencies across the energy
value chain. Examples far outreach
revenue protection and include:
Z real-time pricing signals to
energy consumers;
Z management of sophisticated
energy efficiency and demand
response programs;
Z conservation of energy use;
Z reduction of fuel necessary to power
the grid;
Z real-time reconfiguration of the power
network around points of failure;
Z instantaneous recovery from
power interruptions;
Z accurate prediction of load;
Z efficient management of distributed
generation capacity;
Z rapid recovery from damage
inflicted by weather events and
system failures;
Z reduction of fuel needed to power the
grid; and
Z substantial reduction in adverse
environmental impacts.
Data Analytics Solutions
Data analytics solutions for utilities must
integrate massive amounts of disparate
data, apply sophisticated multilayered
analytics, and provide highly usable
portals that generate actionable realtime insights. Utilities need end-to-end
system visibility across supply-side and
demand-side smart grid operations.
Data analytics enable grid operators
to realize dramatic advances in safety,
reliability, cost efficiency, and environmental benefits by correlating and
analyzing all of the dynamics and interactions associated with the end-to-end
power infrastructure as a fully interconnected and sensored network, including
current and predicted demand, consumption, electric vehicle load, distributed generation capacity, technical and
non-technical losses, weather reports
and forecasts, and generation capacity
across the entire value chain. In another
example from BGE, the utility used the
C3 AMI Operations™ application to
identify 3,600 meter health issues with
99-percent accuracy in order to streamline critical maintenance on AMI assets.
data management system, validated
theft-case data, external weather data,
and Google for address verification.
Leveraging investments in analytical algorithms, machine learning, data
International Impact
integration, and cloud-scale infrastrucThe growth of the smart grid and the
ture, Enel deployed 55 unique and
necessity for next-generation anasophisticated energy flow analytics
lytics solutions are not limited to the
to identify anomalous meter activUnited States. The European market
ity. The company is leveraging these
is seeing strong drivers for analytics,
analytics to execute rule-based and
including the increased number of smart machine-learning algorithms to unlock
meter deployments in Italy, the United
insights from both batch and streamKingdom, France, and Spain, and the
ing data, and to generate increasingly
European Union’s recommendation
targeted and accurate results.
of 80-percent smart meter penetraThe initial deployment proved that
tion in member countries by 2020.
the data-analytics solution could readily
Enel, a leading integrated player in
handle Enel’s smart grid data processthe world’s power and gas markets with
ing and aggregation needs. Based on
the largest customer base (61 million)
the results from the one-million-meter
among its Eurodemonstration,
pean peers,
Enel and C3
is deploying dataEnergy are working
By 2006, Enel had installed
analytics solutions
to expand the
32 million smart meters across
to enable smart
deployment of
Italy; Enel has since deployed
grid and smart city
this solution more
a total of approximately
services. A smart
widely across the
grid pioneer, Enel
group’s distribu40 million smart meters in
was the first utility
tion network. Enel
Europe, representing more
in the world to
also is installing
than 80 percent of the total
replace traditional
additional applismart meters on the continent.
electromechanical
cations to expand
meters with digital
on what will be the
smart meters,
largest deploya major operation carried out among
ment of software-as-a-service
Enel’s entire Italian customer base. By
smart grid analytics in the world.
2006, Enel had installed 32 million
Leading utilities are driving innosmart meters across Italy; Enel has
vation toward the Internet of Energy.
since deployed a total of approximately
They are at the cutting edge of tech40 million smart meters in Europe,
nology advancements and are realrepresenting more than 80 percent of
izing significant returns by applying
the total smart meters on the continent.
data-analytics solutions that combine
To optimize the monitoring of energy
the sciences of cloud-scale computflows, Enel has deployed one of C3
ing, advanced smart grid analytics,
Energy’s data-analytics applications
and machine learning to the benefit of
across one million meters in Italy. Impletheir communities, consumers, stakemented in less than eight months, the
holders, and the environment.
solution ultimately identified 93 percent
of Enel’s already-known operational
issues through the initial deployment.
For Enel, C3 Energy integrated,
normalized, and aggregated more
than 50 billion rows of data from 11
Enel sources, including the customer
information system, billing system,
work order system, outage management system, producer system, meter
MARCH | APRIL 2015 57