IEEE Electrification - December 2022 - 8

TECHNOLOGY LEADERS
companies are training AI models
using thousands of images and video
streams from millions of onsite cameras
and sensors to detect process
anomalies. The models are deployed
at the edge in power plants and use
real-time inferencing to identify
leaks. Rig operators are using computer
vision, deep
learning, and intelligent
video analytics
(IVA) to monitor
heavy machinery,
detect potential hazards,
and alert workers
in real time to
protect their health
and safety, prevent
accidents, and assign
repair technicians
for maintenance.
Edge AI can calculate the optimal
flow of oil to ensure the reliability of
production and protect long-term
pipeline health. Using IVA, these
companies can inspect pipelines for
defects that could lead to dangerous
failures and automatically alert
pipeline operators.
Without distributed
AI solutions, electric
distribution utilities
will struggle to support
the clean energy
transition and
widespread
electrification.
Advancing Decarbonization
and Grid Reliability With AI
As companies and countries race to
decarbonize and meet net-zero emissions
goals, edge AI will play a key role
in managing DERs, such as EVs, home
batteries, solar panels, and wind farms,
to enhance power grid resiliency and
accelerate the energy
transition. Edge AI can
accelerate integrating
DERs and EVs into the
grid through distributed
decision making. In
a world where a utility
distribution system
has tens of millions of
interactive DER devices,
it will be critical to
embed scalable IoT
management within
edge intelligence for in situ scheduling,
condition forecasting, and proactive
dispatch that will manage the entire
power balance and system dynamics
in real time. Real-time edge management
will be critical to reducing and
eliminating upgrade costs for DER interconnections,
maximizing the existing
grid capacity, and reducing the
total cost of ownership of DERs.
Intelligent forecasting using grid
Reliability
Severe Weather
Resource Shortages
Affordability
Inflation
Storm Recovery
DER Transitions
Complexity
Decarbonization
Dynamic Two-Way
Powerflow
simulations, accelerated by machine
learning and AI models, combines
historical data on energy usage and
weather patterns to inform efficient
generation, distribution, and management
of energy resources to
consumers (Figure 2). Climate simulations
can predict the impact of extreme
weather events and generate
insights to save lives and reduce damage
costs. AI helps manage the bidirectional
flow of power in a grid,
delivering reliable energy to residents
and businesses, while automating the
process for consumers to sell their additional
energy back to the grid.
Edge computing can help monitor
the estimated 185 million utility
poles in the United States and reduce
the tens of millions of dollars spent
each year by utilities to manually
track and maintain grid infrastructure.
Fixed camera systems with
edge computing capabilities can be
secured to the roof of field service
trucks to collect standardized highresolution
images of utility poles,
power lines, and pole-mounted
assets. The images can be analyzed
at the edge to determine whether
repairs or vegetation management
are needed. With proactive maintenance,
utilities can accurately detect
defects and reduce unplanned outages
to better serve customers.
Figure 2. Grid attributes and the need for AI.
8
IEEE Electrification Magazine / DECEMBER 2022
How to Deploy AI Intelligence
at the Grid Edge
As the edge of the grid becomes rapidly
more complex with high penetrations
of EVs, distributed solar,
batteries, heat pumps, and extreme
weather, utilities will need real-time
visibility and decentralized decision
making and control. Without distributed
AI solutions, electric distribution
utilities will struggle to support
the clean energy transition and
widespread electrification. Future
smart grid edge intelligent devices
will use distributed computing to
IEEE Electrification - December 2022

Table of Contents for the Digital Edition of IEEE Electrification - December 2022
