Page 30 - Energize June 2021

VIEWS AND OPINION

Why our future energy system will need

artificial intelligence

On any given day, the electric power industry’s operations are complex and its responsibilities vast. As the industry
continues to play a critical role in supporting global climate goal challenges, it must simultaneously support
demand increases, surges in smart appliance adoption and decentralised operating system expansions. And that
just scratches the surface.

by Jeremy Renshaw, EPRI

ehind the scenes, there’s the power grid operator, whose role is to monitor the electricity
network 24 hours per day, 365 days per year. As a larger number of lower capacity systems
B(such as renewables) come online and advanced network components are integrated into
the grid, generation becomes exponentially more complex, decentralised and variable, stretching
control room operators to their limits.
More locally, building owners and controllers are being challenged to deploy grid-interactive
intelligent elements that can flexibly participate in grid level operations to economically
enhance grid resiliency, while also saving money for the building owner.
Outside those buildings, electric utilities collect millions of images of their transmission
and distribution (T&D) infrastructure to assess equipment health and support reliability Jeremy Renshaw
investments. But the ability to collect imagery has outpaced utility staff’s ability to analyse and
evaluate them.
On the generation side, operators are being increasingly pressured by market changes EPRI is developing models and tools
to decrease operations and maintenance costs (O&M) while maintaining and, if possible, which will enable operators to enhance
increasing production revenue. their responsiveness and flexibility to utility
grid signals in the most cost-effective way.
What’s best way to manage these current and future challenges? Coupled with the digitisation of building
The solution may lie within another industry – artificial intelligence.“If you step back for a control systems, AI predictive models will
moment, you realise there are two (separate) trillion-dollar industries – the energy industry provide utilities and customers greater
and the data and information industry – which are now intersecting in a way they never have affordability, resiliency, environmental
before,” said Arun Majumdar, Stanford University Jay Precourt Provostial Chair Professor of performance, and reliability.
Mechanical Engineering, the founding director of ARPA-E, and a member of the EPRI Board
of Directors. Matching challenges and opportunities
Majumdar spoke at an Electric Power Research Institute (EPRI) AI and Electric Power with solutions
Roundtable discussion earlier this year. “The people who focus on data do not generally have In late May, EPRI brought more than 100
expertise regarding the electricity industry and vice versa. We have entities like EPRI trying to organisations together across the two
connect the two and this is of enormous value,” he said. industries in a “Reverse Pitch” event
1
where electric power utilities presented
Discovering new opportunities their biggest challenges, and AI companies
Take the power grid operator challenge, for example. EPRI is exploring an AI “reinforcement responded with potential solutions.
learning (RL) agent” that can act as a continuously learning, algorithm-based autopilot for ( Reverse Pitch is an EPRI thought
1
operators to optimise performance. The goal is not to replace operators, who are essential for leadership event).
transmission operations, but rather to develop tools to augment their decision-making ability “We want to help increase adoption
using RL. of proven AI technologies, and that
Turning to building operators, recent advances in building controls technology, enabled by the means we need to match solutions with
model predictive control (MPC) framework, have focused on minimising operating costs or energy the needs and issues utilities have,”
use, or maximising occupant comfort. But most commercial building MPC case studies have been said Heather Feldman, EPRI Innovation
abandoned because they can be labour-intensive and costly to customise and maintain. Director for the nuclear energy sector.

energize | June 2021 | 28