Accepting A.I. and Machine Learning: Developments promise efficiencies for power management and ECs

Published On
Apr 15, 2022

Artificial intelligence (A.I.) uses data to mimic the cognitive and intellectual capabilities of a human mind, employing machine learning, deep learning, neural networks and other technology to do so.

Machine learning (ML) is an iterative process whereby algorithms and statistical models find patterns in the data, draw inferences and perform tasks. It uses artificial neural networks that observe the data and learn as it is transmitted. Deep learning is a more in-depth form of ML, using artificial neural networks to process information in forms such as audio and language. Such processing is useful in many applications, including in electrical construction.

Power management

A.I. is becoming widely used for power systems. Algorithms can sense irregularities and anomalies in power distribution and other data signals and identify malfunctions and deficiencies. Once notified, operators can take appropriate actions.

A.I. can read weather patterns and forecast weather in variable conditions. Weather data is crucial and useful when solar and wind power are used in combination with fossil fuels or other sources of power generation.

A January 2022 article in Power Magazine cited an investor-owned utility in the southeastern United States that uses A.I. to help its solar-power plant be a resource for power expansion. As it becomes popular in applications such as these, companies are quick to embrace A.I. They’re investing in it heavily, with enthusiasm, but also need to use it safely in today’s modern, and sometimes vulnerable, IT environment.

Advancements hinge on IT

Recently, Arize A.I. Inc. researched the use of A.I. by more than 900 teams and professionals who closely use the technology. According to the report, A.I. is “relied on in nearly every industry today to increase profitability, productivity, and even save lives.”

The report cites researcher International Data Corp., which forecasts A.I. spending will be at least $204 billion by 2025. The report also notes that IT infrastructure does not always keep pace with advancements and it’s common for firms to run outdated A.I. models.

Most of the report’s findings indicate strong enthusiasm and a need to pave the way for A.I. with investment, infrastructure and cybersecurity. For example, “Over half of data scientists, ML engineers and technical executives say their teams would benefit from deeper capabilities around drift monitoring and troubleshooting as well as explaining irregularities or anomalies. Over four in ten want better model performance monitoring.” This implies that A.I. is attractive to engineers for its monitoring capabilities for systems and conditions.

Another interesting finding is the apparently low confidence in A.I.’s ability to weed out bias. Per the report, “79.7% of ML teams report that they ‘lack access to protected data needed to root out bias or ethics issues’ at least some of the time, and nearly half (42.1%) say this is an issue at least somewhat often.”

A.I. helps shape the future

According to a January 2022 report from Market Resource Future, A.I. is expected to make major inroads in the construction industry in various ways. It therefore behooves electrical contractors to embrace and understand as much as they can about the technology. A common usage will be in control systems and monitoring. The firm predicts A.I. in construction markets will reach $2.512 billion, with a compound annual growth rate of 33.2%, by 2030.

The report opines that “the cost-efficiency of using artificial neural networks will offer robust opportunities for the market over the forecast period. Through such networks, professionals generally calculate the overhead price and predict the total expenditure of the project resting on the historical data backed with accurate information that saves the company’s money and time.”

This is only the surface of A.I. capabilities’ of interest to electrical contractors. From control systems, operational monitoring platforms, design simulation software and more, numerous applications have and will continue to benefit from A.I.

As sophisticated as it is, A.I. still cannot substitute for human intellect and the human mind’s ability to troubleshoot and find solutions. However, A.I. can greatly help most organizations in decision-making and bringing efficiency to systems and applications.

About the Author

Jim Romeo

Freelance Writer

Jim Romeo is a freelance writer based in Chesapeake, Va. He focuses on business and technology topics. Find him at www.JimRomeo.net.

Stay Informed Join our Newsletter

Having trouble finding time to sit down with the latest issue of
ELECTRICAL CONTRACTOR? Don't worry, we'll come to you.