The mission of this group is to bring together utility professionals in the power industry who are in the thick of the digital utility transformation. 


AI, A Menace to Stability?

image credit: ID 159087096 © Kosssmosss |
Nevelyn Black's picture
Writer Independent

Nevelyn Black is an independent writer with a background in broadcast and a keen interest in renewable energy.  In the last few years, she transitioned from celebrity interviews and film shoots...

  • Member since 2017
  • 841 items added with 488,158 views
  • Nov 30, 2019

This item is part of the AI & Machine Learning in Utilities - Winter 2019/20 SPECIAL ISSUE, click here for more

In Aldous Huxley’s Brave New World, efficiency is paramount and every change is a menace to stability.  The ‘Savage’ rejects the 'World State' utopia and clings to ideals like inconvenience over comfort and independence over proficiency.  Fortunately, our society doesn’t match either extreme found in the novel but how much are you willing to give up or hand over to machines for comfort and convenience?   Today, Artificial Intelligence(AI) and Machine Learning(ML) promise to provide unparalleled efficiencies for more and more businesses.  In truth, AI and ML are already boosting productivity and efficiency in the energy sector.

Your access to Member Features is limited.

  • Duke Energy uses AI algorithms to safeguard its multi billion-dollar turbines by predicting potential disasters and shut down.  After implementing over 30,000 sensors the utility used machine learning to better identify areas most critical to its infrastructure maintenance and performance.  For example, a small change in normal behavior was detected in a particular turbine which alerted engineers to some loose bolts inside the flow sleeve, something that may have gone unnoticed without sensor data.
  • Georgia Power, a subsidiary of Southern Company, has been employing analytics to improve operations, cut costs and enhance customers’ experience.  Southern Company has considered new algorithms to access grid stability.  For now, they are working on developing and evaluating new analytics and artificial intelligence tools to generate new insights for improved decision support.
  • NextEra is using machine learning and predictive analytics to boost the functionality of wind turbines and reduce maintenance costs.  Florida Power & Light, a subsidiary of NextEra, identified unusual patterns in the functioning of plant combustion turbines using machine learning models.

Looking back, some of last year’s AI projections have come true.  From ‘Ethics in AI’ to concerns about ‘Machine Bias,’ we’re witnessing the cause and effect of Artificial Intelligence and Machine Learning across industries worldwide.  This year has certainly seen legal accountability, transparency, policy and the governance frameworks of AI come under scrutiny.   ML models deserve our undivided attention as they are now being used for decision-making such as hiring, mortgage loans, prisoner parole releases and the types of social service benefits applicants can qualify for.  Trying to get ahead of the issue, the World Economic Forum released a report to prevent discriminatory outcomes in machine learning


The challenges and concerns surrounding artificial intelligence are innumerable but so far the projected benefits far outweigh any growing pains we may experience.  Understanding the need for funding, the U.S. Department of Energy announced $15 million in funding for 23 projects to accelerate the incorporation of machine learning and artificial intelligence into energy technology with the DIFFERENTIATE program.  “The incorporation of AI and Machine Learning into our energy technology design and engineering processes has great potential to increase the productivity of our nation’s engineers and scientists,” said Rick Perry.  Despite plans to resign as Secretary of Energy at the end of the year, Perry conveyed his interest in pursuing AI in Energy by saying, “These DIFFERENTIATE projects truly work towards creating a competitive advantage that further positions the United States as the world leader in AI technology development.” Additional challenges for power companies are limited risk tolerance and lack of internal data science capabilities. Integrating new platform systems with traditional systems is a challenge for any company older than the dot-com era but uniquely so for utilities.  Shutting down operations to test new systems is simply not an option.  This doesn’t mean we have given up.  Currently, the most common applications of AI and ML in the energy industry include asset failure prediction, DER location optimization, customer churn prevention, safety incident prediction, and inventory management.  

Moving Forward

How can AI be more widely used in the industry?  In the past, we limited computers to storing and indexing data and now we are asking them to make decisions. Thanks to several successful applications, machine learning is gaining approval.  The majority of commercially proven applications focus on data or machine-learning/deep learning algorithms for better prediction.  An algorithm is a set of instructions designed to perform a specific task.  In this case, the algorithm gathers information and uses it to make decisions for us.  Within the energy sector, one application of machine learning is analyzing the data gathered and identifying strong predictors of demand during certain hours in the day.  This task had not been identified by internal  SMEs.  However, ML systems are pushing ahead, identifying demand, updating forecast models, improving error rates and reducing financial losses.

Data, Big or Small

A large quantity of accurate data is imperative to predicting behavior and demand.  Not having a good dataset or a well-curated collection of data to train an AI system will hinder performance.  Which will, in turn, undermine the trust companies have in artificial intelligence.  Therefore, the quality of the data impacts the success of any ML system.  Data must be not only collected but indexed correctly to ensure accurate outcomes.  An algorithm is only as good as its author.  That is, of course, if the author has been given the correct information in the first place.  Supervised or unsupervised algorithms are used to find and identify trends in large sets of data.  Supervised learning involves learning with labeled datasets to produce an output that is generic to that dataset.  Unsupervised learning involves finding the connections between unlabeled data or clustering that data. Machine learning algorithms rely on statistical bias, that is, existing data is compared to new data and predictions are made.  

Machine Bias

How do we avoid machine bias? Bias reflects problems related to the gathering or use of data, where systems draw improper conclusions about datasets, either because of human intervention or as a result of a lack of cognitive assessment of data.  One example of bias is the use of these algorithms in law enforcement. COMPAS, a machine learning algorithm used to determine criminal defendants’ likelihood to recommit crime provided inaccurate and biased predictions which were either due to a limited list of data categories, or inappropriate or invalid personal data.  More commonly understood, in the advertising on the webpage you're searching are ads based on data acquired from your search history.  However, this same data gathering algorithm may be inadvertently showing women lower paying jobs than men.  A study by AdFisher revealed that men were six times more likely than women to see Google ads for high paying jobs, leaving women out of the applicant pool. Correcting these algorithms to eliminate bias must be first on our to-do lists.  Learning from the mistakes of others can only help utilities moving forward with machine learning systems.

Data is the New Oil

“Data is the New Oil” according to a 2017 broadcast by the Economist.  Data is crucial so the issue of compliance has surfaced.  Companies have the data but do they have permission to use it?  With Facebook before Congress, privacy protection and access to data privacy are not just the hot topics of late but are actively changing policy.  Companies are responsible for getting consent to use systems that gather customer information.  In other words, data ownership is a-must for utilities implementing ML systems.

Utility Utopia

With computers and systems learning over time, they can optimize and perfect tasks in such a way that changes how we do things forever.  AI in energy calls into question Huxley’s utopian theory that ‘every change is a menace to stability.’  Machine Learning is changing the game.  It will replace jobs as it widens our capabilities.  Will this change be a 'menace to stability' or more you the point, reliability?  AI and ML should provide accuracy, efficiency, and real time feedback that trumps any inconvenience by a brief interruption to ‘stability.'  It is important to note, implementation is not one size fits all.  ML systems require case specific information and often times patience, flexibility, and extensive testing. Be realistic.  Your utopian utility may take time.  Start simple.  Focus on a well-defined goal.  Consider the scalability of the project.   And most of all, obtain, own, clean and verify the data.

Ben Schultz's picture
Ben Schultz on Dec 1, 2019

NextEra is using machine learning and predictive analytics to boost the functionality of wind turbines and reduce maintenance costs. 

How does this so-called boosting happen?

As a side note, the idea of turbines shutting down via machine learning is a brilliant one. Better yet, the alogrothm could be applied to entire farms, not just individual turbines.

Nevelyn Black's picture
Nevelyn Black on Dec 2, 2019

Hi Ben, NextEra is using AI-driven tools to monitor equipment for smooth operations and to prevent unexpected disruptions.  This should lead to reduced downtime and increased productivity.  Space Time software is another digital tool being used to boost productivity at NextEra.  The software uses machine learning for performance optimization, real-time diagnostics and troubleshooting, and maintenance crew scheduling.  By using machine learning based analytics, variables like weather and traffic are also optimizing operations.

Matt Chester's picture
Matt Chester on Dec 2, 2019

Machine Learning is changing the game.  It will replace jobs as it widens our capabilities.  Will this change be a 'menace to stability' or more you the point, reliability?  AI and ML should provide accuracy, efficiency, and real time feedback that trumps any inconvenience by a brief interruption to ‘stability.

The replacement of jobs with AI is definitely a trend to watch, but this is of course not unique to the power industry and will be an overarching trend all of society will be dealing with in the coming decades. 

Nevelyn Black's picture
Thank Nevelyn for the Post!
Energy Central contributors share their experience and insights for the benefit of other Members (like you). Please show them your appreciation by leaving a comment, 'liking' this post, or following this Member.
More posts from this member

Get Published - Build a Following

The Energy Central Power Industry Network is based on one core idea - power industry professionals helping each other and advancing the industry by sharing and learning from each other.

If you have an experience or insight to share or have learned something from a conference or seminar, your peers and colleagues on Energy Central want to hear about it. It's also easy to share a link to an article you've liked or an industry resource that you think would be helpful.

                 Learn more about posting on Energy Central »