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. 


To risk or not to risk? that is the question – AI is the answer

image credit: © SJMPhotos |
Andrew Skumanich, Ph.D.'s picture
Founder and CEO, SolarVision Consulting

Dr. Andy Skumanich is a successful Silicon Valley tech entrepreneur. He is currently CEO and founder of SolarVision Co, which is a technology business development company focused on alternative...

  • Member since 2017
  • 3 items added with 7,069 views
  • Dec 8, 2021

This item is part of the Data Analytics & Intelligence - December 2021 SPECIAL ISSUE, click here for more

Written by: Dr. Andy Skumanich and Dr. Manny Ghiassi

With apologies to Shakespeare, the current state of the utility sector is in a quandary.  Historically the energy domain was built to be a low-risk-taking domain.  And understandably, they became good at not-taking-risks.  However, as with Mr. Shakespeare, those days are gone.

Now the real dilemma – what about the risk that comes with being risk adverse.  Is that an oxymoron?  No, it is a legitimate consideration for present day utilities.  Utilities are under increasing pressure to reduce costs while still maintaining reliability and all the while reducing risk.  Electricity markets try to strike a balance between reliability and affordability, but the latter is in a short-term mode, and in need of forward-looking investments.  Many utilities continue to try to maintain the old ways of proven solutions.  For example, they have a set schedule for trimming vegetation which could impact transmission lines, and they address hardware issues when this equipment presents a problem or failure.  They may ramp up personnel ahead of bad weather, but is there much pro-active planning for predicted storms and the possible impacts?  We recently saw that the Texas grid had some weather-related issues during a deep freeze, due in part to the complexities of substantial wind power (at 22.8% in 2020) which relegated standard power plants to lower utilizations and perhaps lower investment in upgrades.  Portfolio forecasting could help anticipate production trends and could benefit from AI/ML.  In California, there are now Public Safety Power Shutoffs.  A new PSPS may be brought on when it becomes necessary to turn off electricity during very dry and windy conditions, combined with a heightened fire risk.  Although a step in the right direction, however, these show just how limited the approach is for identifying and developing pro-active capabilities, which can save money in the long run. 

Your access to Member Features is limited.

This is where AI and Machine Learning become necessary for utilities.  AI/ML enables: predictive maintenance, streamlined operations, anticipation of equipment failure, more precise disruptive weather event forecasting, etc. [1]   It provides for pro-active management, including grow-out of an energy generating portfolio.  For one simple example of cost-cutting vs. pro-active management, consider vegetation control.  There are now almost 2 dozen drone service companies, which can provide drone equipment or inspection, so that monitoring of vegetation can become real-time, as-needed, instead of by a fixed schedule which may be too often (more expensive) or too infrequent (expensive if a fire results).  The drone data is however big-data and requires AI/ML types of algorithms to extract the image-based information of where issues are developing, and trimming needed.  Importantly, implementing this pro-active mode of AI/ML & drone data is a low risk compared with the reactive response of power shutdowns or to fires which can be devastating.  So, the risk of NOT using AI/ML and drones becomes much higher.   As another example, transformers can be monitored for operating signatures, which again with the right AI/ML analysis can indicate incipient issues that can be caught before a breakdown or an outage.  These are just some of the modes where the risk of implementing AI/ML and developing new approaches are less than the other risks that can occur by using standard operating procedures.  The AI/ML can mitigate risks leading to an overall reduction and many examples are already out there. [2]


One of the key aspects to relying on AI/ML for any operational or forecasting aspect comes down to trust.  Can you trust the results?  Any complex problem can be addressed with lots of AI/ML resources and model training, but ultimately can you accept the results as accurate and bank on them.  The answer is “it depends”.  There are a lot of issues with data sets, training the algorithms, and the selection of algorithms.  Two key issues include (1) over-fitting the data, or (2) tuning to the noise.  These are real concerns and need to be addressed by an adequately sophisticated AI/ML approach.  However, it is indeed possible to get results with high accuracy which can be “trusted”.  As an example of some of our prior work, figure 1 shows the accuracy of prediction of the electricity demand for a utility over an extended period.[2]

In this engagement with Taiwan Power Company, the Ghiassi AI/ML modeling gave highly accurate Predictive Analytics with mean absolute percent error below 1%,  which is better than the standard approaches of multiple linear regression, and of traditional Advanced Neural Nets, by >1000% & >300% respectively.  In this example the accuracy is >99% in terms of the forecasted vs the actual data, and with the Ghiassi algorithm analysis there is both no over-fitting, and no tuning to the noise.  (See the last section for a discussion on achieving 100%.)

Figure 1.  Excellent Forecast of Total Power Sales for an electrical utility, by Ghiassi AI/ML [3]

Figure 2.  Another example of >99% forecast accuracy with the Ghiassi AI/ML [4]


A bit on the technical side, the Ghiassi (author’s) algorithms performed better than alternatives without over-fitting while data sets for training were kept separate from the testing (out-of-sample) data set.  Current published research presents a systematic and critical review of forecasting methods used in 483 utility forecasting models and establishes that ANN is the most utilized approach and outperforms alternative statistical methods in forecasting key parameters such as e.g. energy demand.  The other approaches suffer from long training time, unstable optimization processes, or sensitivity to hyper-parameters.   Furthermore, in the ANN space, the Ghiassi AI/ML set has been shown to be superior to traditional ANNs (Velásquez 2012, Olssonz 2017).  According to recent studies: using accuracy metrics such as mean absolute percentage errors results, the Ghiassi model has better performance than the regression model, existing traditional ANN models, SVM with genetic algorithms (SVMG) model and SVM with immune algorithms (SVMIA) model.   (Wang 2010, Zheng 2014)   Current studies support the Ghiassi algorithm’s advantages. (e.g. Biswajit 2018)    


Nothing is 100%, well except for death & taxes, although some even dispute both of those (but I digress).  And as our data is an example, AI/ML accuracy can be 99% and doesn’t need an IBM Watson level of capability.  This is the indication that adequate accuracy can and has been achieved without over-fitting.  With this kind of accuracy, improved implementation will grow with the learning curve, as the utilities develop a trust in the results and see the advantages for pro-active postures.  This is similar to many other industry learning curves and adoption.  The main takeaway is that it is now a bigger risk to not take the risk on AI/ML.

So not to be too morbid, Shakespeare’s Hamlet contemplates death and suicide, bemoaning the pain and unfairness of life but acknowledging that the alternative might be worse.  Doesn’t that sound a bit familiar? 

To risk, or not to risk.  That is indeed the question, but at least you know the answer (to within 99% certainty).


[1] M. Ghiassi and A. Skumanich, "On the use of AI as a requirement for improved insolation forecasting accuracy to achieve optimized PV utilization"

[2] A. Skumanich and M. Ghiassi, “Achieving significant cost reduction in solar through the targeted use of AI and Machine Learning”

[3] Ghiassi, M., et. al. (2006).  “Medium Term System Load Forecasting with a Dynamic Artificial Neural Network Model,” Electric Power Systems Research Vol. 76, 302-316

[4] Ghiassi, M., et. al. (2006).  “A Dynamic Artificial Neural Network Model for Forecasting Time Series Events”. International Journal of Forecasting, Vol. 21, 341.

Zac Canders's picture
Zac Canders on Dec 13, 2021

Hey Andrew - nice article. True story but about 8 years ago now, my company (DataCapable) was recognized as the 1st to bring AI to the industry. Today, nearly all the large IOU’s benefit from our real-time AI-based threat detection models! It’s really amazing to see how far the industry has come and totally stoked to see people writing about the power of AI! 

Looking forward to connecting more 


Andy Skumanich's picture
Andy Skumanich on Dec 16, 2021

Count yourself in as one of the pioneers.  Do you have any suggestions how to encourage more AI adoption?  Your experiences would be helpful.

Zac Canders's picture
Zac Canders on Dec 20, 2021

I love this question and geeze it has me wondering if I should do a piece related to the question (ya know what, I think will as you got me inspired!). The biggest advice I have is to believe in what you are doing. When we got started there were so many doubters on the value / role of AI. It really has me thinking about some of the teams that are doing wild stuff with AR/VR + quantum + lidar and how they are probably facing early-stage doubt + criticism from folks that have either had a bad initial experience or is a bit rooted in the "if it works why change it". I think the biggest recommendation on the AI front is to not over-state it, or over-sell it. Focus on incremental wins and telling those stories and areas for improvements. Transparency can be awesome...

Andy Skumanich's picture
Andy Skumanich on Dec 21, 2021

Thanks Zac ! very good points.

Varun Perumalla's picture
Varun Perumalla on Dec 14, 2021

AI/ML has always been there, but was overlooked until recent years and since then it has been a trend. With that said, there are many use cases that can be tackled using these technologies to solve real world issues in utilities/power systems. Especially, the burden is on the academia and industry to ensure the young electrical engineer professionals should be trained to have power system skills and as well as programming skills like SAS, R and Python. The value one get from these professionals trained in these two areas will be tremendous. 


As we all know utilities are risk averse and that mindset needs to be changed from the leaders for adopting more ML/AI in utilities.

Andy Skumanich's picture
Andy Skumanich on Dec 16, 2021

Excellent point since AI experts by themselves are not enough - you absolutely need to develop the Domain Experts - otherwise the model training is meaningless.  For good implementation you need 3 things: Data, AI/ML engine, Domain Expertise.  Do you have any thoughts on how to adjust that mindset? 

Vladimir Vinogradov's picture
Vladimir Vinogradov on Dec 16, 2021

Hello Andrew. Artificial intelligence is a very good solution and the right trend. But what will you do if your risks materialize and you don't have a reliable source of energy? This poses big problems for many people, as happened in Texas and continues in Europe today. This means you need a reliable and inexpensive power source. Artificial intelligence is not that kind of energy source.

Andy Skumanich's picture
Andy Skumanich on Dec 17, 2021

Good question - and it's a matter of how to balance things.  By spending increasing amounts of money, the risk can be reduced but you get the "hockey stick" problem.  This has been the case in trying to get 100% Renewables which get more and more expensive closer to 100%.  The reliability has to be a dynamic condition which increases the reliability.  One mode that's working is DER (Distributed Energy Resources) which hedges the bet by dispersing the locations.  Also, more forecasting and predictive analytics can dramatically reduce the types of big problems that we'll be seeing more and more.

Vladimir Vinogradov's picture
Vladimir Vinogradov on Dec 22, 2021


Andrew Skumanich, Ph.D.'s picture
Thank Andrew 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 »