California utilities should have used digital twin technology instead of power shutoffs

Northern California’s proactive power outages were not necessary last fall. Digital Twin technology can predict utility line failures and turn off power in milliseconds to avoid the potential of sparks igniting the surrounding area. 

Digital twin technologies are gaining traction across industries and use cases. Initially devised as a means of monitoring assets and production settings in manufacturing, this technology has quietly seeped into other verticals like hospitality, construction, and building management and soon, electricity delivery.

The premier problem digital twins will solve is predicting power grid failure, which would alleviate the social, economic, and political issues that resulted from efforts to reduce the incidence and degree of catastrophes, property loss, and deaths stemming from downstream effects of power grid failure—such as recurring wildfires.

Digital twins can allay these concerns because they’re based on real-time signals from a comprehensive set of factors that could be indicative of power grid woes related to environmental, meteorological, or technology concerns. Moreover, they can deliver accurate predictions for each of these factors well in advance of failure—in some cases as much as 28 days.

Implementing digital twins to predict power grid failure is the most effective means of ending the harmful effects of this occurrence, improving the electricity utility industry, and enhancing the quality of lives of its many customers.

How do operational digital twins work?

The predictive power of digital twins is implemented in two phases. Utility companies first build an operational digital twin of their entire environment, which becomes the basis for building another digital twin for predicting factors contributing to grid failure. Implementing asset digital twins is implicit to the creation of operational digital twins. Asset digital twins provide real-time data on the performance of infrastructure vital to maintaining power grids, such as transformers. By modernizing this infrastructure with sensors to monitor these datasets, organizations can build four dimensional models (digital twins) for them.

The chief advantage of operational digital twins is that they not only include assets, but also every other factor relevant to the production environment. Thus, organizations can utilize drones or other means of facilitating computer vision to monitor foliage or landscape issues. Specific modeling tools monitor the effects of people on production settings, while also monitoring various aspects of the weather, wildlife, supply chain, maintenance, and more. Once an exhaustive list of germane data points is assembled, analysis of this operational data provides an intelligent context for identifying bottlenecks and optimizing around any outcome — such as maintaining uptime, preventing gas leaks, or eliminating hazardous sparking.

Predictive digital twins

Operational digital twins provide insight into diagnostic information about what is happening or has happened within power grid environs. Predictive digital twins deliver prognostications of most of the factors modeled in operational digital twins to ensure organizations have enough time to act to maintain their objectives. These digital twins create a separate three-dimensional model that can identify predictive maintenance needs, for example, or supply chain issues up the pipeline. 

Predictive digital twins are substantially enhanced by incorporating various dimensions of Artificial Intelligence — both statistical and rules-based methods. Heuristic or rules-based engine techniques can identify constraints and how to deal with them. Expressions of supervised and unsupervised learning yield predictive and prescriptive value, illustrating subsequent steps to take to ensure a similar issue that would have caused a sparking transformer, for example, doesn’t occur again.

Ensemble model approaches (in which various machine learning models are combined for greater predictive accuracy) are especially relevant in the digital twin space. Topological data analysis provides an additional means of examining datasets so organizations can consider potential issues from a variety of perspectives. The pivotal aspect of predictive digital twins is they utilize real-time IoT data (and more) to issue predictions of events long before they occur. In manufacturing, predictive digital twins can prognosticate issues a month or more in advance. They can do the same for power grid failure in utility environments by predicting the occurrence of specific factors like the likelihood of fires starting, or gas leaking from individual asset components.

What are other benefits of digital twins?

The principal benefits digital twins provide for predicting power grid failure are important for two reasons. First, they offer the most comprehensive means of outlining each of the specific factors that determine whether or not grids will fail. They leverage low latent data sources in the IoT and others related to supply chain information and people that are equally important. Although there are alternative methods for predicting failure in power grids, few combine as many different data points as digital twins do.

Secondly, the boons of applying digital twins for predicting power grid failure are equally applicable to other utility companies and energy generation sites. The same implementation strategy of building an operational digital twin and then a predictive one can provide similar benefits for optimization in wind power, nuclear energy, and natural or refined gas facilities. Adoption rates for digital twins will surely increase for these use case in the coming decade, and likely will in several others, as well. 

Asset management is a summit track at DISTRIBUTECH and Digitalizing the Grid is a Knowledge Hub at the event. In each, you’ll find a plethora of educational sessions that explore these topics. If you haven’t registered for DISTRIBUTECH yet, do it today!

Previous articleHow SRP transformed an outdated vegetation management platform into a goal-breaking software solution
Next articleSmart move: Disaggregation and AI can empower utilities to empower their customers
Jans Aasman is a Ph.D. psychologist, expert in Cognitive Science and CEO of  Franz Inc ., an early innovator in Artificial Intelligence and leading provider of Semantic Database technology and Knowledge Graph solutions. As both a scientist and CEO, Dr. Aasman continues to break ground in the areas of Artificial Intelligence and Knowledge Graphs as he works hand-in-hand with numerous Fortune 500 organizations as well as U.S. and foreign governments.  Dr. Aasman has spent a large part of his professional career specializing in applied Artificial Intelligence projects, intelligent user interfaces and telecommunications research. He has gathered patents in the areas of speech technology, multimodal user interaction, recommendation engines while developing precursor technology for tablets and personal assistants. He was a professor in the Industrial Design department of the Technical University of Delft and a noted conference speaker at events such as Smart Data, NoSQL Now, International Semantic Web Conference, GeoWeb, AAAI, Enterprise Data World, Global Graph Summit, Text Analytics, and TTI Vanguard.

No posts to display