Skip to main content

The Role of Artificial Intelligence in the Grid

There’s no shortage of concerns and excitement around artificial intelligence technology. Once considered science fiction, it’s no secret AI faces the stigma of apprehension. But with any threat also comes immense opportunity. And like any other powerful tool, it can be applied in different ways. It is expansive in nature and a construct that is applicable to various industries and multiple domains. For the purposes of this blog, we will explore AI exclusively in the context of its ability to transform the future of the grid within the energy industry.

How Does It Work?
To best appreciate what AI can do for us, it’s important to understand how it works. To simplify this, let’s think about how a human brain works foundationally. Consider a human’s senses: we have eyes, ears, a sense of touch – and all these senses collect information, and we have hands, legs, etc. to take actions as actuators. That information, or data, is then broken down by the human brain to determine our surroundings, experiences, and learnings. Artificial intelligence utilizes the human brain-like functionalities using what we call “models” - which are designed to perform data science tasks and specific analysis. These algorithms are programmed to recognize patterns and use that data to essentially make decisions.

In an intelligent machine, AI processing has sensors as inputs and actuators as outputs. In developing AI, we are essentially training and programming the machine with various scenarios of inputs and outputs. Much like how a human learns that you can’t touch hot surfaces through the experience of getting hurt as the outcome, machines acquire learnings based on the inputs and outputs developers provide – this is called training the model. Once the training is complete, a test is performed with pass/fail criteria, creating predicative algorithms. The more data the machine receives, the more accurate the forecasts and analysis can be.

The Digital Twin
One element of AI is Digital Twin technology. A Digital Twin is a digital model designed to imitate a physical object, system, or process. The physical product is outfitted with sensors that gather intel and then apply it to the digital copy. Digital Twin technology is being used within the power industry primarily for detection purposes related to cybersecurity and troubleshooting of the grid. GE has gone beyond detection. With GE’s Digital Ghost technology, we’ve enabled localization, forecasting, detection, and neutralization – helping to facilitate the energy transition as we move towards the grid of the future and the associated challenges of the Energy Trilemma.

The Digital Ghost
Let’s back up a bit. AI has many functions and can be applied to many applications – ranging from cyber-defense to asset performance management – and multiple domains such as renewable generators, to transmission and distribution. And as global grid demand grows, so does the computation of power: not only are there more machines, but we have the ability to add more information to more machines. With that said, many critical infrastructure such as electric power grids are operated via central control systems. These control systems act like the brain of the network through data collection from sensors. Due to the critical nature of these assets, protection and safety of these assets is imperative. GE Global Research developed Digital Ghost technology which can go beyond detecting anomalies in the grid system. It has the ability to localize the anomaly and neutralize the impact. With modernization and digitalization of the grid, artificial intelligence has the power (pun intended) to make great strides and solve some of the challenges our modern networks are facing.

During the last decade, many companies have escalated their adoption of AI technology and increased related investments.  It’s clear that artificial intelligence is here to stay – within our industry and beyond.

What do you think: can AI help us build something that will solve the Energy Trilemma?

About the Author

Dr. Mital Kanabar is the Senior Director of Innovation at GE Vernova’s Grid Solutions’ Grid Automation business in Toronto, Canada. He has more than 15 years of power industry R&D experience, holds more than 20 international patent applications, and has published more than 50 articles. Mital is also serves as a Chair and Vice-Chair of three Working Groups at the IEEE PES Power System Relaying Committee. Mital focuses on customer-centric innovations and collaboration to accelerate Technology Readiness Levels and validate Cost-Benefit Analysis. He has led R&D efforts in digital substation and software systems, renewables integration algorithms, synchrophasor applications, distributed energy resources, and microgrids. He holds a Ph.D. from Western University and degrees in electrical engineering from Sardar Patel University and the Indian Institute of Technology.

Profile Photo of Mital Kanabar