The challenge of inconsistent flow of wind and solar energy is getting help from artificial intelligence, helping companies predict and adapt, saving them money.
Ten years ago, I was engaged in the writing of an energy power grid report that was part of a national initiative to assess the health of our electrical energy grid and its resilience. Assets like wind farms and contemporary fossil and nuclear fuel systems were in place for energy distribution, but to my surprise there was also equipment in the grid that dated back to the 1890s and was still in production.
SEE: TechRepublic Premium editorial calendar: IT policies, checklists, toolkits, and research for download (TechRepublic Premium)
I began to understand the challenges of using renewable energy such as wind and solar when it came to assessing energy supply and demand and ensuring there is enough on-hand energy to power the homes and businesses that are relying on it.
When utilities were using gas, coal, or nuclear energy to power the grid, the in-flow of that fuel from its source was consistent, so it was easy to assess supply and demand on any given day and to deliver the energy needed to power homes and businesses.
With renewable energy sources such as solar and wind, the consistency of that flow just wasn’t there. What if the wind gusted to 40 mph one day, and was perfectly still on the next day? What if the solar cells harvesting sunlight captured a full solar load on a bright, sunny day, and nothing on the next rainy day? The ebbs and flows of renewable energy into the grid wreaked havoc on components in the energy grid, causing equipment to fail because of sudden uncontrollable bursts of energy.
SEE: Fighting fire with AI: Using deep-learning to help predict wildfires in the US (TechRepublic)
Today, the cost of infrastructure damage to utilities remains enormous. “It’s roughly half a million dollars to replace one failed inverter, and the life of a $25 million battery can be cut in half because of the energy spikes alone,” said Chad Steelberg, CEO of Veritone, which makes an artificial intelligence (AI) operating system. “If you are running a hybrid energy grid with both traditional and renewable energy flowing into it, the tasks of gauging supply and demand and marshaling all of your energy sources to fill it became infinitely more complex.”
The question is, How do you push intelligence back into the grid to ensure that you’re not going to damage your infrastructure?
“AI can operate on every phase of energy grid planning and management, from forecasting and infrastructure protection to functional optimization and energy arbitrage (purchasing and selling energy),” Steelberg said.
With forecasting, the AI looks at historical data and employs infrared cameras at the sites of solar and wind farms. This provides visibility into how well the assets are functioning. There is a controller that assesses how energy collected from both traditional and alternative sources can most expeditiously be pushed through the grid without damaging infrastructure.
On top of this is an optimization engine for energy supply and demand. Its AI mission is to collect and deliver the highest quality of energy from diverse energy sources at any given point in time. If, for example, a wind farm is underproducing at the time it is needed, the AI would shift to look for other energy sources that will guarantee an unbroken flow of energy.
Finally, there are times when energy companies trade with each other. If one company needs additional energy and another has a surplus, an AI arbitrage engine can quickly facilitate energy buys and sells between companies.
“We’ve found that there is a receptive market,” said Steelberg, who has lived through recent energy blackouts that might have been avoided or mitigated with newer energy management approaches.
Can AI solve all of the energy grid’s problems? Likely not. But as more grid equipment providers supply digitalized equipment that can work with AI, and as legacy system vendors reengineer their products with digitalization, there is greater potential to use AI as an energy supply-and-demand forecasting and optimization tool for the grid.
This will reduce the number of blackouts and should propel the energy grid into greater use of renewable energy sources.