At this moment, the lights are on around the country in homes and workplaces. Most don’t realize, perhaps take it for granted, that those lights come on because of the hard work of dispatchers operating one of the most important manmade systems ever built, the national electric power grid.
Without oversimplifying the process too much, this happens because of a complex network of thousands of coordinated individuals in energy control offices across the country. Each office serves as a part of an electric grid nervous system of interconnected generators and transmission lines that deliver power to end users.
For utilities, building accurate estimations of the electricity demand of their customers is critical. Inaccurate forecasts can result in significant financial losses and/or outages for consumers, but unfortunately, the ability to accurately predict demand even within the very short-term is extremely difficult to do. Operators, schedulers, and marketers must make this kind of high-stakes decisions every day, oftentimes based on tedious, manual and error-prone methods.
Like many utilities across the country, the City of Independence, Missouri Power & Light (IPL) found themselves in this difficult position. The department is responsible for predicting the amount of power IPL’s customers would consume each day and buy the required energy at the lowest prices possible. Ultimately, their goal was to ensure customers’ needs were met, while maximizing cost savings on behalf of the city.
To do this, the IPL’s System Operators used an off-the-shelf product alongside their historical data. Every morning before the markets opened, they would study weather forecasts, recent days’ activity, and historical similar day data to build a load profile for the next day. This was time-intensive, manual work, but all too common in the utility industry. Due to the highly dynamic nature of power demand, it was also necessary for the System Operators to constantly update their predictions throughout the day. Ultimately, IPL was running an 8% average error rate.
One of the system operations supervisors knew there had to be a better, easier way to build load forecasts that would save the city time and ultimately the residents, money. They turned to a product from Pattern Recognition Technologies Inc. (PRT), a company that provides load, price, wind, and solar forecasts based on highly adaptive and dynamic machine learning algorithms. Using this artificial intelligence system meant IPL received highly accurate load forecasts updated several times per hour. Now, IPL no longer spent their mornings building load predictions by hand. Instead, PRT’s sophisticated software built technology-driven forecasts that they still had the ability to review and approve.
Within two weeks, IPL’s error rate dropped from 8% to 6%. The improvements continued as PRT’s algorithms were able to “learn” from past load behaviors and build increasingly accurate forecasts. Within a year of using PRT, the error rate was down to within 4%, resulting in annual savings of over $100,000 to the city. IPL’s Operations team was able to stop wasting time on manual activities and rely on technology to do the work. With more accurate forecasts and their team’s time used more efficiently, IPL is creating value and cost savings that they can pass on to their ratepayers.
“The value added by Patter Recognition Technology’s to IPL’s system operations made an immediate impact that continues every day,” said Gary, System Operations Supervisor, Independence Power & Light.
Nearly every industry has its periods of monumental advancements that transform how things were done in the past, resulting in a more efficient, less expensive solution. The tractor improved farming, the automobile enhanced transportation, and I believe artificial intelligence is on the cusp of revolutionizing power. But these historical moments didn’t happen in an isolated vacuum– they took collaboration and communication.
It’s been said that those who cannot remember the past are doomed to repeat it. If we learn from others, we need not commit the same costly mistakes.
—Sogand Shoja is senior vice president at Drillinginfo. Prior to joining PRT in 2001, she was an Engineering Manager at Honeywell Optoelectronics. Her extensive experience in process development, optimization and years of teaching statistical thinking to analyze and improve products has been key to implementing effective solutions for PRT’s clients. Ms. Shoja has played and continues to play a fundamental role in PRT’s overall marketing and strategic development efforts. She also serves on the board of trustees for Dallas Museum of Art and KERA, a National Public Radio member station serving North Texas.