When the University of Michigan solar race car team competes in the Bridgestone World Solar Challenge in the Australian Outback beginning October 18, 2015, it will have a partner in IBM.
The solar race car team will be able to employ IBM’s cognitive computing to help determine how much solar power will be available during the competition. The IBM technology can help predict important information about cloud cover and wind patterns in real-time. Over the course of the 1,800-mile race, having this information can help the racing team make better decisions to ration the car’s battery reserves and electricity consumption.
Obviously, this particular race is about endurance and the strategy to generate as much electricity as possible, while also conserving for cloudy and windy days.
“Our goal is to design, engineer, and race the best solar-powered vehicle in the world. Predicting solar radiation plays a huge part in designing a strategy for solar car racing. IBM’s forecasting technology will help our team adapt and optimize our approach in real-time, and we expect it to provide a true advantage over the course of the race,” explained Leda Daehler, chief strategist on the UM Solar Car Team.
IBM worked previously with the U.S. Department of Energy to develop better solar forecasting. Reducing uncertainty about the amount of sunshine that is available during a day is quite favorable to anyone who depends upon solar power systems for electricity, and cognitive computing can improve solar and wind forecasting by about 30%.
For the race, the IBM technology can help the students predict weather and sunlight two to three days in advance, which will help them with their race planning as they progress through the event. Having extra information may prove to be a competitive advantage.
We may think of solar power systems as being mainly the solar panels and batteries, but smart solar systems can integrate various forms of data that improve electricity production and even optimize it. For example, big data, as it relates to weather patterns, could be useful one day to homeowners with smart solar systems to help make suggestions for electricity consumption.
Image Credit: University of Michigan