Strategic Placement Is Key to EV Charging Station Utilization
Photo courtesy Toyota Motor Corp.
ITHACA, NY—Finding the best place to install electric vehicle charging stations can be challenging. In order to be profitable for investors, they must be convenient for drivers. Random placement is less ideal for both parties.
Engineers at Cornell University recently tackled the issue and discovered that an equal mix of two different kinds of stations—one that charges at a medium speed and another that charges more quickly—may be the optimum solution.
“Improving charging station infrastructure is essentially the chicken-and-the-egg problem,” says Oliver Gao, Ph.D., a professor of civil and environmental engineering at Cornell. He and his colleagues applied Bayesian optimization, a mathematics strategy that uses past attempts at optimization to inform each subsequent attempt. It results in a much faster and more productive analysis.
“Placing publicly available charging stations around cities sounds like a simple thing, but mathematically, it’s actually very hard,” claims Yeuchen Sophia Liu, Ph.D., an operations researcher in Gao’s laboratory who worked on the project. That’s because simple models don’t allow for the complexity of thousands of possible driver decisions, not to mention factors like traffic and road characteristics.
“Economically strategic placement of charging stations could play a pivotal role in accelerating the transition to zero-emission vehicles,” says Liu.
The Cornell engineers set up an algorithm that used Bayesian optimization to analyze data from the Atlanta region, which is home to around 6 million people. They studied the behavior of 30,000 vehicles on more than 113,000 simulated trips, forecasting a variety of commuter traffic patterns. The algorithm found an optimal placement using only 2 percent of the runtime of existing benchmark methods.
“The Bayesian optimization model algorithm allows us to simulate millions of individual behaviors, while at the same time find answers efficiently and quickly,” explains Liu. “This enables the use of the algorithm on a more complex, real-world scale.”
Looking for quick answers on assembly and manufacturing topics? Try Ask ASM, our new smart AI search tool. Ask ASM
According to Liu, medium-speed “level-2” commercial charging stations and direct-current, fast-charging “DCFC” stations serve different needs. For instance, drivers who park for 20 minutes to run into a grocery store are likely to choose fast-charging spots. But, if someone is parking for several hours, they will likely select a level-2 station.
In addition, a sensitivity analysis demonstrated that factors such as the size of the EV market and price can impact the optimal placement and profitability of a charging infrastructure project.
Looking for a reprint of this article?
From high-res PDFs to custom plaques, order your copy today!
