Optimizing EV Charging Station Placement for Maximum Efficiency

Cornell engineers have developed a model to optimize the placement of electric vehicle (EV) charging stations, aiming to balance driver convenience with investor profitability. The study was published in Applied Energy.

A lack of widely available and conveniently located charging stations can deter consumers from purchasing EVs. Conversely, without a significant number of EV owners, public charging stations struggle to be profitable, which can limit their availability.

Improving charging station infrastructure is essentially the chicken-and-the-egg problem.

Oliver Gao, Study Co-Author, Howard Simpson 1942 Professor, Civil and Environmental Engineering, Cornell Engineering

The research team found that in urban areas, strategically positioning a balanced mix of two station types—one with medium charging speed and another with faster capabilities—increases the likelihood of driver use. This method boosts investor profitability by 50 % to 100 % compared to current random placement strategies.

Placing publicly available charging stations around cities sounds like a simple thing, but mathematically, it’s actually very hard.

Yeuchen Sophia Liu, Study Lead Author and Operations Researcher, Cornell Engineering

According to Liu, traditional models fall short because they cannot account for the complexity of thousands of potential driver choices alongside factors like traffic and road conditions.

To overcome this, the team used Bayesian optimization—a technique from six decades ago that uses past optimization attempts to inform new ones. This approach allows for faster and more efficient analysis and has recently become popular in machine learning algorithms.

The Bayesian optimization model algorithm allows us to simulate millions of individual behaviors, while at the same time, find answers efficiently and quickly.

Yeuchen Sophia Liu, Study Lead Author and Operations Researcher, Cornell Engineering

The team developed an algorithm utilizing Bayesian optimization to analyze data from the Atlanta area, which has a population of around six million. They examined the behavior of 30,000 vehicles across more than 113,000 simulated trips, modeling diverse commuter traffic patterns.

The algorithm identified an optimal charging station placement while using only 2 % of the runtime needed by existing benchmark methods.

This enables the use of the algorithm on a more complex, real-world scale,” Liu said.

The team found that medium-speed "level-2" commercial charging stations and fast-charging "DCFC" stations serve distinct needs. For instance, drivers stopping for about 20 minutes—such as during a quick grocery run—are more likely to use fast-charging stations, while those parked for extended periods, like at work, typically prefer level-2 chargers.

Sensitivity analysis further showed that factors like the size of the battery electric vehicle market, charging preferences, and costs greatly influence optimal station placement and profitability.

Liu highlighted the importance of these insights, especially as eight U.S. states have adopted California’s Zero Emission Vehicle program, aiming to replace gasoline-powered cars with at least 3.3 million zero-emission light-duty vehicles by 2025.

Economically strategic placement of charging stations could play a pivotal role in accelerating the transition to zero-emission vehicles.

Yeuchen Sophia Liu, Study Lead Author and Operations Researcher, Cornell Engineering

Alongside Liu and Gao, the co-authors include Mohammad Tayarani, a visiting scientist in Gao’s lab, and Fengqi You, the Roxanne E. and Michael J. Zak Professor in Energy Systems Engineering at Cornell Engineering. This research was funded by a grant from the U.S. Department of Transportation.

Gao and You also serve as senior faculty fellows at the Cornell Atkinson Center for Sustainability.

Journal Reference:

Liu, Y. S., et al. (2024). Bayesian optimization for battery electric vehicle charging station placement by agent-based demand simulation. Applied Energy. doi.org/10.1016/j.apenergy.2024.123975.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.