Besides its adding to our road rage and shouting at our steering wheels, sitting in traffic can negatively affect one’s health. Studies have found that unpredictable traffic compromises psychological wellbeing as well as respiratory problems from being exposed to car exhaust. Not only that, but excessive traffic also contributes a great deal to carbon dioxide emissions.
A new computing model makes it easier to predict traffic and makes it operate more efficiently.
Streamlining traffic
A team from North Carolina State University set out to create an algorithm to optimize traffic prediction models. Existing models assess when and where there will be heavy traffic, and these are used in lots of areas, such as on GPS apps like Google Maps, to avoid gridlock.
“These models work well, but the specific forecasting questions can be so computationally complex that they are either impossible to solve with limited computing resources, or they take so long that the prediction only becomes available when it is no longer useful,” says coauthor Ali Hajbabaie, an assistant professor of civil, construction and environmental engineering at North Carolina State University.
Hajbabaie and other researchers used an algorithm that streamlines complex computing challenges but could not address traffic. The team modified the algorithm so that instead of addressing traffic as one big computational problem it breaks the traffic model up into a collection of smaller problems that can be solved at the same time.
This new model significantly improves computational time compared to previous models and actually improves accuracy with more complex traffic problems. This new model actually outperforms the benchmark standard of algorithms used in most traffic-predicting software.
“At this point, we’re open to working with traffic planners and engineers who are interested in exploring how we can use this modified algorithm to address real-world problems,” said Hajbabaie.
Source Study: NC State University News — Researchers Find Way to Make Traffic Models More Efficient | NC State News (ncsu.edu)
