Get into a cab and it’s safe to assume the driver knows the ins, outs, shortcuts and potential traffic tie-ups between you and your destination. That kind of knowledge comes from years of experience, and IBM is taking a similar tact that blends real-time data and historical information into a new breed of traffic prediction.
IBM is testing the new traffic-management technology in a pilot program in Lyon, France, that’s designed to provide the city’s transportation engineers with “real-time decision support” so they can proactively reduce congestion. Called Decision Support System Optimizer (DSSO), the technology uses IBM’s Data Expansion Algorithm to combine old and new data to predict future traffic flow. Over time the system “learns” from successful outcomes to fine-tune future recommendations.
The company’s technology allows traffic engineers to quickly take action based on constantly updated information, such as putting detours in place or providing alternative routes to get traffic moving after a snag. They’re unable to do this now, according to IBM, since most metro traffic management centers rely only on video feeds and color maps showing real-time traffic conditions. Jurij R. Paraszczak, director of Smarter Cities IBM Research, says this means traffic engineers don’t have a “360-degree view” of traffic, and depending on predefined responses or making reactive decisions, they don’t always fully take into account all current and future patterns.
“Rather than pulling all the data together and displaying it in one place where people make decisions on to what to do with it, the idea is to pull the data, display it and then provide tools to drive what-ifs,” Paraszczak told Wired. “The idea is to help them make decisions.”
DSSO takes into account not only a city’s current, historical and predicted future traffic patterns, but it also fills in the blanks where information doesn’t exist. “In areas where there’s not as much data as you’d like to do a statistical measurement,” adds Paraszczak, “we build a flow model that connects to the area we do know well. Based on these statistics, we’ll provide a prediction as to what traffic volume to expect.”
When an incident occurs, DSSO allows traffic engineers to analyze different scenarios on how to resolve the problem and predicts the outcome of, say, adjusting traffic signals, opening up another lane and routing traffic using statistical analysis.
IBM unveiled the technology at Smart City Expo and World Congress in Barcelona last week. Paraszczak can’t say when (or even if) the pilot will be extended to more cities, but he noted that IBM believes the technology is ready for drive-time and plans to prove it on Lyon’s roads. “There’s many ways to go to market,” Paraszczak says, “but testing it in the marketplace is the best way.”
Via Wired
