Untangling airports using open source tools on Microsoft Azure

Untangling airports using open source tools on Microsoft Azure

Scientists from the Universities of Stirling and Nottingham in the United Kingdom tackled the knotty problem of delays on airport taxiways, where planes are entering or leaving runways. Sandy Brownlee, PhD, and Jason Atkin, PhD, collaborated with Manchester Airport to use cloud computing to model the complex data from many airports worldwide. The team created open-source tools using Linux on Microsoft Azure to expand these insights and create new algorithms, sharing these on Github. The team is helping Manchester Airport to reduce delays, save money and lessen any environmental impact.

Tim Walmsley helps the third-largest airport in the United Kingdom – Manchester - manage an estimated 23 million passengers per year. To successfully plan airport operations and growth, he asked for data science help from university researchers, who specifically sought to gain insights from modeling the movements on taxiways, to and from the runways. “Aviation is an industry that’s growing. So there are lots of ways that the industry is trying to tackle the impacts that that growth could bring. The Airport Optimization Project feeds into that,” Walmsley, Environment Manager for Manchester, explained.

Sandy Brownlee, a senior research assistant at the University of Stirling, began helping Manchester Airport by searching for specific data on what is sometimes called “ground movement” or taxiing to populate a model. At first, he was frustrated because individual airports did not want to share everything with him. What he discovered, however, is that he could access public data using Flight Radar 24 and Open Street Map for dozens of airports worldwide. Jason Atkin, PhD, of the University of Nottingham, partnered with Brownlee to help model how taxiways can be leveraged to make airports more efficient.

Taxiways connect everything
The time aircraft spend getting to and from runways is one of the understudied choke points at airports. “Taxiing is a really critical problem because it connects everything else,” Brownlee explained. Many are familiar with strategies for aligning takeoffs or landings to improve safety or efficiency but that slow crawl toward the gate (called a stand in the UK) can be a crucial link in the chain of events.

“The computing power we’ve got now allows us to understand and analyze data in different ways and pull out different information so we can better understand the true uncertainty in taxiing. We can understand which aircraft take a long time to get there, which aircraft get there quickly, and under what circumstances this is happening,” Atkin said.

Public data sources
Using Microsoft Azure, Brownlee could use Linux virtual machines and develop methods using OpenJDK. By leveraging these open source tools on Azure he completed his work in about one-tenth the time he might if he’d used just his desktop computer. “So rather than spending several months waiting for my data to be ready so that I could get on and do things, I had it within a couple of weeks,” he said.

There were three main tools that the team created to share on Github. TaxiGen reads taxiway and runway information from Open Street Map and then automatically writes it out in a usable format. SnapTracks reads raw GPS coordinates with timings and adds them to TaxiGen material. GM2KML generates helpful visualizations from the other two tools.

“Researchers rely on open tools and platforms to be able to develop and share their work. The ability to use the cloud for access to computing power not available on the desktop can act like a time machine, shrinking the time to results from months to weeks. This is a transformational way of thinking about research computing,” explained Kenji Takeda from Microsoft Research, who was supporting the project. Brownlee’s work on analysis of ground movement was funded by the Sandpit for Integrating and Automating Airport Operations and DAASE grants from the Engineering and Physical Sciences Research Council (EPSRC).

“By getting better predictions, you can start improving the rest of the airport system,” Atkin said. One pilot can take longer than another to cover the same ground, traffic congestion can be heavy at busy times, and mechanical delays of any sort can throw off predictions. Taxiing delays ripple through the entire system. Modeling and predicting that taxi time helps airports change when and where they direct planes and can yield big savings. Brownlee estimates modeling could help cut bottlenecks at Manchester in half.

Open source benefits
Because the tools created by the team are available to anyone, both Brownlee and Atkin foresee that other airports around the world will use them. “The work that Sandy’s doing is going to provide a lot of public domain data and the ability to analyze this for a lot of different airports. And we should be able to see these multi-million-pound savings at airports worldwide,” Atkin said.

Brownlee also hopes models will help guide decisions in weather emergencies or when a runway must be closed. Airports worldwide can use the modeling to understand what to do about a sudden change. “By getting more researchers worldwide involved … we could get a lot more benefit from different areas of knowledge all coming from the same problem,” he said.

No matter what the world does with the open-source tools, for Walmsley the great impact is at Manchester, where he expects “a much better experience for the customer and for the airlines using the airport.”

Microsoft Azure helps researchers predict traffic jams

Microsoft Azure helps researchers predict traffic jams

More than half of the world’s population now lives in cities and suburbs, and as just about any of these billions of people can tell you, urban traffic can be a nightmare. Cars stack up bumper-to-bumper, clogging our highways, jangling our nerves, taxing our patience, polluting our air, and taking a toll on our productivity. In short, traffic jams impair on our emotional, physical, and economic wellbeing.

A study by the Brazilian National Association of Public Transport showed that the country’s traffic exacted an economic toll of about US$7.2 million in 1998. Unfortunately, it’s only getting worse; there are now about three times as many vehicles in Brazil, making traffic exponentially worse, according to Fernando de Oliveira Pessoa, a traffic expert in Belo Horizonte, Brazil’s sixth-largest city.

Microsoft Research has joined forces with the Federal University of Minas Gerais, home to one of Brazil’s foremost computer science programs, to tackle the seemingly intractable problem of traffic jams. The immediate objective of this research is to predict traffic conditions over the next 15 minutes to an hour, so that drivers can be forewarned of likely traffic snarls.

The aptly named Traffic Prediction Project plans to combine all available traffic data—including both historic and current information gleaned from transportation departments, Bing traffic maps, road cameras and sensors, and the social networks of the drivers themselves—to create a solution that gets motorists from point A to point B with minimal stop-and-go. The use of historic data and information from social networks are both unique aspects of the project.

By using algorithms to process all these data, the project team intends to predict traffic jams accurately so that drivers can make smart, real-time choices, like taking an alternative route, using public transit, or maybe even just postponing a trip. The predictions should also be invaluable to traffic planners, especially when they are working to accommodate traffic from special events and when planning for future transportation needs.

Achieving reliable predictions will involve processing terabytes of data, which is why the researchers are using Microsoft Azure as the platform for the service. The exceptional scalability, immense storage capacity, and prodigious computational power of Microsoft Azure makes it the perfect resource for this data-intensive project. And because Microsoft Azure is cloud-based, running the Traffic Prediction service on Azure makes it accessible to all users, in real time, all of the time.

To date, the researchers have tested their prediction model in some of the world’s most traffic-challenged cities: New York, Los Angeles, London, and Chicago. The model achieved a prediction accuracy of 80 percent, and that was based on using only traffic-flow data. The researchers expect the accuracy to increase to 90 percent when traffic incidents and data from social networks are folded in.

So the next time your highway resembles a long, thin parking lot, you might calm yourself by contemplating how Microsoft Azure and the Traffic Prediction Project might help you avoid such tie-ups in the future.

—Juliana Salles, Senior Program Manager, Microsoft Research

A Race Against Time... Management. See how Lotus F1 Team leveraged Office 365 APIs and extensibility to update their legacy travel application. A model for moving your org away from paper systems and legacy applications Watch it all here:

A Race Against Time... Management. See how Lotus F1 Team leveraged Office 365 APIs and extensibility to update their legacy travel application. A model for moving your org away from paper systems and legacy applications Watch it all here:

Read customer success stories to learn how Managed Solution helps businesses implement technology productivity solutions.