Airlines turn to AI to assign gates and reduce wait times

The next time you’re racing to your airport gate, think about the airline staff who made sure that gate was actually available.

Assigning gates is a surprisingly complex task.

“With 15 gates and 10 planes, there are more than 570 billion possibilities,” says Dr. Joseph Doetsch, who worked on the gate assignment problem as head of quantum computing at Lufthansa Industry Solutions.

Choosing the best gate for each flight can help reduce aircraft taxi times and reduce congestion, meaning travelers spend less time waiting on the tarmac.

This also reduces the amount of fuel needed, and therefore the aircraft’s emissions.

Typically, gates are assigned when flight schedules are published, so up to a year in advance, but are then revisited a month in advance, a week in advance, and then finally on the day of the flight.

All kinds of priorities must be juggled to determine the best place to park a plane.

“For example, some carriers may have access to gates located near their lounges and other facilities. Additionally, flights with large numbers of connecting passengers are often placed to optimize transfer times and improve the overall passenger experience,” says co-founder George Richardson. from the airport management company AeroCloud.

“Some airlines, particularly low-cost carriers, may opt for more cost-effective remote stands with lower parking fees, prioritizing operational savings over proximity to the main terminal.”

Other factors include the direction the aircraft is coming from, aircraft type, intended runway assignment, gate availability, airport staff, customer connections and baggage and scheduled movements of other aircraft on the taxiway and on the tarmac.

Worse yet, many of these factors can change at the last minute.

At the same time, delayed flights can compound difficulties, forcing airports and airlines to reassign gates at the last minute, increasing passenger wait times and potentially leading to flight cancellations.

Given this level of complexity, you would think that clever computer software would get the job done, but think again.

Gate assignment work has often been done using surprisingly basic technology, according to an AeroCloud survey of challenges faced by senior airport executives.

“You’d be surprised how many airports around the world still manage the process manually,” Mr Richardson says.

Among airport executives who responded to AeroCloud’s survey, 40% said Excel and Word documents were used to store and manage information related to their airport operations, including gate management .

But serious investments are being made in more advanced systems.

Last year, American Airlines introduced Smart Gating at Dallas Fort Worth International Airport.

The system uses machine learning to assign arriving aircraft to the closest available gate with the shortest taxi time.

Machine learning is a branch of artificial intelligence, in which large amounts of data are used to train a system that can be modified to improve its results.

In the case of American Airlines’ system, real-time flight information and other data are used to choose which gate to send a plane to.

“Traditionally, our team members would manually assign gates using an existing computer system. At Dallas Fort Worth International Airport, our largest hub, this process took approximately four hours,” said a gatekeeper. American Airlines spokesperson.

The new system can complete this process in 10 minutes, which has reduced aircraft taxi times by 20 percent, saving approximately 1.4 million gallons of jet fuel each year, the spokesperson adds.

Lufthansa Industry Solutions, a subsidiary of German airline Lufthansa, plans to use quantum computing to tackle the problem.

Quantum computing uses the strange but powerful properties of quibits to solve certain types of problems much faster than traditional computers.

At the moment, these computers are in their infancy.

Gate assignment is a problem that traditional computers and algorithms struggle to solve quickly, with calculation times increasing disproportionately to the scale of the problem.

But Dr Doetsch is confident that approaches using quantum computing will solve the problem.

“Quantum algorithms will enable optimal allocation of gates and other resources, even in large airports and travel networks. These algorithms will be able to respond to changing external factors with optimal solutions updated in real time “, he said.

Lufthansa is currently studying which of the various new quantum computing systems will be most suitable for its project.

It runs simulations that can give an indication of the effectiveness of quantum computing.

“In our initial trials, our optimized solutions could reduce average passenger transit times by almost 50% compared to corresponding real-world data,” adds Dr. Doetsch.

With increasing pressure on airport capacity, says AeroCloud’s Richardson, these improved techniques could help reduce the amount of expansion required.

“Capacity is a major issue for many airports, and even if they wanted to introduce new carriers or new destinations, physical expansion is a barrier.

“They need to make optimal use of their current resources.”