From Robust Scheduling to Resilient Scheduling and Operations - Optimize on-time performance based on delay risk prediction
May 19, 2018
Next week the Airline Operation Research Community gets together on the annual AGIFORS Ops and SSP conference. This year, the conference is hosted by Hawaiian Airlines and will take place on lovely island Honolulu.
Many participants attend the AGIFORS conferences regularly since years bringing home new optimization and prediction concepts. However, over a long period of time academic talks on robust scheduling are continuously on the agenda.
Session at AGIFORS Ops and SSP conference
My research colleague Marius Radde from DLR and I will also talk about robust scheduling – more precisely: Resilient Scheduling. We adjusted the wording to Resilient Scheduling to indicate that we found a solution which can be used in practice and will soon be available as part of Lufthansa Systems NetLine suite.
Let me give you some more background information:
There are some large delays caused by special events or irregularities (e.g. major technical defects, thunderstorms) and there are many smaller delays that occur at a standard day of operation, but can build up to a massive disruption towards the end of the day.
Where the first type requires the full attention of ops control, scheduling can aim at reducing the impact of the second disruption type by allocating buffer times in the right places in order to avoid propagation of delays in a rotation.
Scheduling requires block- and ground times balancing productivity and punctuality. These planning parameters should be as long as needed to be punctual, but should not be too generous thus influencing negatively the profitability of an airline. Based on historic operations data most suitable block- and ground times are defined. In addition, typical constellations leading to systematic delays are identified and buffered by applying appropriate buffer on the ground.
Delay prediction based on real operations data
Using operations data from different airlines over several years, we predict the lengths of ground and block times of typical operations days. Based on simulation results we assess the delay risk for each leg in a given rotation to support the scheduler in his daily work, thus enabling him to reduce the number of situations with high delay risks.
To further support scheduling in reducing delay critical situations we developed different optimizers using metaheuristic methods. Starting from a given flight schedule, the aircraft rotation is changed in order to improve the delay resilience as predicted by the simulation. With reasonable computation time, a significant improvement of the optimization objective can be achieved after a few iterations. By allowing small time shifts of flights, the delay risks of a schedule can be significantly decreased further.
Please let me know your feedback either in person in Honolulu or get in touch with us!