|
Big Data-Driven Airport Resources Management (BigARM) Engine and Application Tools
Airport business is a “Flow Business”. Managing resources in facilitating the flow of people and goods through the airport is always the biggest challenge. Traditionally, resource management at the airport is based on the flight schedule, available resources and other services-related basic factors. However, with the very dynamic nature of airport operation, the largely inter-dependent processes carried out by various parties of the airport community, and the high uncertainties of internal and external airport-related factors, updated and more airport-related data have to be collected and considered to ensure effective resource management and excellent service delivery. All the required data are essentially big data and whose analysis requires big data technologies.
In this project, we propose a Big Data-Driven Airport Resource Management (BigARM) Engine to provide support for efficient and smart airport resource management. First, BigARM integrates multi-source data such as flight data, airfield operation data and external data. Second, to consider both known and unknown factors related to resource management, BigARM designs data analytic techniques to extract features and make predictions on unknown factors from the collected data. Third, based on the specific application scenarios, BigARM formally formulates the resource management as a task allocation problem, or a reinforcement learning problem, which obtains input from previous feature extraction and unknown factor prediction, and output the optimal resource management plan. Finally, the results of BigARM will be presented via a user-friendly interface and thus it can be used for various applications, such as the visualisation of initial plans, improvement in the baggage carousels allocation plan, recommendation for response to unplanned events.
BigARM will be a general engine for airport resource management and can be applied in the management of all kinds of resources at airports like baggage reclaim belts, aircraft stands, and gates, etc. Specially, this project will utilise BigARM to deal with baggage reclaim belts allocation. The allocation of reclaim belts is expected to balance the utilization of belts and reduce the baggage collection time by eliminating baggage delivery stoppage due to conveyor belt congestion. This can be achieved by predicting the arrival time of flights and the time for passengers to arrive at the baggage reclaim area, and balancing the utilization load of reclaim belts.
|
