The project

Dispatcher3, an Innovative Action within the frame of CleanSky 2 ITD System, will enhance airlines operations by improving the dispatching and flight operating processes, providing an infrastructure able to lever on historical data and machine learning techniques to systematically estimate the variability between planned and executed flight plans.

Dispatcher3 focuses on the activities prior departure; Pilot3, a CleanSky 2 Innovation Action, focuses on the optimisation of the flight during the execution phase.

Dispatcher3 aims at supporting dispatchers, pilots and the strategic scheduling process:

Dispatchers
  • Predicting the expected actual performance of flight.
  • Providing advice on the flight plan design and selection process.
  • Identifying the precursors of the different variations between planning and execution.
Pilots
  • Providing information on the expected variance between the flight plan and the execution.
  • Providing advice on some flight operations.
Schedule planners
  • Creating the infrastructure needed to store and process flights and operational environment data.
  • Providing advice on which flights are more prone to variability between schedules and execution blocks.

An introduction to Dispatcher3

Objectives and approach

Final prototype in 1 minute!

Dispatcher3 at glance

Dispatcher3 will be used during the pre-departure but at different decision periods. Independent user-oriented models, which consider the information available at each time-frame, will be developed.

Dispatcher3 is organised in three layers:

  • Data infrastructure: Powered by DataBeacon (a Multi-sided, open source, data storage and processing platform). Providing private environments, secure data frames, the full-stack AI environment, and a scalable infrastructure;
  • Predictive capabilities; with two different modules:
    • Data acquisition and preparation: with a first phase of data wrangling and a second step of descriptive analytics.
    • Predictive model: consisting on target variable labelling and feature engineering and training, test and validation of machine learning models.
  • Advice capabilities: producing specific advise to users: dispatchers, pilots and schedule planners.

Development approach

Close coordination with stakeholders and with the Topic Manager (Thales) are key to ensure that Dispatcher3 delivers a suitable solution.  An Advisory Board formed by airlines and experts has been set up and will help to steer the project in the right direction. Moreover, counting with Vueling and Skeyes as partners will allow functionalities of Dispatcher3 to be accepted and deploy as soon as possible. Dispatcher3 will maximise synergies with Pilot3 project.

The project will start with the formalisation of the requirements and case studies to be tested. Two prototype versions will be generated, and you will be able to provide feedback to us on the first version on a dedicated workshop!

Coordination and partners

Dispatcher3 is coordinated by the University of Westminster (United Kingdom). There are six participants from four countries:

INX: Innaxis, Spain. PACE: PACE Aerospace Engineering & Information Technology GmbH, Germany. Skeyes: ANSP service provider Belgium. UPC: Universitat Politècnica de Catalunya, Spain. Vueling: Vueling Airlines, Spain.

Topic manager

The Topic Manager of Dispatcher3 is: Thales, France

Advisory Board

This project is supported by an Advisory Board formed by:


This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 886461.

The  opinions  expressed  in this site  reflect  the  authors’  view  only.  Under  no  circumstances  shall  the Commission or Clean Sky Joint Undertaking be responsible for any use that may be made of the information contained herein.