Optimizing a flight of an aircraft with at least one segment of formation flight
A method is provided for optimizing a flight of an aircraft with at least one segment of formation flight. The method includes accessing flight plans for flights of a fleet, and transforming the flight plans into values of a set of features that describe segments of the flights. The values are applied to a machine learning model trained to predict the segment(s) during which the aircraft is within a region that includes at least one second aircraft of the fleet that is thereby capable of serving as a leading aircraft in the segment(s) of formation flight in which the aircraft is a trailing aircraft. A notification is sent to the aircraft of the segment(s) and the second aircraft capable of serving as the leading aircraft. And a second notification is sent to the second aircraft of the segment(s) and the aircraft capable of serving as the trailing aircraft.
1. An apparatus for optimizing a flight of a first aircraft with at least one segment of formation flight in which the first aircraft is a trailing aircraft relative to a vortex generated by a leading aircraft, the apparatus comprising:
a memory configured to store computer-readable program code; and
processing circuitry configured to access the memory, and execute the computer-readable program code to cause the apparatus to at least:
access flight plans for flights of a fleet of aircraft that includes the flight of the first aircraft, the flight plans including real-time sensor data collected during the flight of the first aircraft;
transform the flight plans into values of a set of features that describe segments of the flights;
apply the values of the set of features to a machine learning model trained to output a first formation flight notification, indicating at least one segment of formation flight in which an operational efficiency metric of the flight of the first aircraft would be improved by flying in formation with a second aircraft serving as the leading aircraft, wherein the operational efficiency metric is a standard of measurement of operational efficiency of an aircraft determined by an optimization engine, the optimization engine configured to determine values of the operational efficiency metric subject to air traffic control requirements that comprise operational requirements of the fleet of aircraft that include air traffic separation rules that maintain each aircraft outside a minimum distance from other aircraft;
generate an updated flight plan for the first aircraft indicating the at least one segment of formation flight and the second aircraft that is capable of serving as the leading aircraft;
send the first formation flight notification and the updated flight plan to the first aircraft; and
send a second formation flight notification to the second aircraft indicating the at least one segment of formation flight and indicating that the first aircraft is capable of serving as the trailing aircraft.
2. The apparatus of claim 1 , wherein the processing circuitry is configured to execute the computer-readable program code to cause the apparatus to further at least:
access flight data for historical flights of the fleet of aircraft, the flight data including values of properties or characteristics of the historical flights;
perform a feature construction to create the set of features from the properties or characteristics; and
train the machine learning model using the set of features, and using at least some of the values of the properties or characteristics as a training dataset.
3. The apparatus of claim 1 , wherein the at least one segment of formation flight includes a particular segment during which the first aircraft is within a region that includes multiple formation candidate aircraft that are capable of serving as the leading aircraft, and the processing circuitry is configured to execute the computer-readable program code to cause the apparatus to further at least:
determine the values of the operational efficiency metric for the first aircraft in the formation flight with respective ones of the multiple formation candidate aircraft; and
select one of the multiple formation candidate aircraft as the second aircraft based on a comparison of the values of the operational efficiency metric.
4. The apparatus of claim 1 , wherein the processing circuitry is configured to execute the computer-readable program code to further cause the apparatus to access and transform the flight plans, and apply the values of the set of features to the machine learning model, prior to the flight of the first aircraft, and
wherein the apparatus caused to send the first formation flight notification includes the apparatus caused to send the updated flight plan to the first aircraft.
5. The apparatus of claim 1 , wherein the processing circuitry is configured to execute the computer-readable program code to further cause the apparatus to access and transform the flight plans, apply the values of the set of features to the machine learning model, and send the first formation flight notification to the first aircraft, during the flight of the first aircraft.
6. The apparatus of claim 1 , wherein the processing circuitry is configured to execute the computer-readable program code to further cause the apparatus to:
optimize multiple ones of flights of multiple aircraft of the fleet of aircraft,
wherein the apparatus is caused to apply the values of the set of features to the machine learning model trained to predict a respective at least one segment of formation flight of each of the multiple aircraft during which the first aircraft is within a region that includes a respective at least one second aircraft that is thereby capable of serving as the leading aircraft in the respective at least one segment of formation flight,
wherein the apparatus caused to send the first formation flight notification includes the apparatus caused to send a respective notification to each of the multiple aircraft of the respective at least one segment of formation flight and the respective at least one second aircraft that is capable of serving as the leading aircraft.
7. A method of optimizing a flight of a first aircraft with at least one segment of formation flight in which the first aircraft is a trailing aircraft relative to a vortex generated by a leading aircraft, the method comprising:
accessing flight plans for flights of a fleet of aircraft that includes the flight of the first aircraft, the flight plans including real-time sensor data collected during the flight of the first aircraft;
transforming the flight plans into values of a set of features that describe segments of the flights;
applying the values of the set of features to a machine learning model trained to output a first formation flight notification, indicating at least one segment of formation flight in which an operational efficiency metric of the flight of the first aircraft would be improved by flying in formation with a second aircraft serving as the leading aircraft, wherein the operational efficiency metric is a standard of measurement of operational efficiency of an aircraft determined by an optimization engine, the optimization engine configured to determine values of the operational efficiency metric subject to air traffic control requirements that comprise operational requirements of the fleet of aircraft that include air traffic separation rules that maintain each aircraft outside a minimum distance from other aircraft;
generating an updated flight plan for the first aircraft indicating the at least one segment of formation flight and the second aircraft that is capable of serving as the leading aircraft;
sending the first formation flight notification and the updated flight plan to the first aircraft; and
sending a second formation flight notification to the second aircraft indicating the at least one segment of formation flight and indicating that the first aircraft is capable of serving as the trailing aircraft.
8. The method of claim 7 , further comprising:
accessing flight data for historical flights of the fleet of aircraft, the flight data including values of properties or characteristics of the historical flights;
performing a feature construction to create the set of features from the properties or characteristics; and
training the machine learning model using the set of features, and using at least some of the values of the properties or characteristics as a training dataset.
9. The method of claim 7 , wherein the at least one segment of formation flight includes a particular segment during which the first aircraft is within a region that includes multiple formation candidate aircraft that are capable of serving as the leading aircraft, and the method further comprises:
determining the values of the operational efficiency metric for the first aircraft in the formation flight with respective ones of the multiple formation candidate aircraft; and
selecting one of the multiple formation candidate aircraft as the second aircraft based on a comparison of the values of the operational efficiency metric.
10. The method of claim 7 , wherein the flight plans are accessed and transformed, and the values of the set of features are applied to the machine learning model, prior to the flight of the first aircraft.
11. The method of claim 7 , wherein the flight plans are accessed and transformed, the values of the set of features are applied to the machine learning model, and the first formation flight notification is sent to the first aircraft, during the flight of the first aircraft.
12. The method of claim 7 , further comprising:
optimizing multiple ones of flights of multiple aircraft of the fleet of aircraft,
wherein the values of the set of features are applied to the machine learning model trained to predict a respective at least one segment of formation flight of each of the multiple aircraft during which the first aircraft is within a region that includes a respective at least one second aircraft that is thereby capable of serving as the leading aircraft in the respective at least one segment of formation flight,
wherein sending the first formation flight notification includes sending a respective notification to each of the multiple aircraft of the respective at least one segment of formation flight and the respective at least one second aircraft that is capable of serving as the leading aircraft.
13. A computer-readable storage medium for optimizing a flight of a first aircraft with at least one segment of formation flight in which the first aircraft is a trailing aircraft relative to a vortex generated by a leading aircraft, the computer-readable storage medium being non-transitory and having computer-readable program code stored therein that, in response to execution by processing circuitry, causes an apparatus to at least:
access flight plans for flights of a fleet of aircraft that includes the flight of the first aircraft, the flight plans including real-time sensor data collected during the flight of the first aircraft;
transform the flight plans into values of a set of features that describe segments of the flights;
apply the values of the set of features to a machine learning model trained to output a first formation flight notification, indicating at least one segment of formation flight in which an operational efficiency metric of the flight of the first aircraft would be improved by flying in formation with a second aircraft serving as the leading aircraft, wherein the operational efficiency metric is a standard of measurement of operational efficiency of an aircraft determined by an optimization engine, the optimization engine configured to determine values of the operational efficiency metric subject to air traffic control requirements that comprise operational requirements of the fleet of aircraft that include air traffic separation rules that maintain each aircraft outside a minimum distance from other aircraft;
generate an updated flight plan for the first aircraft indicating the at least one segment of formation flight and the second aircraft that is capable of serving as the leading aircraft;
send the first formation flight notification and the updated flight plan to the first aircraft; and
send a second formation flight notification to the second aircraft indicating the at least one segment of formation flight and indicating that the first aircraft is capable of serving as the trailing aircraft.
14. The computer-readable storage medium of claim 13 , wherein the computer-readable storage medium has further computer-readable program code stored therein that, in response to execution by the processing circuitry, causes the apparatus to further at least:
access flight data for historical flights of the fleet of aircraft, the flight data including values of properties or characteristics of the historical flights;
perform a feature construction to create the set of features from the properties or characteristics; and
train the machine learning model using the set of features, and using at least some of the values of the properties or characteristics as a training dataset.
15. The computer-readable storage medium of claim 13 , wherein the at least one segment of formation flight includes a particular segment during which the first aircraft is within a region that includes multiple formation candidate aircraft that are capable of serving as the leading aircraft, and the computer-readable storage medium has further computer-readable program code stored therein that, in response to execution by the processing circuitry, causes the apparatus to further at least:
determine the values of the operational efficiency metric for the first aircraft in the formation flight with respective ones of the multiple formation candidate aircraft; and
select one of the multiple formation candidate aircraft as the second aircraft based on a comparison of the values of the operational efficiency metric.
16. The computer-readable storage medium of claim 13 , wherein the apparatus is caused to access and transform the flight plans, and apply the values of the set of features to the machine learning model, prior to the flight of the first aircraft.
17. The computer-readable storage medium of claim 13 , wherein the apparatus is caused to access and transform the flight plans, apply the values of the set of features to the machine learning model, and send the first formation flight notification to the first aircraft, during the flight of the first aircraft.
18. The computer-readable storage medium of claim 13 ,
wherein the apparatus is caused to:
apply the values of the set of features to the machine learning model trained to predict a respective at least one segment of formation flight of each of multiple aircraft of the fleet of aircraft during which the first aircraft is within a region that includes a respective at least one second aircraft that is thereby capable of serving as the leading aircraft in the respective at least one segment of formation flight,
wherein the apparatus caused to send the first formation flight notification includes the apparatus caused to send a respective notification to each of the multiple aircraft of the respective at least one segment of formation flight and the respective at least one second aircraft that is capable of serving as the leading aircraft.
19. The apparatus of claim 1 , wherein the air traffic control requirements comprise operational requirements further of the fleet of aircraft that include regulatory requirements of air traffic control.
20. The apparatus of claim 1 , wherein the air traffic control requirements comprise operational requirements further of the fleet of aircraft that include air traffic separation rules that maintain each aircraft outside a minimum distance from obstacles in surrounding terrain.
21. The method of claim 7 , wherein the air traffic control requirements comprise operational requirements further of the fleet of aircraft that include separation rules that maintain each aircraft outside a minimum distance from obstacles in surrounding terrain.