Systems and methods for optimizing energy loading in airline operations

A system for optimizing energy loading in commercial airline operations comprising:

• a computing device comprising a processor and a memory having instructions executable by the processor to perform a set of functions, the set of functions comprising:
• receiving flight plans of a plurality of aircraft in a fleet of aircraft, wherein each flight plan is indicative of a plurality of landing sites and a corresponding plurality of flight legs, wherein each landing site corresponds to a set of jet fuel-related parameters, and wherein each set of jet fuel-related parameters comprises at least (i) a landing site location, (ii) an available jet fuel type, (iii) an expected jet fuel cost, and (iv) an emission standard, wherein the fleet of aircraft is a fleet of commercial aircraft;
• and
• for each aircraft of the plurality of aircraft:
• determining, based on (i) the set of jet fuel-related parameters for each landing site and (ii) an expected payload for each flight leg, an energy load of the aircraft associated with each flight leg, wherein the energy load corresponds to an amount of fuel used during the flight leg;
• calculating a fuel value score for refueling the aircraft at a landing site of each flight leg, wherein the fuel value score relates to a fuel amount and associated emissions cost at the landing site and a time for refueling at the landing site;
• determining a fueling plan corresponding to the flight plan based at least on the energy load of the aircraft at each flight leg of the flight plan and the fuel value score for refueling the aircraft with jet fuel at the landing site of each flight leg of the flight plan;
• and
• providing the fueling plan to the aircraft, the system further comprising:
• a machine learning device, wherein the machine learning device includes a machine learning model automatically trained and updated by the machine learning device using data received from the fleet of aircraft that implemented past fueling plans generated by the machine learning model, wherein the data is indicative of (i) flight plans of the fleet of aircraft, (ii) energy loads of the fleet of aircraft during legs of the flight plans, (iii) jet fuel costs at landing sites of the flight plans, (iv) time taken to refuel at the landing sites, and (v) times that the aircraft waits on the ground at the landing sites waiting for refueling to begin, wherein the machine learning model is trained using the data to calculate the fuel value score, wherein calculating the fuel value score comprises calculating the fuel value score using the trained machine learning model and the flight plan of the aircraft.

A non-transitory computer readable medium having stored thereon instructions, that when executed by one or more processors of a computing device, cause the computing device to perform functions comprising:

• receiving a flight plan of an aircraft indicative of a plurality of landing sites and a corresponding plurality of flight legs, wherein each landing site corresponds to a set of jet fuel-related parameters, and wherein each set of jet fuel-related parameters comprises at least (i) a landing site location, (ii) an available jet fuel type, (iii) an expected jet fuel cost, and (iv) an emission standard, wherein the aircraft is a commercial aircraft;
• determining, based on (i) the set of jet fuel-related parameters for each landing site and (ii) an expected payload for each flight leg, an energy load of the aircraft associated with each flight leg, wherein the energy load corresponds to an amount of fuel used during the flight leg;
• training a machine learning model using data received from a fleet of aircraft that implemented past fueling plans generated by the machine learning model, wherein the data is indicative of (i) flight plans of the fleet of aircraft, (ii) energy loads of the fleet of aircraft during legs of the flight plans, (iii) jet fuel costs at landing sites of the flight plans, and (iv) time taken to refuel at the landing sites, wherein the fleet of aircraft is a fleet of commercial aircraft, wherein training the machine learning model using the data comprises training the machine learning model to calculate a fuel value score, wherein training the machine learning model comprises the computing device automatically updating the machine learning model using data indicative of times that the aircraft waits on the ground at the landing sites waiting for refueling to begin;
• calculating, using the trained machine learning model and the flight plan of the aircraft, the fuel value score for refueling the aircraft at a landing site of each flight leg, wherein the fuel value score relates to a fuel amount and associated emissions cost at the landing site and a time for refueling at the landing site;
• determining a fueling plan corresponding to the flight plan based at least on the energy load of the aircraft at each flight leg of the flight plan and the fuel value score for refueling the aircraft at the landing site of each flight leg of the flight plan;
• and
• fueling the aircraft with jet fuel by a particular amount at a first landing site of the flight plan in accordance with the fueling plan.