Dynamic Target Time Management with Reinforcement Learning: A case study on Zurich short-haul regulated arrivals

This Master Thesis investigates the possible improvements to the Target Time Management concept to optimize the arrival flows for SWISS International Airlines. The aim is to improve operational performance based on the current model used, as well as prove that Target Time Management constitutes a valuable system to improve operations in a...

Solving ML with ML: Effectiveness of the Metropolis-Hastings algorithm for synthesizing Machine Learning Pipelines

In AutoML, the search space of possible pipelines is often large and multidimensional. This makes it very important to use an efficient search algorithm. We measure the effectiveness of the Metropolis-Hastings algorithm (M-H) in a pipeline synthesis framework, when the search space is described by a context-free grammar. We also compare the...

Integrating Predictive and Optimization Model for Intelligent Schedule Management based on Real Time ETA Information: A Concept of Machine Learning and Exact Solution in Petrochemical Loading Facility

This study addresses the truck rescheduling problem as the consequence of uncertain arrival time. It proposes an integrated system of predictive model powered by machine learning algorithm and exact optimization model such that it is distinct from most existing literatures in this domain. The uncertainty of truck arrival time is captured as...

An Investigation Into Predict-and-Optimize Machine Learning

Predict-and-Optimize (PnO) is a relatively new machine learning paradigm that has attracted recent interest: it concerns the prediction of parameters that determine the value of solutions to an optimization problem, such that the optimizer ends up picking a good solution. Training estimators with standard loss functions like mean squared error...

Deepification: Learning Variable Ordering Heuristics in Constraint Optimization Problems

Constraint programming is a paradigm for solving combinatorial problems by checking whether constraints are satisfied in a constraint satisfaction problem or by optimizing an objective in a constraint optimization problem. To find solutions, the solver needs to find a variable and value ordering. Numerous heuristics designed by human experts...

Design of Reinforcement Learning based Incremental Flight Control Laws for the Cessna Citation II(PH-LAB) Aircraft

Online Adaptive Flight Control is interesting in the context of growing complexity of aircraft systems and their adaptability requirements to ensure safety. An Incremental Approximate Dynamic Programming (iADP) controller combines reinforcement learning methods, optimal control and Online identified incremental model to achieve optimal adaptive...

Deep Neural Networks and Optimization: A promising tag team

Machine learning has been a computer sciences buzzword for years. The technology has a lot of potential and a huge number of applications that spoke to people with and without knowledge of computer sciences. Image, text and speech recognition, social profiling, computergames, everything seemed possible. Machine learning is not as much in the...

An Optimisation and Forecasting Framework for ULD Packing in the Air Cargo Supply Chain

The air cargo industry is a challenging environment due to the high competition between the stakeholders involved. This demands, as example, high efficiency from cargo airlines. Efficiency can be ensured by designing loading strategies that fully exploit the available cargo volume. Unknowns in the booking dimensions and flight information make...

Multi-period adaptive fleet planning problem: with Approximate Dynamic Programming

This MSc thesis presents a stochastic modelling approach to the multi-period airline fleet planning problem. Approximate Dynamic Programming (ADP) is used to model the impact of demand uncertainty on fleet decisions. The proposed ADP algorithm applies local value function approximations resulting from Gaussian kernel regressions to estimate...