Control & Software: Distribution of the electricity grid of a tiny house community

This thesis shows the detailed design of the control and software of a DC microgrid of a tiny house community on the roof of a high-rise building in the city of Rotterdam in the Netherlands, consisting of twelve tiny houses powered by solar and wind energy. This thesis is part of a project with two other subgroups, focusing on the microgrid...

Automated lane changing using deep reinforcement learning: a user-acceptance case study

Lane change decision-making is an important challenge for automated vehicles, urging the need for high performance algorithms that are able to handle complex traffic situations. Deep reinforcement learning (DRL), a machine learning method based on artificial neural networks, has recently become a popular choice for modelling the lane change...

Artificial Intelligence-Based Radio Resource Management in Sliced Radio Access Networks

In this thesis, we design and assess a multi-slice resource allocation framework that is based on machine learning techniques (subset of artificial intelligence techniques). The proposed framework employs two machine learning techniques namely, artificial neural networks and reinforcement learning for resource management in sliced RAN....

Artificial Neural Networks for Flow Field Inference: A machine learning approach

Due to their powerful approximation capabilities, artificial neural networks have seen a wide interest in various fields. A particular application is the use of an artificial neural network to predict solutions of the governing equations for fluid flow i.e. the Navier-Stokes equations. This is done by taking the space and time variables as the...

LoRa Localisation in Cities with Neural Networks

Billions of wireless devices are interconnected to provide services to many<br/>aspects of life and form The Internet of Things. These devices which are<br/>often battery-powered and energy efficient can benefit greatly from an ac-<br/>curate localisation service that does not consume extra energy. Several loc-<br/>alisation methods have been...

Machine Learning of Atmospheric Turbulence in a Variational Multiscale Model

Today's leading projections of climate change predicate on Atmospheric General Circulation Models (GCMs). Since the atmosphere consists of a staggering range of scales that impact global trends, but computational constraints prevent many of these scales from being directly represented in numerical simulations, GCMs require "parameterisations'' -...

Artificial neural networks for determining the optimal process conditions of a gasification process