Open thesis topics

2 minute read

Published:

Our research group offers several research topics, which can be scaled to a bachelor thesis, research project, or master’s thesis.

Synthetic Energy Consumption Data Set

To the present day, researchers apply load disaggregation algorithms on real-world consumption data sets in order to assess their performance / accuracy. Recently, the idea of a synthetic data set was born and therefore, a specific software tool needs to be developed that is capable of generating such a data set. The student working on this topic will face the following challenges:

Review appliance modelling approaches Implement appliance models of selected appliance groups (e.g., white goods, washing machines, TV, etc.) Design and implement a software tool that generates the dataset Evaluate the accuracy of the appliance models and apply a load disaggregation algorithm on it

Depending on the type of thesis, the task list can be in or decreased. Contact: Christoph.Klemenjak@aau.at

Deep Neural Networks for Appliance Detection

The objective of this thesis will be to explore the applicability of deep neural networks as appliance detectors. The student will be provided with training data, which includes the energy consumption of typical household appliances over the time span of one year. By using the data, the student will first label the data, train the DNNs and evaluate their performance. Depending on the thesis type, the student will have to compare the performance to another appliance detector. The selected approach will be implemented in Python or C++.

Contact: Christoph.Klemenjak@aau.at Type: Scalable to all thesis types

Forecast of energy consumption in the residential sector

The energy consumption of users can be seen as an aspect of human behaviour. Without a doubt, this behaviour is influenced by weather conditions. When trained with smart meter readings, neural networks can be applied to predict the energy consumption of households. The question is, if weather forecast can serve as adequate training data to successfully predict the energy consumption of households. The scope of this thesis will be to explore this question.

Contact: Christoph.Klemenjak@aau.at Type: Scalable to all thesis types

Supervised learning techniques for energy advisors

Energy Advisors such as Mjölnir provide valuable feedback to the user. The feedback builds on gathered knowledge and observations of the energy consumption in households. The objective of this thesis will be:

Review applicable supervised machine learning techniques and discuss their application in Energy Advisor tools Implement the most preferable technique and embed it into the Mjölnir framework Evaluate the performance by means of a case study

Contact: Christoph.Klemenjak@aau.at Type: Scalable to all thesis types