Thesis Topics on Smart Grids


Unless stated otherwise, all topics are offered at the Alpen-Adria-Universität Klagenfurt at the group of Prof. Wilfried Elmenreich.

Master thesis topics

  • Comparison of NILM Algorithms 
    Non-intrusive load monitoring (NILM) identifies used appliances in a total power load according to their individual load characteristics. The aim of this thesis is to build up a website which is able to import the measured power consumptions of users, disaggregate the used power profiles of appliances, share power profiles and calculate the power costs for each appliance. We are looking for a student which is fit with HTLM5 and object-oriented programming to implement on the one hand the homepage and on the other hand the load disaggregation algorithm. [Contact: Wilfried Elmenreich] 
  • Analysis of energy consumption data in households
    The goal of this project is to combine energy consumption data collected in households with other datasets (e.g. social networks) to extract models of the users and provide them with tailored services. An example may be a recommender system proposing advices to reduce the energy consumption in the household. We are looking for a student with extensive knowledge of object-oriented programming languages (e.g. Java) and basic experience with data mining. [Contact: Wilfried Elmenreich]
  • Solar power at altitude: Photovoltaic systems on mountains have potential for some improvements over a PV system in a valley, for example less fog, cooler temperatures and lower land price. On the other hand, questions regarding grid connection, maintenance and snow/ice arise. The goal of this thesis is to make measurements to assess the potential in Austria.

Bachelor thesis topics

  • Switchgear for RAPSim The task of this project is to add fuses, reclosers and sectionalizers to the RAPSim software. A fuse provides overcurrent protection by a wire melts when too much current flows through it. A fuse must be replaced after it burned through. A circuit breaker is an automatically operated electrical switch designed to protect an electrical circuit from damage caused by overload or short circuit. Its basic function is to detect a fault condition and interrupt current flow. In electric power distribution, a recloser,  is a circuit breaker equipped with a mechanism that can automatically close the breaker after it has been opened due to a fault. A sectionalizer detects and counts fault current interruptions by the recloser (or circuit breaker). After a pre-determined number of interruptions, the sectionalizer will open, thereby isolating the faulty section of the circuit, allowing the recloser to restore supply to the other non-fault sections.
    RAPSim (Renewable Alternativ Powersystems Simulation) is a free and open source micro-grid simulation framework for better understanding of power flowing behavior in smart microgrids with renewable sources. It is able to simulate grid-connected or standalone microgrids with solar, wind or other renewable energy sources. The proposed software calculates the power generated by each source in the microgrid and then it conducts a power flow analysis. This software is helpful for optimal placement of distributed generation units in a micro grid. If you are interested, please contact Wilfried Elmenreich,
  • Build a robot that measures directed solar irradiation The measurement system should turn a sensor to various angles (two degrees of freedom) and record the solar power from that direction. The measurement results can be further analyzed as a Master Thesis topic. [Contact: Wilfried Elmenreich]
  • Exploiting energy consumption information
    The power profile of households is a useful information that can be used to model users' behaviour. The goal of this project is to report about existing companies and projects that exploit energy consumption data to offer value-added services to users. The student will analyse these systems and will propose a list of design guidelines. The student can focus either on platform-related aspects (e.g. communication) or on applications and interfaces. Contact: Christoph Klemenjak
  • Load disaggregation, the logical approach
    Your home has 10 devices, with the following consumption power: ... Writing a program that prints out all possible power states is easy for this. Now think of the opposite problem: you get a number of power consumption states and you should infer about the possible device configuration that is able to create the measured values. If you can solve the second problem, this Bachelor topic is for you. If you are interested, please contact Wilfried Elmenreich,
  • 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 or Ekanki Sharma
  • 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 or Ekanki Sharma
  • Communication in robot swarms: Spiderino is a swarm robot platform for educational and research purposes. Every Spiderino integrates a Wi-Fi interface that allows the robot to communicate with peers and other clients in the network. The prospective student will work on communication techniques in robot swarms and explore swarm algorithms in the course of the thesis. Contact: Wilfried Elmenreich
  • Smart remote control for Spiderino: Every now and then it is required to control swarm robots remotely. Therefore, the student will implement an Android application, which allows the smartphone/tablet to take control of a specific swarm robot. Contact: Wilfried Elmenreich

Research projects/Softwarepraktikum

  • Smart Grid Simulation: Simulation is a substantial method for research on the futures smart energy systems. Problems including power systems, energy markets and user behaviors need new simulation approaches. The "Smart Grid Simulator" is a Java software which the research group started to develop. There are plenty of possibilities for its further development in several areas.
    • Design and implementation of interfaces with other simulation software, e.g. GridLAB-D.
    • Make the results of the simulation easy access- and drawable, e.g. by use of MatLab.
    • Improve the GUI and adapt the controller to support extended functions and requirements of the simulation.
    • Implement a new idea how energy usage could be controlled and evaluate its success.
    • You should know well Java and software design.
    Contact: Wilfried Elmenreich
  • 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:

No comments:

Post a Comment