Jean-Alexander Monin Nylund: Semi-Markov modelling in a Gibbs sampling algorithm for NIALM
Time: Thu 2014-02-06 10.15 - 11.00
Location: Room 3733, Lindstedtsvägen 25, 7th floor, Department of mathematics, KTH
Residential households in the EU are estimated to have a savings potential of around 30 %. The question yet remains on how to realize this savings potential. Non-Intrusive Appliance Load Monitoring (NIALM) aims to disaggregate the combination of household appliance energy signals with only measurements of the total household power load.
The core of this thesis has been the implementation of an extension to a Gibbs sampling model with Hidden Markov Models for energy disaggregation. The goal has been to improve overall performance, by including the duration times of electrical appliances in the probabilistic model.
The final algorithm was evaluated in comparison to the base algorithm, but results remained at the very best inconclusive, due to the model's inherent limitations.
The work was performed at the Swedish company Watty. Watty develops the first energy data analytic tool that can automate the energy efficiency process in buildings.