Kalksma, M (2016) Mining household appliances patterns by monitoring electric plug loads. Master's Thesis / Essay, Computing Science.
|
Text
thesis_mathieu_kalksma_v2.pdf - Published Version Download (3MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
Toestemming.pdf - Other Restricted to Backend only Download (78kB) |
Abstract
About 20% of the total energy consumption in the Netherlands is consumed by households. For this thesis an attempt is made to mine patterns for household appliances by monitoring electric plug loads which later can be used to reduce the energy consumed. Three experiments are conducted on data sets from three buildings: two households and one office building. For the experiments Markov models are created which characterise the usage of household appliances over time. Experiments are conducted to predict the usage of household appliances in the near future, an experiment to recover error upcoming energy consumption in real-time. Usage prediction is predicted correctly for over 87% for all the data sets while the recovery of erroneous sensor results in the same prediction for at least 80% of the time. The accuracy for forecasting the energy consumption of devices depends highly on the device with the Mean Absolute Percentage Error (MAPE) varying from 6% to 70%.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Degree programme: | Computing Science |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 15 Feb 2018 08:26 |
| Last Modified: | 15 Feb 2018 08:26 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/14733 |
Actions (login required)
 |
View Item |