Change search
ReferencesLink to record
Permanent link

Direct link
Exploiting Temporal Difference for Energy Disaggregation via Discriminative Sparse Coding
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematical Statistics.
2015 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Utforskande av temporära skillnader för Energi Disaggregering med Sparse Coding (Swedish)
Abstract [en]

This thesis analyzes one hour based energy disaggregation using Sparse Coding by exploiting temporal differences. Energy disaggregation is the task of taking a whole-home energy signal and separating it into its component appliances. Studies have shown that having device-level energy information can cause users to conserve significant amounts of energy, but current electricity meters only report whole-home data. Thus, developing algorithmic methods for disaggregation presents a key technical challenge in the effort to maximize energy conservation. In Energy Disaggregation or sometimes called Non- Intrusive Load Monitoring (NILM) most approaches are based on high frequent monitored appliances, while households only measure their consumption via smart-meters, which only account for one-hour measurements. This thesis aims at implementing key algorithms from J. Zico Kotler, Siddarth Batra and Andrew Ng paper "Energy Disaggregation via Discriminative Sparse Coding" and try to replicate the results by exploiting temporal differences that occur when dealing with time series data. The implementation was successful, but the results were inconclusive when dealing with large datasets, as the algorithm was too computationally heavy for the resources available. The work was performed at the Swedish company Greenely, who develops visualizations based on gamification for energy bills via a mobile application.

Abstract [sv]

I den här uppsatsen analyseras Energi Disaggregering med hjälp av Sparse Coding genom att utforska temporala skillnader på en timbaserade data. Studier har visat att presentera information på apparat nivå kan det göra att användare utnyttjar mindre energy i hemmen där man idag bara presenterar hela hushållets användning. Denna uppsats har som mål att implementera och utveckla de algoritmer J. Zico Kotler, Siddarth Batra and Andrew Ng presenterar i deras artikel "Energy Disaggregation via Discriminative Sparse Coding", genom att använda sig utav de temporära skillnader som uppstår inom tidsseriedata. I uppsatsen uppnådde man ett sämre resultat, där datakraften var inte tillräcklig för att utnyttja datan på bästa sätt. Arbetet var utfört på Greenely, ett företag som utvecklar visualiseringar utav elräkningen via en mobilapplikation.

Place, publisher, year, edition, pages
TRITA-MAT-E, 2015:59
National Category
Probability Theory and Statistics
URN: urn:nbn:se:kth:diva-172997OAI: diva2:864063
Subject / course
Mathematical Statistics
Educational program
Master of Science - Applied and Computational Mathematics
Available from: 2015-10-24 Created: 2015-09-06 Last updated: 2015-10-24Bibliographically approved

Open Access in DiVA

fulltext(5364 kB)55 downloads
File information
File name FULLTEXT01.pdfFile size 5364 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
Mathematical Statistics
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 55 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 458 hits
ReferencesLink to record
Permanent link

Direct link