Home |  ENGLISH |  Kontakt |  Impressum |  Anmelden |  KIT

Using smart meter data for automated energy efficiency services

Aus Aifbportal

Wechseln zu: Navigation, Suche

Using smart meter data for automated energy efficiency services

Veranstaltungsart:
Kolloquium Angewandte Informatik



Utility companies are currently deploying smart electricity meters in millions of households to collect fine-grained electricity consumption data. At the Bits to Energy Lab at ETH Zurich and the Universi-ty of Bamberg, we have developed several approaches to automatically analyze this data with the ultimate goal to enable personalized and scalable energy efficiency programs targeting private households. In particular, we have implemented and tested a system that uses supervised machine learning techniques to automatically estimate specific characteristics of a household from its elec-tricity consumption. The characteristics are related to a household's socio-economic status, its dwelling, and its appliance stock. We evaluated our approach by analyzing smart meter data col-lected from 4232 households over a period of 1.5 years. Our analysis shows that revealing charac-teristics from smart meter data is feasible, as our method achieves an accuracy of more than 70% over all households for many of the characteristics and even exceeds 80% for some of the house-hold properties. The findings are applicable to smart metering systems without making changes to the measurement infrastructure. The inferred knowledge paves the way for targeted energy effi-ciency programs and other services that benefit from improved customer insights. On the basis of these results, Thorsten Staake will detail the technical approach and outline the potential for utilities as well as the policy and privacy implications.

(Prof. Dr. Thorsten Staake)




Start: 20. Mai 2016 um 14:00
Ende: 20. Mai 2016 um 15:30


Im Gebäude 11.40, Raum: 231

Veranstaltung vormerken: (iCal)


Veranstalter: Forschungsgruppe(n) Effiziente Algorithmen
Information: Media:Staake 20-05-2016.pdf