Privacy Enhancing Mechanisms in the Smart Grid

Wide range deployment of smart grid technologies enables utilities/energy company to gather electricity consumption data on a much more granular level than ever before. On the other hand, this consumption data can be used to infer consumer’s activity at home (consumer’s presence, what kind of activity currently happening at home), breaching consumer’s home privacy.

Given the historical data of customer’s electricity consumption, we will employ privacy protection technique on top of it, such as k-anonymization, data obfuscation, data hiding, etc. Then we will study the trade-off between privacy protection (which is useful for consumer’s side) and forecasting accuracy (useful for the utilities’ side). For forecasting task, whenever it is possible we will not implement machine learning algorithm from scratch, instead we will use public machine learning library available.

If you have any question, just drop us an email, or come to our office:

• Thanasis G. Papaioannou (BC132): [email protected]
• Tri Kurniawan Wijaya (BC147): [email protected]

Prerequisites

• Familiar with (or at least having desire to learn) data mining/machine learning techniques

Student’s availability during August – September 2012 is preferred.
Possible starting date: asap.