Consumption Forecasting 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. While the utilities can potentially better understand the customers, design the demand response programs, forecast and control the loads, and plan the systems, etc., they are facing analytic issues with making sense and taking advantage of this data.

Given the historical data of customer’s electricity consumption, we will forecast the electricity load (next hour, next day, etc.). We will also consider external information such as weather, temperature, weekend/weekday, public holiday, etc. 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:

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

Prerequisites

• Having the spirit of data exploration
• 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.