My name is Oliver Parson, and I'm currently employed as a Senior Data Scientist at Bulb. I'm interested in investigating the ways in which machine learning can be used to break down household energy consumption data into individual appliances, also known as Non-intrusive Appliance Load Monitoring (NILM) or energy disaggregation.
Thursday 20 October 2011
Paper accepted at NIPS2011 MLSUST workshop
I recently had a paper accepted at the 2011 Neural Information Processing Systems workshop on Machine Learning for Sustainability. The paper is titled Using Hidden Markov Models for Iterative Non-intrusive Appliance Monitoring, and focuses specifically on how individual appliances can be separated from a household's aggregate load. We presented an approach which does not require training data to be collected by sub-metering individual appliances. Instead, prior models of general appliance types are tuned to specific appliance instances using only signatures extracted from the aggregate load. The tuned appliance models are then used to estimate each appliance’s load, which is subsequently subtracted from the aggregate load. We evaluated our approach using the REDD data set, and show that it can disaggregate 35% of a typical household’s total energy consumption to an accuracy of 83% by only disaggregating three of its highest energy consuming appliances.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment
Note: only a member of this blog may post a comment.