Machine Learning Approaches to Reduce Electrical Waste and Improve Power Grid Stability
Abstract
Machine learning applications to electrical time series data will have wide-ranging impacts in the near future, including reducing billions of dollars of annual electrical waste. My contributions to electricity disaggregation include the first label correction approach for training samples, event detection for unsupervised disaggregation that does not require parameter tuning, and appliance discovery that makes no assumptions on appliance types.