Towards a New Evolutionary Subsampling Technique for Heuristic Optimisation of Load Disaggregators

Abstract

Abstract. In this paper we present some preliminary work towards the development of a new evolutionary subsampling technique for solving the non-intrusive load monitoring (NILM) problem. The NILM problem concerns using predictive algorithms to analyse whole-house energy usage measurements, so that individual appliance energy usages can be disaggregated. The motivation is to educate home owners about their energy usage. However, by their very nature, the datasets used in this research are are massively imbalanced in their target value distributions. Consequently standard machine learning techniques, which often rely on optimising for root mean squared error (RMSE), typically fail. We therefore propose the target-weighted RMSE (TW-RMSE) metric as an alternative fitness function for optimising load disaggregators, and show in a simple initial study in which random search is utilised that TW-RMSE is a metric that can be optimised, and therefore has the potential to be included in a larger evolutionary subsampling-based solution to this problem.

Handling imbalance in an extended PLAID

“…This is present in NILM datasets that contain consumption patterns over time. In [4], which determines how much energy a specific appliance consumes at any given moment using regression, the imbalance caused by the difference in activation and idle time of appliances is present. To handle it, they propose the usage of the target-weighted root mean squared error as an alternative error metric for optimizing the regression.…”