A Bayesian Approach to Unsupervised, Non-Intrusive Load Disaggregation

Abstract

Estimating household energy use patterns and user consumption habits is a fundamental requirement for management and control techniques of demand response programs, leading to a growing interest in non-intrusive load disaggregation methods. In this work we propose a new methodology for disaggregating the electrical load of a household from low-frequency electrical consumption measurements obtained from a smart meter and contextual environmental information. The method proposed allows, with an unsupervised and non-intrusive approach, to separate loads into two components related to environmental conditions and occupants' habits. We use a Bayesian approach, in which disaggregation is achieved by exploiting actual electrical load information to update the a priori estimate of user consumption habits, to obtain a probabilistic forecast with hourly resolution of the two components. We obtain a remarkably good accuracy for a benchmark dataset, higher than that obtained with other unsupervised methods and comparable to the results of supervised algorithms based on deep learning. The proposed procedure is of great application interest in that, from the knowledge of the time series of electricity consumption alone, it enables the identification of households from which it is possible to extract flexibility in energy demand and to realize the prediction of the respective load components.

Keywords: Bayesian methods; NILM; energy disaggregation; non-intrusive load monitoring.

Figure 1

Ridgeline plot of average daily total, base, and thermal load distribution as a function of mean outdoor temperature.

Figure 2

Ridgeline plot of average daily load distribution for heat pump, furnace, and unmonitored loads as a function of mean outdoor temperature.

Figure 3

Ridgeline plot of distribution of the measured base hourly load, and of its prior and posterior distributions, grouped by the hour of the day.

Figure 4

Ridgeline plot of distribution of the measured thermal hourly load, and of its prior and posterior distributions, grouped by the hour of the day, when the average outside temperature is in the range [5–7 °C].

Figure 5

Load disaggregation examples for different periods in a year, with different values of the outdoor mean temperature.