Disaggregation of domestic smart meter energy data

Abstract

Many countries are rolling out smart electricity meters. A smart meter measures the aggregate energy consumption of an entire building. However, appliance-by-appliance energy consumption information may be more valuable than aggregate data for a variety of uses including reducing energy demand and improving load forecasting for the electricity grid. Electricity disaggregation algorithms – the focus of this thesis – estimate appliance-by-appliance electricity demand from aggregate electricity demand.

This thesis has three main goals: 1) to critically evaluate the benefits of energy disaggregation; 2) to develop tools to enable rigorous disaggregation research; 3) to advance the state of the art in disaggregation algorithms.

The first part of this thesis explores whether disaggregated energy feedback helps domestic users to reduce energy consumption; and discusses threats to the NILM. Evidence is collected, summarised and aggregated by means of a critical, systematic review of the literature. Multiple uses for disaggregated data are discussed. Our review finds no robust evidence to support the hypothesis that current forms of disaggregated energy feedback are more effective than aggregate energy feedback at reducing energy consumption in the general population. But the absence of evidence does not necessarily imply the absence of any beneficial effect of disaggregated feedback. The review ends with a discussion of ways in which the effectiveness of disaggregated feedback may be increased and a discussion of opportunities for new research into the effectiveness of disaggregated feedback. We conclude that more social science research into the effects of disaggregated energy feedback is required. This motivates the remainder of the thesis: to enable cost-effective research into the effects of disaggregated feedback, we work towards developing robust NILM algorithms and software.

The second part of this thesis describes three tools and one dataset developed to enable disaggregation research. The first of these tools is a novel, low-cost data collection system, which records appliance-by-appliance electricity demand every six seconds and records the whole-home voltage and current at 16 kHz. This system enabled us to collect the UK’s first and only high-frequency (kHz) electricity dataset, the UK Disaggregated Appliance-Level Electricity dataset (UK-DALE). Next, to help the disaggregation community to conduct open, rigorous,repeatable research, we collaborated with other researchers to build the first open-source dissaggregation framework, NILMTK. NILMTK has gained significant traction in the community,both in terms of contributed code and in terms of users. The third tool described in this thesis is a metadata schema for disaggregated energy data. This schema was developed to make it easier for researchers to describe their own datasets and to reduce the effort required to import datasets.

The third part of this thesis describes our effort to advance the state of the art in disaggregation algorithms. Three disaggregation approaches based on deep learning are discussed: 1) a form of recurrent neural network called ‘long short-term memory’ (LSTM); 2) denoising autoencoders; and 3) a neural network which regresses the start time, end time and average power demand of each appliance activation. The disaggregation performance was measured using seven metrics and compared to two ‘benchmark’ algorithms from NILMTK: combinatorial optimisation and factorial hidden Markov models. To explore how well the algorithms generalise to unseen houses,the performance of the algorithms was measured in two separate scenarios: one using test data from a house not seen during training and a second scenario using test data from houses which were seen during training. All three neural nets achieve better F1 scores (averaged over all five appliances) than either benchmark algorithm. The neural net algorithms also generalise well to unseen houses.