Investigating the Benefit of Time-Series Imaging for Load Disaggregation

In this paper, we investigate the benefits of time-series imaging in load disaggregation, as we augment the wide-spread sequence-to-sequence approach by a key element: an imaging block.  

A Recurrence Plot

The approach presented in this paper converts an input sequence to an image, which in turn serves as input to a modified version of a common Denoising Autoencoder architecture used in load disaggregation. Based on these input images, the Autoencoder estimates the power consumption of a particular appliance. 

The main contribution presented in this paper is a comparison study of three common imaging techniques: 

• Gramian Angular Fields, 
• Markov Transition Fields, 
• Recurrence Plots.

Further, we assess the performance of our augmented networks by a comparison with two benchmarking implementations, one based on Markov Models and the other one being a common Denoising Autoencoder. ´

The outcome of our study reveals that in 19 of 24 cases, the considered augmentation techniques provide improved performance over the baseline implementation. Further, the findings presented in this paper indicate that the Gramian Angular Field could be better suited, though the Recurrence Plot was observed to be a viable alternative in some cases. 

Our paper is to appear at the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys ’20):

Hafsa Bousbiat, Christoph Klemenjak, and Wilfried Elmenreich. 2020. Exploring Time Series Imaging for Load Disaggregation. In The 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys ’20), November 18–20, 2020, Virtual Event, Japan.

 We are looking forward to discussing our paper at BuildSys!

Investigating Synthetic Data for Load Disaggregation

Electrical consumption data contain a wealth of information, and their collection at scale is facilitated by the deployment of smart meters. Data collected this way is an aggregation of the power demands of all appliances within a building, hence inferences on the operation of individual devices cannot be drawn directly. By using methods to disaggregate data collected from a single measurement location, however, appliance-level detail can often be reconstructed. A major impediment to the improvement of such disaggregation algorithms lies in the way they are evaluated so far: Their performance is generally assessed using a small number of publicly available electricity consumption data sets recorded from actual buildings. As a result, algorithm parameters are often tuned to produce optimal results for the used datasets, but do not necessarily generalize to different input data well.

 "We propose to break this tradition by presenting a toolchain to create synthetic benchmarking data sets for the evaluation of disaggregation performance in this work. Generated synthetic data with a configurable amount of concurrent appliance activity is subsequently used to comparatively evaluate eight existing disaggregation algorithms." - Christoph Klemenjak

Instead of attempting to compile a benchmarking corpus from existing data sets, we present a methodological way to synthetically create data sets of definable disaggregation complexity. A high degree of realism can be accomplished by using accurate models of existing appliances and user activities. By forwarding synthetically generated data of gradually increasing levels of concurrent appliance activity to state-of-the-art disaggregation algorithms, we determine their sensitivity to specific data characteristics in a much more fine-grained way.

We present a toolchain, ANTgen, that generates synthetic macroscopic load signatures for their use in conjunction with NILM (load disaggregation) tools. By default, it runs in scripted mode (i.e., with no graphical user interface) and processes an input configuration file into a set of CSV output files containing power consumption values and the timestamps of their occurrence, as well as a file summarizing the events that have occurred during the simulation). If you find this tool useful and use it (or parts of it), we ask you to cite the following work in your publications:

Andreas Reinhardt and Christoph Klemenjak. 2020. How does Load Disaggregation Performance Depend on Data Characteristics? Insights from a Benchmarking Study. In Proceedings of the Eleventh ACM International Conference on Future Energy Systems (e-Energy ’20). Association for Computing Machinery, New York, NY, USA, 167–177. 

Learn more about the authors Andreas Reinhardt and Christoph Klemenjak.