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!

Evolving NILM to NIAD: Non-Intrusive Activity Detection

Almost all documented practical use cases of load disaggregation rely on the analysis of appliance operational times and their impact on the monthly electricity bill. However, load disaggregation bears promising potential for other use cases. Recognizing user activities without the need to set up a dedicated sensing infrastructure is one such application, given that many household activities involve the use of electrical appliances. State-of-the-art disaggregation algorithms only provide support for the recognition of one appliance at a time, however. 

In collaboration with Andreas Reinhardt from TU Clausthal, we thus take load disaggregation to the next level, and present to what extent it is applicable to monitor user activities involving multiple appliances (operating sequentially or in parallel) using this technique. For the evaluation of our Non-Intrusive Activity Detection (NIAD), we synthetically generate load signature data to model nine typical user activities, followed by an assessment to what extent they can be detected in aggregate electrical consumption data. Our results prove that state-of-the-art load disaggregation algorithms are also well-suited to identify user activities, at accuracy levels comparable to (but slightly below) the disaggregation of individual appliances.

Our paper is to appear at the 2nd ACM Workshop on Device-Free Human Sensing (DFHS'20):

Andreas Reinhardt and Christoph Klemenjak. 2020. Device-Free User Activity Detection using Non-Intrusive Load Monitoring: A Case Study. In The 2nd ACM Workshop on Device-Free Human Sensing (DFHS ’20), November 15, 2020, Virtual Event, Japan.

 We are happily looking forward to pitching the concept of NIAD to the community!

Stop! Exploring Bayesian Surprise for Load Disaggregation

In our latest paper, which is the result of the ongoing collaboration between our lab and SFU's Computational Sustainability Lab, we bring the concept of Bayesian Surprise to NILM. When has enough prior training been done? When has a NILM algorithm encountered new, unseen data? We apply the notion of Bayesian surprise to answer these important questions for both, supervised and unsupervised algorithms.

"Bayesian surprise quantifies how data affects natural or artificial observers, by measuring differences between posterior and prior beliefs of the observers" - ilab.usc.edu

Bayesian Surprise is measured in "wow"

We compare the performance of several NILM algorithms to establish a suggested threshold on two combined measures of surprise: postdictive surprise and transitional surprise.

We provide preliminary insights and clear evidence showing a point of diminishing returns for model performance with respect to dataset size, which can have implications for future model development, dataset acquisition, as well as aiding in model flexibility during deployment.

The paper is to appear at the 5th International Workshop on Non-Intrusive Load Monitoring (NILM'20): 

Richard Jones, Christoph Klemenjak, Stephen Makonin, and Ivan V. Bajić. 2020. Stop! Exploring Bayesian Surprise to Better Train NILM. In The 5th International Workshop on Non-Intrusive Load Monitoring (NILM ’20), November 18, 2020, Virtual Event, Japan.

An author's copy can be obtained from Christoph's personal website

We are looking forward to discussing this novel approach for NILM.

SYND - A Synthetic Energy Dataset

As with related Machine Learning problems, applications like Non-Intrusive Load Monitoring (NILM) require a sufficient amount of data to train and validate new approaches. With SynD, we present a synthetic energy dataset emulating the power consumption of residential buildings. The dataset is freely available and contains 180 days of synthetic power data on aggregate level and individual appliances.

The SynD dataset is based upon
measurements of real devices

SynD is the result of a custom simulation process that relies on power traces of real household appliances. During a measurement campaign in two Austrian households, we monitored 21 electrical household appliances. The main goal of the measurement campaign was to record representative power consumption patterns of those 21 appliances, where a each pattern is represented by the shape of the power consumption over time for a single operation.

Technical validation of SYND by comparing with other datasets

In contrast to datasets entirely based on measurement campaigns, such as our dataset GREEND, the SynD dataset is constructed from a simulation model utilizing the measured devices. This way, a synthetic but realistic power consumption dataset can be obtained. In a technical validation of the dataset we compared SynD with a number of measured datasets showing that SynD is well within the varaiation between mutual datasets.

Wilfried Elmenreich states “Usually I rely on measured data, but with the SYND dataset, we are among the first who created a convincing synthetic dataset.”

The full paper describing the dataset is available under an open access policy here:

Christoph Klemenjak, Christoph Kovatsch, Manuel Herold, and Wilfried Elmenreich. A synthetic energy dataset for non-intrusive load monitoring in households. Scientific Data, 7(1):1–17, 2020. (doi:10.6084/m9.figshare.11940324)

The SynD dataset can be obtained freely at the SynD Github Repository.

Adaptive Weighted Recurrence Graph blocks for event-based NILM

To this day, hyperparameter tuning remains a cumbersome task in Non-Intrusive Load Monitoring (NILM) research, as researchers and practitioners are forced to invest a considerable amount of time in this task.

This paper proposes adaptive weighted recurrence graph blocks (AWRG) for appliance feature representation in event-based NILM. An AWRG block can be combined with traditional deep neural network architectures such as Convolutional Neural Networks for appliance recognition. Our approach transforms one cycle per activation current into a weighted recurrence graph and treats the associated hyper-parameters as learn-able parameters.

We evaluate our technique on two energy datasets, the industrial dataset LILACD and the residential PLAID dataset. The outcome of our experiments shows that transforming current waveforms into weighted recurrence graphs provides a better feature representation and thus, improved classification results. It is concluded that our approach can guarantee uniqueness of appliance features, leading to enhanced generalisation abilities when compared to the widely researched V-I image features. Furthermore, we show that the initialisation parameters of the AWRG’s have a significant impact on the performance and training convergence.

We provide the implementation of AWRG on Github.  If you find this tool useful and use it (or parts of it), we ask you to cite the following work in your publications:

A. Faustine, L. Pereira and C. Klemenjak, "Adaptive Weighted Recurrence Graphs for Appliance Recognition in Non-Intrusive Load Monitoring," in IEEE Transactions on Smart Grid, doi: 10.1109/TSG.2020.3010621.

Learn more about the authors Anthony Faustine, Lucas Pereira and Christoph Klemenjak.

Supporting the Grid with Dynamic Residential Load Scheduling

Demand response (DR) for smart grids intends to balance the required power demand with the available supply resources. This is especially important with an increased amount of renewable energy sources since for most of them the energy yield cannot be shifted in time. For example, photovoltaic systems will provide their peak power at noon while customers might want to use energy at different times.

Residential load scheduling systems provide a solution to this problem by incentivizing consumers to use energy at times where production is high while motivating lower energy consumption in times of peak power. The goals of such residential load scheduling systems are therefore manifold: to cut peak power, to follow supply and to reduce the overall energy cost for the customer.

In a study we investigated different dynamic residential load scheduling systems with respect to optimal scheduling of household appliances on the basis of an adaptive consumption level pricing scheme (ACLPS). The proposed load scheduling system encourages customers to manage their energy consumption within the allowable consumption allowance of the proposed DR pricing scheme to achieve lower energy bills.

Dynamic pricing scheme motivating customers
to avoid energy consumption in peak periods

Simulation results show that employing the proposed approach benefits the customers by reducing their energy bill and the utility companies by decreasing the peak load of the aggregated load demand. For a given case study, the proposed residential load scheduling system based on ACLPS allows customers to reduce their energy bills by up to 53% and to decrease the peak load by  35%.

The full results are available in the paper

H. T. Haider, O. H. See, and W. Elmenreich. Dynamic residential load scheduling based on adaptive consumption level pricing scheme. Electric Power Systems Research, 133:27–35, 2016.

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.

Augmenting an Assisted Living Lab with Non-Intrusive Load Monitoring

The global epidemic of the COVID-19 virus required severe restrictions on travel and meetings. Among many other events, also the International Instrumentation and Measurement Technology Conference (I2MTC 2020) could not take place physically.

Therefore, we made our paper presentation in the form of a video:


In her talk, Hafsa Bousbiat describes how abnormal behavior can be detected among common household devices using Non-Intrusive Load Monitoring. The need for reducing our energy consumption footprint and the increasing number of electric devices in today’s homes is calling for new solutions that allow users to efficiently manage their energy consumption. Real-time feedback at device level would be of significant benefit for this application. In addition, the aging population and their wish to be more autonomous have motivated the use of this same real-time data to indirectly monitor the household’s occupants for their safety.
By breaking down aggregate power consumption into appliance level consumption, Non-Intrusive Load Monitoring allows for reducing the energy consumption footprint and has the potential to indirectly monitor the elderly and help them to fulfil their wish to be more autonomous in a secure manner. Therefore, the work aims to depict an architecture supporting non-intrusive measurement with a smart electricity meter and the handling of these data using an open-source platform that allows us to visualize and process real-time data about the total consumed energy. The proposed architecture is depicted in the figure below.

Proposed architecture for integrating an AAL with an energy monitoring system

More details about our work can be found in the full version of our paper here.

Please reference the paper as follows:
 
Hafsa Bousbiat, Christoph Klemenjak, Gerhard Leitner, and Wilfried Elmenreich. Augmenting an Assisted Living Lab with Non-Intrusive Load Monitoring. International Instrumentation and Measurement Technology Conference. May 2020.

This work was supported by DECIDE - Doctoral school on "Decision-making in a digital environment" at the University of Klagenfurt.

Reproducibility: Best practise examples

In the blog article "Why it is important to share your code and make your paper accessible", we advocated for sharing source code together with papers that involve a simulation-based evaluation. One argument is that such papers will be of higher utility to the reader and therefore, will create higher impact.

To help in this effort, the paper

Wilfried Elmenreich, Philipp Moll, Sebastian Theuermann, and Mathias Lux. Making simulation results reproducible - Survey, guidelines, and examples based on Gradle and Docker. PeerJ Computer Science, 5(e240):1–27, Dezember 2019. (doi:10.7717/peerj-cs.240) 

gives a good overview of which tools are suitable to provide your code in a useful way. It is also a paper that shares its code.

If you want to prepare datasets well, have a look at this paper, which provides a useful set of checks to be considered for electricity consumption datasets.

Christoph Klemenjak, Andreas Reinhardt, Lucas Pereira, Mario Berges, Stephen Makonin, and Wilfried Elmenreich. Electricity consumption data sets: Pitfalls and opportunities. In BuildSys ’19: The 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, pages 1–4. ACM New York, November 2019. (doi:10.1145/3360322.3360867)

Last but not least I would like to draw your attention to an excellent list of "Papers with Code", compiled by researcher Christoph Klemenjak:

 

On this page a list of papers targeting the field of load disaggregation can be accessed. And the name of the page does not lie - all of them come with code that can be freely accessed.

Happy researching!