Posts by Collection



YoMo: the Arduino-based smart metering board

Published in Springer Journal: Computer Science-Research and Development, 2015

This paper introduces a design for a low-cost smart meter system as well as the fundamentals of smart metering. The suggested design can switch loads, offers a variable sampling frequency, and provides measurement data such as active power, reactive and apparent power. Read more

Non-Intrusive Load Monitoring: A Review and Outlook

Published in SKILL Students Conference 2016, part of the INFORMATIK 2016 congress, 2016

Researchers provided multiple review papers on NILM so far, but none for students. With our paper we provide an introductory paper for students. In this paper we discuss the fundamental building-blocks of NILM, first giving a taxonomy of appliance models and device signatures and then explaining common supervised and unsupervised learning methods. Read more

Yay - an open-hardware energy measurement system for feedback and appliance detection based on the Arduino platform

Published in 2017 13th Workshop on Intelligent Solutions in Embedded Systems (WISES), 2017

We present a distributed measurement system that records and monitors electrical household appliances. Our low-cost measurement system integrates the YaY smart meter, a set of smart plugs, and several networked ambient sensors. In conjunction with energy advisor tools the presented measurement system provides an efficient low-cost alternative to commercial energy monitoring systems by surpassing them with machine learning techniques, appliance identification methods, and applications based on load disaggregation. Read more

On the Applicability of Correlation Filters for Appliance Detection in Smart Meter Readings

Published in 2017 IEEE International Conference on Smart Grid Communications, 2017

Communication systems utilise correlation filters to detect waveforms. In a broader sense, these filters examine the amount of resemblance between a template pattern and the input pattern. We assess the performance of the correlation filters on the real-world energy consumption dataset GREEND, which provides readings from smart meter data as well as appliance-level measurement equipment. Read more

Electricity Consumption Data Sets: Pitfalls and Opportunities

Published in Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Built Environments, Cities, and Transportation (BuildSys), 2019

There is a lack of widely agreed best practices for designing, deploying, and operating electrical data collection systems. We address this limitation by dissecting the collection methodologies used in existing data sets. Read more

Towards Comparability in Non-Intrusive Load Monitoring: On Data and Performance Evaluation

Published in 2020 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2019

In this paper, we draw attention to comparability in NILM with a focus on highlighting the considerable differences amongst common energy datasets used to test the performance of algorithms. We divide discussion on comparability into data aspects, performance metrics, and give a close view on evaluation processes. Read more

Augmenting an Assisted Living Lab with Non-Intrusive Load Monitoring

Published in 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2020

Our 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 to visualize and process real-time data about the total energy consumed. Read more

How does Load Disaggregation Performance Depend on Data Characteristics? Insights from a Benchmarking Study.

Published in ACM International Conference on Future Energy Systems (e-Energy ’20), 2020

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 data sets, 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. Read more

Device-Free User Activity Detection using Non-Intrusive Load Monitoring: A Case Study.

Published in The 2nd ACM Workshop on Device-Free Human Sensing (DFHS ’20), 2020

State-of-the-art disaggregation algorithms only provide support for the recognition of one appliance at a time, however. 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. Read more

On the Relationship between Seasons of the Year and Disaggregation Performance

Published in The 5th International Workshop on Non-Intrusive Load Monitoring (NILM’20), 2020

We utilize an auto-correlation function to detect usage patterns of dishwashers in each season. Then, we examine the dissimilarity across each season with the help of the Keogh Lower Bound measure. Finally, we conduct a disaggregation study using the REFIT dataset and relate the outcome to the dissimilarity across seasons. Read more

Stop! Exploring Bayesian Surprise to Better Train NILM.

Published in The 5th International Workshop on Non-Intrusive Load Monitoring (NILM ’20), 2020

When has enough prior training been done? When has a NILM algorithm encountered new, unseen data? This work applies the notion of Bayesian surprise to answer these important questions for both, supervised and unsupervised algorithms. Read more

Exploring Time Series Imaging for Load Disaggregation.

Published in The 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, andTransportation (BuildSys ’20), 2020

The main contribution presented in this paper is a comparison study between three common imaging techniques: Gramian Angular Fields, Markov Transition Fields, and Recurrence Plots. Read more



Grundlagenlabor: Energieinformatik - Lab on Energy Informatics.

Lab Course, University of Klagenfurt, Institute of Networked and Embedded Systems, 2018

The enhancement of the traditional power grid with elements of information and communication systems plays an important role in the ongoing energy transition. A key factor with regard to the success of this transition is the number of Smart Grid specialists in research and industry, which actively drive change. As a result of highly active research in the domain of Smart Grids and Energy Informatics, a plethora of novel methods and algorithms are being introduced and evaluated every year. Therefore, our innovative university class “Energy Informatics” combines the latest findings of international and domestic research with approved hands-on teaching material. Read more