Investigating Synthetic Data for Machine Learning Applications in Smart Homes

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.

ANTgen – the AMBAL-based NILM Trace generator

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

5th “Renewable Energies In Austria” report released

What do Austrians think about renewable energy technologies and related topics?

This question is examined annually by Prof. Nina Hampl and Dr. Robert Sposato in collaboration with Deloitte and Wien Energie in the Renewable Energies In Austria report series. At the core of this report lies a representative survey of over 1,000 participants conducted most recently in autumn 2019. Two clear signals emerged in this year’s report: a high level of acceptance for renewable energy technologies in general and broad support for climate policy measures.

As has been shown in the years before, the population holds a generally positive attitude towards renewable energy technologies: 77 % of the older respondents questioned are clearly in favour of building renewable energy technologies in their community. A number that is even higher among young respondents with 82 %. More specifically, photovoltaic power plants receive the broadest approval with 88%, followed by small hydropower with 74% and wind power with 67%.

An equally positive result was shown with respect to energy communities: Already around two thirds of the Austrian respondents are considering active participation in such communities, which allow private individuals to generate, consume, store and sell electricity or heat together. Austrian consumers attach particular importance to the fact that energy is generated locally and on the basis of renewable energy sources.

Albeit a little downslope from 2018 the group of potential electric car buyers also remains at a good level with 44 % considering to buy an electric vehicle as their next car. Again at 59 % young adults are even more interested in buying. Almost half of those interested in buying a car can imagine buying such a vehicle within the next five years.

Finally, with respect to the continuously dominant theme of climate change, the survey finds that there is a lot of support for planned policy measures regarding climate change mitigation. Two thirds of the respondents support the climate bonus for commuters who use public transport. A majority of 64 % would like an inexpensive 1-2-3 climate ticket for public transport, and 55 % consider CO 2 tariffs for non-climate-neutral imports to the EU to be sensible. Of particular interest to the Federal Government: an ecological tax reform with fewer taxes on work and fairer taxes on climate-damaging activities is conceivable for the majority surveyed respondents.

To find out more about the most recent report, download it here.

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.

Privacy vs. NILM: Obfuscating your Power Consumption with Load Hiding

With the development and introduction of smart metering, the energy information from costumers changes from infrequent manual meter readings to fine-grained energy consumption data. On the one hand, these measurements will lead to an improvement in costumers’ energy habits, but on the other hand, the fine-grained data produces information about a household and households’ inhabitants, which give rise to privacy issues because these monitoring results disclose user behavior which could be extracted by smart algorithms and techniques. The loss of privacy by load disaggregation and data mining is a huge upcoming smart grid and social issue which enforces the need for privacy-preserving techniques, which can be divided into the following three possibilities:

  1. Anonymization of metering data: The metering data and customer identity are separated by a third-party id
  2. Privacy-preserving metering data aggregation: Metering data is geographically encapsulated by aggregating the metering data of co-located consumers 
  3. Masking and obfuscation of metering data: Masking the power demand by adding or withdrawing the to the meter visible energy demand with the help of rechargeable batteries or controllable loads.
Load-based load hiding approach

In the paper

D. Egarter, C. Prokop, and W. Elmenreich. Load hiding of household’s power demand. In Proc. IEEE International Conference on Smart Grid Communications (SmartGridComm’14), Venice, Italy, 2014.

a state-of-the-art battery-based load hiding (BLH) technique, which uses a controllable battery to disguise the power consumption and a novel load hiding technique called load-based load hiding (LLH) are presented and compared. A load-based load hiding system controls appliances in a specific way to obfuscate a household’s power demand. For example, an electric water boiler could be instrumented to consume energy in a way that masks the power consumption of smaller household devices like coffee machines or a TV. There is no comfort loss expected for the customer: Overall, the boiler will consume a typical amount of energy and produce the expected amount of hot water.
Using this approach, however, reduces the predictability of your energy consumption, which is good for privacy, but a disadvantage for grid operators.

8 Open Positions at Alpen-Adria-Universität Klagenfurt

Alpen-Adria-Universität Klagenfurt (Austria) is establishing a Graduate School under the title ”Decision-making in a digital environment(DECIDE), and is therefore pleased to announce the following open positions:

8 Predoc Scientists (f/m)

These are 75 % employment positions (30 hours per week; Uni-KV: B1 – cf. www.aau.at/en/uni-kv), limited to 36 months. The minimum gross annual salary amounts to € 30.077,- and can increase depending on previous professional experience. Expected starting date is 1st October, 2019.

The graduate school “Decision-making in a digital environment” (DECIDE) is dedicated to interconnecting the ongoing digitalization and its effect on (human) decision-making. The distinctive feature of this graduate school is its interdisciplinary nature: The involved faculty members have a strong background in either social sciences and economics, computer science, engineering or psychology, perform research in their dedicated fields, and foster interdisciplinarity. The research projects to be carried out in the context of this graduate school address the current challenges of digitalization and decision-making from multiple perspectives, thereby exploiting the interdisciplinary setting of the graduate school. The faculty will encourage and strongly support successful candidates in their interdisciplinary research, in presenting their research at scientific conferences, as well as in publishing their work in international top journals and conference proceedings. The graduate school has a highly dynamic, familiar, and friendly attitude and thus provides a collaborative and very inspiring work environment with modern infrastructure.

Tasks and responsibilities:

  • independent research and scientific qualification within DECIDE with the goal to acquire a doctoral degree,
  • involvement in third-party funding proposals,
  • presentation of scientific results in publications and at conferences.

Required qualifications:

  • master or diploma degree in one of the following fields:
    • business administration,
    • cognitive science,
    • computer science,
    • economics (with a mathematical specialization),
    • information systems,
    • (technical) mathematics,
    • psychology,
    • electrical or computer engineering or
    • natural sciences (with a focus on economics),
  • good to very good study results with regard to the respective field,
  • good to very good written and spoken English skills.

All required qualifications are to be completed by 30th September, 2019

Desired qualifications:

  • good knowledge in one or more of the following areas:
    • simulation-based research methods (e.g., agent-based simulation, multi-agent simulation, Monte-Carlo simulation),
    • modelling of economic systems,
    • decision-support and recommendation systems,
    • decision-theory,
    • machine learning / artificial intelligence,
    • energy informatics,
    • networked autonomous systems,
    • diffusion processes,
    • decision-making and judgment,
    • management control systems,
    • quantitative research methods,
    • uni- and multivariate data analysis methods,
  • dedication to interdisciplinary research,
  • social and communication skills and ability to work independently,
  • basic experience in research projects,
  • subject-specific international, academic or practical experience.

The positions are aimed at the scientific training of graduates of a diploma or master’s programme with the goal of completing a doctoral study in the relevant field. Applications from persons already holding such a degree can therefore not be taken into account.

Alpen-Adria-Universität Klagenfurt seeks to increase the ratio of women in scientific positions and therefore encourages qualified female candidates to apply. Among equally qualified applicants, women will receive preferential consideration.

People with disabilities or chronic diseases, who fulfil the requirements, are particularly encouraged to apply. Applications from qualified candidates with a migration background are encouraged as well.

Applications should be submitted with the usual documents (application letter, CV, master/diploma thesis, certificates and further supporting documents) no later than 13 th March, 2019 mentioning the code 134/19 to Universität Klagenfurt, recruitment office. Applications can only be submitted online via www.aau.at/obf.

General information for applicants is available at www.aau.at/en/jobs/information.

More information on the graduate school on “Decision-making in a digital environment” is provided at www.aau.at/en/hda

Short-listed candidates will be invited to an interview. Travel and accommodation costs incurred during the application procedure cannot be reimbursed.

Call for Papers Energy Informatics 2019

Energy Informatics 2019 — Call for Papers
==========================================

The 8th DACH+ Conference on Energy Informatics
in Salzburg Austria from Sep 26, 2019 to Sep 27, 2019

Europe has put forward ambitious targets to reduce greenhouse gas emissions, to increase energy efficiency, and to raise the share of renewable energies. Energy Informatics is developing IT-based solutions necessary to achieve these targets.

The objective of the DACH+ conference series on Energy Informatics is to promote the research, development, and implementation of information and communication technologies in the energy domain and to foster the exchange between academia, industry, and service providers in the German-Austrian-Swiss region and its neighboring countries (DACH+).

We seek high-quality, original papers on smart energy systems and energy-efficient computing and communication.

Submissions describing theoretical contributions as well as system design, implementation, and experimentation are welcome. The list of topics of interest to the conference includes, but is not limited to:

* ICT for energy networks, micro-grids, and management of distributed generation.
* Energy-efficient mobility, charge management for electric vehicles, energy-aware traffic control, and smart grid integration of mobile storage.
* Smart buildings, digital metering, occupant comfort, and user interaction.
* Protocols and architectures for IT systems in the energy sector.
* Data analytics for smart energy systems and platforms for data analysis.
* Information systems for behavior change, market mechanisms, and business cases.
* Cross-cutting issues including: cyber security and privacy protection, interoperability, verification of networked smart grid systems, and more.

Submission and Publication
==========================

Submitted papers will be reviewed in a double-blind process.

Submission Deadline is on Apr 25, 2019

Notification Due Jun 10, 2019 and Final Version Due Jul 8, 2019

Accepted and presented papers will be published in the Springer Open Journal “Energy Informatics” https://energyinformatics.springeropen.com.

The Open Access fee for the journal article is included in the registration fee.

The conference language is English and papers must be written in English. We solicit full research papers (max. 18 pages of content plus 2 additional pages for references) as well as short papers (max. 10 pages of content plus 2 additional pages for references).

Submissions must be prepared following the Instructions for Authors, see https://www.energy-informatics.eu/.

Energy Informatics in Klagenfurt at a Glance

In the present day, the electric power grid faces an evolutionary step towards the smart grid. The smart grid is defined as the enhancement of the electric power grid with information and communication technology. This sort of digitisation will enable a bidirectional flow of energy and information within the power grid and provide several novel applications and allow to unlock the full potential of renewable energy technologies. To cope with the challenge of digitisation in power grids, key elements of future energy systems have to be explored and furthermore, computational methods have to be developed and refined.

The Smart Grids group, located at the University of Klagenfurt, contributes to this challenge by investigating how power meter readings can be analysed to discover solutions to sustainably increase the energy efficiency of energy systems.  

“We carried out a measurement campaign in eight selected households to track power consumption of individual electrical appliances for over one year. The main outcome was the GREEND dataset, which was analysed to gain further insights into energy consumption behaviour”, says Andrea Monacchi, the coordinator of the campaign. 

On basis of such data, policies can be formulated to improve energy efficiency by shedding of standby losses, postponement to off-peak periods, replacement of inefficient appliances, and operation curtailment. The networked power meter (smart meter) represents the key element in the transition towards the smart grid since such measurement equipment provides feedback to the users, other appliances, and the electric utility.  

“The smart meter is a vital tool for researchers to record the energy consumption of households and industrial buildings. On basis of the collected data, computational methods and effectivity of efficiency measures are evaluated”, states Christoph Klemenjak. “We developed an open-hardware smart metering board called YoMo, which is an extension unit for the Arduino platform. The YoMo is designed to monitor current flow and voltage level, as well as active, reactive, and apparent power at the feed point of households.”

In general, smart meters serve several purposes such as billing of consumed energy, providing immediate feedback to the users, or switching loads. Smart metering and fine-grained energy data are one of the major enablers for the future smart grid and an improved energy efficiency in smart homes. On the one hand these fine-grained measurements will lead to improved energy consumption habits, on the other hand the fine-grained data produces many questions with respect to privacy issues. To ensure both, household privacy and smart meter information, load hiding techniques were introduced to obfuscate the load demand visible at the household energy meter.  

“The load hiding technique we developed works with devices that are already in the system. By controlling these household appliances in a certain way, your power profile becomes scrambled”, Professor Elmenreich explains. 

Selected Publications 

C. Klemenjak, D. Egarter, and W. Elmenreich. YOMO-The Arduino based smart metering board. Computer Science – Research and Development (Springer), 2016. 


M. Pöchacker, D. Egarter, and W. Elmenreich. Proficiency of power values for load disaggregation. IEEE Transactions on Instrumentation and Measurement, 2016. 


D. Egarter, V. P. Bhuvana, and W. Elmenreich. PALDi: Online Load Disaggregation based on Particle Filtering. IEEE Transactions on Instrumentations and Measurement, 2015. 


D. Egarter, C. Prokop, and W. Elmenreich. Load Hiding of Household’s Power Demand. IEEE International Conference on Smart Grid Communications, 2014. 


A. Monacchi, D. Egarter, W. Elmenreich, S. D’Alessandro, and A. M. Tonello. GREEND: An energy consumption dataset of households in Italy and Austria. In Proc. IEEE International Conference on Smart Grid Communications, 2014. 

The Energy Informatics Lab

Data will be one of the most important resources in the future. Among other timely research questions, activities in energy informatics explore how data provided by advanced metering infrastructure (AMI) can be utilised in the most adequate and efficient way. In order to record energy data, the Energy Informatics Lab provides a wide range of measurement instruments such as smart meters, oscilloscopes, and self-designed power meters. Furthermore, modern computer infrastructure allows to evaluate novel computational methods for prediction and user feedback for future energy systems.

The Energy Informatics lab also integrates a well-equipped soldering work station and a 3D printer, which allows the researchers to craft prototypes and custom enclosures for all kinds of measurement equipment. “Previously our students often had problems apply the theoretic concepts they learned. The Energy Informatics Lab offers the possibility to try out things in practice, which gives them a different perspective,” states Professor Wilfried Elmenreich.

More detailed information can be found in our research blogs Energy InformaticsThe Smart Grid, and on the institute’s web page Networked and Embedded Systems.

Universitätsassistentin / Universitätsassistent (prae doc)

Am Institut für Produktions-, Energie- und Umweltmanagement, Abteilung Nachhaltiges Energiemanagement, Fakultät für Wirtschaftswissenschaften, im Beschäftigungsausmaß von 100 % (Uni-KV: B1) befristet auf die Dauer von 4 Jahren. Das monatliche Mindestentgelt für diese Verwendung beträgt € 2.731,- brutto (14 x jährlich) und kann sich auf Basis der kollektiv-vertraglichen Vorschriften durch die Anrechnung tätigkeitsspezifischer Vorerfahrungen erhöhen. Voraussichtlicher Beginn des Angestelltenverhältnisses ist ehest möglich.

Der Aufgabenbereich umfasst:

  • Mitwirkung bei Forschungsprojekten der Abteilung für Nachhaltiges Energiemanagement
  • selbstständiges wissenschaftliches Arbeiten und wissenschaftliche Weiterqualifikation mit dem Ziel der Erstellung einer Dissertation
  • Mitwirkung bei Lehrveranstaltungen der Abteilung sowie Durchführung von eigenen Lehrveranstaltungen
  • Betreuung von Studierenden
  • Mitarbeit bei administrativen und organisatorischen Aufgaben der Abteilung sowie gegebenenfalls in universitären Gremien
  • Mitarbeit bei der Konzeption, Beantragung, Umsetzung und Koordination von universitären Projekten und Veranstaltungen (Drittmittelprojekte, Gastvorträge, Konferenzen etc.)
  • Mitwirkung bei der Weiterentwicklung der Abteilung für Nachhaltiges Energiemanagement

Voraussetzungen für die Einstellung:

  • abgeschlossenes Master- oder Diplomstudium der Wirtschafts- und Sozialwissenschaften (insbesondere Betriebswirtschaftslehre mit dem Schwerpunkt Finanzwirtschaft oder Marketing; Volkswirtschaftslehre) oder eines nahestehenden Studienfachs (z. B. Psychologie mit einem Schwerpunkt auf Wirtschaftspsychologie)
  • Erfahrung bei der Anwendung von empirischen Forschungsmethoden (insbesondere im Bereich quantitativer Methoden)
  • gute Deutsch- und Englischkenntnisse in Wort und Schrift

Erwünscht sind:

  • ausgeprägte Team- und Kommunikationsfähigkeit
  • Auslandserfahrung
  • Grunderfahrungen in der Lehre (z. B. Studienassistenz, Tutorium) oder ausdrückliches Interesse an universitärer Lehrtätigkeit
  • ausdrückliches Interesse an den Forschungsthemen der Abteilung für Nachhaltiges Energiemanagement (z. B. soziale Akzeptanz von erneuerbaren Energietechnologien)

Diese Stelle dient der fachlichen und wissenschaftlichen Bildung von AbsolventInnen eines Master- bzw. Diplomstudiums mit dem Ziel des Abschlusses eines Doktorats-/Ph.D.-Studiums Sozial- und Wirtschaftswissenschaften. Bewerbungen von Personen, die bereits über ein facheinschlägiges Doktorat bzw. einen facheinschlägigen Ph.D. verfügen, können daher nicht berücksichtigt werden.

Die Universität strebt eine Erhöhung des Frauenanteils beim wissenschaftlichen Personal an und fordert daher qualifizierte Frauen zur Bewerbung auf. Frauen werden bei gleicher Qualifikation vorrangig aufgenommen.

Menschen mit Behinderungen oder chronischen Erkrankungen, die die geforderten Qualifikationskriterien erfüllen, werden ausdrücklich zur Bewerbung aufgefordert.

Allgemeine Informationen finden BewerberInnen unter www.aau.at/jobs/information.

Bewerbungen sind mit den üblichen Unterlagen (Anschreiben, Lebenslauf, Zeugniskopien und Arbeitszeugnisse) bis spätestens 5. April 2017 unter der Kennung 179/17 an die Alpen-Adria-Universität Klagenfurt, Dekanatekanzlei/Recruiting, ausschließlich über das Online-Bewerbungsformular unter www.aau.at/obf zu richten.

Nähere Auskünfte erteilt Univ.-Prof. Dr. Nina Hampl, E-Mail: nina.hampl@aau.at.

Es besteht kein Anspruch auf Abgeltung von entstandenen Reise- und Aufenthaltskosten, die aus Anlass des Aufnahmeverfahrens entstehen.

Beiträge zur Energieinformatik 2017 gesucht

6th D-A-CH+ Conference on Energy Informatics
8th Symposium on Communications for Energy Systems

5. bis 6. Oktober 2017, Lugano, Schweiz
www.energieinformatik2017.org

Europa hat sich zur Reduzierung der Treibhausgasemissionen, zur Erhöhung der
Energieeffizienz und des Anteils erneuerbarer Energien ehrgeizige Ziele gesetzt. Die Energieinformatik trägt mit der Entwicklung von IT-basierten Lösungen zur Erreichung dieser Ziele bei.
Die D-A-CH+ Energieinformatik Konferenzreihe dient der Förderung des Austausches zwischen Hochschulen, Industrie und Dienstleistern auf diesem Gebiet in Deutschland, Österreich und in der Schweiz. Dabei werden die Anwendung von Konzepten aus der Informatik, aber auch angrenzender Fachgebiete für Energiesysteme diskutiert und aktuelle Forschungs- und Umsetzungsprojekte werden vorgestellt.

Einreichungen werden einem double-blind Review-Prozess unterzogen. Akzeptierte Papers werden im Springer Journal Computer Science – Research and Development (CSRD) veröffentlicht. Konferenzsprache ist Englisch.

CALL FOR PAPERS als pdf zum Download

TIMELINE

8. Mai 2017 Submission Deadline
31. Juli 2017 Information on acceptance or rejection
21. August 2017 Submission of final papers