Correlation Filters for Load Classification @ IEEE SmartGridComm

We are happy to announce that our paper "On the Applicability of Correlation Filters for Appliance Detection in Smart Meter Readings" was accepted and presented at this year's SmartGridComm conference in Dresden.

With our load classification approach based on correlation filters, we aim to provide a low-cost non-Intrusive Load Monitoring (NILM) method for measurement equipment with limited computational capabilities such as networked sensors or smart plugs. One of these small devices to run such an algorithm on would be our YoMo metering board.

Abstract:

"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. In the domain of smart grids, many applications require the detection of active electrical appliances, their condition as well as their current state of operation. Furthermore, the identification of power eaters, the recognition of ageing effects, and the forecast of required maintenance represent important challenges in (home) energy management systems.

In this paper, we examine the applicability of correlation filters as a possible solution to meet such challenges. First, we introduce the concept of predictability to power consumption patterns of electrical appliances. Second, we present our concept and the implementation of correlation filters for this kind of application. The correlation filters utilise a particular consumption pattern of an electrical appliance to detect the respective appliance in energy readings from smart meters and smart plugs.

Lastly, 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. As the results approve, the correlation filters show a good performance for appliances with predictable consumption patterns such as refrigerators, dishwashers, or washing machines. Thus, we propose that future work should evaluate the applicability of correlation filters in appliance diagnosis systems."

Christoph Klemenjak presenting at the load classification session

C. Klemenjak and W. Elmenreich. On the Applicability of Correlation Filters for Appliance Detection in Smart Meter Readings. In Proceedings of the 2017 IEEE International Conference on Smart Grid Communications (SmartGridComm), Dresden, Germany, October 2017.


The Correlation Filters were evaluated on real-world energy consumption data provided by the GREEND dataset, which is available at Sourceforge:

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 (SmartGridComm'14), Venice, Italy, 2014.

Mjölnir: The Movie

Because of the great interest in Mjölnir, we decided to maka a short introduction video providing a walk through the system.

Find out more about the idea behind the system in

A. Monacchi, F. Versolatto, M. Herold, D. Egarter, A. M. Tonello, and W. Elmenreich. An open solution to provide personalized feedback for building energy management. ArXiv preprint arXiv:1505.01311, 2015.

or download the software at mjoelnir.sourceforge.net.
 

Building Management with Mjölnir

We recently announced the release of the stable version 0.2 of our open source energy management system Mjölnir at http://mjoelnir.sourceforge.net.

While the tool targeted so far mostly "disaggregated" device-level energy and power usage, we have now introduced full support for circuit-level measurements (buildings, rooms) which unlocks a considerable potential for further data analysis.

The DIN-RAIL module running the measurement system

As most of energy meters use the industrial automation system ModBus, we have been looking for possible shields to extend our open hardware solution with RS485 communication. We finally selected this RPi hat from Libelium while the meter is the Carlo Gavazzi EM24. The implementation is eased by the Libelium ArduPi library, which makes the C code written for Arduino compatible with the Raspberry Pi. The data is then being sent to our servers through a REST interface.

The overall component shown on the picture is therefore a low cost solution able to retrieve remote measurements via the RS485/ModBus and the USB/ZigBee network. This opens for the future integration of other measurement units, such as water and gas meters.

The support of circuit-level measurements required changes on the Mjölnir system.

The system is now organised in buildings, rooms and devices. A circuit is described by its ID and can be associated to a single building or room.
As usual, the code of the gateway is available on SourceForge, along with the dashboard system.

Bibliography:

1. A. Monacchi, F. Versolatto, M. Herold, D. Egarter, A. M. Tonello, and W. Elmenreich. An open solution to provide personalized feedback for building energy management. ArXiv preprint arXiv:1505.01311, 2015.

Impressions from IEEE Conference on Smart Grid Communication 2014

The IEEE Conference on Smart Grid Communication 2014 was held from November the 13th to 14th in Venice. Wilfried Elmenreich, Dominik Egarter and Andrea Monacchi from our group participated at this event.

The conference was organized in 5 different symposia:

• Communications and Networks to enable the Smart Grid
• Cyber Security and Privacy
• Architectures, Control and Operation for Smart Grid, Microgrids and Distributed Resources
• Demand Response and Dynamic Pricing
• Data Management and Grid Analytics

Dominik presented his paper Load Hiding of Household's Power Demand, (Dominik Egarter, Christoph Prokop, Wilfried Elmenreich) in the session on "Cyber Security and Privacy".

Andrea gave a talk about his paper GREEND: An Energy Consumption Dataset of Households in Italy and Austria (Andrea Monacchi, Dominik Egarter, Wilfried Elmenreich, Salvatore D’Alessandro, Andrea M. Tonello) in the "Data Management and Grid Analytics" session.

GREEND: An Energy Consumption Dataset of Households in Italy and Austria

Some days ago, we got notice that our paper "GREEND: An Energy Consumption Dataset of Households in Italy and Austria" is accepted at the IEEE SmartGridComm 2014. The SmartGridComm 2014 will take place in Venice, a fascinating and marvelous Italian city, on November 3-6, 2014.

GREEND: An Energy Consumption Dataset of Households in Italy and Austria, 
Andrea Monacchi, Dominik Egarter, Wilfried Elmenreich, Salvatore D’Alessandro, Andrea M. Tonello

Home energy management systems can be used to monitor and optimize consumption and local production from renewable energy. To assess solutions before their deployment, researchers and designers of those systems demand for energy consumption datasets. In this paper, we present the GREEND dataset, containing detailed power usage information obtained through a measurement campaign in households in Austria and Italy. We provide a description of consumption scenarios and discuss design choices for the sensing infrastructure. Finally, we bench- mark the dataset with state-of-the-art techniques in load disaggregation, occupancy detection and appliance usage mining.

An authors' version is available in arXiv: http://arxiv.org/abs/1405.3100

The GREEND dataset is publicly availble, donwload the newest version at https://sourceforge.net/projects/greend/files/GREEND_0-2_300615.zip

Load Hiding of Household's Power Demand

Our publication "Load Hiding of Household's Power Demand" is accepted at the IEEE SmartGridComm 2014. The SmartGridComm 2014 will take place in Venice, a fascinating and marvelous Italian city, on November 3-6, 2014.

Load Hiding of Household's Power Demand, Dominik Egarter, Christoph Prokop, Wilfried Elmenreich

With the development and introduction of smart metering, the energy information for costumers will change from infrequent manual meter readings to fine-grained energy consumption data. On the one hand these fine-grained measurements will lead to an improvement in costumers’ energy habits, but on the other hand the fined-grained data produces in- formation about a household and also households’ inhabitants, which are the basis for many future privacy issues. To ensure household privacy and smart meter information owned by the household inhabitants, load hiding techniques were introduced to obfuscate the load demand visible at the household energy meter. In this work, 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. An LLH system uses an controllable household appliance to obfuscate the household’s power demand. We evaluate and compare both load hiding techniques on real household data and show that both techniques can strengthen household privacy but only LLH can increase appliance level privacy.

An authors' version is available in arXiv: http://arxiv.org/abs/1406.2534