Monthly Archives: June 2020

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.