@article{WenningerMaierSchmidt2021, author = {Wenninger, Marc and Maier, Andreas and Schmidt, Jochen}, title = {DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany}, series = {Scientific Data}, volume = {8}, journal = {Scientific Data}, number = {176}, pages = {15}, year = {2021}, abstract = {Real-world domestic electricity demand datasets are the key enabler for developing and evaluating machine learning algorithms that facilitate the analysis of demand attribution and usage behavior. Breaking down the electricity demand of domestic households is seen as the key technology for intelligent smart-grid management systems that seek an equilibrium of electricity supply and demand. For the purpose of comparable research, we publish DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany. The dataset contains recordings of 15 homes over a period of up to 3.5 years, wherein total 50 appliances have been recorded at a frequency of 1 Hz. Recorded appliances are of significance for load-shifting purposes such as dishwashers, washing machines and refrigerators. One home also includes three-phase mains readings that can be used for disaggregation tasks. Additionally, DEDDIAG contains manual ground truth event annotations for 14 appliances, that provide precise start and stop timestamps. Such annotations have not been published for any long-term electricity dataset we are aware of.}, language = {en} } @article{StecherNeumayerRamachandranetal.2024, author = {Stecher, Dominik and Neumayer, Martin and Ramachandran, Adithya and Hort, Anastasia and Maier, Andreas and B{\"u}cker, Dominikus and Schmidt, Jochen}, title = {Creating a labelled district heating data set: From anomaly detection towards fault detection}, series = {Energy}, volume = {313}, journal = {Energy}, publisher = {Elsevier}, doi = {10.1016/j.energy.2024.134016}, pages = {134016}, year = {2024}, abstract = {For an efficient operation of district heating systems, being able to detect anomalies and faults at an early stage is highly desirable. Here, data-driven machine learning methods can be a cornerstone, particularly for fault detection in district heating substations, where the availability of heat meter data keeps increasing. However, the creation of data sets suitable for training such machine learning models poses challenges to researchers and practitioners alike. To address this problem, we propose a systematic and domain-specific process for data set creation for fault detection in the form of practical guidelines. This process concretizes the data science and data mining cross-industry standard CRISP-DM for the district heating domain and focuses on the process steps of goal definition, data acquisition and understanding, and data curation. We aim to enable researchers and practitioners to create data sets for fault detection in the district heating domain and therefore also enable the creation or improvement of machine learning models in this domain. In addition, we propose a minimum viable feature set for fault detection in district heating networks with the goal of enabling better cooperation between researchers and easier transfer of the resulting machine learning models, to better proliferate new progress in the field.}, language = {en} }