TY - CHAP A1 - Wenninger, Marc A1 - Schmidt, Jochen A1 - Goeller, Toni T1 - Appliance Usage Prediction for the Smart Home with an Application to Energy Demand Side Management - And Why Accuracy is not a Good Performance Metric for this Problem. T2 - 6th International Conference on Smart Cities and Green ICT Systems (SMARTGREENS) N2 - Shifting energy peak load is a subject that plays a huge role in the currently changing energy market, where renewable energy sources no longer produce the exact amount of energy demanded. Matching demand to supply requires behavior Changes on the customerside, which can be achieved by incentives suchas Real-Time-Pricing (RTP). Various studies show that such incentives cannot be utilized without a complexity reduction, e.g., by smart home automation systems that inform the customer about possible savings or automatically schedule appliances to off-peak load phases. We propose a probabilistic appliance usage prediction based on historical energy data that can be used to identify the times of day where an appliance will be used and therefore make load shift recommendations that suite the customer’s usage profile. A huge issue is how to provide a valid performance evaluation for this particular problem. We will argue why the commonly used accuracy metric is not suitable, and suggest to use other metrics like the area under the Receiver Operating Characteristic (ROC) curve, Matthews Correlation Coefficient (MCC) or F1-Score instead. KW - Real Time Pricing (RTP) KW - Household Appliance Usage Prediction KW - Demand Side Management Y1 - 2017 ER - TY - CHAP A1 - Goeller, Toni A1 - Wenninger, Marc A1 - Schmidt, Jochen T1 - Towards Cost-Effective Utility Business Models - Selecting a Communication Architecture for the Rollout of New Smart Energy Services T2 - Proceedings of the 7th International Conference on Smart Cities and Green ICT Systems - Volume 1: SMARTGREENS N2 - The IT architecture for meter reading and utility services is at the core of new business models and has a decisive role as an enabler for resource efficiency measures. The communication architecture used by those services has significant impact on cost, flexibility and speed of new service rollout. This article describes how the dominant system model for meter reading came about, what alternative models exist, and what trade-offs those models have for rollout of new services by different stakeholders. Control of a self learning home automation system by dynamic tariff information (Real-Time-Pricing) is given as an application example. KW - Smart Meter, Advanced Metering Infrastructure, AMI Y1 - 2018 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:861-opus4-8332 SN - 978-989-758-292-9 SP - 231 EP - 237 PB - SciTePress ER - TY - JOUR A1 - Wenninger, Marc A1 - Maier, Andreas A1 - Schmidt, Jochen T1 - DEDDIAG, a domestic electricity demand dataset of individual appliances in Germany JF - Scientific Data N2 - 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. KW - Machine Learning Y1 - 2021 UR - https://doi.org/10.1038/s41597-021-00963-2 VL - 8 IS - 176 ER - TY - CHAP A1 - Bayerl, Sebastian P. A1 - Wenninger, Marc A1 - Schmidt, Jochen A1 - Wolff von Gudenberg, Alexander A1 - Riedhammer, Korbinian T1 - STAN: A stuttering therapy analysis helper T2 - 2021 IEEE Spoken Language Technology Workshop (SLT) N2 - Stuttering is a complex speech disorder identified by repetitions, prolongations of sounds, syllables or words and blockswhile speaking. Specific stuttering behaviour differs strongly,thus needing personalized therapy. Therapy sessions requirea high level of concentration by the therapist. We introduce STAN, a system to aid speech therapists in stuttering therapysessions. Such an automated feedback system can lower the cognitive load on the therapist and thereby enable a more consistent therapy as well as allowing analysis of stuttering over the span of multiple therapy sessions. KW - Machine Learning Y1 - 2021 ER - TY - CHAP A1 - Wenninger, Marc A1 - Bayerl, Sebastian P. A1 - Maier, Andreas A1 - Schmidt, Jochen T1 - Recurrence Plot Spacial Pyramid Pooling Network for Appliance Identification in Non-Intrusive Load Monitoring T2 - 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) N2 - Parameter free Non-intrusive Load Monitoring (NILM) algorithms are a major step toward real-world NILM scenarios. The identification of appliances is the key element in NILM. The task consists of identification of the appliance category and its current state. In this paper, we present a param- eter free appliance identification algorithm for NILM using a 2D representation of time series known as unthresholded Recurrence Plots (RP) for appliance category identification. One cycle of voltage and current (V-I trajectory) are transformed into a RP and classified using a Spacial Pyramid Pooling Convolutional Neural Network architecture. The performance of our approach is evaluated on the three public datasets COOLL, PLAID and WHITEDv1.1 and compared to previous publications. We show that compared to other approaches using our architecture no initial parameters have to be manually tuned for each specific dataset. KW - NILM KW - V-I trajectory KW - Recurrence Plot Y1 - 2021 UR - https://doi.org/10.1109/ICMLA52953.2021.00025 SP - 108 EP - 115 ER - TY - RPRT A1 - Auer, Veronika A1 - Beneken, Gerd A1 - Brummer, Benjamin A1 - Châteauvieux-Hellwig, Camille A1 - Engler, Benjamin A1 - Gilly, Alexander A1 - Hagl, Rainer A1 - Hummel, Felix A1 - Hummel, Sabine A1 - Karlinger, Peter A1 - Knorr, Ludwig A1 - Köster, Heinrich A1 - Kucich, Martin A1 - Mecking, Simon A1 - Rabold, Andreas A1 - Sandor, Viktor A1 - Schalk, Daniel A1 - Schanda, Ulrich A1 - Schemme, Michael A1 - Schiffner, Ivonne A1 - Schmidt, Jochen A1 - Schugmann, Reinhard A1 - Seidlmeier, Heinrich A1 - Sigg, Ferdinand A1 - Stauss, Kilian A1 - Sussmann, Monika A1 - Wellisch, Ulrich A1 - Wenninger, Marc A1 - Wittmann, Josef A1 - Zscheile, Matthias T1 - Jahresbericht 2016, Forschung - Entwicklung - Innovation N2 - Mit dem jährlich erscheinenden Forschungsbericht möchte die Hochschule Rosenheim einen Einblick in ihre vielfältigen Projekte und Aktivitäten der angewandten Forschung und Entwicklung geben. Im Jahresbericht 2016 wird über Vorhaben im Jahr 2016 berichtet. T3 - Schriftenreihen - Forschungsbericht - 5 KW - Forschung Y1 - 2017 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:861-opus4-12282 ER - TY - JOUR A1 - Wenninger, Marc A1 - Bayerl, Sebastian P. A1 - Schmidt, Jochen A1 - Riedhammer, Korbinian T1 - Timage – A Robust Time Series Classification Pipeline JF - Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series. ICANN 2019. Lecture Notes in Computer Science N2 - Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset. KW - neural networks Y1 - 2019 VL - 11730 PB - Springer CY - Cham ER - TY - JOUR A1 - Wenninger, Marc A1 - Stecher, Dominik A1 - Schmidt, Jochen T1 - SVM-Based Segmentation of Home Appliance Energy Measurements JF - Proceedings 8th IEEE International Conference on Machine Learning and Applications -ICMLA 2019 N2 - Generating a more detailed understanding of domestic electricity demand is a major topic for energy suppliers and householders in times of climate change. Over the years there have been many studies on consumption feedback systems to inform householders, disaggregation algorithms for Non-Intrusive-Load-Monitoring (NILM), Real-Time-Pricing (RTP) to promote supply aware behavior through monetary incentives and appliance usage prediction algorithms. While these studies are vital steps towards energy awareness, one of the most fundamental challenges has not yet been tackled: Automated detection of start and stop of usage cycles of household appliances. We argue that most research efforts in this area will benefit from a reliable segmentation method to provide accurate usage information. We propose a SVM-based segmentation method for home appliances such as dishwashers and washing machines. The method is evaluated using manually annotated electricity measurements of five different appliances recorded over two years in multiple households. KW - Machine Learning Y1 - 2019 SP - 1666 EP - 1670 ER -