Paper: Using Knowledge Discovery for Autonomous Decision Making in Smart Grid Nodes


Smart and energy efficient (office) buildings do not only have to implement smart sensors and actuators, they should also be able to be optimized to be as energy efficient as possible based on the behavior of the user. This paper focuses on knowledge extraction of a smart building and automatic rule creation based on that knowledge. We are using different methods to analyze this data, create the appropriate rule set based on the extracted data and based on the correlation and dependencies of different datasets. The methods are also detecting changes in the data (resp. the behavior of the user) and adapts the ruleset accordingly.

Authors: Pragya Kirti Gupta, Ann-Katrin Gibtner, Markus Duchon, Dagmar Koss, Bernhard Schätz

ICIT 2015

Paper: Smartphones as Multisensors in Smart Building Environments


This paper aims to integrate smartphones into a smart building environment. Stress is laid upon integrating the sensor capabilities of the smartphones which has not been done previously. In addition a profile system is introduced to allow users to automatically adjust room settings. To assign users and data to the room they are currently located in, a localization mechanism is proposed. After presenting relevant aspects of the system a proof of concept is evaluated.

Authors: Philipp Lauchner, Peter Bludau, Markus Duchon and Dagmar Koss

LBAS conference 2014

Paper: An Energy Management System for a Smart Office Environment


The evolution of the electricity grid towards the smart grid paradigm is fostering the integration of distributed renewable energy sources in Smart Buildings: a combination of local power generation, battery storage and controllable loads can greatly increase the energetic self-sufficiency of a Smart Building, enabling it to operate in islanded mode or to participate in an Automatic Demand Response framework, thus taking advantage of time-variable tariffs to achieve economical savings.

This paper proposes an energy management system specifically tailored for a Smart Office building, which relies on actual data and on forecasting algorithms to predict the future patterns of both local energy generation and power loads. Performance is compared to the optimal energy usage scheduling, which would be obtained assuming the exact knowledge of the future energy production and consumption trends, showing gaps below 10% w.r.t. the optimum.

Authors: Cristina Rottondi, Markus Duchon, Dagmar Koss, Giacomo Verticale and Bernhard Schätz

MidSEE 2015 conference

Paper: Advancement of a Sensor Aided Smart Grid Node Architecture


Flexible, extensible and lightweight architectures are necessary to allow the participation of small energy producers in the smart grid. In addition to an intelligent energy management system on top of a home control system these nodes exchange information with other smart grid components to establish energy trading as well as a stable and scalable smart grid subsystem. In order to support future developments in the areas of communication protocols, sens- ing and metering devices, actuators, production and stor- age technologies a flexible and extensible design is essential. The proposed enhanced architecture supports a distributed deployment on small and energy-saving computing devices to decrease visibility and energy consumption as much as possible. In the further implementation of the layered approach we distinguish between core components and func- tional components. Connected via an enterprise message bus the components can be implemented using different programming languages and deployed on various networked devices following the SOA principles. The core components form a consistent system including authentication, configuration, persistent storage and registration of functional com- ponents. Hereby, the registration component allows for the easy integration of different sensors and actuators and is responsible for the interaction of the core system and the lower device layer. Other functional components support energy production and consumption forecasting, analysis of historical data, and self-optimization capabilities. In this paper, the design and functionality of our layered and component based architecture is presented. The implemented system provides open interfaces for the integration and utilization of additional smart grid and smart home components in a plug and play manner.

Authors: Markus Duchon, Pragya Kirti Gupta, Dagmar Koss, Denis Bytschkow, Bernhard Schätz and Sebastian Wilzbach

CyperC Conference 2014

Paper: Establishing a Smart Grid Node Architecture and Demonstrator in an Office Environment Using the SOA Approach


The introduction of low-cost renewable energy production, e.g., by photovoltaic, has turned classical grid nodes like homes and offices in prosumers, taking an active role in smart energy systems by merging home-automation and energy production functionality. However, to become a self-balancing element of a stable smart grid, supporting the energy-aware cooperative production, storage, and consumption, a scalable software is needed, tailored for smart micro grids and their integration in large-scale systems. In the following, the imple- mentation of a layered SOA-based distributed architecture is presented, that provides open interfaces simplifying the plug- and-play of hardware and software components.

Authors: Dagmar Koß, Denis Bytschkow, Pragya Kirti Gupta, Bernhard Schätz, Florian Sellmayr and Steffen Bauereiß

SE4SG Workshop @ ICSE 2012