Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 2019, p.1192-1198
Deep Learning in Building Management Systems over NDN: Use Case of Forwarding and HVAC Control
Ist Teil von
2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 2019, p.1192-1198
Ort / Verlag
IEEE
Erscheinungsjahr
2019
Link zum Volltext
Quelle
IEEE Electronic Library (IEL)
Beschreibungen/Notizen
Recently, the building sector has been considered as one of the largest consumers of energy. Therefore the building industry was actually facing more and more challenges of over-dimensioning and control optimization of energy use. On another side, recent successful applications of Deep learning such as healthcare or speech and image recognition aroused a lot of research on further applications that could be genuinely self-improving. In this paper, we propose a new approach for intelligent forwarding of data and HVAC control based on deep learning in Building Management Systems (BMS) that could improve forwarding performance and energy consumption. As an application field, we chose the Named Data Networking (NDN) communication model along with a BACnet IP/KNX based installation. Simulation results of the forwarding model were promising in terms of cross-validation score and prediction.