%0 Conference Proceedings
%T Opportunities of Big Data Tools in Smart Energy Systems
%+ Bergische Universität Wuppertal
%A Birkner, Peter
%Z Part 2: SmartER Europe 2017
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 3rd and 4th International Conference on Smart Energy Research (SmartER Europe 2016 and 2017)
%C Essen, Germany
%Y Christian Derksen
%Y Christoph Weber
%I Springer International Publishing
%3 Smart Energy Research. At the Crossroads of Engineering, Economics, and Computer Science
%V AICT-495
%P 161-177
%8 2017-02-09
%D 2017
%R 10.1007/978-3-319-66553-5_12
%K “Energiewende”
%K System transformation
%K Digitalization
%K Renewables
%K Demand side management
%K Smart grid
%K Smart market
%K Big data
%K Neuronal networks
%K Predictive maintenance
%K Asset condition
%K Failure identification
%K Virtual power plants
%K Cellular systems
%Z Computer Science [cs]Conference papers
%X The implementation of an energy supply system based on dispersed, small and volatile electricity sources with limited annual operational availability requires a smart structure and a smart operation. The necessity increases when also efficient but powerful and highly volatile applications like electrical vehicles and heat pumps are integrated. A smart energy system consists of the main components smart market and smart grids. Smart markets intend to balance generation and demand with respect to time, while smart grids are focusing on the optimized use of the grid infrastructure by employing the existing non-linear grid utilization through active capacity management. Smart grids are managing the location aspect. Important technical devices with respect to smart energy systems are the so-called power-to-X (P2G) technologies. They are coupling electricity with other forms of energy, like gas, heat, cold or mobility and thus allow, to cope with a temporary overproduction or the lack of generation.A smart energy system has a filigree and complex structure, which needs active control and coordination. Therefore, static and dynamic data are required. Energy and digitation are merging in this respect. Instruments like big data tools or neuronal networks become important and allow the implementation of new options like predictive maintenance, generation and load forecast as well as failure identification and evaluation of asset condition. Finally, the data can be used in order to identify options for the increase of energy efficiency in the building stock or the public infrastructure.
%G English
%Z TC 12
%2 https://inria.hal.science/hal-01691200/document
%2 https://inria.hal.science/hal-01691200/file/450780_1_En_12_Chapter.pdf
%L hal-01691200
%U https://inria.hal.science/hal-01691200
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC12
%~ IFIP-AICT-495
%~ IFIP-SMARTER