DocumentCode :
3737757
Title :
Predictive data analytics for agent-based management of electrical micro grids
Author :
Jonas Queiroz;Artur Dias;Paulo Leitão
Author_Institution :
Polytechnic Institute of Braganç
fYear :
2015
Firstpage :
4684
Lastpage :
4689
Abstract :
Micro grids represent an emergent vision to address the challenges imposed by recent trends in smart electrical grids, where the large-scale integration of distributed energy production units plays an important role. Nevertheless, the realization of this vision requires the use of advanced intelligent approaches to manage the micro grids elements, such as distributed renewable energy production units, loads and storage devices. Multi-agent systems provide a suitable framework to design and implement such systems, where autonomous agents are endowed with predictive data analytics capabilities, e.g., for the prediction of renewable energy production and consumption, taking advantage of the large amount of data produced in these environments. In this context, this paper presents an agent-based system for the management of micro grids, where predictive capabilities were embedded in agents to provide real-time data analytics. The proposed approach was applied to an experimental case study where a set of predictive models was tested for short and long term forecasting of the energy produced by photovoltaic units.
Publisher :
ieee
Conference_Titel :
Industrial Electronics Society, IECON 2015 - 41st Annual Conference of the IEEE
Type :
conf
DOI :
10.1109/IECON.2015.7392831
Filename :
7392831
Link To Document :
بازگشت