UnivIS
Information system of Friedrich-Alexander-University Erlangen-Nuremberg © Config eG 
FAU Logo
  Collection/class schedule    module collection Home  |  Legal Matters  |  Contact  |  Help    
search:      semester:   
 
 Layout
 
printable version

 
 
Forecasting of the power output of solar power plants

In recent years, the percentage of renewable energies in the total power production has increased steadily. Along with new types of power plants, new problems emerged of how these power plants can be efficiently integrated into the existing power grid. While the power production of conventional power plants can be influenced and controlled, the power production of for example solar power plants depends on uncontrollable influences like the current weather. In fact, the major cause for drop-offs in the power production are occlusions of the sun by individual clouds.

In this project we strive to develop a forecast system for the power output of solar power plants. The sky will be monitored with a camera located at the solar power plant. We will evaluate different methods of registering and forecasting the movement of the clouds to detect possible occlusions of the sun in the future. In a next step, it is then possible to predict the solar irradiation and therefore the power output of the power plant.

Project manager:
Prof. Dr.-Ing. Joachim Hornegger, Elli Angelopoulou, Ph.D., Akad. Rat

Project participants:
Dipl.-Phys. David Bernecker, PD Dr.-Ing. Christian Riess

Keywords:
computer vision; tracking; non-rigid registration

Duration: 1.10.2011 - 30.11.2015

Contact:
Bernecker, David
Phone +49 9131 85 27882, Fax +49 9131 85 27270, E-Mail: david.bernecker@cs.fau.de
Publications
Bernecker, David ; Riess, Christian ; Angelopoulou, Elli ; Hornegger, Joachim: Towards Improving Solar Irradiance Forecasts with Methods from Computer Vision. In: DAGM (Ed.) : Computer Vision in Applications Workshop (DAGM Graz, Austria 28.08). 2012, pp n/a.
Bernecker, David ; Riess, Christian ; Christlein, Vincent ; Angelopoulou, Elli ; Hornegger, Joachim: Representation Learning for Cloud Classification. In: Weickert, Joachim ; Hein, Matthias ; Schiele, Bernt (Ed.) : Pattern Recognition (35th German Conference on Pattern Recognition (GCPR) Saarbrücken 06.09.2013). 2013, pp 395-404.
[doi>10.1007/978-3-642-40602-7_42]
Bernecker, David ; Riess, Christian ; Angelopoulou, Elli ; Hornegger, Joachim: Continuous short-term irradiance forecasts using sky images. In: Solar Energy 110 (2014), pp 303-315
[doi>10.1016/j.solener.2014.09.005]

Institution: Chair of Computer Science 5 (Pattern Recognition)
UnivIS is a product of Config eG, Buckenhof