Title :
Energy demand forecast for a cogeneration system
Author :
Schellong, Wolfgang ; Hentges, François
Author_Institution :
Cologne Univ. of Appl. Sci., Cologne, Germany
Abstract :
The cogeneration of heat and power in a combined process saves primary energy resources and combats the climate change. Efficient forecast tools are necessary to predict the energy demand of the supply area of the cogeneration plant. The tools are needed to control and optimize the operating schedule of the different units of the cogeneration system. The paper describes the data management and the mathematical modeling of the power and heat demand by neural networks. The design of clusters depending on seasonal impacts and the influence of climate factors are investigated. The paper shows that neural networks with similar structure can be applied for both the power and the heat demand forecast. The experiences of the modeling process to real data sets are presented.
Keywords :
cogeneration; energy resources; environmental factors; load forecasting; neural nets; power engineering computing; climate factors; cogeneration plant; data management; energy demand forecast; heat demand forecast; mathematical modeling; neural networks; operating schedule; power demand forecast; primary energy resources; real data sets; seasonal impacts; Biological neural networks; Cogeneration; Neurons; Power demand; Predictive models; cogeneration; mathematical modeling; neural networks; power and heat demand forecast;
Conference_Titel :
Clean Electrical Power (ICCEP), 2011 International Conference on
Conference_Location :
Ischia
Print_ISBN :
978-1-4244-8929-9
Electronic_ISBN :
978-1-4244-8928-2
DOI :
10.1109/ICCEP.2011.6036344
