DocumentCode :
2328188
Title :
Comparing SPO-tuned GP and NARX prediction models for stormwater tank fill level prediction
Author :
Flasch, Oliver ; Bartz-Beielstein, Thomas ; Davtyan, Artur ; Koch, Patrick ; Konen, Wolfgang ; Oyetoyan, Tosin Daniel ; Tamutan, Michael
Author_Institution :
Dept. of Comput. Sci. & Eng. Sci., Cologne Univ. of Appl. Sci., Gummersbach, Germany
fYear :
2010
fDate :
18-23 July 2010
Firstpage :
1
Lastpage :
8
Abstract :
The prediction of fill levels in stormwater tanks is an important practical problem in water resource management. In this study state-of-the-art CI methods, i.e., Neural Networks (NN) and Genetic Programming (GP), are compared with respect to their applicability to this problem. The performance of both methods crucially depends on their parametrization. We compare different parameter tuning approaches, e.g. neuro-evolution and Sequential Parameter Optimization (SPO). In comparison to NN, GP yields superior results. By optimizing GP parameters, GP runtime can be significantly reduced without degrading result quality. The SPO-based parameter tuning leads to results with significantly lower standard deviation as compared to the GA based parameter tuning. Our methodology can be transferred to other optimization and simulation problems, where complex models have to be tuned.
Keywords :
autoregressive processes; genetic algorithms; neural nets; tanks (containers); water resources; CI method; GA based parameter tuning; NARX prediction model; SPO based parameter tuning; SPO tuned GP; genetic programming; neural network; neuroevolution; sequential parameter optimization; stormwater tank fill level prediction; water resource management; Algorithm design and analysis; Artificial neural networks; Computational modeling; Optimization; Time series analysis; Training; Tuning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation (CEC), 2010 IEEE Congress on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-6909-3
Type :
conf
DOI :
10.1109/CEC.2010.5586172
Filename :
5586172
Link To Document :
بازگشت