Abstract
The use of genetic algorithms to design neural networks for real-time control of flows in sewerage networks is discussed. In many control applications, standard supervised learning techniques (such as back-propagation) cannot be used through lack of training data. Reinforcement learning techniques, such as genetic algorithms, are a computationally-expensive but viable alternative if a simulator is available for the system in question. The paper briefly describes why genetic algorithms and neural networks were selected, then reports the results of a feasibility study. This demonstrates that the approach does indeed have merits. The implications of high computational cost are discussed, in terms of scaling up to significantly complex problems.
Similar content being viewed by others
References
Green JM, Chapman RE. Future Role of RTC. Conf RTC On-line, Oxford Conferences, 1–2 November 1993
Petersen, SO. Real time control of urban drainage systems. MSc Thesis. Department of Environmental Engineering, Technical University of Denmark, August 1987
Koza JR. Genetic programming: On the programming of computers by means of natural selection. MIT Press, 1992
Goldberg DE. Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, 1989.
Haykin S. Neural Networks: A comprehensive foundation. Macmillan, New York, 1994
Dill FA, Deer BC. An exploration of genetic algorithms for the selection of connection weights in dynamical neural networks. Proc IEEE91 National Aerospace and Electronics Conf NAECON91, IEEE, NY
Montana DJ, Davis L. Training neural networks using genetic algorithms. Proc 1989 Int Joint Conf Artificial Intelligence, 1989.
Harp SA, Samad T, Guha A. Towards the genetic synthesis of neural networks. Int Conf Genetic Algorithms. ICGA89, 1989
Anthony D, Hines E, Barham J, Taylor D. The use of genetic algorithms to learn the most appropriate inputs to a neural network. Proc IASTED Int Symposium Artificial Intelligence Application and Neural Networks. AINN90, ACTA, Anaheim, CA
Baba, N. Utilisation of stochastic automata and genetic algorithms for neural network learning. In: Parallel Problem Solving from Nature 2. Elsevier, 1992
Hunter A. The Sugal Genetic Algorithm Simulator. http://osiris.sund.ac.uk/ahu/sugal/home.html
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hunter, A., Hare, G. & Brown, K. Genetic design of real-time neural network controllers. Neural Comput & Applic 6, 12–18 (1997). https://doi.org/10.1007/BF01670149
Issue Date:
DOI: https://doi.org/10.1007/BF01670149