Abstract
Organic Computing tackles design issues of future technical systems by equipping them with self-x properties. A key self-x feature is self-optimisation, i.e. the system’s ability to adapt its dynamic behaviour to its current environment and requirements. In this article, it is shown how self-optimisation can be realised in a safe and goal-directed way, but also why it has to be enhanced and embedded into a suitable, modular system architecture. Then, a suitable framework for controlled self-optimisation is developed, which enables the system designer to give a priori guarantees of important dynamic system properties, and which ensures the system’s ability to cope dynamically with anomalies. The key features are online machine learning, which is complemented by incremental, local regularisation in a local Observer/Controller architecture as well as expressing anomalies by health signals, which are exploited to guide the learning process dynamically in order to achieve fast, but safe learning.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Brockmann, W.: Online machine learning for adaptive control. In: Proc. IEEE Int. Work. Emerging Technologies and Factory Automation, pp. 190–195 (1992)
Brockmann, W., Buschermöhle, A., Hülsmann, J.: A generic concept to increase the robustness of embedded systems by trust management. In: Proc. IEEE Conf. Systems, Man, and Cybernetics, SMC, pp. 2037–2044 (2010)
Brockmann, W., Horst, A.: Stabilizing the convergence of online-learning in neuro-fuzzy systems by an immune system-inspired approach. In: Proc. IEEE Int. Conf. Fuzzy Systems, FUZZ-IEEE, pp. 351–356 (2007)
Brockmann, W., Maehle, E., Mosch, F.: Organic fault-tolerant control architecture for robotic applications. In: IARP/IEEE-RAS/EURON Workshop on Dependable Robots in Human Environments (2005)
Brockmann, W., Rosemann, N.: Instantaneous anomaly detection in online learning fuzzy systems. In: Hoffmann, F., Cordón, O., Angelov, P., Klawonn, F. (eds.) 3rd Int. Workshop on Genetic and Evolving Fuzzy Systems, pp. 23–28. IEEE Press, Piscataway (2008)
Brockmann, W., Rosemann, N., Lintze, C.: Dynamic rate adaptation in self-adapting real-time control systems. In: Lohweg, V., Niggemann, O. (eds.) Proc. Workshop Machine Learning in Real-Time Applications—MLRTA 09. Lemgo Series on Industrial Information Technology, vol. 3 (2009). ISSN 1869-2087
Farrell, J., Polycarpou, M.: Approximation Based Control: Unifying Neural, Fuzzy and Traditional Adaptive Approximation Approaches. Wiley-Interscience, Hoboken (2006)
Geibel, P., Wysotzki, F.: Risk-sensitive reinforcement learning applied to control under constraints. J. Artif. Intell. Res. 24, 81–108 (2005)
Hafner, R., Riedmiller, M.: Neural reinforcement learning controllers for a real robot application. In: Proc. IEEE Int. Conf. Robotics and Automation, ICRA, pp. 2098–2103 (2007)
Hsu, C.F.: Self-organizing adaptive fuzzy neural control for a class of nonlinear systems. IEEE Trans. Neural Netw. 18(4), 1232–1241 (2007)
Kleinlützum, K., Brockmann, W., Rosemann, N.: Modellierung von Anomalien in einer modularen Roboter-Steuerung. In: Berns, K., Luksch, T. (eds.) Autonome Mobile Systeme 2007, pp. 89–95. Springer, Berlin (2007)
Mösch, F., Litza, M., Auf, E.S., Jakimovski, B., Maehle, E., Brockmann, W.: Organic fault-tolerant controller for the walking robot OSCAR. In: Proc. Work. Dependability and Fault Tolerance, ARCS. VDE Verlag GmbH (2007)
Peters, J., Schaal, S.: Natural actor-critic. Neurocomputing 71(7–9), 1180–1190 (2008)
Polycarpou, M.: Stable adaptive neural control scheme for nonlinear systems. IEEE Trans. Autom. Control 41(3), 447–451 (1996)
Riedmiller, M., Montemerlo, M., Dahlkamp, H.: Learning to drive a real car in 20 minutes. In: Proc. Frontiers in the Convergence of Bioscience and Information Technologies, FBIT, pp. 645–650 (2007)
Riedmiller, M., Peters, J., Schaal, S.: Evaluation of policy gradient methods and variants on the cart-pole benchmark. In: Proc. IEEE Int. Symp. Approximate Dynamic Programming and Reinforcement Learning, ADPRL, pp. 254–261 (2007)
Rosemann, N., Brockmann, W.: Concept for controlled self-optimization in online learning neuro-fuzzy systems. In: Hertzberg, J., Beetz, M., Englert, R. (eds.) KI 2007: Advances in Artificial Intelligence. LNAI, vol. 4667, pp. 498–501. Springer, Berlin (2007)
Rosemann, N., Brockmann, W.: Incremental regularization to compensate biased teachers in incremental learning. In: Proc.World Congress Computational Intelligence, pp. 1963–1970. IEEE Press, Piscataway (2010)
Rosemann, N., Brockmann, W., Neumann, B.: Enforcing local properties in online learning first order ts-fuzzy systems by incremental regularization. In: Proc. Int. Fuzzy Systems Assoc. World Congress / 2009 European Soc. for Fuzzy Logic and Technology Conf.—IFSA/EUSFLAT, pp. 466–471 (2009)
Rosemann, N., Buschermöhle, A., Brockmann, W.: Beschleunigung der Selbstoptimierung durch Selbstsimulation. In: Hoffmann, E., Hüllermeier, E. (eds.) Proc. Workshop Computational Intelligence, pp. 114–128. KIT Scientific, Karlsruhe (2009)
Rosemann, N., Hülsmann, J., Brockmann, W.: Disrupted Learning—Lernen Bei Harten Zustands - Oder Strukturwechseln. In: Proc. Workshop Computational Intelligence, pp. 105–117. Universitätsverlag Karlsruhe, Karlsruhe (2008)
Rosemann, N., Neumann, B., Brockmann, W.: Formale Eigenschaften des Silke-Ansatzes zur Kontrolle selbstoptimierender Systeme. In: Hegering, H.-G., Lehmann, A. (eds.) Proc. Informatik 2008 Beherrschbare Systeme—dank Informatik. LNI, vol. 134, pp. 755–762. Köllen, Bonn (2008)
Zhang, T., Ge, S.: Adaptive neural control of MIMO nonlinear state time-varying delay systems with unknown dead-zones and gain signs. Automatica 43(6), 1021–1033 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Basel AG
About this chapter
Cite this chapter
Brockmann, W., Rosemann, N., Maehle, E. (2011). A Framework for Controlled Self-optimisation in Modular System Architectures. In: Müller-Schloer, C., Schmeck, H., Ungerer, T. (eds) Organic Computing — A Paradigm Shift for Complex Systems. Autonomic Systems, vol 1. Springer, Basel. https://doi.org/10.1007/978-3-0348-0130-0_18
Download citation
DOI: https://doi.org/10.1007/978-3-0348-0130-0_18
Publisher Name: Springer, Basel
Print ISBN: 978-3-0348-0129-4
Online ISBN: 978-3-0348-0130-0
eBook Packages: Computer ScienceComputer Science (R0)