NN-Based Iterative Learning Control Under Resource Constraints: A Feedback Scheduling Approach

  • Feng Xia
  • Youxian Sun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3498)


The problem of neural network based iterative learning control (NNILC) in a resource-constrained environment with workload uncertainty is examined from the real-time implementation perspective. Thanks to the iterative nature of the NNILC algorithm, it is possible to abort the optimization routine before it reaches the optimum. Taking into account the impact of resource constraints, a feedback scheduling approach is suggested, with the primary goal of maximize the control performance. The execution time of the NNILC task is dynamically adjusted to achieve a desired CPU utilization level. Thus a tradeoff is done between the available CPU time and the control performance. For the sake of easy implementation, a practical solution with a dynamic iteration stop criterion is proposed. Preliminary simulation results argue that the proposed approach is efficient and delivers better performance in the face of workload variations than the traditional NNILC algorithm.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Narendra, K.S., Parthasarathy, K.: Identification and Control of Dynamical Systems Using Neural Networks. IEEE Trans. on Neural Networks 1, 4–27 (1990)CrossRefGoogle Scholar
  2. 2.
    Chow, T.W.S., Li, X.D., Fang, Y.: A Real-Time Learning Control Approach for Nonlinear Continuous-Time System Using Recurrent Neural Networks. IEEE Trans. on Industrial Electronics 47, 478–486 (2000)CrossRefGoogle Scholar
  3. 3.
    Xiong, Z., Zhang, J.: A Batch-to-batch iterative Optimal Control Strategy Based on Recurrent Neural Network Models. Journal of Process Control 15, 11–21 (2005)CrossRefGoogle Scholar
  4. 4.
    Wang, F., Li, M.: Optimal Iterative Control of Unknown Nonlinear Systems Using Neural Networks. In: Proc. 36th CDC, San Diego, California, USA, pp. 2201–2206 (1997)Google Scholar
  5. 5.
    Årzen, K.-E., et al.: Integrated Control and Scheduling. Research report: ISSN 0820-5316, Lund Institute of Technology (1999)Google Scholar
  6. 6.
    Cervin, A., Eker, J., Bernhardsson, B., Årzén, K.-E.: Feedback-Feedforward Scheduling of Control Tasks, vol. 23 (2002)Google Scholar
  7. 7.
    Henriksson, D., Cervin, A., Åkesson, J., Årzén, K.-E.: Feedback Scheduling of Model Predictive Controllers. In: Proc. 8th IEEE RTAS, San Jose, CA, pp. 207–216 (2002)Google Scholar
  8. 8.
    Xu, J.X., Tan, Y.: Linear and Nonlinear Iterative Learning Control. In: Thoma, M. (ed.). Lecture Notes in Control and Information Sciences, vol. 291, Springer, Heidelberg (2003)Google Scholar
  9. 9.
    He, Y., Li, X.: Neural Network Control Technology and Its Applications. Science Press, Beijing (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Feng Xia
    • 1
  • Youxian Sun
    • 1
  1. 1.National Laboratory of Industrial Control Technology, Institute of Modern Control EngineeringZhejiang UniversityHangzhouChina

Personalised recommendations