Advertisement

Linear and neural dynamical models for energy flows prediction in facility systems

  • Lucia Frosini
  • Giovanni Petrecca
Conference paper

Abstract

A procedure for the short-term prediction of the thermal energy consumption of an hospital is shown in this paper. At first, linear ARX models are built to get information on the influence of the input variables on the output of the system. Therefore, non-linear models based on feedforward neural networks (NNARX) are built using the information provided by the linear estimate. The results obtained from the ARX and NNARX models are compared, concluding that NNARX models provide better results than ARX models, but the analysis of ARX models is necessary to obtain guidelines in the choice of the best regression vector as input for neural models.

Keywords

Hide Neuron Mixed Integer Linear Programming Feedforward Neural Network Feedforward Network Recurrent Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Anglani N., Frosini L. and Petrecca G., “Forecasting and optimizing techniques for energy flows management in facility systems”, The 3 rd Annual International Conference on Industrial Engineering Theories, Applications and Practice, Hong Kong, Dec. 1998.Google Scholar
  2. [2]
    Sjöberg J., Hjalmerson H. and Ljung L., “Neural Networks in System Identification”, 10 th IFAC symposium on SYSID, Copenhagen, 1994.Google Scholar
  3. [3]
    Ljung L., 1995, System Identification Toolbox for use with MATLAB®. The MathWorks.Google Scholar
  4. [4]
    Pham D. T. and Liu X., 1995, Neural Networks for Identification, Prediction and Control. Springer Verlag.Google Scholar
  5. [5]
    Nørgaard M., 1997, Neural Network Based System Identification Toolbox. Technical Report, Department of Automation, Technical University of Denmark.Google Scholar
  6. [6]
    Haykin S., 1994, Neural Networks — A comprehensive foundation. Macmillan.Google Scholar
  7. [7]
    Jones S., Fengjer W., Hatch T. et al, “Performance Modeling for Economic Optimizing of Central Plant Operations”, International District Energy Association, 11 th Annual College/University Conference, Redondo Beach, Feb. 1998.Google Scholar
  8. [8]
    Prasad G., Swidenbank E. and Hogg B. W., “A Neural Net Model-based Multivariable Long-range Predictive Control Strategy applied in thermal power plant control”, IEEE Trans. Energy Conversion, Vol. 13, No. 2, Jun. 1998.Google Scholar
  9. [9]
    Irwin G., Brown M., Hogg B. W. et al, “Neural Network modelling of a 200 MW boiler system”, IEEE Proc. Control Theory Appl., Vol. 142, No. 6, Nov. 1995.Google Scholar

Copyright information

© Springer-Verlag London 2000

Authors and Affiliations

  • Lucia Frosini
    • 1
  • Giovanni Petrecca
    • 1
  1. 1.Department of Electrical EngineeringUniversity of PaviaPaviaItaly

Personalised recommendations