Publication

Gaussian-process-based demand forecasting for predictive control of drinking water networks

Conference Article

Conference

International Conference on Critical Information Infrastructures Security (CRITIS)

Edition

9th

Pages

69-80

Doc link

http://dx.oi.org/10.1007/978-3-319-31664-2_8

File

Download the digital copy of the doc pdf document

Abstract

This paper focuses on short-term water demand forecasting for predictive control of DrinkingWater Networks (DWN) by using Gaussian Process (GP). For the predictive control strategy, system state prediction in a nite horizon are generated by a DWN model and demands are regarded as system disturbances. The goal is to provide a demand estimation within a given condence interval. For the sake of obtaining a desired forecasting performance, the forecasting process is carried out in two parts: the expected part is forecasted by Double-Seasonal Holt-Winters (DSHW) method and the stochastic part is forecasted by GP method. The mean value of water demand is rstly estimated by DSHW while GP provides estimations within a condence interval. GP is applied with random inputs to propagate uncertainty at each step. Results of the application of the proposed approach to a real case study based on the Barcelona DWN have shown that the general goal has been successfully reached.

Categories

automation, observability, predictive control.

Author keywords

Gaussian process, water demand forecasting, drinking water networks, double-seasonal holt-winters, predictive control

Scientific reference

Y. Wang, C. Ocampo-Martínez, V. Puig and J. Quevedo. Gaussian-process-based demand forecasting for predictive control of drinking water networks, 9th International Conference on Critical Information Infrastructures Security, 2014, Limassol, Cyprus, in Critical Information Infrastructures Security, Vol 8985 of Lecture Notes in Computer Science, pp. 69-80, 2016, Springer.