Amali, S. and El Faddouli, N.-E. and Boutoulout, A. (2018) Machine learning and graph theory to optimize drinking water. In: UNSPECIFIED.

Full text not available from this repository.
Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....

Abstract

The preservation of the water quality in a distribution network requires maintenance of a permanent minimum residual chlorine at any point of the network. This is possible only if we plan chlorine injections at various points of the network for intermediate rechlorination. Given the high cost of the implementation of such stations, the optimization of the number and the choice of location of these stations are the two main difficulties facing managers. To optimize the placement of these locations, we have adopted two different approaches: one based on dynamic programming while the other is based on graph theory. We also proposed a regression model of pipes determined by Machine Learning. Performance tests of our decision support system were done on real sites of the Wilaya Rabat-Sale (network of Morocco's capital). The results obtained show that the contribution of graph theory is better than that of dynamic programming in that the response time (could you explain: Response time of what) is improved. © 2018 The Authors. Published by Elsevier B.V.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: Chlorine; Computation theory; Decision support systems; Dynamic programming; Intelligent computing; Learning systems; Linear regression; Location; Potable water; Water quality, Chlorine injection; High costs; Multiple linear regressions; Performance tests; Regression model; Residual chlorines, Graph theory
Subjects: Computer Science
Divisions: SCIENTIFIC PRODUCTION > Computer Science
Depositing User: Administrateur Eprints Administrateur Eprints
Last Modified: 31 Jan 2020 15:46
URI: http://eprints.umi.ac.ma/id/eprint/2434

Actions (login required)

View Item View Item