Weighted spectral clustering for water distribution network partitioning

Abstract In order to improve the management and to better locate water losses, Water Distribution Networks can be physically divided into District Meter Areas (DMAs), inserting hydraulic devices on proper pipes and thus simplifying the control of water budget and pressure regime. Traditionally, the...

Full description

Bibliographic Details
Main Authors:	Armando Di Nardo, Michele Di Natale, Carlo Giudicianni, Roberto Greco, Giovanni Francesco Santonastaso
Format:	Article
Language:	English
Published:	Springer 2017-06-01
Series:	Applied Network Science
Subjects:	Laplacian spectrum Spectral clustering k-means Water network partitioning
Online Access:	http://link.springer.com/article/10.1007/s41109-017-0033-4

id	doaj-art-798d4287c1374555b19a6fa5f7f176bd
recordtype	oai_dc
spelling	doaj-art-798d4287c1374555b19a6fa5f7f176bd2018-08-20T08:12:45ZengSpringerApplied Network Science2364-82282017-06-012111610.1007/s41109-017-0033-4Weighted spectral clustering for water distribution network partitioningArmando Di Nardo0Michele Di Natale1Carlo Giudicianni2Roberto Greco3Giovanni Francesco Santonastaso4Dipartimento di Ingegneria Civile Design Edilizia e Ambiente, Università degli Studi della Campania ‘L. Vanvitelli’Dipartimento di Ingegneria Civile Design Edilizia e Ambiente, Università degli Studi della Campania ‘L. Vanvitelli’Dipartimento di Ingegneria Civile Design Edilizia e Ambiente, Università degli Studi della Campania ‘L. Vanvitelli’Dipartimento di Ingegneria Civile Design Edilizia e Ambiente, Università degli Studi della Campania ‘L. Vanvitelli’Dipartimento di Ingegneria Civile Design Edilizia e Ambiente, Università degli Studi della Campania ‘L. Vanvitelli’Abstract In order to improve the management and to better locate water losses, Water Distribution Networks can be physically divided into District Meter Areas (DMAs), inserting hydraulic devices on proper pipes and thus simplifying the control of water budget and pressure regime. Traditionally, the water network division is based on empirical suggestions and on ‘trial and error’ approaches, checking results step by step through hydraulic simulation, and so making it very difficult to apply such approaches to large networks. Recently, some heuristic procedures, based on graph and network theory, have shown that it is possible to automatically identify optimal solutions in terms of number, shape and dimension of DMAs. In this paper, weighted spectral clustering methods have been used to define the optimal layout of districts in a real water distribution system, taking into account both geometric and hydraulic features, through weighted adjacency matrices. The obtained results confirm the feasibility of the use of spectral clustering to address the arduous problem of water supply network partitioning with an elegant mathematical approach compared to other heuristic procedures proposed in the literature. A comparison between different spectral clustering solutions has been carried out through topological and energy performance indices, in order to identify the optimal water network partitioning procedure.http://link.springer.com/article/10.1007/s41109-017-0033-4Laplacian spectrumSpectral clusteringk-meansWater network partitioning
institution	Open Data Bank
collection	Open Access Journals
building	Directory of Open Access Journals
language	English
format	Article
author	Armando Di Nardo Michele Di Natale Carlo Giudicianni Roberto Greco Giovanni Francesco Santonastaso
spellingShingle	Armando Di Nardo Michele Di Natale Carlo Giudicianni Roberto Greco Giovanni Francesco Santonastaso Weighted spectral clustering for water distribution network partitioning Applied Network Science Laplacian spectrum Spectral clustering k-means Water network partitioning
author_facet	Armando Di Nardo Michele Di Natale Carlo Giudicianni Roberto Greco Giovanni Francesco Santonastaso
author_sort	Armando Di Nardo
title	Weighted spectral clustering for water distribution network partitioning
title_short	Weighted spectral clustering for water distribution network partitioning
title_full	Weighted spectral clustering for water distribution network partitioning
title_fullStr	Weighted spectral clustering for water distribution network partitioning
title_full_unstemmed	Weighted spectral clustering for water distribution network partitioning
title_sort	weighted spectral clustering for water distribution network partitioning
publisher	Springer
series	Applied Network Science
issn	2364-8228
publishDate	2017-06-01
description	Abstract In order to improve the management and to better locate water losses, Water Distribution Networks can be physically divided into District Meter Areas (DMAs), inserting hydraulic devices on proper pipes and thus simplifying the control of water budget and pressure regime. Traditionally, the water network division is based on empirical suggestions and on ‘trial and error’ approaches, checking results step by step through hydraulic simulation, and so making it very difficult to apply such approaches to large networks. Recently, some heuristic procedures, based on graph and network theory, have shown that it is possible to automatically identify optimal solutions in terms of number, shape and dimension of DMAs. In this paper, weighted spectral clustering methods have been used to define the optimal layout of districts in a real water distribution system, taking into account both geometric and hydraulic features, through weighted adjacency matrices. The obtained results confirm the feasibility of the use of spectral clustering to address the arduous problem of water supply network partitioning with an elegant mathematical approach compared to other heuristic procedures proposed in the literature. A comparison between different spectral clustering solutions has been carried out through topological and energy performance indices, in order to identify the optimal water network partitioning procedure.
topic	Laplacian spectrum Spectral clustering k-means Water network partitioning
url	http://link.springer.com/article/10.1007/s41109-017-0033-4
_version_	1612691214430109696

Weighted spectral clustering for water distribution network partitioning

Similar Items