Hybrid SOM+k-Means clustering to improve planning, operation and management in water distribution systems

Abstract With the advance of new technologies and emergence of the concept of the smart city, there has been a dramatic increase in available information. Water distribution systems (WDSs) in which databases can be updated every few minutes are no exception. Suitable techniques to evaluate available information and produce optimized responses are necessary for planning, operation, and management. This can help identify critical characteristics, such as leakage patterns, pipes to be replaced, and other features. This paper presents a clustering method based on self-organizing maps coupled with k-means algorithms to achieve groups that can be easily labeled and used for WDS decision-making. Three case-studies are presented, namely a classification of Brazilian cities in terms of their water utilities; district metered area creation to improve pressure control; and transient pressure signal analysis to identify burst pipes. In the three cases, this hybrid technique produces excellent results.

[1]  Idel Montalvo,et al.  Injecting problem-dependent knowledge to improve evolutionary optimization search ability , 2016, J. Comput. Appl. Math..

[2]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[3]  Idel Montalvo,et al.  A Novel Water Supply Network Sectorization Methodology Based on a Complete Economic Analysis, Including Uncertainties , 2016 .

[4]  Mattias Höjer,et al.  Smart sustainable cities - Exploring ICT solutions for reduced energy use in cities , 2014, Environ. Model. Softw..

[5]  Joby Boxall,et al.  Relating Water Quality and Age in Drinking Water Distribution Systems Using Self-Organising Maps , 2016 .

[6]  Joaquín Izquierdo,et al.  An approach to water supply clusters by semi-supervised learning , 2010 .

[7]  Edmundo Koelle,et al.  Fluid transients in pipe networks , 1991 .

[8]  Bruno Melo Brentan,et al.  Social Network Community Detection for DMA Creation: Criteria Analysis through Multilevel Optimization , 2017 .

[9]  Chen Lin,et al.  Consistency in performance rankings: the Peru water sector , 2008 .

[10]  Helena M. Ramos,et al.  Pressure Control for Leakage Minimisation in Water Distribution Systems Management , 2006 .

[11]  Riku Vahala,et al.  Leakage detection in a real distribution network using a SOM , 2009 .

[12]  Gholam Reza Rakhshandehroo,et al.  A SELF ORGANIZING MAP BASED HYBRID MULTI-OBJECTIVE OPTIMIZATION OF WATER DISTRIBUTION NETWORKS , 2011 .

[13]  A. M. Kalteh,et al.  Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application , 2008, Environ. Model. Softw..

[14]  Dragan Savic,et al.  Decision support system for the optimal design of district metered areas , 2016 .

[15]  Nathalie Godin,et al.  Integration of the Kohonen's self-organising map and k-means algorithm for the segmentation of the AE data collected during tensile tests on cross-ply composites , 2005 .

[16]  José Ramón Gil-García,et al.  Understanding Smart Cities: An Integrative Framework , 2012, HICSS.

[17]  Yi Sun,et al.  On quantization error of self-organizing map network , 2000, Neurocomputing.

[18]  Idel Montalvo,et al.  A flexible methodology to sectorize water supply networks based on social network theory concepts and multi-objective optimization , 2016 .

[19]  Ujjwal Maulik,et al.  Performance Evaluation of Some Clustering Algorithms and Validity Indices , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  T. Caliński,et al.  A dendrite method for cluster analysis , 1974 .

[21]  Emmanuel Thanassoulis,et al.  The use of data envelopment analysis in the regulation of UK water utilities: Water distribution , 2000, Eur. J. Oper. Res..

[22]  Enrique Cabrera,et al.  Towards an Energy Labelling of Pressurized Water Networks , 2014 .

[23]  Leandros Tassiulas,et al.  Exploring Patterns in Water Consumption by Clustering , 2015 .

[24]  Alfred Ultsch,et al.  Kohonen Networks on Transputers: Implementation and Animation , 1990 .

[25]  Edevar Luvizotto Junior,et al.  Classification of water supply systems based on energy efficiency , 2015 .

[26]  Michael Allen,et al.  Water Main Burst Event Detection and Localization , 2011 .

[27]  J. E. van Zyl.  Theoretical Modeling of Pressure and Leakage in Water Distribution Systems , 2014 .

[28]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[29]  Armando Di Nardo,et al.  A heuristic design support methodology based on graph theory for district metering of water supply networks , 2011 .

[30]  Samuel Kaski,et al.  Self organization of a massive document collection , 2000, IEEE Trans. Neural Networks Learn. Syst..

[31]  Helena M. Ramos,et al.  Case Studies of Leak Detection and Location in Water Pipe Systems by Inverse Transient Analysis , 2010 .

[32]  Avi Ostfeld,et al.  Battle of the Water Networks II , 2014 .

[33]  S. Gonçalves,et al.  The Effects of Participatory Budgeting on Municipal Expenditures and Infant Mortality in Brazil , 2014 .