Simulation and Machine Learning Strategies for Enabling Integrated Water Resource Management: H2OLeak Project

In this paper the main Decision Support functionalities proposed and developed within the H2OLEAK research project are presented. H2OLEAK, cofounded by Regione Lombardia in Italy, is aimed at designing and developing an innovative technological platform for supporting a rational and integrated management of urban water distribution systems. It integrates already available and robust technological solutions, such as Supervisory Control And Data Acquisition (SCADA) systems, Geographical Information Systems (GIS) and Business Intelligence tools, with advanced analytical methodologies to support managers in their decision making activities, enabling prompt and proactive actions that may reduce costs while guaranteeing high customers satisfaction. In particular, computational approaches proposed to address three main problems are described: (i) automatic districts identification to obtain the “optimal” partition of a water distribution system into virtually independent sub-networks, (ii) computational localization of leaky pipelines through the analysis of flows and pressures measured at the entry points of each district and (iii) regression models for estimating the loss intensity of the leak to improve localization effectiveness by further reducing the set of pipelines to be checked physically.

[1]  Francesco Archetti,et al.  Multimedia Summarization in Law Courts: A Clustering-Based Environment for Browsing and Consulting Judicial Folders , 2010, ICDM.

[2]  Zoran Kapelan,et al.  A review of methods for leakage management in pipe networks , 2010 .

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

[4]  Stewart Burn,et al.  An Approach to Leak Detection in Pipe Networks Using Analysis of Monitored Pressure Values by Support Vector Machine , 2009, 2009 Third International Conference on Network and System Security.

[5]  Idel Montalvo,et al.  Division of Water Supply Systems into District Metered Areas Using a Multi-agent Based Approach , 2009, ICSOFT.

[6]  Kourosh Behzadian,et al.  Stochastic sampling design using a multi-objective genetic algorithm and adaptive neural networks , 2009, Environ. Model. Softw..

[7]  Min-kyu Choi,et al.  Assessment of the Vulnerabilities of SCADA, Control Systems and Critical Infrastructure Systems , 2009 .

[8]  Qian Yin,et al.  The design of water supply network based on GIS , 2008, 2008 IEEE Conference on Cybernetics and Intelligent Systems.

[9]  Sorin Enache,et al.  SCADA system for monitoring water supply networks , 2008 .

[10]  Yiyun Chen,et al.  Functional Structure of Urban Water Supply Network Based on GIS , 2008, 2008 ISECS International Colloquium on Computing, Communication, Control, and Management.

[11]  Helena M. Ramos,et al.  Water Pipe System Diagnosis by Transient Pressure Signals , 2008 .

[12]  Enrique Cabrera,et al.  THE MINIMUM NIGHT FLOW METHOD REVISITED , 2008 .

[13]  C.R.I. Clayton,et al.  The effect of pressure on leakage in water distribution systems , 2007 .

[14]  J. E. van Zyl,et al.  An experimental investigation into the pressure - leakage relationship of some failed water pipes , 2007 .

[15]  Francesco Archetti,et al.  A Hierarchical Document Clustering Environment Based on the Induced Bisecting k-Means , 2006, FQAS.

[16]  Michael J. Brennan,et al.  Axisymmetric wave propagation in buried, fluid-filled pipes : Effects of wall discontinuities , 2005 .

[17]  Steven G. Buchberger,et al.  Leak estimation in water distribution systems by statistical analysis of flow readings , 2004 .

[18]  Michael J. Brennan,et al.  Axisymmetric wave propagation in fluid-filled pipes: wavenumber measurements in in vacuo and buried pipes , 2004 .

[19]  Malcolm Farley,et al.  Developing a Non-Revenue Water Reduction Strategy Part 1: Investigating and Assessing Water Losses , 2004 .

[20]  Philip M. Long,et al.  Performance guarantees for hierarchical clustering , 2002, J. Comput. Syst. Sci..

[21]  Sergio M. Savaresi,et al.  On the performance of bisecting K-means and PDDP , 2001, SDM.

[22]  George Karypis,et al.  A Comparison of Document Clustering Techniques , 2000 .

[23]  David B. Shmoys,et al.  A Best Possible Heuristic for the k-Center Problem , 1985, Math. Oper. Res..