Intelligent Urban Water Infrastructure Management

Urban population growth together with other pressures, such as climate change, create enormous challenges to provision of urban infrastructure services, including gas, electricity, transport, water, etc. Smart-grid technology is viewed as the way forward to ensure that infrastructure networks are flexible, accessible, reliable and economical. “Intelligent water networks” take advantage of the latest information and communication technologies to gather and act on information to minimise waste and deliver more sustainable water services. The effective management of water distribution, urban drainage and sewerage infrastructure is likely to require increasingly sophisticated computational techniques to keep pace with the level of data that is collected from measurement instruments in the field.  This paper describes two examples of intelligent systems developed to utilise this increasingly available real-time sensed information in the urban water environment. The first deals with the failure-management decision-support system for water distribution networks, NEPTUNE, that takes advantage of intelligent computational methods and tools applied to near real-time logger data providing pressures, flows and tank levels at selected points throughout the system. The second, called RAPIDS, deals with urban drainage systems and the utilisation of rainfall data to predict flooding of urban areas in near real-time. The two systems have the potential to provide early warning and scenario testing for decision makers within reasonable time, this being a key requirement of such systems. Computational methods that require hours or days to run will not be able to keep pace with fast-changing situations such as pipe bursts or manhole flooding and thus the systems developed are able to react in close to real time.

[1]  N. Metropolis,et al.  The Monte Carlo method. , 1949 .

[2]  Ralph L. Keeney,et al.  Decisions with multiple objectives: preferences and value tradeoffs , 1976 .

[3]  Albert S. Chen,et al.  RAPIDS: Early Warning System for Urban Flooding and Water Quality Hazards , 2013 .

[4]  Zoran Kapelan,et al.  CONCEPTUAL RISK-BASED DECISION SUPPORT METHODOLOGY FOR IMPROVED NEAR REAL-TIME RESPONSE TO WDS FAILURES , 2009 .

[5]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[6]  W. Lowrance,et al.  Of Acceptable Risk: Science and the Determination of Safety , 1976 .

[7]  Zoran Kapelan,et al.  Automated Detection of Pipe Bursts and Other Events in Water Distribution Systems , 2014 .

[8]  Martin Fodslette Meiller A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[9]  Edward Keedwell,et al.  Urban flood prediction in real-time from weather radar and rainfall data using artificial neural networks , 2011 .

[10]  John C. Worsley,et al.  Practical PostgreSQL , 2002 .

[11]  Erwan Bocher,et al.  An overview on current free and open source desktop GIS developments , 2009, Int. J. Geogr. Inf. Sci..

[12]  A. Soldati,et al.  Artificial neural network approach to flood forecasting in the River Arno , 2003 .

[13]  P D Widdop,et al.  A neural network approach to burst detection. , 2002, Water science and technology : a journal of the International Association on Water Pollution Research.

[14]  Sara Liguori,et al.  Quantitative Precipitation Forecasting For A Small Urban Area: Use Of Radar Nowcasting , 2009 .

[15]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[16]  Orazio Giustolisi,et al.  Pressure-Driven Demand and Leakage Simulation for Water Distribution Networks , 2008 .

[17]  R. Sadiq,et al.  Aggregative risk analysis for water quality failure in distribution networks , 2004 .

[18]  François Anctil,et al.  A soil moisture index as an auxiliary ANN input for stream flow forecasting , 2004 .

[19]  Guido Vaes,et al.  Towards a roadmap for use of radar rainfall data in urban drainage , 2004 .

[20]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[21]  Ashish Sharma,et al.  A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting , 2000 .

[22]  Ronnie Belmans,et al.  Vision and Strategy for Europe’s Electricity Networks of the Future: European Technology PlatformSmartGrids , 2006 .

[23]  Jeffrey G. Arnold,et al.  Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations , 2007 .

[24]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[25]  Noel E. O'Connor,et al.  Short-term rainfall nowcasting: using rainfall radar imaging , 2009 .

[26]  Zoran Kapelan,et al.  Operational Perspective of the Impact of Failures in Water Distribution Systems , 2009 .

[27]  R. L. Keeney,et al.  Decisions with Multiple Objectives: Preferences and Value Trade-Offs , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[28]  Ian Postlethwaite,et al.  Project neptune: Improved operation of water distribution networks. , 2009 .

[29]  Joby Boxall,et al.  Modeling Discoloration in Potable Water Distribution Systems , 2005 .

[30]  Zoran Kapelan,et al.  Pipe burst diagnostics using evidence theory , 2011 .

[31]  Mark S. Morley,et al.  Pressure-Driven Demand Extension for EPANET (EPANETpdd) , 2008 .

[32]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[33]  Eduardo Saliby,et al.  An empirical evaluation of sampling methods in risk analysis simulation: quasi-Monte Carlo, descriptive sampling, and latin hypercube sampling , 2002, Proceedings of the Winter Simulation Conference.

[34]  Albert S. Chen,et al.  Urban pluvial flood modelling with real time rainfall information - UK case studies , 2011 .

[35]  B.F. Wollenberg,et al.  Toward a smart grid: power delivery for the 21st century , 2005, IEEE Power and Energy Magazine.