Improvement of Water Network Reliability: A Conflict Resolution Approach

A water distribution system is an interconnected collection of storage tanks, pipes, and hydraulic control elements (e.g. pumps, valves, regulators) delivering water to the consumers in prescribed quantities and at desired pressures. Reliability analysis of a water distribution system is concerned with measuring its ability to meet consumers’ demands in terms of quantity and quality, under normal and low flow conditions. This paper presents an approach to optimal operation of water networks in order to increase reliability by pressure management and adding pipes between nodes in the network. As the decision variables have several attributes, the utility of them could be used by the decision makers in form of Nash products. The developed methodology is used by combination of the Genetic Algorithms (GA) and the Artificial Neural Networks (ANN). Cost of piping, amount of leakage and water network reliability are considered in the objective function of the model. In the proposed methodology, the results of the EPANET hydraulic simulation model are used to train the ANNs based simulation model. This model is then linked to the GA based optimization model to develop the optimized piping extensions and pressure in each node. The proposed model is applied to a hypothetical water distribution network but it can be used in real world problems.

[1]  Godfrey A. Walters,et al.  Multiobjective Genetic Algorithms for Pump Scheduling in Water Supply , 1997, Evolutionary Computing, AISB Workshop.

[2]  David E. Goldberg,et al.  Genetic Algorithms in Pipeline Optimization , 1987 .

[3]  Julio Ortega,et al.  ANNs and GAs for predictive control of water supply networks , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[4]  Jakobus E. van Zyl,et al.  Operational Optimization of Water Distribution Systems using a Hybrid Genetic Algorithm , 2004 .

[5]  Zong Woo Geem.  Window-Based Decision Support System for the Water Pipe Condition Assessment using Artificial Neural Network , 2003 .

[6]  Kuolin Hsu,et al.  Artificial Neural Network Modeling of the Rainfall‐Runoff Process , 1995 .

[7]  Graeme C. Dandy,et al.  Optimal Scheduling of Water Pipe Replacement Using Genetic Algorithms , 2001 .

[8]  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.

[9]  Mitsuo Gen,et al.  Genetic Algorithms , 1999, Wiley Encyclopedia of Computer Science and Engineering.

[10]  Dragan Savic,et al.  WATER NETWORK REHABILITATION WITH STRUCTURED MESSY GENETIC ALGORITHM , 1997 .

[11]  Ezio Todini,et al.  Looped water distribution networks design using a resilience index based heuristic approach , 2000 .