Use of Domain Knowledge to Increase the Convergence Rate of Evolutionary Algorithms for Optimizing the Cost and Resilience of Water Distribution Systems

AbstractEvolutionary algorithms (EAs) have been used extensively for the optimization of water distribution systems (WDSs) over the last two decades. However, computational efficiency can be a problem, especially when EAs are applied to complex problems that have multiple competing objectives. In order to address this issue, there has been a move toward developing EAs that identify near-optimal solutions within acceptable computational budgets, rather than necessarily identifying globally optimal solutions. This paper contributes to this work by developing and testing a method for identifying high-quality initial populations for multiobjective EAs (MOEAs) for WDS design problems aimed at minimizing cost and maximizing network resilience. This is achieved by considering the relationship between pipe size and distance to the source(s) of water, as well as the relationship between flow velocities and network resilience. The benefit of using the proposed approach compared with randomly generating initial popu...

[1]  Patrick M. Reed,et al.  Comparing state-of-the-art evolutionary multi-objective algorithms for long-term groundwater monitoring design , 2005 .

[2]  Angus R. Simpson,et al.  Genetic Algorithms for Reliability-Based Optimization of Water Distribution Systems , 2004 .

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

[4]  Aaron C. Zecchin,et al.  Improved understanding of the searching behavior of ant colony optimization algorithms applied to the water distribution design problem , 2012 .

[5]  Angus R. Simpson,et al.  A computational software tool for the minimization of costs and greenhouse gas emissions associated with water distribution systems , 2015, Environ. Model. Softw..

[6]  Holger R. Maier,et al.  Using characteristics of the optimisation problem to determine the Genetic Algorithm population size when the number of evaluations is limited , 2015, Environ. Model. Softw..

[7]  Dragan A. Savic,et al.  Multi-objective optimization of water distribution systems based on a real options approach , 2015, Environ. Model. Softw..

[8]  Patrick M. Reed,et al.  Borg: An Auto-Adaptive Many-Objective Evolutionary Computing Framework , 2013, Evolutionary Computation.

[9]  Patrick M. Reed,et al.  Diagnostic Assessment of Search Controls and Failure Modes in Many-Objective Evolutionary Optimization , 2012, Evolutionary Computation.

[10]  Bryan A. Tolson,et al.  Dynamically dimensioned search algorithm for computationally efficient watershed model calibration , 2007 .

[11]  DebK.,et al.  A fast and elitist multiobjective genetic algorithm , 2002 .

[12]  A. Simpson,et al.  An efficient hybrid approach for multiobjective optimization of water distribution systems , 2014 .

[13]  Jh van Vuuren,et al.  Comparison of four reliability surrogate measures for water distribution systems design , 2010 .

[14]  Aaron C. Zecchin,et al.  Hybrid discrete dynamically dimensioned search (HD‐DDS) algorithm for water distribution system design optimization , 2009 .

[15]  Kevin E Lansey,et al.  Revisiting Optimal Water-Distribution System Design: Issues and a Heuristic Hierarchical Approach , 2012 .

[16]  Avi Ostfeld,et al.  Evolutionary algorithms and other metaheuristics in water resources: Current status, research challenges and future directions , 2014, Environ. Model. Softw..

[17]  Xiang Li,et al.  Knowledge-Based Approach for Reservoir System Optimization , 2014 .

[18]  Wenyan Wu,et al.  Single-Objective versus Multiobjective Optimization of Water Distribution Systems Accounting for Greenhouse Gas Emissions by Carbon Pricing , 2010 .

[19]  Holger R. Maier,et al.  A genetic algorithm calibration method based on convergence due to genetic drift , 2008, Inf. Sci..

[20]  Bryan A. Tolson,et al.  Comparing Optimization Techniques with an Engineering Judgment Approach to WDN Design , 2016 .

[21]  S. M. Sapuan,et al.  A knowledge-based system for materials selection in mechanical engineering design , 2001 .

[22]  Thomas M. Walski,et al.  The Wrong Paradigm—Why Water Distribution Optimization Doesn't Work , 2001 .

[23]  T. Devi Prasad,et al.  Multiobjective Genetic Algorithms for Design of Water Distribution Networks , 2004 .

[24]  Feifei Zheng,et al.  Comparing the real-time searching behavior of four differential-evolution variants applied to water-distribution-network design optimization. , 2015 .

[25]  Qi Wang,et al.  Two-Objective Design of Benchmark Problems of a Water Distribution System via MOEAs: Towards the Best-Known Approximation of the True Pareto Front , 2015 .

[26]  Yew-Soon Ong,et al.  A domain knowledge based search advisor for design problem solving environments , 2002 .

[27]  Avi Ostfeld,et al.  State of the Art for Genetic Algorithms and Beyond in Water Resources Planning and Management , 2010 .

[28]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[29]  Enrico Creaco,et al.  Fast network multi-objective design algorithm combined with an a posteriori procedure for reliability evaluation under various operational scenarios , 2012 .

[30]  A. Simpson,et al.  A combined NLP‐differential evolution algorithm approach for the optimization of looped water distribution systems , 2011 .

[31]  Angus R. Simpson,et al.  Effect of storage tank size on the minimization of water distribution system cost and greenhouse gas emissions while considering time-dependent emissions factors , 2016 .

[32]  Holger R. Maier,et al.  Improved genetic algorithm optimization of water distribution system design by incorporating domain knowledge , 2015, Environ. Model. Softw..

[33]  Sung-Hoon Hong,et al.  Reliability based design of water distribution networks using multi-objective genetic algorithms , 2003 .

[34]  Lothar Thiele,et al.  Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach , 1999, IEEE Trans. Evol. Comput..

[35]  Wenyan Wu,et al.  Multiobjective optimization of water distribution systems accounting for economic cost, hydraulic reliability, and greenhouse gas emissions , 2013 .

[36]  Joseph R. Kasprzyk,et al.  A new epsilon-dominance hierarchical Bayesian optimization algorithm for large multiobjective monitoring network design problems , 2008 .

[37]  Joseph R. Kasprzyk,et al.  Thematic issue on Evolutionary Algorithms in Water Resources , 2015, Environ. Model. Softw..

[38]  K. Deb.  An Efficient Constraint Handling Method for Genetic Algorithms , 2000 .

[39]  Christopher S. Stokes,et al.  Water Distribution System Pumping Operational Greenhouse Gas Emissions Minimization by Considering Time-Dependent Emissions Factors , 2015 .

[40]  Edward Keedwell,et al.  A novel evolutionary meta-heuristic for the multi-objective optimization of real-world water distribution networks , 2006 .

[41]  Patrick M. Reed,et al.  Large-scale parallelization of the Borg multiobjective evolutionary algorithm to enhance the management of complex environmental systems , 2015, Environ. Model. Softw..

[42]  Holger R. Maier,et al.  Relationship between problem characteristics and the optimal number of genetic algorithm generations , 2011 .