Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
| Hi-index | 0.00 |
The paper describes the development of a genetic algorithm (GA) formulation by using real representation for the water pipe networks optimization. The research has taken two widely known and published problems and solved them in illustration of the efficiency and performance of this method towards realizing good designs. The first problem has been a small hypothetical network and the second a primary real system, the New York City water supply tunnels. The results have been compared with those of other search techniques (simulated annealing) and coding GA (binary, Gray, and Integer). They proved for the small network systems, that real coding GAs gives slightly more costly solution than that of simulated annealing and of Gray coding GAs. This can be attributed to the number of genes used in the chromosome caused by real representation, which is less than what is needed for keeping the diversity of the population. As for the larger network systems, it has been found that the real representation is very effective and provides the least-cost feasible solution to the New York tunnels problem.