Author(s): Yufeng Guo
Linked Author(s):
Keywords: Sewer network design; Cellular automata; Genetic algorithm; Optimization
Abstract: For the optimal cost-effective design of a storm sewer system, one of the state-of-the-art approaches is to incorporate Genetic Algorithms (GA) with a sewer network hydraulic simulator. However GA based optimization approaches suffer from very high computation costs. This problem is even more significant when designing a large network which also requires extensive hydraulic computation. This paper introduces an innovative heuristic approach for sewer network design based on cellular automata (CA) principles. The method preserves all the key features of CA: locality, homogeneity, and parallelism. A case study on a small artificial sewer network is presented, and results are compared with the solutions achieved by GAs. Although this study is still at its early stage, it demonstrates promising advantages on modelling efficiency compared to GAs, whilst achieving near optimal solutions.
Year: 2005