Application of immune algorithms on solving minimum-cost problem of water distribution network

Immune algorithm (IA) is a set of computational systems inspired by the defense process of the biological immune system. This study proposed an optimization procedure based on IA framework to optimize the designs of water distribution networks. A modified IA (mIA) procedure, which employs genetic algorithm (GA) to briefly screen initial antibody repertoires for IA, is also developed. The well-known benchmark instance, New York City Tunnel (NYCT) problem, is utilized as a case study to evaluate the optimization performance of IA and mIA. The least-cost designs of NYCT obtained by IA and mIA are compared with those by GA and fast messy GA previously published in the literature. The results of comparison reveal that IA and mIA are able to find the optimal solutions of NYCT with higher computational efficiency (less number of evaluations) than GA and fmGA. Notable performance enhancement is observed in mIA, indicating that the combination of GA can significantly improve the optimization performance of IA.