Self-adaptive cuckoo search algorithm is used to optimize the design of water distribution system problems. It is proposed to dynamically adjust the two sensitive parameters of the algorithm, (i) step size control parameter ‘α’ and (ii) discovering probability parameter ‘Pa’ which largely govern the exploration and exploitation search strategies of the algorithm. These parameters are essential for enhancing the performance of the algorithm and normally the values of these parameters needs careful selection according to the type of problem. Single objective self-adaptive cuckoo search algorithm (SACSA) and multi-objective self-adaptive cuckoo search algorithm (SAMOSCA) are proposed in this study. Robustness and efficiency of these algorithms in single (minimization of cost) and multi-objective scenarios (minimization of cost and maximization of resilience) is validated using standard water distribution benchmark problems i.e. Two loop and Hanoi network. These are later applied to solve a medium size real-life water distribution system located at Pamapur, Telangana, India. A simulation-optimization based program combining the water distribution network simulation software EPANET 2.2 and MATLAB is used for computation. The proposed methodology has provided better results in terms of computational efficiency as well as found better solutions when compared to the previously reported results in both single and multi-objective scenarios. In the case of multi-objective problems, it has been observed that SAMOCSA has been able to find new points in pareto front when compared to the best-known pareto front reported in the literature. Self-adaptive cuckoo search algorithm has been found to be an attractive alternative in both exploration and exploitation of larger search spaces for finding better optimal solutions.

自适应布谷鸟搜索算法用于优化供水系统问题的设计。建议动态调整算法的两个敏感参数，（i）步长控制参数“α”和（ii）发现概率参数“ Pa”，这些参数主要控制着算法的探索和开发搜索策略。这些参数对于增强算法的性能至关重要，通常需要根据问题的类型仔细选择这些参数的值。提出了单目标自适应杜鹃搜索算法（SACSA）和多目标自适应杜鹃搜索算法（SAMOSCA）。使用标准水分配基准问题（即两回路和河内网络）验证了这些算法在单一（成本最小）和多目标场景（成本最小和弹性最大化）中的鲁棒性和效率。这些后来被用于解决位于印度特兰甘纳邦Pamapur的中等规模的生活用水分配系统。结合供水网络仿真软件EPANET 2.2和MATLAB的基于仿真优化的程序进行计算。与先前在单目标和多目标方案中报告的结果相比，该方法论在计算效率方面提供了更好的结果，并且找到了更好的解决方案。如果是多目标问题，据观察，与文献中报道的最著名的pareto front相比，SAMOCSA能够在pareto front找到新的点。自适应布谷鸟搜索算法已被发现在探索和利用更大的搜索空间来寻找更好的最佳解决方案方面是一种有吸引力的选择。