Optimal Design of Urban Water Distribution Network Using Improved Artificial Bee Colony Algorithm

Urban Water Distribution Networks are the most important and costly network in each city. The Major part of the urban water distribution network costs is related to the executive progress and purchase of water distribution network accessories. Therefore, the cost of the water distribution network can be reduced by reducing and optimizing this part. For this purpose, the problem of water distribution network design should be defined as an optimization model and solved it using an efficient method. Nowadays, Meta-heuristics algorithms are the most efficient methods for solving optimization models. In this research, two sample problems mean Schaake and Lai (1969) water distribution network and NEWYORK city are modeled in the EPANET software and solved using an improved version of the artificial bee colony algorithm that is called MATLAB software. To evaluate the efficiency of the proposed algorithm, the results are presented and compared with the basic and standard version of the artificial bee colony algorithm and other results. Using an improved artificial bee colony algorithm for the two-loop network (NEWYORK), the objective function value and computational cost are 419000 $ (38.13 M$) and 2800 (3800), respectively. A comparison of the results shows that the construction and computed costs are reduced compared with the result of the standard version. Therefore, this algorithm is an efficient algorithm for solving optimization problems such as the design of a water distribution network.