Convex Model for Global Optimization of Water Distribution System

In this paper, a convex model is proposed for the optimal design of water distribution system (WDS). The WDS problem is well known for its poor solution efficiency and difficulty in finding global optimal solution due to the nonconvex head loss equations. To address the nonconvex issue, the head loss equations are rigorously reformulated into convex inequalities. Mixed-integer programming (MIP) method is applied to facilitate the convexification. The proposed model is formulated as mixed-integer nonlinear programming (MINLP) model. Since the model is convex and rigorously formulated, global optimality is guaranteed. The effectiveness of the model is illustrated by a benchmark example.