Hybrid Evolutionary‐Exact Optimization Method for the Bi‐Objective Design‐For‐Control of Water Distribution Networks

Abstract This work considers the design‐for‐control of water distribution networks (WDN) for the joint optimization of performance and cost‐related objectives. In particular, we focus on the problem of optimizing the placement (design) and settings (control) of pressure reducing valves to minimize leakage at minimum cost. We present an integrative hybrid method combining the complementary advantages of deterministic and evolutionary algorithms (EA) to efficiently approximate the Pareto front of the resulting non‐convex bi‐objective mixed‐integer non‐linear program. Design decisions are fixed by an outer multi‐objective EA, while a non‐linear programming solver is called during the fitness evaluation stage to compute continuous control settings. The algorithm is applied to case study and operational networks and evaluated against alternative heuristic methods based on computational performance and quality of the solutions returned. Our results show that the proposed method converges faster and more consistently than existing approaches, producing better trade‐offs between cost and leakage reduction. In particular, the Pareto front approximations computed using the proposed integrative hybrid method are characterized by a more marked knee (i.e., more efficient trade‐offs), while the achieved computational improvements facilitate the integration of expert feedback into the design‐for‐control of WDNs during offline planning.