Adaptive MPC for Burst Incident Management in Water Distribution Networks

Abstract

This paper investigates an adaptive control strategy which takes advantage of remotely actuated pumps and valves to improve the performance of water distribution networks (WDN) during burst incidents. The proposed strategy relies on model predictive control (MPC) to switch between problem formulations corresponding to normal operating conditions and burst conditions. The optimal control problems are formulated as non-convex non-linear programs (NLP), where the action of fixed-speed pumps and control valves (non-return and bi-directional) is modeled exactly and burst remedial interventions are represented using time-dependent connectivity matrices. We propose an efficient solution method based on reformulations and approximations of the non-convex objectives and constraints and apply the proposed strategy to the adaptive control of an operational WDN during a burst incident. The numerical experiments show that the computed burst control settings allow to partially or completely restore customer supply following the detection of a burst while maintaining minimum water levels in the network tanks and without increasing the cost of pumping operations. The results suggest that the proposed adaptive control strategy can be implemented alone, to mitigate the impact of bursts incidents in WDNs at minimum cost, or to complement traditional remedial interventions.