Optimizing Chlorination in Water Distribution Systems via Surrogate-assisted Neuroevolution

TL;DR

This paper introduces a neuroevolution-based optimization framework using surrogate models to improve chlorine dosing in complex water distribution systems, balancing safety, efficiency, and homogeneity.

Contribution

It presents a novel combination of neuroevolution, multi-objective optimization, and surrogate modeling to optimize water chlorination, outperforming standard reinforcement learning methods.

Findings

Evolved controllers achieved diverse Pareto-optimal policies.

Surrogate models enabled efficient evaluation of complex hydraulic simulations.

The approach outperformed PPO in optimizing chlorination strategies.

Abstract

Ensuring the microbiological safety of large, heterogeneous water distribution systems (WDS) typically requires managing appropriate levels of disinfectant residuals including chlorine. WDS include complex fluid interactions that are nonlinear and noisy, making such maintenance a challenging problem for traditional control algorithms. This paper proposes an evolutionary framework to this problem based on neuroevolution, multi-objective optimization, and surrogate modeling. Neural networks were evolved with NEAT to inject chlorine at strategic locations in the distribution network at select times. NSGA-II was employed to optimize four objectives: minimizing the total amount of chlorine injected, keeping chlorine concentrations homogeneous across the network, ensuring that maximum concentrations did not exceed safe bounds, and distributing the injections regularly over time. Each network was evaluated against a surrogate model, i.e.\ a neural network trained to emulate EPANET, an industry-level hydraulic WDS simulator that is accurate but infeasible in terms of computational cost to support machine learning. The evolved controllers produced a diverse range of Pareto-optimal policies that could be implemented in practice, outperforming PPO, a standard reinforcement learning method. The results thus suggest a pathway toward improving urban water systems, and highlight the potential of using evolution with surrogate modeling to optimize complex real-world systems.