Optimal Pump Control for Water Distribution Networks via Data-based Distributional Robustness

TL;DR

This paper introduces a data-driven, distributionally robust optimization approach for multi-period water flow management in water distribution networks, explicitly accounting for demand forecast errors and balancing cost and risk.

Contribution

It develops a novel distributionally robust framework using Wasserstein ambiguity sets, enabling more reliable pump control decisions under demand uncertainty.

Findings

Effective tradeoff between operational cost and constraint violation risk.

Robustness of the approach demonstrated on a three-tank network case study.

Out-of-sample performance improves with the proposed method.

Abstract

In this paper, we propose a data-based methodology to solve a multi-period stochastic optimal water flow (OWF) problem for water distribution networks (WDNs). The framework explicitly considers the pump schedule and water network head level with limited information of demand forecast errors for an extended period simulation. The objective is to determine the optimal feedback decisions of network-connected components, such as nominal pump schedules and tank head levels and reserve policies, which specify device reactions to forecast errors for accommodation of fluctuating water demand. Instead of assuming the uncertainties across the water network are generated by a prescribed certain distribution, we consider ambiguity sets of distributions centered at an empirical distribution, which is based directly on a finite training data set. We use a distance-based ambiguity set with the Wasserstein metric to quantify the distance between the real unknown data-generating distribution and the empirical distribution. This allows our multi-period OWF framework to trade off system performance and inherent sampling errors in the training dataset. Case studies on a three-tank water distribution network systematically illustrate the tradeoff between pump operational cost, risks of constraint violation, and out-of-sample performance.