Aly-Joy Ulusoy

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.

This paper presents an optimal scheduling problem for coordinating pressure and self-cleaning operations in dynamically adaptive water networks. Our problem imposes a set of time-coupling constraints to manage pressure variations during the transition between operational modes. Solving this time-coupled, nonlinear optimization problem poses challenges for off-the-shelf nonlinear solvers due to its high memory demands. We compare the performance of a decomposition method using the alternating direction method of multipliers (ADMM) with a gradient-based sequential convex programming (SCP) monolithic solver. Solution quality and computational efficiency are evaluated using a model of a large-scale network in the UK.

In this paper, we present a new control model for optimizing pressure and water quality operations in water distribution networks. Our formulation imposes a set of time-coupling constraints to manage temporal pressure variations, which are exacerbated by the transition between pressure and water quality controls. The resulting optimization problem is a nonconvex, nonlinear program with nonseparable structure across time steps. This problem proves challenging for state-of-the-art nonlinear solvers, often precluding their direct use for near real-time control in large-scale networks. To overcome this computational burden, we investigate a distributed optimization approach based on the alternating direction method of multipliers (ADMM). In particular, we implement and evaluate two algorithms: a standard ADMM scheme and a two-level variant that provides theoretical convergence guarantees for our nonconvex problem. We use a benchmarking water network and a large-scale operational network in the UK for our numerical experiments. The results demonstrate good convergence behavior across all problem instances for the two-level algorithm, whereas the standard ADMM approach struggles to converge in some instances. With an appropriately tuned penalty parameter, however, both distributed algorithms yield good quality solutions and computational times compatible with near real-time (e.g. hourly) control requirements for large-scale water networks.

Machine learning models such as artificial neural networks (ANNs) are becoming increasingly popular in short-term water demand forecasting. This is because, despite their lack of interpretability, ANNs are able to capture complex interactions between explanatory variables and water consumption better than a traditional time series analysis or simple linear regression. In this work, we forecast the hourly water demand of ten operational district metered areas using optimal trees, a machine learning model which has been shown to combine the interpretability of regression approaches and the accuracy of ANNs. We show that, compared to existing water demand forecasting models, optimal trees offer valuable insights without sacrificing predictive or computational performance.

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.