Learning optimal control of water distribution networks through sequential model-based optimization

Sequential Model-based Bayesian Optimization has been successfully applied to several application domains, characterized by complex search spaces, such as Automated Machine Learning and Neural Architecture Search. This paper focuses on optimal control problems, proposing a Sequential Model-based Bayesian Optimization framework to learn optimal control strategies. The strategies are synthetized by pressure-based rules, whose parameters are the design variables of the optimization problem whose black-box objective is the energy cost. A Bayesian optimization framework is presented which handles a quite general formalization of the control problem including multiple constraints, also black box. Relevant results on a real-life Water Distribution Network are reported, comparing different possible choices for the proposed framework.