Learning Optimal Control of Water Distribution Networks through Sequential Model-based Optimization
Systems and Control
2020-03-10 v1 Systems and Control
Optimization and Control
Abstract
Sequential Model-based Bayesian Optimization has been successful-ly 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. A quite general formalization of the problem is provided, along with a specific instance related to optimization of pumping operations in an urban Water Distri-bution Network. Relevant results on a real-life Water Distribution Network are reported, comparing different possible choices for the proposed framework.
Keywords
Cite
@article{arxiv.2003.04268,
title = {Learning Optimal Control of Water Distribution Networks through Sequential Model-based Optimization},
author = {Antonio Candelieri and Bruno Galuzzi and Ilaria Giordani and Francesco Archetti},
journal= {arXiv preprint arXiv:2003.04268},
year = {2020}
}