Learning-based hierarchical control of water reservoir systems

TL;DR

This paper introduces a real-time, learning-based hierarchical control method for water reservoir systems that improves performance over traditional stochastic dynamic programming by adapting to uncertainties and environmental changes.

Contribution

It presents a novel hierarchical predictive control architecture combining data-driven inner control and outer economic MPC for reservoir management.

Findings

Outperforms stochastic dynamic programming in simulations

Adapts effectively to hydrologic uncertainties

Enhances control performance and constraint handling

Abstract

The optimal control of a water reservoir systems represents a challenging problem, due to uncertain hydrologic inputs and the need to adapt to changing environment and varying control objectives. In this work, we propose a real-time learning-based control strategy based on a hierarchical predictive control architecture. Two control loops are implemented: the inner loop is aimed to make the overall dynamics similar to an assigned linear through data-driven control design, then the outer economic model-predictive controller compensates for model mismatches, enforces suitable constraints, and boosts the tracking performance. The effectiveness of the proposed approach as compared to traditional dynamic programming strategies is illustrated on an accurate simulator of the Hoa Binh reservoir in Vietnam. Results show that the proposed approach performs better than the one based on stochastic dynamic programming.