Reinforcement Learning for Model-Free Control of a Cooling Network with Uncertain Future Demands

Reinforcement Learning for Model-Free Control of a Cooling Network with Uncertain Future Demands ■

Jeroen Willems, Jeroen Willems, Jeroen Willems, Denis Steckelmacher, Denis Steckelmacher, Denis Steckelmacher, Woulte Schoulte, Woulte Schoulte, Woulte Schoulte, Bruno Depraetere, Bruno Depraetere, Bruno Depraetere, Edward Kikken, Edward Kikken, Edward Kikken, Abdellatif Bey-Temsamani, Abdellatif Bey-Temsamani, Abdellatif Bey-Temsamani, Ann Nowe, Ann Nowe, Ann Nowe

Abstract ■

Optimal control of complex systems often requires access to a high-fidelity model, and information about the (future) external stimuli applied to the system (load, demand, …). An example of such a system is a cooling network, in which one or more chillers provide cooled liquid to a set of users with a variable demand. In this paper, we propose a Reinforcement Learning (RL) method for such a system with 3 chillers. It does not assume any model, and does not observe the future cooling demand, nor approximations of it. Still, we show that, after a training phase in a simulator, the learned controller achieves a performance better than classical rule-based controllers, and similar to a model predictive controller that does rely on a model and demand predictions. We show that the RL algorithm has learned implicitly how to anticipate, without requiring explicit predictions. This demonstrates that RL can allow to produce high-quality controllers in challenging industrial contexts.