District Cooling System Control for Providing Operating Reserve based on Safe Deep Reinforcement Learning

TL;DR

This paper introduces a safe deep reinforcement learning control strategy for district cooling systems to provide operating reserve, ensuring system security and thermal comfort while managing peak power rebound.

Contribution

It develops a model-free, safe DRL control scheme with a self-adaptive reward function to effectively regulate DCS for reserve provision without system modeling.

Findings

The proposed safe-DRL scheme guarantees system safety during training.

The method effectively manages peak power rebound after reserve provision.

Numerical studies validate the approach's effectiveness on realistic DCS data.

Abstract

Heating, ventilation, and air conditioning (HVAC) systems are well proved to be capable to provide operating reserve for power systems. As a type of large-capacity and energy-efficient HVAC system (up to 100 MW), district cooling system (DCS) is emerging in modern cities and has huge potential to be regulated as a flexible load. However, strategically controlling a DCS to provide flexibility is challenging, because one DCS services multiple buildings with complex thermal dynamics and uncertain cooling demands. Improper control may lead to significant thermal discomfort and even deteriorate the power system's operation security. To address the above issues, we propose a model-free control strategy based on the deep reinforcement learning (DRL) without the requirement of accurate system model and uncertainty distribution. To avoid damaging "trial & error" actions that may violate the system's operation security during the training process, we further propose a safe layer combined to the DRL to guarantee the satisfaction of critical constraints, forming a safe-DRL scheme. Moreover, after providing operating reserve, DCS increases power and tries to recover all the buildings' temperature back to set values, which may probably cause an instantaneous peak-power rebound and bring a secondary impact on power systems. Therefore, we design a self-adaption reward function within the proposed safe-DRL scheme to constrain the peak-power effectively. Numerical studies based on a realistic DCS demonstrate the effectiveness of the proposed methods.