Exploring Deep Reinforcement Learning for Holistic Smart Building Control

TL;DR

This paper introduces OCTOPUS, a deep reinforcement learning system for holistic control of building subsystems, optimizing energy use and comfort through a data-driven approach trained on calibrated simulations.

Contribution

The paper presents a novel DRL framework with a unique reward function for multi-system building control, trained on simulated data matching real building operations.

Findings

Achieves 14.26% energy savings over rule-based methods.

Outperforms existing DRL approaches by 8.1%.

Maintains user comfort within desired ranges.

Abstract

In this paper, we take a holistic approach to deal with the tradeoffs between energy use and comfort in commercial buildings. We developed a system called OCTOPUS, which employs a novel deep reinforcement learning (DRL) framework that uses a data-driven approach to find the optimal control sequences of all building's subsystems, including HVAC, lighting, blind and window systems. The DRL architecture includes a novel reward function that allows the framework to explore the tradeoffs between energy use and users' comfort, while at the same time enabling the solution of the high-dimensional control problem due to the interactions of four different building subsystems. In order to cope with OCTOPUS's data training requirements, we argue that calibrated simulations that match the target building operational points are the vehicle to generate enough data to be able to train our DRL framework to find the control solution for the target building. In our work, we trained OCTOPUS with 10-year weather data and a building model that is implemented in the EnergyPlus building simulator, which was calibrated using data from a real production building. Through extensive simulations, we demonstrate that OCTOPUS can achieve 14.26% and 8.1% energy savings compared with the state-of-the-art rule-based method in a LEED Gold Certified building and the latest DRL-based method available in the literature respectively, while maintaining human comfort within a desired range.