Development of a Soft Actor Critic Deep Reinforcement Learning Approach for Harnessing Energy Flexibility in a Large Office Building

TL;DR

This paper demonstrates that Soft Actor Critic Deep Reinforcement Learning can effectively control cooling loads in large office buildings, reducing energy costs by nearly 10% while maintaining comfort, and is adaptable across different climates and seasons.

Contribution

The study applies SAC DRL to building energy management, showing its effectiveness and robustness in real-world simulation, which is novel for this control approach.

Findings

SAC DRL reduces energy costs by 9.7% compared to rule-based control.

The algorithm maintains thermal comfort over a week-long test period.

Minimal training data needed for effective control policy learning.

Abstract

This research is concerned with the novel application and investigation of `Soft Actor Critic' (SAC) based Deep Reinforcement Learning (DRL) to control the cooling setpoint (and hence cooling loads) of a large commercial building to harness energy flexibility. The research is motivated by the challenge associated with the development and application of conventional model-based control approaches at scale to the wider building stock. SAC is a model-free DRL technique that is able to handle continuous action spaces and which has seen limited application to real-life or high-fidelity simulation implementations in the context of automated and intelligent control of building energy systems. Such control techniques are seen as one possible solution to supporting the operation of a smart, sustainable and future electrical grid. This research tests the suitability of the SAC DRL technique through training and deployment of the agent on an EnergyPlus based environment of the office building. The SAC DRL was found to learn an optimal control policy that was able to minimise energy costs by 9.7% compared to the default rule-based control (RBC) scheme and was able to improve or maintain thermal comfort limits over a test period of one week. The algorithm was shown to be robust to the different hyperparameters and this optimal control policy was learnt through the use of a minimal state space consisting of readily available variables. The robustness of the algorithm was tested through investigation of the speed of learning and ability to deploy to different seasons and climates. It was found that the SAC DRL requires minimal training sample points and outperforms the RBC after three months of operation and also without disruption to thermal comfort during this period. The agent is transferable to other climates and seasons although further retraining or hyperparameter tuning is recommended.