Accelerating Reinforcement Learning for HVAC Systems Using an LSTM-based Surrogate Simulator

Date

2025-01-01

Author

Hekimoglu, Mehmet Burak
Alioğlu, Alper
Filiz, Ulas
Ulusoy, İlkay
Schmidt, Klaus Verner

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

422
views

0
downloads

Cite This

Reinforcement learning (RL) has shown great potential in optimizing the operation of HVAC systems, improving energy efficiency, and enhancing user comfort. However, the slow input/output operations associated with simulation tools like EnergyPlus significantly hinder the training process. This paper proposes a novel approach to accelerate RL training by using a data-driven LSTM model to replicate the behavior of a building energy simulator. By training the LSTM model on a set of observations and actions, the model learns to approximate the simulator's dynamics, providing a faster and more efficient training environment for RL agents. We demonstrate that using the LSTM-based surrogate simulator leads to substantial reductions in computational time while maintaining the accuracy of the system's behavior.

Subject Keywords

Building Energy Management, Data-Driven Models, Reinforcement Learning, Training Acceleration

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105015517509&origin=inward
https://hdl.handle.net/11511/115769

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar