Deep Reinforcement Learning for Building HVAC Control

Tianshu Wei; Yanzhi Wang; Qi Zhu

doi:10.1145/3061639.3062224

Deep Reinforcement Learning for Building HVAC Control

Tianshu Wei, Yanzhi Wang, Qi Zhu

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

369 Scopus citations

Abstract

Buildings account for nearly 40% of the total energy consumption in the United States, about half of which is used by the HVAC (heating, ventilation, and air conditioning) system. Intelligent scheduling of building HVAC systems has the potential to significantly reduce the energy cost. However, the traditional rule-based and model-based strategies are often inefficient in practice, due to the complexity in building thermal dynamics and heterogeneous environment disturbances. In this work, we develop a data-driven approach that leverages the deep reinforcement learning (DRL) technique, to intelligently learn the effective strategy for operating the building HVAC systems. We evaluate the performance of our DRL algorithm through simulations using the widely-adopted EnergyPlus tool. Experiments demonstrate that our DRL-based algorithm is more effective in energy cost reduction compared with the traditional rule-based approach, while maintaining the room temperature within desired range.

Original language	English (US)
Title of host publication	Proceedings of the 54th Annual Design Automation Conference 2017, DAC 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781450349277
DOIs	https://doi.org/10.1145/3061639.3062224
State	Published - Jun 18 2017
Event	54th Annual Design Automation Conference, DAC 2017 - Austin, United States Duration: Jun 18 2017 → Jun 22 2017

Publication series

Name	Proceedings - Design Automation Conference
Volume	Part 128280
ISSN (Print)	0738-100X

Other

Other	54th Annual Design Automation Conference, DAC 2017
Country/Territory	United States
City	Austin
Period	6/18/17 → 6/22/17

Funding

The authors gratefully acknowledge the support from the National Science Foundation award CCF-1553757 and the Riverside Public Utilities.

ASJC Scopus subject areas

Computer Science Applications
Control and Systems Engineering
Electrical and Electronic Engineering
Modeling and Simulation

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3061639.3062224

Cite this

@inproceedings{9bbb270f34924e5699b800e8185987db,

title = "Deep Reinforcement Learning for Building HVAC Control",

abstract = "Buildings account for nearly 40% of the total energy consumption in the United States, about half of which is used by the HVAC (heating, ventilation, and air conditioning) system. Intelligent scheduling of building HVAC systems has the potential to significantly reduce the energy cost. However, the traditional rule-based and model-based strategies are often inefficient in practice, due to the complexity in building thermal dynamics and heterogeneous environment disturbances. In this work, we develop a data-driven approach that leverages the deep reinforcement learning (DRL) technique, to intelligently learn the effective strategy for operating the building HVAC systems. We evaluate the performance of our DRL algorithm through simulations using the widely-adopted EnergyPlus tool. Experiments demonstrate that our DRL-based algorithm is more effective in energy cost reduction compared with the traditional rule-based approach, while maintaining the room temperature within desired range.",

author = "Tianshu Wei and Yanzhi Wang and Qi Zhu",

note = "Funding Information: The authors gratefully acknowledge the support from the National Science Foundation award CCF-1553757 and the Riverside Public Utilities. Publisher Copyright: {\textcopyright} 2017 ACM.; 54th Annual Design Automation Conference, DAC 2017 ; Conference date: 18-06-2017 Through 22-06-2017",

year = "2017",

month = jun,

day = "18",

doi = "10.1145/3061639.3062224",

language = "English (US)",

series = "Proceedings - Design Automation Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of the 54th Annual Design Automation Conference 2017, DAC 2017",

address = "United States",

}

Wei, T, Wang, Y & Zhu, Q 2017, Deep Reinforcement Learning for Building HVAC Control. in Proceedings of the 54th Annual Design Automation Conference 2017, DAC 2017., 22, Proceedings - Design Automation Conference, vol. Part 128280, Institute of Electrical and Electronics Engineers Inc., 54th Annual Design Automation Conference, DAC 2017, Austin, United States, 6/18/17. https://doi.org/10.1145/3061639.3062224

Deep Reinforcement Learning for Building HVAC Control. / Wei, Tianshu; Wang, Yanzhi; Zhu, Qi.
Proceedings of the 54th Annual Design Automation Conference 2017, DAC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 22 (Proceedings - Design Automation Conference; Vol. Part 128280).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deep Reinforcement Learning for Building HVAC Control

AU - Wei, Tianshu

AU - Wang, Yanzhi

AU - Zhu, Qi

PY - 2017/6/18

Y1 - 2017/6/18

N2 - Buildings account for nearly 40% of the total energy consumption in the United States, about half of which is used by the HVAC (heating, ventilation, and air conditioning) system. Intelligent scheduling of building HVAC systems has the potential to significantly reduce the energy cost. However, the traditional rule-based and model-based strategies are often inefficient in practice, due to the complexity in building thermal dynamics and heterogeneous environment disturbances. In this work, we develop a data-driven approach that leverages the deep reinforcement learning (DRL) technique, to intelligently learn the effective strategy for operating the building HVAC systems. We evaluate the performance of our DRL algorithm through simulations using the widely-adopted EnergyPlus tool. Experiments demonstrate that our DRL-based algorithm is more effective in energy cost reduction compared with the traditional rule-based approach, while maintaining the room temperature within desired range.

AB - Buildings account for nearly 40% of the total energy consumption in the United States, about half of which is used by the HVAC (heating, ventilation, and air conditioning) system. Intelligent scheduling of building HVAC systems has the potential to significantly reduce the energy cost. However, the traditional rule-based and model-based strategies are often inefficient in practice, due to the complexity in building thermal dynamics and heterogeneous environment disturbances. In this work, we develop a data-driven approach that leverages the deep reinforcement learning (DRL) technique, to intelligently learn the effective strategy for operating the building HVAC systems. We evaluate the performance of our DRL algorithm through simulations using the widely-adopted EnergyPlus tool. Experiments demonstrate that our DRL-based algorithm is more effective in energy cost reduction compared with the traditional rule-based approach, while maintaining the room temperature within desired range.

UR - http://www.scopus.com/inward/record.url?scp=85023647422&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023647422&partnerID=8YFLogxK

U2 - 10.1145/3061639.3062224

DO - 10.1145/3061639.3062224

M3 - Conference contribution

AN - SCOPUS:85023647422

T3 - Proceedings - Design Automation Conference

BT - Proceedings of the 54th Annual Design Automation Conference 2017, DAC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 54th Annual Design Automation Conference, DAC 2017

Y2 - 18 June 2017 through 22 June 2017

ER -

Deep Reinforcement Learning for Building HVAC Control

Abstract

Publication series

Other

Funding

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this