Community Microgrid Scheduling Considering Building Thermal Dynamics Using a Deep Learning Approach

Dhiraj Pokhrel; Saurav Dulal; Guodong Liu

doi:10.3390/electronics15081719

Community Microgrid Scheduling Considering Building Thermal Dynamics Using a Deep Learning Approach

Dhiraj Pokhrel
, Saurav Dulal
, Guodong Liu

Grid Systems Architecture

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

This paper proposes a deep-learning-based scheduling approach for community microgrids that explicitly accounts for building thermal dynamics and customer comfort preferences. Traditional heating, ventilation, and air-conditioning (HVAC) scheduling models are NP-hard and scale poorly, especially for large systems with many buildings. To address this challenge, we develop a dual-encoder deep learning model that predicts building-level HVAC ON/OFF schedules using temporal load and temperature profiles, along with static building thermal parameters. The proposed model is trained in a supervised manner using solutions generated by an optimization-based HVAC scheduling framework, thereby serving as a computationally efficient surrogate for predicting HVAC schedules within a microgrid. The model is trained on samples generated by the optimization-based HVAC scheduling framework and evaluated using precision, recall, and F1-score. The results indicate strong predictive performance.

Original language	English
Article number	1719
Journal	Electronics (Switzerland)
Volume	15
Issue number	8
DOIs	https://doi.org/10.3390/electronics15081719
State	Published - Apr 2026

Funding

This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan ( http://energy.gov/downloads/doe-public-access-plan accessed on 17 April 2026).

Keywords

HVAC scheduling
community microgrid
customer comfort
deep learning
optimization
thermal dynamic model

Access to Document

10.3390/electronics15081719

Cite this

@article{41556f117f9f40869b70a323032eac5e,

title = "Community Microgrid Scheduling Considering Building Thermal Dynamics Using a Deep Learning Approach",

abstract = "This paper proposes a deep-learning-based scheduling approach for community microgrids that explicitly accounts for building thermal dynamics and customer comfort preferences. Traditional heating, ventilation, and air-conditioning (HVAC) scheduling models are NP-hard and scale poorly, especially for large systems with many buildings. To address this challenge, we develop a dual-encoder deep learning model that predicts building-level HVAC ON/OFF schedules using temporal load and temperature profiles, along with static building thermal parameters. The proposed model is trained in a supervised manner using solutions generated by an optimization-based HVAC scheduling framework, thereby serving as a computationally efficient surrogate for predicting HVAC schedules within a microgrid. The model is trained on samples generated by the optimization-based HVAC scheduling framework and evaluated using precision, recall, and F1-score. The results indicate strong predictive performance.",

keywords = "HVAC scheduling, community microgrid, customer comfort, deep learning, optimization, thermal dynamic model",

author = "Dhiraj Pokhrel and Saurav Dulal and Guodong Liu",

note = "Publisher Copyright: {\textcopyright} 2026 by the authors.",

year = "2026",

month = apr,

doi = "10.3390/electronics15081719",

language = "English",

volume = "15",

journal = "Electronics (Switzerland)",

issn = "2079-9292",

publisher = "MDPI",

number = "8",

}

TY - JOUR

T1 - Community Microgrid Scheduling Considering Building Thermal Dynamics Using a Deep Learning Approach

AU - Pokhrel, Dhiraj

AU - Dulal, Saurav

AU - Liu, Guodong

PY - 2026/4

Y1 - 2026/4

N2 - This paper proposes a deep-learning-based scheduling approach for community microgrids that explicitly accounts for building thermal dynamics and customer comfort preferences. Traditional heating, ventilation, and air-conditioning (HVAC) scheduling models are NP-hard and scale poorly, especially for large systems with many buildings. To address this challenge, we develop a dual-encoder deep learning model that predicts building-level HVAC ON/OFF schedules using temporal load and temperature profiles, along with static building thermal parameters. The proposed model is trained in a supervised manner using solutions generated by an optimization-based HVAC scheduling framework, thereby serving as a computationally efficient surrogate for predicting HVAC schedules within a microgrid. The model is trained on samples generated by the optimization-based HVAC scheduling framework and evaluated using precision, recall, and F1-score. The results indicate strong predictive performance.

AB - This paper proposes a deep-learning-based scheduling approach for community microgrids that explicitly accounts for building thermal dynamics and customer comfort preferences. Traditional heating, ventilation, and air-conditioning (HVAC) scheduling models are NP-hard and scale poorly, especially for large systems with many buildings. To address this challenge, we develop a dual-encoder deep learning model that predicts building-level HVAC ON/OFF schedules using temporal load and temperature profiles, along with static building thermal parameters. The proposed model is trained in a supervised manner using solutions generated by an optimization-based HVAC scheduling framework, thereby serving as a computationally efficient surrogate for predicting HVAC schedules within a microgrid. The model is trained on samples generated by the optimization-based HVAC scheduling framework and evaluated using precision, recall, and F1-score. The results indicate strong predictive performance.

KW - HVAC scheduling

KW - community microgrid

KW - customer comfort

KW - deep learning

KW - optimization

KW - thermal dynamic model

UR - https://www.scopus.com/pages/publications/105037212664

U2 - 10.3390/electronics15081719

DO - 10.3390/electronics15081719

M3 - Article

AN - SCOPUS:105037212664

SN - 2079-9292

VL - 15

JO - Electronics (Switzerland)

JF - Electronics (Switzerland)

IS - 8

M1 - 1719

ER -

Community Microgrid Scheduling Considering Building Thermal Dynamics Using a Deep Learning Approach

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this