Reinforcement Learning-Based School Energy Management System

<p dir="ltr">Energy efficiency is a key to reduced carbon footprint, savings on energy bills, and sustainability for future generations. For instance, in hot climate countries such as Qatar, buildings are high energy consumers due to air conditioning that resulted from high temperatu...

Full description

Saved in:
Bibliographic Details
Main Author: Yassine Chemingui (18891757) (author)
Other Authors: Adel Gastli (14151273) (author), Omar Ellabban (16864227) (author)
Published: 2020
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513511917355008
author Yassine Chemingui (18891757)
author2 Adel Gastli (14151273)
Omar Ellabban (16864227)
author2_role author
author
author_facet Yassine Chemingui (18891757)
Adel Gastli (14151273)
Omar Ellabban (16864227)
author_role author
dc.creator.none.fl_str_mv Yassine Chemingui (18891757)
Adel Gastli (14151273)
Omar Ellabban (16864227)
dc.date.none.fl_str_mv 2020-12-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.3390/en13236354
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Reinforcement_Learning-Based_School_Energy_Management_System/26114554
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Information and computing sciences
Machine learning
energy efficiency
energy management
indoor air quality
reinforcement learning
smart building
thermal comfort
dc.title.none.fl_str_mv Reinforcement Learning-Based School Energy Management System
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Energy efficiency is a key to reduced carbon footprint, savings on energy bills, and sustainability for future generations. For instance, in hot climate countries such as Qatar, buildings are high energy consumers due to air conditioning that resulted from high temperatures and humidity. Optimizing the building energy management system will reduce unnecessary energy consumptions, improve indoor environmental conditions, maximize building occupant’s comfort, and limit building greenhouse gas emissions. However, lowering energy consumption cannot be done despite the occupants’ comfort. Solutions must take into account these tradeoffs. Conventional Building Energy Management methods suffer from a high dimensional and complex control environment. In recent years, the Deep Reinforcement Learning algorithm, applying neural networks for function approximation, shows promising results in handling such complex problems. In this work, a Deep Reinforcement Learning agent is proposed for controlling and optimizing a school building’s energy consumption. It is designed to search for optimal policies to minimize energy consumption, maintain thermal comfort, and reduce indoor contaminant levels in a challenging 21-zone environment. First, the agent is trained with the baseline in a supervised learning framework. After cloning the baseline strategy, the agent learns with proximal policy optimization in an actor-critic framework. The performance is evaluated on a school model simulated environment considering thermal comfort, CO2 levels, and energy consumption. The proposed methodology can achieve a 21% reduction in energy consumption, a 44% better thermal comfort, and healthier CO<sub>2</sub> concentrations over a one-year simulation, with reduced training time thanks to the integration of the behavior cloning learning technique.</p><h2>Other Information</h2><p dir="ltr">Published in: Energies<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/en13236354" target="_blank">https://dx.doi.org/10.3390/en13236354</a></p>
eu_rights_str_mv openAccess
id Manara2_f5df9bf43fc9ec180aa0b700d04ee593
identifier_str_mv 10.3390/en13236354
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26114554
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Reinforcement Learning-Based School Energy Management SystemYassine Chemingui (18891757)Adel Gastli (14151273)Omar Ellabban (16864227)EngineeringElectrical engineeringInformation and computing sciencesMachine learningenergy efficiencyenergy managementindoor air qualityreinforcement learningsmart buildingthermal comfort<p dir="ltr">Energy efficiency is a key to reduced carbon footprint, savings on energy bills, and sustainability for future generations. For instance, in hot climate countries such as Qatar, buildings are high energy consumers due to air conditioning that resulted from high temperatures and humidity. Optimizing the building energy management system will reduce unnecessary energy consumptions, improve indoor environmental conditions, maximize building occupant’s comfort, and limit building greenhouse gas emissions. However, lowering energy consumption cannot be done despite the occupants’ comfort. Solutions must take into account these tradeoffs. Conventional Building Energy Management methods suffer from a high dimensional and complex control environment. In recent years, the Deep Reinforcement Learning algorithm, applying neural networks for function approximation, shows promising results in handling such complex problems. In this work, a Deep Reinforcement Learning agent is proposed for controlling and optimizing a school building’s energy consumption. It is designed to search for optimal policies to minimize energy consumption, maintain thermal comfort, and reduce indoor contaminant levels in a challenging 21-zone environment. First, the agent is trained with the baseline in a supervised learning framework. After cloning the baseline strategy, the agent learns with proximal policy optimization in an actor-critic framework. The performance is evaluated on a school model simulated environment considering thermal comfort, CO2 levels, and energy consumption. The proposed methodology can achieve a 21% reduction in energy consumption, a 44% better thermal comfort, and healthier CO<sub>2</sub> concentrations over a one-year simulation, with reduced training time thanks to the integration of the behavior cloning learning technique.</p><h2>Other Information</h2><p dir="ltr">Published in: Energies<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/en13236354" target="_blank">https://dx.doi.org/10.3390/en13236354</a></p>2020-12-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.3390/en13236354https://figshare.com/articles/journal_contribution/Reinforcement_Learning-Based_School_Energy_Management_System/26114554CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/261145542020-12-01T00:00:00Z
spellingShingle Reinforcement Learning-Based School Energy Management System
Yassine Chemingui (18891757)
Engineering
Electrical engineering
Information and computing sciences
Machine learning
energy efficiency
energy management
indoor air quality
reinforcement learning
smart building
thermal comfort
status_str publishedVersion
title Reinforcement Learning-Based School Energy Management System
title_full Reinforcement Learning-Based School Energy Management System
title_fullStr Reinforcement Learning-Based School Energy Management System
title_full_unstemmed Reinforcement Learning-Based School Energy Management System
title_short Reinforcement Learning-Based School Energy Management System
title_sort Reinforcement Learning-Based School Energy Management System
topic Engineering
Electrical engineering
Information and computing sciences
Machine learning
energy efficiency
energy management
indoor air quality
reinforcement learning
smart building
thermal comfort