Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency

Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly being considered as solutions to support carbon reduction goals and increase grid reliability and resiliency. However, dynamic control of these r...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied energy Jg. 304; S. 117733
Hauptverfasser: Touzani, Samir, Prakash, Anand Krishnan, Wang, Zhe, Agarwal, Shreya, Pritoni, Marco, Kiran, Mariam, Brown, Richard, Granderson, Jessica
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Elsevier Ltd 15.12.2021
Elsevier
Schlagworte:
ISSN:0306-2619, 1872-9118
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly being considered as solutions to support carbon reduction goals and increase grid reliability and resiliency. However, dynamic control of these resources in concert with traditional building loads, to effect efficiency and demand flexibility, is not yet commonplace in commercial control products. Traditional rule-based control algorithms do not offer integrated closed-loop control to optimize across systems, and most often, PV and battery systems are operated for energy arbitrage and demand charge management, and not for the provision of grid services. More advanced control approaches, such as MPC control have not been widely adopted in industry because they require significant expertise to develop and deploy. Recent advances in deep reinforcement learning (DRL) offer a promising option to optimize the operation of DER systems and building loads with reduced setup effort. However, there are limited studies that evaluate the efficacy of these methods to control multiple building subsystems simultaneously. Additionally, most of the research has been conducted in simulated environments as opposed to real buildings. This paper proposes a DRL approach that uses a deep deterministic policy gradient algorithm for integrated control of HVAC and electric battery storage systems in the presence of on-site PV generation. The DRL algorithm, trained on synthetic data, was deployed in a physical test building and evaluated against a baseline that uses the current best-in-class rule-based control strategies. Performance in delivering energy efficiency, load shift, and load shed was tested using price-based signals. The results showed that the DRL-based controller can produce cost savings of up to 39.6% as compared to the baseline controller, while maintaining similar thermal comfort in the building. The project team has also integrated the simulation components developed during this work as an OpenAIGym environment and made it publicly available so that prospective DRL researchers can leverage this environment to evaluate alternate DRL algorithms. •Traditional controls do not integrate distributed energy resources (DER) systems.•Deterministic policy gradient algorithm is proposed to optimize the operation of DER.•The algorithm is deployed and evaluated in a physical test building.•Tests include energy efficiency, load shift, and load shed.•An OpenAI Gym environment is made it publicly available for other researchers.
AbstractList Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly being considered as solutions to support carbon reduction goals and increase grid reliability and resiliency. However, dynamic control of these resources in concert with traditional building loads, to effect efficiency and demand flexibility, is not yet commonplace in commercial control products. Traditional rule-based control algorithms do not offer integrated closed-loop control to optimize across systems, and most often, PV and battery systems are operated for energy arbitrage and demand charge management, and not for the provision of grid services. More advanced control approaches, such as MPC control have not been widely adopted in industry because they require significant expertise to develop and deploy. Recent advances in deep reinforcement learning (DRL) offer a promising option to optimize the operation of DER systems and building loads with reduced setup effort. However, there are limited studies that evaluate the efficacy of these methods to control multiple building subsystems simultaneously. Additionally, most of the research has been conducted in simulated environments as opposed to real buildings. This paper proposes a DRL approach that uses a deep deterministic policy gradient algorithm for integrated control of HVAC and electric battery storage systems in the presence of on-site PV generation. The DRL algorithm, trained on synthetic data, was deployed in a physical test building and evaluated against a baseline that uses the current best-in-class rule-based control strategies. Performance in delivering energy efficiency, load shift, and load shed was tested using price-based signals. The results showed that the DRL-based controller can produce cost savings of up to 39.6% as compared to the baseline controller, while maintaining similar thermal comfort in the building. The project team has also integrated the simulation components developed during this work as an OpenAIGym environment and made it publicly available so that prospective DRL researchers can leverage this environment to evaluate alternate DRL algorithms. •Traditional controls do not integrate distributed energy resources (DER) systems.•Deterministic policy gradient algorithm is proposed to optimize the operation of DER.•The algorithm is deployed and evaluated in a physical test building.•Tests include energy efficiency, load shift, and load shed.•An OpenAI Gym environment is made it publicly available for other researchers.
Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly being considered as solutions to support carbon reduction goals and increase grid reliability and resiliency. However, dynamic control of these resources in concert with traditional building loads, to effect efficiency and demand flexibility, is not yet commonplace in commercial control products. Traditional rule-based control algorithms do not offer integrated closed-loop control to optimize across systems, and most often, PV and battery systems are operated for energy arbitrage and demand charge management, and not for the provision of grid services. More advanced control approaches, such as MPC control have not been widely adopted in industry because they require significant expertise to develop and deploy. Recent advances in deep reinforcement learning (DRL) offer a promising option to optimize the operation of DER systems and building loads with reduced setup effort. However, there are limited studies that evaluate the efficacy of these methods to control multiple building subsystems simultaneously. Additionally, most of the research has been conducted in simulated environments as opposed to real buildings. This paper proposes a DRL approach that uses a deep deterministic policy gradient algorithm for integrated control of HVAC and electric battery storage systems in the presence of on-site PV generation. The DRL algorithm, trained on synthetic data, was deployed in a physical test building and evaluated against a baseline that uses the current best-in-class rule-based control strategies. Performance in delivering energy efficiency, load shift, and load shed was tested using price-based signals. The results showed that the DRL-based controller can produce cost savings of up to 39.6% as compared to the baseline controller, while maintaining similar thermal comfort in the building. The project team has also integrated the simulation components developed during this work as an OpenAIGym environment and made it publicly available so that prospective DRL researchers can leverage this environment to evaluate alternate DRL algorithms.
ArticleNumber 117733
Author Wang, Zhe
Pritoni, Marco
Kiran, Mariam
Prakash, Anand Krishnan
Agarwal, Shreya
Brown, Richard
Touzani, Samir
Granderson, Jessica
Author_xml – sequence: 1
  givenname: Samir
  surname: Touzani
  fullname: Touzani, Samir
– sequence: 2
  givenname: Anand Krishnan
  orcidid: 0000-0002-3694-3225
  surname: Prakash
  fullname: Prakash, Anand Krishnan
– sequence: 3
  givenname: Zhe
  orcidid: 0000-0002-2231-1606
  surname: Wang
  fullname: Wang, Zhe
– sequence: 4
  givenname: Shreya
  surname: Agarwal
  fullname: Agarwal, Shreya
– sequence: 5
  givenname: Marco
  orcidid: 0000-0003-4200-6905
  surname: Pritoni
  fullname: Pritoni, Marco
  email: mpritoni@lbl.gov
– sequence: 6
  givenname: Mariam
  surname: Kiran
  fullname: Kiran, Mariam
– sequence: 7
  givenname: Richard
  surname: Brown
  fullname: Brown, Richard
– sequence: 8
  givenname: Jessica
  surname: Granderson
  fullname: Granderson, Jessica
BackLink https://www.osti.gov/servlets/purl/1860348$$D View this record in Osti.gov
BookMark eNqFUcFuEzEQtVCRSEN_oVpx4rKp7XW9uxIHUAQtUiUucLac8WyZyLGD7VTk7_FqoQcuvcxIT-89zbx3yS5CDMjYteAbwYW-2W_sEQOmx_NGcik2QvR9171iKzH0sh2FGC7Yindct1KL8Q27zHnPeWVKvmJ5G0NJ0XsKj42jXBLtTgVdszg2CXM8JcDcPJFtHOKxQhSmWLEDhtJ4tCnM4go1PlrXTB5_0448lXNjw7MTThMBYYDzW_Z6sj7j1d-9Zj--fP6-vW8fvt193X56aEFJXlqtOEgN4wBj1w-yzs6p8XYHgKrXgMK6WxwmoToQ3O0GPQFoMSmtnVT92Hdr9m7xjbmQyUAF4SfEEBCKEYPmnRoq6f1COqb464S5mANlQO9twHjKRupOK6lU3WumFyqkmHPCyRwTHWw6G8HNXIXZm39VmLkKs1RRhR_-E9ZbbKE5ekv-ZfnHRY41rCfCNP9Sg0RHaX7FRXrJ4g9nPK4N
CitedBy_id crossref_primary_10_1109_ACCESS_2025_3541841
crossref_primary_10_1109_JIOT_2023_3263261
crossref_primary_10_1016_j_jobe_2023_106114
crossref_primary_10_1109_THMS_2022_3216365
crossref_primary_10_1016_j_enbuild_2022_112709
crossref_primary_10_1016_j_enbuild_2024_113913
crossref_primary_10_1016_j_buildenv_2022_109681
crossref_primary_10_1016_j_energy_2024_132636
crossref_primary_10_1016_j_est_2025_116209
crossref_primary_10_3390_en15176392
crossref_primary_10_1016_j_buildenv_2023_110435
crossref_primary_10_1016_j_jobe_2025_114024
crossref_primary_10_3390_en18071724
crossref_primary_10_1016_j_jobe_2025_111909
crossref_primary_10_1016_j_applthermaleng_2023_120430
crossref_primary_10_1016_j_energy_2023_129097
crossref_primary_10_3390_en16083477
crossref_primary_10_1016_j_enbuild_2023_112778
crossref_primary_10_1016_j_enbuild_2023_112779
crossref_primary_10_1109_ACCESS_2024_3378749
crossref_primary_10_1016_j_applthermaleng_2025_126106
crossref_primary_10_3389_fenrg_2021_735551
crossref_primary_10_1109_TSG_2025_3536211
crossref_primary_10_1016_j_egyr_2024_11_022
crossref_primary_10_1016_j_enbuild_2024_115066
crossref_primary_10_3390_en16134844
crossref_primary_10_1007_s12273_023_0984_6
crossref_primary_10_1016_j_enbuild_2025_116097
crossref_primary_10_1016_j_engappai_2023_105932
crossref_primary_10_1016_j_suscom_2025_101151
crossref_primary_10_1016_j_enbuild_2025_116170
crossref_primary_10_1016_j_enbuild_2022_112765
crossref_primary_10_1016_j_buildenv_2025_113045
crossref_primary_10_3390_app13053155
crossref_primary_10_3390_buildings15040648
crossref_primary_10_1016_j_rser_2022_112249
crossref_primary_10_3390_su151310480
crossref_primary_10_1007_s12273_025_1233_y
crossref_primary_10_1016_j_apenergy_2023_121792
crossref_primary_10_1016_j_apenergy_2024_124467
crossref_primary_10_1016_j_dib_2023_109149
crossref_primary_10_3390_en15176297
crossref_primary_10_1109_TSG_2023_3308013
crossref_primary_10_1016_j_jobe_2024_110085
crossref_primary_10_1016_j_enbuild_2025_116045
crossref_primary_10_1016_j_egyai_2025_100521
crossref_primary_10_3390_en15228663
crossref_primary_10_1016_j_adapen_2025_100237
crossref_primary_10_1016_j_enbuild_2023_113527
crossref_primary_10_1016_j_apenergy_2022_120021
crossref_primary_10_1016_j_enconman_2023_116802
crossref_primary_10_3389_fbuil_2022_849754
crossref_primary_10_1016_j_enbuild_2024_114355
crossref_primary_10_1016_j_enbuild_2025_116439
crossref_primary_10_1007_s11367_024_02390_y
crossref_primary_10_1016_j_apenergy_2025_126459
crossref_primary_10_3389_fenrg_2025_1542501
crossref_primary_10_3390_buildings15152793
crossref_primary_10_1016_j_apenergy_2022_118863
crossref_primary_10_1109_TPWRS_2023_3286094
Cites_doi 10.1109/TCYB.2019.2927410
10.3390/pr5030046
10.1080/19401493.2013.808265
10.1016/j.apenergy.2020.115036
10.1016/0377-2217(89)90348-2
10.1016/j.rser.2016.10.034
10.1016/j.compeleceng.2019.07.019
10.1109/TSG.2018.2834219
10.1109/TIA.2019.2932963
10.1016/j.energy.2018.03.113
10.1038/nature24270
10.1145/3061639.3062224
10.1016/j.egyai.2020.100020
10.1016/j.enbuild.2019.109608
10.1016/j.enbuild.2019.109420
10.1016/j.energy.2017.12.019
10.1016/j.arcontrol.2020.09.001
10.1145/3360322.3360849
10.1080/00401706.1991.10484804
10.1109/ACCESS.2020.2974286
10.1016/j.enbuild.2020.110490
10.1016/j.enbuild.2019.07.029
10.1038/nature14236
10.1016/j.enbuild.2020.110055
10.1016/j.epsr.2016.12.012
10.1016/j.arcontrol.2020.03.001
10.1109/TPWRS.2018.2823641
10.1016/j.enbuild.2017.06.027
10.1016/j.egypro.2019.01.494
10.3182/20080706-5-KR-1001.01934
10.1016/j.apenergy.2020.115258
10.3390/s20072157
10.1016/j.enbuild.2015.08.025
10.1016/j.apenergy.2018.11.002
10.1109/JIOT.2019.2957289
10.1016/j.enbuild.2020.110225
10.1016/j.apenergy.2019.01.145
ContentType Journal Article
Copyright 2021
Copyright_xml – notice: 2021
CorporateAuthor Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
CorporateAuthor_xml – name: Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
DBID 6I.
AAFTH
AAYXX
CITATION
7S9
L.6
OIOZB
OTOTI
DOI 10.1016/j.apenergy.2021.117733
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
AGRICOLA
AGRICOLA - Academic
OSTI.GOV - Hybrid
OSTI.GOV
DatabaseTitle CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList

AGRICOLA
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Environmental Sciences
EISSN 1872-9118
ExternalDocumentID 1860348
10_1016_j_apenergy_2021_117733
S0306261921010801
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
23M
4.4
457
4G.
5GY
5VS
6I.
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAFTH
AAHCO
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARJD
AAXUO
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ADBBV
ADEZE
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHIDL
AHJVU
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BELTK
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
JARJE
JJJVA
KOM
LY6
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SSR
SST
SSZ
T5K
TN5
~02
~G-
9DU
AAHBH
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABEFU
ABFNM
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
G-2
HVGLF
HZ~
R2-
SAC
SEW
WUQ
ZY4
~HD
7S9
L.6
AALMO
AAPBV
ABPIF
ABPTK
OIOZB
OTOTI
ID FETCH-LOGICAL-c420t-640c26c98c93782c933d495bcce476ce1ad5e8f143c10db86fcc61f466d247973
ISICitedReferencesCount 73
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000701881800003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0306-2619
IngestDate Fri May 19 00:43:35 EDT 2023
Sun Nov 09 14:34:41 EST 2025
Sat Nov 29 07:21:30 EST 2025
Tue Nov 18 20:59:28 EST 2025
Fri Feb 23 02:40:59 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Deep deterministic policy gradient algorithm
Smart buildings
Distributed energy resources
Load flexibility
Deep reinforcement learning
Control systems
Energy efficiency
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c420t-640c26c98c93782c933d495bcce476ce1ad5e8f143c10db86fcc61f466d247973
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
AC02-05CH11231
USDOE Office of Science (SC), Basic Energy Sciences (BES)
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office
ORCID 0000-0002-3694-3225
0000-0003-4200-6905
0000-0002-2231-1606
0000000222311606
0000000342006905
0000000236943225
OpenAccessLink https://www.osti.gov/servlets/purl/1860348
PQID 2636424426
PQPubID 24069
ParticipantIDs osti_scitechconnect_1860348
proquest_miscellaneous_2636424426
crossref_primary_10_1016_j_apenergy_2021_117733
crossref_citationtrail_10_1016_j_apenergy_2021_117733
elsevier_sciencedirect_doi_10_1016_j_apenergy_2021_117733
PublicationCentury 2000
PublicationDate 2021-12-15
PublicationDateYYYYMMDD 2021-12-15
PublicationDate_xml – month: 12
  year: 2021
  text: 2021-12-15
  day: 15
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Applied energy
PublicationYear 2021
Publisher Elsevier Ltd
Elsevier
Publisher_xml – name: Elsevier Ltd
– name: Elsevier
References Vázquez-Canteli, Nagy (b13) 2019; 235
Alfaverh, Denaï, Sun (b48) 2020; 8
Wang, Velswamy, Huang (b27) 2017; 5
Brandi, Piscitelli, Martellacci, Capozzoli (b30) 2020; 224
Kazmi, Mehmood, Lodeweyckx, Driesen (b43) 2018; 144
Liu, Yin, Pritoni, Piette, Neukomm (b57) 2020
Bayram, Ustun (b1) 2017; 72
(b53) 2020
Azuatalam, Lee, de Nijs, Liebman (b33) 2020; 2
Bergstra, Bengio (b64) 2012; 13
Zhang, Chong, Pan, Zhang, Lam (b62) 2019; 199
Lee, Choi (b35) 2020; 20
Mason, Grijalva (b25) 2019; 78
Prakash, Touzani, Kiran, Agarwal, Pritoni, Granderson (b67) 2020
Krishnan Prakash, Zhang, Gupta, Blum, Marshall, Fierro, Alstone, Zoellick, Brown, Pritoni (b5) 2020; 13
Bruno, Giannoccaro, La Scala (b6) 2019; 55
Drgoňa, Arroyo, Cupeiro Figueroa, Blum, Arendt, Kim, Ollé, Oravec, Wetter, Vrabie, Helsen (b12) 2020; 50
Silver, Lever, Heess, Degris, Wierstra, Riedmiller (b22) 2014
Chen B, Cai Z, Bergés M. Gnu-rl: A precocial reinforcement learning solution for building hvac control using a differentiable mpc policy. In: Proceedings of the 6th ACM international conference on systems for energy-efficient buildings, cities, and transportation. 2019; p. 316–25.
Moriyama, De Magistris, Tatsubori, Pham, Munawar, Tachibana (b38) 2018
Zhang, Lam (b37) 2018
Wang, Yang, Wang (b9) 2011
Schreiber, Eschweiler, Baranski, Müller (b49) 2020; 229
Kim, Braun, Cai, Fugate (b7) 2015; 107
Asadinejad, Tomsovic (b56) 2017; 144
Vasudevan, Swarup (b55) 2016
Nouidui, Wetter, Zuo (b59) 2014; 7
Li, Wen, Tao, Guan (b42) 2020; 50
Gehbauer, Mueller, Swenson, Vrettos (b60) 2020
Andersson, Åkesson, Führer (b61) 2016
Lillicrap, Hunt, Pritzel, Heess, Erez, Tassa, Silver, Wierstra (b21) 2015
Neukomm, Nubbe, Fares (b3) 2019
Henderson, Islam, Bachman, Pineau, Precup, Meger (b23) 2018
Foruzan, Soh, Asgarpoor (b2) 2018; 33
Wang, Hong (b15) 2020; 269
Zhang, Zhang, Lam (b40) 2018
Zhang, Chong, Pan, Zhang, Lu, Lam (b39) 2018
Yu, Qin, Zhang, Shen, Jiang, Guan (b52) 2020
Bonthu, Pham, Aguilera, Ha (b8) 2017
Wei T, Wang Y, Zhu Q. Deep reinforcement learning for building HVAC control. In: Proceedings of the 54th annual design automation conference 2017. 2017; p. 1–6.
Granderson, Kramer, Rui, Brown, Curtin (b4) 2020
(b51) 2020
Yang, Zhao, Li, Zomaya (b26) 2020; 49
Kingma, Ba (b65) 2014
Wu, Partridge, Bucknall (b44) 2020; 275
Mnih, Kavukcuoglu, Silver, Rusu, Veness, Bellemare, Graves, Riedmiller, Fidjeland, Ostrovski, Petersen, Beattie, Sadik, Antonoglou, King, Kumaran, Wierstra, Legg, Hassabis (b20) 2015; 518
Gao, Li, Wen (b32) 2019
Tan, Yang, Chen, Song, Chen, Ye, Su (b68) 2018
Yoon, Moon (b31) 2019; 203
Morris (b63) 1991; 33
Qiu, Li, Li, Li, Long, Li (b45) 2020; 218
Wei, Wang, Zhu (b29) 2017
Nagy, Kazmi, Cheaib, Driesen (b34) 2018
Hua, Qin, Hao, Cao (b50) 2019; 239
(b58) 2018
Macarulla, Casals, Forcada, Gangolells (b11) 2017; 151
Silver, Schrittwieser, Simonyan, Antonoglou, Huang, Guez, Hubert, Baker, Lai, Bolton (b17) 2017; 550
Liang, Liaw, Nishihara, Moritz, Fox, Goldberg, Gonzalez, Jordan, Stoica (b24) 2018; vol. 80
Soares, Geysen, Spiessens, Ectors, De Somer, Vanthournout (b46) 2020; 207
Sohlberg, Jacobsen (b69) 2008; 41
Jia, Jin, Sun, Hong, Spanos (b28) 2019; 158
White, White (b16) 1989; 39
Zhang, Chong, Pan, Zhang, Lam (b41) 2019; 199
Islam, Henderson, Gomrokchi, Precup (b66) 2017
(b54) 2020
Yu, Xie, Xie, Zou, Zhang, Sun, Zhang, Zhang, Jiang (b47) 2020; 7
Mocanu, Mocanu, Nguyen, Liotta, Webber, Gibescu, Slootweg (b18) 2019; 10
Sutton, Barto (b14) 2018
Reynolds, Rezgui, Kwan, Piriou (b10) 2018; 151
Jia (10.1016/j.apenergy.2021.117733_b28) 2019; 158
Lillicrap (10.1016/j.apenergy.2021.117733_b21) 2015
10.1016/j.apenergy.2021.117733_b19
Nagy (10.1016/j.apenergy.2021.117733_b34) 2018
Bergstra (10.1016/j.apenergy.2021.117733_b64) 2012; 13
Islam (10.1016/j.apenergy.2021.117733_b66) 2017
Granderson (10.1016/j.apenergy.2021.117733_b4) 2020
Lee (10.1016/j.apenergy.2021.117733_b35) 2020; 20
Foruzan (10.1016/j.apenergy.2021.117733_b2) 2018; 33
Bruno (10.1016/j.apenergy.2021.117733_b6) 2019; 55
Wang (10.1016/j.apenergy.2021.117733_b9) 2011
(10.1016/j.apenergy.2021.117733_b53) 2020
Morris (10.1016/j.apenergy.2021.117733_b63) 1991; 33
Azuatalam (10.1016/j.apenergy.2021.117733_b33) 2020; 2
White (10.1016/j.apenergy.2021.117733_b16) 1989; 39
Sohlberg (10.1016/j.apenergy.2021.117733_b69) 2008; 41
(10.1016/j.apenergy.2021.117733_b51) 2020
Zhang (10.1016/j.apenergy.2021.117733_b37) 2018
Kim (10.1016/j.apenergy.2021.117733_b7) 2015; 107
Yu (10.1016/j.apenergy.2021.117733_b52) 2020
Asadinejad (10.1016/j.apenergy.2021.117733_b56) 2017; 144
Liu (10.1016/j.apenergy.2021.117733_b57) 2020
(10.1016/j.apenergy.2021.117733_b54) 2020
Bonthu (10.1016/j.apenergy.2021.117733_b8) 2017
Silver (10.1016/j.apenergy.2021.117733_b22) 2014
Yang (10.1016/j.apenergy.2021.117733_b26) 2020; 49
Krishnan Prakash (10.1016/j.apenergy.2021.117733_b5) 2020; 13
Tan (10.1016/j.apenergy.2021.117733_b68) 2018
Yu (10.1016/j.apenergy.2021.117733_b47) 2020; 7
Liang (10.1016/j.apenergy.2021.117733_b24) 2018; vol. 80
Mason (10.1016/j.apenergy.2021.117733_b25) 2019; 78
10.1016/j.apenergy.2021.117733_b36
Hua (10.1016/j.apenergy.2021.117733_b50) 2019; 239
(10.1016/j.apenergy.2021.117733_b58) 2018
Gehbauer (10.1016/j.apenergy.2021.117733_b60) 2020
Vasudevan (10.1016/j.apenergy.2021.117733_b55) 2016
Zhang (10.1016/j.apenergy.2021.117733_b41) 2019; 199
Soares (10.1016/j.apenergy.2021.117733_b46) 2020; 207
Macarulla (10.1016/j.apenergy.2021.117733_b11) 2017; 151
Alfaverh (10.1016/j.apenergy.2021.117733_b48) 2020; 8
Kingma (10.1016/j.apenergy.2021.117733_b65) 2014
Henderson (10.1016/j.apenergy.2021.117733_b23) 2018
Brandi (10.1016/j.apenergy.2021.117733_b30) 2020; 224
Andersson (10.1016/j.apenergy.2021.117733_b61) 2016
Schreiber (10.1016/j.apenergy.2021.117733_b49) 2020; 229
Nouidui (10.1016/j.apenergy.2021.117733_b59) 2014; 7
Bayram (10.1016/j.apenergy.2021.117733_b1) 2017; 72
Neukomm (10.1016/j.apenergy.2021.117733_b3) 2019
Zhang (10.1016/j.apenergy.2021.117733_b39) 2018
Prakash (10.1016/j.apenergy.2021.117733_b67) 2020
Silver (10.1016/j.apenergy.2021.117733_b17) 2017; 550
Gao (10.1016/j.apenergy.2021.117733_b32) 2019
Zhang (10.1016/j.apenergy.2021.117733_b40) 2018
Reynolds (10.1016/j.apenergy.2021.117733_b10) 2018; 151
Zhang (10.1016/j.apenergy.2021.117733_b62) 2019; 199
Wei (10.1016/j.apenergy.2021.117733_b29) 2017
Qiu (10.1016/j.apenergy.2021.117733_b45) 2020; 218
Yoon (10.1016/j.apenergy.2021.117733_b31) 2019; 203
Mocanu (10.1016/j.apenergy.2021.117733_b18) 2019; 10
Drgoňa (10.1016/j.apenergy.2021.117733_b12) 2020; 50
Moriyama (10.1016/j.apenergy.2021.117733_b38) 2018
Sutton (10.1016/j.apenergy.2021.117733_b14) 2018
Mnih (10.1016/j.apenergy.2021.117733_b20) 2015; 518
Kazmi (10.1016/j.apenergy.2021.117733_b43) 2018; 144
Wu (10.1016/j.apenergy.2021.117733_b44) 2020; 275
Wang (10.1016/j.apenergy.2021.117733_b15) 2020; 269
Vázquez-Canteli (10.1016/j.apenergy.2021.117733_b13) 2019; 235
Li (10.1016/j.apenergy.2021.117733_b42) 2020; 50
Wang (10.1016/j.apenergy.2021.117733_b27) 2017; 5
References_xml – volume: 144
  start-page: 215
  year: 2017
  end-page: 223
  ident: b56
  article-title: Optimal use of incentive and price based demand response to reduce costs and price volatility
  publication-title: Electr Power Syst Res
– volume: 7
  start-page: 192
  year: 2014
  end-page: 202
  ident: b59
  article-title: Functional mock-up unit for co-simulation import in EnergyPlus
  publication-title: J Build Perform Simul
– year: 2016
  ident: b61
  article-title: Pyfmi: A Python package for simulation of coupled dynamic models with the functional mock-up interface
– year: 2015
  ident: b21
  article-title: Continuous control with deep reinforcement learning
– year: 2018
  ident: b68
  article-title: Sim-to-real optimization of complex real world mobile network with imperfect information via deep reinforcement learning from self-play
– start-page: 1
  year: 2011
  end-page: 7
  ident: b9
  article-title: Intelligent multi-agent control for integrated building and micro-grid systems
  publication-title: ISGT 2011
– volume: 33
  start-page: 5749
  year: 2018
  end-page: 5758
  ident: b2
  article-title: Reinforcement learning approach for optimal distributed energy management in a microgrid
  publication-title: IEEE Trans Power Syst
– start-page: 45
  year: 2018
  end-page: 59
  ident: b38
  article-title: Reinforcement learning testbed for power-consumption optimization
  publication-title: Methods and applications for modeling and simulation of complex systems
– volume: 20
  year: 2020
  ident: b35
  article-title: Energy management of smart home with home appliances, energy storage system and electric vehicle: A hierarchical deep reinforcement learning approach
  publication-title: Sensors
– start-page: 397
  year: 2018
  end-page: 402
  ident: b40
  article-title: A deep reinforcement learning method for model-based optimal control of HVAC systems
– volume: 275
  year: 2020
  ident: b44
  article-title: Cost-effective reinforcement learning energy management for plug-in hybrid fuel cell and battery ships
  publication-title: Appl Energy
– year: 2020
  ident: b51
  article-title: FLEXLAB: Advanced integrated building & grid technologies testbed
– volume: 199
  start-page: 472
  year: 2019
  end-page: 490
  ident: b41
  article-title: Whole building energy model for HVAC optimal control: A practical framework based on deep reinforcement learning
  publication-title: Energy Build
– volume: 158
  start-page: 6158
  year: 2019
  end-page: 6163
  ident: b28
  article-title: Advanced building control via deep reinforcement learning
  publication-title: Energy Procedia
– volume: 518
  start-page: 529
  year: 2015
  end-page: 533
  ident: b20
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
– volume: 151
  start-page: 729
  year: 2018
  end-page: 739
  ident: b10
  article-title: A zone-level, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control
  publication-title: Energy
– volume: 218
  year: 2020
  ident: b45
  article-title: Model-free control method based on reinforcement learning for building cooling water systems: Validation by measured data-based simulation
  publication-title: Energy Build
– year: 2020
  ident: b4
  article-title: Market brief: Customer-sited distributed energy resources
– start-page: 1
  year: 2017
  end-page: 6
  ident: b29
  article-title: Deep reinforcement learning for building HVAC control
  publication-title: 2017 54th ACM/EDAC/IEEE design automation conference (DAC)
– volume: 8
  start-page: 39310
  year: 2020
  end-page: 39321
  ident: b48
  article-title: Demand response strategy based on reinforcement learning and fuzzy reasoning for home energy management
  publication-title: IEEE Access
– volume: 72
  start-page: 1208
  year: 2017
  end-page: 1232
  ident: b1
  article-title: A survey on behind the meter energy management systems in smart grid
  publication-title: Renew Sustain Energy Rev
– volume: 13
  year: 2012
  ident: b64
  article-title: Random search for hyper-parameter optimization
  publication-title: J Mach Learn Res
– volume: 199
  start-page: 472
  year: 2019
  end-page: 490
  ident: b62
  article-title: Whole building energy model for HVAC optimal control: A practical framework based on deep reinforcement learning
  publication-title: Energy Build
– volume: 49
  start-page: 145
  year: 2020
  end-page: 163
  ident: b26
  article-title: Reinforcement learning in sustainable energy and electric systems: a survey
  publication-title: Annu Rev Control
– volume: 550
  start-page: 354
  year: 2017
  end-page: 359
  ident: b17
  article-title: Mastering the game of go without human knowledge
  publication-title: Nature
– volume: 224
  year: 2020
  ident: b30
  article-title: Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings
  publication-title: Energy Build
– volume: 33
  start-page: 161
  year: 1991
  end-page: 174
  ident: b63
  article-title: Factorial sampling plans for preliminary computational experiments
  publication-title: Technometrics
– year: 2017
  ident: b66
  article-title: Reproducibility of benchmarked deep reinforcement learning tasks for continuous control
– volume: 107
  start-page: 279
  year: 2015
  end-page: 293
  ident: b7
  article-title: Development and experimental demonstration of a plug-and-play multiple RTU coordination control algorithm for small/medium commercial buildings
  publication-title: Energy Build
– volume: 78
  start-page: 300
  year: 2019
  end-page: 312
  ident: b25
  article-title: A review of reinforcement learning for autonomous building energy management
  publication-title: Comput Electr Eng
– volume: 5
  year: 2017
  ident: b27
  article-title: A long-short term memory recurrent neural network based reinforcement learning controller for office heating ventilation and air conditioning systems
  publication-title: Processes
– year: 2018
  ident: b34
  article-title: Deep reinforcement learning for optimal control of space heating
  publication-title: 4th building simulation and optimization conference
– volume: 144
  start-page: 159
  year: 2018
  end-page: 168
  ident: b43
  article-title: Gigawatt-hour scale savings on a budget of zero: Deep reinforcement learning based optimal control of hot water systems
  publication-title: Energy
– volume: 239
  start-page: 598
  year: 2019
  end-page: 609
  ident: b50
  article-title: Optimal energy management strategies for energy Internet via deep reinforcement learning approach
  publication-title: Appl Energy
– year: 2020
  ident: b60
  article-title: Photovoltaic and behind-the-meter battery storage: Advanced smart inverter controls and field demonstration
– volume: 55
  start-page: 7052
  year: 2019
  end-page: 7061
  ident: b6
  article-title: A demand response implementation in tertiary buildings through model predictive control
  publication-title: IEEE Trans Ind Appl
– year: 2019
  ident: b3
  article-title: Grid-interactive efficient buildings
– volume: 50
  start-page: 190
  year: 2020
  end-page: 232
  ident: b12
  article-title: All you need to know about model predictive control for buildings
  publication-title: Annu Rev Control
– start-page: 1
  year: 2016
  end-page: 6
  ident: b55
  article-title: Price based demand response strategy considering load priorities
  publication-title: 2016 IEEE 6th international conference on power systems (ICPS)
– start-page: 148
  year: 2018
  end-page: 157
  ident: b37
  article-title: Practical implementation and evaluation of deep reinforcement learning control for a radiant heating system
  publication-title: Proceedings of the 5th conference on systems for built environments
– start-page: I
  year: 2014
  end-page: 387–I–395
  ident: b22
  article-title: Deterministic policy gradient algorithms
  publication-title: Proceedings of the 31st international conference on international conference on machine learning - Volume 32
– volume: vol. 80
  start-page: 3053
  year: 2018
  end-page: 3062
  ident: b24
  article-title: RLlib: Abstractions for distributed reinforcement learning
  publication-title: Proceedings of the 35th international conference on machine learning
– year: 2020
  ident: b53
  article-title: 2012 CBECS survey data - microdata
– volume: 10
  start-page: 3698
  year: 2019
  end-page: 3708
  ident: b18
  article-title: On-line building energy optimization using deep reinforcement learning
  publication-title: IEEE Trans Smart Grid
– volume: 269
  year: 2020
  ident: b15
  article-title: Reinforcement learning for building controls: The opportunities and challenges
  publication-title: Appl Energy
– start-page: 1
  year: 2017
  end-page: 6
  ident: b8
  article-title: Minimization of building energy cost by optimally managing PV and battery energy storage systems
  publication-title: 2017 20th international conference on electrical machines and systems (ICEMS)
– year: 2020
  ident: b52
  article-title: Deep reinforcement learning for smart building energy management: A survey
– volume: 203
  year: 2019
  ident: b31
  article-title: Performance based thermal comfort control (PTCC) using deep reinforcement learning for space cooling
  publication-title: Energy Build
– volume: 50
  start-page: 2002
  year: 2020
  end-page: 2013
  ident: b42
  article-title: Transforming cooling optimization for green data center via deep reinforcement learning
  publication-title: IEEE Trans Cybern
– year: 2018
  ident: b58
  article-title: New guideline on standardized advanced sequences of operation for common HVAC systems
– volume: 235
  start-page: 1072
  year: 2019
  end-page: 1089
  ident: b13
  article-title: Reinforcement learning for demand response: A review of algorithms and modeling techniques
  publication-title: Appl Energy
– year: 2018
  ident: b39
  article-title: A deep reinforcement learning approach to using whole building energy model for HVAC optimal control
  publication-title: ASHRAE and IBPSA-USA simbuild building performance modeling conference
– volume: 207
  year: 2020
  ident: b46
  article-title: Using reinforcement learning for maximizing residential self-consumption – Results from a field test
  publication-title: Energy Build
– reference: Chen B, Cai Z, Bergés M. Gnu-rl: A precocial reinforcement learning solution for building hvac control using a differentiable mpc policy. In: Proceedings of the 6th ACM international conference on systems for energy-efficient buildings, cities, and transportation. 2019; p. 316–25.
– start-page: 48
  year: 2020
  end-page: 51
  ident: b67
  article-title: Deep reinforcement learning in buildings: Implicit assumptions and their impact
  publication-title: Proceedings of the 1st international workshop on reinforcement learning for energy management in buildings & cities
– year: 2018
  ident: b23
  article-title: Deep reinforcement learning that matters
  publication-title: Proceedings of the AAAI conference on artificial intelligence, Vol. 32
– year: 2020
  ident: b57
  article-title: Developing and evaluating metrics for demand flexibility in buildings: Comparing simulations and field data
– volume: 7
  start-page: 2751
  year: 2020
  end-page: 2762
  ident: b47
  article-title: Deep reinforcement learning for smart home energy management
  publication-title: IEEE Internet Things J
– volume: 2
  year: 2020
  ident: b33
  article-title: Reinforcement learning for whole-building HVAC control and demand response
  publication-title: Energy AI
– reference: Wei T, Wang Y, Zhu Q. Deep reinforcement learning for building HVAC control. In: Proceedings of the 54th annual design automation conference 2017. 2017; p. 1–6.
– volume: 229
  year: 2020
  ident: b49
  article-title: Application of two promising Reinforcement Learning algorithms for load shifting in a cooling supply system
  publication-title: Energy Build
– volume: 13
  year: 2020
  ident: b5
  article-title: Solar+ optimizer: A model predictive control optimization platform for grid responsive building microgrids
  publication-title: Energies
– year: 2014
  ident: b65
  article-title: Adam: A method for stochastic optimization
– year: 2018
  ident: b14
  article-title: Reinforcement learning: An introduction
– volume: 39
  start-page: 1
  year: 1989
  end-page: 16
  ident: b16
  article-title: Markov decision processes
  publication-title: European J Oper Res
– year: 2020
  ident: b54
  article-title: Electric schedule B-19
– volume: 41
  start-page: 11415
  year: 2008
  end-page: 11420
  ident: b69
  article-title: Grey box modelling - branches and experiences
  publication-title: IFAC Proc Vol
– year: 2019
  ident: b32
  article-title: Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning
– volume: 151
  start-page: 511
  year: 2017
  end-page: 519
  ident: b11
  article-title: Implementation of predictive control in a commercial building energy management system using neural networks
  publication-title: Energy Build
– volume: 50
  start-page: 2002
  issue: 5
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b42
  article-title: Transforming cooling optimization for green data center via deep reinforcement learning
  publication-title: IEEE Trans Cybern
  doi: 10.1109/TCYB.2019.2927410
– year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b4
– volume: 5
  issue: 3
  year: 2017
  ident: 10.1016/j.apenergy.2021.117733_b27
  article-title: A long-short term memory recurrent neural network based reinforcement learning controller for office heating ventilation and air conditioning systems
  publication-title: Processes
  doi: 10.3390/pr5030046
– start-page: I
  year: 2014
  ident: 10.1016/j.apenergy.2021.117733_b22
  article-title: Deterministic policy gradient algorithms
– start-page: 148
  year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b37
  article-title: Practical implementation and evaluation of deep reinforcement learning control for a radiant heating system
– year: 2014
  ident: 10.1016/j.apenergy.2021.117733_b65
– year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b3
– volume: 7
  start-page: 192
  issue: 3
  year: 2014
  ident: 10.1016/j.apenergy.2021.117733_b59
  article-title: Functional mock-up unit for co-simulation import in EnergyPlus
  publication-title: J Build Perform Simul
  doi: 10.1080/19401493.2013.808265
– year: 2015
  ident: 10.1016/j.apenergy.2021.117733_b21
– volume: 269
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b15
  article-title: Reinforcement learning for building controls: The opportunities and challenges
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2020.115036
– start-page: 45
  year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b38
  article-title: Reinforcement learning testbed for power-consumption optimization
– volume: 39
  start-page: 1
  year: 1989
  ident: 10.1016/j.apenergy.2021.117733_b16
  article-title: Markov decision processes
  publication-title: European J Oper Res
  doi: 10.1016/0377-2217(89)90348-2
– year: 2016
  ident: 10.1016/j.apenergy.2021.117733_b61
– volume: 72
  start-page: 1208
  year: 2017
  ident: 10.1016/j.apenergy.2021.117733_b1
  article-title: A survey on behind the meter energy management systems in smart grid
  publication-title: Renew Sustain Energy Rev
  doi: 10.1016/j.rser.2016.10.034
– volume: 78
  start-page: 300
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b25
  article-title: A review of reinforcement learning for autonomous building energy management
  publication-title: Comput Electr Eng
  doi: 10.1016/j.compeleceng.2019.07.019
– volume: 10
  start-page: 3698
  issue: 4
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b18
  article-title: On-line building energy optimization using deep reinforcement learning
  publication-title: IEEE Trans Smart Grid
  doi: 10.1109/TSG.2018.2834219
– volume: 55
  start-page: 7052
  issue: 6
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b6
  article-title: A demand response implementation in tertiary buildings through model predictive control
  publication-title: IEEE Trans Ind Appl
  doi: 10.1109/TIA.2019.2932963
– year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b54
– year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b52
– year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b57
– volume: 151
  start-page: 729
  year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b10
  article-title: A zone-level, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control
  publication-title: Energy
  doi: 10.1016/j.energy.2018.03.113
– volume: 550
  start-page: 354
  issue: 7676
  year: 2017
  ident: 10.1016/j.apenergy.2021.117733_b17
  article-title: Mastering the game of go without human knowledge
  publication-title: Nature
  doi: 10.1038/nature24270
– ident: 10.1016/j.apenergy.2021.117733_b19
  doi: 10.1145/3061639.3062224
– start-page: 1
  year: 2017
  ident: 10.1016/j.apenergy.2021.117733_b29
  article-title: Deep reinforcement learning for building HVAC control
– volume: 13
  issue: 12
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b5
  article-title: Solar+ optimizer: A model predictive control optimization platform for grid responsive building microgrids
  publication-title: Energies
– year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b51
– start-page: 1
  year: 2011
  ident: 10.1016/j.apenergy.2021.117733_b9
  article-title: Intelligent multi-agent control for integrated building and micro-grid systems
– volume: 2
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b33
  article-title: Reinforcement learning for whole-building HVAC control and demand response
  publication-title: Energy AI
  doi: 10.1016/j.egyai.2020.100020
– volume: 207
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b46
  article-title: Using reinforcement learning for maximizing residential self-consumption – Results from a field test
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2019.109608
– volume: 203
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b31
  article-title: Performance based thermal comfort control (PTCC) using deep reinforcement learning for space cooling
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2019.109420
– volume: 144
  start-page: 159
  year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b43
  article-title: Gigawatt-hour scale savings on a budget of zero: Deep reinforcement learning based optimal control of hot water systems
  publication-title: Energy
  doi: 10.1016/j.energy.2017.12.019
– volume: 50
  start-page: 190
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b12
  article-title: All you need to know about model predictive control for buildings
  publication-title: Annu Rev Control
  doi: 10.1016/j.arcontrol.2020.09.001
– ident: 10.1016/j.apenergy.2021.117733_b36
  doi: 10.1145/3360322.3360849
– volume: 33
  start-page: 161
  issue: 2
  year: 1991
  ident: 10.1016/j.apenergy.2021.117733_b63
  article-title: Factorial sampling plans for preliminary computational experiments
  publication-title: Technometrics
  doi: 10.1080/00401706.1991.10484804
– volume: 8
  start-page: 39310
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b48
  article-title: Demand response strategy based on reinforcement learning and fuzzy reasoning for home energy management
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2974286
– volume: 229
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b49
  article-title: Application of two promising Reinforcement Learning algorithms for load shifting in a cooling supply system
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2020.110490
– year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b68
– start-page: 1
  year: 2017
  ident: 10.1016/j.apenergy.2021.117733_b8
  article-title: Minimization of building energy cost by optimally managing PV and battery energy storage systems
– volume: 199
  start-page: 472
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b62
  article-title: Whole building energy model for HVAC optimal control: A practical framework based on deep reinforcement learning
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2019.07.029
– volume: 518
  start-page: 529
  issue: 7540
  year: 2015
  ident: 10.1016/j.apenergy.2021.117733_b20
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
  doi: 10.1038/nature14236
– volume: 13
  issue: 2
  year: 2012
  ident: 10.1016/j.apenergy.2021.117733_b64
  article-title: Random search for hyper-parameter optimization
  publication-title: J Mach Learn Res
– year: 2017
  ident: 10.1016/j.apenergy.2021.117733_b66
– year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b34
  article-title: Deep reinforcement learning for optimal control of space heating
– volume: 218
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b45
  article-title: Model-free control method based on reinforcement learning for building cooling water systems: Validation by measured data-based simulation
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2020.110055
– year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b53
– year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b58
– volume: 144
  start-page: 215
  year: 2017
  ident: 10.1016/j.apenergy.2021.117733_b56
  article-title: Optimal use of incentive and price based demand response to reduce costs and price volatility
  publication-title: Electr Power Syst Res
  doi: 10.1016/j.epsr.2016.12.012
– volume: 49
  start-page: 145
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b26
  article-title: Reinforcement learning in sustainable energy and electric systems: a survey
  publication-title: Annu Rev Control
  doi: 10.1016/j.arcontrol.2020.03.001
– start-page: 48
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b67
  article-title: Deep reinforcement learning in buildings: Implicit assumptions and their impact
– year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b32
– volume: 33
  start-page: 5749
  issue: 5
  year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b2
  article-title: Reinforcement learning approach for optimal distributed energy management in a microgrid
  publication-title: IEEE Trans Power Syst
  doi: 10.1109/TPWRS.2018.2823641
– year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b14
– volume: 151
  start-page: 511
  year: 2017
  ident: 10.1016/j.apenergy.2021.117733_b11
  article-title: Implementation of predictive control in a commercial building energy management system using neural networks
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2017.06.027
– start-page: 397
  year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b40
– year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b60
– volume: vol. 80
  start-page: 3053
  year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b24
  article-title: RLlib: Abstractions for distributed reinforcement learning
– volume: 158
  start-page: 6158
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b28
  article-title: Advanced building control via deep reinforcement learning
  publication-title: Energy Procedia
  doi: 10.1016/j.egypro.2019.01.494
– volume: 41
  start-page: 11415
  issue: 2
  year: 2008
  ident: 10.1016/j.apenergy.2021.117733_b69
  article-title: Grey box modelling - branches and experiences
  publication-title: IFAC Proc Vol
  doi: 10.3182/20080706-5-KR-1001.01934
– volume: 275
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b44
  article-title: Cost-effective reinforcement learning energy management for plug-in hybrid fuel cell and battery ships
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2020.115258
– volume: 20
  issue: 7
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b35
  article-title: Energy management of smart home with home appliances, energy storage system and electric vehicle: A hierarchical deep reinforcement learning approach
  publication-title: Sensors
  doi: 10.3390/s20072157
– volume: 107
  start-page: 279
  year: 2015
  ident: 10.1016/j.apenergy.2021.117733_b7
  article-title: Development and experimental demonstration of a plug-and-play multiple RTU coordination control algorithm for small/medium commercial buildings
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2015.08.025
– volume: 235
  start-page: 1072
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b13
  article-title: Reinforcement learning for demand response: A review of algorithms and modeling techniques
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2018.11.002
– volume: 7
  start-page: 2751
  issue: 4
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b47
  article-title: Deep reinforcement learning for smart home energy management
  publication-title: IEEE Internet Things J
  doi: 10.1109/JIOT.2019.2957289
– volume: 199
  start-page: 472
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b41
  article-title: Whole building energy model for HVAC optimal control: A practical framework based on deep reinforcement learning
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2019.07.029
– volume: 224
  year: 2020
  ident: 10.1016/j.apenergy.2021.117733_b30
  article-title: Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings
  publication-title: Energy Build
  doi: 10.1016/j.enbuild.2020.110225
– volume: 239
  start-page: 598
  year: 2019
  ident: 10.1016/j.apenergy.2021.117733_b50
  article-title: Optimal energy management strategies for energy Internet via deep reinforcement learning approach
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2019.01.145
– start-page: 1
  year: 2016
  ident: 10.1016/j.apenergy.2021.117733_b55
  article-title: Price based demand response strategy considering load priorities
– year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b23
  article-title: Deep reinforcement learning that matters
– year: 2018
  ident: 10.1016/j.apenergy.2021.117733_b39
  article-title: A deep reinforcement learning approach to using whole building energy model for HVAC optimal control
SSID ssj0002120
Score 2.6174338
Snippet Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly...
SourceID osti
proquest
crossref
elsevier
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 117733
SubjectTerms algorithms
batteries
carbon
Control systems
Deep deterministic policy gradient algorithm
Deep reinforcement learning
Distributed energy resources
Energy efficiency
industry
issues and policy
Load flexibility
POWER TRANSMISSION AND DISTRIBUTION
Smart buildings
Title Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency
URI https://dx.doi.org/10.1016/j.apenergy.2021.117733
https://www.proquest.com/docview/2636424426
https://www.osti.gov/servlets/purl/1860348
Volume 304
WOSCitedRecordID wos000701881800003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect Freedom Collection
  customDbUrl:
  eissn: 1872-9118
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002120
  issn: 0306-2619
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Rb9MwELaqjgd4QDCYKANkJN6ijNRJnfhxmooAoWlSh6h4iVzHod1KWiVtmfgJ_Gru7DgJDDQQ4sWqrNhOcl_P58t9d4S8mIk4U1JFfpQhJUcJ7Ys8Fn4ejViikY2em6ol7-LT02Q6FWe93jfHhdkt46JIrq7E-r-KGvpA2Eid_QtxN5NCB_wGoUMLYof2jwR_YoPPDc08w7S4WNEKzEptWX5l7a-vvN1CepnWa-gy6VOV8RS6OhI2vnK5kpmXY9JME0RrkzXVM2mTfQKpm10L15m19qLWib39aqtHeRP5edFEBJ-V8lJWcxtaiXOj0pkXLWQ_1P7sj_MWm59k-cXUKfAmiETZ9VywIUaBWO6mdac5Sk0bv2RoXAH38VhnNyirlZOYoVZOumo7tGWLr20B1htxcSTX9kGPcGnzbdpm3PgpvfYEFzTHSBgJ5jOcpPdYPBKgIfeO34ynb5t9ndVJPt0Ndvjmv17td6ZOfwXa-9rebwya83vkbn0SoccWQfdJTxf75E4nP-U-ORi3NEi4tN4Hqgek6oCMdkBG7e3RBmQUQEYRZPQHkFEHMgpdFEFGOyCjAAQ3Uwuyh-T9q_H5yWu_Lt_hq4gFG59HgWJciUSBCZwwaMMMjuMzpXQUc6WHMhvpJAeDXQ2DbJbwXCk-zCPOMxbFIg4PSL9YFfoRoVph-LBmYByHeMKYgRWf54ESHBMyzuSAjNybTlWd2x5LrCxTF8R4kToJpSih1EpoQF4249Y2u8uNI4QTZFrbqNb2TAF_N449RMnjOEzQrDCSDQbCEwRhlAzIcweIFFQ8freThV5tq5TxkCMflfHH_7D6Ibnd_gmfkP6m3Oqn5JbabRZV-awG-3eQotY5
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Controlling+distributed+energy+resources+via+deep+reinforcement+learning+for+load+flexibility+and+energy+efficiency&rft.jtitle=Applied+energy&rft.au=Touzani%2C+Samir&rft.au=Prakash%2C+Anand+Krishnan&rft.au=Wang%2C+Zhe&rft.au=Agarwal%2C+Shreya&rft.date=2021-12-15&rft.pub=Elsevier+Ltd&rft.issn=0306-2619&rft.eissn=1872-9118&rft.volume=304&rft_id=info:doi/10.1016%2Fj.apenergy.2021.117733&rft.externalDocID=S0306261921010801
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-2619&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-2619&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-2619&client=summon