Ten questions concerning reinforcement learning for building energy management

被引:40
|
作者
Nagy, Zoltan [1 ]
Henze, Gregor [2 ,4 ]
Dey, Sourav [2 ]
Arroyo, Javier [3 ]
Helsen, Lieve [3 ]
Zhang, Xiangyu [4 ]
Chen, Bingqing [5 ]
Amasyali, Kadir [6 ]
Kurte, Kuldeep [6 ]
Zamzam, Ahmed [4 ]
Zandi, Helia [6 ]
Drgona, Jan [7 ]
Quintana, Matias [8 ,14 ]
McCullogh, Steven [9 ]
Park, June Young [9 ]
Li, Han [10 ]
Hong, Tianzhen [10 ]
Brandi, Silvio [11 ]
Pinto, Giuseppe [11 ,12 ]
Capozzoli, Alfonso [11 ]
Vrabie, Draguna [7 ]
Berges, Mario [13 ]
Nweye, Kingsley [1 ]
Marzullo, Thibault [4 ]
Bernstein, Andrey [4 ]
机构
[1] Univ Texas Austin, Dept Civil Architectural & Environm Engn, Austin, TX 78712 USA
[2] Univ Colorado, Dept Civil Environm & Architectural Engn, Boulder, CO USA
[3] Univ Leuven, KU Leuven, Dept Mech Engn, EnergyVille, Leuven, Belgium
[4] Natl Renewable Energy Lab, Golden, CO USA
[5] Bosch Res North Amer, Bosch Ctr Artificial Intelligence, Pittsburgh, PA USA
[6] Oak Ridge Natl Lab, Knoxville, TN USA
[7] Pacific Northwest Natl Lab, Richland, WA USA
[8] Natl Univ Singapore, Dept Built Environm, Singapore, Singapore
[9] Univ Texas Arlington, Dept Civil Engn, Arlington, TX USA
[10] Lawrence Berkeley Natl Lab, Bldg Technol & Urban Syst Div, Berkeley, CA USA
[11] Politecn Torino, BAEDA Lab, TEBE Res Grp, Dept Energy, Turin, Italy
[12] PassiveLogic, Salt Lake City, UT USA
[13] Carnegie Mellon Univ, Dept Civil & Environm Engn, Pittsburgh, PA USA
[14] Singapore ETH Ctr, Future Cities Lab Global, Singapore, Singapore
基金
新加坡国家研究基金会;
关键词
Open AI Gym; DEMAND RESPONSE; THERMAL COMFORT; SIMULATION; MODEL; SATISFACTION; BEHAVIOR; GO;
D O I
10.1016/j.buildenv.2023.110435
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
As buildings account for approximately 40% of global energy consumption and associated greenhouse gas emissions, their role in decarbonizing the power grid is crucial. The increased integration of variable energy sources, such as renewables, introduces uncertainties and unprecedented flexibilities, necessitating buildings to adapt their energy demand to enhance grid resiliency. Consequently, buildings must transition from passive energy consumers to active grid assets, providing demand flexibility and energy elasticity while maintaining occupant comfort and health. This fundamental shift demands advanced optimal control methods to manage escalating energy demand and avert power outages. Reinforcement learning (RL) emerges as a promising method to address these challenges. In this paper, we explore ten questions related to the application of RL in buildings, specifically targeting flexible energy management. We consider the growing availability of data, advancements in machine learning algorithms, open-source tools, and the practical deployment aspects associated with software and hardware requirements. Our objective is to deliver a comprehensive introduction to RL, present an overview of existing research and accomplishments, underscore the challenges and opportunities, and propose potential future research directions to expedite the adoption of RL for building energy management.
引用
收藏
页数:18
相关论文
共 50 条
  • [31] Ten questions concerning future buildings beyond zero energy and carbon neutrality
    Wang, Na
    Phelan, Patrick E.
    Gonzalez, Jorge
    Harris, Chioke
    Henze, Gregor P.
    Hutchinson, Robert
    Langevin, Jared
    Lazarus, Mary Ann
    Nelson, Brent
    Pyke, Chris
    Roth, Kurt
    Rouse, David
    Sawyer, Karma
    Selkowitz, Stephen
    BUILDING AND ENVIRONMENT, 2017, 119 : 169 - 182
  • [32] Ten Questions Concerning Generative Computer Art
    McCormack, Jon
    Bown, Oliver
    Dorin, Alan
    McCabe, Jonathan
    Monro, Gordon
    Whitelaw, Mitchell
    LEONARDO, 2014, 47 (02) : 135 - 141
  • [33] Ten questions concerning indoor ultrafine particles
    Nazaroff, William W.
    BUILDING AND ENVIRONMENT, 2023, 243
  • [34] Ten questions concerning computational urban acoustics
    Hornikx, Maarten
    BUILDING AND ENVIRONMENT, 2016, 106 : 409 - 421
  • [35] Ten questions concerning thermal comfort and ageing
    van Hoof, J.
    Schellen, L.
    Soebarto, V.
    Wong, J. K. W.
    Kazak, J. K.
    BUILDING AND ENVIRONMENT, 2017, 120 : 123 - 133
  • [36] Reinforcement learning for microgrid energy management
    Kuznetsova, Elizaveta
    Li, Yan-Fu
    Ruiz, Carlos
    Zio, Enrico
    Ault, Graham
    Bell, Keith
    ENERGY, 2013, 59 : 133 - 146
  • [37] Building Load Management Clusters Using Reinforcement Learning
    Ahmed, Shamwilu
    Bouffard, Francois
    2017 8TH IEEE ANNUAL INFORMATION TECHNOLOGY, ELECTRONICS AND MOBILE COMMUNICATION CONFERENCE (IEMCON), 2017, : 372 - 377
  • [38] Reinforcement Learning in Smart Building Management: A Paradigm Shift towards Intelligent Energy Efficiency and Optimization
    Almalaq, Abdulaziz
    4TH INTERDISCIPLINARY CONFERENCE ON ELECTRICS AND COMPUTER, INTCEC 2024, 2024,
  • [39] Systematic Review on Deep Reinforcement Learning-Based Energy Management for Different Building Types
    Shaqour, Ayas
    Hagishima, Aya
    ENERGIES, 2022, 15 (22)
  • [40] Deep Reinforcement Learning-Based Optimal Building Energy Management Strategies with Photovoltaic Systems
    Sim, Minjeong
    Hong, Geonkyo
    Suh, Dongjun
    PROCEEDINGS OF BUILDING SIMULATION 2021: 17TH CONFERENCE OF IBPSA, 2022, 17 : 2125 - 2132