4.8 Article

A practical deep reinforcement learning framework for multivariate occupant-centric control in buildings

Related references

Note: Only part of the references are listed.
Article Construction & Building Technology

Chilled water temperature resetting using model-free reinforcement learning: Engineering application

Shunian Qiu et al.

Summary: This study proposes a hybrid model-free chilled water temperature resetting method for chillers using reinforcement learning and expertise knowledge. The results of engineering practice show that the method achieves energy-saving performance close to expert manual control with good robustness and learning speed. A supplementary simulation study indicates that the method converges within one cooling season and outperforms other control methods in certain scenarios.

ENERGY AND BUILDINGS (2022)

Article Energy & Fuels

Reinforced model predictive control (RL-MPC) for building energy management

Javier Arroyo et al.

Summary: This paper compares model predictive control (MPC) and reinforcement learning (RL) in building energy management and proposes a novel algorithm RL-MPC that combines the advantages of both approaches. The algorithm can meet constraints, provide similar performance to MPC, and enable continuous learning.

APPLIED ENERGY (2022)

Article Energy & Fuels

Dynamics analysis of a novel hybrid deep clustering for unsupervised learning by reinforcement of multi-agent to energy saving in intelligent buildings

Raad Z. Homod et al.

Summary: This study explores the use of reinforcement learning to optimize the energy efficiency and thermal comfort of HVAC systems. The authors propose a hybrid deep clustering multi-agent reinforcement learning approach that can better handle the challenges of large-scale nonlinearity and action space expansion, achieving significant performance improvements in energy savings and thermal comfort compared to PID control.

APPLIED ENERGY (2022)

Article Construction & Building Technology

The effects of a mismatch between thermal comfort modeling and HVAC controls from an occupancy perspective

Eikichi Ono et al.

Summary: Incorporating data-driven thermal comfort models into occupant-centric HVAC controls is crucial for meeting occupants' preferences in thermal comfort. A mismatch between the occupancy resolutions of thermal comfort modeling and HVAC controls can lead to decreased voting for no change in thermal and air movement preferences, but also increased energy savings when considering a suitable comfort model for the HVAC control.

BUILDING AND ENVIRONMENT (2022)

Article Energy & Fuels

Impact of occupant related data on identification and model predictive control for buildings

Sicheng Zhan et al.

Summary: This paper bridges the knowledge gaps in the interactions between data requirements, model quality, and control performance by integrating real-world measurements and simulation-based experiments. The results indicate that the usefulness of data is jointly affected by measurement suitability, model complexity, and modeling purpose. The study also reveals the heterogeneous requirements on models from traditional prediction tests and control tasks.

APPLIED ENERGY (2022)

Article Energy & Fuels

Impact of occupant related data on identification and model predictive control for buildings

Sicheng Zhan et al.

Summary: This paper explores the importance of data usage in building control and conducts experiments in various spatial environments. The results indicate that the effectiveness of data is jointly affected by measurement suitability, model complexity, and modeling purpose in achieving satisfactory prediction and control performance.

APPLIED ENERGY (2022)

Review Construction & Building Technology

Calibrating building energy simulation models: A review of the basics to guide future work

Adrian Chong et al.

Summary: This study provides a foundation for future research by conducting a detailed systematic review of vital aspects of BES calibration through meta-analysis and categorization. Reproducible simulations are identified as a critical issue, and an incremental approach is proposed to encourage future research's reproducibility.

ENERGY AND BUILDINGS (2021)

Article Engineering, Electrical & Electronic

Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings

Liang Yu et al.

Summary: This paper investigates the minimization of energy consumption of HVAC systems in commercial buildings, taking into account random zone occupancy, thermal comfort, and indoor air quality comfort. Research shows that the HVAC control algorithm based on multi-agent deep reinforcement learning has effectiveness, robustness, and scalability demonstrated through real-world trace simulations.

IEEE TRANSACTIONS ON SMART GRID (2021)

Article Computer Science, Artificial Intelligence

Challenges of real-world reinforcement learning: definitions, benchmarks and analysis

Gabriel Dulac-Arnold et al.

Summary: Reinforcement learning has shown success in artificial domains but faces challenges in practical applications. By identifying and analyzing a series of challenges, as well as presenting existing attempts to tackle them, a path towards addressing these difficulties and making RL more deployable in real-world problems can be paved.

MACHINE LEARNING (2021)

Article Green & Sustainable Science & Technology

Data requirements and performance evaluation of model predictive control in buildings: A modeling perspective

Sicheng Zhan et al.

Summary: This study explores the potential of MPC in improving building performance and saving energy, identifies the main factors hindering its application, and suggests future research directions to address these challenges. By categorizing past studies and comparing data requirements, the study provides insights for future research on the relationship between data requirements, model performance, and control performance.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Review Computer Science, Information Systems

A Review of Deep Reinforcement Learning for Smart Building Energy Management

Liang Yu et al.

Summary: Global buildings contribute to a significant portion of energy consumption and carbon emission, calling for the development of smart building energy management technologies. However, challenges such as accurate thermal dynamics models, uncertain system parameters, and spatial-temporal operational constraints must be addressed. Deep reinforcement learning shows promise in overcoming these challenges, but a systematic overview of its application in SBEM is currently lacking.

IEEE INTERNET OF THINGS JOURNAL (2021)

Article Energy & Fuels

Sensor impacts on building and HVAC controls: A critical review for building energy performance

Yeonjin Bae et al.

Summary: This paper provides a comprehensive literature review on sensor systems in building/HVAC systems, focusing on their impacts on energy efficiency and thermal comfort in the context of controls. The study aims to understand past and current research while identifying future research opportunities. Through interviews and literature review, the researchers summarized key aspects of sensors and collected insights from industry experts and practitioners.

ADVANCES IN APPLIED ENERGY (2021)

Editorial Material Public, Environmental & Occupational Health

The COVID-19 epidemic

Thirumalaisamy P. Velavan et al.

TROPICAL MEDICINE & INTERNATIONAL HEALTH (2020)

Review Construction & Building Technology

Review on occupant-centric thermal comfort sensing, predicting, and controlling

Jiaqing Xie et al.

ENERGY AND BUILDINGS (2020)

Review Automation & Control Systems

Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications

Thanh Thi Nguyen et al.

IEEE TRANSACTIONS ON CYBERNETICS (2020)

Article Engineering, Electrical & Electronic

On-Line Building Energy Optimization Using Deep Reinforcement Learning

Elena Mocanu et al.

IEEE TRANSACTIONS ON SMART GRID (2019)

Article Construction & Building Technology

Temperature-preference learning with neural networks for occupant-centric building indoor climate controls

Yuzhen Peng et al.

BUILDING AND ENVIRONMENT (2019)

Article Construction & Building Technology

Analysis of the accuracy on PMV - PPD model using the ASHRAE Global Thermal Comfort Database II

Toby Cheung et al.

BUILDING AND ENVIRONMENT (2019)

Review Behavioral Sciences

Reinforcement Learning, Fast and Slow

Matthew Botvinick et al.

TRENDS IN COGNITIVE SCIENCES (2019)

Article Construction & Building Technology

Comparative assessment of HVAC control strategies using personal thermal comfort and sensitivity models

Wooyoung Jung et al.

BUILDING AND ENVIRONMENT (2019)

Article Construction & Building Technology

Continuous-time Bayesian calibration of energy models using BIM and energy data

Adrian Chong et al.

ENERGY AND BUILDINGS (2019)

Article Construction & Building Technology

Thermal comfort and energy performance of a dedicated outdoor air system with ceiling fans in hot and humid climate

Kuniaki Mihara et al.

ENERGY AND BUILDINGS (2019)

Article Construction & Building Technology

Whole building energy model for HVAC optimal control: A practical framework based on deep reinforcement learning

Zhiang Zhang et al.

ENERGY AND BUILDINGS (2019)

Review Construction & Building Technology

A critical review of field implementations of occupant-centric building controls

June Young Park et al.

BUILDING AND ENVIRONMENT (2019)

Article Construction & Building Technology

LightLearn: An adaptive and occupant centered controller for lighting based on reinforcement learning

June Young Park et al.

BUILDING AND ENVIRONMENT (2019)

Proceedings Paper Computer Science, Theory & Methods

A Human-centered Wearable Sensing Platform with Intelligent Automated Data Annotation Capabilities

Roger Solis et al.

PROCEEDINGS OF THE 2019 INTERNATIONAL CONFERENCE ON INTERNET OF THINGS DESIGN AND IMPLEMENTATION (IOTDI '19) (2019)

Article Construction & Building Technology

Personal comfort models - A new paradigm in thermal comfort for occupant-centric environmental control

Joyce Kim et al.

BUILDING AND ENVIRONMENT (2018)

Review Construction & Building Technology

Individual difference in thermal comfort: A literature review

Zhe Wang et al.

BUILDING AND ENVIRONMENT (2018)

Article Construction & Building Technology

Optimal control of HVAC and window systems for natural ventilation through reinforcement learning

Yujiao Chen et al.

ENERGY AND BUILDINGS (2018)

Article Automation & Control Systems

Adaptive Critic-Based Event-Triggered Control for HVAC System

Narendra Kumar Dhar et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2018)

Review Green & Sustainable Science & Technology

Comprehensive analysis of the relationship between thermal comfort and building control research - A data-driven literature review

June Young Park et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Review Green & Sustainable Science & Technology

Modeling techniques used in building HVAC control systems: A review

Zakia Afroz et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Article Construction & Building Technology

An integrated control-oriented modelling for HVAC performance benchmarking

Harish Satyavada et al.

JOURNAL OF BUILDING ENGINEERING (2016)

Article Energy & Fuels

Reinforcement learning for optimal control of low exergy buildings

Lei Yang et al.

APPLIED ENERGY (2015)

Article Automation & Control Systems

Event-Based Optimization Within the Lagrangian Relaxation Framework for Energy Savings in HVAC Systems

Biao Sun et al.

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING (2015)

Article Construction & Building Technology

Modelica Buildings library

Michael Wetter et al.

JOURNAL OF BUILDING PERFORMANCE SIMULATION (2014)

Article Construction & Building Technology

RLF and TS fuzzy model identification of indoor thermal comfort based on PMV/PPD

Raad Z. Hornod et al.

BUILDING AND ENVIRONMENT (2012)

Article Construction & Building Technology

Overall thermal sensation, acceptability and comfort

Yufeng Zhang et al.

BUILDING AND ENVIRONMENT (2008)

Review Thermodynamics

Supervisory and optimal control of building HVAC systems: A review

Shengwei Wang et al.

HVAC&R RESEARCH (2008)

Article Pediatrics

Recall bias, MMR, and autism

N Andrews et al.

ARCHIVES OF DISEASE IN CHILDHOOD (2002)

Article Computer Science, Artificial Intelligence

A sparse sampling algorithm for near-optimal planning in large Markov decision processes

M Kearns et al.

MACHINE LEARNING (2002)

Article Construction & Building Technology

The validity of ISO-PMV for predicting comfort votes in every-day thermal environments

MA Humphreys et al.

ENERGY AND BUILDINGS (2002)