894 Hits in 4.5 sec

Personalized Thermal Comfort Model with Decision Tree

Yuze Jiang
2019 Intelligent Control and Automation  
Then, a comfort-based HVAC controller was developed with the thermal sensation prediction results with the trained model above.  ...  As a result, the proposed controller indeed improves occupant's thermal comfort model.  ...  Moreover, many researchers in HVAC control has investigated much on reinforcement learning control (RL) recently.  ... 
doi:10.4236/ica.2019.104012 fatcat:jwpk4dyvcram5aj7hhbjwew3gy

Designing a generalised reward for Building Energy Management Reinforcement Learning agents

Rubén Mulero Martinez, Beñat Arregi Goikolea, Iñigo Mendialdua Beitia, Roberto Garay Martinez
2021 Zenodo  
In this regard, Reinforcement Learning (RL) approaches are giving a good balance between data requirements and intelligent operations to control building systems.  ...  intelligent agents for building energy management.  ...  [27] relied on that same neural network to estimate the Q-values of their deep reinforcement learning algorithm model to manage and control the heating system and the domestic hot water.  ... 
doi:10.5281/zenodo.5583237 fatcat:rfuv5cedanfqpfcgi3xxnldt34

A Review of Reinforcement Learning Applications to Control of Heating, Ventilation and Air Conditioning Systems

Seppo Sierla, Heikki Ihasalo, Valeriy Vyatkin
2022 Energies  
Reinforcement learning has emerged as a potentially disruptive technology for control and optimization of HVAC systems.  ...  A reinforcement learning agent takes actions, which can be direct HVAC actuator commands or setpoints for control loops in building automation systems.  ...  Introduction Reinforcement learning (RL) is emerging as an advanced technique for HVAC control, due to its ability to process complex sensor information to achieve complex control objectives.  ... 
doi:10.3390/en15103526 fatcat:mp2vv45qu5byjff32ckwh2tevu

Artificial Intelligence for Efficient Thermal Comfort Systems: Requirements, Current Applications and Future Directions

Ali Ghahramani, Parson Galicia, David Lehrer, Zubin Varghese, Zhe Wang, Yogesh Pandit
2020 Frontiers in Built Environment  
Aside from the use of ANN and genetic algorithms, some BMSs implement a reinforcement learning technique to increase the adaptability of the HVAC controller with different environments (as discussed in  ...  Reinforcement learning can help model the thermal environment in which tools regulating thermal comfort, whether spanning the building (i.e., HVAC systems) or an individual occupant (i.e., personal comfort  ...  The funder provided logistics support and high-level directions for this review. Copyright © 2020 Ghahramani, Galicia, Lehrer, Varghese, Wang and Pandit.  ... 
doi:10.3389/fbuil.2020.00049 fatcat:gbjaeirtz5gn5adse4mikkjy7e

Multi-agent Reinforcement Learning Embedded Game for the Optimization of Building Energy Control and Power System Planning [article]

Jun Hao
2019 arXiv   pre-print
In my study, we address a novel methodology to control the operation of heating, ventilation, and air conditioning system (HVAC).  ...  Compared with the existing distribution power system planning mechanisms and the related game theoretical methodologies, our proposed algorithm can plan and optimize the hourly energy usage, and have the  ...  Hence, multi-agent reinforce learning comes into our searching scope and fits for our optimizing and controlling needs.  ... 
arXiv:1901.07333v1 fatcat:7inwy3w43rg4jcil2rlpxxrbmy

Intelligent Building Control Systems for Thermal Comfort and Energy-Efficiency: A Systematic Review of Artificial Intelligence-Assisted Techniques [article]

Ghezlane Halhoul Merabet, Mohamed Essaaidi, Mohamed Ben Haddou, Basheer Qolomany, Junaid Qadir, Muhammad Anan, Ala Al-Fuqaha, Mohamed Riduan Abid, Driss Benhaddou
2021 arXiv   pre-print
Over the last decade, different methodologies based on the Artificial Intelligence (AI) techniques have been deployed to find the sweet spot between energy use in HVAC systems and suitable indoor comfort  ...  Among the 20 AI tools developed for both energy consumption and comfort control, functions such as identification and recognition patterns, optimization, predictive control.  ...  [134] 2017 A deep reinforcement learning based data-driven approach development for building HVAC control.  ... 
arXiv:2104.02214v1 fatcat:gl4b47zbw5g3djvq2fccvaox2e

Smart buildings as Cyber-Physical Systems: Data-driven predictive control strategies for energy efficiency

Mischa Schmidt, Christer Åhlund
2018 Renewable & Sustainable Energy Reviews  
Due to its significant contribution to global energy usage and the associated greenhouse gas emissions, existing building stock's energy efficiency must improve.  ...  Predictive building control promises to contribute to that by increasing the efficiency of building operations.  ...  Reinforcement Learning Using Reinforcement Learning (RL) to optimize the economic aspects of operating electric water heaters, [94] demonstrates in simulations 24% savings for using day-head prices and  ... 
doi:10.1016/j.rser.2018.04.013 fatcat:ighz33gmeze3nbrpjewpk3wmhi

Reinforcement Learning-Based BEMS Architecture for Energy Usage Optimization

Sanguk Park, Sangmin Park, Myeong-in Choi, Sanghoon Lee, Tacklim Lee, Seunghwan Kim, Keonhee Cho, Sehyun Park
2020 Sensors  
on reinforcement learning (RL).  ...  Through this process, a purpose-oriented energy saving methodology to achieve energy saving goals is proposed.  ...  Almost all the reinforcement learning problems can be modeled as a MDP [44] .  ... 
doi:10.3390/s20174918 pmid:32878089 pmcid:PMC7506749 fatcat:vyc7rj57xvewvklisr5ciz2sty

An Autonomic Cycle of Data Analysis Tasks for the Supervision of HVAC Systems of Smart Building

Jose Aguilar, Douglas Ardila, Andrés Avendaño, Felipe Macias, Camila White, José Gomez-Pulido, José Gutierrez de Mesa, Alberto Garces-Jimenez
2020 Energies  
Data models for fault detection and diagnosis are increasingly used for extracting knowledge in the supervisory tasks.  ...  The proposed supervisory functionality of the HVAC system is capable of detecting deviations, such as faults or gradual increment of energy consumption in similar working conditions.  ...  Another important approach is the MORL (multi-objective reinforced learning), whereas the objective is to learn multiple policies simultaneously for every objective [28, 29] .  ... 
doi:10.3390/en13123103 fatcat:33qlg2ppkrarpe75ifgrkridem

Real-Time Autonomous Residential Demand Response Management Based on Twin Delayed Deep Deterministic Policy Gradient Learning

Yujian Ye, Dawei Qiu, Huiyu Wang, Yi Tang, Goran Strbac
2021 Energies  
through comprehensive comparisons with the state-of-the-art deep reinforcement learning (DRL) methods.  ...  The proposed method is applied to the energy management problem for a household with a portfolio of the most prominent types of DERs.  ...  A model-free and data-driven deep-reinforcement-learning-based demand response management strategy whose performance does not rely on accurate mathematical modeling of the distributed energy resources'  ... 
doi:10.3390/en14030531 fatcat:qeis2kw5v5fghcm6bohhofrbsm

Benchmarking Approaches for Assessing the Performance of Building Control Strategies: A Review

Clara Ceccolini, Roozbeh Sangi
2022 Energies  
In the last few decades, researchers have shown that advanced building controllers can reduce energy consumption without negatively impacting occupants' wellbeing and help to manage building systems, which  ...  This study presents an overview of the different benchmarking approaches used to assess control performance.  ...  Control Multiple review papers have qualitatively evaluated the testing methodologies used to assess specific advanced controls (i.e., model predictive control (MPC) [13, 20, 24] , reinforcement learning  ... 
doi:10.3390/en15041270 fatcat:minx76us5fctfoo5mkgwvqf5ai

Deep Highway Networks and Tree-Based Ensemble for Predicting Short-Term Building Energy Consumption

Muhammad Ahmad, Anthony Mouraud, Yacine Rezgui, Monjur Mourshed
2018 Energies  
The paper concludes that all developed models are equally applicable for predicting hourly HVAC energy consumption.  ...  HVAC) energy consumption of a hotel building.  ...  The funding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.  ... 
doi:10.3390/en11123408 fatcat:w7ppb325cnagblatp6ygkmy2he

Experimental analysis of simulated reinforcement learning control for active and passive building thermal storage inventory

Simeng Liu, Gregor P. Henze
2006 Energy and Buildings  
The proposed building control approach is based on simulated reinforcement learning, which is a hybrid control scheme that combines features of model-based optimal control and model-free learning control  ...  learning controller.  ...  In general, the results of these simulation studies confirm that reinforcement learning control is a feasible methodology to derive the optimal control policy for this specific problem.  ... 
doi:10.1016/j.enbuild.2005.06.002 fatcat:3tov6ao2aff35jdbjur2276c6q

Neural networks based predictive control for thermal comfort and energy savings in public buildings

P.M. Ferreira, A.E. Ruano, S. Silva, E.Z.E. Conceição
2012 Energy and Buildings  
A discrete model-based predictive control methodology is applied, consisting of three major components: the predictive models, implemented by radial basis function neural networks identified by means of  ...  The paper addresses the problem of controlling a Heating Ventilation and Air Conditioning (HVAC) system with the purpose of achieving a desired thermal comfort level and energy savings.  ...  and the University of Algarve for the Ceratonia 2008 Award.  ... 
doi:10.1016/j.enbuild.2012.08.002 fatcat:kkokjy75rvhpnieyhsfqc5ddwy

Evaluating energy performance in non-domestic buildings: A review

E.H. Borgstein, R. Lamberts, J.L.M. Hensen
2016 Energy and Buildings  
Methodologies are grouped in five categories: engineering calculations, simulation, statistical methods, machine learning and other methods.  ...  This paper provides a comprehensive review of the available methods for analysing, classifying, benchmarking, rating and evaluating energy performance in non-domestic buildings.  ...  As with statistical models, it would seem that one of the main drawbacks of machine learning methods is that their "black-box" approach makes it difficult to show real, physical interpretations for the  ... 
doi:10.1016/j.enbuild.2016.07.018 fatcat:icstrrdpivcclaoqw23xjnbg6m
« Previous Showing results 1 — 15 out of 894 results