191 Hits in 10.1 sec

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
Among the 20 AI tools developed for both energy consumption and comfort control, functions such as identification and recognition patterns, optimization, predictive control.  ...  This paper performs a comprehensive and an in-depth systematic review of AI-based techniques used for building control systems by assessing the outputs of these techniques, and their implementations in  ...  [38] , where a dynamic neural network based on the idea of Nonlinear Autoregressive Exogenous (NARX) is used to model and control an HVAC system.  ... 
arXiv:2104.02214v1 fatcat:gl4b47zbw5g3djvq2fccvaox2e

Data-driven Model Predictive and Reinforcement Learning Based Control for Building Energy Management: a Survey [article]

Huiliang Zhang, Sayani Seal, Di Wu, Benoit Boulet, Francois Bouffard, Geza Joos
2021 arXiv   pre-print
This paper presents a compact review of the recent advances in data-driven MPC and reinforcement learning based control methods for BEMS.  ...  Classical model predictive control (MPC) has shown its capacity to reduce building energy consumption, but it suffers from labor-intensive modelling and complex on-line control optimization.  ...  Data-driven Predictive Model for MPC An artificial neural network (ANN)-based MPC driven HVAC control system is presented [15] .  ... 
arXiv:2106.14450v1 fatcat:bmgvjtqig5c4vhntu5eqroarn4

Transfer Learning for Thermal Comfort Prediction in Multiple Cities [article]

Nan Gao, Wei Shao, Mohammad Saiedur Rahaman, Jun Zhai, Klaus David, Flora D. Salim
2020 arXiv   pre-print
We present a transfer learning based multilayer perceptron model from the same climate zone (TL-MLP-C*) for accurate thermal comfort prediction.  ...  HVAC (Heating, Ventilation and Air Conditioning) system is an important part of a building, which constitutes up to 40% of building energy usage.  ...  The first two datasets have different building types (HVAC, naturally ventilated and mixed ventilated) while there is only one HVAC building in Medium US Office dataset.  ... 
arXiv:2004.14382v3 fatcat:3k3u4u6lpfe2lktdstjar6jaei

Gnu-RL: A Practical and Scalable Reinforcement Learning Solution for Building HVAC Control Using a Differentiable MPC Policy

Bingqing Chen, Zicheng Cai, Mario Bergés
2020 Frontiers in Built Environment  
Ventilation and Air Conditioning (HVAC) controllers.  ...  Specifically, Gnu-RL adopts a recently-developed Differentiable Model Predictive Control (MPC) policy, which encodes domain knowledge on planning and system dynamics, making it both sample-efficient and  ...  In comparison, Chen et al. (2018) used a special input-convex neural network ) to model the system dynamics.  ... 
doi:10.3389/fbuil.2020.562239 fatcat:mavxixol25hbxpp32uzxfkoi5u

A Review of Reinforcement Learning for Autonomous Building Energy Management [article]

Karl Mason, Santiago Grijalva
2019 arXiv   pre-print
Reinforcement learning is one of the most prominent machine learning algorithms used for control problems and has had many successful applications in the area of building energy management.  ...  This area is concerned with combining advancements in sensor technologies, communications and advanced control algorithms to optimize energy utilization.  ...  neural network) for HVAC control [73] .  ... 
arXiv:1903.05196v2 fatcat:lihv4ftuovc3hhmofr7vpgn3mq

A Computer Vision-Based Occupancy and Equipment Usage Detection Approach for Reducing Building Energy Demand

Paige Wenbin Tien, Shuangyu Wei, John Calautit
2020 Energies  
A model based on region-based convolutional neural network (R-CNN) was developed, trained and deployed to a camera for real-time detection of occupancy activities and equipment usage.  ...  This study proposes a vision-based occupancy and equipment usage detection method based on deep learning for demand-driven control systems.  ...  The use of such a transfer learning method to establish the deep learning model allows the development of accurate detection models with a reduced network training time and requiring fewer amounts of input  ... 
doi:10.3390/en14010156 fatcat:ytr6nldns5cytjpqtejy5r2fku

Transfer Learning Applied to Reinforcement Learning-Based HVAC Control

Paulo Lissa, Michael Schukat, Enda Barrett
2020 SN Computer Science  
the use of transfer learning applied to reinforcement learning based HVAC control.  ...  Moreover, an analysis of the user's time out comfort has been made, comparing models with and without transfer learning.  ...  Reference [14] used a model-free RL method applying recurrent neural networks for control and management of a central HVAC of a building.  ... 
doi:10.1007/s42979-020-00146-7 fatcat:4yan4nulxfafrbq5uhp2g25hky

Deep-Learning-Based, Multi-Timescale Load Forecasting in Buildings: Opportunities and Challenges from Research to Deployment [article]

Sakshi Mishra, Stephen M. Frank, Anya Petersen, Robert Buechler, Michelle Slovensky
2021 arXiv   pre-print
In this work, we present a deep-learning-based load forecasting system that predicts the building load at 1-hour intervals for 18 hours in the future.  ...  Efficient operation and dispatch of DERs require reasonably accurate predictions of future energy consumption in order to conduct near-real-time optimized dispatch of on-site generation and storage assets  ...  Proportional-integral-derivative (PID) controllers are still widely used in building controls for heating, ventilating, and airconditioning (HVAC) systems, largely because of their simplicity and fast  ... 
arXiv:2008.05458v2 fatcat:756a63wr55a5zdna2wqu6yyujm

A Critical Review on the Control Strategies Applied to PCM-Enhanced Buildings

Gohar Gholamibozanjani, Mohammed Farid
2021 Energies  
, adaptive, and predictive control) and intelligent controls.  ...  The paper further discusses the opportunities and challenges associated with the design of PCM-enhanced buildings in combination with control strategies.  ...  A variety of AI techniques such as fuzzy logic, genetic algorithm, analytic hierarchy process, simulated annealing, and neural network, as well as AI subsets such as machine learning and deep learning,  ... 
doi:10.3390/en14071929 fatcat:tkxxunxmczbufbm5o45qqyvv5q

Intelligent Controllers and Optimization Algorithms for Building Energy Management Towards Achieving Sustainable Development: Challenges and Prospects

K. Parvin, M.S. Hossain Lipu, M. A. Hannan, Majid A. Abdullah, Ker Pin Jern, R. A. Begum, M. Mansur, K. M. Muttaqi, T. M. Indra Mahlia, Z. Y. Dong
2021 IEEE Access  
The contributions of controller and optimization in building energy management with the relation of sustainable development goals (SDGs) are explained rigorously.  ...  Buildings account for a significant amount of energy consumption leading to the issues of global emissions and climate change.  ...  ] , neural networks [89] , fuzzy with conventional controls [90] , and adaptive fuzzy neural network (ANFIS) systems [91] , [92] , etc.; (ii) the model-based predictive control (MPC) technique [93  ... 
doi:10.1109/access.2021.3065087 fatcat:3bzootbznvby7esnk3vlldovce

2019 Index IEEE Transactions on Industrial Informatics Vol. 15

2019 IEEE Transactions on Industrial Informatics  
Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks.  ...  Feature selection A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks.  ... 
doi:10.1109/tii.2020.2968165 fatcat:utk3ywxc6zgbdbfsys5f4otv7u

A Relearning Approach to Reinforcement Learning for control of Smart Buildings

Avisek Naug, Marcos Q'uiñones -Grueiro, Gautam Biswas
2020 Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM  
This paper demonstrates that continual relearning of control policies using incremental deep reinforcement learning (RL) can improve policy learning for non-stationary processes.  ...  This approach has been demonstrated in a data-driven "smart building environment" that we use as a test-bed for developing HVAC controllers for reducing energy consumption of large buildings on our university  ...  We use Long Short-Term Memory (LSTM) Neural Network to model the dynamics of the system and the the Proximal Policy Optimization (PPO) algorithm to train the control policy.  ... 
doi:10.36001/phmconf.2020.v12i1.1296 fatcat:jownxtnslra2bjmv3k6gj7kb4q

Review on fault detection and diagnosis feature engineering in building heating, ventilation, air conditioning and refrigeration systems

Guannan Li, Yunpeng Hu, Jiangyan Liu, Xi Fang, Jing Kang
2020 IEEE Access  
With the increasing utilization of these systems, their fault detection and diagnosis has become more significant for maintaining their operation and performance.  ...  between fault-related features and real-time fault impacts with energy consumption, occupants' thermal comfort, etc.  ...  There are many types of NN structures, including deep belief networks (DBNs), deep neural networks (DNNs), convolutional neural networks (CNNs) and auto-encoders (AEs). Guo et al.  ... 
doi:10.1109/access.2020.3040980 fatcat:apiekeylirccth3syg2gd65jby

Application of Computational Intelligence to Energy Systems

Matteo De Felice
2011 Zenodo  
Wang and Chen [223] developed a fault-tolerant control for buildings' ventilation based on neural network models.  ...  The modelling work suggested a building dimensional ratio for an optimal choice of natural ventilation.  ...  Appendix A Computational Intelligence in Software Packages This appendix gives a list of some of the most common software implementations of neural networks and computational intelligence algorithms.  ... 
doi:10.5281/zenodo.4068383 fatcat:ee6uyhkcdzh3hlvty33twlqnva

A Relearning Approach to Reinforcement Learning for Control of Smart Buildings [article]

Avisek Naug and Marcos Quiñones-Grueiro and Gautam Biswas
2020 arXiv   pre-print
This paper demonstrates that continual relearning of control policies using incremental deep reinforcement learning (RL) can improve policy learning for non-stationary processes.  ...  We demonstrate this approach for a data-driven 'smart building environment' that we use as a test-bed for developing HVAC controllers for reducing energy consumption of large buildings on our university  ...  Long Short-Term Memory Networks for Modeling Dynamic Systems Despite their known success in machine learning tasks, such as image classification, deep learning approaches for energy consumption prediction  ... 
arXiv:2008.01879v1 fatcat:epddy7mzqvgohjxspykwp5px7q
« Previous Showing results 1 — 15 out of 191 results