User comfort and energy efficiency in HVAC systems by Q-learning

Date

2018-05-05

Author

Ulusoy, İlkay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

158
views

0
downloads

This study focuses on applying Q-learning techniques for an HVAC agent where the agent learns to find the optimal sequence of ventilator rate variations to satisfy user comfort and energy efficiency simultaneously. On-Off and Setpoint control methods are investigated besides the proposed control method under different occupant number. The results show the advantage of the proposed Q-learning method to keep the Indoor Air Quality (IAQ), i.e., the indoor CO2 concentration, at the desired level while operating the HVAC efficiently.

Subject Keywords

Reinforcement Learning (RL) , Q-Learning , HVAC , Ventilation System , Comfort And Energy Efficiency

URI

https://hdl.handle.net/11511/48730

DOI

https://doi.org/10.1109/siu.2018.8404287

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Exergetic optimization of generated electric power split in a heat pump coupled poly-generation system Kilkis, Birol I.; Kılkış, Şiir (2007-01-01) This study analyzes environmental, energy, and economical benefits of a ground source heat pump, coupled poly-generation system by incorporating exergy into the energy efficiency analysis. Two additional terms, namely the rational exergy efficiency and the coefficient of performance were introduced to the primary energy savings equation in the European Union Directive 2004/8/EC. Based on the new equation, an optimization algorithm was developed, which can quantify the environmental, energy and economy benef...
VISUAL FIELD TESTING USING FORECASTING AND VIRTUAL REALITY Bülbül, Emre; Akar, Gözde; Department of Electrical and Electronics Engineering (2022-2) The standard method for assessing a patient’s visual field is visual field testing. Many diseases, including glaucoma, which affects more than 80 million people, require visual field testing for monitoring and diagnosis. The testing is done by sending light to fixed locations with different luminosities while the patient is fixating at a certain point, then the sensitivities to light at each location are determined by recording the responses of the patient to seen stimuli. Because of their form and digital ...
Computer aided noise prediction in heating, ventilating and air conditioning systems Güngör, Faruk Emre; Çalışkan, Mehmet; Department of Mechanical Engineering (2003) This thesis aims at preparing a user-friendly software tool for the prediction and analysis of the noise generated in Heating, Ventilating and Air Conditioning (HVAC) Systems elaborating the standardized prediction formulae and data coming from the research studies. For the analysis portion of the software, different types of indoor noise criteria are introduced and implemented in the software to ease the investigation of the level and the quality of the sound perceived by the occupant in a room through suc...
Joint and interactive effects of trust and (inter) dependence on relational behaviors in long-term channel dyads Yilmaz, C; Sezen, B; Özdemir, Özlem (Elsevier BV, 2005-04-01) The authors investigate the effects of trust on the relational behaviors of firms in long-term channel dyads across different interdependence structures. Based on the long-term nature of the empirical setting, trust is posited to exert a positive effect on the emergence of relational behaviors in all interdependence conditions. This positive effect of trust is hypothesized to be stronger in highly and symmetrically interdependent channel dyads than in low-interdependence-type symmetric dyads. In addition, f...
Multi-time-scale input approaches for hourly-scale rainfall-runoff modeling based on recurrent neural networks Ishida, Kei; Kiyama, Masato; Ercan, Ali; Amagasaki, Motoki; Tu, Tongbi (2021-11-01) This study proposes two effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input time-series data to RNN in parallel. The other concatenates the coarse and fine temporal resolutions of the input time-series data over time before considering them as the input to RNN. In both approaches, first, ...

Citation Formats

İ. Ulusoy, “User comfort and energy efficiency in HVAC systems by Q-learning,” 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/48730.