A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in Buildings
The temperature of indoor spaces is at the core of highly relevant topics such as comfort, productivity and health. In conditioned spaces, this temperature is determined by thermostat preferences, but there is a lack of understanding of this phenomenon as a time-dependent magnitude. In addition to t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/14/2363 |
| _version_ | 1797445447751565312 |
|---|---|
| author | Alfonso P. Ramallo-González Aurora González-Vidal Fernando Terroso-Saenz Antonio F. Skarmeta-Gómez |
| author_facet | Alfonso P. Ramallo-González Aurora González-Vidal Fernando Terroso-Saenz Antonio F. Skarmeta-Gómez |
| author_sort | Alfonso P. Ramallo-González |
| collection | DOAJ |
| description | The temperature of indoor spaces is at the core of highly relevant topics such as comfort, productivity and health. In conditioned spaces, this temperature is determined by thermostat preferences, but there is a lack of understanding of this phenomenon as a time-dependent magnitude. In addition to this, there is scientific evidence that the mental models of how users understand the operation of the billions of air-conditioning machines around the world are incorrect, which causes systems to ‘compensate’ for temperatures outside by adjusting the thermostat, which leads to erratic changes on set-points over the day. This paper presents the first model of set-point temperature as a time-dependent variable. Additionally, a new mathematical algorithm was developed to complement these models and make possible their identification on the go, called the life Bayesian inference of transition matrices. Data from a total of 75 + 35 real thermostats in two buildings for more than a year were used to validate the model. The method was shown to be highly accurate, fast, and computationally trivial in terms of time and memory, representing a change in the paradigm for smart thermostats. |
| first_indexed | 2024-03-09T13:25:58Z |
| format | Article |
| id | doaj.art-14d4941a220d4ee7ada3939ae9be42d8 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T13:25:58Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-14d4941a220d4ee7ada3939ae9be42d82023-11-30T21:23:09ZengMDPI AGMathematics2227-73902022-07-011014236310.3390/math10142363A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in BuildingsAlfonso P. Ramallo-González0Aurora González-Vidal1Fernando Terroso-Saenz2Antonio F. Skarmeta-Gómez3Faculty of Computer Science, Campus de Espinardo, Universidad de Murcia, 30100 Murcia, SpainFaculty of Computer Science, Campus de Espinardo, Universidad de Murcia, 30100 Murcia, SpainFacultad de Informática, Campus de Los Jerónimos, Universidad Católica de San Antonio de Murcia UCAM, Guadalupe, 30107 Murcia, SpainFaculty of Computer Science, Campus de Espinardo, Universidad de Murcia, 30100 Murcia, SpainThe temperature of indoor spaces is at the core of highly relevant topics such as comfort, productivity and health. In conditioned spaces, this temperature is determined by thermostat preferences, but there is a lack of understanding of this phenomenon as a time-dependent magnitude. In addition to this, there is scientific evidence that the mental models of how users understand the operation of the billions of air-conditioning machines around the world are incorrect, which causes systems to ‘compensate’ for temperatures outside by adjusting the thermostat, which leads to erratic changes on set-points over the day. This paper presents the first model of set-point temperature as a time-dependent variable. Additionally, a new mathematical algorithm was developed to complement these models and make possible their identification on the go, called the life Bayesian inference of transition matrices. Data from a total of 75 + 35 real thermostats in two buildings for more than a year were used to validate the model. The method was shown to be highly accurate, fast, and computationally trivial in terms of time and memory, representing a change in the paradigm for smart thermostats.https://www.mdpi.com/2227-7390/10/14/2363thermostatIoTcomfortenvironment |
| spellingShingle | Alfonso P. Ramallo-González Aurora González-Vidal Fernando Terroso-Saenz Antonio F. Skarmeta-Gómez A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in Buildings Mathematics thermostat IoT comfort environment |
| title | A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in Buildings |
| title_full | A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in Buildings |
| title_fullStr | A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in Buildings |
| title_full_unstemmed | A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in Buildings |
| title_short | A Novel Learning Algorithm Based on Bayesian Statistics: Modelling Thermostat Adjustments for Heating and Cooling in Buildings |
| title_sort | novel learning algorithm based on bayesian statistics modelling thermostat adjustments for heating and cooling in buildings |
| topic | thermostat IoT comfort environment |
| url | https://www.mdpi.com/2227-7390/10/14/2363 |
| work_keys_str_mv | AT alfonsopramallogonzalez anovellearningalgorithmbasedonbayesianstatisticsmodellingthermostatadjustmentsforheatingandcoolinginbuildings AT auroragonzalezvidal anovellearningalgorithmbasedonbayesianstatisticsmodellingthermostatadjustmentsforheatingandcoolinginbuildings AT fernandoterrososaenz anovellearningalgorithmbasedonbayesianstatisticsmodellingthermostatadjustmentsforheatingandcoolinginbuildings AT antoniofskarmetagomez anovellearningalgorithmbasedonbayesianstatisticsmodellingthermostatadjustmentsforheatingandcoolinginbuildings AT alfonsopramallogonzalez novellearningalgorithmbasedonbayesianstatisticsmodellingthermostatadjustmentsforheatingandcoolinginbuildings AT auroragonzalezvidal novellearningalgorithmbasedonbayesianstatisticsmodellingthermostatadjustmentsforheatingandcoolinginbuildings AT fernandoterrososaenz novellearningalgorithmbasedonbayesianstatisticsmodellingthermostatadjustmentsforheatingandcoolinginbuildings AT antoniofskarmetagomez novellearningalgorithmbasedonbayesianstatisticsmodellingthermostatadjustmentsforheatingandcoolinginbuildings |