Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in Buildings
This paper focuses on the development of a multi agent control system (MACS), combined with a stochastic based approach for occupancy estimation. The control framework aims to maintain the comfort levels of a building in high levels and reduce the overall energy consumption. Three independent agents...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/16/4971 |
| _version_ | 1827685331993886720 |
|---|---|
| author | Panagiotis Korkidis Anastasios Dounis Panagiotis Kofinas |
| author_facet | Panagiotis Korkidis Anastasios Dounis Panagiotis Kofinas |
| author_sort | Panagiotis Korkidis |
| collection | DOAJ |
| description | This paper focuses on the development of a multi agent control system (MACS), combined with a stochastic based approach for occupancy estimation. The control framework aims to maintain the comfort levels of a building in high levels and reduce the overall energy consumption. Three independent agents, each dedicated to the thermal comfort, the visual comfort, and the indoor air quality, are deployed. A stochastic model describing the CO<sub>2</sub> concentration has been studied, focused on the occupancy estimation problem. A probabilistic approach, as well as an evolutionary algorithm, are used to provide insights on the stochastic model. Moreover, in order to induce uncertainty, parameters are treated in a fuzzy modelling framework and the results on the occupancy estimation are investigated. In the control framework, to cope with the continuous state-action space, the three agents utilise Fuzzy <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="script">Q</mi></semantics></math></inline-formula>-learning. Simulation results highlight the precision of parameter and occupancy estimation, as well as the high capabilities of the control framework, when taking into account the occupancy state, as energy consumption is reduced by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>55.9</mn><mo>%</mo></mrow></semantics></math></inline-formula>, while the overall comfort index is kept in high levels, with values close to one. |
| first_indexed | 2024-03-10T08:50:20Z |
| format | Article |
| id | doaj.art-0e12499b98f04168a3e1aeec33a3b969 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T08:50:20Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-0e12499b98f04168a3e1aeec33a3b9692023-11-22T07:30:08ZengMDPI AGEnergies1996-10732021-08-011416497110.3390/en14164971Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in BuildingsPanagiotis Korkidis0Anastasios Dounis1Panagiotis Kofinas2Department of Biomedical Engineering, Egaleo Park Campus, University of West Attica, 12243 Athina, GreeceDepartment of Biomedical Engineering, Egaleo Park Campus, University of West Attica, 12243 Athina, GreeceDepartment of Biomedical Engineering, Egaleo Park Campus, University of West Attica, 12243 Athina, GreeceThis paper focuses on the development of a multi agent control system (MACS), combined with a stochastic based approach for occupancy estimation. The control framework aims to maintain the comfort levels of a building in high levels and reduce the overall energy consumption. Three independent agents, each dedicated to the thermal comfort, the visual comfort, and the indoor air quality, are deployed. A stochastic model describing the CO<sub>2</sub> concentration has been studied, focused on the occupancy estimation problem. A probabilistic approach, as well as an evolutionary algorithm, are used to provide insights on the stochastic model. Moreover, in order to induce uncertainty, parameters are treated in a fuzzy modelling framework and the results on the occupancy estimation are investigated. In the control framework, to cope with the continuous state-action space, the three agents utilise Fuzzy <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="script">Q</mi></semantics></math></inline-formula>-learning. Simulation results highlight the precision of parameter and occupancy estimation, as well as the high capabilities of the control framework, when taking into account the occupancy state, as energy consumption is reduced by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>55.9</mn><mo>%</mo></mrow></semantics></math></inline-formula>, while the overall comfort index is kept in high levels, with values close to one.https://www.mdpi.com/1996-1073/14/16/4971stochastic processesfuzzy reinforcement learningmulti agent control systemsoccupancy estimationevolutionary algorithmsbuildings |
| spellingShingle | Panagiotis Korkidis Anastasios Dounis Panagiotis Kofinas Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in Buildings Energies stochastic processes fuzzy reinforcement learning multi agent control systems occupancy estimation evolutionary algorithms buildings |
| title | Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in Buildings |
| title_full | Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in Buildings |
| title_fullStr | Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in Buildings |
| title_full_unstemmed | Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in Buildings |
| title_short | Computational Intelligence Technologies for Occupancy Estimation and Comfort Control in Buildings |
| title_sort | computational intelligence technologies for occupancy estimation and comfort control in buildings |
| topic | stochastic processes fuzzy reinforcement learning multi agent control systems occupancy estimation evolutionary algorithms buildings |
| url | https://www.mdpi.com/1996-1073/14/16/4971 |
| work_keys_str_mv | AT panagiotiskorkidis computationalintelligencetechnologiesforoccupancyestimationandcomfortcontrolinbuildings AT anastasiosdounis computationalintelligencetechnologiesforoccupancyestimationandcomfortcontrolinbuildings AT panagiotiskofinas computationalintelligencetechnologiesforoccupancyestimationandcomfortcontrolinbuildings |