A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Heating setpoint recommendation strategy for thermal comfort and energy consumption optimization
https://orcid.org/0000-0003-0536-0163
https://orcid.org/0000-0002-6424-6590
https://orcid.org/0000-0002-9985-2806
Abstract Residential Heating, Ventilation, and Air Conditioning (HVAC) systems are progressing towards smarter climate control solutions, centered on the user needs and the system's energetic performance. This work introduces a strategy to assist households select more energy-conscious HVAC setpoints without compromising their comfort level. To do so, it explores the adaptive comfort theory for homes combined with predictive indoor temperature models to define an adaptable strategy for optimized indoor temperature setpoints. Using smart thermostat data from European households, energy savings up to 5.2% were estimated from adopting the new thermostat setpoint schedules in several test cases for the heating season. The proposed methodology is independent of direct information about building construction or personal information, which is often unfeasible to measure and collect in real installations. The solution complexity was taken into account, looking for its application in smart thermostat devices with constrained computational capabilities. The Multi-Layer Perceptron (MLP) predictive models achieved performances with Mean Squared Errors (MSEs) lower than 0.06. The same were used to evaluate the setpoints' impact on the indoor temperature, with simulation errors lower than 1.1 ∘C.
Heating setpoint recommendation strategy for thermal comfort and energy consumption optimization
https://orcid.org/0000-0003-0536-0163
https://orcid.org/0000-0002-6424-6590
https://orcid.org/0000-0002-9985-2806
Abstract Residential Heating, Ventilation, and Air Conditioning (HVAC) systems are progressing towards smarter climate control solutions, centered on the user needs and the system's energetic performance. This work introduces a strategy to assist households select more energy-conscious HVAC setpoints without compromising their comfort level. To do so, it explores the adaptive comfort theory for homes combined with predictive indoor temperature models to define an adaptable strategy for optimized indoor temperature setpoints. Using smart thermostat data from European households, energy savings up to 5.2% were estimated from adopting the new thermostat setpoint schedules in several test cases for the heating season. The proposed methodology is independent of direct information about building construction or personal information, which is often unfeasible to measure and collect in real installations. The solution complexity was taken into account, looking for its application in smart thermostat devices with constrained computational capabilities. The Multi-Layer Perceptron (MLP) predictive models achieved performances with Mean Squared Errors (MSEs) lower than 0.06. The same were used to evaluate the setpoints' impact on the indoor temperature, with simulation errors lower than 1.1 ∘C.
Heating setpoint recommendation strategy for thermal comfort and energy consumption optimization
https://orcid.org/0000-0003-0536-0163
https://orcid.org/0000-0002-6424-6590
https://orcid.org/0000-0002-9985-2806
Abstract Residential Heating, Ventilation, and Air Conditioning (HVAC) systems are progressing towards smarter climate control solutions, centered on the user needs and the system's energetic performance. This work introduces a strategy to assist households select more energy-conscious HVAC setpoints without compromising their comfort level. To do so, it explores the adaptive comfort theory for homes combined with predictive indoor temperature models to define an adaptable strategy for optimized indoor temperature setpoints. Using smart thermostat data from European households, energy savings up to 5.2% were estimated from adopting the new thermostat setpoint schedules in several test cases for the heating season. The proposed methodology is independent of direct information about building construction or personal information, which is often unfeasible to measure and collect in real installations. The solution complexity was taken into account, looking for its application in smart thermostat devices with constrained computational capabilities. The Multi-Layer Perceptron (MLP) predictive models achieved performances with Mean Squared Errors (MSEs) lower than 0.06. The same were used to evaluate the setpoints' impact on the indoor temperature, with simulation errors lower than 1.1 ∘C.
Heating setpoint recommendation strategy for thermal comfort and energy consumption optimization
Almeida, Rodrigo (author) / Georgieva, Petia (author) / Martins, Nelson (author)
Energy and Buildings ; 296
2023-07-25
Article (Journal)
Electronic Resource
English
Energy, heating and thermal comfort
| TIBKAT | 1978
Analysis of Thermal Comfort and Space Heating Strategy
| Springer Verlag | 2013
Ventilation Control Strategy Using the Supply CO2 Concentration Setpoint
| Taylor & Francis Verlag | 2005