A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Forecasting office indoor CO2 concentration using machine learning with a one-year dataset
https://orcid.org/0000-0002-7408-170X
https://orcid.org/0000-0002-6248-152X
Abstract Modern buildings are expected to fulfill energy efficiency regulations while providing a healthy and comfortable living environment for their occupants. Demand-controlled heating, ventilation, and air conditioning can improve energy efficiency and well-being, especially if changes in indoor environmental factors can be forecast reliably enough. As a first step, this study afforded a baseline for CO2 forecasting evaluation by providing for the public use a comprehensive dataset covering a full year. Secondly, we studied the applicability of four machine learning methods, Ridge regression, Decision Tree, Random Forest, and Multilayer Perceptron, for modeling the future concentration of CO2 in indoors. We evaluated their prediction accuracy within different forecasting and history window time frames and the impact of multiple sensor modalities. All models performed better than the baseline method of predicting the last observed value, and the Decision Tree was found to be almost as accurate as the computationally heavier Random Forest model. When the future forecasting window was longer than a minute, the optimal sensor modalities included occupant activity data from passive infrared sensors in addition to CO2 concentration. Our findings suggest that machine learning can be applied in multimodal time-series data to find a simple, accurate, and resource-efficient forecasting model for proactive control of indoor environments.
Highlights A lightweight sensor-based machine-learning approach for proactive ventilation control. Occupant activity data and CO2 provided the best result for longer future predictions. Decision Tree selected as the most lightweight, robust, and viable model. One-year indoor environment dataset available online. Potential for rapid deployment in HVAC applications.
Forecasting office indoor CO2 concentration using machine learning with a one-year dataset
https://orcid.org/0000-0002-7408-170X
https://orcid.org/0000-0002-6248-152X
Abstract Modern buildings are expected to fulfill energy efficiency regulations while providing a healthy and comfortable living environment for their occupants. Demand-controlled heating, ventilation, and air conditioning can improve energy efficiency and well-being, especially if changes in indoor environmental factors can be forecast reliably enough. As a first step, this study afforded a baseline for CO2 forecasting evaluation by providing for the public use a comprehensive dataset covering a full year. Secondly, we studied the applicability of four machine learning methods, Ridge regression, Decision Tree, Random Forest, and Multilayer Perceptron, for modeling the future concentration of CO2 in indoors. We evaluated their prediction accuracy within different forecasting and history window time frames and the impact of multiple sensor modalities. All models performed better than the baseline method of predicting the last observed value, and the Decision Tree was found to be almost as accurate as the computationally heavier Random Forest model. When the future forecasting window was longer than a minute, the optimal sensor modalities included occupant activity data from passive infrared sensors in addition to CO2 concentration. Our findings suggest that machine learning can be applied in multimodal time-series data to find a simple, accurate, and resource-efficient forecasting model for proactive control of indoor environments.
Highlights A lightweight sensor-based machine-learning approach for proactive ventilation control. Occupant activity data and CO2 provided the best result for longer future predictions. Decision Tree selected as the most lightweight, robust, and viable model. One-year indoor environment dataset available online. Potential for rapid deployment in HVAC applications.
Forecasting office indoor CO2 concentration using machine learning with a one-year dataset
https://orcid.org/0000-0002-7408-170X
https://orcid.org/0000-0002-6248-152X
Abstract Modern buildings are expected to fulfill energy efficiency regulations while providing a healthy and comfortable living environment for their occupants. Demand-controlled heating, ventilation, and air conditioning can improve energy efficiency and well-being, especially if changes in indoor environmental factors can be forecast reliably enough. As a first step, this study afforded a baseline for CO2 forecasting evaluation by providing for the public use a comprehensive dataset covering a full year. Secondly, we studied the applicability of four machine learning methods, Ridge regression, Decision Tree, Random Forest, and Multilayer Perceptron, for modeling the future concentration of CO2 in indoors. We evaluated their prediction accuracy within different forecasting and history window time frames and the impact of multiple sensor modalities. All models performed better than the baseline method of predicting the last observed value, and the Decision Tree was found to be almost as accurate as the computationally heavier Random Forest model. When the future forecasting window was longer than a minute, the optimal sensor modalities included occupant activity data from passive infrared sensors in addition to CO2 concentration. Our findings suggest that machine learning can be applied in multimodal time-series data to find a simple, accurate, and resource-efficient forecasting model for proactive control of indoor environments.
Highlights A lightweight sensor-based machine-learning approach for proactive ventilation control. Occupant activity data and CO2 provided the best result for longer future predictions. Decision Tree selected as the most lightweight, robust, and viable model. One-year indoor environment dataset available online. Potential for rapid deployment in HVAC applications.
Forecasting office indoor CO2 concentration using machine learning with a one-year dataset
Kallio, Johanna (author) / Tervonen, Jaakko (author) / Räsänen, Pauli (author) / Mäkynen, Riku (author) / Koivusaari, Jani (author) / Peltola, Johannes (author)
Building and Environment ; 187
2020-10-25
Article (Journal)
Electronic Resource
English
Carbon dioxide , Modeling , Indoor air quality , Environmental sensor data , Energy efficiency , Well-being , architecture, engineering, and construction industry , (AEC) , artificial neural network , (ANN) , decision tree , (DT) , heating, ventilation, and air conditioning , (HVAC) , indoor air quality , (IAQ) , indoor environmental quality , (IEQ) , last-observation-carried-forward , (LOCF) , multilayer perceptron , (MLP) , random forest , (RF)
| DataCite | 2024
| DataCite | 2024
| DataCite | 2024
Dynamic forecasting model for indoor pollutant concentration using recurrent neural network
| SAGE Publications | 2021