A problem that exhibition halls have is the balance between having good indoor air quality andminimizing energy waste due to the naturally slow decrease of CO2 concentration, which causes Heat-ing, Ventilation and Air-Conditioning systems to keep ventilating empty halls when occupants have leftthe vicinity. Several studies have been made on the topic of CO2 prediction and occupancy predictionbased on CO2 for smaller spaces such as offices and schools. However, few studies have been madefor bigger venues where a larger group of people gather. An online machine learning model using theRiver library was developed to tackle this problem by predicting the CO2 ahead of time. Five datasetswere used for training and predicting, three with real data and two with simulated data. The resultsfrom this model was compared with three already developed traditional models in order to evaluate theperformance of an online machine learning model compared to traditional models. The online machinelearning model was successful in predicting CO2 one hour ahead of time considerably faster than thetraditional models, achieving a r2 score of up to 0.95.

It is a dilemma problem to achieve both these two goals: a) to maintain a best indoor air quality and b) to use a most efficient energy for a house at the same time. One of the outstanding components involving these goals is a smart ventilation system in the house. Smart ventilation strategies, including demand-controlled ventilation (DCV), have been of great interests and some studies believe that DCV strategies have the potential for energy reductions for all ventilation systems. This research aims to improve smart ventilation system, in aspects of energy consumption, indoor CO2 concentrations and living comfortness, by analyzing long-term sensor data. Based on a case study on an experimental house -- Dalarnas Villa, this research investigates how the current two ventilations modes work in the house and improves its ventilation system by developing customized ventilation schedules. A variety of data analysis methods were used in this research. Clustering analysis is used to identify the CO2 patterns and hence determine the residents living patterns; correlation analysis and regression analysis are used to quantify a model to estimate fan energy consumption; a mathematical model is built to simulation the CO2 decreasing when the house is under 0 occupancy. And finally, two customized schedules are created for a typical workday and holiday, respectively, which show advantages in all aspects of energy consumption, CO2 concentrations and living comfortness, compared with the current ventilation modes.