Abstract: Continuous measurements and multivariate methods are applied in researching the effects of energy consumption on indoor air quality (IAQ) in a Finnish one-family house. Measured data used in this study was collected continuously in a house in Kuopio, Eastern Finland, during fourteen months long period. Consumption parameters measured were the consumptions of district heat, electricity and water. Indoor parameters gathered were temperature, relative humidity (RH), the concentrations of carbon dioxide (CO2) and carbon monoxide (CO) and differential air pressure. In this study, self-organizing map (SOM) and Sammon's mapping were applied to resolve the effects of energy consumption on indoor air quality. Namely, the SOM was qualified as a suitable method having a property to summarize the multivariable dependencies into easily observable two-dimensional map. Accompanying that, the Sammon's mapping method was used to cluster pre-processed data to find similarities of the variables, expressing distances and groups in the data. The methods used were able to distinguish 7 different clusters characterizing indoor air quality and energy efficiency in the study house. The results indicate, that the cost implications in euros of heating and electricity energy vary according to the differential pressure, concentration of carbon dioxide, temperature and season.
Abstract: The use of neural networks is popular in various
building applications such as prediction of heating load, ventilation
rate and indoor temperature. Significant is, that only few papers deal
with indoor carbon dioxide (CO2) prediction which is a very good
indicator of indoor air quality (IAQ). In this study, a data-driven
modelling method based on multilayer perceptron network for indoor
air carbon dioxide in an apartment building is developed.
Temperature and humidity measurements are used as input variables
to the network. Motivation for this study derives from the following
issues. First, measuring carbon dioxide is expensive and sensors
power consumptions is high and secondly, this leads to short
operating times of battery-powered sensors. The results show that
predicting CO2 concentration based on relative humidity and
temperature measurements, is difficult. Therefore, more additional
information is needed.
Abstract: The building sector is the largest energy consumer and
CO2 emitter in the European Union (EU) and therefore the active
reduction of energy consumption and elimination of energy wastage
are among the main goals in it. Healthy housing and energy
efficiency are affected by many factors which set challenges to
monitoring, control and research of indoor air quality (IAQ) and
energy consumption, especially in old buildings. These challenges
include measurement and equipment costs, for example.
Additionally, the measurement results are difficult to interpret and
their usage in the ventilation control is also limited when taking into
account the energy efficiency of housing at the same time. The main
goal of this study is to develop a cost-effective building monitoring
and control system especially for old buildings. The starting point or
keyword of the development process is a wireless system; otherwise
the installation costs become too high. As the main result, this paper
describes an idea of a wireless building monitoring and control
system. The first prototype of the system has been installed in 10
residential buildings and in 10 school buildings located in the City of
Kuopio, Finland.