Aleksandra Sretenovic

Prediction of a building energy use for heating is very important for adequate energy planning. In this paper the daily district heating use of one university campus was predicted using the support vector machine model. Support vector machine is the artificial intelligence method that has recently proved that it can achieve comparable, or even better prediction results than the much more used artificial neural networks. The proposed model was trained and tested on the real, measured data. The model accuracy was compared with the results of the previously published models (various neural networks and their ensembles) on the same database. The results showed that the support vector machine model can achieve better results than the individual neural networks, but also better than the conventional and multistage ensembles. It is expected that this theoretically well-known methodology finds wider application, especially in prediction tasks.

The study of the building energy demand has become a topic of great importance, because of the significant increase of interest in energy sustainability. University campuses represent specific groups of diverse buildings, with significant energy consumption. They consist of many different buildings, representing small-scale town for itself. Therefore, they provide an excellent testbed to characterize and understand energy consumption of group of „mixed use“ buildings. Suitable building database for University campus NTNU Gloshaugen is created, and available data of heating and electricity energy use are collected and organized. Having correct and reliable data is essential, so data error analysis using statistical methods is performed. Heating energy use was modeled using Matlab statistical toolbox functions. Creating a model of energy use helps in future building planning; it can provide useful information about most probable energy consumption for similar buildings, or predict energy use in different conditions. This assignment is realised as a part of the collaborative project “Sustainable Energy and Environment in Western Balkans” that aims to develop and establish five new internationally recognized MSc study programs for the field of “Sustainable Energy and Environment”, one at each of the five collaborating universities in three different WB countries. The project is funded through the Norwegian Programme in Higher Education, Research and Development in the Western Balkans, Programme 3: Energy Sector (HERD Energy) for the period 2011-2013.

Feedforward neural network models are created for prediction of heating energy consumption of a university campus. Actual measured data are used for training and testing the models. Multistage neural network ensemble is proposed for the possible improvement of prediction accuracy. Previously trained feed-forward neural networks are first separated into clusters, using k-means algorithm, and then the best network of each cluster is chosen as a member of the ensemble. Three different averaging methods (simple, weighted and median) for obtaining ensemble output are applied. Besides this conventional approach, single radial basis neural network in the second level is used to aggregate the selected ensemble members. It is shown that heating energy consumption can be predicted with better accuracy by using ensemble of neural networks than using the best trained single neural network, while the best results are achieved with multistage ensemble.

The feasibility of solar assisted air conditioning in an office building under Tripoli weather conditions is investigated in this paper. A single-effect lithium bromide absorption cycle powered by means of flat-plate solar collectors was modeled in order to predict the potential of the solar energy share. The cooling load profile was generated by using an detailed hourly based program and Typical meteorological year for Tripoli. System performance and solar energy fraction were calculated by varying two major parameters (collector?s slope angle and collector area). The maximum solar fraction of 48% was obtained by means of 1400 m2 of collector surface area. Analysis of results showed that, besides the collector surface area, the main factors affecting the solar fraction were the local weather conditions (intensity of incident solar radiation) and the time of day when the plant was operated.

aUniversity of Belgrade, Faculty of Mechanical Engineering, Belgrade, Serbia bNorwegian University of Science and Technology,Department of Energy and Process Engineering, Trondheim, Norway corresponding author: Aleksandra A. SRETENOVIĆ tel: +381652433379 , mail: asretenovic@mas.bg.ac.rs Currently, in the building sector there is an increase in energy use due to the increased demand for indoor thermal comfort. Proper energy planning based on a real measurement data is a necessity. In this study, we developed and evaluated hybrid artificial intelligence models for the prediction of the daily heating energy use. Building energy use is defined by significant number of influencing factors, while many of them are hard to define and quantify. For heating energy use modelling, complex relationship between the input and output variables is not strictly linear nor non-linear. The main idea of this paper was to divide the heat demand prediction problem into the linear and the non-linear part (...