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.
nema
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.
Traditional Vojvodina house represents an important part of the building stock of the northern Serbian province of Vojvodina. The research examines the thermal transmittance of the walls of rammed ...earth, which is the basic structural and fa?ade element of traditional Vojvodina house, in two ways: by calculations in accordance with Serbian regulations and by measuring in situ. Parameters obtained from the measurements are compared with the calculated values for the three typical traditional Vojvodina rammed earth single family residential houses. The comparison between the values of the heat transfer coefficient, obtained by the calculation, and the results determined by in situ measurements show significant differences. It indicates that the thermal characteristics are better than calculated ones according to national regulations, but at the same time that, due to the complexity of the rammed earth walls and differences in the rammed earth structures, the results differ from case to case and can not be standardized.
nema
The conducted research examines the thermal behaviour of the rammed earth walls, which is the basic structural and fa?ade element of traditional Vojvodina house. The traditional rammed earth house ...represents an important part of the total building stock of Vojvodina. Earth is a locally available, cheap, natural, environmentally friendly building material and has been used extensively for traditional family houses in Vojvodina. It has ecological and ?green? characteristics, which can be assessed as very high quality, and they are of significant importance in the context of sustainable development and striving to reduce energy consumption today. The research examines thermal behaviour of rammed earth wall, including theoretical analysis of: the heat transfer coefficient, U, the thermal resistance, R, and thermal conductivity, ?. One of the basic elements of thermal behaviour, the thermal mass, has been analyzed both theoretically and by measuring in situ. The in situ measurements were conducted on the traditional house in Vojvodina by measuring inside and outside surface wall and air temperature in summer. Analyses of rammed earth wall thermal performances have shown that the wall has low thermal conductivity, high heat capacity and significant thermal mass effect which is the key element enabling thermal stability. The research indicates rather good thermal properties of the rammed earth walls. Potential of rammed earth wall in Vojvodina should be an issue of further analysis, although the possibility of improvement of existing facilities to meet current standards in terms of energy efficiency should be considered.
nema
Global discussion on climate change and strengthening environmental protection has been launched, especially in the last three decades. As climate change is a result of greenhouse gas emissions, ...different mechanisms were introduced in order to reduce this impact, surely the most significant was set by the Kyoto Protocol. The Republic of Serbia considers a proper policy on environmental protection as one of its priorities. As the switch from traditional to renewable energy sources carries valuable improvements in environmental protection and economic efficacy, the Government encourages the use of renewable energy sources for the production of energy. This paper provides analysis of the potential of renewable energy sources in the Republic of Serbia, carbon potential and their possible role in mitigation of climate changes. Results presented in the paper can be useful for the improvement of the strategic planning on the national level with the final aim to contribute to the increase in importance of use of renewable energy sources in that planning.
•Three networks, FFNN, RBFN and ANFIS, were used for heating consumption prediction.•Ensemble of neural networks is proposed using three types of output combination.•Three different models using ...different number of input variables are analyzed.•Better prediction results are achieved using ensemble comparing to single network.
For prediction of heating energy consumption of a university campus, various artificial neural networks are used: feed forward backpropagation neural network (FFNN), radial basis function network (RBFN) and adaptive neuro-fuzzy interference system (ANFIS). Actual measured data are used for training and testing the models. For each neural networks type, three models (using different number of input parameters) are analyzed. In order to improve prediction accuracy, ensemble of neural networks is examined. Three different combinations of output are analyzed. It is shown that all proposed neural networks can predict heating consumption with great accuracy, and that using ensemble achieves even better results.
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.
The aim of this study was to compare major biochemical properties of nutria meat with relevant composition and texture data of rabbit carcasses. The meat from nutria m. semimembranosus (MS; thigh ...muscle) contained 29.54% dry matter (DM), 20.05% total protein (TP), 7.83% total fat (TF) and 1.23% total ash (TA). The ratio of polyunsaturated fatty acids (PUFA) to saturated fatty acids (SFA) was lower in nutria than in rabbit meat (0.55-0.58 and 0.93-0.94, respectively). The n-6/n-3 PUFA ratio was 15.3 (MS) and 11.22 (m. longissimus dorsi, MLD; loin) in nutria meat and 7.55 and 8.08 respectively in rabbit meat, which appeared more beneficial for the consumer. Among the most important texture parameters, hardness ranged from 66 for MS to 73 N for MLD, and overall chewiness was 23 N. The collagen content was between 0.68 and 0.72%. The results show that in comparison with rabbit meat, nutria meat has valuable properties and is recommended for the human diet.
Celem badań było porównanie wskaźników biochemicznych mięsa nutrii i królików. Mięso nutrii charakteryzowało się wyższą zawartością tłuszczu (od 3,12% m. longissimus dorsi do 7,83% m. semimembranosus) w porównaniu z mięsem króliczym (odpowiednio 0,7 i 1,41%). Stosunek wielonienasyconych do nasyconych kwasów tłuszczowych w mięsie nutrii wynosił 0,55-0,58, natomiast w mięsie króliczym 0,93-0,94. Stosunek wielonienasyconych kwasów tłuszczowych n-6/n-3 w mięsie nutrii był mniej korzystny dla konsumenta i wynosił 15,3 (m. semimembranosus) i 11,22 (m. longissimus dorsi) w porównaniu z mięsem króliczym (odpowiednio 7,55 i 8,08). Mięso nutrii w porównaniu do mięsa króliczego charakteryzowało się mniejszą zawartością białka oraz większą zawartością kolagenu. Wyższa zawartość kolagenu spowodowała, że mięso nutrii było twardsze i wymagało większej siły cięcia. Jednocześnie mięso nutrii było ciemniejsze (L* od 31,72 do 34,56) w porównaniu z mięsem króliczym (L* od 46,39 do 48,88). Mięśnie nutrii charakteryzują się wyższym wskaźnikiem pH w porównaniu z mięśniami królików i różnią się przebiegiem stężenia pośmiertnego rigor mortis. Najniższą wartość pH w mięśniach nutrii stwierdzono w 10. godzinie po uboju, natomiast w mięśniach królików już w 5. godzinie po uboju. Wysokie pH mięsa nutriowego może sprzyjać szybszemu psuciu się tego mięsa. Dobre parametry mięsa nutriowego wskazują, że jest to mięso delikatne, nadające się zarówno do przetwórstwa (produkcja kiełbas i pasztetów), jak i jako mięso kulinarne do pieczenia i smażenia. Może być mięsem alternatywnym dla innych gatunków, co pozwoli zachować nutrie jako gatunek hodowlany i zwierzęta rzeźne w polskiej hodowli.
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 difficult to adequately quantify. For heating energy use modelling, the complex relationship between the input and output variables is hard to define. The main idea of this paper was to divide the heat demand prediction problem into the linear and the non-linear part (residuals) by using different statistical methods for the prediction. The expectations were that the joint hybrid model, could outperform the individual predictors. Multiple linear regression was selected for the linear modelling, while the non-linear part was predicted using feedforward and radial basis neural networks. The hybrid model prediction consisted of the sum of the outputs of the linear and the non-linear model. The results showed that both hybrid models achieved better results than each of the individual feedforward and radial basis neural networks and multiple linear regression on the same dataset. It was shown that this hybrid approach improved the accuracy of artificial intelligence models.