Μεταπτυχιακές Διατριβές
Μόνιμο URI για αυτήν τη συλλογήhttps://dspace.library.tuc.gr/handle/123456789/141
Νέα
27
Περιηγούμαι
Πλοήγηση Μεταπτυχιακές Διατριβές ανά Θέμα "Artificial neural networks"
Τώρα δείχνει 1 - 2 από 2
- Αποτελέσματα ανά σελίδα
- Επιλογές ταξινόμησης
Δημοσίευση Development of optimization algorithms for a smart grid community(Technical University of Crete, 2014) Provata Eleni; Προβατα Ελενη; Kolokotsa Dionysia; Κολοκοτσα Διονυσια; Kalaitzakis Konstantinos; Καλαϊτζακης Κωνσταντινος; Karatzas Giorgos; Καρατζας ΓιωργοςThe aim of this work is the development of an optimization model in order to minimize the cost of Leaf Community microgrid. This cost is a sum of energy cost and the maintenance cost of the Energy storage system. The developed objective function is constrained and the problem here is solved by using the method of genetic algorithms at Matlab. The genetic algorithm decides about the transportation of the energy from or to the ESS and it calculates an optimum cost. The optimization time horizon is 24 h ahead, thus the prediction of energy production and consumption was necessary. This was achieved by using neural networks. In order to verify the performance of the developed optimization model, some scenarios were tested evaluated. This study concludes that a management of a microgrid can achieve energy and money savings.Δημοσίευση Long-term prediction of temperature data for the assessment of future trends of the building heating and cooling loads(Technical University of Crete, 2015) Georgatou Christina; Γεωργατου Χριστινα; Kolokotsa Dionysia; Κολοκοτσα Διονυσια; Nikolaidis Nikolaos; Νικολαιδης Νικολαος; Kalaitzakis Kostas; Καλαϊτζακης ΚωσταςThe present work focuses on the long term prediction of temperature data employing neural network models. Primarily, a benchmarking auto regressive model is developed. Then, different neural networks are developed regarding the network type, the training function and the training intervals. Temperature predictions are calculated for ten and for five year intervals. Each model’s results are compared with the corresponding real temperature data, in terms of mean, maximum and minimum temperature values, cooling degree days and frequency distribution. The best predicted temperature data are used as outdoor temperature for the heating and cooling loads calculations of a typical office building. The building simulation model which is used for the energy demand calculations is the open source ESP-r model. The results indicate a relative accurate potential of the neural networks for the simulation of the mean temperature data and prediction of the cooling degree days. Regarding the high temperature values and the maximum peaks, the neural network models are unable to reach precise values, due to the lack of similar training data. As a result, the cooling loads calculated from neural network predictions are underestimated, while the heating loads prediction is more accurate.